baram2584/ResearchProject
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

initial commit FESurrogateModelTutorial

Browse Source
This commit is contained in:
김경종
2026-05-21 17:03:51 +09:00
parent 93665d9ee6
commit 43b86669fa
122 changed files with 7929 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
FESurrogateModelTutorial/.agents/skills/harness-review/SKILL.md
+42
View File
@@ -0,0 +1,42 @@
---
name: harness-review
description: "Use when reviewing this Harness repository: local changes, generated phase files, step outputs, implementation diffs, missing tests, build readiness, or compliance with AGENTS.md, docs/ARCHITECTURE.md, docs/ADR.md, and Harness acceptance criteria."
---
# Harness Review
## Overview
Use this skill to review Harness work against the repository's persistent rules, architecture docs, and executable verification requirements. Prioritize bugs, regressions, missing tests, and rule violations.
## Review Process
1. Read `/AGENTS.md`, `/docs/ARCHITECTURE.md`, and `/docs/ADR.md`.
2. Inspect the changed files with `git status --short` and `git diff`.
3. Check architecture, stack choices, tests, critical rules, and build readiness.
4. Run relevant verification commands when feasible. If a command cannot be run, report that as residual risk.
5. Lead with actionable findings. Keep summaries secondary.
## Checklist
| Item | Question |
| --- | --- |
| Architecture | Does the change follow `docs/ARCHITECTURE.md` directory and module boundaries? |
| Stack | Does the change stay within choices documented in `docs/ADR.md`? |
| Tests | Are new or changed behaviors covered by tests? |
| Critical Rules | Does the change violate any `AGENTS.md` CRITICAL rule? |
| Build | Do relevant build/test/lint commands pass? |
## Output Format
If there are findings, list them first in severity order with file and line references when possible. Then include this table:
| 항목 | 결과 | 비고 |
| --- | --- | --- |
| 아키텍처 준수 | PASS/FAIL | {상세} |
| 기술 스택 준수 | PASS/FAIL | {상세} |
| 테스트 존재 | PASS/FAIL | {상세} |
| CRITICAL 규칙 | PASS/FAIL | {상세} |
| 빌드 가능 | PASS/FAIL | {상세} |
When there are no findings, say that clearly, then mention any commands not run or remaining risk.
FESurrogateModelTutorial/.agents/skills/harness-review/agents/openai.yaml
+4
View File
@@ -0,0 +1,4 @@
interface:
display_name: "Harness Review"
short_description: "Review Harness changes safely"
default_prompt: "Use $harness-review to review Harness repository changes."
FESurrogateModelTutorial/.agents/skills/harness-workflow/SKILL.md
+124
View File
@@ -0,0 +1,124 @@
---
name: harness-workflow
description: "Use when planning or running this Harness framework: reading AGENTS.md and docs/*.md, discussing implementation scope, creating or updating phases/index.json, phases/{task}/index.json, phases/{task}/stepN.md, or invoking scripts/execute.py for staged Codex execution."
---
# Harness Workflow
## Overview
Use this skill to turn a user-approved task into small, self-contained Harness steps that another Codex session can execute reliably. Keep the workflow grounded in repository docs and executable acceptance criteria.
## Workflow
1. Read `AGENTS.md` and relevant files under `docs/`, especially `docs/PRD.md`, `docs/ARCHITECTURE.md`, and `docs/ADR.md`.
2. Discuss unresolved product or technical decisions with the user before writing phase files.
3. When the user asks for an implementation plan, draft steps and get approval before creating files.
4. Create or update `phases/index.json`, `phases/{task-name}/index.json`, and one `phases/{task-name}/stepN.md` per step.
5. Run the phase with `python scripts/execute.py {task-name}` when asked to execute it. Use `--push` only when the user asks to push.
## Step Design Rules
- Scope each step to one layer or module. Split steps when multiple modules would otherwise change together.
- Make every step self-contained. Do not rely on prior conversation; include all required context and file paths.
- Force context gathering. Each step must tell Codex which docs and previous outputs to read before editing.
- Specify interfaces and signatures, not full implementations, unless exact code is required for a constraint.
- Put core invariants directly in the step: idempotency, security, data integrity, API contracts, or other non-negotiables.
- Use executable acceptance criteria such as `npm run build && npm test`, not abstract statements.
- Write cautions concretely: "Do not do X. Reason: Y."
- Name steps with kebab-case slugs such as `project-setup`, `api-layer`, or `auth-flow`.
## Phase Files
Create or update `phases/index.json`:
```json
{
"phases": [
{
"dir": "0-mvp",
"status": "pending"
}
]
}
```
Create `phases/{task-name}/index.json`:
```json
{
"project": "<project-name>",
"phase": "<task-name>",
"steps": [
{ "step": 0, "name": "project-setup", "status": "pending" },
{ "step": 1, "name": "core-types", "status": "pending" },
{ "step": 2, "name": "api-layer", "status": "pending" }
]
}
```
Rules:
- `project` comes from `AGENTS.md`.
- `phase` matches the task directory name.
- `steps[].step` starts at `0`.
- Initial status is always `pending`.
- Do not add timestamps when creating files. `scripts/execute.py` records `created_at`, `started_at`, `completed_at`, `failed_at`, and `blocked_at`.
## Step Template
```markdown
# Step {N}: {name}
## 읽어야 할 파일
먼저 아래 파일들을 읽고 프로젝트의 아키텍처와 설계 의도를 파악하라:
- `/AGENTS.md`
- `/docs/ARCHITECTURE.md`
- `/docs/ADR.md`
- {previously created or modified files}
이전 step에서 만들어진 코드를 꼼꼼히 읽고, 설계 의도를 이해한 뒤 작업하라.
## 작업
{Concrete instructions with file paths, interfaces, signatures, and rules.}
## Acceptance Criteria
```bash
npm run build
npm test
```
## 검증 절차
1. 위 AC 커맨드를 실행한다.
2. 아키텍처 체크리스트를 확인한다:
- ARCHITECTURE.md 디렉토리 구조를 따르는가?
- ADR 기술 스택을 벗어나지 않았는가?
- AGENTS.md CRITICAL 규칙을 위반하지 않았는가?
3. 결과에 따라 `phases/{task-name}/index.json`의 해당 step을 업데이트한다:
- 성공: `"status": "completed"`, `"summary": "산출물 한 줄 요약"`
- 3회 수정 시도 후 실패: `"status": "error"`, `"error_message": "구체적 에러 내용"`
- 사용자 개입 필요: `"status": "blocked"`, `"blocked_reason": "구체적 사유"` 후 중단
## 금지사항
- {Do not do X. Reason: Y.}
- 기존 테스트를 깨뜨리지 마라.
```
## Execution And Recovery
Run:
```bash
python scripts/execute.py {task-name}
python scripts/execute.py {task-name} --push
```
`scripts/execute.py` creates or checks out `feat-{task-name}`, injects `AGENTS.md` and `docs/*.md` into each prompt, carries completed step summaries forward, retries failed steps up to three times, separates code and metadata commits, and records timestamps.
If a step is `error`, set it back to `pending` and remove `error_message` after fixing the cause. If a step is `blocked`, resolve `blocked_reason`, set it back to `pending`, remove `blocked_reason`, and rerun.
FESurrogateModelTutorial/.agents/skills/harness-workflow/agents/openai.yaml
+4
View File
@@ -0,0 +1,4 @@
interface:
display_name: "Harness Workflow"
short_description: "Plan staged Harness workflow steps"
default_prompt: "Use $harness-workflow to plan Harness phases and step files."
FESurrogateModelTutorial/.codex/config.toml
+4
View File
@@ -0,0 +1,4 @@
#:schema https://developers.openai.com/codex/config-schema.json
[features]
codex_hooks = true
FESurrogateModelTutorial/.codex/hooks.json
+28
View File
@@ -0,0 +1,28 @@
{
"hooks": {
"PreToolUse": [
{
"matcher": "^Bash$",
"hooks": [
{
"type": "command",
"command": "python -c \"import pathlib, runpy, subprocess; root = pathlib.Path(subprocess.check_output(['git', 'rev-parse', '--show-toplevel'], text=True).strip()); runpy.run_path(str(root / '.codex' / 'hooks' / 'pre_commit_checks.py'), run_name='__main__')\"",
"timeout": 600,
"statusMessage": "Running pre-commit checks"
}
]
},
{
"matcher": "^(apply_patch|Edit|Write)$",
"hooks": [
{
"type": "command",
"command": "python -c \"import pathlib, runpy, subprocess; root = pathlib.Path(subprocess.check_output(['git', 'rev-parse', '--show-toplevel'], text=True).strip()); runpy.run_path(str(root / '.codex' / 'hooks' / 'tdd-guard.py'), run_name='__main__')\"",
"timeout": 30,
"statusMessage": "Checking TDD guard"
}
]
}
]
}
}
FESurrogateModelTutorial/.codex/hooks/pre_commit_checks.py
+111
View File
@@ -0,0 +1,111 @@
import json
import re
import shutil
import subprocess
import sys
from pathlib import Path
CHECKS = ("lint", "build", "test")
def _repo_root(cwd: Path) -> Path:
try:
root = subprocess.check_output(
["git", "rev-parse", "--show-toplevel"],
cwd=cwd,
text=True,
stderr=subprocess.DEVNULL,
).strip()
except (subprocess.CalledProcessError, FileNotFoundError):
return cwd
return Path(root)
def _load_scripts(root: Path) -> dict[str, str]:
package_json = root / "package.json"
if not package_json.exists():
return {}
try:
package = json.loads(package_json.read_text(encoding="utf-8"))
except json.JSONDecodeError as exc:
_deny(f"Invalid package.json: {exc}")
raise SystemExit(0) from exc
scripts = package.get("scripts", {})
if not isinstance(scripts, dict):
return {}
return {str(name): str(command) for name, command in scripts.items()}
def _is_git_commit(command: str) -> bool:
return re.search(r"\bgit(?:\s+(?:-[A-Za-z]\s+\S+|--[A-Za-z0-9-]+(?:=\S+)?))*\s+commit\b", command) is not None
def _deny(reason: str) -> None:
print(
json.dumps(
{
"hookSpecificOutput": {
"hookEventName": "PreToolUse",
"permissionDecision": "deny",
"permissionDecisionReason": reason,
}
}
)
)
def _tail(text: str, limit: int = 1200) -> str:
text = text.strip()
if len(text) <= limit:
return text
return text[-limit:]
def _run_checks(root: Path, scripts: dict[str, str]) -> str | None:
npm = shutil.which("npm") or shutil.which("npm.cmd")
if npm is None:
return "npm was not found, so pre-commit checks could not run."
for check in CHECKS:
if check not in scripts:
continue
result = subprocess.run(
[npm, "run", check],
cwd=root,
capture_output=True,
text=True,
)
if result.returncode != 0:
details = _tail(result.stdout + "\n" + result.stderr)
if details:
return f"npm run {check} failed:\n{details}"
return f"npm run {check} failed with exit code {result.returncode}."
return None
def main() -> int:
try:
payload = json.load(sys.stdin)
except json.JSONDecodeError:
return 0
command = payload.get("tool_input", {}).get("command", "")
if not isinstance(command, str) or not _is_git_commit(command):
return 0
cwd = Path(payload.get("cwd") or Path.cwd())
root = _repo_root(cwd)
failure = _run_checks(root, _load_scripts(root))
if failure:
_deny(f"PRE-COMMIT CHECKS: {failure}")
return 0
if __name__ == "__main__":
raise SystemExit(main())
FESurrogateModelTutorial/.codex/hooks/tdd-guard.py
+189
View File
@@ -0,0 +1,189 @@
import json
import subprocess
import sys
from pathlib import Path
SOURCE_SUFFIXES = {".ts", ".tsx", ".js", ".jsx"}
TEST_SUFFIXES = ("ts", "tsx", "js", "jsx")
CONFIG_SUFFIXES = {".json", ".css", ".scss", ".md", ".yml", ".yaml"}
NEXT_SPECIAL_FILES = {
"layout.ts",
"layout.tsx",
"page.ts",
"page.tsx",
"loading.tsx",
"error.tsx",
"not-found.tsx",
"globals.css",
}
def _repo_root(cwd: Path) -> Path:
try:
root = subprocess.check_output(
["git", "rev-parse", "--show-toplevel"],
cwd=cwd,
text=True,
stderr=subprocess.DEVNULL,
).strip()
except (subprocess.CalledProcessError, FileNotFoundError):
return cwd
return Path(root)
def _extract_patch_paths(command: str) -> list[str]:
prefixes = (
"*** Add File: ",
"*** Update File: ",
"*** Delete File: ",
"*** Move to: ",
)
paths: list[str] = []
for raw_line in command.splitlines():
line = raw_line.strip()
for prefix in prefixes:
if line.startswith(prefix):
paths.append(line[len(prefix) :].strip())
break
return paths
def _touched_paths(payload: dict) -> list[str]:
tool_input = payload.get("tool_input", {})
if not isinstance(tool_input, dict):
return []
file_path = tool_input.get("file_path")
if isinstance(file_path, str) and file_path:
return [file_path]
command = tool_input.get("command")
if isinstance(command, str):
return _extract_patch_paths(command)
return []
def _normalize(path_text: str) -> str:
return path_text.replace("\\", "/").lower()
def _is_test_path(path_text: str) -> bool:
normalized = _normalize(path_text)
name = normalized.rsplit("/", 1)[-1]
return (
"__tests__/" in normalized
or ".test." in name
or ".spec." in name
or "test" in name
or "spec" in name
)
def _is_exempt(path_text: str) -> bool:
normalized = _normalize(path_text)
path = Path(path_text)
name = path.name.lower()
if _is_test_path(path_text):
return True
if name in NEXT_SPECIAL_FILES:
return True
if path.suffix.lower() in CONFIG_SUFFIXES:
return True
if ".env" in name or ".config." in name:
return True
if any(token in name for token in ("tailwind", "postcss", "next.config", "tsconfig")):
return True
if "/types/" in normalized or name in {"types.ts", "types.d.ts"}:
return True
return False
def _resolve_path(path_text: str, cwd: Path) -> Path:
path = Path(path_text)
if path.is_absolute():
return path
return (cwd / path).resolve()
def _base_name(path: Path) -> str:
for suffix in (".tsx", ".ts", ".jsx", ".js"):
if path.name.endswith(suffix):
return path.name[: -len(suffix)]
return path.stem
def _has_existing_test(path: Path, root: Path) -> bool:
directory = path.parent
parent = directory.parent
base = _base_name(path)
for ext in TEST_SUFFIXES:
if (directory / f"{base}.test.{ext}").exists():
return True
if (directory / f"{base}.spec.{ext}").exists():
return True
for ext in TEST_SUFFIXES:
if (parent / "__tests__" / f"{base}.test.{ext}").exists():
return True
if (directory / "__tests__" / f"{base}.test.{ext}").exists():
return True
for ext in TEST_SUFFIXES:
if (root / "src" / "__tests__" / f"{base}.test.{ext}").exists():
return True
return False
def _guarded_paths(paths: list[str], cwd: Path, root: Path) -> list[str]:
missing_tests: list[str] = []
for path_text in paths:
if _is_exempt(path_text):
continue
path = _resolve_path(path_text, cwd)
if path.suffix.lower() not in SOURCE_SUFFIXES:
continue
if not _has_existing_test(path, root):
missing_tests.append(_base_name(path))
return missing_tests
def main() -> int:
try:
payload = json.load(sys.stdin)
except json.JSONDecodeError:
return 0
cwd = Path(payload.get("cwd") or Path.cwd())
root = _repo_root(cwd)
missing_tests = _guarded_paths(_touched_paths(payload), cwd, root)
if not missing_tests:
return 0
names = ", ".join(sorted(set(missing_tests)))
print(
json.dumps(
{
"hookSpecificOutput": {
"hookEventName": "PreToolUse",
"permissionDecision": "deny",
"permissionDecisionReason": (
"TDD GUARD: missing test file for "
f"{names}. Write or add the test first."
),
}
}
)
)
return 0
if __name__ == "__main__":
raise SystemExit(main())
FESurrogateModelTutorial/.gitignore
+19
View File
@@ -0,0 +1,19 @@
node_modules/
.next/
out/
next-env.d.ts
tsconfig.tsbuildinfo
# Python
__pycache__/
*.py[cod]
.pytest_cache/
.ruff_cache/
.venv/
*.egg-info/
.ipynb_checkpoints/
*.nbconvert.ipynb
# phase execution outputs
phases/**/phase*-output.json
phases/**/step*-output.json
FESurrogateModelTutorial/AGENTS.md
+168
View File
@@ -0,0 +1,168 @@
# FEMSurrogateTutorial Agent Instructions
## Project Purpose
This repository is a Korean tutorial project for studying surrogate models in finite element method (FEM) structural analysis. The tutorial combines:
- Theory documents on surrogate modeling methods.
- NumPy/SciPy implementation of a 2D Euler-Bernoulli beam/frame element.
- Jupyter notebooks that build, validate, and compare surrogate models from generated FEM data.
The primary audience is graduate students and researchers who already know basic FEM and Python.
## Tech Stack
- Python `>=3.12,<3.15`
- Environment and dependency management: `uv`, `pyproject.toml`, `uv.lock`
- Numerical computing: NumPy, SciPy
- Machine learning: scikit-learn
- Data and plotting: pandas, matplotlib
- Notebook workflow: JupyterLab, ipykernel, nbconvert
- Testing and quality: pytest, ruff
- Model/result persistence: joblib, CSV, JSON
## Architecture Rules
- CRITICAL: At the start of every new task or session, read `AGENTS.md`, `PROGRESS.md`, and `WORKNOTES.md` before planning or editing. Use them to understand current scope, completed work, open tasks, and known pitfalls.
- CRITICAL: Keep `PROGRESS.md` current while working. Update it whenever the task state materially changes, including completed milestones, in-progress work, blockers, verification status, and next actions.
- CRITICAL: Record meaningful trial-and-error, mistakes, false starts, debugging discoveries, and corrective decisions in `WORKNOTES.md`. Do not log routine command output; log lessons future agents need.
- CRITICAL: Core calculation logic must live under `src/femsurrogate/`; notebooks should explain and orchestrate, not hide reusable implementation in cells.
- CRITICAL: FEM data for the tutorial must be generated with the in-repository 2D beam/frame implementation using NumPy/SciPy. Do not introduce Abaqus, ANSYS, OpenSeesPy, CalculiX, or other external solvers for v1.
- CRITICAL: Keep the structural model linear static and Euler-Bernoulli based for v1. Do not add Timoshenko shear deformation, geometric nonlinearity, material nonlinearity, dynamics, contact, or shell/solid elements unless explicitly requested.
- CRITICAL: Use `BeamExamples/CantileverBeam.txt` and `BeamExamples/CantileverBeam_Displacements.txt` as the canonical solver verification fixture. The solver must reproduce the listed `Ux`, `Uy`, and `Rz` values within documented floating-point tolerance before it is used to generate surrogate training data.
- CRITICAL: All random sampling, train/test splits, and model training examples must use fixed seeds for reproducibility.
- CRITICAL: Keep the project document and Python notebook based. Do not add browser app or design-system work.
- Keep public helper interfaces small and stable:
- `run_beam2d_case(params)`
- `generate_lhs_samples(bounds, n, seed)`
- `build_dataset(samples)`
- `make_model(model_name, random_state)`
- `evaluate_model(...)`
## Expected Repository Shape
```text
docs/
PRD.md
ARCHITECTURE.md
ADR.md
theory/
00_surrogate_modeling_for_fem.md
01_doe_sampling_validation.md
02_response_surface_methodology.md
03_gaussian_process_kriging.md
04_random_forest.md
05_gradient_boosting.md
06_mlp_neural_network.md
PROGRESS.md
WORKNOTES.md
BeamExamples/
CantileverBeam.txt
CantileverBeam_Displacements.txt
notebooks/
00_beam2d_fea_dataset.ipynb
01_response_surface_surrogate.ipynb
02_gaussian_process_kriging_surrogate.ipynb
03_random_forest_surrogate.ipynb
04_gradient_boosting_surrogate.ipynb
05_mlp_surrogate.ipynb
06_compare_surrogate_models.ipynb
src/femsurrogate/
fea/
io.py
data/
surrogates/
plotting/
tests/
```
## Development Process
- Start each session by reading `PROGRESS.md` and `WORKNOTES.md` after `AGENTS.md`.
- Before making changes, update `PROGRESS.md` with the current task, intended scope, and success criteria when they are not already recorded.
- During longer tasks, update `PROGRESS.md` after each meaningful milestone instead of waiting until the end.
- When you encounter an implementation mistake, incorrect assumption, failed approach, non-obvious parser/detail issue, or verification problem, add a concise note to `WORKNOTES.md` with the date and lesson learned.
- At the end of a task, update `PROGRESS.md` with completed work, verification commands/results, remaining risks, and recommended next step.
- Use TDD for code changes: write a failing pytest first, implement the smallest passing change, then refactor only if needed.
- For documentation changes, verify that links, filenames, and referenced commands match the repository.
- Prefer simple educational implementations over production abstractions.
- Keep every change traceable to the tutorial goal. Do not add speculative tooling, dashboards, APIs, or deployment layers.
- Commit messages should follow Conventional Commits, for example `docs: define tutorial architecture` or `feat: add beam2d solver`.
## Commands
Use these commands once the Python project files exist:
```powershell
uv sync
uv run pytest
uv run ruff check .
uv run jupyter nbconvert --to notebook --execute notebooks/00_beam2d_fea_dataset.ipynb
```
For full notebook verification:
```powershell
uv run jupyter nbconvert --to notebook --execute notebooks/00_beam2d_fea_dataset.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/01_response_surface_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/02_gaussian_process_kriging_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/03_random_forest_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/04_gradient_boosting_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/05_mlp_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/06_compare_surrogate_models.ipynb
```
## Documentation Standards
- Write tutorial content in Korean.
- Keep technical terms such as surrogate model, response surface, Gaussian process, Kriging, Random Forest, Gradient Boosting, MLP, DOE, LHS, RMSE, MAE, and R2 in English when that is clearer.
- Theory documents must include citations and links to primary or official sources where possible.
- Avoid long quotations. Summarize sources in your own words.
- When adding equations, define symbols and units near the equation.
- Each model-specific theory document should explain:
- Core idea and assumptions.
- Mathematical form.
- FEM structural-analysis use case.
- Strengths, weaknesses, and failure modes.
- Hyperparameters used in the matching notebook.
- References.
## Progress And Work Notes
`PROGRESS.md` and `WORKNOTES.md` are mandatory handoff files for future agents.
`PROGRESS.md` should answer:
- What is the current project/task state?
- What has been completed?
- What is in progress?
- What is blocked or intentionally deferred?
- What verification has been run, with command names and results?
- What should the next agent do first?
`WORKNOTES.md` should answer:
- What assumptions turned out to be wrong?
- What approaches were tried and rejected?
- What parsing, numerical, notebook, or tooling pitfalls were discovered?
- What should future agents avoid repeating?
Keep both files concise and factual. Do not use them as a full chat transcript.
## Data And Result Conventions
- Treat files under `BeamExamples/` as checked-in verification fixtures, not generated data.
- `BeamExamples/CantileverBeam.txt` defines a six-node, five-element cantilever beam with fixed node 1 and a downward nodal load at node 6.
- `BeamExamples/CantileverBeam_Displacements.txt` defines expected nodal `Ux`, `Uy`, and `Rz` values for that example.
- The BeamExamples fixture uses clockwise-positive `Rz`; keep element stiffness, solver output, and regression comparisons in that convention.
- For the 2D in-plane beam/frame solver, use `Area`, `ElasticModulus`, and `Izz` from the example input. Preserve `J`, `Iyy`, and `Poisson'sRatio` when parsing metadata, but do not use them in the v1 Euler-Bernoulli in-plane solve.
- Store generated reference data under `data/reference/`.
- Store derived or regenerated data under `data/processed/`.
- Store metrics under `reports/results/`.
- Store predictions under `reports/predictions/`.
- Store generated figures under `reports/figures/`.
- Use SI units in data columns and encode units in column names where practical, for example `tip_uy_m`, `max_abs_bending_stress_pa`, `mass_kg`, `compliance_j`.
- Include metadata JSON for generated datasets with seed, sample count, bounds, and code version notes.
## Review Checklist
- Does the change keep notebooks thin and reusable code in `src/femsurrogate/`?
- Does the FEM implementation remain a linear static 2D Euler-Bernoulli beam/frame model?
- Does the solver pass the `BeamExamples/CantileverBeam.txt` displacement regression check?
- Are random seeds fixed?
- Are tests added or updated for new code behavior?
- Do docs and notebooks refer to the same paths and artifact names?
- Are citations present for theory claims?
- Has browser-app and design-system work been avoided?
FESurrogateModelTutorial/BeamExamples/CantileverBeam.txt
+29
View File
@@ -0,0 +1,29 @@
Area, 1.0
J, 0.140625
Iyy, 0.0833333
Izz, 0.0833333
ElasticModulus, 2.05e+011
Poisson'sRatio, 0.3
# Node, NodeID, X, Y
Node, 1, 0.0, 0.0,
Node, 2, 1.0, 0.0,
Node, 3, 2.0, 0.0,
Node, 4, 3.0, 0.0,
Node, 5, 4.0, 0.0,
Node, 6, 5.0, 0.0,
# Beam, BeamID, NodeID1, NodeID2
Beam, 1, 1, 2,
Beam, 2, 2, 3,
Beam, 3, 3, 4,
Beam, 4, 4, 5,
Beam, 5, 5, 6,
# Fix, NodeID
Fix, 1,
# NodalLoad, NodeID, Fx, Fy, Mz
NodeLoad, 6, 0.0, -100000.0, 0.0,
FESurrogateModelTutorial/BeamExamples/CantileverBeam_Displacements.txt
+7
View File
@@ -0,0 +1,7 @@
# NodeID, Ux, Uy, Rz
1 0.000000, 0.000000, 0.000000
2 0.000000, -0.000014, 0.000026
3 0.000000, -0.000051, 0.000047
4 0.000000, -0.000105, 0.000061
5 0.000000, -0.000172, 0.000070
6 0.000000, -0.000244, 0.000073
FESurrogateModelTutorial/PROGRESS.md
+91
View File
@@ -0,0 +1,91 @@
# Progress
## Current State
- Project direction is defined as a Korean FEM surrogate tutorial using NumPy/SciPy 2D Euler-Bernoulli beam/frame analysis and scikit-learn surrogate models.
- Documentation files have been populated for PRD, architecture, ADR, and model-specific theory.
- `BeamExamples/CantileverBeam.txt` and `BeamExamples/CantileverBeam_Displacements.txt` are designated as canonical solver verification fixtures.
- Implementation work is active on branch `codex/harness-implementation`.
## Completed
- Replaced template project instructions in `AGENTS.md`.
- Removed UI-oriented documentation from the planned scope.
- Added theory document structure under `docs/theory/`.
- Updated PRD and architecture to require BeamExamples-based solver regression verification.
- Added `PROGRESS.md` and `WORKNOTES.md` as mandatory handoff files and documented their workflow in `AGENTS.md`.
- Created Harness phase files under `phases/`.
- Completed phase `0-project-foundation` step 0: `pyproject.toml`, package skeleton, artifact directories, and lint configuration.
- Completed phase `0-project-foundation` step 1 with TDD: package import smoke tests and `femsurrogate.__version__`.
- Completed phase `1-beam2d-solver` step 0 with TDD: BeamExamples input and displacement parser.
- Completed phase `1-beam2d-solver` step 1 with TDD: frame local stiffness and transformation matrix.
- Completed phase `1-beam2d-solver` step 2 with TDD: sparse global assembly, constrained DOF handling, load vector assembly, and linear static solve.
- Completed phase `1-beam2d-solver` step 3 with TDD: BeamExamples displacement regression and analytical cantilever tip check.
- Completed phase `2-dataset-and-surrogates` step 0 with TDD: LHS sampling, dataset schema, Beam2D case runner, and dataset builder.
- Completed phase `2-dataset-and-surrogates` step 1 with TDD: common split/evaluate utilities, metrics, timings, and prediction table.
- Completed phase `2-dataset-and-surrogates` step 2 with TDD: scikit-learn model builders and registry for RSM, GPR, Random Forest, Gradient Boosting, and MLP.
- Completed phase `2-dataset-and-surrogates` step 3 with TDD: plotting diagnostics and metric comparison helpers.
- Completed phase `3-notebooks-and-final-verification` step 0: dataset notebook, reference CSV, and metadata JSON.
- Completed phase `3-notebooks-and-final-verification` step 1: five surrogate model notebooks with metrics, predictions, and diagnostic figures.
- Completed phase `3-notebooks-and-final-verification` step 2: comparison notebook and model comparison outputs.
- Completed phase `3-notebooks-and-final-verification` step 3: full pytest, ruff, and all notebook execution checks.
## In Progress
- None.
## Blockers
- None recorded.
## Verification
- Documentation checks were run manually with PowerShell/`rg` to confirm required BeamExamples references and absence of stale template terms.
- Verified that `AGENTS.md` references `PROGRESS.md` and `WORKNOTES.md`, both files exist, and stale template terms are absent.
- `uv sync` passed.
- `uv run python -c "import femsurrogate; print(femsurrogate.__name__)"` printed `femsurrogate`.
- `uv run ruff check .` passed after excluding existing local harness infrastructure from ruff scope.
- RED: `uv run pytest tests/test_project_structure.py -q` failed because `femsurrogate.__version__` was missing.
- GREEN: `uv run pytest tests/test_project_structure.py -q` passed with 2 tests.
- `uv run ruff check .` passed.
- RED: `uv run pytest tests/test_beamexamples_io.py -q` failed because `femsurrogate.fea.io` did not exist.
- GREEN: `uv run pytest tests/test_beamexamples_io.py tests/test_project_structure.py -q` passed with 4 tests.
- `uv run ruff check .` passed.
- RED: `uv run pytest tests/test_frame_element.py -q` failed because `femsurrogate.fea.element` did not exist.
- GREEN: `uv run pytest tests/test_frame_element.py tests/test_beamexamples_io.py tests/test_project_structure.py -q` passed with 8 tests.
- `uv run ruff check .` passed.
- RED: `uv run pytest tests/test_beam_solver.py -q` failed because `femsurrogate.fea.assembly` did not exist.
- GREEN: `uv run pytest tests/test_beam_solver.py tests/test_frame_element.py tests/test_beamexamples_io.py -q` passed with 9 tests.
- `uv run ruff check .` passed after solver import formatting was corrected.
- RED: `uv run pytest tests/test_cantilever_fixture_regression.py -q` failed because `femsurrogate.fea.benchmark` did not exist.
- Regression discovery: fixture comparison then exposed an `Rz` sign convention mismatch; the element convention was aligned to BeamExamples clockwise-positive `Rz`.
- GREEN: `uv run pytest tests/test_cantilever_fixture_regression.py tests/test_beam_solver.py tests/test_frame_element.py tests/test_beamexamples_io.py -q` passed with 11 tests.
- `uv run ruff check .` passed.
- GREEN: `uv run pytest -q` passed with 13 tests after completing phase 1.
- RED: `uv run pytest tests/test_sampling.py tests/test_dataset_builder.py -q` failed because `femsurrogate.data.bounds` did not exist.
- GREEN: `uv run pytest tests/test_sampling.py tests/test_dataset_builder.py -q` passed with 4 tests.
- `uv run ruff check .` passed.
- GREEN: `uv run pytest -q` passed with 17 tests after completing dataset builder work.
- RED: `uv run pytest tests/test_surrogate_common.py -q` failed because `femsurrogate.surrogates.common` did not exist.
- GREEN: `uv run pytest tests/test_surrogate_common.py -q` passed with 2 tests.
- `uv run ruff check .` passed.
- GREEN: `uv run pytest -q` passed with 19 tests after completing surrogate common utilities.
- RED: `uv run pytest tests/test_surrogate_models.py -q` failed because `femsurrogate.surrogates.registry` did not exist.
- GREEN: `uv run pytest tests/test_surrogate_models.py -q` passed with 2 tests.
- `uv run ruff check .` passed.
- GREEN: `uv run pytest -q` passed with 21 tests after completing surrogate model builders.
- RED: `uv run pytest tests/test_plotting_and_results.py -q` failed because `femsurrogate.plotting.comparison` did not exist.
- GREEN: `uv run pytest tests/test_plotting_and_results.py -q` passed with 2 tests.
- `uv run ruff check .` passed.
- Initial `uv run jupyter nbconvert --to notebook --execute notebooks/00_beam2d_fea_dataset.ipynb` failed because nbconvert executed with `notebooks/` as the working directory; notebooks now locate the repository root by checking for `pyproject.toml`.
- `uv run jupyter nbconvert --to notebook --execute notebooks/00_beam2d_fea_dataset.ipynb` passed.
- `uv run jupyter nbconvert --to notebook --execute` passed for notebooks 01 through 05.
- `uv run jupyter nbconvert --to notebook --execute notebooks/06_compare_surrogate_models.ipynb` exited 0 and wrote comparison output; Windows/Jupyter emitted a transient zmq connection-reset message after execution.
- `uv run ruff check .` passed after notebook cell style fixes.
- FINAL: `uv run pytest` passed with 23 tests.
- FINAL: `uv run ruff check .` passed.
- FINAL: `uv run jupyter nbconvert --to notebook --execute notebooks/00_beam2d_fea_dataset.ipynb` passed.
- FINAL: `uv run jupyter nbconvert --to notebook --execute notebooks/01_response_surface_surrogate.ipynb` passed.
- FINAL: `uv run jupyter nbconvert --to notebook --execute notebooks/02_gaussian_process_kriging_surrogate.ipynb` passed.
- FINAL: `uv run jupyter nbconvert --to notebook --execute notebooks/03_random_forest_surrogate.ipynb` passed.
- FINAL: `uv run jupyter nbconvert --to notebook --execute notebooks/04_gradient_boosting_surrogate.ipynb` passed.
- FINAL: `uv run jupyter nbconvert --to notebook --execute notebooks/05_mlp_surrogate.ipynb` passed.
- FINAL: `uv run jupyter nbconvert --to notebook --execute notebooks/06_compare_surrogate_models.ipynb` passed and `reports/results/model_comparison.csv` exists.
## Next Actions
- Review generated tutorial outputs and continue with documentation polish or additional explanatory notebook text if desired.
FESurrogateModelTutorial/WORKNOTES.md
+16
View File
@@ -0,0 +1,16 @@
# Work Notes
## 2026-05-21
- Initial repository documents were generic templates for a web project. They were replaced with FEM surrogate tutorial-specific instructions before implementation work.
- The previous design-guide document was removed from the active scope because the project is notebook based.
- BeamExamples fixture files use a simple comma/space text format rather than JSON/CSV. Future parser work should handle comments, trailing commas, and labels such as `Poisson'sRatio`.
- For the v1 in-plane Euler-Bernoulli frame solver, use `Area`, `ElasticModulus`, and `Izz` from `BeamExamples/CantileverBeam.txt`; preserve `J`, `Iyy`, and `Poisson'sRatio` as metadata but do not use them in the in-plane solve.
- Avoid writing removed/stale file names into handoff notes when the project uses simple `rg` checks for stale terms; describe the lesson without preserving obsolete filenames unless the exact name matters.
- `scripts/execute.py` expects `git rev-parse --abbrev-ref HEAD` to succeed. On an unborn repository with no initial commit, it returns `HEAD` plus a fatal stderr and nonzero exit code, so create an initial commit before running Harness execution.
- `ruff check .` should exclude existing local agent/harness infrastructure (`.agents`, `.codex`, `scripts/execute.py`) so linting focuses on tutorial package code and future project scripts.
- Use `Izz` as the code parameter name for the in-plane bending inertia instead of bare `I`; ruff flags `I` as an ambiguous variable name and the fixture also uses `Izz`.
- The BeamExamples displacement fixture reports downward cantilever rotations as positive `Rz`, so this project treats `Rz` as clockwise-positive. A textbook counterclockwise-positive Euler-Bernoulli matrix reproduces `Uy` but flips every `Rz`; keep the element stiffness convention aligned instead of flipping only solver output.
- `jupyter nbconvert --execute notebooks/*.ipynb` can run cells with `Path.cwd()` equal to `notebooks/` on Windows. Notebook code should discover the repository root by walking/checking for `pyproject.toml`, not by assuming the shell working directory.
- `ruff check .` lints notebook code cells too. Generated notebooks must keep imports sorted and line lengths under the configured limit.
- nbconvert writes `*.nbconvert.ipynb` output files by default; keep them ignored because they are verification artifacts, not source notebooks.
- On Windows, nbconvert may emit a zmq Proactor event loop warning, and comparison execution once printed a libzmq connection-reset assertion after finishing with exit code 0. Treat this as an environment warning only when the command exit code is 0 and expected output files exist.
FESurrogateModelTutorial/data/processed/.gitkeep
+1
View File
@@ -0,0 +1 @@
FESurrogateModelTutorial/data/reference/.gitkeep
+1
View File
@@ -0,0 +1 @@
FESurrogateModelTutorial/data/reference/beam2d_lhs_300.csv
+301
View File
@@ -0,0 +1,301 @@
L_m,b_m,h_m,E_pa,P_n,A_m2,I_m4,tip_uy_m,max_abs_bending_stress_pa,mass_kg,compliance_j
1.8314998429486489,0.02288848310526338,0.0815229398597667,172594545239.26154,1204.4650264605164,0.0018659364316716727,1.0334161957807233e-06,-0.013829015619417438,87011299.20020096,26.827078910236825,16.656565663964518
1.485780501096186,0.0703451958583708,0.15227975734470864,134603011411.74176,430.61187485571196,0.01071214935567871,2.070044708657494e-05,-0.00016896401045085464,2353277.332637697,124.93983570435536,0.07275790932338262
1.912481924636748,0.047325586440789394,0.13412538162234836,137384268072.70396,1491.016058175157,0.006347562341872312,9.51585181099103e-06,-0.0026593065863062455,20096154.678896487,95.29584621803525,3.965068823793571
1.9005563087063533,0.03892541267357975,0.07695136609138858,204751900490.29495,1095.028618079069,0.002995363680903012,1.4780903506148138e-06,-0.008279755549199318,54174082.80724987,44.68893012378931,9.066569277072231
1.5947212929865011,0.028377670567845643,0.060651928533480566,143550315733.9896,285.4873970880711,0.0017211604472276289,5.27629829547462e-07,-0.005095497266108835,26167185.46189781,21.54645402864454,1.4547002513707934
1.07237473124558,0.060835540739851784,0.1272283305923341,194807902395.3725,841.5626396886561,0.0077400042890132725,1.0440651813465087e-05,-0.00017008684513586912,5498690.043104498,65.15645240127142,0.14313873436885768
1.719404317170917,0.05385550434598768,0.12141457596271288,180228444125.88403,780.2860073349921,0.006538843223426135,8.03269604288166e-06,-0.0009132337131101088,10139378.371577015,88.25688485115214,0.7125834877663964
1.8443936254162967,0.06781937032695569,0.0906637700929121,206850241685.69434,664.8332582220359,0.0061487597991691754,4.2118590646042665e-06,-0.0015959616691765433,13197640.606252536,89.02475701575838,1.0610483965161202
1.1133087091552474,0.07276333760631655,0.08972554699620917,109961391102.16035,527.9000060948273,0.00652873026799659,4.380056467488244e-06,-0.0005041471272986309,6019683.850035296,57.057664296625695,0.2661392715736369
1.7653262594338854,0.05980665036951069,0.10875237157317413,126953548532.28677,896.458597440227,0.006504115063531939,6.410389856402397e-06,-0.0020200152084294265,13423924.977437384,90.13279816085453,1.8108600005565714
2.4184005785926237,0.046583251237609244,0.1568083429212308,150170594507.19855,1012.1064382265317,0.007304642434452879,1.4967733662081683e-05,-0.00212299367486471,12821461.97409473,138.67457919566064,2.148695566644777
1.0122542173163664,0.0257631638203873,0.05996802707039356,122101793297.94275,196.1163789614812,0.0015449661053999694,4.629959923088148e-07,-0.0011993946892279361,12856299.886894634,12.276602878045393,0.23522094339701388
2.99885756490169,0.034208042406339394,0.06827291867439919,212556641451.73248,222.15212458178422,0.0023354828972184083,9.071777376802585e-07,-0.010356897291806043,25068733.85015985,54.979677349072226,2.30080673745004
2.5090373124694736,0.0644222822855815,0.06190015136572917,213676707662.4631,1509.0204900058407,0.003987749024803228,1.2732978139795645e-06,-0.029201695277680767,92030965.56296098,78.54247710356118,44.06595651692707
1.8803275265391401,0.03546362707534823,0.141638741145562,188165807683.9365,370.8129344289211,0.005023023495407992,8.39746263160384e-06,-0.0005200502893437317,5880203.563159812,74.14269535721769,0.19284137384215863
2.2767602373665152,0.05078719396396178,0.1319282799922206,113377538465.96469,502.63221905928657,0.006700267145296765,9.718218816358546e-06,-0.001794598357182278,7767635.770409364,119.75097925673768,0.9020229545906786
1.8387426022120184,0.03598261817712693,0.042756728124461955,139276750527.0553,693.7486407804699,0.0015384990226057391,2.3438235152907022e-07,-0.04403927624425049,116351676.43422394,22.20689401616478,30.552188035404416
1.3011131084669427,0.05481935324204158,0.08484687238436737,115209362593.83258,1734.3755729455568,0.004651250668721058,2.7903596005967974e-06,-0.003961130049810408,34308668.80130053,47.50665524433302,6.870087199651787
2.6198549887683336,0.07887793897606994,0.13647070121249977,207909603351.69885,1561.5862492494184,0.01076452764226103,1.670677321550229e-05,-0.0026946933734432015,16709370.142657414,221.38178634570068,4.2079961179124314
1.9163836401280836,0.0692936197063689,0.09353918410176623,173905530654.12637,1950.663751507745,0.006481668650791817,4.725989305697665e-06,-0.005568040616383383,36994376.79622444,97.50770554040177,10.861374997301908
2.460080176958872,0.03952084747455992,0.0688781284182868,107735300872.5662,974.7000408118613,0.002722122007552264,1.0761901586120548e-06,-0.041720592641427086,76733069.55438615,52.56861136183609,40.66506335029402
2.7755844200326263,0.05125709604641546,0.05692408518502546,175283604103.8452,1997.850111329783,0.0029177633016831852,7.878815513196515e-07,-0.10311046485275611,200319153.39364558,63.57321213773421,205.99925368534448
1.4102930025734708,0.022265414249600112,0.08705755680218691,186941727856.41827,117.79790590776206,0.0019383725657587836,1.2242467456018725e-06,-0.00048124824409759455,5906829.594940002,21.45933513707948,0.05669003537648415
2.7187095888004675,0.04325268945427481,0.08898072117551989,134150937902.88864,326.1913240502886,0.0038486555004221762,2.53933287372463e-06,-0.0064139601803737635,15537513.364638543,82.13750641195135,2.092178163641946
1.5015451743314063,0.0280474634849621,0.11212059965520282,163640968179.4723,1011.4454299974409,0.0031446984247413554,3.294341222963827e-06,-0.002117267779164323,25844473.813744865,37.06696794352397,2.1415008193165854
1.5613872984144939,0.039382290755115124,0.11412904353427888,149887803869.72943,1234.6779455652597,0.004494663176070163,4.878746594076833e-06,-0.002142346946215878,22548738.685472872,55.09059345107331,2.6451085262418284
2.2823683011586327,0.021672540627220464,0.05066818292659669,184397309151.04816,1023.8895143480386,0.001098108252984105,2.3492788514504826e-07,-0.09366986044671798,252005249.36306617,19.674356622635106,95.90758792183861
2.6010016269455036,0.06835079352389664,0.1545043674209379,186248249676.83844,589.1393859193188,0.01056049611612879,2.100799452968336e-05,-0.0008831650596319473,5634882.319220892,215.62276049831084,0.520307320896964
2.6988235184899976,0.050858874149295734,0.14880865969476118,102787761774.47253,1136.1743909684308,0.007568240895741235,1.396593804751516e-05,-0.005186037815692381,16336069.803628998,160.33897020574037,5.892243356783542
1.601688330241449,0.03963062111434279,0.1144439338431775,113729873278.4416,1702.5081209908894,0.004535484180973879,4.950259498266031e-06,-0.004141898486083398,31521147.53931131,57.02579186458539,7.051615808876856
1.9382531257107587,0.03620970064654632,0.15745742612342728,141534717182.76892,1897.3497040557022,0.005701486264504984,1.1779670221306714e-05,-0.0027622405372338702,24578642.735462748,86.74975005098388,5.240936265851348
1.5591287409274512,0.049392939146356715,0.06940672689731209,100163372270.41394,1158.927649116863,0.0034282022379867358,1.376221431308448e-06,-0.01062144848682015,45563969.61218766,41.9583178158119,12.309490325046339
1.0169440865973296,0.05593646414679583,0.07417492434149953,100476764002.75151,160.82272485226002,0.004149082996019581,1.902326686036506e-06,-0.0002949623926723835,3188500.632999652,33.122175528188606,0.04743665571851501
1.2608420992915117,0.021894964398804215,0.040383667280905984,106701680904.53453,680.973354795578,0.0008841989574085911,1.2016562860306466e-07,-0.035484561670924356,144273416.82930407,8.751456866755749,24.16404100449994
1.1681065315811268,0.03651047386470185,0.06101704401387274,172176203613.8894,1116.1525285212006,0.0022277611907698634,6.911776980931584e-07,-0.004982953168829409,57548956.32287725,20.427759822268623,5.5617357788916735
2.613091893660169,0.0428529520046492,0.08746146285403349,188757426541.5191,1856.724475458743,0.0037479818699403056,2.3891846138442986e-06,-0.02448705173017026,88805359.56713,76.8814951791214,45.46570827923148
1.957399449788186,0.02352144812631788,0.13224525759397504,144858300254.10114,1813.4632198003533,0.0031105999664482295,4.533390505297857e-06,-0.0069033416455300395,51774414.247427806,47.79619030326978,12.518956167884774
1.0754425740145133,0.05632837492058661,0.10197971033879796,127852674408.22131,1402.1610993072868,0.0057443513582566335,4.978371458644394e-06,-0.0009133583838071284,15444776.195958031,48.49510208452314,1.28067559550053
2.748190193991543,0.029189783685797673,0.13914471791153568,194550648608.6056,1991.810225336548,0.004061604216859064,6.553145407482807e-06,-0.010808976488024223,58114120.24030992,87.62217791307721,21.529429894268976
2.737376665709003,0.059793119208386175,0.15846534399138273,197171418728.4136,1360.1770486512287,0.009475137203674669,1.982772363055239e-05,-0.0023788171016291743,14878578.766606314,203.60560296298277,3.23561242457504
2.127996843275138,0.07648227551987294,0.065583255277641,210719969283.56403,1765.8392275775352,0.0050159565996347,1.7978707338303775e-06,-0.014971960976924529,68537246.1786959,83.79042750871774,26.438076006813407
2.339542531006592,0.05110218729810469,0.11375155805330195,217519353948.91022,1324.3401998970633,0.005812953425091065,6.268019011143268e-06,-0.0041461301601332,28114318.46768957,106.75726638477374,5.490886845070045
2.4807541533989843,0.07280280445677859,0.1434690996526244,188989500502.69434,1030.2910044573773,0.010444952807600093,1.791603828409672e-05,-0.0015484963132998005,10233637.532757176,203.40417646715596,1.5954018220281971
1.611259544606639,0.020965647782533448,0.0793032577437884,132195515076.3166,301.11512726835883,0.0016626441698637357,8.713650254441947e-07,-0.003644945025297345,22077962.1869384,21.02976761062358,1.0975480851785815
1.1380693108621813,0.054688929246585666,0.1302823502190609,172923054616.7614,1611.8077500652946,0.007125002233209116,1.0078013308574489e-05,-0.0004544334545482174,11856666.740908664,63.65365909430245,0.7324593639297616
1.1970560162717296,0.07686991602122166,0.07875653775878153,161018911947.34885,236.11945674620944,0.006054008443639709,3.129212149325244e-06,-0.00026794277217479195,3556868.926398274,56.88884975564729,0.06326650180498523
2.2366756486113366,0.032494419533240844,0.04880067870206303,133425120710.35454,1317.3621792082665,0.0015857497272517274,3.1470607277950625e-07,-0.11701734408260855,228454093.01701942,27.842441227927658,154.15422340582876
1.5799282239183674,0.07445087941133813,0.07008585625845357,190051464709.8472,885.9142139521327,0.005217953632738504,2.135894201675166e-06,-0.0028690064822059374,22964113.163278602,64.71533889136836,2.5416936225070463
2.875760889847622,0.027160509123923204,0.11772326594936802,198436241667.45178,1085.3627463884377,0.0031974238389158483,3.6926960907836247e-06,-0.011742144368100255,49752673.59576146,72.18095743013201,12.744486059850818
2.43133244952272,0.07060028264520024,0.10016988958032483,196552139300.14716,467.0925737092751,0.007072022516909432,5.913393489384802e-06,-0.001925307900863989,9618729.896012884,134.97633695857036,0.8992970225973624
2.454532752038515,0.060416097529133087,0.09619491473650338,212976693312.94727,472.14750470019595,0.005811721350527229,4.481545039166519e-06,-0.0024383895768227836,12437723.079946205,111.98072414463617,1.151279554183844
2.2659447659220726,0.028952339083094296,0.04094356756849021,124497478994.26439,1125.413412036063,0.0011854120515145112,1.6559966563004738e-07,-0.21169898568446774,315251844.6210834,21.08571413368349,238.2488778037305
2.8870356750940136,0.07720109864779011,0.07803697159449194,118508819724.02277,1241.3343766667094,0.006024539942241167,3.057338015981658e-06,-0.027480830284222508,45737022.472930476,136.53553465334076,34.11289933114898
1.1291014037948819,0.03573057699007314,0.052549547438675834,183667874579.9599,1353.1837966588705,0.0018776256505511077,4.320815517243893e-07,-0.008181547419697236,92910114.81121816,16.642233599032494,11.07113739993049
2.2414313057299413,0.06872856088386628,0.12359238421025875,146548487465.68164,812.8953468340021,0.008494326702976963,1.0812624845355039e-05,-0.0019256493507311863,10413354.435320249,149.45968087623032,1.5653513968432986
1.4065306561811344,0.020273390641434193,0.1040998919792323,135341893943.94872,397.70883693499695,0.0021104577758260788,1.90588187213665e-06,-0.0014300899817837975,15277023.517729312,23.30212494816057,0.5687594233676251
1.826249320085565,0.04697611579152199,0.11924746491239926,144621923926.2337,1653.5705281560415,0.005601782719570324,6.638092864183832e-06,-0.0034970690839348415,27124305.438361306,80.30747728062661,5.7826503721203
2.2246456016622407,0.05005609518099281,0.15198244049392126,197936724240.38977,142.72425932125824,0.007607647507203299,1.4643873337184473e-05,-0.00018070772012295034,1647654.2683857938,132.85590859228773,0.025791375508181322
1.042833035705912,0.058779886893946726,0.14493211466677136,126379582748.83847,1972.5755796896055,0.008519093307413338,1.4912188568033188e-05,-0.00039567484010969616,9996355.198026434,69.73933669156939,0.7804985270979758
2.899760811553612,0.0318220486590499,0.13490142046062267,194336063708.38275,1659.3238440922435,0.004292839566072884,6.510231879122651e-06,-0.010659738945541567,49852093.38463715,97.71843236028197,17.68795900413583
1.780938884510343,0.03761604152904589,0.11829859744482052,216411005745.66534,307.6507833259193,0.004449924954312251,5.189561130770031e-06,-0.0005157910996826229,6244907.491086512,62.21159841665765,0.15868353584989625
2.4755986030522696,0.07137351869202158,0.05303918024990824,138485060383.08636,688.5633491549236,0.0037855929229763273,8.874548585343163e-07,-0.028334407686754395,50938325.87525222,73.56712713198132,19.510034653112616
2.9282979381162413,0.07048741960062826,0.06795280784918846,205214703573.28278,479.0341318296734,0.004789818079906613,1.8431156484791915e-06,-0.010600587323396578,25858691.500124387,110.10421309763807,5.078043145347921
2.102098815519008,0.026402623716520364,0.12228369270545006,151914192477.86105,253.96104698542044,0.003228610325168604,4.023198635307189e-06,-0.0012865758997511547,8113108.99264617,53.276834831428495,0.3267401625270126
1.438691137842491,0.053003422601885564,0.06601178728785918,110575643852.93709,942.6032728618675,0.0034988506583241777,1.2705364910413264e-06,-0.006659839671566904,35229044.54530091,39.51505866290807,6.2775866711542685
1.414403183805858,0.04882944216761645,0.14845767749078817,149309506519.0759,610.60676382933,0.007249105577375095,1.3313998479414166e-05,-0.00028971038864845423,4815030.022969181,80.48729036581547,0.1768991228603701
2.0353686403612703,0.02332481098639935,0.15539943358306796,179856019927.0757,1945.7396345704922,0.0036246624157185796,7.29432621084417e-06,-0.004168526314270902,42185389.05134458,57.91356507087033,8.110866867426946
2.885249561289233,0.07502641998074575,0.05528161931795067,147988357964.81046,606.4353783401605,0.004147581988164274,1.0562707308145347e-06,-0.031060656337359775,45787130.56863121,93.93945152733245,18.836280877440476
2.351414219740206,0.02986481013474012,0.09828716313145244,214871839997.58304,505.5376364361669,0.0029353274656030563,2.3630282440532682e-06,-0.0043149050563687525,24721824.882794213,54.18204032637211,2.181346903643125
1.4311801416075802,0.02434680593601473,0.1293718902803398,191379545728.0371,1304.2210211934942,0.0031497923062308235,4.393195391237984e-06,-0.001515782214629715,27483681.44445964,35.387173561097285,1.976915027871303
1.8605504351019462,0.042054043274588296,0.14538206538300838,155548354819.96948,404.43763353660887,0.006113903668966059,1.0768594273778364e-05,-0.0005183584838648528,5079428.273869284,89.29552513200956,0.20964367853792554
2.838279252077004,0.06353785559677937,0.15836925718719325,157717901217.78394,355.8809369288714,0.010062442994129098,2.1031194818127544e-05,-0.0008177186490437612,3803091.596639364,224.19618192723718,0.2910104789659047
2.0111673108402313,0.06485092449088713,0.12682787158977285,111271833012.24095,1986.3541833732334,0.008224904723808288,1.1025011173054024e-05,-0.004390517963427739,22977911.960835844,129.85202719509425,8.721123723830017
1.8574788390230883,0.0685463759352212,0.0947230269330848,105468411318.24774,613.2931684395832,0.0064929202138773135,4.854784488659686e-06,-0.0025587398737420674,11113417.203661704,94.67462592082764,1.5692576843799715
2.6392631901607957,0.050586520941824586,0.07477415415586579,205756877676.9475,1792.692131769722,0.0037825643151129244,1.7624146452234193e-06,-0.030294940628359013,100369516.79162282,78.36798467615259,54.30950169689008
2.111956910778975,0.04150066578872504,0.15400899877518737,152541561771.2149,316.0008881453181,0.006391475986625215,1.263316331472268e-05,-0.0005148988350637654,4067966.312636845,105.96339675824329,0.1627084891851395
1.0014264214742683,0.061764448541219166,0.11708875672061811,125718315392.91345,1376.2922971645733,0.007231922489225947,8.262337020810443e-06,-0.00044355257253967935,9765894.263652556,56.85157033130386,0.6104579889738913
1.6856494847041383,0.0663499842356854,0.1189675311235549,108626234296.58911,263.5662911187316,0.00789349381460628,9.309898043819937e-06,-0.0004160933527119218,2838642.271951645,104.44946068168507,0.10966818173343947
1.1458396446677404,0.026891163534892886,0.08406813850038895,178256591425.2339,1547.380576946341,0.002260690060487984,1.331443190666247e-06,-0.003269483729673584,55975731.78183147,20.33454812056554,5.059135619938985
1.6712647923371784,0.04365954073872256,0.12457052002277555,128972751590.80008,1905.650002103744,0.005438691693778223,7.03305071686388e-06,-0.003269007846047917,28205248.893309005,71.35252746187737,6.229584808698369
2.1384126500867273,0.05709307593456131,0.055745934746160644,215490403396.62256,970.0232332545547,0.0031827068855056493,8.242174439925595e-07,-0.0178018726648786,70147961.63245386,53.42663422404477,17.268230080371417
1.2557271906680043,0.044839093908410316,0.12255691330320925,160243710423.25885,1111.453854069051,0.0054953409447275016,6.878425296936459e-06,-0.0006655582310943875,12433847.260623487,54.17009501334135,0.739737261057237
2.588034071579322,0.021174945313894144,0.15511863778583707,207517772888.27136,1141.6966984823966,0.0032846286722808538,6.586170934589154e-06,-0.004826709522544038,34795391.17509136,66.73073769334123,5.510638326422073
2.807867229176492,0.0666381271839097,0.10374811733425016,113085413208.90451,1067.323026027182,0.0069135802380109485,6.201292416114119e-06,-0.011230925047518122,25069199.434559733,152.38746078475626,11.987024906801516
1.227061247834137,0.029723238153739916,0.1029526971865092,177496282147.6928,1883.8957752126732,0.0030600875370444826,2.7028880727597e-06,-0.0024183380949151356,44025346.65861299,29.476081428746827,4.5558969200464885
2.9710431244066564,0.060186340327272714,0.13692333426772887,166872332657.3057,729.6871195986578,0.008240914394982451,1.2875054890388292e-05,-0.0029689908975776454,11527735.869587757,192.20027960848614,2.1664344161680655
2.210021847705903,0.051760835238663316,0.13811991091366066,176150450348.11322,1826.625937519196,0.007149201951980845,1.1365509212876897e-05,-0.003282807450351345,24529211.211943835,124.02915618418395,5.996461236693027
2.4487914057713125,0.053673046310513686,0.14252070565784486,213317360550.77258,191.55717833418424,0.0076495204349805975,1.2948184857742409e-05,-0.00033946692094041287,2581602.071297701,147.04682721070228,0.0650273255131391
2.045876965049992,0.04954726517142617,0.0833183854162591,117833768369.22206,1959.1727057772932,0.004128198135874477,2.3881465726731752e-06,-0.019872809059518277,69920110.49397166,66.29941596578111,38.93426509653193
1.3947201725217278,0.07977939782851484,0.1589662855852927,142043082185.1145,332.6222866889177,0.01268223453903037,2.6706968102347878e-05,-7.929515677140202e-05,1380666.7640673867,138.852121502264,0.026375336368659956
2.727914991379722,0.07249126009796847,0.07971050709530414,120733477883.6434,265.75679548591074,0.005778315102386654,3.0595046598209796e-06,-0.004868293923976997,9443862.782197664,123.73760628282379,1.2937821927196567
1.5080205001189793,0.07929796780301963,0.059519692129124196,104269368673.55035,1047.7877266045866,0.004719790630100931,1.3933583994093103e-06,-0.008244307928712086,33748027.387947045,55.87269705772418,8.638284662053405
2.7117035361833945,0.06135319406939463,0.12096633619886818,108056962302.81097,583.7158701538976,0.007421671100672796,9.050019442820886e-06,-0.00396738732995687,10578612.956230627,157.98416837946354,2.315826947543323
1.0939706323345735,0.06893894354764854,0.1361355202715921,157283226091.914,536.4549517916284,0.009385038946833051,1.4494316622265394e-05,-0.00010269489179134353,2756021.731196738,80.59561238053969,0.055091183225171696
1.1622913272795432,0.05786893010930312,0.0460773074504991,157178725492.1706,1425.8497974086044,0.0026664444844778047,4.717647482754067e-07,-0.010064177004606168,80932021.23996015,24.32860459700026,14.35000474310204
2.7716878936706366,0.04312541237999208,0.12480506453875065,156706246149.03607,1682.697094517661,0.005382269875345148,6.9863227093708594e-06,-0.010908944065388938,41658520.38609861,117.10608219360417,18.356448483085646
2.5389745767420147,0.05546185075884183,0.1291954309889122,169475506176.02783,1536.9320110250876,0.007165417712231298,9.966773228725662e-06,-0.0049641733799332816,25291558.42784295,142.81358521427373,7.629596975898065
2.691255638827559,0.06297069741791503,0.0765125118485241,182849657583.16687,1188.249760943137,0.00481804623229805,2.3504695887419873e-06,-0.017963979523115015,52048775.4075278,101.7877636128114,21.345694373928826
2.471636471146515,0.05778734751839677,0.08634307603146052,201290879335.22626,314.4498614731415,0.004989537340437364,3.099802786616029e-06,-0.002536446909736171,10824291.000963096,96.80873134846313,0.7975853794005168
1.1749551739564756,0.07225278999907067,0.06712687228516774,217670736453.52356,165.16932008621438,0.004850103806514662,1.821220843370476e-06,-0.00022527311363690155,3576469.151747768,44.734438309269635,0.03720820701311154
2.3809623473625416,0.04852277304787561,0.06134584352093114,140821987726.1037,1039.775234610213,0.0029766704425966324,9.335117613737227e-07,-0.03558652100852212,81344341.81955363,55.635620917987154,37.00198323059736
2.0875962313292424,0.03274970697390237,0.04426037959548125,190994540317.8186,1457.9021947833785,0.0014495144623056986,2.3663096529928056e-07,-0.09782596018411872,284635101.82364684,23.754107290817885,142.6206820592181
1.7941800678946425,0.045497545343850115,0.10729594440554388,103020088720.08171,995.1496827382779,0.0048817020958024536,4.683350275692161e-06,-0.003970879214337942,20452721.60720234,68.75542289185287,3.9516191903404247
2.0574912934882548,0.034019059204692954,0.14686011359844534,189703355518.88113,498.1916558730003,0.004996042899313445,8.979509875556454e-06,-0.0008491053312872404,8382154.9957609605,80.69262092276516,0.4230171910045828
2.5323886742521076,0.071607908391047,0.07490476862260115,137178636631.16434,622.871006540016,0.005363773809579794,2.507888032320121e-06,-0.009801066218384816,23555905.66826902,106.6278063660451,6.104799980610698
2.3301750347380024,0.05527413751107069,0.09549247389991775,123981563453.13733,1556.5889191219576,0.005278264133616382,4.010958444788195e-06,-0.01320118883679208,43177099.64580963,96.54934259061136,20.548824262587036
1.677122085801654,0.07462903940988234,0.11497922397710428,206518586292.924,1232.4381175880685,0.008580789037505004,9.453327962571316e-06,-0.0009926451687196605,12569976.11805454,112.96959184597424,1.2233737431697491
2.0323791598945036,0.04277015701138904,0.09154170388539487,140161625063.5206,554.0170695932885,0.003915253048268421,2.7341137178513925e-06,-0.004045483107103573,18849520.242546406,62.46463780296122,2.2412666960866736
2.8062624068569506,0.07985373881967696,0.11337690514066068,200031319360.05948,205.79991536540234,0.009053569771285607,9.698125558017938e-06,-0.0007814891818280886,3375827.68091437,199.44253610156997,0.16083040747919816
2.2717225155456804,0.04716473377826938,0.0949863969839479,127466196746.35666,1090.6494644510033,0.0044800081263049124,3.3683746050520937e-06,-0.009926916544691682,34934256.698401086,79.89208234328272,10.826786213117787
1.7378500598700533,0.0738777679130561,0.14607640565505262,219006087605.34467,1760.7324236745358,0.010791798794557413,1.9189901333882387e-05,-0.0007329596853289192,11646166.685165578,147.2230462226333,1.290545883204913
1.5137154358328395,0.05407141725293492,0.10531225799488872,198347582797.3896,491.23308203901007,0.005694383043890359,5.262877731885171e-06,-0.0005440626066401296,7439735.481965973,67.66445276199077,0.26726155108200844
1.4492631580499715,0.025535568028259188,0.10835483609802105,181044649435.6347,962.4982454017294,0.002766902288371891,2.7071303983189564e-06,-0.0019926250153884852,27916201.656973228,31.47826095542309,1.917898081055011
1.2689404943203408,0.06687857997010405,0.058791498763259065,123206849125.83661,272.9127958972913,0.003931891951600894,1.132529158521066e-06,-0.0013321163869399325,8988770.643501224,39.16629479592707,0.3635516076203749
1.4258128606535507,0.0758595259575483,0.06400342688102204,202271809950.72742,1362.0811610946794,0.004855269622852936,1.6574428459527883e-06,-0.003925503713462117,37497316.15409862,54.34324108110321,5.346854655913956
1.0313069010984408,0.03073462810610016,0.143667461943138,203435921628.17838,653.2340954951508,0.004415566013769644,7.594898511996559e-06,-0.0001545830051510399,6371815.872576612,35.74735906271248,0.10097888954876179
2.904521170293873,0.03156970614678105,0.14293141312972282,121103625103.24872,1964.0599277206998,0.004512302711649512,7.681965562248249e-06,-0.017243587282486036,53070675.69776106,102.8827182091696,33.8674387916851
1.4573945036854046,0.06471900711662265,0.14999607121470343,145928435034.80405,104.33495908973752,0.00970759680040983,1.820079053666575e-05,-4.0533098182527294e-05,626565.6961965796,111.06021603415373,0.0042290191406542995
2.3995696313896944,0.03826366264328562,0.08648192895824242,106970536155.77838,1569.0855127466498,0.0033091153543987816,2.0624403488417235e-06,-0.032755170141048756,78939422.57360174,62.332553782768194,51.39566293587124
1.5831564779291536,0.06158952125377512,0.14651519020975837,134859695898.89427,1524.898180279426,0.009023800421424817,1.6142602099109667e-05,-0.0009264786171953522,10955792.648574464,112.14579152784042,1.4127855574289916
2.763846605279553,0.07855458480595,0.14787570706278394,135672389234.38428,649.6311811736562,0.011616314771203281,2.11680471453804e-05,-0.0015918976721288796,6271433.8012254285,252.029840348054,1.0341463650526777
1.3259034621897743,0.023928018494800956,0.1309319860687389,139710905166.88168,1446.3098788607458,0.0031329429842138056,4.475718424778278e-06,-0.0017971434688577397,28049573.410042908,32.60874260445615,2.599226352739018
1.4630438878749488,0.0753596491752525,0.12043197556765828,203664306156.47577,1650.7582276289302,0.009075711428261307,1.0969404555335327e-05,-0.0007713230369176848,13257742.691050088,104.23358844589103,1.2732678493516012
1.054406551847298,0.027783601365745487,0.05215405511524665,147170484989.8246,1287.711424834247,0.0014490274769291323,3.284517181024652e-07,-0.010409486893534211,107798617.8929205,11.993732914024568,13.404415199466358
2.7894324144038096,0.07145804127893124,0.08227478525214643,148956404054.46942,849.1079141955836,0.0058791950007630826,3.3164246451966493e-06,-0.012435402609648991,29379564.91368695,128.7369942799756,10.558998772061372
2.2539066242101127,0.0380942901797728,0.11154464927677643,115056077385.51292,826.4707556456384,0.004249214237550506,4.405800892019677e-06,-0.006222710058892296,23580732.457847882,75.1820571239686,5.142887884536431
2.402994457545718,0.024450172665569057,0.07333284694924996,119617979556.28087,1486.8203416185795,0.0017930007699669106,8.035193158826713e-07,-0.0715488673316161,163035992.62936315,33.822281663954676,106.38031136841587
2.742828039600342,0.023609133476818346,0.09170812089936714,159918493491.65118,395.0861585155586,0.002165149267221353,1.5174772399310487e-06,-0.011198127962772995,32745076.440472394,46.61826214243065,4.424225359377641
1.5697906829164001,0.07549512638840895,0.07604579502760658,181453987934.30493,1258.2507780822061,0.0057410869069162,2.7667077354952207e-06,-0.0032317770495882414,27145064.58942552,70.74659217987953,4.066385987232621
1.0361433009419025,0.06182983510372808,0.04805833918607037,111760346401.94025,706.8580808633781,0.0029714391872337647,5.719039774627004e-07,-0.0041007149991116746,30772848.329627056,24.168868942866858,2.8986235344397473
1.1891332822946319,0.0527875598961165,0.08766354684184721,139024803572.45477,1499.9087014354996,0.004627544729620024,2.963517222398649e-06,-0.0020404944982919558,26380130.898834437,43.196724508391526,3.0605554532193686
2.544032769922248,0.06594414947234263,0.05742754543697271,120109802061.00427,156.39458008854078,0.0037870106401254764,1.0407724496932926e-06,-0.006866482356673922,10976878.837448228,75.62909147290901,1.073880624857392
2.4113491041746977,0.06806925253289528,0.15637898691304603,165932504055.44736,1719.6287239408757,0.010644600751022457,2.1692266004892448e-05,-0.0022328385307194484,14946457.070863962,201.4926106094112,3.8396532733471047
1.5923443831004058,0.04005190618973452,0.05773069148673035,151035260497.287,1282.6360973889136,0.0023122242396950293,6.421880539337018e-07,-0.017797239006710864,91802603.88603026,28.90257965229384,22.82738118386537
2.14854194002951,0.05439898896951202,0.11195997362774329,147207832368.7976,1631.9826419816247,0.006090509370402464,6.362062696420984e-06,-0.005760987394660233,30852774.00784508,102.7228613248515,9.401831428760444
2.9217862660688345,0.032843445417127595,0.048757074670193176,195326934051.26315,761.0501315585215,0.001601350320629304,3.1723448179120516e-07,-0.10211624123203614,170879107.52690297,36.72860648574005,77.71557882390282
2.650969177806023,0.033149857480434794,0.07285282237491812,112263045235.50276,562.2891172867971,0.002415060678775967,1.0681680006457648e-06,-0.029118974501895014,50832465.96639513,50.25767366243609,16.3732824689673
2.645330657566194,0.05809176556486251,0.062398521644742064,192519600897.1284,1836.6219985253722,0.0036248402909803547,1.176132446739775e-06,-0.05005036379772565,128880680.4817552,75.27287403151523,91.92359918510083
1.7116485574723677,0.04607224077507914,0.05080289837571628,133938373623.35886,414.7005979668885,0.0023406033660378772,5.034119949422421e-07,-0.01028084050401299,35816586.66371313,31.44937944448555,4.263470704616394
2.3179594419089993,0.0698117402640165,0.12983737616156665,109203043249.62506,1619.773916426538,0.009064173181152699,1.273345944268063e-05,-0.004835812948398948,19141834.59741644,164.93152859555715,7.832923678534328
2.2170807507995125,0.06206830874195027,0.09726977055680387,219837925483.5011,1265.2639654958202,0.0060373701501783665,4.760168652730884e-06,-0.00439217324060257,28660793.27513042,105.07489659148435,5.557258531549435
1.5294680246631351,0.04242086202547611,0.1352559504127669,140463337062.4261,856.1338645748704,0.0057376740105846225,8.747166327492526e-06,-0.0008310195877148452,10123742.215554321,68.88837314076949,0.711464011167726
2.2316117653477456,0.07494208675424054,0.09992226275683394,208295443337.3362,956.7772193039224,0.007488382884202668,6.230620737223157e-06,-0.0027310799449712883,17121050.84331536,131.18263228035056,2.6130350754463385
1.2445404504507112,0.020747849981456956,0.10212715532645167,196038222403.36148,1775.016121825097,0.002118918897746172,1.8416858803310756e-06,-0.0031590156914121205,61250127.86547549,20.701080193835935,5.607303781354969
2.595558640536703,0.07828353095980646,0.04130940703342244,116560683003.23747,124.8123838731956,0.0032338462444321723,4.5987102109595957e-07,-0.013571905660408055,14550283.171452533,65.89005486093926,1.6939418991776465
1.316696947387901,0.04519978117597574,0.15359480367917966,136273168756.41151,1435.5960470836774,0.006942451516065875,1.364849156707118e-05,-0.0005873182212224315,10636039.812315397,71.75767204095068,0.8431517167671394
1.626844127395485,0.05282349110856836,0.047938376313797666,167988424833.00262,793.6237756270751,0.0025322723949710952,4.849487175130852e-07,-0.013981574273287148,63814316.719322376,32.338957926586744,11.096109763976525
1.0617097056098412,0.05157370872018972,0.12594127202734143,132787328876.609,1712.9943483542802,0.0064952584793882846,8.585218314452442e-06,-0.000599437708845018,13339773.44982657,54.13421989888761,1.0268334074419545
1.690444257651822,0.021496426584195448,0.0818724117236866,121600668008.59973,1672.1450161760738,0.0017599642878892516,9.83100182416688e-07,-0.022522754868352028,117702206.53730504,23.35470396445711,37.66131230367025
2.197356544114635,0.0249116415865122,0.15997594369687082,183594002331.03647,1251.4457206043853,0.003985263371840501,8.499338833351692e-06,-0.0028362775317182136,25879274.133217223,68.74279971855255,3.549447379515127
1.4693122091591027,0.059152260883236454,0.1331021331716896,191936918720.63373,1417.963699048954,0.007873292105487064,1.1623720270335684e-05,-0.0006720203919551751,11928588.864011742,90.81134510241475,0.952900520813088
2.8602167128648457,0.07186473302707089,0.09702997350637749,143986230123.234,698.2192085353996,0.006973033141659579,5.470818525639466e-06,-0.006913438243374578,17709827.89240488,156.56342955941122,4.827095378547361
2.2941834394689877,0.037284593794104204,0.11294452893614798,144254417101.51257,1604.7796995369506,0.004211090882650726,4.476553355336487e-06,-0.010002434203830587,46444575.73239496,75.83896747584768,16.051703356261367
2.0844917675866554,0.05949897487368812,0.14722733877245786,202799760420.5213,1572.01388989613,0.008759875730342438,1.5823174704596453e-05,-0.0014790219398015017,15244788.603835296,143.3401274331005,2.3250430328290785
2.304222089828586,0.03906286972043847,0.12026734480875395,107303479831.53624,230.63138968017876,0.004697987621887408,5.662732780013312e-06,-0.0015478550699345377,5643316.537703733,84.97787382033972,0.3569839658025127
2.288668294374408,0.07636508084636587,0.13870445205023224,115956690685.08931,1784.523748927207,0.010592176694566862,1.6981841100838293e-05,-0.0036213379155577586,16679415.125940835,190.29953490874354,6.4623635132033685
1.619280685381442,0.06031216365010704,0.12285413804816706,208559810329.4909,1179.1318813706505,0.007409598879053893,9.319508963432962e-06,-0.000858586154413993,12584943.811277138,94.18602975751622,1.0123863075729633
1.9764133743797743,0.04862186406220104,0.04718223796736001,209818554532.6043,914.5179335817894,0.002294088360599399,4.255846630641964e-07,-0.026355694473561814,100191893.13257454,35.592425305496334,24.102755248074736
2.5811156078482758,0.04791637475969256,0.07180650089040813,162818322054.708,1394.271398804625,0.0034407072068469934,1.4784069635400225e-06,-0.0332009996887741,87396601.42829902,69.71477512798624,46.29120427777899
2.4240966074345485,0.0550835490300282,0.1164652314828088,137726245762.51544,291.74655046003613,0.006415318288676882,7.251528374280895e-06,-0.0013870368085180226,5679268.500204659,122.07810769867636,0.40466320424623076
1.8119409846568342,0.03615284614821878,0.043978129880797225,168655136048.6181,1384.97239798188,0.0015899345634668451,2.562545111832703e-07,-0.06354493181927395,215337868.01679626,22.61481064797419,88.00797660133492
1.5203382549442104,0.0661720352183438,0.13349617672348985,153446858345.07272,1758.8207431663848,0.008833713707661018,1.3118969722462246e-05,-0.0010234420659766342,13605073.890493095,105.42732813140951,1.8000511350687638
1.119274932276804,0.03118191689650051,0.15397494615710128,130820606053.8404,1267.9718041324911,0.004801233975213873,9.48575157053905e-06,-0.00047758510126295325,11518467.262977421,42.185121534752895,0.6055644424751853
2.8264732580246443,0.03711519596359855,0.04504328364823122,210362584278.08685,1195.6522622459536,0.001671790299448056,2.826575829108088e-07,-0.1513523398706324,269270748.2849036,37.0933740091573,180.96476756254006
1.9700378017525204,0.02010190573151893,0.06320283381208486,176721792183.19147,378.1281448349977,0.001270497407255387,4.229272215427543e-07,-0.012893941091676782,55661445.40198045,19.64798416667518,4.875562024607487
2.3540189868785317,0.05728838900570228,0.10253006432107029,166687539871.52856,860.9030418047646,0.005873782209605151,5.145635904998451e-06,-0.004364361156086619,20190467.95615102,108.5419095426689,3.7572917948095292
2.681783428693869,0.06279757642523184,0.0903787048143618,131752029800.08102,579.2534526212464,0.005675563622793355,3.863313725592832e-06,-0.007316463209146168,18170566.797023073,119.48196490602393,4.2380865748742425
1.1228746478704057,0.03003018546318814,0.10893177537958146,164989127617.54022,1929.469855839357,0.003271241417483183,3.2347484534134203e-06,-0.0017061402656593592,36479875.439676814,28.8345733298308,3.291946212423486
2.3452421725929256,0.06721105485541519,0.08017800091707836,171857774746.8822,798.8693930488431,0.005388848017835283,2.8868561032027542e-06,-0.006923461670399869,26017380.52327449,99.20950602000063,5.530941622429273
2.1921406572154005,0.04161487558830651,0.11868647536109089,125111735826.98828,1697.0981515337937,0.004939122906166404,5.7979044364939595e-06,-0.008215270238589898,38078125.56060209,84.99392924869139,13.942119936261504
1.6538092114275944,0.023076624935595744,0.15312730231001884,170280287585.6021,1465.4676397641606,0.0035336613228078885,6.90476560049627e-06,-0.0018793076552264289,26874187.02850412,45.87541291894207,2.7540645538953936
2.572389637442625,0.06310861419853078,0.15585331463983307,117112596843.1493,989.0783852809141,0.009835686705167455,1.99092787415357e-05,-0.0024069139974230015,9958592.990530154,198.61456567641395,2.3806266100811726
1.9501819587052847,0.06965944772581867,0.05461591488166573,102058969811.37593,756.6883347626233,0.0038045144676971555,9.45706599929415e-07,-0.019382669354814672,42611318.31850184,58.24303949080942,14.666639797349244
2.169380236533605,0.07309913637665019,0.14042989389535024,185356904469.80307,1328.859299956813,0.010265303965214724,1.686979103822627e-05,-0.0014462597918054655,11998709.765359618,174.81437822155294,1.921875774494297
1.9210801752994098,0.03752749610171206,0.09940157815533544,105927512798.03633,675.2751286959088,0.003730292336728378,3.0714834610985046e-06,-0.004905000029512263,20991397.246766213,56.25459665085755,3.31222452618233
1.8672525327673226,0.06439535012713746,0.14110818184384483,161447928371.44077,871.9607816125334,0.009086710775638168,1.5077517842054512e-05,-0.0007773606289221339,7618901.494090041,133.19239212612575,0.6778279815897544
2.5139736529173735,0.0523306246636633,0.08575743461063907,158554436079.10913,1902.691856398136,0.004487740122728002,2.7503629902673907e-06,-0.023107925436530653,74572886.04475248,88.56417437297526,43.967261546342215
2.8287887582563256,0.0655810217625155,0.1502194765651921,185857541823.98007,132.24380229654287,0.00985154676177555,1.8525744315176733e-05,-0.00028980092717855843,1516688.6192816324,218.7633661395054,0.0383243765191561
1.1491168951070976,0.043562541919502956,0.13726800646592155,214735079097.06833,1303.003086355074,0.005979743285878311,9.38944552879265e-06,-0.0003268691068341117,10944830.456825476,53.940678699917086,0.42591145503897393
1.816452532974277,0.031336992307416156,0.053829698863246477,169898635912.34576,1175.1395559848966,0.001686860859188083,4.073257968145525e-07,-0.03392411627878146,141046897.41507798,24.05320604151176,39.865570941027244
1.7201861883903216,0.05216015809158496,0.08834191964205884,124165131519.08154,1368.5047738109579,0.004607928494643884,2.9968026860878492e-06,-0.006240129876809475,34697681.819949664,62.22298538557642,8.539647525614152
1.4466566045237335,0.027334226317785183,0.07884479362491571,159208365270.32013,739.752259166604,0.0021551614329225126,1.1164636867654345e-06,-0.004200015783817907,37787675.500095166,24.47456138790466,3.1069711646146914
1.8527855752852664,0.03493335622852884,0.14129445290853324,116134563701.037,335.50969196930976,0.004935889456568885,8.211725114663548e-06,-0.000745870451627361,5347994.409986015,71.78938657271767,0.25024676547450586
2.7971497624395587,0.024165381669526993,0.09574930693548259,118806388105.07796,1437.322937855852,0.0023138185466886245,1.7677438297101707e-06,-0.049925352234107614,108882075.16564503,50.805961435856894,71.75885394661577
1.2963080909812095,0.04750360625822915,0.09387910852407244,145324504696.18393,752.151047413974,0.0044595962072011015,3.2753084462676986e-06,-0.001147406876847494,13973334.399871632,45.38093357034563,0.8630232842308393
1.9936770076287835,0.03342559856298535,0.07239437329396463,180532790604.77344,953.707162368382,0.0024198252599429686,1.0568476488097286e-06,-0.013203519451001034,65122681.703268915,37.871147368336985,12.592291068889933
1.3869643241945444,0.058219887610593324,0.13360766982317238,104935850950.06586,547.9444957150688,0.007778623521018357,1.157135682245887e-05,-0.0004013312796635827,4387518.563440152,84.69108552269515,0.21990726564994506
2.5564017033384347,0.03856683579322107,0.1511509527738792,164293231268.08487,627.6901227004914,0.005829413975619112,1.1098529223897001e-05,-0.0019170181887193482,10926721.058913376,116.98324196138995,1.2032933820963216
1.3502967241920518,0.07867742122415634,0.049844588613273774,148097496367.31027,983.0855480332484,0.003921643694071328,8.11938095415363e-07,-0.006709452211138715,40746060.66989111,41.56875367339051,6.595965503990194
2.8669274755305993,0.04082263006107567,0.08536535809262197,174577218859.83533,1923.2652766415831,0.0034848384334463588,2.116239102299512e-06,-0.04088987199949751,111209742.10429634,78.42761556316417,78.64207098295249
2.321092882149906,0.0624418907370763,0.11083112427626327,156235495722.25974,790.1308036373971,0.006920504952325756,7.084023859237722e-06,-0.002975744043477069,14346410.090740222,126.09560806795292,2.351227032491734
1.6420849752535778,0.05664594997241158,0.1006076067015132,203193406480.75067,1199.838353027825,0.005699013456057977,4.807065859132985e-06,-0.0018130036740156116,20617647.849358328,73.46237530419205,2.175311342264287
2.6727701007027393,0.06108791293093188,0.0710279279220952,103940414216.20375,454.08890509393973,0.004338947876569457,1.8241539064487798e-06,-0.015242581589106612,23628718.435804565,91.0365297010695,6.921487184602466
1.7744739384736667,0.06564742067871134,0.1216052643240628,123074084192.20244,511.90463757274773,0.007983071943827637,9.837699424928616e-06,-0.0007874382793362332,5614195.354110834,111.2011619392673,0.40309330699452256
2.960533583025227,0.07947322771835542,0.15159347388603736,178840793298.61615,1346.2324845207952,0.012047622670761614,2.307178104636529e-05,-0.0028220264349158876,13093611.348032258,279.9890233723858,3.7991036588601776
1.2157155733362761,0.06378382198624324,0.06471442790537063,109114310589.13678,149.76433221439063,0.0041277335494577325,1.4405642793286307e-06,-0.0005706485592192375,4089581.3660352468,39.39247717546836,0.08546280040057326
2.389810404232901,0.05241290466780049,0.13599722167844264,162288211966.3734,1937.3023089560381,0.007128009414917944,1.0986189627661704e-05,-0.004943475859068718,28655882.859444786,133.72153983074168,9.577007196042262
2.0263533456094995,0.051833773855205115,0.12841653159329114,215618442447.67346,1634.7370694283527,0.006656313457876456,9.147330929693026e-06,-0.002298750802032596,23251963.77338491,105.88113790162892,3.757853149460842
2.1801583211376006,0.0544373241338348,0.08478722391231747,182444307143.85284,1227.1349606572255,0.004615589590522854,2.765074079163017e-06,-0.008402298097986923,41017955.65846277,78.99232101396575,10.310753745903463
2.14563415133425,0.04819637311475541,0.08252572251278449,205188393280.99457,596.2179361203249,0.003977440513790931,2.2573615199825473e-06,-0.0042383507360532644,23384006.977611676,66.9929377801286,2.5269807284037373
1.7926478098633127,0.04021839785799433,0.0836200901763734,167578973472.24176,659.5016413182734,0.0033630660556347486,1.959636024754766e-06,-0.003856422518740346,25224123.077278662,47.32602504261536,2.543316980726008
2.3756280674227153,0.0483290729257396,0.09665149195898387,200871859581.95782,130.53595113399155,0.004671077003267266,3.636243060911639e-06,-0.0007986789177711991,4121300.169104623,87.10942182732785,0.1042563121819305
1.6958661415634104,0.06526374561339524,0.062458407865225524,168178476222.96375,1870.3868278064733,0.004076269642333763,1.3251452289488016e-06,-0.013644291790094198,74751591.11529726,54.265540211985474,25.520103638940196
2.4433997055693606,0.04408042722693588,0.09428494243490745,131315942784.47629,1341.246356802283,0.004156120543597776,3.078871543997218e-06,-0.016131019880204368,50179213.1978636,79.71725014341997,21.635671645829305
1.1028063868576052,0.06406947408643922,0.046615887590654936,190473321972.5782,1310.082184245514,0.00298665540200583,5.408437141121633e-07,-0.005685506510251672,62262992.35227599,25.855565823497166,7.448480787492602
2.0518223806710534,0.05934782620461518,0.04929105853191075,161709968680.2527,1056.1085577582949,0.0029253171751933535,5.922812776066097e-07,-0.03174985874842365,90169252.42114542,47.11751531739171,33.53129753182728
1.0223759978198008,0.03397969986648991,0.12554263886747186,142541733129.8655,523.4450425052518,0.004265901189163824,5.602889429367168e-06,-0.00023346817289116728,5995576.4022467835,34.23663663124551,0.12220775768264053
1.5385843620956283,0.0569991138377577,0.14001589228789396,146082075158.87045,877.2234445545054,0.00798078178361289,1.3038236515113336e-05,-0.0005591613347830274,7247029.445275793,96.39098248908093,0.49050943216006226
2.5662646359499606,0.028666054976278867,0.04563183452125549,129906583615.10869,175.8268955552439,0.0013080846770547698,2.2698150440767e-07,-0.033592841401824065,45355944.012306854,26.351597863296394,5.9065250165623935
2.5475806232002713,0.026145266709118133,0.060181120434581035,141646259842.15485,456.35486046361933,0.0015734514446156804,4.7488957685110224e-07,-0.03739103507369861,73666197.535083,31.46668113301765,17.063580593648027
1.8023601030541823,0.04529786577896972,0.04061234069047676,199529001178.22357,1584.56457706168,0.0018396523575670068,2.528544241506192e-07,-0.061296658313751695,229355403.64641982,26.028370700231466,97.12851345622427
2.0785411776654135,0.030505920460044238,0.11257009285054553,184566302940.21112,1074.432761558658,0.0034340542986785365,3.6263687238748333e-06,-0.004805178356806669,34662425.026948035,56.03191263921675,5.1628410516856835
1.383765571277426,0.0456377171355702,0.06848166717680429,101575719368.99918,425.77229281039746,0.0031253469555872567,1.221421724284707e-06,-0.003031015502007379,16516522.223900557,33.94926799619116,1.2905224198335397
1.8869495499350393,0.02206603407158994,0.13149700401976216,176890774227.61542,917.97242336677,0.0029016173710120713,4.181100558450406e-06,-0.002779671352508547,27238624.543780982,42.98036389967212,2.5516616476254583
2.9070650191280567,0.07764107771594184,0.05129676553297728,201713576323.0376,1684.3832381599352,0.0039827361593223354,8.733337723868289e-07,-0.07830121620547195,143805463.9610624,90.88787280808175,131.88925610403405
1.7054965108590037,0.0670474566809185,0.11559254638985875,154576172017.00507,1878.5585276090378,0.007750186246711116,8.629597801067986e-06,-0.002328750055407863,21457782.839533187,103.76063747784498,4.37469327525646
1.184295505330851,0.027483044815957383,0.045438835799037305,104640068317.19223,716.4567217412143,0.001248797560649871,2.1486475721748903e-07,-0.017643540894781685,89718510.65179947,11.609720904444318,12.640833469382338
2.6278699871233693,0.02582792346346185,0.09088122248710997,197355116711.1208,738.0035598900417,0.0023472732586629244,1.615588397802971e-06,-0.01400134349726241,54547615.502999134,48.421382241937906,10.333041344222945
2.7024519568205987,0.03539519932942396,0.04210185934832423,133110101253.87187,248.86983309758128,0.0014902037037733077,2.2012377114750704e-07,-0.055878789497748604,64318302.56899091,31.613550735289312,13.906545015999573
1.3297143707186265,0.020598701447028227,0.08283703529892925,204128818615.94937,1890.6208917107308,0.0017063353588795823,9.757357983043522e-07,-0.007439122734166268,106714916.20655371,17.81116838654492,14.064560857215
2.493970388921495,0.029519715390018526,0.12384489925720596,211627243968.80576,772.5088228459828,0.0036558661785782366,4.67267195611426e-06,-0.004039421782807421,25531573.26245612,71.57333266258458,3.1204889664149817
1.2376104313828369,0.07799389912769801,0.15785801418451584,152877308824.47632,1841.6809879495952,0.01231196203480585,2.5566971772605712e-05,-0.00029773007909170217,7036484.147785957,119.61368926376164,0.5483238262039172
1.4771859313584725,0.040513737564428005,0.10497583568425264,189411673010.8775,632.8111067480272,0.004252963457518328,3.905611909384729e-06,-0.0009190994374579616,12562599.497313634,49.31697962031793,0.5816163322292619
2.819157854789256,0.05351171996944851,0.14819831316475116,155105351085.70502,184.8837000512838,0.007930346634016799,1.4514345119172876e-05,-0.0006133541746896295,2660932.375508624,175.50165718524644,0.11339918925852019
1.3369512392761456,0.053296070850150104,0.11593498395800672,103501600362.37758,1152.4278222710052,0.006178879119036942,6.920818587591752e-06,-0.0012815473411189504,12904950.645225698,64.84775174994141,1.4768908114629091
2.8501593284628433,0.02277771271481304,0.0532787527568028,138339274506.69586,1866.5618870210176,0.0012135681240980074,2.8707211811440863e-07,-0.36273715876780366,493678907.641683,27.152070700541252,677.071355562274
2.0951792560264026,0.07406533974700003,0.07146009099466157,110929048849.82607,1740.7797644535306,0.005292715917871146,2.25229082633491e-06,-0.02136074396510656,57859425.41469475,87.05013050344027,37.18435084813037
1.0836687756578331,0.04222388045854136,0.041856923487206044,193639384841.11835,726.7213463140549,0.0017673617336861002,2.5803511413136545e-07,-0.006169697030512495,63873832.58763539,15.034592599791754,4.483650532363868
2.7546212839409696,0.04461943357315988,0.12642371509089032,192860071445.43384,767.1257728362566,0.005640954557570071,7.513260584185761e-06,-0.0036885887754046563,17778641.534867678,121.97874386530671,2.8296115150074383
1.5467854062971749,0.049870594991660216,0.04470165073126904,218740964751.01474,640.2836832422215,0.00222929791907777,3.712222395568458e-07,-0.009726963089415511,59629625.15415055,27.068727077017517,6.228015753652102
2.173910077761913,0.06642213976014666,0.13974731270509982,211435093105.7926,417.4666239245434,0.00928231553560306,1.5106435890405407e-05,-0.0004475959511004225,4197732.824075782,158.40451640933568,0.1868563705881884
2.9881608632106027,0.06226482992396756,0.06380558300294158,187433213647.60504,446.12442249273533,0.003972843773877753,1.3478377128018105e-06,-0.015705888459199183,31553755.344870836,93.1912458038986,7.006780418595552
1.928995177822485,0.021303088247859245,0.11962160800408958,130279639299.75061,485.0840592149928,0.002548309671661946,3.0387168120254663e-06,-0.0029317193820578113,18417791.69843448,38.58806498563921,1.4221303383278734
1.6519785274161694,0.0302512897817867,0.10102083746353827,110336460642.15823,1386.2454826876135,0.00305601062810827,2.5989357504399295e-06,-0.007264696769490036,44507168.68080702,39.63044190694513,10.070653079800861
1.7318884807611248,0.07204950073348351,0.15261615406608325,154159461726.3519,708.8711369355949,0.010995917704325698,2.134279264448713e-05,-0.00037306489081996894,4389413.364616604,149.49307017902404,0.264454933306305
1.660836317721548,0.029259975287818117,0.06563276847501871,216087586514.02155,1599.6674590351797,0.0019204131836501354,6.893739688650444e-07,-0.01639850496561314,126471418.98158444,25.037511889433635,26.232154770318147
1.3605777007928852,0.05032300096904793,0.10614835262365957,106246645726.0461,1625.703309806559,0.005341703651943262,5.01562503462157e-06,-0.0025612371482731057,23405764.992079355,57.05225255366169,4.1638117091471
2.9558431518635926,0.07374489336359635,0.12823646225845173,206271115408.20898,901.4139582943543,0.009456784234574371,1.295941182037301e-05,-0.0029028424886419295,13182625.226640377,219.4292517095832,2.616662737991756
2.249765552000813,0.03329480317374009,0.12404159838985881,148666125744.9088,1060.8610296626157,0.004129940603746465,5.295381665986321e-06,-0.005114930511678461,27953477.905458976,72.93747510162815,5.426230449271942
1.7725347730110497,0.04188773776384526,0.08091372269812258,192280991525.7248,1538.9560461677734,0.0033892927978754527,1.8491502826542483e-06,-0.008034903989242845,59681668.88542053,47.15996882017868,12.365364074622839
2.940011731978143,0.07566834988588603,0.059190285389112834,162741747361.5662,1126.6770492461765,0.004478831224668837,1.3076283241468332e-06,-0.04484789766891998,74969502.74749662,103.36735831669986,50.52909701051324
2.624776066505209,0.043805932405658055,0.08922955060496712,174865528976.846,881.0331896034272,0.003908783662388435,2.5934495239728607e-06,-0.011710239589151218,39781892.249888845,80.53850217854237,10.317109736250226
2.7240323279965777,0.05656983266985362,0.10595797521122305,174184264326.22763,211.23376340607712,0.005994024927735386,5.607956031341586e-06,-0.001457019403494844,5435939.931264098,128.17415377205305,0.3077716919558935
1.4930080857952328,0.05746940956810506,0.08857761921629925,181986546190.57208,1726.7551338255507,0.0050905034773091554,3.328338577228582e-06,-0.0031624902764392274,34305158.0410692,59.66127839127186,5.460846320514821
1.4978591215046884,0.030966805920008115,0.10651328394486723,101910433057.51341,381.2722785189818,0.0032983761918234196,3.1183617195054307e-06,-0.0013439457646466806,9753342.762155218,38.78294749085136,0.5124092638927752
2.4904040188857453,0.04111838637386729,0.11614233792704334,125431018377.34157,927.0671449994952,0.0047755855252484295,5.368173072711737e-06,-0.007088721321710404,24975549.821073905,93.36112846919856,6.571720637415113
1.6202029806615617,0.07332331449794896,0.0674029628912004,218117586637.73328,1645.1576020070886,0.00494220864616507,1.8711034749810364e-06,-0.005714865914334549,48009603.80757185,62.85794225960871,9.401855103418674
1.5406629516324877,0.04120566430531498,0.07240269404633617,119564303692.352,1748.06148661587,0.002983401105673756,1.303286368322009e-06,-0.013674673808985646,74808202.8299052,36.081862093962,23.90417062752255
1.960630680308092,0.03506576023661653,0.08072497564950115,118234799547.0885,215.9390093583068,0.0028306826412321153,1.5371837366101303e-06,-0.002984874888866303,11116780.867309257,43.566897376029544,0.6445509265602756
2.4397064110239333,0.02535178025825994,0.1106155953071023,160769926256.55527,1799.7399897197276,0.0028043022653622667,2.8594091243021e-06,-0.018950475123467307,84929271.86628518,53.707142589738105,34.105927903893004
2.0647253922351423,0.046344053185831235,0.11735671690144217,163550742253.26984,815.8856469688461,0.005438785929794975,6.242184805680148e-06,-0.002344799933806798,15835541.745614268,88.15235538560438,1.9130886110064667
1.0523732677245807,0.032248275964980415,0.05625056779683694,158803880645.26825,278.6476441083222,0.0018139838334992379,4.783061746560689e-07,-0.0014252020732370275,17243130.329282057,14.985556541504364,0.3971292000857942
1.7401156422876118,0.04582209130992622,0.05172123384202792,173440774897.3228,1694.7117816808484,0.002369975099771449,5.283239400985305e-07,-0.03248309717520949,144348591.41050282,32.37364133211387,55.04948748831141
1.206060508769472,0.0735780027774754,0.06659308000994577,166028251316.1757,1498.1950736613505,0.00489978582593243,1.810731492584172e-06,-0.002914193282266561,33226340.64116436,46.38908976077129,4.366030019188764
1.7583912519298883,0.025094062051144405,0.07049933995135561,150585897268.83624,1576.7306984844304,0.0017691148113040415,7.327315204746838e-07,-0.025897249241152977,133377698.35273038,24.41974866167448,40.83298788482852
1.9922434745333981,0.07701808187849038,0.07756755245216204,219344889732.8167,387.5516471728011,0.0059741041058747136,2.995378556826978e-06,-0.0015547348521333635,9997015.741973927,93.42967888072982,0.6025400528612463
2.9755934765842085,0.03475764166615617,0.05659374519233602,170948948382.8667,905.0359449688766,0.001967065115940964,5.25018202556666e-07,-0.08855734201116047,145145476.28413817,45.94751109703079,80.14757771100261
1.3094892725297502,0.07093992867841134,0.09238199660591137,195849893830.10547,1852.1065781860923,0.006553572250392591,4.660918768946262e-06,-0.0015186429556610496,24035531.69588962,67.36738558530635,2.8126886080958
1.8981167520140687,0.038721206016067364,0.13766089031344603,121475057997.73196,1454.1325339922068,0.005330395694182196,8.417814504873018e-06,-0.003241641893466258,22568782.972723186,79.42404989162846,4.713776940841385
1.3574827743366096,0.03447660181414077,0.1421915841094498,114059411442.89397,1911.9193096375288,0.004902282626663407,8.25971162199173e-06,-0.0016922139691061726,22339986.12159546,52.23989913190785,3.2353765635724563
2.3614452255990823,0.056194595351063276,0.15040608205209757,170741500984.13037,1146.7202174889098,0.008452008919256444,1.593343809830657e-05,-0.0018502109703872754,12780894.536866957,156.67780545642705,2.1216743263628635
1.2835769902090703,0.03370516955796104,0.06515841870363565,117335088497.90169,1786.1736193459988,0.0021961755505346594,7.770104836812091e-07,-0.013810627192923274,96130069.42665954,22.128839164539308,24.668177958622035
2.844162452744898,0.07675297437317298,0.09281253990843882,128746469431.01382,1804.5579421198604,0.0071236384971014996,5.113684640101157e-06,-0.02102052230264616,46576617.9910677,159.04716335201582,37.932750468747784
1.7485215564374665,0.028478863066171697,0.1012479627143423,153814855172.39337,1078.618158304916,0.002883426865870612,2.4632034319057656e-06,-0.005072953519384799,38760978.732904285,39.57761214637765,5.471779782245274
1.6367506690640443,0.031673975209392455,0.10710018393981813,126460361692.25813,804.6497488754809,0.0033922885710311714,3.2425895336681313e-06,-0.002868050609130363,21749919.389263835,43.585795118104606,2.3077762023989163
2.8593012729562552,0.039935660012452856,0.06986382492509467,187784073528.28076,1274.6650253987286,0.0027900579593781107,1.134845387465724e-06,-0.04660785489340355,112186772.41173568,62.624287757741776,59.409402541480496
1.2894122392511047,0.07003745071138104,0.07587294613660116,182345905342.1501,1666.9298081007958,0.005313947725369472,2.549235324139676e-06,-0.0025625094730750667,31985719.588014014,53.787173501280925,4.271523424209492
2.5007519169881003,0.02472886936083557,0.10324005577111053,198895061932.1864,1528.157161891395,0.0025530098519691707,2.2676065649571843e-06,-0.017663098512832365,86993972.04948102,50.11788760900107,26.991990493578026
2.575713827835502,0.06074189800573748,0.13939833856790468,178616507363.1539,571.5920948948395,0.008467319663460928,1.3711340152901193e-05,-0.0013294018832493678,7483961.0802418385,171.20372988375613,0.759875607403651
2.3127451009760245,0.03796653861409344,0.12617502498012312,193413776489.3423,1101.938323212827,0.004790428958042049,6.355357079950439e-06,-0.003696510805289008,25298134.89069752,86.97047266864062,4.073326918518267
1.0867103616976994,0.058812886692577795,0.07546259379684746,112590649803.91116,1594.1365388368088,0.004438172978502014,2.106136119624612e-06,-0.0028757883752170105,31035205.190956067,37.8606172175473,4.584399326895575
2.1545894431208374,0.04435398512393907,0.13450475818736907,114782616266.9025,1729.1938392131376,0.00596582204374159,8.99423736084342e-06,-0.0055843874647924854,27858101.40911099,100.9030929806182,9.656488399898238
2.9161579355363765,0.047608153993703106,0.06288634706975409,185042648477.68683,564.93738666509,0.0029939028953983125,9.866638140493067e-07,-0.025578268905592966,52501115.328370355,68.53594544013282,14.450120390942622
2.000970817284346,0.03692262640850094,0.10948735191872908,155690935171.92496,1166.5925641960014,0.004042560591351303,4.038342930675903e-06,-0.004955114455666087,31643952.152809307,63.49900929762199,5.780599678720175
2.5257575434441066,0.049619483679336954,0.15926963098288882,128319429680.0518,347.56102305797657,0.007902876855169471,1.670590149549538e-05,-0.0008708080825570729,4184617.698189847,156.69189403005493,0.30265894806069116
1.8742592357417815,0.06944088769281627,0.0986166055119026,165387780700.4831,1036.5394879150635,0.006848024627998794,5.549887332477966e-06,-0.002478369121151686,17260421.557063296,100.75454123406925,2.5689274597030747
1.2481383635438636,0.07808945345119186,0.04746855694708957,209349288623.42667,1479.3639341378,0.003706793668115001,6.96032029338957e-07,-0.006580232727711145,62962877.45763502,36.318742355889135,9.734558975609067
1.275326027497872,0.0321316650017885,0.1304934908462004,175661232869.35196,1412.3338300614255,0.004192973132784065,5.950021456310129e-06,-0.0009342977827756744,19751446.500165913,41.97715098538465,1.3195403659654659
2.9333622363830667,0.07107695027394666,0.05409851593936968,158363799031.54465,1518.188155176256,0.0038451575273168895,9.377856727866733e-07,-0.08600860998612192,128452646.89814313,88.54203308606732,130.57725292410456
1.3703702447732584,0.027947534902596813,0.07398694652962075,179263668998.52936,109.23131917603185,0.00206775277047314,9.432516503091359e-07,-0.0005541404200699495,5870601.936981746,22.243656931100304,0.060529489093001015
1.1567270365111966,0.06386407424978399,0.10457363801910008,171509667256.70508,1405.6795964765386,0.0066784985830218415,6.086141230807372e-06,-0.0006947476967621571,13969067.724642783,60.64281901312218,0.9765926620376335
2.950898911344147,0.0774297823386892,0.05496187934167775,211191670593.61926,178.12924338747985,0.004255686354351407,1.0713010128343616e-06,-0.006743551272841987,13483716.681648755,98.58108680611,1.20122368597602
1.2245838548143226,0.046656130713799045,0.14458165377891735,214231300322.82773,1931.3916143840818,0.006745620537526405,1.175078924724582e-05,-0.00046963960449313805,14550403.131653015,64.84553730752617,0.9070579939007035
2.654042778904257,0.06908777372321699,0.15664819627399507,177931027615.85968,1216.535491985191,0.010822475138327854,2.2130750799585856e-05,-0.0019252159470979626,11426992.90055299,225.47799912738665,2.342093529380555
1.341647441716586,0.06518563156775864,0.1276817747379519,199710785525.73175,1296.2575257759631,0.008323017125985684,1.1307259608286994e-05,-0.00046208979063604963,9819090.191774791,87.65745388036989,0.5989873686962185
2.119507188432695,0.0445034505665908,0.10768973330179513,169075513542.73682,441.7098327760789,0.004792564722525787,4.63164583863495e-06,-0.0017902118817806182,10883809.28827098,79.73932173631543,0.7907541909350664
1.9833354161451644,0.026723614080772236,0.09760623526288784,164792672870.41846,1005.0305193964633,0.002608391363042477,2.070840412147525e-06,-0.007658821840670438,46976034.399680264,40.61052251049103,7.6973496924939875
2.9830555649770574,0.07432930167586123,0.043372498172153065,186610332176.64044,933.5025178522313,0.003223847501073705,5.053847335008139e-07,-0.08758313029815197,119492090.63789581,75.49279239541507,81.75907265470491
2.2059194362242263,0.06750011366567416,0.05817678090920038,209145047096.00708,1830.4582337522565,0.003926939324074048,1.1075728938136135e-06,-0.028274023080775923,106046623.13896349,68.00071747180812,51.75441834950763
2.372138401379674,0.04908727021159006,0.13277350189106182,216988375018.40353,834.7645356514713,0.006517488764265615,9.574627017102846e-06,-0.0017877404859739238,13729779.534080055,121.36402521945894,1.492342356639358
2.12015487262597,0.03674782348618326,0.14563549833092412,129541030934.79411,1470.121780419921,0.005351787585987137,9.45915003841848e-06,-0.003811319465878837,23994186.74255478,89.07095544236498,5.603103758926898
2.016354373847353,0.06773755385580861,0.0776701506922517,136685689093.0688,542.9227248488031,0.005261186015505169,2.644908830182127e-06,-0.004103775526658433,16073791.377157208,83.27606115680874,2.2280329911012284
2.6656097913052337,0.040681731393672725,0.04307193176899242,143020562662.46283,1208.9931467032854,0.0017522407588327486,2.7089515186277925e-07,-0.19701196119820402,256202601.8744024,36.66570246922919,238.18611090720225
2.7834542390347785,0.026360463582715998,0.14929065592923285,152346166625.45764,240.32891356571506,0.003935370898862327,7.30919714808926e-06,-0.001551442980384774,6831609.964977957,85.98830976330774,0.3728566059350277
1.2116712982771045,0.07911760326114853,0.11039028427685474,122653054422.75237,942.102232455435,0.008733814715301595,8.86919966074582e-06,-0.0005135330986130388,7103939.887531149,83.07272402775914,0.4838006786431009
1.3743417983180422,0.07603784896307911,0.05026209108819763,130676803187.83884,1976.5708030753901,0.003821821290732896,8.045818570399575e-07,-0.016266969392967665,84849141.58795275,41.23203665261483,32.15281675666089
2.0690065573514795,0.02248557684543056,0.14406425226894867,151244101150.64072,341.9052137577071,0.003239367815072939,5.602623980454012e-06,-0.0011912424166293971,9094992.56856866,52.61284502081509,0.4072919930949216
2.6751069756974353,0.06320983032140148,0.09257444072869406,100880770512.19016,362.8125614439693,0.00585161469055939,4.1790413614801725e-06,-0.00549160714740934,10749986.04889828,122.88150793080075,1.992424055595592
2.161070148505975,0.05567257776565458,0.09899735765114717,200734643086.90546,831.3373741828162,0.005511438092427811,4.5012267733521605e-06,-0.0030953475561482768,19756448.814332534,93.49824404454299,2.573278109511506
1.9431887660878542,0.058471811981890304,0.10969641005462585,212336367484.17975,1817.640943138909,0.006414147863802424,6.431948395661203e-06,-0.0032551040880256102,30119166.95645154,97.84161557279313,5.916610464574188
1 L_m b_m h_m E_pa P_n A_m2 I_m4 tip_uy_m max_abs_bending_stress_pa mass_kg compliance_j
2 1.8314998429486489 0.02288848310526338 0.0815229398597667 172594545239.26154 1204.4650264605164 0.0018659364316716727 1.0334161957807233e-06 -0.013829015619417438 87011299.20020096 26.827078910236825 16.656565663964518
3 1.485780501096186 0.0703451958583708 0.15227975734470864 134603011411.74176 430.61187485571196 0.01071214935567871 2.070044708657494e-05 -0.00016896401045085464 2353277.332637697 124.93983570435536 0.07275790932338262
4 1.912481924636748 0.047325586440789394 0.13412538162234836 137384268072.70396 1491.016058175157 0.006347562341872312 9.51585181099103e-06 -0.0026593065863062455 20096154.678896487 95.29584621803525 3.965068823793571
5 1.9005563087063533 0.03892541267357975 0.07695136609138858 204751900490.29495 1095.028618079069 0.002995363680903012 1.4780903506148138e-06 -0.008279755549199318 54174082.80724987 44.68893012378931 9.066569277072231
6 1.5947212929865011 0.028377670567845643 0.060651928533480566 143550315733.9896 285.4873970880711 0.0017211604472276289 5.27629829547462e-07 -0.005095497266108835 26167185.46189781 21.54645402864454 1.4547002513707934
7 1.07237473124558 0.060835540739851784 0.1272283305923341 194807902395.3725 841.5626396886561 0.0077400042890132725 1.0440651813465087e-05 -0.00017008684513586912 5498690.043104498 65.15645240127142 0.14313873436885768
8 1.719404317170917 0.05385550434598768 0.12141457596271288 180228444125.88403 780.2860073349921 0.006538843223426135 8.03269604288166e-06 -0.0009132337131101088 10139378.371577015 88.25688485115214 0.7125834877663964
9 1.8443936254162967 0.06781937032695569 0.0906637700929121 206850241685.69434 664.8332582220359 0.0061487597991691754 4.2118590646042665e-06 -0.0015959616691765433 13197640.606252536 89.02475701575838 1.0610483965161202
10 1.1133087091552474 0.07276333760631655 0.08972554699620917 109961391102.16035 527.9000060948273 0.00652873026799659 4.380056467488244e-06 -0.0005041471272986309 6019683.850035296 57.057664296625695 0.2661392715736369
11 1.7653262594338854 0.05980665036951069 0.10875237157317413 126953548532.28677 896.458597440227 0.006504115063531939 6.410389856402397e-06 -0.0020200152084294265 13423924.977437384 90.13279816085453 1.8108600005565714
12 2.4184005785926237 0.046583251237609244 0.1568083429212308 150170594507.19855 1012.1064382265317 0.007304642434452879 1.4967733662081683e-05 -0.00212299367486471 12821461.97409473 138.67457919566064 2.148695566644777
13 1.0122542173163664 0.0257631638203873 0.05996802707039356 122101793297.94275 196.1163789614812 0.0015449661053999694 4.629959923088148e-07 -0.0011993946892279361 12856299.886894634 12.276602878045393 0.23522094339701388
14 2.99885756490169 0.034208042406339394 0.06827291867439919 212556641451.73248 222.15212458178422 0.0023354828972184083 9.071777376802585e-07 -0.010356897291806043 25068733.85015985 54.979677349072226 2.30080673745004
15 2.5090373124694736 0.0644222822855815 0.06190015136572917 213676707662.4631 1509.0204900058407 0.003987749024803228 1.2732978139795645e-06 -0.029201695277680767 92030965.56296098 78.54247710356118 44.06595651692707
16 1.8803275265391401 0.03546362707534823 0.141638741145562 188165807683.9365 370.8129344289211 0.005023023495407992 8.39746263160384e-06 -0.0005200502893437317 5880203.563159812 74.14269535721769 0.19284137384215863
17 2.2767602373665152 0.05078719396396178 0.1319282799922206 113377538465.96469 502.63221905928657 0.006700267145296765 9.718218816358546e-06 -0.001794598357182278 7767635.770409364 119.75097925673768 0.9020229545906786
18 1.8387426022120184 0.03598261817712693 0.042756728124461955 139276750527.0553 693.7486407804699 0.0015384990226057391 2.3438235152907022e-07 -0.04403927624425049 116351676.43422394 22.20689401616478 30.552188035404416
19 1.3011131084669427 0.05481935324204158 0.08484687238436737 115209362593.83258 1734.3755729455568 0.004651250668721058 2.7903596005967974e-06 -0.003961130049810408 34308668.80130053 47.50665524433302 6.870087199651787
20 2.6198549887683336 0.07887793897606994 0.13647070121249977 207909603351.69885 1561.5862492494184 0.01076452764226103 1.670677321550229e-05 -0.0026946933734432015 16709370.142657414 221.38178634570068 4.2079961179124314
21 1.9163836401280836 0.0692936197063689 0.09353918410176623 173905530654.12637 1950.663751507745 0.006481668650791817 4.725989305697665e-06 -0.005568040616383383 36994376.79622444 97.50770554040177 10.861374997301908
22 2.460080176958872 0.03952084747455992 0.0688781284182868 107735300872.5662 974.7000408118613 0.002722122007552264 1.0761901586120548e-06 -0.041720592641427086 76733069.55438615 52.56861136183609 40.66506335029402
23 2.7755844200326263 0.05125709604641546 0.05692408518502546 175283604103.8452 1997.850111329783 0.0029177633016831852 7.878815513196515e-07 -0.10311046485275611 200319153.39364558 63.57321213773421 205.99925368534448
24 1.4102930025734708 0.022265414249600112 0.08705755680218691 186941727856.41827 117.79790590776206 0.0019383725657587836 1.2242467456018725e-06 -0.00048124824409759455 5906829.594940002 21.45933513707948 0.05669003537648415
25 2.7187095888004675 0.04325268945427481 0.08898072117551989 134150937902.88864 326.1913240502886 0.0038486555004221762 2.53933287372463e-06 -0.0064139601803737635 15537513.364638543 82.13750641195135 2.092178163641946
26 1.5015451743314063 0.0280474634849621 0.11212059965520282 163640968179.4723 1011.4454299974409 0.0031446984247413554 3.294341222963827e-06 -0.002117267779164323 25844473.813744865 37.06696794352397 2.1415008193165854
27 1.5613872984144939 0.039382290755115124 0.11412904353427888 149887803869.72943 1234.6779455652597 0.004494663176070163 4.878746594076833e-06 -0.002142346946215878 22548738.685472872 55.09059345107331 2.6451085262418284
28 2.2823683011586327 0.021672540627220464 0.05066818292659669 184397309151.04816 1023.8895143480386 0.001098108252984105 2.3492788514504826e-07 -0.09366986044671798 252005249.36306617 19.674356622635106 95.90758792183861
29 2.6010016269455036 0.06835079352389664 0.1545043674209379 186248249676.83844 589.1393859193188 0.01056049611612879 2.100799452968336e-05 -0.0008831650596319473 5634882.319220892 215.62276049831084 0.520307320896964
30 2.6988235184899976 0.050858874149295734 0.14880865969476118 102787761774.47253 1136.1743909684308 0.007568240895741235 1.396593804751516e-05 -0.005186037815692381 16336069.803628998 160.33897020574037 5.892243356783542
31 1.601688330241449 0.03963062111434279 0.1144439338431775 113729873278.4416 1702.5081209908894 0.004535484180973879 4.950259498266031e-06 -0.004141898486083398 31521147.53931131 57.02579186458539 7.051615808876856
32 1.9382531257107587 0.03620970064654632 0.15745742612342728 141534717182.76892 1897.3497040557022 0.005701486264504984 1.1779670221306714e-05 -0.0027622405372338702 24578642.735462748 86.74975005098388 5.240936265851348
33 1.5591287409274512 0.049392939146356715 0.06940672689731209 100163372270.41394 1158.927649116863 0.0034282022379867358 1.376221431308448e-06 -0.01062144848682015 45563969.61218766 41.9583178158119 12.309490325046339
34 1.0169440865973296 0.05593646414679583 0.07417492434149953 100476764002.75151 160.82272485226002 0.004149082996019581 1.902326686036506e-06 -0.0002949623926723835 3188500.632999652 33.122175528188606 0.04743665571851501
35 1.2608420992915117 0.021894964398804215 0.040383667280905984 106701680904.53453 680.973354795578 0.0008841989574085911 1.2016562860306466e-07 -0.035484561670924356 144273416.82930407 8.751456866755749 24.16404100449994
36 1.1681065315811268 0.03651047386470185 0.06101704401387274 172176203613.8894 1116.1525285212006 0.0022277611907698634 6.911776980931584e-07 -0.004982953168829409 57548956.32287725 20.427759822268623 5.5617357788916735
37 2.613091893660169 0.0428529520046492 0.08746146285403349 188757426541.5191 1856.724475458743 0.0037479818699403056 2.3891846138442986e-06 -0.02448705173017026 88805359.56713 76.8814951791214 45.46570827923148
38 1.957399449788186 0.02352144812631788 0.13224525759397504 144858300254.10114 1813.4632198003533 0.0031105999664482295 4.533390505297857e-06 -0.0069033416455300395 51774414.247427806 47.79619030326978 12.518956167884774
39 1.0754425740145133 0.05632837492058661 0.10197971033879796 127852674408.22131 1402.1610993072868 0.0057443513582566335 4.978371458644394e-06 -0.0009133583838071284 15444776.195958031 48.49510208452314 1.28067559550053
40 2.748190193991543 0.029189783685797673 0.13914471791153568 194550648608.6056 1991.810225336548 0.004061604216859064 6.553145407482807e-06 -0.010808976488024223 58114120.24030992 87.62217791307721 21.529429894268976
41 2.737376665709003 0.059793119208386175 0.15846534399138273 197171418728.4136 1360.1770486512287 0.009475137203674669 1.982772363055239e-05 -0.0023788171016291743 14878578.766606314 203.60560296298277 3.23561242457504
42 2.127996843275138 0.07648227551987294 0.065583255277641 210719969283.56403 1765.8392275775352 0.0050159565996347 1.7978707338303775e-06 -0.014971960976924529 68537246.1786959 83.79042750871774 26.438076006813407
43 2.339542531006592 0.05110218729810469 0.11375155805330195 217519353948.91022 1324.3401998970633 0.005812953425091065 6.268019011143268e-06 -0.0041461301601332 28114318.46768957 106.75726638477374 5.490886845070045
44 2.4807541533989843 0.07280280445677859 0.1434690996526244 188989500502.69434 1030.2910044573773 0.010444952807600093 1.791603828409672e-05 -0.0015484963132998005 10233637.532757176 203.40417646715596 1.5954018220281971
45 1.611259544606639 0.020965647782533448 0.0793032577437884 132195515076.3166 301.11512726835883 0.0016626441698637357 8.713650254441947e-07 -0.003644945025297345 22077962.1869384 21.02976761062358 1.0975480851785815
46 1.1380693108621813 0.054688929246585666 0.1302823502190609 172923054616.7614 1611.8077500652946 0.007125002233209116 1.0078013308574489e-05 -0.0004544334545482174 11856666.740908664 63.65365909430245 0.7324593639297616
47 1.1970560162717296 0.07686991602122166 0.07875653775878153 161018911947.34885 236.11945674620944 0.006054008443639709 3.129212149325244e-06 -0.00026794277217479195 3556868.926398274 56.88884975564729 0.06326650180498523
48 2.2366756486113366 0.032494419533240844 0.04880067870206303 133425120710.35454 1317.3621792082665 0.0015857497272517274 3.1470607277950625e-07 -0.11701734408260855 228454093.01701942 27.842441227927658 154.15422340582876
49 1.5799282239183674 0.07445087941133813 0.07008585625845357 190051464709.8472 885.9142139521327 0.005217953632738504 2.135894201675166e-06 -0.0028690064822059374 22964113.163278602 64.71533889136836 2.5416936225070463
50 2.875760889847622 0.027160509123923204 0.11772326594936802 198436241667.45178 1085.3627463884377 0.0031974238389158483 3.6926960907836247e-06 -0.011742144368100255 49752673.59576146 72.18095743013201 12.744486059850818
51 2.43133244952272 0.07060028264520024 0.10016988958032483 196552139300.14716 467.0925737092751 0.007072022516909432 5.913393489384802e-06 -0.001925307900863989 9618729.896012884 134.97633695857036 0.8992970225973624
52 2.454532752038515 0.060416097529133087 0.09619491473650338 212976693312.94727 472.14750470019595 0.005811721350527229 4.481545039166519e-06 -0.0024383895768227836 12437723.079946205 111.98072414463617 1.151279554183844
53 2.2659447659220726 0.028952339083094296 0.04094356756849021 124497478994.26439 1125.413412036063 0.0011854120515145112 1.6559966563004738e-07 -0.21169898568446774 315251844.6210834 21.08571413368349 238.2488778037305
54 2.8870356750940136 0.07720109864779011 0.07803697159449194 118508819724.02277 1241.3343766667094 0.006024539942241167 3.057338015981658e-06 -0.027480830284222508 45737022.472930476 136.53553465334076 34.11289933114898
55 1.1291014037948819 0.03573057699007314 0.052549547438675834 183667874579.9599 1353.1837966588705 0.0018776256505511077 4.320815517243893e-07 -0.008181547419697236 92910114.81121816 16.642233599032494 11.07113739993049
56 2.2414313057299413 0.06872856088386628 0.12359238421025875 146548487465.68164 812.8953468340021 0.008494326702976963 1.0812624845355039e-05 -0.0019256493507311863 10413354.435320249 149.45968087623032 1.5653513968432986
57 1.4065306561811344 0.020273390641434193 0.1040998919792323 135341893943.94872 397.70883693499695 0.0021104577758260788 1.90588187213665e-06 -0.0014300899817837975 15277023.517729312 23.30212494816057 0.5687594233676251
58 1.826249320085565 0.04697611579152199 0.11924746491239926 144621923926.2337 1653.5705281560415 0.005601782719570324 6.638092864183832e-06 -0.0034970690839348415 27124305.438361306 80.30747728062661 5.7826503721203
59 2.2246456016622407 0.05005609518099281 0.15198244049392126 197936724240.38977 142.72425932125824 0.007607647507203299 1.4643873337184473e-05 -0.00018070772012295034 1647654.2683857938 132.85590859228773 0.025791375508181322
60 1.042833035705912 0.058779886893946726 0.14493211466677136 126379582748.83847 1972.5755796896055 0.008519093307413338 1.4912188568033188e-05 -0.00039567484010969616 9996355.198026434 69.73933669156939 0.7804985270979758
61 2.899760811553612 0.0318220486590499 0.13490142046062267 194336063708.38275 1659.3238440922435 0.004292839566072884 6.510231879122651e-06 -0.010659738945541567 49852093.38463715 97.71843236028197 17.68795900413583
62 1.780938884510343 0.03761604152904589 0.11829859744482052 216411005745.66534 307.6507833259193 0.004449924954312251 5.189561130770031e-06 -0.0005157910996826229 6244907.491086512 62.21159841665765 0.15868353584989625
63 2.4755986030522696 0.07137351869202158 0.05303918024990824 138485060383.08636 688.5633491549236 0.0037855929229763273 8.874548585343163e-07 -0.028334407686754395 50938325.87525222 73.56712713198132 19.510034653112616
64 2.9282979381162413 0.07048741960062826 0.06795280784918846 205214703573.28278 479.0341318296734 0.004789818079906613 1.8431156484791915e-06 -0.010600587323396578 25858691.500124387 110.10421309763807 5.078043145347921
65 2.102098815519008 0.026402623716520364 0.12228369270545006 151914192477.86105 253.96104698542044 0.003228610325168604 4.023198635307189e-06 -0.0012865758997511547 8113108.99264617 53.276834831428495 0.3267401625270126
66 1.438691137842491 0.053003422601885564 0.06601178728785918 110575643852.93709 942.6032728618675 0.0034988506583241777 1.2705364910413264e-06 -0.006659839671566904 35229044.54530091 39.51505866290807 6.2775866711542685
67 1.414403183805858 0.04882944216761645 0.14845767749078817 149309506519.0759 610.60676382933 0.007249105577375095 1.3313998479414166e-05 -0.00028971038864845423 4815030.022969181 80.48729036581547 0.1768991228603701
68 2.0353686403612703 0.02332481098639935 0.15539943358306796 179856019927.0757 1945.7396345704922 0.0036246624157185796 7.29432621084417e-06 -0.004168526314270902 42185389.05134458 57.91356507087033 8.110866867426946
69 2.885249561289233 0.07502641998074575 0.05528161931795067 147988357964.81046 606.4353783401605 0.004147581988164274 1.0562707308145347e-06 -0.031060656337359775 45787130.56863121 93.93945152733245 18.836280877440476
70 2.351414219740206 0.02986481013474012 0.09828716313145244 214871839997.58304 505.5376364361669 0.0029353274656030563 2.3630282440532682e-06 -0.0043149050563687525 24721824.882794213 54.18204032637211 2.181346903643125
71 1.4311801416075802 0.02434680593601473 0.1293718902803398 191379545728.0371 1304.2210211934942 0.0031497923062308235 4.393195391237984e-06 -0.001515782214629715 27483681.44445964 35.387173561097285 1.976915027871303
72 1.8605504351019462 0.042054043274588296 0.14538206538300838 155548354819.96948 404.43763353660887 0.006113903668966059 1.0768594273778364e-05 -0.0005183584838648528 5079428.273869284 89.29552513200956 0.20964367853792554
73 2.838279252077004 0.06353785559677937 0.15836925718719325 157717901217.78394 355.8809369288714 0.010062442994129098 2.1031194818127544e-05 -0.0008177186490437612 3803091.596639364 224.19618192723718 0.2910104789659047
74 2.0111673108402313 0.06485092449088713 0.12682787158977285 111271833012.24095 1986.3541833732334 0.008224904723808288 1.1025011173054024e-05 -0.004390517963427739 22977911.960835844 129.85202719509425 8.721123723830017
75 1.8574788390230883 0.0685463759352212 0.0947230269330848 105468411318.24774 613.2931684395832 0.0064929202138773135 4.854784488659686e-06 -0.0025587398737420674 11113417.203661704 94.67462592082764 1.5692576843799715
76 2.6392631901607957 0.050586520941824586 0.07477415415586579 205756877676.9475 1792.692131769722 0.0037825643151129244 1.7624146452234193e-06 -0.030294940628359013 100369516.79162282 78.36798467615259 54.30950169689008
77 2.111956910778975 0.04150066578872504 0.15400899877518737 152541561771.2149 316.0008881453181 0.006391475986625215 1.263316331472268e-05 -0.0005148988350637654 4067966.312636845 105.96339675824329 0.1627084891851395
78 1.0014264214742683 0.061764448541219166 0.11708875672061811 125718315392.91345 1376.2922971645733 0.007231922489225947 8.262337020810443e-06 -0.00044355257253967935 9765894.263652556 56.85157033130386 0.6104579889738913
79 1.6856494847041383 0.0663499842356854 0.1189675311235549 108626234296.58911 263.5662911187316 0.00789349381460628 9.309898043819937e-06 -0.0004160933527119218 2838642.271951645 104.44946068168507 0.10966818173343947
80 1.1458396446677404 0.026891163534892886 0.08406813850038895 178256591425.2339 1547.380576946341 0.002260690060487984 1.331443190666247e-06 -0.003269483729673584 55975731.78183147 20.33454812056554 5.059135619938985
81 1.6712647923371784 0.04365954073872256 0.12457052002277555 128972751590.80008 1905.650002103744 0.005438691693778223 7.03305071686388e-06 -0.003269007846047917 28205248.893309005 71.35252746187737 6.229584808698369
82 2.1384126500867273 0.05709307593456131 0.055745934746160644 215490403396.62256 970.0232332545547 0.0031827068855056493 8.242174439925595e-07 -0.0178018726648786 70147961.63245386 53.42663422404477 17.268230080371417
83 1.2557271906680043 0.044839093908410316 0.12255691330320925 160243710423.25885 1111.453854069051 0.0054953409447275016 6.878425296936459e-06 -0.0006655582310943875 12433847.260623487 54.17009501334135 0.739737261057237
84 2.588034071579322 0.021174945313894144 0.15511863778583707 207517772888.27136 1141.6966984823966 0.0032846286722808538 6.586170934589154e-06 -0.004826709522544038 34795391.17509136 66.73073769334123 5.510638326422073
85 2.807867229176492 0.0666381271839097 0.10374811733425016 113085413208.90451 1067.323026027182 0.0069135802380109485 6.201292416114119e-06 -0.011230925047518122 25069199.434559733 152.38746078475626 11.987024906801516
86 1.227061247834137 0.029723238153739916 0.1029526971865092 177496282147.6928 1883.8957752126732 0.0030600875370444826 2.7028880727597e-06 -0.0024183380949151356 44025346.65861299 29.476081428746827 4.5558969200464885
87 2.9710431244066564 0.060186340327272714 0.13692333426772887 166872332657.3057 729.6871195986578 0.008240914394982451 1.2875054890388292e-05 -0.0029689908975776454 11527735.869587757 192.20027960848614 2.1664344161680655
88 2.210021847705903 0.051760835238663316 0.13811991091366066 176150450348.11322 1826.625937519196 0.007149201951980845 1.1365509212876897e-05 -0.003282807450351345 24529211.211943835 124.02915618418395 5.996461236693027
89 2.4487914057713125 0.053673046310513686 0.14252070565784486 213317360550.77258 191.55717833418424 0.0076495204349805975 1.2948184857742409e-05 -0.00033946692094041287 2581602.071297701 147.04682721070228 0.0650273255131391
90 2.045876965049992 0.04954726517142617 0.0833183854162591 117833768369.22206 1959.1727057772932 0.004128198135874477 2.3881465726731752e-06 -0.019872809059518277 69920110.49397166 66.29941596578111 38.93426509653193
91 1.3947201725217278 0.07977939782851484 0.1589662855852927 142043082185.1145 332.6222866889177 0.01268223453903037 2.6706968102347878e-05 -7.929515677140202e-05 1380666.7640673867 138.852121502264 0.026375336368659956
92 2.727914991379722 0.07249126009796847 0.07971050709530414 120733477883.6434 265.75679548591074 0.005778315102386654 3.0595046598209796e-06 -0.004868293923976997 9443862.782197664 123.73760628282379 1.2937821927196567
93 1.5080205001189793 0.07929796780301963 0.059519692129124196 104269368673.55035 1047.7877266045866 0.004719790630100931 1.3933583994093103e-06 -0.008244307928712086 33748027.387947045 55.87269705772418 8.638284662053405
94 2.7117035361833945 0.06135319406939463 0.12096633619886818 108056962302.81097 583.7158701538976 0.007421671100672796 9.050019442820886e-06 -0.00396738732995687 10578612.956230627 157.98416837946354 2.315826947543323
95 1.0939706323345735 0.06893894354764854 0.1361355202715921 157283226091.914 536.4549517916284 0.009385038946833051 1.4494316622265394e-05 -0.00010269489179134353 2756021.731196738 80.59561238053969 0.055091183225171696
96 1.1622913272795432 0.05786893010930312 0.0460773074504991 157178725492.1706 1425.8497974086044 0.0026664444844778047 4.717647482754067e-07 -0.010064177004606168 80932021.23996015 24.32860459700026 14.35000474310204
97 2.7716878936706366 0.04312541237999208 0.12480506453875065 156706246149.03607 1682.697094517661 0.005382269875345148 6.9863227093708594e-06 -0.010908944065388938 41658520.38609861 117.10608219360417 18.356448483085646
98 2.5389745767420147 0.05546185075884183 0.1291954309889122 169475506176.02783 1536.9320110250876 0.007165417712231298 9.966773228725662e-06 -0.0049641733799332816 25291558.42784295 142.81358521427373 7.629596975898065
99 2.691255638827559 0.06297069741791503 0.0765125118485241 182849657583.16687 1188.249760943137 0.00481804623229805 2.3504695887419873e-06 -0.017963979523115015 52048775.4075278 101.7877636128114 21.345694373928826
100 2.471636471146515 0.05778734751839677 0.08634307603146052 201290879335.22626 314.4498614731415 0.004989537340437364 3.099802786616029e-06 -0.002536446909736171 10824291.000963096 96.80873134846313 0.7975853794005168
101 1.1749551739564756 0.07225278999907067 0.06712687228516774 217670736453.52356 165.16932008621438 0.004850103806514662 1.821220843370476e-06 -0.00022527311363690155 3576469.151747768 44.734438309269635 0.03720820701311154
102 2.3809623473625416 0.04852277304787561 0.06134584352093114 140821987726.1037 1039.775234610213 0.0029766704425966324 9.335117613737227e-07 -0.03558652100852212 81344341.81955363 55.635620917987154 37.00198323059736
103 2.0875962313292424 0.03274970697390237 0.04426037959548125 190994540317.8186 1457.9021947833785 0.0014495144623056986 2.3663096529928056e-07 -0.09782596018411872 284635101.82364684 23.754107290817885 142.6206820592181
104 1.7941800678946425 0.045497545343850115 0.10729594440554388 103020088720.08171 995.1496827382779 0.0048817020958024536 4.683350275692161e-06 -0.003970879214337942 20452721.60720234 68.75542289185287 3.9516191903404247
105 2.0574912934882548 0.034019059204692954 0.14686011359844534 189703355518.88113 498.1916558730003 0.004996042899313445 8.979509875556454e-06 -0.0008491053312872404 8382154.9957609605 80.69262092276516 0.4230171910045828
106 2.5323886742521076 0.071607908391047 0.07490476862260115 137178636631.16434 622.871006540016 0.005363773809579794 2.507888032320121e-06 -0.009801066218384816 23555905.66826902 106.6278063660451 6.104799980610698
107 2.3301750347380024 0.05527413751107069 0.09549247389991775 123981563453.13733 1556.5889191219576 0.005278264133616382 4.010958444788195e-06 -0.01320118883679208 43177099.64580963 96.54934259061136 20.548824262587036
108 1.677122085801654 0.07462903940988234 0.11497922397710428 206518586292.924 1232.4381175880685 0.008580789037505004 9.453327962571316e-06 -0.0009926451687196605 12569976.11805454 112.96959184597424 1.2233737431697491
109 2.0323791598945036 0.04277015701138904 0.09154170388539487 140161625063.5206 554.0170695932885 0.003915253048268421 2.7341137178513925e-06 -0.004045483107103573 18849520.242546406 62.46463780296122 2.2412666960866736
110 2.8062624068569506 0.07985373881967696 0.11337690514066068 200031319360.05948 205.79991536540234 0.009053569771285607 9.698125558017938e-06 -0.0007814891818280886 3375827.68091437 199.44253610156997 0.16083040747919816
111 2.2717225155456804 0.04716473377826938 0.0949863969839479 127466196746.35666 1090.6494644510033 0.0044800081263049124 3.3683746050520937e-06 -0.009926916544691682 34934256.698401086 79.89208234328272 10.826786213117787
112 1.7378500598700533 0.0738777679130561 0.14607640565505262 219006087605.34467 1760.7324236745358 0.010791798794557413 1.9189901333882387e-05 -0.0007329596853289192 11646166.685165578 147.2230462226333 1.290545883204913
113 1.5137154358328395 0.05407141725293492 0.10531225799488872 198347582797.3896 491.23308203901007 0.005694383043890359 5.262877731885171e-06 -0.0005440626066401296 7439735.481965973 67.66445276199077 0.26726155108200844
114 1.4492631580499715 0.025535568028259188 0.10835483609802105 181044649435.6347 962.4982454017294 0.002766902288371891 2.7071303983189564e-06 -0.0019926250153884852 27916201.656973228 31.47826095542309 1.917898081055011
115 1.2689404943203408 0.06687857997010405 0.058791498763259065 123206849125.83661 272.9127958972913 0.003931891951600894 1.132529158521066e-06 -0.0013321163869399325 8988770.643501224 39.16629479592707 0.3635516076203749
116 1.4258128606535507 0.0758595259575483 0.06400342688102204 202271809950.72742 1362.0811610946794 0.004855269622852936 1.6574428459527883e-06 -0.003925503713462117 37497316.15409862 54.34324108110321 5.346854655913956
117 1.0313069010984408 0.03073462810610016 0.143667461943138 203435921628.17838 653.2340954951508 0.004415566013769644 7.594898511996559e-06 -0.0001545830051510399 6371815.872576612 35.74735906271248 0.10097888954876179
118 2.904521170293873 0.03156970614678105 0.14293141312972282 121103625103.24872 1964.0599277206998 0.004512302711649512 7.681965562248249e-06 -0.017243587282486036 53070675.69776106 102.8827182091696 33.8674387916851
119 1.4573945036854046 0.06471900711662265 0.14999607121470343 145928435034.80405 104.33495908973752 0.00970759680040983 1.820079053666575e-05 -4.0533098182527294e-05 626565.6961965796 111.06021603415373 0.0042290191406542995
120 2.3995696313896944 0.03826366264328562 0.08648192895824242 106970536155.77838 1569.0855127466498 0.0033091153543987816 2.0624403488417235e-06 -0.032755170141048756 78939422.57360174 62.332553782768194 51.39566293587124
121 1.5831564779291536 0.06158952125377512 0.14651519020975837 134859695898.89427 1524.898180279426 0.009023800421424817 1.6142602099109667e-05 -0.0009264786171953522 10955792.648574464 112.14579152784042 1.4127855574289916
122 2.763846605279553 0.07855458480595 0.14787570706278394 135672389234.38428 649.6311811736562 0.011616314771203281 2.11680471453804e-05 -0.0015918976721288796 6271433.8012254285 252.029840348054 1.0341463650526777
123 1.3259034621897743 0.023928018494800956 0.1309319860687389 139710905166.88168 1446.3098788607458 0.0031329429842138056 4.475718424778278e-06 -0.0017971434688577397 28049573.410042908 32.60874260445615 2.599226352739018
124 1.4630438878749488 0.0753596491752525 0.12043197556765828 203664306156.47577 1650.7582276289302 0.009075711428261307 1.0969404555335327e-05 -0.0007713230369176848 13257742.691050088 104.23358844589103 1.2732678493516012
125 1.054406551847298 0.027783601365745487 0.05215405511524665 147170484989.8246 1287.711424834247 0.0014490274769291323 3.284517181024652e-07 -0.010409486893534211 107798617.8929205 11.993732914024568 13.404415199466358
126 2.7894324144038096 0.07145804127893124 0.08227478525214643 148956404054.46942 849.1079141955836 0.0058791950007630826 3.3164246451966493e-06 -0.012435402609648991 29379564.91368695 128.7369942799756 10.558998772061372
127 2.2539066242101127 0.0380942901797728 0.11154464927677643 115056077385.51292 826.4707556456384 0.004249214237550506 4.405800892019677e-06 -0.006222710058892296 23580732.457847882 75.1820571239686 5.142887884536431
128 2.402994457545718 0.024450172665569057 0.07333284694924996 119617979556.28087 1486.8203416185795 0.0017930007699669106 8.035193158826713e-07 -0.0715488673316161 163035992.62936315 33.822281663954676 106.38031136841587
129 2.742828039600342 0.023609133476818346 0.09170812089936714 159918493491.65118 395.0861585155586 0.002165149267221353 1.5174772399310487e-06 -0.011198127962772995 32745076.440472394 46.61826214243065 4.424225359377641
130 1.5697906829164001 0.07549512638840895 0.07604579502760658 181453987934.30493 1258.2507780822061 0.0057410869069162 2.7667077354952207e-06 -0.0032317770495882414 27145064.58942552 70.74659217987953 4.066385987232621
131 1.0361433009419025 0.06182983510372808 0.04805833918607037 111760346401.94025 706.8580808633781 0.0029714391872337647 5.719039774627004e-07 -0.0041007149991116746 30772848.329627056 24.168868942866858 2.8986235344397473
132 1.1891332822946319 0.0527875598961165 0.08766354684184721 139024803572.45477 1499.9087014354996 0.004627544729620024 2.963517222398649e-06 -0.0020404944982919558 26380130.898834437 43.196724508391526 3.0605554532193686
133 2.544032769922248 0.06594414947234263 0.05742754543697271 120109802061.00427 156.39458008854078 0.0037870106401254764 1.0407724496932926e-06 -0.006866482356673922 10976878.837448228 75.62909147290901 1.073880624857392
134 2.4113491041746977 0.06806925253289528 0.15637898691304603 165932504055.44736 1719.6287239408757 0.010644600751022457 2.1692266004892448e-05 -0.0022328385307194484 14946457.070863962 201.4926106094112 3.8396532733471047
135 1.5923443831004058 0.04005190618973452 0.05773069148673035 151035260497.287 1282.6360973889136 0.0023122242396950293 6.421880539337018e-07 -0.017797239006710864 91802603.88603026 28.90257965229384 22.82738118386537
136 2.14854194002951 0.05439898896951202 0.11195997362774329 147207832368.7976 1631.9826419816247 0.006090509370402464 6.362062696420984e-06 -0.005760987394660233 30852774.00784508 102.7228613248515 9.401831428760444
137 2.9217862660688345 0.032843445417127595 0.048757074670193176 195326934051.26315 761.0501315585215 0.001601350320629304 3.1723448179120516e-07 -0.10211624123203614 170879107.52690297 36.72860648574005 77.71557882390282
138 2.650969177806023 0.033149857480434794 0.07285282237491812 112263045235.50276 562.2891172867971 0.002415060678775967 1.0681680006457648e-06 -0.029118974501895014 50832465.96639513 50.25767366243609 16.3732824689673
139 2.645330657566194 0.05809176556486251 0.062398521644742064 192519600897.1284 1836.6219985253722 0.0036248402909803547 1.176132446739775e-06 -0.05005036379772565 128880680.4817552 75.27287403151523 91.92359918510083
140 1.7116485574723677 0.04607224077507914 0.05080289837571628 133938373623.35886 414.7005979668885 0.0023406033660378772 5.034119949422421e-07 -0.01028084050401299 35816586.66371313 31.44937944448555 4.263470704616394
141 2.3179594419089993 0.0698117402640165 0.12983737616156665 109203043249.62506 1619.773916426538 0.009064173181152699 1.273345944268063e-05 -0.004835812948398948 19141834.59741644 164.93152859555715 7.832923678534328
142 2.2170807507995125 0.06206830874195027 0.09726977055680387 219837925483.5011 1265.2639654958202 0.0060373701501783665 4.760168652730884e-06 -0.00439217324060257 28660793.27513042 105.07489659148435 5.557258531549435
143 1.5294680246631351 0.04242086202547611 0.1352559504127669 140463337062.4261 856.1338645748704 0.0057376740105846225 8.747166327492526e-06 -0.0008310195877148452 10123742.215554321 68.88837314076949 0.711464011167726
144 2.2316117653477456 0.07494208675424054 0.09992226275683394 208295443337.3362 956.7772193039224 0.007488382884202668 6.230620737223157e-06 -0.0027310799449712883 17121050.84331536 131.18263228035056 2.6130350754463385
145 1.2445404504507112 0.020747849981456956 0.10212715532645167 196038222403.36148 1775.016121825097 0.002118918897746172 1.8416858803310756e-06 -0.0031590156914121205 61250127.86547549 20.701080193835935 5.607303781354969
146 2.595558640536703 0.07828353095980646 0.04130940703342244 116560683003.23747 124.8123838731956 0.0032338462444321723 4.5987102109595957e-07 -0.013571905660408055 14550283.171452533 65.89005486093926 1.6939418991776465
147 1.316696947387901 0.04519978117597574 0.15359480367917966 136273168756.41151 1435.5960470836774 0.006942451516065875 1.364849156707118e-05 -0.0005873182212224315 10636039.812315397 71.75767204095068 0.8431517167671394
148 1.626844127395485 0.05282349110856836 0.047938376313797666 167988424833.00262 793.6237756270751 0.0025322723949710952 4.849487175130852e-07 -0.013981574273287148 63814316.719322376 32.338957926586744 11.096109763976525
149 1.0617097056098412 0.05157370872018972 0.12594127202734143 132787328876.609 1712.9943483542802 0.0064952584793882846 8.585218314452442e-06 -0.000599437708845018 13339773.44982657 54.13421989888761 1.0268334074419545
150 1.690444257651822 0.021496426584195448 0.0818724117236866 121600668008.59973 1672.1450161760738 0.0017599642878892516 9.83100182416688e-07 -0.022522754868352028 117702206.53730504 23.35470396445711 37.66131230367025
151 2.197356544114635 0.0249116415865122 0.15997594369687082 183594002331.03647 1251.4457206043853 0.003985263371840501 8.499338833351692e-06 -0.0028362775317182136 25879274.133217223 68.74279971855255 3.549447379515127
152 1.4693122091591027 0.059152260883236454 0.1331021331716896 191936918720.63373 1417.963699048954 0.007873292105487064 1.1623720270335684e-05 -0.0006720203919551751 11928588.864011742 90.81134510241475 0.952900520813088
153 2.8602167128648457 0.07186473302707089 0.09702997350637749 143986230123.234 698.2192085353996 0.006973033141659579 5.470818525639466e-06 -0.006913438243374578 17709827.89240488 156.56342955941122 4.827095378547361
154 2.2941834394689877 0.037284593794104204 0.11294452893614798 144254417101.51257 1604.7796995369506 0.004211090882650726 4.476553355336487e-06 -0.010002434203830587 46444575.73239496 75.83896747584768 16.051703356261367
155 2.0844917675866554 0.05949897487368812 0.14722733877245786 202799760420.5213 1572.01388989613 0.008759875730342438 1.5823174704596453e-05 -0.0014790219398015017 15244788.603835296 143.3401274331005 2.3250430328290785
156 2.304222089828586 0.03906286972043847 0.12026734480875395 107303479831.53624 230.63138968017876 0.004697987621887408 5.662732780013312e-06 -0.0015478550699345377 5643316.537703733 84.97787382033972 0.3569839658025127
157 2.288668294374408 0.07636508084636587 0.13870445205023224 115956690685.08931 1784.523748927207 0.010592176694566862 1.6981841100838293e-05 -0.0036213379155577586 16679415.125940835 190.29953490874354 6.4623635132033685
158 1.619280685381442 0.06031216365010704 0.12285413804816706 208559810329.4909 1179.1318813706505 0.007409598879053893 9.319508963432962e-06 -0.000858586154413993 12584943.811277138 94.18602975751622 1.0123863075729633
159 1.9764133743797743 0.04862186406220104 0.04718223796736001 209818554532.6043 914.5179335817894 0.002294088360599399 4.255846630641964e-07 -0.026355694473561814 100191893.13257454 35.592425305496334 24.102755248074736
160 2.5811156078482758 0.04791637475969256 0.07180650089040813 162818322054.708 1394.271398804625 0.0034407072068469934 1.4784069635400225e-06 -0.0332009996887741 87396601.42829902 69.71477512798624 46.29120427777899
161 2.4240966074345485 0.0550835490300282 0.1164652314828088 137726245762.51544 291.74655046003613 0.006415318288676882 7.251528374280895e-06 -0.0013870368085180226 5679268.500204659 122.07810769867636 0.40466320424623076
162 1.8119409846568342 0.03615284614821878 0.043978129880797225 168655136048.6181 1384.97239798188 0.0015899345634668451 2.562545111832703e-07 -0.06354493181927395 215337868.01679626 22.61481064797419 88.00797660133492
163 1.5203382549442104 0.0661720352183438 0.13349617672348985 153446858345.07272 1758.8207431663848 0.008833713707661018 1.3118969722462246e-05 -0.0010234420659766342 13605073.890493095 105.42732813140951 1.8000511350687638
164 1.119274932276804 0.03118191689650051 0.15397494615710128 130820606053.8404 1267.9718041324911 0.004801233975213873 9.48575157053905e-06 -0.00047758510126295325 11518467.262977421 42.185121534752895 0.6055644424751853
165 2.8264732580246443 0.03711519596359855 0.04504328364823122 210362584278.08685 1195.6522622459536 0.001671790299448056 2.826575829108088e-07 -0.1513523398706324 269270748.2849036 37.0933740091573 180.96476756254006
166 1.9700378017525204 0.02010190573151893 0.06320283381208486 176721792183.19147 378.1281448349977 0.001270497407255387 4.229272215427543e-07 -0.012893941091676782 55661445.40198045 19.64798416667518 4.875562024607487
167 2.3540189868785317 0.05728838900570228 0.10253006432107029 166687539871.52856 860.9030418047646 0.005873782209605151 5.145635904998451e-06 -0.004364361156086619 20190467.95615102 108.5419095426689 3.7572917948095292
168 2.681783428693869 0.06279757642523184 0.0903787048143618 131752029800.08102 579.2534526212464 0.005675563622793355 3.863313725592832e-06 -0.007316463209146168 18170566.797023073 119.48196490602393 4.2380865748742425
169 1.1228746478704057 0.03003018546318814 0.10893177537958146 164989127617.54022 1929.469855839357 0.003271241417483183 3.2347484534134203e-06 -0.0017061402656593592 36479875.439676814 28.8345733298308 3.291946212423486
170 2.3452421725929256 0.06721105485541519 0.08017800091707836 171857774746.8822 798.8693930488431 0.005388848017835283 2.8868561032027542e-06 -0.006923461670399869 26017380.52327449 99.20950602000063 5.530941622429273
171 2.1921406572154005 0.04161487558830651 0.11868647536109089 125111735826.98828 1697.0981515337937 0.004939122906166404 5.7979044364939595e-06 -0.008215270238589898 38078125.56060209 84.99392924869139 13.942119936261504
172 1.6538092114275944 0.023076624935595744 0.15312730231001884 170280287585.6021 1465.4676397641606 0.0035336613228078885 6.90476560049627e-06 -0.0018793076552264289 26874187.02850412 45.87541291894207 2.7540645538953936
173 2.572389637442625 0.06310861419853078 0.15585331463983307 117112596843.1493 989.0783852809141 0.009835686705167455 1.99092787415357e-05 -0.0024069139974230015 9958592.990530154 198.61456567641395 2.3806266100811726
174 1.9501819587052847 0.06965944772581867 0.05461591488166573 102058969811.37593 756.6883347626233 0.0038045144676971555 9.45706599929415e-07 -0.019382669354814672 42611318.31850184 58.24303949080942 14.666639797349244
175 2.169380236533605 0.07309913637665019 0.14042989389535024 185356904469.80307 1328.859299956813 0.010265303965214724 1.686979103822627e-05 -0.0014462597918054655 11998709.765359618 174.81437822155294 1.921875774494297
176 1.9210801752994098 0.03752749610171206 0.09940157815533544 105927512798.03633 675.2751286959088 0.003730292336728378 3.0714834610985046e-06 -0.004905000029512263 20991397.246766213 56.25459665085755 3.31222452618233
177 1.8672525327673226 0.06439535012713746 0.14110818184384483 161447928371.44077 871.9607816125334 0.009086710775638168 1.5077517842054512e-05 -0.0007773606289221339 7618901.494090041 133.19239212612575 0.6778279815897544
178 2.5139736529173735 0.0523306246636633 0.08575743461063907 158554436079.10913 1902.691856398136 0.004487740122728002 2.7503629902673907e-06 -0.023107925436530653 74572886.04475248 88.56417437297526 43.967261546342215
179 2.8287887582563256 0.0655810217625155 0.1502194765651921 185857541823.98007 132.24380229654287 0.00985154676177555 1.8525744315176733e-05 -0.00028980092717855843 1516688.6192816324 218.7633661395054 0.0383243765191561
180 1.1491168951070976 0.043562541919502956 0.13726800646592155 214735079097.06833 1303.003086355074 0.005979743285878311 9.38944552879265e-06 -0.0003268691068341117 10944830.456825476 53.940678699917086 0.42591145503897393
181 1.816452532974277 0.031336992307416156 0.053829698863246477 169898635912.34576 1175.1395559848966 0.001686860859188083 4.073257968145525e-07 -0.03392411627878146 141046897.41507798 24.05320604151176 39.865570941027244
182 1.7201861883903216 0.05216015809158496 0.08834191964205884 124165131519.08154 1368.5047738109579 0.004607928494643884 2.9968026860878492e-06 -0.006240129876809475 34697681.819949664 62.22298538557642 8.539647525614152
183 1.4466566045237335 0.027334226317785183 0.07884479362491571 159208365270.32013 739.752259166604 0.0021551614329225126 1.1164636867654345e-06 -0.004200015783817907 37787675.500095166 24.47456138790466 3.1069711646146914
184 1.8527855752852664 0.03493335622852884 0.14129445290853324 116134563701.037 335.50969196930976 0.004935889456568885 8.211725114663548e-06 -0.000745870451627361 5347994.409986015 71.78938657271767 0.25024676547450586
185 2.7971497624395587 0.024165381669526993 0.09574930693548259 118806388105.07796 1437.322937855852 0.0023138185466886245 1.7677438297101707e-06 -0.049925352234107614 108882075.16564503 50.805961435856894 71.75885394661577
186 1.2963080909812095 0.04750360625822915 0.09387910852407244 145324504696.18393 752.151047413974 0.0044595962072011015 3.2753084462676986e-06 -0.001147406876847494 13973334.399871632 45.38093357034563 0.8630232842308393
187 1.9936770076287835 0.03342559856298535 0.07239437329396463 180532790604.77344 953.707162368382 0.0024198252599429686 1.0568476488097286e-06 -0.013203519451001034 65122681.703268915 37.871147368336985 12.592291068889933
188 1.3869643241945444 0.058219887610593324 0.13360766982317238 104935850950.06586 547.9444957150688 0.007778623521018357 1.157135682245887e-05 -0.0004013312796635827 4387518.563440152 84.69108552269515 0.21990726564994506
189 2.5564017033384347 0.03856683579322107 0.1511509527738792 164293231268.08487 627.6901227004914 0.005829413975619112 1.1098529223897001e-05 -0.0019170181887193482 10926721.058913376 116.98324196138995 1.2032933820963216
190 1.3502967241920518 0.07867742122415634 0.049844588613273774 148097496367.31027 983.0855480332484 0.003921643694071328 8.11938095415363e-07 -0.006709452211138715 40746060.66989111 41.56875367339051 6.595965503990194
191 2.8669274755305993 0.04082263006107567 0.08536535809262197 174577218859.83533 1923.2652766415831 0.0034848384334463588 2.116239102299512e-06 -0.04088987199949751 111209742.10429634 78.42761556316417 78.64207098295249
192 2.321092882149906 0.0624418907370763 0.11083112427626327 156235495722.25974 790.1308036373971 0.006920504952325756 7.084023859237722e-06 -0.002975744043477069 14346410.090740222 126.09560806795292 2.351227032491734
193 1.6420849752535778 0.05664594997241158 0.1006076067015132 203193406480.75067 1199.838353027825 0.005699013456057977 4.807065859132985e-06 -0.0018130036740156116 20617647.849358328 73.46237530419205 2.175311342264287
194 2.6727701007027393 0.06108791293093188 0.0710279279220952 103940414216.20375 454.08890509393973 0.004338947876569457 1.8241539064487798e-06 -0.015242581589106612 23628718.435804565 91.0365297010695 6.921487184602466
195 1.7744739384736667 0.06564742067871134 0.1216052643240628 123074084192.20244 511.90463757274773 0.007983071943827637 9.837699424928616e-06 -0.0007874382793362332 5614195.354110834 111.2011619392673 0.40309330699452256
196 2.960533583025227 0.07947322771835542 0.15159347388603736 178840793298.61615 1346.2324845207952 0.012047622670761614 2.307178104636529e-05 -0.0028220264349158876 13093611.348032258 279.9890233723858 3.7991036588601776
197 1.2157155733362761 0.06378382198624324 0.06471442790537063 109114310589.13678 149.76433221439063 0.0041277335494577325 1.4405642793286307e-06 -0.0005706485592192375 4089581.3660352468 39.39247717546836 0.08546280040057326
198 2.389810404232901 0.05241290466780049 0.13599722167844264 162288211966.3734 1937.3023089560381 0.007128009414917944 1.0986189627661704e-05 -0.004943475859068718 28655882.859444786 133.72153983074168 9.577007196042262
199 2.0263533456094995 0.051833773855205115 0.12841653159329114 215618442447.67346 1634.7370694283527 0.006656313457876456 9.147330929693026e-06 -0.002298750802032596 23251963.77338491 105.88113790162892 3.757853149460842
200 2.1801583211376006 0.0544373241338348 0.08478722391231747 182444307143.85284 1227.1349606572255 0.004615589590522854 2.765074079163017e-06 -0.008402298097986923 41017955.65846277 78.99232101396575 10.310753745903463
201 2.14563415133425 0.04819637311475541 0.08252572251278449 205188393280.99457 596.2179361203249 0.003977440513790931 2.2573615199825473e-06 -0.0042383507360532644 23384006.977611676 66.9929377801286 2.5269807284037373
202 1.7926478098633127 0.04021839785799433 0.0836200901763734 167578973472.24176 659.5016413182734 0.0033630660556347486 1.959636024754766e-06 -0.003856422518740346 25224123.077278662 47.32602504261536 2.543316980726008
203 2.3756280674227153 0.0483290729257396 0.09665149195898387 200871859581.95782 130.53595113399155 0.004671077003267266 3.636243060911639e-06 -0.0007986789177711991 4121300.169104623 87.10942182732785 0.1042563121819305
204 1.6958661415634104 0.06526374561339524 0.062458407865225524 168178476222.96375 1870.3868278064733 0.004076269642333763 1.3251452289488016e-06 -0.013644291790094198 74751591.11529726 54.265540211985474 25.520103638940196
205 2.4433997055693606 0.04408042722693588 0.09428494243490745 131315942784.47629 1341.246356802283 0.004156120543597776 3.078871543997218e-06 -0.016131019880204368 50179213.1978636 79.71725014341997 21.635671645829305
206 1.1028063868576052 0.06406947408643922 0.046615887590654936 190473321972.5782 1310.082184245514 0.00298665540200583 5.408437141121633e-07 -0.005685506510251672 62262992.35227599 25.855565823497166 7.448480787492602
207 2.0518223806710534 0.05934782620461518 0.04929105853191075 161709968680.2527 1056.1085577582949 0.0029253171751933535 5.922812776066097e-07 -0.03174985874842365 90169252.42114542 47.11751531739171 33.53129753182728
208 1.0223759978198008 0.03397969986648991 0.12554263886747186 142541733129.8655 523.4450425052518 0.004265901189163824 5.602889429367168e-06 -0.00023346817289116728 5995576.4022467835 34.23663663124551 0.12220775768264053
209 1.5385843620956283 0.0569991138377577 0.14001589228789396 146082075158.87045 877.2234445545054 0.00798078178361289 1.3038236515113336e-05 -0.0005591613347830274 7247029.445275793 96.39098248908093 0.49050943216006226
210 2.5662646359499606 0.028666054976278867 0.04563183452125549 129906583615.10869 175.8268955552439 0.0013080846770547698 2.2698150440767e-07 -0.033592841401824065 45355944.012306854 26.351597863296394 5.9065250165623935
211 2.5475806232002713 0.026145266709118133 0.060181120434581035 141646259842.15485 456.35486046361933 0.0015734514446156804 4.7488957685110224e-07 -0.03739103507369861 73666197.535083 31.46668113301765 17.063580593648027
212 1.8023601030541823 0.04529786577896972 0.04061234069047676 199529001178.22357 1584.56457706168 0.0018396523575670068 2.528544241506192e-07 -0.061296658313751695 229355403.64641982 26.028370700231466 97.12851345622427
213 2.0785411776654135 0.030505920460044238 0.11257009285054553 184566302940.21112 1074.432761558658 0.0034340542986785365 3.6263687238748333e-06 -0.004805178356806669 34662425.026948035 56.03191263921675 5.1628410516856835
214 1.383765571277426 0.0456377171355702 0.06848166717680429 101575719368.99918 425.77229281039746 0.0031253469555872567 1.221421724284707e-06 -0.003031015502007379 16516522.223900557 33.94926799619116 1.2905224198335397
215 1.8869495499350393 0.02206603407158994 0.13149700401976216 176890774227.61542 917.97242336677 0.0029016173710120713 4.181100558450406e-06 -0.002779671352508547 27238624.543780982 42.98036389967212 2.5516616476254583
216 2.9070650191280567 0.07764107771594184 0.05129676553297728 201713576323.0376 1684.3832381599352 0.0039827361593223354 8.733337723868289e-07 -0.07830121620547195 143805463.9610624 90.88787280808175 131.88925610403405
217 1.7054965108590037 0.0670474566809185 0.11559254638985875 154576172017.00507 1878.5585276090378 0.007750186246711116 8.629597801067986e-06 -0.002328750055407863 21457782.839533187 103.76063747784498 4.37469327525646
218 1.184295505330851 0.027483044815957383 0.045438835799037305 104640068317.19223 716.4567217412143 0.001248797560649871 2.1486475721748903e-07 -0.017643540894781685 89718510.65179947 11.609720904444318 12.640833469382338
219 2.6278699871233693 0.02582792346346185 0.09088122248710997 197355116711.1208 738.0035598900417 0.0023472732586629244 1.615588397802971e-06 -0.01400134349726241 54547615.502999134 48.421382241937906 10.333041344222945
220 2.7024519568205987 0.03539519932942396 0.04210185934832423 133110101253.87187 248.86983309758128 0.0014902037037733077 2.2012377114750704e-07 -0.055878789497748604 64318302.56899091 31.613550735289312 13.906545015999573
221 1.3297143707186265 0.020598701447028227 0.08283703529892925 204128818615.94937 1890.6208917107308 0.0017063353588795823 9.757357983043522e-07 -0.007439122734166268 106714916.20655371 17.81116838654492 14.064560857215
222 2.493970388921495 0.029519715390018526 0.12384489925720596 211627243968.80576 772.5088228459828 0.0036558661785782366 4.67267195611426e-06 -0.004039421782807421 25531573.26245612 71.57333266258458 3.1204889664149817
223 1.2376104313828369 0.07799389912769801 0.15785801418451584 152877308824.47632 1841.6809879495952 0.01231196203480585 2.5566971772605712e-05 -0.00029773007909170217 7036484.147785957 119.61368926376164 0.5483238262039172
224 1.4771859313584725 0.040513737564428005 0.10497583568425264 189411673010.8775 632.8111067480272 0.004252963457518328 3.905611909384729e-06 -0.0009190994374579616 12562599.497313634 49.31697962031793 0.5816163322292619
225 2.819157854789256 0.05351171996944851 0.14819831316475116 155105351085.70502 184.8837000512838 0.007930346634016799 1.4514345119172876e-05 -0.0006133541746896295 2660932.375508624 175.50165718524644 0.11339918925852019
226 1.3369512392761456 0.053296070850150104 0.11593498395800672 103501600362.37758 1152.4278222710052 0.006178879119036942 6.920818587591752e-06 -0.0012815473411189504 12904950.645225698 64.84775174994141 1.4768908114629091
227 2.8501593284628433 0.02277771271481304 0.0532787527568028 138339274506.69586 1866.5618870210176 0.0012135681240980074 2.8707211811440863e-07 -0.36273715876780366 493678907.641683 27.152070700541252 677.071355562274
228 2.0951792560264026 0.07406533974700003 0.07146009099466157 110929048849.82607 1740.7797644535306 0.005292715917871146 2.25229082633491e-06 -0.02136074396510656 57859425.41469475 87.05013050344027 37.18435084813037
229 1.0836687756578331 0.04222388045854136 0.041856923487206044 193639384841.11835 726.7213463140549 0.0017673617336861002 2.5803511413136545e-07 -0.006169697030512495 63873832.58763539 15.034592599791754 4.483650532363868
230 2.7546212839409696 0.04461943357315988 0.12642371509089032 192860071445.43384 767.1257728362566 0.005640954557570071 7.513260584185761e-06 -0.0036885887754046563 17778641.534867678 121.97874386530671 2.8296115150074383
231 1.5467854062971749 0.049870594991660216 0.04470165073126904 218740964751.01474 640.2836832422215 0.00222929791907777 3.712222395568458e-07 -0.009726963089415511 59629625.15415055 27.068727077017517 6.228015753652102
232 2.173910077761913 0.06642213976014666 0.13974731270509982 211435093105.7926 417.4666239245434 0.00928231553560306 1.5106435890405407e-05 -0.0004475959511004225 4197732.824075782 158.40451640933568 0.1868563705881884
233 2.9881608632106027 0.06226482992396756 0.06380558300294158 187433213647.60504 446.12442249273533 0.003972843773877753 1.3478377128018105e-06 -0.015705888459199183 31553755.344870836 93.1912458038986 7.006780418595552
234 1.928995177822485 0.021303088247859245 0.11962160800408958 130279639299.75061 485.0840592149928 0.002548309671661946 3.0387168120254663e-06 -0.0029317193820578113 18417791.69843448 38.58806498563921 1.4221303383278734
235 1.6519785274161694 0.0302512897817867 0.10102083746353827 110336460642.15823 1386.2454826876135 0.00305601062810827 2.5989357504399295e-06 -0.007264696769490036 44507168.68080702 39.63044190694513 10.070653079800861
236 1.7318884807611248 0.07204950073348351 0.15261615406608325 154159461726.3519 708.8711369355949 0.010995917704325698 2.134279264448713e-05 -0.00037306489081996894 4389413.364616604 149.49307017902404 0.264454933306305
237 1.660836317721548 0.029259975287818117 0.06563276847501871 216087586514.02155 1599.6674590351797 0.0019204131836501354 6.893739688650444e-07 -0.01639850496561314 126471418.98158444 25.037511889433635 26.232154770318147
238 1.3605777007928852 0.05032300096904793 0.10614835262365957 106246645726.0461 1625.703309806559 0.005341703651943262 5.01562503462157e-06 -0.0025612371482731057 23405764.992079355 57.05225255366169 4.1638117091471
239 2.9558431518635926 0.07374489336359635 0.12823646225845173 206271115408.20898 901.4139582943543 0.009456784234574371 1.295941182037301e-05 -0.0029028424886419295 13182625.226640377 219.4292517095832 2.616662737991756
240 2.249765552000813 0.03329480317374009 0.12404159838985881 148666125744.9088 1060.8610296626157 0.004129940603746465 5.295381665986321e-06 -0.005114930511678461 27953477.905458976 72.93747510162815 5.426230449271942
241 1.7725347730110497 0.04188773776384526 0.08091372269812258 192280991525.7248 1538.9560461677734 0.0033892927978754527 1.8491502826542483e-06 -0.008034903989242845 59681668.88542053 47.15996882017868 12.365364074622839
242 2.940011731978143 0.07566834988588603 0.059190285389112834 162741747361.5662 1126.6770492461765 0.004478831224668837 1.3076283241468332e-06 -0.04484789766891998 74969502.74749662 103.36735831669986 50.52909701051324
243 2.624776066505209 0.043805932405658055 0.08922955060496712 174865528976.846 881.0331896034272 0.003908783662388435 2.5934495239728607e-06 -0.011710239589151218 39781892.249888845 80.53850217854237 10.317109736250226
244 2.7240323279965777 0.05656983266985362 0.10595797521122305 174184264326.22763 211.23376340607712 0.005994024927735386 5.607956031341586e-06 -0.001457019403494844 5435939.931264098 128.17415377205305 0.3077716919558935
245 1.4930080857952328 0.05746940956810506 0.08857761921629925 181986546190.57208 1726.7551338255507 0.0050905034773091554 3.328338577228582e-06 -0.0031624902764392274 34305158.0410692 59.66127839127186 5.460846320514821
246 1.4978591215046884 0.030966805920008115 0.10651328394486723 101910433057.51341 381.2722785189818 0.0032983761918234196 3.1183617195054307e-06 -0.0013439457646466806 9753342.762155218 38.78294749085136 0.5124092638927752
247 2.4904040188857453 0.04111838637386729 0.11614233792704334 125431018377.34157 927.0671449994952 0.0047755855252484295 5.368173072711737e-06 -0.007088721321710404 24975549.821073905 93.36112846919856 6.571720637415113
248 1.6202029806615617 0.07332331449794896 0.0674029628912004 218117586637.73328 1645.1576020070886 0.00494220864616507 1.8711034749810364e-06 -0.005714865914334549 48009603.80757185 62.85794225960871 9.401855103418674
249 1.5406629516324877 0.04120566430531498 0.07240269404633617 119564303692.352 1748.06148661587 0.002983401105673756 1.303286368322009e-06 -0.013674673808985646 74808202.8299052 36.081862093962 23.90417062752255
250 1.960630680308092 0.03506576023661653 0.08072497564950115 118234799547.0885 215.9390093583068 0.0028306826412321153 1.5371837366101303e-06 -0.002984874888866303 11116780.867309257 43.566897376029544 0.6445509265602756
251 2.4397064110239333 0.02535178025825994 0.1106155953071023 160769926256.55527 1799.7399897197276 0.0028043022653622667 2.8594091243021e-06 -0.018950475123467307 84929271.86628518 53.707142589738105 34.105927903893004
252 2.0647253922351423 0.046344053185831235 0.11735671690144217 163550742253.26984 815.8856469688461 0.005438785929794975 6.242184805680148e-06 -0.002344799933806798 15835541.745614268 88.15235538560438 1.9130886110064667
253 1.0523732677245807 0.032248275964980415 0.05625056779683694 158803880645.26825 278.6476441083222 0.0018139838334992379 4.783061746560689e-07 -0.0014252020732370275 17243130.329282057 14.985556541504364 0.3971292000857942
254 1.7401156422876118 0.04582209130992622 0.05172123384202792 173440774897.3228 1694.7117816808484 0.002369975099771449 5.283239400985305e-07 -0.03248309717520949 144348591.41050282 32.37364133211387 55.04948748831141
255 1.206060508769472 0.0735780027774754 0.06659308000994577 166028251316.1757 1498.1950736613505 0.00489978582593243 1.810731492584172e-06 -0.002914193282266561 33226340.64116436 46.38908976077129 4.366030019188764
256 1.7583912519298883 0.025094062051144405 0.07049933995135561 150585897268.83624 1576.7306984844304 0.0017691148113040415 7.327315204746838e-07 -0.025897249241152977 133377698.35273038 24.41974866167448 40.83298788482852
257 1.9922434745333981 0.07701808187849038 0.07756755245216204 219344889732.8167 387.5516471728011 0.0059741041058747136 2.995378556826978e-06 -0.0015547348521333635 9997015.741973927 93.42967888072982 0.6025400528612463
258 2.9755934765842085 0.03475764166615617 0.05659374519233602 170948948382.8667 905.0359449688766 0.001967065115940964 5.25018202556666e-07 -0.08855734201116047 145145476.28413817 45.94751109703079 80.14757771100261
259 1.3094892725297502 0.07093992867841134 0.09238199660591137 195849893830.10547 1852.1065781860923 0.006553572250392591 4.660918768946262e-06 -0.0015186429556610496 24035531.69588962 67.36738558530635 2.8126886080958
260 1.8981167520140687 0.038721206016067364 0.13766089031344603 121475057997.73196 1454.1325339922068 0.005330395694182196 8.417814504873018e-06 -0.003241641893466258 22568782.972723186 79.42404989162846 4.713776940841385
261 1.3574827743366096 0.03447660181414077 0.1421915841094498 114059411442.89397 1911.9193096375288 0.004902282626663407 8.25971162199173e-06 -0.0016922139691061726 22339986.12159546 52.23989913190785 3.2353765635724563
262 2.3614452255990823 0.056194595351063276 0.15040608205209757 170741500984.13037 1146.7202174889098 0.008452008919256444 1.593343809830657e-05 -0.0018502109703872754 12780894.536866957 156.67780545642705 2.1216743263628635
263 1.2835769902090703 0.03370516955796104 0.06515841870363565 117335088497.90169 1786.1736193459988 0.0021961755505346594 7.770104836812091e-07 -0.013810627192923274 96130069.42665954 22.128839164539308 24.668177958622035
264 2.844162452744898 0.07675297437317298 0.09281253990843882 128746469431.01382 1804.5579421198604 0.0071236384971014996 5.113684640101157e-06 -0.02102052230264616 46576617.9910677 159.04716335201582 37.932750468747784
265 1.7485215564374665 0.028478863066171697 0.1012479627143423 153814855172.39337 1078.618158304916 0.002883426865870612 2.4632034319057656e-06 -0.005072953519384799 38760978.732904285 39.57761214637765 5.471779782245274
266 1.6367506690640443 0.031673975209392455 0.10710018393981813 126460361692.25813 804.6497488754809 0.0033922885710311714 3.2425895336681313e-06 -0.002868050609130363 21749919.389263835 43.585795118104606 2.3077762023989163
267 2.8593012729562552 0.039935660012452856 0.06986382492509467 187784073528.28076 1274.6650253987286 0.0027900579593781107 1.134845387465724e-06 -0.04660785489340355 112186772.41173568 62.624287757741776 59.409402541480496
268 1.2894122392511047 0.07003745071138104 0.07587294613660116 182345905342.1501 1666.9298081007958 0.005313947725369472 2.549235324139676e-06 -0.0025625094730750667 31985719.588014014 53.787173501280925 4.271523424209492
269 2.5007519169881003 0.02472886936083557 0.10324005577111053 198895061932.1864 1528.157161891395 0.0025530098519691707 2.2676065649571843e-06 -0.017663098512832365 86993972.04948102 50.11788760900107 26.991990493578026
270 2.575713827835502 0.06074189800573748 0.13939833856790468 178616507363.1539 571.5920948948395 0.008467319663460928 1.3711340152901193e-05 -0.0013294018832493678 7483961.0802418385 171.20372988375613 0.759875607403651
271 2.3127451009760245 0.03796653861409344 0.12617502498012312 193413776489.3423 1101.938323212827 0.004790428958042049 6.355357079950439e-06 -0.003696510805289008 25298134.89069752 86.97047266864062 4.073326918518267
272 1.0867103616976994 0.058812886692577795 0.07546259379684746 112590649803.91116 1594.1365388368088 0.004438172978502014 2.106136119624612e-06 -0.0028757883752170105 31035205.190956067 37.8606172175473 4.584399326895575
273 2.1545894431208374 0.04435398512393907 0.13450475818736907 114782616266.9025 1729.1938392131376 0.00596582204374159 8.99423736084342e-06 -0.0055843874647924854 27858101.40911099 100.9030929806182 9.656488399898238
274 2.9161579355363765 0.047608153993703106 0.06288634706975409 185042648477.68683 564.93738666509 0.0029939028953983125 9.866638140493067e-07 -0.025578268905592966 52501115.328370355 68.53594544013282 14.450120390942622
275 2.000970817284346 0.03692262640850094 0.10948735191872908 155690935171.92496 1166.5925641960014 0.004042560591351303 4.038342930675903e-06 -0.004955114455666087 31643952.152809307 63.49900929762199 5.780599678720175
276 2.5257575434441066 0.049619483679336954 0.15926963098288882 128319429680.0518 347.56102305797657 0.007902876855169471 1.670590149549538e-05 -0.0008708080825570729 4184617.698189847 156.69189403005493 0.30265894806069116
277 1.8742592357417815 0.06944088769281627 0.0986166055119026 165387780700.4831 1036.5394879150635 0.006848024627998794 5.549887332477966e-06 -0.002478369121151686 17260421.557063296 100.75454123406925 2.5689274597030747
278 1.2481383635438636 0.07808945345119186 0.04746855694708957 209349288623.42667 1479.3639341378 0.003706793668115001 6.96032029338957e-07 -0.006580232727711145 62962877.45763502 36.318742355889135 9.734558975609067
279 1.275326027497872 0.0321316650017885 0.1304934908462004 175661232869.35196 1412.3338300614255 0.004192973132784065 5.950021456310129e-06 -0.0009342977827756744 19751446.500165913 41.97715098538465 1.3195403659654659
280 2.9333622363830667 0.07107695027394666 0.05409851593936968 158363799031.54465 1518.188155176256 0.0038451575273168895 9.377856727866733e-07 -0.08600860998612192 128452646.89814313 88.54203308606732 130.57725292410456
281 1.3703702447732584 0.027947534902596813 0.07398694652962075 179263668998.52936 109.23131917603185 0.00206775277047314 9.432516503091359e-07 -0.0005541404200699495 5870601.936981746 22.243656931100304 0.060529489093001015
282 1.1567270365111966 0.06386407424978399 0.10457363801910008 171509667256.70508 1405.6795964765386 0.0066784985830218415 6.086141230807372e-06 -0.0006947476967621571 13969067.724642783 60.64281901312218 0.9765926620376335
283 2.950898911344147 0.0774297823386892 0.05496187934167775 211191670593.61926 178.12924338747985 0.004255686354351407 1.0713010128343616e-06 -0.006743551272841987 13483716.681648755 98.58108680611 1.20122368597602
284 1.2245838548143226 0.046656130713799045 0.14458165377891735 214231300322.82773 1931.3916143840818 0.006745620537526405 1.175078924724582e-05 -0.00046963960449313805 14550403.131653015 64.84553730752617 0.9070579939007035
285 2.654042778904257 0.06908777372321699 0.15664819627399507 177931027615.85968 1216.535491985191 0.010822475138327854 2.2130750799585856e-05 -0.0019252159470979626 11426992.90055299 225.47799912738665 2.342093529380555
286 1.341647441716586 0.06518563156775864 0.1276817747379519 199710785525.73175 1296.2575257759631 0.008323017125985684 1.1307259608286994e-05 -0.00046208979063604963 9819090.191774791 87.65745388036989 0.5989873686962185
287 2.119507188432695 0.0445034505665908 0.10768973330179513 169075513542.73682 441.7098327760789 0.004792564722525787 4.63164583863495e-06 -0.0017902118817806182 10883809.28827098 79.73932173631543 0.7907541909350664
288 1.9833354161451644 0.026723614080772236 0.09760623526288784 164792672870.41846 1005.0305193964633 0.002608391363042477 2.070840412147525e-06 -0.007658821840670438 46976034.399680264 40.61052251049103 7.6973496924939875
289 2.9830555649770574 0.07432930167586123 0.043372498172153065 186610332176.64044 933.5025178522313 0.003223847501073705 5.053847335008139e-07 -0.08758313029815197 119492090.63789581 75.49279239541507 81.75907265470491
290 2.2059194362242263 0.06750011366567416 0.05817678090920038 209145047096.00708 1830.4582337522565 0.003926939324074048 1.1075728938136135e-06 -0.028274023080775923 106046623.13896349 68.00071747180812 51.75441834950763
291 2.372138401379674 0.04908727021159006 0.13277350189106182 216988375018.40353 834.7645356514713 0.006517488764265615 9.574627017102846e-06 -0.0017877404859739238 13729779.534080055 121.36402521945894 1.492342356639358
292 2.12015487262597 0.03674782348618326 0.14563549833092412 129541030934.79411 1470.121780419921 0.005351787585987137 9.45915003841848e-06 -0.003811319465878837 23994186.74255478 89.07095544236498 5.603103758926898
293 2.016354373847353 0.06773755385580861 0.0776701506922517 136685689093.0688 542.9227248488031 0.005261186015505169 2.644908830182127e-06 -0.004103775526658433 16073791.377157208 83.27606115680874 2.2280329911012284
294 2.6656097913052337 0.040681731393672725 0.04307193176899242 143020562662.46283 1208.9931467032854 0.0017522407588327486 2.7089515186277925e-07 -0.19701196119820402 256202601.8744024 36.66570246922919 238.18611090720225
295 2.7834542390347785 0.026360463582715998 0.14929065592923285 152346166625.45764 240.32891356571506 0.003935370898862327 7.30919714808926e-06 -0.001551442980384774 6831609.964977957 85.98830976330774 0.3728566059350277
296 1.2116712982771045 0.07911760326114853 0.11039028427685474 122653054422.75237 942.102232455435 0.008733814715301595 8.86919966074582e-06 -0.0005135330986130388 7103939.887531149 83.07272402775914 0.4838006786431009
297 1.3743417983180422 0.07603784896307911 0.05026209108819763 130676803187.83884 1976.5708030753901 0.003821821290732896 8.045818570399575e-07 -0.016266969392967665 84849141.58795275 41.23203665261483 32.15281675666089
298 2.0690065573514795 0.02248557684543056 0.14406425226894867 151244101150.64072 341.9052137577071 0.003239367815072939 5.602623980454012e-06 -0.0011912424166293971 9094992.56856866 52.61284502081509 0.4072919930949216
299 2.6751069756974353 0.06320983032140148 0.09257444072869406 100880770512.19016 362.8125614439693 0.00585161469055939 4.1790413614801725e-06 -0.00549160714740934 10749986.04889828 122.88150793080075 1.992424055595592
300 2.161070148505975 0.05567257776565458 0.09899735765114717 200734643086.90546 831.3373741828162 0.005511438092427811 4.5012267733521605e-06 -0.0030953475561482768 19756448.814332534 93.49824404454299 2.573278109511506
301 1.9431887660878542 0.058471811981890304 0.10969641005462585 212336367484.17975 1817.640943138909 0.006414147863802424 6.431948395661203e-06 -0.0032551040880256102 30119166.95645154 97.84161557279313 5.916610464574188
FESurrogateModelTutorial/data/reference/beam2d_lhs_300_metadata.json
+36
View File
@@ -0,0 +1,36 @@
{
"dataset_name": "beam2d_lhs_300",
"sample_count": 300,
"random_seed": 20260521,
"unit_system": "SI",
"fea_model": "2D Euler-Bernoulli beam/frame, linear static",
"target_columns": [
"tip_uy_m",
"max_abs_bending_stress_pa",
"mass_kg",
"compliance_j"
],
"parameter_bounds": {
"L_m": {
"lower": 1.0,
"upper": 3.0
},
"b_m": {
"lower": 0.02,
"upper": 0.08
},
"h_m": {
"lower": 0.04,
"upper": 0.16
},
"E_pa": {
"lower": 100000000000.0,
"upper": 220000000000.0
},
"P_n": {
"lower": 100.0,
"upper": 2000.0
}
},
"notes": "Generated by notebooks/00_beam2d_fea_dataset.ipynb using src/femsurrogate."
}
FESurrogateModelTutorial/docs/ADR.md
+76
View File
@@ -0,0 +1,76 @@
# Architecture Decision Records
## 철학
이 프로젝트는 연구용 개념 전달과 재현성을 우선한다. 구현은 작고 명시적이어야 하며, notebook 교육 흐름과 테스트 가능한 Python 모듈 사이의 경계를 분명히 둔다.
---
## ADR-001: Python tutorial project로 구성
**결정**: Python `>=3.12,<3.15` 기반의 문서 + notebook + src package 구조를 사용한다.
**이유**: 대상 사용자는 FEM/CAE 연구자이며 Python scientific stack에 익숙하다. NumPy, SciPy, scikit-learn, pandas, matplotlib로 FEM 데이터 생성과 surrogate 모델링을 모두 재현할 수 있다.
**트레이드오프**: 브라우저 대시보드 기반 상호작용은 제공하지 않는다. 시각적 결과는 notebook과 저장된 figure로 제한한다.
---
## ADR-002: `uv`와 `pyproject.toml` 사용
**결정**: 의존성 관리는 `uv`, 프로젝트 설정은 `pyproject.toml`, lock은 `uv.lock`으로 관리한다.
**이유**: 튜토리얼 재현성을 높이고, pytest/ruff/jupyter 실행 명령을 하나의 환경에서 고정하기 쉽다.
**트레이드오프**: conda 기반 연구실 환경보다 초기 학습 비용이 있을 수 있다. 대신 repository-local workflow가 단순해진다.
---
## ADR-003: 자체 2D Euler-Bernoulli beam/frame solver 사용
**결정**: FEM 데이터는 NumPy/SciPy로 구현한 2-node 2D Euler-Bernoulli beam/frame element에서 생성한다.
**이유**: 외부 CAE solver 없이 해석 데이터 생성 과정을 완전히 설명할 수 있다. 요소 강성, 조립, 경계조건, 응답 계산이 surrogate 학습 데이터와 직접 연결된다.
**트레이드오프**: 산업용 고충실도 해석과 차이가 있다. v1은 선형 정적, slender beam 가정에 제한된다.
---
## ADR-004: Notebook은 orchestration layer로 제한
**결정**: 핵심 계산과 학습 helper는 `src/femsurrogate/`에 두고 notebook은 설명, 호출, 시각화, 해석을 담당한다.
**이유**: notebook hidden state 문제를 줄이고, pytest로 핵심 로직을 검증할 수 있다. 모델별 notebook도 같은 helper를 사용하므로 비교 조건이 일관된다.
**트레이드오프**: 독자가 처음 볼 파일 수는 늘어난다. 대신 코드 재사용성과 검증 가능성이 높아진다.
---
## ADR-005: scikit-learn 중심 surrogate 모델
**결정**: Response Surface, Gaussian Process/Kriging, Random Forest, Gradient Boosting, MLP를 모두 scikit-learn API로 구현한다.
**이유**: 공통 `fit/predict` 인터페이스를 사용하면 모델별 비교가 단순하다. 연구자에게 익숙하고 설치 부담이 낮다.
**트레이드오프**: PyTorch 기반 deep learning, GPU 학습, 복잡한 Bayesian optimization framework는 제외한다.
---
## ADR-006: 기준 데이터셋은 CSV + metadata JSON
**결정**: 기준 FEM 데이터는 CSV로 저장하고, 생성 조건은 JSON metadata로 별도 저장한다.
**이유**: CSV는 notebook, pandas, spreadsheet, 다른 ML 도구에서 쉽게 읽을 수 있다. Metadata JSON은 seed, bounds, 단위, target 정보를 명확히 남긴다.
**트레이드오프**: 대용량/버전관리형 데이터셋에는 Parquet, DVC, database가 더 적합할 수 있다. v1에서는 단순성과 가독성을 우선한다.
---
## ADR-007: 모델별 이론 문서와 모델별 notebook 분리
**결정**: 각 surrogate 모델은 별도 이론 문서와 별도 실습 notebook으로 구성한다. 최종 비교는 별도 notebook에서 수행한다.
**이유**: 모델별 가정, 장점, 실패 모드, hyperparameter가 다르므로 독립적으로 학습하는 편이 좋다. 최종 비교 notebook은 같은 입력 데이터와 metric을 기준으로 모델 선택을 돕는다.
**트레이드오프**: notebook 수가 늘어난다. 대신 각 notebook의 목표가 분명하고 실행 실패 범위가 작아진다.
---
## ADR-008: Notebook 중심 범위 고정
**결정**: 브라우저 앱과 디자인 시스템 계획을 프로젝트 범위에서 제외한다.
**이유**: 튜토리얼은 notebook 기반이다. 브라우저 앱 설계 지침은 현재 목표에 직접 기여하지 않으며 미래 agent에게 잘못된 구현 방향을 줄 수 있다.
**트레이드오프**: 웹 기반 인터랙티브 학습 환경은 제공하지 않는다.
FESurrogateModelTutorial/docs/ARCHITECTURE.md
+226
View File
@@ -0,0 +1,226 @@
# 아키텍처
## 개요
이 프로젝트는 문서와 Jupyter notebook이 중심인 교육용 Python 프로젝트다. 재사용 가능한 계산 로직은 `src/femsurrogate/`에 모듈화하고, notebook은 설명, 시각화, 실행 순서, 결과 해석을 담당한다.
## 기술 스택
- Python `>=3.12,<3.15`
- `uv` + `pyproject.toml` + `uv.lock`
- NumPy, SciPy
- pandas, matplotlib
- scikit-learn
- JupyterLab, ipykernel, nbconvert
- pytest, ruff
- joblib, CSV, JSON
## 디렉토리 구조
```text
docs/
PRD.md
ARCHITECTURE.md
ADR.md
theory/
00_surrogate_modeling_for_fem.md
01_doe_sampling_validation.md
02_response_surface_methodology.md
03_gaussian_process_kriging.md
04_random_forest.md
05_gradient_boosting.md
06_mlp_neural_network.md
BeamExamples/
CantileverBeam.txt
CantileverBeam_Displacements.txt
notebooks/
00_beam2d_fea_dataset.ipynb
01_response_surface_surrogate.ipynb
02_gaussian_process_kriging_surrogate.ipynb
03_random_forest_surrogate.ipynb
04_gradient_boosting_surrogate.ipynb
05_mlp_surrogate.ipynb
06_compare_surrogate_models.ipynb
src/femsurrogate/
fea/
element.py
model.py
io.py
assembly.py
solver.py
responses.py
benchmark.py
data/
bounds.py
sampling.py
dataset.py
schema.py
surrogates/
common.py
rsm.py
gpr.py
random_forest.py
boosting.py
mlp.py
registry.py
plotting/
diagnostics.py
comparison.py
tests/
data/
reference/
processed/
reports/
results/
predictions/
figures/
```
## 핵심 모듈 책임
### `femsurrogate.fea`
2D Euler-Bernoulli beam/frame 요소 기반 선형 정적 해석을 담당한다.
- `element.py`: local 6x6 stiffness matrix와 좌표 변환 행렬.
- `model.py`: node, element, support, load, material, section, parameter dataclass.
- `io.py`: `BeamExamples/*.txt`의 간단한 텍스트 fixture parser.
- `assembly.py`: global sparse stiffness matrix 조립.
- `solver.py`: 경계조건 적용과 `K u = f` 풀이.
- `responses.py`: tip displacement, bending stress, mass, compliance 계산.
- `benchmark.py`: cantilever analytical solution 등 검증 helper.
### `femsurrogate.data`
입력 공간 정의, 샘플링, batch 해석, dataset schema를 담당한다.
- `bounds.py`: 설계변수 범위와 단위.
- `sampling.py`: Latin Hypercube Sampling.
- `dataset.py`: 샘플별 FEM 실행과 CSV/metadata 저장.
- `schema.py`: 컬럼명, target명, 단위, split seed.
### `femsurrogate.surrogates`
scikit-learn 기반 모델 생성, 학습, 평가를 담당한다.
- `common.py`: train/test split, scaling, metric, timing, JSON 저장.
- `rsm.py`: `PolynomialFeatures` + `Ridge`.
- `gpr.py`: `GaussianProcessRegressor`.
- `random_forest.py`: `RandomForestRegressor`.
- `boosting.py`: `GradientBoostingRegressor`.
- `mlp.py`: `MLPRegressor`.
- `registry.py`: notebook에서 모델명을 통해 builder를 가져오는 작은 registry.
### `femsurrogate.plotting`
모델 진단과 최종 비교 그림을 담당한다.
- `diagnostics.py`: parity plot, residual plot, error histogram.
- `comparison.py`: 모델별 metric table, bar plot, prediction-time comparison.
## 주요 인터페이스
```python
def run_beam2d_case(params: BeamParameters) -> AnalysisResult:
...
def generate_lhs_samples(bounds: ParameterBounds, n: int, seed: int) -> pd.DataFrame:
...
def build_dataset(samples: pd.DataFrame) -> pd.DataFrame:
...
def make_model(model_name: str, random_state: int):
...
def evaluate_model(model, X_train, X_test, y_train, y_test) -> MetricsReport:
...
```
## 데이터 흐름
```text
Parameter bounds
-> Latin Hypercube samples
-> Beam2D FEM batch analysis
-> data/reference/beam2d_lhs_300.csv
-> model-specific notebooks
-> reports/results/<model>_metrics.json
-> reports/predictions/<model>_predictions.csv
-> notebooks/06_compare_surrogate_models.ipynb
```
## FEM 해석 설계
- 요소: 2-node 2D Euler-Bernoulli frame element.
- 노드 DOF: `[ux, uy, rz]`.
- Local stiffness matrix: axial `EA/L` 항과 bending `EI` 항을 포함한 6x6 matrix.
- Global assembly: sparse matrix 기반.
- Solver: constrained DOF 제거 후 `scipy.sparse.linalg.spsolve`.
- 기준 검증: cantilever tip displacement `P L^3 / (3 E I)`.
## Solver Verification Fixture
`BeamExamples/`의 cantilever 예제는 solver 구현의 canonical regression fixture다.
```text
BeamExamples/CantileverBeam.txt
BeamExamples/CantileverBeam_Displacements.txt
```
입력 파일은 다음 항목을 포함한다.
- Section/material metadata: `Area`, `J`, `Iyy`, `Izz`, `ElasticModulus`, `Poisson'sRatio`.
- Geometry: `Node, NodeID, X, Y`.
- Connectivity: `Beam, BeamID, NodeID1, NodeID2`.
- Boundary condition: `Fix, NodeID`.
- Load: `NodeLoad, NodeID, Fx, Fy, Mz`.
2D in-plane Euler-Bernoulli frame solver는 `Area`, `Izz`, `ElasticModulus`, node coordinates, beam connectivity, fixed nodes, nodal loads를 사용한다. `J`, `Iyy`, `Poisson'sRatio`는 fixture metadata로 보존하되 v1 해석에는 사용하지 않는다.
기준 변위 파일은 다음 형식을 가진다.
```text
# NodeID, Ux, Uy, Rz
1 0.000000, 0.000000, 0.000000
...
```
검증 test는 solver 결과의 모든 node별 `[Ux, Uy, Rz]`를 기준 파일과 비교한다. 기준 파일 값은 소수점 6자리로 반올림되어 있으므로 기본 허용오차는 `atol=5e-7`, `rtol=1e-6`로 둔다. Tip displacement는 별도로 해석해 `P L^3 / (3 E I)`와 비교해 부호와 크기를 확인한다.
## Dataset Schema
기본 dataset은 SI 단위 컬럼을 사용한다.
```text
L_m
b_m
h_m
E_pa
P_n
A_m2
I_m4
tip_uy_m
max_abs_bending_stress_pa
mass_kg
compliance_j
```
Metadata JSON에는 다음을 포함한다.
```text
dataset_name
created_by
sample_count
random_seed
parameter_bounds
target_columns
unit_system
fea_model
notes
```
## Notebook 책임
- Notebook은 한 번에 위에서 아래로 실행 가능해야 한다.
- Notebook 셀에 핵심 FEM 또는 ML helper 구현을 길게 두지 않는다.
- 각 모델별 notebook은 같은 dataset, target, split seed를 사용한다.
- 각 모델별 notebook은 metric JSON과 prediction CSV를 저장한다.
- 최종 비교 notebook은 이전 notebook 결과물을 읽어 비교만 수행한다.
## 검증 전략
- Unit tests: FEM element, solver, dataset generation, model factory.
- Regression tests: `BeamExamples/CantileverBeam.txt`를 해석하고 `BeamExamples/CantileverBeam_Displacements.txt`와 비교.
- Integration tests: 작은 sample count로 dataset 생성과 모든 surrogate smoke test.
- Notebook tests: `nbconvert --execute`로 순차 실행.
- Documentation checks: 문서의 경로와 notebook/file 이름이 실제 구조와 일치하는지 검토.
FESurrogateModelTutorial/docs/PRD.md
+60
View File
@@ -0,0 +1,60 @@
# PRD: FEM Surrogate Tutorial
## 목표
FEM 기반 구조해석 데이터로 surrogate model을 구축하고 검증하는 전체 절차를 학습할 수 있는 한국어 튜토리얼을 만든다. 독자는 2D beam 요소로 해석 데이터를 직접 생성하고, 여러 surrogate 모델을 같은 데이터셋에서 학습, 평가, 비교한다.
## 사용자
- FEM과 선형 정적 구조해석의 기본 개념을 아는 대학원생.
- CAE 해석 결과를 기계학습 모델로 근사하고 싶은 연구자.
- surrogate 기반 설계 탐색, 민감도 분석, 최적화의 입문 파이프라인을 재현하고 싶은 엔지니어.
## 사용자 문제
고정밀 구조해석은 반복 설계, 불확실성 분석, 최적화에서 계산 비용이 커진다. Surrogate model은 해석 데이터에서 입력 변수와 응답의 관계를 학습하여 빠른 근사 예측을 제공하지만, 모델별 가정, 데이터 설계, 검증 방법, 외삽 위험을 함께 이해해야 실무적으로 사용할 수 있다.
## 학습 성과
튜토리얼을 완료한 독자는 다음을 할 수 있어야 한다.
1. 2D Euler-Bernoulli beam/frame 요소를 이용해 선형 정적 FEM 해석 데이터를 생성한다.
2. DOE와 Latin Hypercube Sampling으로 입력 공간을 정의하고 해석 케이스를 만든다.
3. Response Surface, Gaussian Process/Kriging, Random Forest, Gradient Boosting, MLP를 같은 데이터셋에 적용한다.
4. RMSE, MAE, R2, residual, parity plot, uncertainty 또는 feature importance로 모델을 진단한다.
5. 최종 비교표를 통해 구조해석 surrogate 문제에 맞는 모델을 선택하는 기준을 설명한다.
## 핵심 산출물
- `docs/theory/`: surrogate 모델별 이론 문서와 출처.
- `notebooks/`: 데이터 생성, 모델별 학습, 최종 비교 notebook.
- `src/femsurrogate/`: notebook에서 재사용하는 FEM, 데이터, 모델, plotting helper.
- `tests/`: FEM 공식 검증, dataset schema, surrogate pipeline smoke test.
- `BeamExamples/`: 2D beam solver 검증용 cantilever 예제와 기준 변위 파일.
- `data/reference/`: 재현 가능한 기준 해석 데이터.
- `reports/`: 모델별 metric, 예측값, 그림.
## MVP 범위
- 선형 정적 2D Euler-Bernoulli beam/frame 요소.
- 기준 구조: fixed-free cantilever beam 또는 간단한 planar frame.
- Solver 검증 기준 fixture: `BeamExamples/CantileverBeam.txt`와 `BeamExamples/CantileverBeam_Displacements.txt`.
- 입력 변수: `L`, `b`, `h`, `E`, `P`.
- 응답 변수: `tip_uy_m`, `max_abs_bending_stress_pa`, `mass_kg`, `compliance_j`.
- Surrogate 모델:
- Response Surface Methodology: polynomial features + Ridge regression.
- Gaussian Process Regression/Kriging.
- Random Forest Regressor.
- Gradient Boosting Regressor.
- Multi-layer Perceptron Regressor.
## MVP 제외 사항
- 상용 CAE 연동.
- 3D beam, shell, solid element.
- Timoshenko beam, geometric nonlinearity, material nonlinearity, contact, buckling, modal, transient analysis.
- PyTorch/TensorFlow 기반 deep learning framework.
- Bayesian optimization, active learning, MLflow, DVC, browser dashboard.
- 배포용 Python package publishing.
## 성공 기준
- 이론 문서가 모델별로 분리되어 있고 각 문서에 출처가 있다.
- FEM solver가 `BeamExamples/CantileverBeam.txt`를 해석했을 때 `BeamExamples/CantileverBeam_Displacements.txt`의 모든 노드 `Ux`, `Uy`, `Rz` 기준값과 허용오차 내에서 일치한다.
- `00_beam2d_fea_dataset.ipynb`가 데이터셋을 생성하고, 생성 데이터가 동일 seed에서 재현된다.
- 모든 모델별 notebook이 같은 dataset과 split을 사용한다.
- 최종 비교 notebook이 모든 모델의 metric JSON을 읽어 하나의 비교표와 그림을 만든다.
- FEM solver는 cantilever beam 해석해와 BeamExamples regression fixture를 모두 비교하는 pytest를 통과한다.
- 전체 notebook은 `nbconvert --execute`로 순서대로 실행 가능하다.
FESurrogateModelTutorial/docs/theory/00_surrogate_modeling_for_fem.md
+98
View File
@@ -0,0 +1,98 @@
# FEM 구조해석을 위한 Surrogate Modeling 개요
## 목적
Surrogate model은 계산 비용이 큰 해석 모델을 반복 호출하기 어려울 때, 입력 변수와 출력 응답 사이의 관계를 데이터 기반으로 근사하는 모델이다. FEM 구조해석에서는 설계변수 변화에 따른 변위, 응력, 질량, compliance 같은 응답을 빠르게 예측하기 위해 사용한다.
이 튜토리얼의 surrogate는 고충실도 산업용 solver를 대체하는 범용 도구가 아니라, 제한된 입력 범위 안에서 반복 설계 탐색과 모델 비교를 학습하기 위한 교육용 근사 모델이다.
## 문제 정의
FEM 해석 모델을 다음 함수로 본다.
```text
y = f(x)
```
- `x`: 설계변수 벡터. 예: beam 길이 `L`, 폭 `b`, 높이 `h`, 탄성계수 `E`, 하중 `P`.
- `f`: FEM solver. 이 튜토리얼에서는 2D Euler-Bernoulli beam/frame solver.
- `y`: 응답. 예: tip displacement, maximum bending stress, mass, compliance.
Surrogate model은 해석 데이터 `{x_i, y_i}`를 이용해 `f`를 근사하는 `\hat{f}`를 만든다.
```text
\hat{y} = \hat{f}(x)
```
좋은 surrogate는 빠른 예측뿐 아니라, 어떤 영역에서 믿을 수 있고 어떤 영역에서 위험한지도 설명할 수 있어야 한다.
## 왜 FEM에서 필요한가
구조해석에서는 다음 작업이 반복 평가를 요구한다.
- 설계변수 sweep.
- 민감도 분석.
- 최적화.
- 불확실성 전파.
- 신뢰성 분석.
- inverse problem 또는 model calibration.
Queipo et al.은 surrogate-based analysis and optimization이 비싼 high-fidelity model의 계산 부담을 줄이고 민감도/최적화 연구를 가능하게 한다고 정리한다. Forrester와 Keane도 긴 계산 시간이 필요한 aerospace design evaluation에서 surrogate 기반 방법이 효율적 최적화를 가능하게 하는 배경을 설명한다.
## 전체 workflow
```text
1. 해석 문제 정의
2. 입력 변수와 범위 설정
3. DOE로 샘플 생성
4. FEM batch 해석
5. 데이터 정리와 train/test split
6. surrogate 모델 학습
7. 검증과 진단
8. 모델 비교
9. 설계 탐색 또는 최적화에 활용
```
이 workflow에서 가장 중요한 판단은 데이터의 범위다. Surrogate는 학습한 입력 영역 안에서만 신뢰할 수 있다. 학습 범위를 벗어난 외삽은 모델별로 다르게 실패하며, 예측값이 그럴듯해 보여도 구조적으로 틀릴 수 있다.
## 이 튜토리얼의 FEM 모델
기준 해석 모델은 2D Euler-Bernoulli beam/frame element이다.
- 노드당 자유도: `ux`, `uy`, `rz`.
- 요소: 축방향 변형과 굽힘 변형을 포함한 2-node frame element.
- 해석: 선형 정적 해석.
- solver: sparse global stiffness matrix를 조립하고 `scipy.sparse.linalg.spsolve`로 선형 시스템을 푼다.
- 검증: cantilever beam tip displacement 해석해 `P L^3 / (3 E I)`와 비교한다.
이 선택은 학습 목적에 맞다. Beam 요소는 수식이 충분히 작아 직접 구현할 수 있고, 단면 형상과 하중 변화가 변위/응력에 비선형적인 영향을 주므로 surrogate 비교에도 적합하다.
## 모델 비교 관점
이 튜토리얼은 다음 질문에 답하도록 설계한다.
| 모델 | 핵심 질문 |
| --- | --- |
| Response Surface | 낮은 차수 다항식으로 구조 응답을 충분히 설명할 수 있는가? |
| Gaussian Process/Kriging | 적은 데이터에서 예측 불확실성을 함께 얻을 수 있는가? |
| Random Forest | 비선형성과 변수 상호작용을 튼튼하게 포착하는가? |
| Gradient Boosting | 작은 tree를 순차적으로 더해 높은 정확도를 얻는가? |
| MLP | scaling과 충분한 데이터가 있을 때 매끄러운 비선형 근사가 가능한가? |
## 검증 원칙
Surrogate 검증은 단순히 test R2 하나로 끝내지 않는다.
- Train/test split은 고정 seed로 재현한다.
- K-fold cross validation으로 표본 의존성을 확인한다.
- RMSE, MAE, R2를 함께 본다.
- Parity plot으로 편향과 outlier를 본다.
- Residual plot으로 입력 영역별 오류 구조를 본다.
- 모델별 uncertainty 또는 feature importance를 해석한다.
- 해석 데이터의 물리 단위와 target 정의를 metadata에 남긴다.
## 실패 모드
- 학습 영역 밖에서 외삽한다.
- 입력 변수 범위가 물리적으로 의미 없는 조합을 포함한다.
- 응력처럼 국소적이고 비선형적인 응답을 너무 단순한 모델로 근사한다.
- train/test split이 샘플링 편향을 숨긴다.
- feature scaling을 하지 않아 MLP나 GPR 학습이 불안정하다.
- 예측 정확도만 보고 물리 제약을 확인하지 않는다.
## References
- Queipo, N. V. et al. (2005), "Surrogate-based analysis and optimization", Progress in Aerospace Sciences. https://doi.org/10.1016/j.paerosci.2005.02.001
- Forrester, A. I. J. and Keane, A. J. (2009), "Recent advances in surrogate-based optimization", Progress in Aerospace Sciences. https://doi.org/10.1016/j.paerosci.2008.11.001
- SciPy `spsolve` documentation. https://docs.scipy.org/doc/scipy/reference/generated/scipy.sparse.linalg.spsolve.html
FESurrogateModelTutorial/docs/theory/01_doe_sampling_validation.md
+114
View File
@@ -0,0 +1,114 @@
# DOE, Sampling, Validation
## 목적
Surrogate model의 품질은 모델 종류만큼이나 데이터 설계에 좌우된다. FEM surrogate에서는 입력 변수 범위, 샘플링 방법, train/test split, 검증 지표가 모두 모델 해석에 영향을 준다.
## 입력 공간 정의
이 튜토리얼의 기본 입력 변수는 다음과 같다.
| 변수 | 의미 | 단위 | 예시 범위 |
| --- | --- | --- | --- |
| `L_m` | beam length | m | 1.0-3.0 |
| `b_m` | rectangular section width | m | 0.02-0.08 |
| `h_m` | rectangular section height | m | 0.04-0.16 |
| `E_pa` | Young's modulus | Pa | 100e9-220e9 |
| `P_n` | tip point load magnitude | N | 100-2000 |
파생 변수는 FEM 해석 직전에 계산한다.
```text
A = b h
I = b h^3 / 12
```
`h`는 bending stiffness에 세제곱으로 들어가므로, tip displacement와 bending stress에 큰 영향을 준다. 이런 구조적 비선형성 때문에 단순 선형 회귀보다 다양한 surrogate 비교가 의미를 가진다.
## Latin Hypercube Sampling
Latin Hypercube Sampling(LHS)은 각 입력 변수의 marginal distribution을 층화하여, 적은 샘플에서도 각 변수 범위를 비교적 고르게 덮도록 설계한다. McKay, Beckman, Conover의 1979년 논문은 computer code output 분석에서 sampling plan을 비교한 고전적 출처다.
SciPy의 `scipy.stats.qmc.LatinHypercube`는 `[0, 1)^d` 단위 hypercube에 샘플을 만들고, 이후 사용자가 물리 범위로 scaling한다.
```text
u ~ LHS([0,1)^d)
x_j = lower_j + u_j (upper_j - lower_j)
```
이 튜토리얼은 다음을 기본값으로 사용한다.
- `n_samples = 300`
- `seed = 20260521`
- `target = tip_uy_m`
- 동일 dataset과 동일 split을 모든 model notebook에서 사용
## Train/Test Split
단일 test set만으로 모델을 판단하면 샘플 배치에 민감할 수 있다. 따라서 다음 두 가지를 함께 사용한다.
- Hold-out test set: 최종 성능 비교용.
- K-fold cross validation: 학습 데이터 안에서 모델 안정성 확인용.
추천 기본값:
```text
test_size = 0.2
cv_folds = 5
random_state = 20260521
```
## 평가 지표
### RMSE
큰 오차에 민감하다. 구조해석 surrogate에서 위험한 outlier를 확인하는 데 유용하다.
```text
RMSE = sqrt(mean((y - y_hat)^2))
```
### MAE
평균적인 절대 오차를 직관적으로 보여준다.
```text
MAE = mean(abs(y - y_hat))
```
### R2
분산 설명력을 나타낸다. 다만 target scale이나 test set 분포에 따라 해석이 왜곡될 수 있으므로 RMSE/MAE와 함께 본다.
```text
R2 = 1 - sum((y - y_hat)^2) / sum((y - mean(y))^2)
```
## Plot 기반 진단
- Parity plot: 예측값과 실제값이 `y=x` 선 주변에 있는지 확인.
- Residual plot: 예측값 또는 주요 입력 변수에 따른 오차 패턴 확인.
- Error histogram: 오차 분포와 outlier 확인.
- Model comparison bar plot: RMSE, MAE, R2, 학습 시간, 예측 시간 비교.
## Dataset Metadata
CSV만으로는 dataset의 생성 조건을 알기 어렵다. 따라서 metadata JSON을 함께 저장한다.
```json
{
"dataset_name": "beam2d_lhs_300",
"sample_count": 300,
"random_seed": 20260521,
"unit_system": "SI",
"fea_model": "2D Euler-Bernoulli beam/frame, linear static",
"target_columns": [
"tip_uy_m",
"max_abs_bending_stress_pa",
"mass_kg",
"compliance_j"
]
}
```
## 주의점
- DOE 범위는 surrogate의 유효 영역이다. 범위 밖 예측은 별도 경고를 둔다.
- 물리적으로 불가능한 조합을 허용하지 않는다.
- FEM solver 실패 케이스는 조용히 버리지 말고 metadata에 기록한다.
- 단위가 섞이면 모델 비교가 무의미해진다.
- 동일 데이터셋을 쓰지 않으면 모델별 비교가 공정하지 않다.
## References
- McKay, M. D., Beckman, R. J., and Conover, W. J. (1979), "Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code", Technometrics. https://doi.org/10.1080/00401706.1979.10489755
- OSTI bibliographic record for McKay et al. https://www.osti.gov/biblio/5236110
- SciPy `LatinHypercube` documentation. https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.qmc.LatinHypercube.html
FESurrogateModelTutorial/docs/theory/02_response_surface_methodology.md
+77
View File
@@ -0,0 +1,77 @@
# Response Surface Methodology
## 핵심 아이디어
Response Surface Methodology(RSM)는 입력 변수와 응답 사이의 관계를 낮은 차수 다항식으로 근사한다. 구조해석 surrogate에서는 물리 응답이 충분히 매끄럽고 입력 범위가 좁을 때 강력한 기준선이 된다.
기본 2차 response surface는 다음 형태다.
```text
y = beta_0 + sum beta_i x_i + sum beta_ii x_i^2 + sum beta_ij x_i x_j + epsilon
```
- `x_i`: scaling된 설계변수.
- `beta`: 회귀 계수.
- `x_i x_j`: 변수 상호작용.
- `epsilon`: 모델이 설명하지 못한 잔차.
## FEM surrogate에서의 의미
Beam 문제에서는 `I = b h^3 / 12` 때문에 응답이 입력 변수에 대해 비선형이다. 낮은 차수 다항식은 이 관계를 완벽히 재현하지 못할 수 있지만, 다음 장점이 있다.
- 빠르다.
- 계수 해석이 가능하다.
- 적은 데이터에서도 안정적이다.
- 복잡한 모델의 baseline으로 적합하다.
RSM은 특히 설계변수 범위가 좁고 응답이 단조롭고 매끄러울 때 유용하다.
## 구현 선택
이 튜토리얼에서는 scikit-learn의 `PolynomialFeatures`와 `Ridge`를 조합한다.
```text
StandardScaler
-> PolynomialFeatures(degree=2, include_bias=False)
-> Ridge(alpha=...)
```
`PolynomialFeatures`는 입력 변수의 다항 조합을 만들고, `Ridge`는 L2 regularization으로 계수 크기를 제어한다. 일반 선형회귀 대신 Ridge를 쓰는 이유는 다항 feature가 늘어나면 feature 간 상관성이 커지고 계수가 불안정해질 수 있기 때문이다.
## Notebook 실습 포인트
`notebooks/01_response_surface_surrogate.ipynb`는 다음을 보여준다.
1. 동일 FEM dataset 로드.
2. target `tip_uy_m` 선택.
3. degree 1, 2, 3 비교.
4. Ridge `alpha` 변화에 따른 train/test error 비교.
5. parity plot과 residual plot.
6. 다항 feature 이름과 계수 크기 해석.
## 장점
- 학습과 예측이 매우 빠르다.
- 작은 데이터에서 baseline으로 좋다.
- 변수 간 interaction을 명시적으로 볼 수 있다.
- extrapolation이 tree model보다 연속적이다.
## 한계와 실패 모드
- 실제 응답이 강하게 비선형이면 낮은 차수 다항식으로 부족하다.
- 높은 차수는 과적합과 수치 불안정을 만든다.
- 입력 scaling 없이 다항 feature를 만들면 큰 단위의 변수가 학습을 지배할 수 있다.
- 설계공간 경계 밖에서는 다항식이 물리적으로 말이 안 되는 큰 값을 낼 수 있다.
## 구조해석 해석 기준
RSM이 좋은 선택인 경우:
- 설계변수 수가 적다.
- 입력 범위가 좁다.
- 응답이 매끄럽고 단조적이다.
- 설명 가능한 surrogate가 중요하다.
RSM을 피해야 하는 경우:
- 응답에 threshold, discontinuity, contact-like behavior가 있다.
- 입력 범위가 넓고 상호작용이 복잡하다.
- 국소 응력 peak처럼 고차 비선형성이 크다.
## References
- Box, G. E. P. and Wilson, K. B. (1951), "On the Experimental Attainment of Optimum Conditions", Journal of the Royal Statistical Society Series B. https://doi.org/10.1111/j.2517-6161.1951.tb00067.x
- scikit-learn `PolynomialFeatures` documentation. https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.PolynomialFeatures.html
- scikit-learn `Ridge` documentation. https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html
FESurrogateModelTutorial/docs/theory/03_gaussian_process_kriging.md
+86
View File
@@ -0,0 +1,86 @@
# Gaussian Process Regression and Kriging
## 핵심 아이디어
Gaussian Process Regression(GPR)은 함수값을 확률변수로 보고, 입력 위치 사이의 상관관계를 kernel로 정의한다. Engineering design 분야에서는 Kriging이라는 이름으로 널리 사용된다.
GPR은 예측 평균뿐 아니라 예측 표준편차를 제공한다.
```text
y(x) ~ GP(m(x), k(x, x'))
```
- `m(x)`: mean function.
- `k(x, x')`: covariance function 또는 kernel.
- 예측 결과: `mean`, `standard deviation`.
## FEM surrogate에서의 의미
FEM 해석 데이터는 deterministic한 computer experiment인 경우가 많다. 같은 입력을 넣으면 같은 출력이 나온다. 이런 상황에서 GPR/Kriging은 적은 해석점으로 매끄러운 응답면을 만들고, 학습점에서 먼 영역의 불확실성을 크게 줄 수 있어 surrogate 신뢰도 설명에 유리하다.
Sacks et al.의 computer experiment 연구는 계산 모델 입력과 출력 사이의 응답을 stochastic process로 모델링하는 관점을 제시했다. Rasmussen과 Williams의 GPML은 Gaussian process의 수학적 기반과 kernel 관점을 체계적으로 설명한다.
## 구현 선택
이 튜토리얼에서는 다음 kernel을 기본으로 사용한다.
```text
ConstantKernel * RBF + WhiteKernel
```
- `ConstantKernel`: 응답 scale.
- `RBF`: 입력 공간에서 가까운 점은 비슷한 응답을 가진다는 smoothness 가정.
- `WhiteKernel`: 수치 noise 또는 모델 불일치 허용.
Notebook pipeline:
```text
StandardScaler
-> GaussianProcessRegressor(kernel=..., normalize_y=True)
```
## Hyperparameter 의미
- `length_scale`: 각 입력 방향에서 함수가 얼마나 빨리 변하는지 나타낸다.
- `noise_level`: 해석 데이터의 noise 또는 모델 불일치 허용량이다.
- `alpha`: numerical stability를 위한 diagonal jitter로 사용할 수 있다.
- `n_restarts_optimizer`: kernel hyperparameter 최적화의 local optimum 위험을 줄인다.
## Notebook 실습 포인트
`notebooks/02_gaussian_process_kriging_surrogate.ipynb`는 다음을 보여준다.
1. 동일 dataset과 split 로드.
2. RBF kernel 기반 GPR 학습.
3. 예측 평균과 표준편차 계산.
4. parity plot에 uncertainty band 또는 error coloring 추가.
5. 입력 공간에서 학습점과 먼 샘플의 uncertainty 확인.
6. 학습 sample 수 증가에 따른 RMSE와 예측 표준편차 변화.
## 장점
- 작은 데이터에서 강력하다.
- 예측 uncertainty를 제공한다.
- Smooth response surface에 적합하다.
- Bayesian optimization과 active learning으로 확장하기 좋다.
## 한계와 실패 모드
- 기본 exact GPR은 학습 데이터 수가 커지면 계산 비용이 급격히 증가한다.
- Kernel 선택이 성능을 크게 좌우한다.
- 입력 scaling이 중요하다.
- 고차원 입력에서는 length scale 학습이 불안정할 수 있다.
- 예측 표준편차는 모델 가정 하의 불확실성이지, 모든 물리 오류를 보장하지 않는다.
## 구조해석 해석 기준
GPR/Kriging이 좋은 선택인 경우:
- FEM 해석이 비싸고 sample 수가 작다.
- 응답이 매끄럽다.
- uncertainty 기반 추가 샘플링을 설명하고 싶다.
- 설계공간 탐색에서 신뢰도 경고가 필요하다.
주의할 경우:
- sample 수가 수천 개 이상이다.
- 응답이 불연속적이다.
- 입력 차원이 많고 상호작용이 복잡하다.
## References
- Sacks, J., Welch, W. J., Mitchell, T. J., and Wynn, H. P. (1989), "Design and Analysis of Computer Experiments", Statistical Science. https://doi.org/10.1214/ss/1177012413
- Sacks, J., Schiller, S. B., and Welch, W. J. (1989), "Designs for Computer Experiments", Technometrics. https://doi.org/10.1080/00401706.1989.10488474
- Rasmussen, C. E. and Williams, C. K. I. (2006), Gaussian Processes for Machine Learning. https://gaussianprocess.org/gpml/chapters/RW.pdf
- scikit-learn Gaussian Process documentation. https://scikit-learn.org/stable/modules/gaussian_process.html
FESurrogateModelTutorial/docs/theory/04_random_forest.md
+76
View File
@@ -0,0 +1,76 @@
# Random Forest Surrogate
## 핵심 아이디어
Random Forest는 여러 decision tree를 bootstrap sample로 학습하고 평균하여 예측하는 ensemble 모델이다. 각 tree는 입력 공간을 여러 영역으로 나누고, 회귀 문제에서는 leaf의 평균값을 예측한다.
```text
\hat{f}(x) = (1 / T) sum_{t=1}^{T} h_t(x)
```
- `T`: tree 개수.
- `h_t`: 개별 regression tree.
Breiman의 2001년 Random Forest 논문은 bagging과 random feature selection을 결합한 ensemble 방법을 제시했다.
## FEM surrogate에서의 의미
Random Forest는 비선형성과 변수 상호작용을 명시적 feature engineering 없이 포착할 수 있다. Beam surrogate에서는 `h`, `b`, `L`, `P`, `E`의 비선형 영향과 interaction을 빠르게 잡는 비교 모델로 좋다.
## 구현 선택
이 튜토리얼에서는 scikit-learn의 `RandomForestRegressor`를 사용한다.
기본 설정 예:
```text
RandomForestRegressor(
n_estimators=300,
max_depth=None,
min_samples_leaf=2,
random_state=20260521,
n_jobs=-1
)
```
Tree model은 feature scaling이 필수는 아니지만, 다른 모델과 공통 전처리 구조를 설명하기 위해 입력 column 관리는 동일하게 유지한다.
## Notebook 실습 포인트
`notebooks/03_random_forest_surrogate.ipynb`는 다음을 보여준다.
1. 동일 dataset과 split 로드.
2. `n_estimators`, `max_depth`, `min_samples_leaf` 영향 비교.
3. test metric 계산.
4. parity plot과 residual plot.
5. permutation importance로 입력 변수 영향 확인.
6. feature importance와 beam 물리 관계 비교.
## 장점
- scaling에 덜 민감하다.
- 비선형성과 interaction을 잘 포착한다.
- outlier에 비교적 튼튼하다.
- feature importance를 계산하기 쉽다.
- 학습이 안정적이고 baseline으로 좋다.
## 한계와 실패 모드
- 예측이 piecewise constant라 매끄러운 응답면이 필요한 경우 부자연스러울 수 있다.
- 학습 데이터 범위 밖으로 외삽하지 못한다.
- 물리적으로 단조여야 하는 관계를 자동으로 보장하지 않는다.
- uncertainty는 GPR처럼 원래 제공되는 개념이 아니다.
- feature importance는 correlated feature에서 오해될 수 있다.
## 구조해석 해석 기준
Random Forest가 좋은 선택인 경우:
- 빠르고 안정적인 비선형 baseline이 필요하다.
- 변수 중요도 분석을 보고 싶다.
- 데이터가 중간 규모 이상이다.
- target이 매끄러운 global response다.
주의할 경우:
- 설계 최적화에서 매끄러운 gradient-like response가 필요하다.
- 외삽이 필요하다.
- 응답면의 국소 smoothness가 중요하다.
## References
- Breiman, L. (2001), "Random Forests", Machine Learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
- CiNii bibliographic record for Breiman (2001). https://cir.nii.ac.jp/crid/1360574092892023168
- scikit-learn `RandomForestRegressor` documentation. https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestRegressor.html
FESurrogateModelTutorial/docs/theory/05_gradient_boosting.md
+77
View File
@@ -0,0 +1,77 @@
# Gradient Boosting Surrogate
## 핵심 아이디어
Gradient Boosting은 약한 예측기, 보통 shallow decision tree를 순차적으로 더해 손실함수를 줄이는 additive model이다. 각 단계의 tree는 이전 모델의 오차를 보정하는 방향으로 학습된다.
```text
F_M(x) = F_0(x) + sum_{m=1}^{M} nu h_m(x)
```
- `F_M`: 최종 모델.
- `h_m`: m번째 weak learner.
- `nu`: learning rate.
Friedman의 2001년 논문은 gradient boosting machine을 함수공간에서의 greedy approximation으로 설명한다.
## FEM surrogate에서의 의미
Gradient Boosting은 Random Forest보다 bias를 더 적극적으로 줄이는 경우가 많다. Beam surrogate에서 낮은 차수 RSM이 놓치는 비선형성을 tree ensemble이 순차적으로 보정할 수 있다.
## 구현 선택
이 튜토리얼에서는 scikit-learn의 `GradientBoostingRegressor`를 사용한다.
기본 설정 예:
```text
GradientBoostingRegressor(
loss="squared_error",
learning_rate=0.05,
n_estimators=300,
max_depth=3,
subsample=0.9,
random_state=20260521
)
```
`learning_rate`와 `n_estimators`는 함께 조정해야 한다. 작은 learning rate는 더 많은 tree를 요구하지만 과적합을 완화할 수 있다.
## Notebook 실습 포인트
`notebooks/04_gradient_boosting_surrogate.ipynb`는 다음을 보여준다.
1. 동일 dataset과 split 로드.
2. `learning_rate`와 `n_estimators` tradeoff.
3. staged prediction으로 train/test error curve 확인.
4. parity plot과 residual plot.
5. permutation importance 또는 built-in feature importance 비교.
6. Random Forest와 오차 패턴 비교.
## 장점
- tabular regression에서 높은 성능을 내기 쉽다.
- 비선형성과 interaction을 잘 포착한다.
- model size와 성능의 tradeoff를 조절하기 쉽다.
- staged prediction으로 과적합 진행을 관찰할 수 있다.
## 한계와 실패 모드
- hyperparameter에 Random Forest보다 민감하다.
- noise가 큰 데이터에서는 오차를 과도하게 따라갈 수 있다.
- tree 기반 모델이므로 외삽은 약하다.
- 학습 순서가 sequential하므로 Random Forest보다 병렬화 이점이 작다.
- 너무 복잡한 설정은 교육용 notebook을 흐리게 만들 수 있다.
## 구조해석 해석 기준
Gradient Boosting이 좋은 선택인 경우:
- 정확도가 중요한 tabular surrogate가 필요하다.
- 입력 변수 수가 적거나 중간 규모다.
- 해석 응답이 비선형이지만 불연속은 아니다.
- 최종 비교에서 강한 classical ML baseline이 필요하다.
주의할 경우:
- uncertainty가 핵심 요구사항이다.
- 모델 해석성이 RSM 수준으로 필요하다.
- 데이터 수가 매우 적다.
## References
- Friedman, J. H. (2001), "Greedy Function Approximation: A Gradient Boosting Machine", The Annals of Statistics. https://doi.org/10.1214/aos/1013203451
- CiNii bibliographic record for Friedman (2001). https://cir.nii.ac.jp/crid/1360292617909870720
- scikit-learn `GradientBoostingRegressor` documentation. https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html
FESurrogateModelTutorial/docs/theory/06_mlp_neural_network.md
+90
View File
@@ -0,0 +1,90 @@
# MLP Neural Network Surrogate
## 핵심 아이디어
Multi-layer Perceptron(MLP)은 affine transform과 nonlinear activation을 여러 층으로 쌓아 입력과 출력의 비선형 관계를 학습한다.
단일 hidden layer MLP는 다음처럼 표현할 수 있다.
```text
\hat{y} = W_2 phi(W_1 x + b_1) + b_2
```
- `x`: scaling된 입력.
- `phi`: activation function.
- `W`, `b`: 학습되는 weight와 bias.
Cybenko의 universal approximation theorem은 충분한 hidden unit을 가진 신경망이 넓은 함수군을 근사할 수 있음을 보인 고전적 결과다. 다만 "근사 가능하다"는 말이 적은 데이터에서 항상 잘 학습된다는 뜻은 아니다.
## FEM surrogate에서의 의미
MLP는 beam 응답처럼 매끄러운 비선형 함수를 학습할 수 있다. 그러나 데이터 수, scaling, regularization, optimization 설정에 민감하다. 이 튜토리얼에서는 deep learning framework를 도입하지 않고 scikit-learn의 `MLPRegressor`로 작은 neural surrogate의 특성을 보여준다.
## 구현 선택
기본 pipeline:
```text
StandardScaler
-> TransformedTargetRegressor(
regressor=MLPRegressor(...),
transformer=StandardScaler()
)
```
추천 기본 설정:
```text
MLPRegressor(
hidden_layer_sizes=(64, 32),
activation="relu",
solver="adam",
alpha=1e-4,
learning_rate_init=1e-3,
early_stopping=True,
max_iter=2000,
random_state=20260521
)
```
입력뿐 아니라 target scaling도 중요하다. FEM 응답은 단위와 scale이 크게 다를 수 있기 때문이다.
## Notebook 실습 포인트
`notebooks/05_mlp_surrogate.ipynb`는 다음을 보여준다.
1. 동일 dataset과 split 로드.
2. 입력 scaling과 target scaling의 효과.
3. hidden layer 크기 비교.
4. train/test learning curve.
5. parity plot과 residual plot.
6. RSM, GPR, tree ensemble 대비 MLP의 장단점 정리.
## 장점
- 매끄러운 비선형 함수 근사에 적합하다.
- 다중 출력 surrogate로 확장하기 쉽다.
- 충분한 데이터와 tuning이 있으면 복잡한 관계를 학습할 수 있다.
- 동일 pipeline 구조로 다른 neural framework로 확장 가능하다.
## 한계와 실패 모드
- 작은 데이터에서는 과적합하거나 불안정할 수 있다.
- scaling 없이 학습하면 convergence가 나빠질 수 있다.
- hyperparameter 선택이 성능에 큰 영향을 준다.
- GPR처럼 기본 uncertainty를 제공하지 않는다.
- 모델 해석성이 낮다.
## 구조해석 해석 기준
MLP가 좋은 선택인 경우:
- 데이터 수가 충분하다.
- 응답이 매끄럽지만 단순 다항식으로 부족하다.
- 다중 출력 또는 복잡한 feature representation 확장을 고려한다.
- 최종 정확도가 중요하고 해석성 요구가 낮다.
주의할 경우:
- sample 수가 매우 작다.
- 예측 불확실성이 중요하다.
- 실험자가 scaling과 validation을 엄격히 관리하기 어렵다.
## References
- Cybenko, G. (1989), "Approximation by Superpositions of a Sigmoidal Function", Mathematics of Control, Signals, and Systems. https://doi.org/10.1007/BF02551274
- CiNii bibliographic record for Cybenko (1989). https://cir.nii.ac.jp/crid/1361981471344652032
- Glorot, X. and Bengio, Y. (2010), "Understanding the difficulty of training deep feedforward neural networks", AISTATS. https://proceedings.mlr.press/v9/glorot10a.html
- scikit-learn `MLPRegressor` documentation. https://scikit-learn.org/stable/modules/generated/sklearn.neural_network.MLPRegressor.html
FESurrogateModelTutorial/notebooks/.gitkeep
+1
View File
@@ -0,0 +1 @@
FESurrogateModelTutorial/notebooks/00_beam2d_fea_dataset.ipynb
+173
View File
@@ -0,0 +1,173 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "7e3ade70",
"metadata": {},
"source": [
"# 00 Beam2D FEM Dataset\n",
"\n",
"BeamExamples ?? ??? ?? ??? ? LHS sample? ???, repository solver? FEM surrogate ??? dataset? ????."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "71929240",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"from pathlib import Path\n",
"\n",
"import numpy as np\n",
"\n",
"from femsurrogate.data.bounds import DEFAULT_PARAMETER_BOUNDS\n",
"from femsurrogate.data.dataset import build_dataset\n",
"from femsurrogate.data.sampling import generate_lhs_samples\n",
"from femsurrogate.data.schema import DEFAULT_RANDOM_SEED, TARGET_COLUMNS\n",
"from femsurrogate.fea.io import read_beam_example, read_expected_displacements\n",
"from femsurrogate.fea.solver import solve_linear_static\n",
"\n",
"ROOT = Path.cwd().resolve()\n",
"if not (ROOT / \"pyproject.toml\").exists():\n",
" ROOT = ROOT.parent\n",
"assert (ROOT / \"pyproject.toml\").exists(), ROOT\n",
"REFERENCE_DIR = ROOT / \"data\" / \"reference\"\n",
"REFERENCE_DIR.mkdir(parents=True, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"id": "df256ebc",
"metadata": {},
"source": [
"## BeamExamples ?? ??\n",
"\n",
"Fixture? ?? node? ?? `Ux`, `Uy`, `Rz`? ???? ???? ?? ????? ????."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0a8c947c",
"metadata": {},
"outputs": [],
"source": [
"model = read_beam_example(ROOT / \"BeamExamples\" / \"CantileverBeam.txt\")\n",
"expected = read_expected_displacements(ROOT / \"BeamExamples\" / \"CantileverBeam_Displacements.txt\")\n",
"actual = solve_linear_static(model)\n",
"\n",
"max_abs_error = 0.0\n",
"for node_id, expected_displacement in expected.items():\n",
" actual_displacement = actual[node_id]\n",
" actual_values = np.array(\n",
" [actual_displacement.ux, actual_displacement.uy, actual_displacement.rz]\n",
" )\n",
" expected_values = np.array(\n",
" [expected_displacement.ux, expected_displacement.uy, expected_displacement.rz]\n",
" )\n",
" error = float(np.max(np.abs(actual_values - expected_values)))\n",
" max_abs_error = max(max_abs_error, error)\n",
"\n",
"assert max_abs_error <= 5e-7\n",
"max_abs_error"
]
},
{
"cell_type": "markdown",
"id": "6620d0ee",
"metadata": {},
"source": [
"## LHS sampling? FEM batch ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9923fd04",
"metadata": {},
"outputs": [],
"source": [
"N_SAMPLES = 300\n",
"\n",
"samples = generate_lhs_samples(DEFAULT_PARAMETER_BOUNDS, n=N_SAMPLES, seed=DEFAULT_RANDOM_SEED)\n",
"dataset = build_dataset(samples)\n",
"\n",
"assert len(dataset) == N_SAMPLES\n",
"assert set(TARGET_COLUMNS).issubset(dataset.columns)\n",
"dataset.head()"
]
},
{
"cell_type": "markdown",
"id": "c0efee15",
"metadata": {},
"source": [
"## Dataset ??\n",
"\n",
"?? notebook? ?? CSV? metadata? ??? `data/reference/`? ????."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d80890bd",
"metadata": {},
"outputs": [],
"source": [
"dataset_path = REFERENCE_DIR / \"beam2d_lhs_300.csv\"\n",
"metadata_path = REFERENCE_DIR / \"beam2d_lhs_300_metadata.json\"\n",
"\n",
"dataset.to_csv(dataset_path, index=False)\n",
"metadata = {\n",
" \"dataset_name\": \"beam2d_lhs_300\",\n",
" \"sample_count\": N_SAMPLES,\n",
" \"random_seed\": DEFAULT_RANDOM_SEED,\n",
" \"unit_system\": \"SI\",\n",
" \"fea_model\": \"2D Euler-Bernoulli beam/frame, linear static\",\n",
" \"target_columns\": list(TARGET_COLUMNS),\n",
" \"parameter_bounds\": {\n",
" name: {\"lower\": bound.lower, \"upper\": bound.upper}\n",
" for name, bound in DEFAULT_PARAMETER_BOUNDS.items()\n",
" },\n",
" \"notes\": \"Generated by notebooks/00_beam2d_fea_dataset.ipynb using src/femsurrogate.\",\n",
"}\n",
"metadata_path.write_text(json.dumps(metadata, indent=2), encoding=\"utf-8\")\n",
"\n",
"{\"dataset_path\": str(dataset_path), \"metadata_path\": str(metadata_path)}"
]
},
{
"cell_type": "markdown",
"id": "d56bcddb",
"metadata": {},
"source": [
"## ?? sanity check"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e560e50c",
"metadata": {},
"outputs": [],
"source": [
"dataset.describe().T.loc[[\"L_m\", \"b_m\", \"h_m\", \"E_pa\", \"P_n\", *TARGET_COLUMNS]]"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"pygments_lexer": "ipython3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
FESurrogateModelTutorial/notebooks/01_response_surface_surrogate.ipynb
+168
View File
@@ -0,0 +1,168 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "260fc3ce",
"metadata": {},
"source": [
"# Response Surface Surrogate\n",
"\n",
"Response Surface? polynomial feature? Ridge regression?? ?? baseline? ???.\n",
"\n",
"?? ?? notebook? ?? dataset, target, train/test split seed? ????."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "56528a9c",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import warnings\n",
"from pathlib import Path\n",
"\n",
"import pandas as pd\n",
"from sklearn.exceptions import ConvergenceWarning\n",
"\n",
"from femsurrogate.data.schema import DEFAULT_RANDOM_SEED, PARAMETER_COLUMNS\n",
"from femsurrogate.plotting.diagnostics import plot_parity, plot_residuals\n",
"from femsurrogate.surrogates.common import evaluate_model, metrics_to_dict, split_dataset\n",
"from femsurrogate.surrogates.registry import make_model\n",
"\n",
"ROOT = Path.cwd().resolve()\n",
"if not (ROOT / \"pyproject.toml\").exists():\n",
" ROOT = ROOT.parent\n",
"assert (ROOT / \"pyproject.toml\").exists(), ROOT\n",
"DATASET_PATH = ROOT / \"data\" / \"reference\" / \"beam2d_lhs_300.csv\"\n",
"RESULTS_DIR = ROOT / \"reports\" / \"results\"\n",
"PREDICTIONS_DIR = ROOT / \"reports\" / \"predictions\"\n",
"FIGURES_DIR = ROOT / \"reports\" / \"figures\"\n",
"for directory in [RESULTS_DIR, PREDICTIONS_DIR, FIGURES_DIR]:\n",
" directory.mkdir(parents=True, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"id": "7cd36ad9",
"metadata": {},
"source": [
"## Dataset? split"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "50689a07",
"metadata": {},
"outputs": [],
"source": [
"dataset = pd.read_csv(DATASET_PATH)\n",
"target_column = \"tip_uy_m\"\n",
"split = split_dataset(\n",
" dataset,\n",
" feature_columns=list(PARAMETER_COLUMNS),\n",
" target_column=target_column,\n",
" test_size=0.2,\n",
" random_state=DEFAULT_RANDOM_SEED,\n",
")\n",
"\n",
"len(split.X_train), len(split.X_test)"
]
},
{
"cell_type": "markdown",
"id": "0473847f",
"metadata": {},
"source": [
"## ?? ??? ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "539ffb4d",
"metadata": {},
"outputs": [],
"source": [
"MODEL_NAME = \"rsm\"\n",
"model = make_model(MODEL_NAME, random_state=DEFAULT_RANDOM_SEED, **{})\n",
"\n",
"with warnings.catch_warnings():\n",
" warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)\n",
" result = evaluate_model(\n",
" model,\n",
" split.X_train,\n",
" split.X_test,\n",
" split.y_train,\n",
" split.y_test,\n",
" model_name=MODEL_NAME,\n",
" target_column=target_column,\n",
" )\n",
"\n",
"metrics = metrics_to_dict(result.metrics)\n",
"metrics"
]
},
{
"cell_type": "markdown",
"id": "78c34610",
"metadata": {},
"source": [
"## ?? ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e15bf80d",
"metadata": {},
"outputs": [],
"source": [
"metrics_path = RESULTS_DIR / f\"{MODEL_NAME}_metrics.json\"\n",
"predictions_path = PREDICTIONS_DIR / f\"{MODEL_NAME}_predictions.csv\"\n",
"\n",
"metrics_path.write_text(json.dumps(metrics, indent=2), encoding=\"utf-8\")\n",
"result.predictions.to_csv(predictions_path, index=False)\n",
"\n",
"{\"metrics_path\": str(metrics_path), \"predictions_path\": str(predictions_path)}"
]
},
{
"cell_type": "markdown",
"id": "2142e40b",
"metadata": {},
"source": [
"## ?? plot"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "14b89510",
"metadata": {},
"outputs": [],
"source": [
"parity_fig = plot_parity(result.predictions, title=f\"{MODEL_NAME} parity\")\n",
"residual_fig = plot_residuals(result.predictions, title=f\"{MODEL_NAME} residuals\")\n",
"parity_fig.savefig(FIGURES_DIR / f\"{MODEL_NAME}_parity.png\", dpi=150, bbox_inches=\"tight\")\n",
"residual_fig.savefig(FIGURES_DIR / f\"{MODEL_NAME}_residuals.png\", dpi=150, bbox_inches=\"tight\")\n",
"parity_fig"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"pygments_lexer": "ipython3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
FESurrogateModelTutorial/notebooks/02_gaussian_process_kriging_surrogate.ipynb
+168
View File
@@ -0,0 +1,168 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "144f56e0",
"metadata": {},
"source": [
"# Gaussian Process / Kriging Surrogate\n",
"\n",
"GPR? smooth response? ?? ???? ??? ???? ????.\n",
"\n",
"?? ?? notebook? ?? dataset, target, train/test split seed? ????."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7a5a2974",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import warnings\n",
"from pathlib import Path\n",
"\n",
"import pandas as pd\n",
"from sklearn.exceptions import ConvergenceWarning\n",
"\n",
"from femsurrogate.data.schema import DEFAULT_RANDOM_SEED, PARAMETER_COLUMNS\n",
"from femsurrogate.plotting.diagnostics import plot_parity, plot_residuals\n",
"from femsurrogate.surrogates.common import evaluate_model, metrics_to_dict, split_dataset\n",
"from femsurrogate.surrogates.registry import make_model\n",
"\n",
"ROOT = Path.cwd().resolve()\n",
"if not (ROOT / \"pyproject.toml\").exists():\n",
" ROOT = ROOT.parent\n",
"assert (ROOT / \"pyproject.toml\").exists(), ROOT\n",
"DATASET_PATH = ROOT / \"data\" / \"reference\" / \"beam2d_lhs_300.csv\"\n",
"RESULTS_DIR = ROOT / \"reports\" / \"results\"\n",
"PREDICTIONS_DIR = ROOT / \"reports\" / \"predictions\"\n",
"FIGURES_DIR = ROOT / \"reports\" / \"figures\"\n",
"for directory in [RESULTS_DIR, PREDICTIONS_DIR, FIGURES_DIR]:\n",
" directory.mkdir(parents=True, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"id": "a2c2b3fe",
"metadata": {},
"source": [
"## Dataset? split"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ef13216f",
"metadata": {},
"outputs": [],
"source": [
"dataset = pd.read_csv(DATASET_PATH)\n",
"target_column = \"tip_uy_m\"\n",
"split = split_dataset(\n",
" dataset,\n",
" feature_columns=list(PARAMETER_COLUMNS),\n",
" target_column=target_column,\n",
" test_size=0.2,\n",
" random_state=DEFAULT_RANDOM_SEED,\n",
")\n",
"\n",
"len(split.X_train), len(split.X_test)"
]
},
{
"cell_type": "markdown",
"id": "6c3be3f4",
"metadata": {},
"source": [
"## ?? ??? ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d5e09c8a",
"metadata": {},
"outputs": [],
"source": [
"MODEL_NAME = \"gpr\"\n",
"model = make_model(MODEL_NAME, random_state=DEFAULT_RANDOM_SEED, **{})\n",
"\n",
"with warnings.catch_warnings():\n",
" warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)\n",
" result = evaluate_model(\n",
" model,\n",
" split.X_train,\n",
" split.X_test,\n",
" split.y_train,\n",
" split.y_test,\n",
" model_name=MODEL_NAME,\n",
" target_column=target_column,\n",
" )\n",
"\n",
"metrics = metrics_to_dict(result.metrics)\n",
"metrics"
]
},
{
"cell_type": "markdown",
"id": "4b9e74af",
"metadata": {},
"source": [
"## ?? ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5af40658",
"metadata": {},
"outputs": [],
"source": [
"metrics_path = RESULTS_DIR / f\"{MODEL_NAME}_metrics.json\"\n",
"predictions_path = PREDICTIONS_DIR / f\"{MODEL_NAME}_predictions.csv\"\n",
"\n",
"metrics_path.write_text(json.dumps(metrics, indent=2), encoding=\"utf-8\")\n",
"result.predictions.to_csv(predictions_path, index=False)\n",
"\n",
"{\"metrics_path\": str(metrics_path), \"predictions_path\": str(predictions_path)}"
]
},
{
"cell_type": "markdown",
"id": "37a881b4",
"metadata": {},
"source": [
"## ?? plot"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d156a54d",
"metadata": {},
"outputs": [],
"source": [
"parity_fig = plot_parity(result.predictions, title=f\"{MODEL_NAME} parity\")\n",
"residual_fig = plot_residuals(result.predictions, title=f\"{MODEL_NAME} residuals\")\n",
"parity_fig.savefig(FIGURES_DIR / f\"{MODEL_NAME}_parity.png\", dpi=150, bbox_inches=\"tight\")\n",
"residual_fig.savefig(FIGURES_DIR / f\"{MODEL_NAME}_residuals.png\", dpi=150, bbox_inches=\"tight\")\n",
"parity_fig"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"pygments_lexer": "ipython3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
FESurrogateModelTutorial/notebooks/03_random_forest_surrogate.ipynb
+168
View File
@@ -0,0 +1,168 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "1638813f",
"metadata": {},
"source": [
"# Random Forest Surrogate\n",
"\n",
"Random Forest? feature scaling ??? ????? interaction? ??? ???? tree ensemble??.\n",
"\n",
"?? ?? notebook? ?? dataset, target, train/test split seed? ????."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b8bdcff3",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import warnings\n",
"from pathlib import Path\n",
"\n",
"import pandas as pd\n",
"from sklearn.exceptions import ConvergenceWarning\n",
"\n",
"from femsurrogate.data.schema import DEFAULT_RANDOM_SEED, PARAMETER_COLUMNS\n",
"from femsurrogate.plotting.diagnostics import plot_parity, plot_residuals\n",
"from femsurrogate.surrogates.common import evaluate_model, metrics_to_dict, split_dataset\n",
"from femsurrogate.surrogates.registry import make_model\n",
"\n",
"ROOT = Path.cwd().resolve()\n",
"if not (ROOT / \"pyproject.toml\").exists():\n",
" ROOT = ROOT.parent\n",
"assert (ROOT / \"pyproject.toml\").exists(), ROOT\n",
"DATASET_PATH = ROOT / \"data\" / \"reference\" / \"beam2d_lhs_300.csv\"\n",
"RESULTS_DIR = ROOT / \"reports\" / \"results\"\n",
"PREDICTIONS_DIR = ROOT / \"reports\" / \"predictions\"\n",
"FIGURES_DIR = ROOT / \"reports\" / \"figures\"\n",
"for directory in [RESULTS_DIR, PREDICTIONS_DIR, FIGURES_DIR]:\n",
" directory.mkdir(parents=True, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"id": "6957e06b",
"metadata": {},
"source": [
"## Dataset? split"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "209f40be",
"metadata": {},
"outputs": [],
"source": [
"dataset = pd.read_csv(DATASET_PATH)\n",
"target_column = \"tip_uy_m\"\n",
"split = split_dataset(\n",
" dataset,\n",
" feature_columns=list(PARAMETER_COLUMNS),\n",
" target_column=target_column,\n",
" test_size=0.2,\n",
" random_state=DEFAULT_RANDOM_SEED,\n",
")\n",
"\n",
"len(split.X_train), len(split.X_test)"
]
},
{
"cell_type": "markdown",
"id": "fdc2fbed",
"metadata": {},
"source": [
"## ?? ??? ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "63ed6060",
"metadata": {},
"outputs": [],
"source": [
"MODEL_NAME = \"random_forest\"\n",
"model = make_model(MODEL_NAME, random_state=DEFAULT_RANDOM_SEED, **{})\n",
"\n",
"with warnings.catch_warnings():\n",
" warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)\n",
" result = evaluate_model(\n",
" model,\n",
" split.X_train,\n",
" split.X_test,\n",
" split.y_train,\n",
" split.y_test,\n",
" model_name=MODEL_NAME,\n",
" target_column=target_column,\n",
" )\n",
"\n",
"metrics = metrics_to_dict(result.metrics)\n",
"metrics"
]
},
{
"cell_type": "markdown",
"id": "25dafcbf",
"metadata": {},
"source": [
"## ?? ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8357de5d",
"metadata": {},
"outputs": [],
"source": [
"metrics_path = RESULTS_DIR / f\"{MODEL_NAME}_metrics.json\"\n",
"predictions_path = PREDICTIONS_DIR / f\"{MODEL_NAME}_predictions.csv\"\n",
"\n",
"metrics_path.write_text(json.dumps(metrics, indent=2), encoding=\"utf-8\")\n",
"result.predictions.to_csv(predictions_path, index=False)\n",
"\n",
"{\"metrics_path\": str(metrics_path), \"predictions_path\": str(predictions_path)}"
]
},
{
"cell_type": "markdown",
"id": "069f56dd",
"metadata": {},
"source": [
"## ?? plot"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "00159cc2",
"metadata": {},
"outputs": [],
"source": [
"parity_fig = plot_parity(result.predictions, title=f\"{MODEL_NAME} parity\")\n",
"residual_fig = plot_residuals(result.predictions, title=f\"{MODEL_NAME} residuals\")\n",
"parity_fig.savefig(FIGURES_DIR / f\"{MODEL_NAME}_parity.png\", dpi=150, bbox_inches=\"tight\")\n",
"residual_fig.savefig(FIGURES_DIR / f\"{MODEL_NAME}_residuals.png\", dpi=150, bbox_inches=\"tight\")\n",
"parity_fig"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"pygments_lexer": "ipython3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
FESurrogateModelTutorial/notebooks/04_gradient_boosting_surrogate.ipynb
+168
View File
@@ -0,0 +1,168 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "ad3ce4ad",
"metadata": {},
"source": [
"# Gradient Boosting Surrogate\n",
"\n",
"Gradient Boosting? shallow tree? ????? ?? residual pattern? ??? ensemble??.\n",
"\n",
"?? ?? notebook? ?? dataset, target, train/test split seed? ????."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0fec75b1",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import warnings\n",
"from pathlib import Path\n",
"\n",
"import pandas as pd\n",
"from sklearn.exceptions import ConvergenceWarning\n",
"\n",
"from femsurrogate.data.schema import DEFAULT_RANDOM_SEED, PARAMETER_COLUMNS\n",
"from femsurrogate.plotting.diagnostics import plot_parity, plot_residuals\n",
"from femsurrogate.surrogates.common import evaluate_model, metrics_to_dict, split_dataset\n",
"from femsurrogate.surrogates.registry import make_model\n",
"\n",
"ROOT = Path.cwd().resolve()\n",
"if not (ROOT / \"pyproject.toml\").exists():\n",
" ROOT = ROOT.parent\n",
"assert (ROOT / \"pyproject.toml\").exists(), ROOT\n",
"DATASET_PATH = ROOT / \"data\" / \"reference\" / \"beam2d_lhs_300.csv\"\n",
"RESULTS_DIR = ROOT / \"reports\" / \"results\"\n",
"PREDICTIONS_DIR = ROOT / \"reports\" / \"predictions\"\n",
"FIGURES_DIR = ROOT / \"reports\" / \"figures\"\n",
"for directory in [RESULTS_DIR, PREDICTIONS_DIR, FIGURES_DIR]:\n",
" directory.mkdir(parents=True, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"id": "1d93d9fb",
"metadata": {},
"source": [
"## Dataset? split"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c905b0aa",
"metadata": {},
"outputs": [],
"source": [
"dataset = pd.read_csv(DATASET_PATH)\n",
"target_column = \"tip_uy_m\"\n",
"split = split_dataset(\n",
" dataset,\n",
" feature_columns=list(PARAMETER_COLUMNS),\n",
" target_column=target_column,\n",
" test_size=0.2,\n",
" random_state=DEFAULT_RANDOM_SEED,\n",
")\n",
"\n",
"len(split.X_train), len(split.X_test)"
]
},
{
"cell_type": "markdown",
"id": "c5e7af1a",
"metadata": {},
"source": [
"## ?? ??? ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f5168f3e",
"metadata": {},
"outputs": [],
"source": [
"MODEL_NAME = \"gradient_boosting\"\n",
"model = make_model(MODEL_NAME, random_state=DEFAULT_RANDOM_SEED, **{})\n",
"\n",
"with warnings.catch_warnings():\n",
" warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)\n",
" result = evaluate_model(\n",
" model,\n",
" split.X_train,\n",
" split.X_test,\n",
" split.y_train,\n",
" split.y_test,\n",
" model_name=MODEL_NAME,\n",
" target_column=target_column,\n",
" )\n",
"\n",
"metrics = metrics_to_dict(result.metrics)\n",
"metrics"
]
},
{
"cell_type": "markdown",
"id": "f02aead6",
"metadata": {},
"source": [
"## ?? ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1daaf0f6",
"metadata": {},
"outputs": [],
"source": [
"metrics_path = RESULTS_DIR / f\"{MODEL_NAME}_metrics.json\"\n",
"predictions_path = PREDICTIONS_DIR / f\"{MODEL_NAME}_predictions.csv\"\n",
"\n",
"metrics_path.write_text(json.dumps(metrics, indent=2), encoding=\"utf-8\")\n",
"result.predictions.to_csv(predictions_path, index=False)\n",
"\n",
"{\"metrics_path\": str(metrics_path), \"predictions_path\": str(predictions_path)}"
]
},
{
"cell_type": "markdown",
"id": "14f71882",
"metadata": {},
"source": [
"## ?? plot"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "807c1025",
"metadata": {},
"outputs": [],
"source": [
"parity_fig = plot_parity(result.predictions, title=f\"{MODEL_NAME} parity\")\n",
"residual_fig = plot_residuals(result.predictions, title=f\"{MODEL_NAME} residuals\")\n",
"parity_fig.savefig(FIGURES_DIR / f\"{MODEL_NAME}_parity.png\", dpi=150, bbox_inches=\"tight\")\n",
"residual_fig.savefig(FIGURES_DIR / f\"{MODEL_NAME}_residuals.png\", dpi=150, bbox_inches=\"tight\")\n",
"parity_fig"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"pygments_lexer": "ipython3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
FESurrogateModelTutorial/notebooks/05_mlp_surrogate.ipynb
+168
View File
@@ -0,0 +1,168 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "69c9cc92",
"metadata": {},
"source": [
"# MLP Neural Network Surrogate\n",
"\n",
"MLP? scaled input? target? ??? ???? ??? ??? ????.\n",
"\n",
"?? ?? notebook? ?? dataset, target, train/test split seed? ????."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eed089f5",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import warnings\n",
"from pathlib import Path\n",
"\n",
"import pandas as pd\n",
"from sklearn.exceptions import ConvergenceWarning\n",
"\n",
"from femsurrogate.data.schema import DEFAULT_RANDOM_SEED, PARAMETER_COLUMNS\n",
"from femsurrogate.plotting.diagnostics import plot_parity, plot_residuals\n",
"from femsurrogate.surrogates.common import evaluate_model, metrics_to_dict, split_dataset\n",
"from femsurrogate.surrogates.registry import make_model\n",
"\n",
"ROOT = Path.cwd().resolve()\n",
"if not (ROOT / \"pyproject.toml\").exists():\n",
" ROOT = ROOT.parent\n",
"assert (ROOT / \"pyproject.toml\").exists(), ROOT\n",
"DATASET_PATH = ROOT / \"data\" / \"reference\" / \"beam2d_lhs_300.csv\"\n",
"RESULTS_DIR = ROOT / \"reports\" / \"results\"\n",
"PREDICTIONS_DIR = ROOT / \"reports\" / \"predictions\"\n",
"FIGURES_DIR = ROOT / \"reports\" / \"figures\"\n",
"for directory in [RESULTS_DIR, PREDICTIONS_DIR, FIGURES_DIR]:\n",
" directory.mkdir(parents=True, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"id": "b2547495",
"metadata": {},
"source": [
"## Dataset? split"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "039279d4",
"metadata": {},
"outputs": [],
"source": [
"dataset = pd.read_csv(DATASET_PATH)\n",
"target_column = \"tip_uy_m\"\n",
"split = split_dataset(\n",
" dataset,\n",
" feature_columns=list(PARAMETER_COLUMNS),\n",
" target_column=target_column,\n",
" test_size=0.2,\n",
" random_state=DEFAULT_RANDOM_SEED,\n",
")\n",
"\n",
"len(split.X_train), len(split.X_test)"
]
},
{
"cell_type": "markdown",
"id": "71b3323f",
"metadata": {},
"source": [
"## ?? ??? ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "605253ef",
"metadata": {},
"outputs": [],
"source": [
"MODEL_NAME = \"mlp\"\n",
"model = make_model(MODEL_NAME, random_state=DEFAULT_RANDOM_SEED, **{'max_iter': 500})\n",
"\n",
"with warnings.catch_warnings():\n",
" warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)\n",
" result = evaluate_model(\n",
" model,\n",
" split.X_train,\n",
" split.X_test,\n",
" split.y_train,\n",
" split.y_test,\n",
" model_name=MODEL_NAME,\n",
" target_column=target_column,\n",
" )\n",
"\n",
"metrics = metrics_to_dict(result.metrics)\n",
"metrics"
]
},
{
"cell_type": "markdown",
"id": "f70ad9fd",
"metadata": {},
"source": [
"## ?? ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fb08797b",
"metadata": {},
"outputs": [],
"source": [
"metrics_path = RESULTS_DIR / f\"{MODEL_NAME}_metrics.json\"\n",
"predictions_path = PREDICTIONS_DIR / f\"{MODEL_NAME}_predictions.csv\"\n",
"\n",
"metrics_path.write_text(json.dumps(metrics, indent=2), encoding=\"utf-8\")\n",
"result.predictions.to_csv(predictions_path, index=False)\n",
"\n",
"{\"metrics_path\": str(metrics_path), \"predictions_path\": str(predictions_path)}"
]
},
{
"cell_type": "markdown",
"id": "39a34166",
"metadata": {},
"source": [
"## ?? plot"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "694a1081",
"metadata": {},
"outputs": [],
"source": [
"parity_fig = plot_parity(result.predictions, title=f\"{MODEL_NAME} parity\")\n",
"residual_fig = plot_residuals(result.predictions, title=f\"{MODEL_NAME} residuals\")\n",
"parity_fig.savefig(FIGURES_DIR / f\"{MODEL_NAME}_parity.png\", dpi=150, bbox_inches=\"tight\")\n",
"residual_fig.savefig(FIGURES_DIR / f\"{MODEL_NAME}_residuals.png\", dpi=150, bbox_inches=\"tight\")\n",
"parity_fig"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"pygments_lexer": "ipython3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
FESurrogateModelTutorial/notebooks/06_compare_surrogate_models.ipynb
+115
View File
@@ -0,0 +1,115 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "741ede83",
"metadata": {},
"source": [
"# 06 Compare Surrogate Models\n",
"\n",
"? notebook? ?? model notebook?? ??? metrics JSON? ?? ??? ????. ??? ?? ???? ???."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "10f43a71",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"from pathlib import Path\n",
"\n",
"import pandas as pd\n",
"\n",
"from femsurrogate.plotting.comparison import plot_metric_comparison\n",
"\n",
"ROOT = Path.cwd().resolve()\n",
"if not (ROOT / \"pyproject.toml\").exists():\n",
" ROOT = ROOT.parent\n",
"assert (ROOT / \"pyproject.toml\").exists(), ROOT\n",
"RESULTS_DIR = ROOT / \"reports\" / \"results\"\n",
"FIGURES_DIR = ROOT / \"reports\" / \"figures\"\n",
"FIGURES_DIR.mkdir(parents=True, exist_ok=True)\n",
"MODEL_NAMES = [\"rsm\", \"gpr\", \"random_forest\", \"gradient_boosting\", \"mlp\"]"
]
},
{
"cell_type": "markdown",
"id": "9798e3bb",
"metadata": {},
"source": [
"## Metrics ??"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "55d2447d",
"metadata": {},
"outputs": [],
"source": [
"records = []\n",
"for model_name in MODEL_NAMES:\n",
" metrics_path = RESULTS_DIR / f\"{model_name}_metrics.json\"\n",
" assert metrics_path.exists(), metrics_path\n",
" records.append(json.loads(metrics_path.read_text(encoding=\"utf-8\")))\n",
"\n",
"comparison = pd.DataFrame(records).sort_values(\"rmse\").reset_index(drop=True)\n",
"comparison_path = RESULTS_DIR / \"model_comparison.csv\"\n",
"comparison.to_csv(comparison_path, index=False)\n",
"comparison"
]
},
{
"cell_type": "markdown",
"id": "731bb2f7",
"metadata": {},
"source": [
"## Metric ?? plot"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "64657b84",
"metadata": {},
"outputs": [],
"source": [
"figures = {}\n",
"for metric in [\"rmse\", \"mae\", \"r2\", \"fit_time_s\", \"predict_time_s\"]:\n",
" figure = plot_metric_comparison(comparison, metric=metric, title=f\"Surrogate {metric}\")\n",
" figure.savefig(FIGURES_DIR / f\"comparison_{metric}.png\", dpi=150, bbox_inches=\"tight\")\n",
" figures[metric] = figure\n",
"\n",
"figures[\"rmse\"]"
]
},
{
"cell_type": "markdown",
"id": "63cb5b8d",
"metadata": {},
"source": [
"## ?? ???\n",
"\n",
"- `rmse`? `mae`? ?? ??? ?? ????.\n",
"- `r2`? ??? residual plot?? ?? ?? ??? bias? ??? ????? ????.\n",
"- `fit_time_s`, `predict_time_s`? ?? ??? ??? loop?? ????.\n",
"- GPR? ?? dataset?? ???? sample ?? ??? ?? ??? ??? ?? ? ??."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"pygments_lexer": "ipython3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
FESurrogateModelTutorial/phases/0-project-foundation/index.json
+18
View File
@@ -0,0 +1,18 @@
{
"project": "FEMSurrogateTutorial",
"phase": "0-project-foundation",
"steps": [
{
"step": 0,
"name": "python-project-skeleton",
"status": "completed",
"summary": "Created uv/pyproject foundation, src package skeleton, artifact directories, and ruff configuration."
},
{
"step": 1,
"name": "import-smoke-test",
"status": "completed",
"summary": "Added package import smoke tests and exposed femsurrogate.__version__."
}
]
}
FESurrogateModelTutorial/phases/0-project-foundation/step0.md
+40
View File
@@ -0,0 +1,40 @@
# Step 0: python-project-skeleton
## 읽어야 할 파일
- `/AGENTS.md`
- `/PROGRESS.md`
- `/WORKNOTES.md`
- `/docs/PRD.md`
- `/docs/ARCHITECTURE.md`
- `/docs/ADR.md`
## 작업
Python tutorial project의 최소 기반을 만든다.
- `/pyproject.toml` 생성: Python `>=3.12,<3.15`, setuptools src layout, pytest `pythonpath = ["src"]`, ruff target `py312`.
- runtime dependencies: `numpy`, `scipy`, `pandas`, `scikit-learn`, `matplotlib`, `joblib`.
- dev dependencies: `pytest`, `ruff`, `jupyterlab`, `ipykernel`, `nbconvert`.
- Python package directories: `/src/femsurrogate/`, `/src/femsurrogate/fea/`, `/src/femsurrogate/data/`, `/src/femsurrogate/surrogates/`, `/src/femsurrogate/plotting/`.
- artifact directories: `/tests/`, `/data/reference/`, `/data/processed/`, `/reports/results/`, `/reports/predictions/`, `/reports/figures/`, `/notebooks/`.
- 빈 artifact directory에는 `.gitkeep`을 둔다.
- Python cache, virtualenv, notebook checkpoint를 `.gitignore`에 추가한다.
- `/PROGRESS.md`에 phase 0 시작 상태를 기록한다.
## Acceptance Criteria
```powershell
uv sync
uv run python -c "import femsurrogate; print(femsurrogate.__name__)"
uv run ruff check .
```
## 검증 절차
AC 커맨드를 실행하고 성공하면 `phases/0-project-foundation/index.json`의 step 0을 `completed`로 갱신한다.
## 금지사항
- Beam solver, parser, dataset, surrogate 모델 구현을 이 step에서 만들지 마라.
- Notebook 내용을 만들지 마라.
FESurrogateModelTutorial/phases/0-project-foundation/step1.md
+36
View File
@@ -0,0 +1,36 @@
# Step 1: import-smoke-test
## 읽어야 할 파일
- `/AGENTS.md`
- `/PROGRESS.md`
- `/WORKNOTES.md`
- `/docs/ARCHITECTURE.md`
- `/pyproject.toml`
- `/src/femsurrogate/__init__.py`
## 작업
TDD로 package import smoke test를 추가한다.
- 먼저 `/tests/test_project_structure.py`를 작성한다.
- 테스트는 `femsurrogate.__version__`이 문자열인지 확인한다.
- 테스트는 `femsurrogate.fea`, `femsurrogate.data`, `femsurrogate.surrogates`, `femsurrogate.plotting` import 가능성을 확인한다.
- 테스트 실패를 먼저 확인한 뒤 최소 구현으로 통과시킨다.
- `/PROGRESS.md`에 검증 결과를 기록한다.
## Acceptance Criteria
```powershell
uv run pytest tests/test_project_structure.py -q
uv run ruff check .
```
## 검증 절차
테스트가 먼저 실패한 기록을 확인하고, 구현 후 AC가 통과하면 `phases/0-project-foundation/index.json`의 step 1을 `completed`로 갱신한다.
## 금지사항
- solver API를 만들지 마라.
- 테스트를 구현 후에만 작성하지 마라.
FESurrogateModelTutorial/phases/1-beam2d-solver/index.json
+30
View File
@@ -0,0 +1,30 @@
{
"project": "FEMSurrogateTutorial",
"phase": "1-beam2d-solver",
"steps": [
{
"step": 0,
"name": "beamexamples-parser",
"status": "completed",
"summary": "Added BeamExamples parser dataclasses and tests for cantilever input and displacement fixtures."
},
{
"step": 1,
"name": "frame-element",
"status": "completed",
"summary": "Added 2D Euler-Bernoulli frame local stiffness and transformation matrix tests and implementation."
},
{
"step": 2,
"name": "assembly-and-solver",
"status": "completed",
"summary": "Added sparse global stiffness assembly, load vector assembly, constrained DOF handling, and linear static solve."
},
{
"step": 3,
"name": "fixture-regression",
"status": "completed",
"summary": "Added BeamExamples displacement regression, analytical cantilever tip check, and clockwise-positive Rz convention alignment."
}
]
}
FESurrogateModelTutorial/phases/1-beam2d-solver/step0.md
+32
View File
@@ -0,0 +1,32 @@
# Step 0: beamexamples-parser
## 읽어야 할 파일
- `/AGENTS.md`
- `/PROGRESS.md`
- `/WORKNOTES.md`
- `/docs/ARCHITECTURE.md`
- `/BeamExamples/CantileverBeam.txt`
- `/BeamExamples/CantileverBeam_Displacements.txt`
## 작업
TDD로 `BeamExamples` parser를 구현한다.
- `/tests/test_beamexamples_io.py`를 먼저 작성한다.
- `read_beam_example()`은 metadata, 6 nodes, 5 beams, fixed node 1, node 6 load를 읽는다.
- `read_expected_displacements()`는 node별 `Ux`, `Uy`, `Rz` 기준값을 읽는다.
- parser는 comment, blank line, trailing comma, `Poisson'sRatio` label을 처리한다.
- 구현 파일: `/src/femsurrogate/fea/model.py`, `/src/femsurrogate/fea/io.py`.
## Acceptance Criteria
```powershell
uv run pytest tests/test_beamexamples_io.py -q
uv run ruff check .
```
## 금지사항
- solver 구현을 이 step에 넣지 마라.
- fixture 파일을 수정하지 마라.
FESurrogateModelTutorial/phases/1-beam2d-solver/step1.md
+28
View File
@@ -0,0 +1,28 @@
# Step 1: frame-element
## 읽어야 할 파일
- `/AGENTS.md`
- `/docs/ARCHITECTURE.md`
- `/src/femsurrogate/fea/model.py`
- `/src/femsurrogate/fea/io.py`
## 작업
TDD로 2-node 2D Euler-Bernoulli frame element 행렬을 구현한다.
- `/tests/test_frame_element.py`를 먼저 작성한다.
- `local_frame_stiffness(E, A, I, L)`의 shape, symmetry, axial/bending 계수를 검증한다.
- `transformation_matrix(x1, y1, x2, y2)`의 shape와 orthogonality를 검증한다.
- 구현 파일: `/src/femsurrogate/fea/element.py`.
## Acceptance Criteria
```powershell
uv run pytest tests/test_frame_element.py tests/test_beamexamples_io.py -q
uv run ruff check .
```
## 금지사항
- Timoshenko beam, 3D beam DOF를 추가하지 마라.
FESurrogateModelTutorial/phases/1-beam2d-solver/step2.md
+31
View File
@@ -0,0 +1,31 @@
# Step 2: assembly-and-solver
## 읽어야 할 파일
- `/AGENTS.md`
- `/docs/ARCHITECTURE.md`
- `/src/femsurrogate/fea/model.py`
- `/src/femsurrogate/fea/io.py`
- `/src/femsurrogate/fea/element.py`
## 작업
TDD로 global assembly와 constrained linear static solver를 구현한다.
- `/tests/test_beam_solver.py`를 먼저 작성한다.
- BeamExamples model의 global stiffness shape `(18, 18)`을 검증한다.
- fixed node 1의 3 DOF가 constrained 처리되는지 검증한다.
- `solve_linear_static(model)`이 모든 node displacement를 finite 값으로 반환하는지 검증한다.
- 구현 파일: `/src/femsurrogate/fea/assembly.py`, `/src/femsurrogate/fea/solver.py`.
- solver는 `scipy.sparse`와 `scipy.sparse.linalg.spsolve`를 사용한다.
## Acceptance Criteria
```powershell
uv run pytest tests/test_beam_solver.py tests/test_frame_element.py tests/test_beamexamples_io.py -q
uv run ruff check .
```
## 금지사항
- expected displacement 값을 solver에 hard-code하지 마라.
FESurrogateModelTutorial/phases/1-beam2d-solver/step3.md
+30
View File
@@ -0,0 +1,30 @@
# Step 3: fixture-regression
## 읽어야 할 파일
- `/AGENTS.md`
- `/docs/PRD.md`
- `/docs/ARCHITECTURE.md`
- `/BeamExamples/CantileverBeam.txt`
- `/BeamExamples/CantileverBeam_Displacements.txt`
- `/src/femsurrogate/fea/`
## 작업
TDD로 BeamExamples displacement regression을 완성한다.
- `/tests/test_cantilever_fixture_regression.py`를 먼저 작성한다.
- solver 결과의 모든 node별 `Ux`, `Uy`, `Rz`를 기준 displacement file과 `atol=5e-7`, `rtol=1e-6`으로 비교한다.
- tip displacement 부호와 해석해 `P L^3 / (3 E I)` 대비 크기를 검증한다.
- 필요한 helper는 `/src/femsurrogate/fea/benchmark.py`, `/src/femsurrogate/fea/responses.py`에 둔다.
## Acceptance Criteria
```powershell
uv run pytest tests/test_cantilever_fixture_regression.py tests/test_beam_solver.py tests/test_frame_element.py tests/test_beamexamples_io.py -q
uv run ruff check .
```
## 금지사항
- 허용오차를 문서 기준보다 느슨하게 키우지 마라.
FESurrogateModelTutorial/phases/2-dataset-and-surrogates/index.json
+30
View File
@@ -0,0 +1,30 @@
{
"project": "FEMSurrogateTutorial",
"phase": "2-dataset-and-surrogates",
"steps": [
{
"step": 0,
"name": "sampling-and-dataset",
"status": "completed",
"summary": "Added reproducible LHS sampling, BeamParameters/AnalysisResult schema, and Beam2D dataset builder using the in-repository solver."
},
{
"step": 1,
"name": "surrogate-common",
"status": "completed",
"summary": "Added reproducible dataset split helper, evaluation result dataclasses, regression metrics, fit/predict timing, and prediction table generation."
},
{
"step": 2,
"name": "surrogate-models",
"status": "completed",
"summary": "Added scikit-learn builders and registry for RSM, GPR, Random Forest, Gradient Boosting, and MLP models."
},
{
"step": 3,
"name": "plotting-and-results",
"status": "completed",
"summary": "Added parity and residual diagnostic plots, metrics table creation, and metric comparison plot helpers returning matplotlib figures."
}
]
}
FESurrogateModelTutorial/phases/2-dataset-and-surrogates/step0.md
+28
View File
@@ -0,0 +1,28 @@
# Step 0: sampling-and-dataset
## 읽어야 할 파일
- `/AGENTS.md`
- `/docs/ARCHITECTURE.md`
- `/docs/theory/01_doe_sampling_validation.md`
- `/src/femsurrogate/fea/`
## 작업
TDD로 LHS sampling과 Beam2D dataset builder를 구현한다.
- 테스트: `/tests/test_sampling.py`, `/tests/test_dataset_builder.py`.
- 구현: `/src/femsurrogate/data/bounds.py`, `schema.py`, `sampling.py`, `dataset.py`.
- 기본 seed는 `20260521`.
- dataset schema는 문서의 SI 단위 컬럼을 따른다.
## Acceptance Criteria
```powershell
uv run pytest tests/test_sampling.py tests/test_dataset_builder.py -q
uv run ruff check .
```
## 금지사항
- surrogate 학습을 이 step에 넣지 마라.
FESurrogateModelTutorial/phases/2-dataset-and-surrogates/step1.md
+26
View File
@@ -0,0 +1,26 @@
# Step 1: surrogate-common
## 읽어야 할 파일
- `/AGENTS.md`
- `/docs/ARCHITECTURE.md`
- `/src/femsurrogate/data/`
## 작업
TDD로 surrogate 공통 split/evaluate/result helper를 구현한다.
- 테스트: `/tests/test_surrogate_common.py`.
- 구현: `/src/femsurrogate/surrogates/common.py`.
- metrics는 `rmse`, `mae`, `r2`, `fit_time_s`, `predict_time_s`를 포함한다.
## Acceptance Criteria
```powershell
uv run pytest tests/test_surrogate_common.py -q
uv run ruff check .
```
## 금지사항
- 개별 모델 builder를 이 step에 섞지 마라.
FESurrogateModelTutorial/phases/2-dataset-and-surrogates/step2.md
+30
View File
@@ -0,0 +1,30 @@
# Step 2: surrogate-models
## 읽어야 할 파일
- `/AGENTS.md`
- `/docs/theory/02_response_surface_methodology.md`
- `/docs/theory/03_gaussian_process_kriging.md`
- `/docs/theory/04_random_forest.md`
- `/docs/theory/05_gradient_boosting.md`
- `/docs/theory/06_mlp_neural_network.md`
- `/src/femsurrogate/surrogates/common.py`
## 작업
TDD로 모델별 scikit-learn pipeline builder와 registry를 구현한다.
- 테스트: `/tests/test_surrogate_models.py`.
- 구현: `rsm.py`, `gpr.py`, `random_forest.py`, `boosting.py`, `mlp.py`, `registry.py`.
- 모델명: `rsm`, `gpr`, `random_forest`, `gradient_boosting`, `mlp`.
## Acceptance Criteria
```powershell
uv run pytest tests/test_surrogate_models.py -q
uv run ruff check .
```
## 금지사항
- PyTorch/TensorFlow, AutoML, MLflow를 추가하지 마라.
FESurrogateModelTutorial/phases/2-dataset-and-surrogates/step3.md
+26
View File
@@ -0,0 +1,26 @@
# Step 3: plotting-and-results
## 읽어야 할 파일
- `/AGENTS.md`
- `/docs/ARCHITECTURE.md`
- `/src/femsurrogate/surrogates/`
## 작업
TDD로 diagnostics plotting과 result comparison helper를 구현한다.
- 테스트: `/tests/test_plotting_and_results.py`.
- 구현: `/src/femsurrogate/plotting/diagnostics.py`, `/src/femsurrogate/plotting/comparison.py`.
- plotting 함수는 matplotlib Figure를 반환한다.
## Acceptance Criteria
```powershell
uv run pytest tests/test_plotting_and_results.py -q
uv run ruff check .
```
## 금지사항
- browser dashboard를 만들지 마라.
FESurrogateModelTutorial/phases/3-notebooks-and-final-verification/index.json
+30
View File
@@ -0,0 +1,30 @@
{
"project": "FEMSurrogateTutorial",
"phase": "3-notebooks-and-final-verification",
"steps": [
{
"step": 0,
"name": "dataset-notebook",
"status": "completed",
"summary": "Added and executed dataset notebook that validates BeamExamples, generates LHS samples, builds FEM dataset, and writes reference CSV/metadata."
},
{
"step": 1,
"name": "model-notebooks",
"status": "completed",
"summary": "Added and executed five model notebooks sharing the same dataset, target, and split seed while saving metrics, predictions, and diagnostic figures."
},
{
"step": 2,
"name": "comparison-notebook",
"status": "completed",
"summary": "Added and executed comparison notebook that reads saved metrics and writes model comparison CSV and figures without retraining."
},
{
"step": 3,
"name": "final-verification",
"status": "completed",
"summary": "Ran full pytest, ruff, all seven nbconvert executions, and verified comparison outputs exist."
}
]
}
FESurrogateModelTutorial/phases/3-notebooks-and-final-verification/step0.md
+23
View File
@@ -0,0 +1,23 @@
# Step 0: dataset-notebook
## 읽어야 할 파일
- `/AGENTS.md`
- `/docs/PRD.md`
- `/docs/ARCHITECTURE.md`
- `/src/femsurrogate/`
## 작업
`notebooks/00_beam2d_fea_dataset.ipynb`를 만든다. Notebook은 BeamExamples regression 검증, LHS sampling, FEM batch run, dataset 저장을 설명하고 실행한다.
## Acceptance Criteria
```powershell
uv run jupyter nbconvert --to notebook --execute notebooks/00_beam2d_fea_dataset.ipynb
uv run ruff check .
```
## 금지사항
- 핵심 solver 구현을 notebook cell에 넣지 마라.
FESurrogateModelTutorial/phases/3-notebooks-and-final-verification/step1.md
+39
View File
@@ -0,0 +1,39 @@
# Step 1: model-notebooks
## 읽어야 할 파일
- `/AGENTS.md`
- `/docs/theory/02_response_surface_methodology.md`
- `/docs/theory/03_gaussian_process_kriging.md`
- `/docs/theory/04_random_forest.md`
- `/docs/theory/05_gradient_boosting.md`
- `/docs/theory/06_mlp_neural_network.md`
- `/src/femsurrogate/surrogates/`
- `/src/femsurrogate/plotting/`
## 작업
모델별 notebook 5개를 만든다.
- `notebooks/01_response_surface_surrogate.ipynb`
- `notebooks/02_gaussian_process_kriging_surrogate.ipynb`
- `notebooks/03_random_forest_surrogate.ipynb`
- `notebooks/04_gradient_boosting_surrogate.ipynb`
- `notebooks/05_mlp_surrogate.ipynb`
각 notebook은 같은 dataset, target, split seed를 쓰고 metric JSON과 prediction CSV를 저장한다.
## Acceptance Criteria
```powershell
uv run jupyter nbconvert --to notebook --execute notebooks/01_response_surface_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/02_gaussian_process_kriging_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/03_random_forest_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/04_gradient_boosting_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/05_mlp_surrogate.ipynb
uv run ruff check .
```
## 금지사항
- 모델별로 다른 split을 쓰지 마라.
FESurrogateModelTutorial/phases/3-notebooks-and-final-verification/step2.md
+24
View File
@@ -0,0 +1,24 @@
# Step 2: comparison-notebook
## 읽어야 할 파일
- `/AGENTS.md`
- `/docs/PRD.md`
- `/reports/results/`
- `/reports/predictions/`
- `/src/femsurrogate/plotting/comparison.py`
## 작업
`notebooks/06_compare_surrogate_models.ipynb`를 만든다. 이전 notebook 결과물을 읽어 RMSE, MAE, R2, 학습 시간, 예측 시간을 비교하고 모델 선택 가이드를 정리한다.
## Acceptance Criteria
```powershell
uv run jupyter nbconvert --to notebook --execute notebooks/06_compare_surrogate_models.ipynb
uv run ruff check .
```
## 금지사항
- 비교 notebook에서 모델을 다시 학습하지 마라.
FESurrogateModelTutorial/phases/3-notebooks-and-final-verification/step3.md
+37
View File
@@ -0,0 +1,37 @@
# Step 3: final-verification
## 읽어야 할 파일
- `/AGENTS.md`
- `/PROGRESS.md`
- `/WORKNOTES.md`
- `/docs/PRD.md`
- `/docs/ARCHITECTURE.md`
## 작업
전체 검증과 handoff 문서 정리를 수행한다.
- `uv run pytest`
- `uv run ruff check .`
- 모든 notebook 순차 `nbconvert --execute`
- `/PROGRESS.md` 최종 업데이트
- `/WORKNOTES.md`에 남은 주의점 기록
## Acceptance Criteria
```powershell
uv run pytest
uv run ruff check .
uv run jupyter nbconvert --to notebook --execute notebooks/00_beam2d_fea_dataset.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/01_response_surface_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/02_gaussian_process_kriging_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/03_random_forest_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/04_gradient_boosting_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/05_mlp_surrogate.ipynb
uv run jupyter nbconvert --to notebook --execute notebooks/06_compare_surrogate_models.ipynb
```
## 금지사항
- 실패한 검증을 성공으로 기록하지 마라.
FESurrogateModelTutorial/phases/index.json
+20
View File
@@ -0,0 +1,20 @@
{
"phases": [
{
"dir": "0-project-foundation",
"status": "completed"
},
{
"dir": "1-beam2d-solver",
"status": "completed"
},
{
"dir": "2-dataset-and-surrogates",
"status": "completed"
},
{
"dir": "3-notebooks-and-final-verification",
"status": "completed"
}
]
}
FESurrogateModelTutorial/pyproject.toml
+46
View File
@@ -0,0 +1,46 @@
[project]
name = "femsurrogate-tutorial"
version = "0.1.0"
description = "Korean tutorial for FEM structural-analysis surrogate models."
readme = "docs/PRD.md"
requires-python = ">=3.12,<3.15"
dependencies = [
"joblib",
"matplotlib",
"numpy",
"pandas",
"scikit-learn",
"scipy",
]
[dependency-groups]
dev = [
"ipykernel",
"jupyterlab",
"nbconvert",
"pytest",
"ruff",
]
[build-system]
requires = ["setuptools>=69", "wheel"]
build-backend = "setuptools.build_meta"
[tool.setuptools.packages.find]
where = ["src"]
[tool.pytest.ini_options]
pythonpath = ["src"]
testpaths = ["tests"]
[tool.ruff]
target-version = "py312"
line-length = 100
extend-exclude = [
".agents",
".codex",
"scripts/execute.py",
]
[tool.ruff.lint]
select = ["E", "F", "I", "UP", "B"]
FESurrogateModelTutorial/reports/figures/.gitkeep
+1
View File
@@ -0,0 +1 @@
FESurrogateModelTutorial/reports/figures/comparison_fit_time_s.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 24 KiB

FESurrogateModelTutorial/reports/figures/comparison_mae.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 25 KiB

FESurrogateModelTutorial/reports/figures/comparison_predict_time_s.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 26 KiB

FESurrogateModelTutorial/reports/figures/comparison_r2.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 20 KiB

FESurrogateModelTutorial/reports/figures/comparison_rmse.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 25 KiB

FESurrogateModelTutorial/reports/figures/gpr_parity.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 40 KiB

FESurrogateModelTutorial/reports/figures/gpr_residuals.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 38 KiB

FESurrogateModelTutorial/reports/figures/gradient_boosting_parity.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 40 KiB

FESurrogateModelTutorial/reports/figures/gradient_boosting_residuals.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 35 KiB

FESurrogateModelTutorial/reports/figures/mlp_parity.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 39 KiB

FESurrogateModelTutorial/reports/figures/mlp_residuals.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 38 KiB

FESurrogateModelTutorial/reports/figures/random_forest_parity.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 40 KiB

FESurrogateModelTutorial/reports/figures/random_forest_residuals.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 38 KiB

FESurrogateModelTutorial/reports/figures/rsm_parity.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 40 KiB

FESurrogateModelTutorial/reports/figures/rsm_residuals.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 37 KiB

FESurrogateModelTutorial/reports/predictions/.gitkeep
+1
View File
@@ -0,0 +1 @@
FESurrogateModelTutorial/reports/predictions/gpr_predictions.csv
+61
View File
@@ -0,0 +1,61 @@
y_true,y_pred,residual
-0.0098010662183848,-0.015250421684545492,0.005449355466160691
-0.0038113194658788,-0.0017486039076851003,-0.0020627155581936997
-0.0027310799449712,-0.00530647071310256,0.0025753907681313605
-0.0100024342038305,-0.010316738327277896,0.00031430412344739603
-0.0499253522341076,-0.04382392281863989,-0.006101429415467707
-0.001425202073237,0.005078412534373628,-0.006503614607610628
-0.0082152702385898,-0.009571524248486946,0.0013562540098971468
-0.030294940628359,-0.02508246148372859,-0.005212479144630411
-0.0003394669209404,-0.0023962303315858673,0.0020567634106454674
-0.0104094868935342,-0.017755890098581213,0.007346403205047012
-0.0007458704516273,-0.001982076369748365,0.0012362059181210648
-0.0019926250153884,-0.003373505311388497,0.0013808802960000974
-0.0067094522111387,-0.005789165245259511,-0.0009202869658791885
-0.0007713230369176,0.0012402266579821346,-0.0020115496948997346
-0.0009264786171953,0.0010793023104413834,-0.002005780927636683
-0.0048682939239769,-0.010842246768661199,0.0059739528446842985
-0.0015514429803847,-0.005987417572614714,0.004435974592230015
-0.0082797555491993,-0.006796396801820442,-0.0014833587473788582
-0.0067435512728419,0.00680790397400651,-0.01355145524684841
-0.0002679427721747,0.0006763820975785838,-0.0009443248697532838
-0.0117102395891512,0.0006489142032870647,-0.012359153792438266
-0.0038564225187403,-0.0035722131493459413,-0.00028420936939435853
-0.0043643611560866,-0.002491745084681229,-0.0018726160714053709
-0.00690334164553,0.00027024498753304947,-0.007173586633063049
-0.0032694837296735,-0.003198392657812337,-7.109107186116298e-05
-0.0065802327277111,-0.006997526861566011,0.000417294133854911
-0.0057609873946602,-0.008005191210867332,0.0022442038162071324
-0.0978259601841187,-0.10476466176020587,0.0069387015760871695
-0.0012815473411189,0.005795482786457884,-0.007077030127576784
-0.2116989856844677,-0.1421513721299082,-0.06954761355455952
-0.0005873182212224,0.003556659925605549,-0.004143978146827949
-0.0102808405040129,-0.013683666669211234,0.0034028261651983336
-0.0274808302842225,-0.023811924704933395,-0.0036689055792891064
-0.0055843874647924,-0.004446019039931307,-0.0011383684248610932
-0.0936698604467179,-0.08476905261398741,-0.008900807832730492
-0.0042383507360532,-0.0028395908107003084,-0.0013987599253528918
-0.0064139601803737,-0.002776365124053777,-0.003637595056319923
-0.0500503637977256,-0.04468561411923253,-0.005364749678493069
-0.0032551040880256,-0.007385900526260484,0.004130796438234884
-0.0006720203919551,-0.0017365014801694594,0.0010644810882143594
-0.0140013434972624,-0.018657807128895445,0.004656463631633044
-0.0136746738089856,-0.01026732343038411,-0.0034073503786014904
-0.0029028424886419,-0.006199045083251903,0.003296202594610003
-0.0002977300790917,-0.003466576745293704,0.003168846666202004
-0.0004013312796635,0.006938137232452899,-0.0073394685121164
-0.001387036808518,-0.002671626354811536,0.0012845895462935358
-0.0032416418934662,-2.721371817649039e-05,-0.0032144281752897095
-0.0012865758997511,-0.004382274888399403,0.003095698988648303
-0.000781489181828,0.014354677949252189,-0.015136167131080189
-0.0282740230807759,-0.024446790443019183,-0.0038272326377567153
-0.0014462597918054,-0.0025761975119785365,0.0011299377201731365
-0.0009190994374579,-0.0015752616401020422,0.0006561622026441422
-0.0024183380949151,0.001816942808085446,-0.004235280903000546
-0.0080349039892428,-0.008306703776443457,0.00027179978720065674
-0.0317498587484236,-0.026193372689921272,-0.005556486058502327
-0.0028680506091303,-0.006249707444856041,0.003381656835725741
-0.0327551701410487,-0.032500451863128575,-0.0002547182779201254
-0.0002898009271785,-0.004854942238588591,0.00456514131141009
-0.0049641733799332,-0.008914425892218376,0.003950252512285176
-0.0005541404200699,0.0025102185642642497,-0.00306435898433415
1 y_true y_pred residual
2 -0.0098010662183848 -0.015250421684545492 0.005449355466160691
3 -0.0038113194658788 -0.0017486039076851003 -0.0020627155581936997
4 -0.0027310799449712 -0.00530647071310256 0.0025753907681313605
5 -0.0100024342038305 -0.010316738327277896 0.00031430412344739603
6 -0.0499253522341076 -0.04382392281863989 -0.006101429415467707
7 -0.001425202073237 0.005078412534373628 -0.006503614607610628
8 -0.0082152702385898 -0.009571524248486946 0.0013562540098971468
9 -0.030294940628359 -0.02508246148372859 -0.005212479144630411
10 -0.0003394669209404 -0.0023962303315858673 0.0020567634106454674
11 -0.0104094868935342 -0.017755890098581213 0.007346403205047012
12 -0.0007458704516273 -0.001982076369748365 0.0012362059181210648
13 -0.0019926250153884 -0.003373505311388497 0.0013808802960000974
14 -0.0067094522111387 -0.005789165245259511 -0.0009202869658791885
15 -0.0007713230369176 0.0012402266579821346 -0.0020115496948997346
16 -0.0009264786171953 0.0010793023104413834 -0.002005780927636683
17 -0.0048682939239769 -0.010842246768661199 0.0059739528446842985
18 -0.0015514429803847 -0.005987417572614714 0.004435974592230015
19 -0.0082797555491993 -0.006796396801820442 -0.0014833587473788582
20 -0.0067435512728419 0.00680790397400651 -0.01355145524684841
21 -0.0002679427721747 0.0006763820975785838 -0.0009443248697532838
22 -0.0117102395891512 0.0006489142032870647 -0.012359153792438266
23 -0.0038564225187403 -0.0035722131493459413 -0.00028420936939435853
24 -0.0043643611560866 -0.002491745084681229 -0.0018726160714053709
25 -0.00690334164553 0.00027024498753304947 -0.007173586633063049
26 -0.0032694837296735 -0.003198392657812337 -7.109107186116298e-05
27 -0.0065802327277111 -0.006997526861566011 0.000417294133854911
28 -0.0057609873946602 -0.008005191210867332 0.0022442038162071324
29 -0.0978259601841187 -0.10476466176020587 0.0069387015760871695
30 -0.0012815473411189 0.005795482786457884 -0.007077030127576784
31 -0.2116989856844677 -0.1421513721299082 -0.06954761355455952
32 -0.0005873182212224 0.003556659925605549 -0.004143978146827949
33 -0.0102808405040129 -0.013683666669211234 0.0034028261651983336
34 -0.0274808302842225 -0.023811924704933395 -0.0036689055792891064
35 -0.0055843874647924 -0.004446019039931307 -0.0011383684248610932
36 -0.0936698604467179 -0.08476905261398741 -0.008900807832730492
37 -0.0042383507360532 -0.0028395908107003084 -0.0013987599253528918
38 -0.0064139601803737 -0.002776365124053777 -0.003637595056319923
39 -0.0500503637977256 -0.04468561411923253 -0.005364749678493069
40 -0.0032551040880256 -0.007385900526260484 0.004130796438234884
41 -0.0006720203919551 -0.0017365014801694594 0.0010644810882143594
42 -0.0140013434972624 -0.018657807128895445 0.004656463631633044
43 -0.0136746738089856 -0.01026732343038411 -0.0034073503786014904
44 -0.0029028424886419 -0.006199045083251903 0.003296202594610003
45 -0.0002977300790917 -0.003466576745293704 0.003168846666202004
46 -0.0004013312796635 0.006938137232452899 -0.0073394685121164
47 -0.001387036808518 -0.002671626354811536 0.0012845895462935358
48 -0.0032416418934662 -2.721371817649039e-05 -0.0032144281752897095
49 -0.0012865758997511 -0.004382274888399403 0.003095698988648303
50 -0.000781489181828 0.014354677949252189 -0.015136167131080189
51 -0.0282740230807759 -0.024446790443019183 -0.0038272326377567153
52 -0.0014462597918054 -0.0025761975119785365 0.0011299377201731365
53 -0.0009190994374579 -0.0015752616401020422 0.0006561622026441422
54 -0.0024183380949151 0.001816942808085446 -0.004235280903000546
55 -0.0080349039892428 -0.008306703776443457 0.00027179978720065674
56 -0.0317498587484236 -0.026193372689921272 -0.005556486058502327
57 -0.0028680506091303 -0.006249707444856041 0.003381656835725741
58 -0.0327551701410487 -0.032500451863128575 -0.0002547182779201254
59 -0.0002898009271785 -0.004854942238588591 0.00456514131141009
60 -0.0049641733799332 -0.008914425892218376 0.003950252512285176
61 -0.0005541404200699 0.0025102185642642497 -0.00306435898433415
FESurrogateModelTutorial/reports/predictions/gradient_boosting_predictions.csv
+61
View File
@@ -0,0 +1,61 @@
y_true,y_pred,residual
-0.0098010662183848,-0.011534131293699368,0.0017330650753145677
-0.0038113194658788,-0.004566781630798601,0.0007554621649198006
-0.0027310799449712,-0.002569043760932535,-0.0001620361840386649
-0.0100024342038305,-0.008113001885148158,-0.0018894323186823426
-0.0499253522341076,-0.05179401032427151,0.0018686580901639063
-0.001425202073237,-0.0027429307062308422,0.0013177286329938422
-0.0082152702385898,-0.005244392438185645,-0.002970877800404154
-0.030294940628359,-0.026941379068354337,-0.003353561560004662
-0.0003394669209404,0.0011920263930887208,-0.0015314933140291207
-0.0104094868935342,-0.02009314147825499,0.009683654584720789
-0.0007458704516273,-0.0006783343667398965,-6.753608488740351e-05
-0.0019926250153884,-0.0035238050937769078,0.001531180078388508
-0.0067094522111387,0.0045098371679258165,-0.011219289379064516
-0.0007713230369176,0.0009525966890204713,-0.0017239197259380713
-0.0009264786171953,-0.0010291487366641794,0.00010267011946887947
-0.0048682939239769,-0.008554456850656682,0.003686162926679782
-0.0015514429803847,-0.003701977800637113,0.002150534820252413
-0.0082797555491993,-0.010581044499564738,0.0023012889503654377
-0.0067435512728419,-0.03214833568118499,0.02540478440834309
-0.0002679427721747,0.0012861204508787876,-0.0015540632230534876
-0.0117102395891512,-0.011566111843574601,-0.00014412774557659956
-0.0038564225187403,-0.007016644417818661,0.0031602218990783608
-0.0043643611560866,-0.0037020847290705405,-0.0006622764270160595
-0.00690334164553,-0.006957646097004912,5.430445147491282e-05
-0.0032694837296735,-0.008033853112083723,0.0047643693824102225
-0.0065802327277111,-0.0029191448483979277,-0.003661087879313172
-0.0057609873946602,-0.005458264133573717,-0.0003027232610864827
-0.0978259601841187,-0.07722849901007466,-0.02059746117404404
-0.0012815473411189,-0.0006360341549186051,-0.0006455131862002948
-0.2116989856844677,-0.08524519557269143,-0.12645379011177627
-0.0005873182212224,0.00015120038122322824,-0.0007385186024456282
-0.0102808405040129,-0.013413515680865662,0.0031326751768527613
-0.0274808302842225,-0.021333224751441966,-0.006147605532780535
-0.0055843874647924,-0.004638268193139127,-0.0009461192716532733
-0.0936698604467179,-0.10583589880087134,0.012166038354153433
-0.0042383507360532,-0.006994619539973823,0.002756268803920623
-0.0064139601803737,-0.00721593555420163,0.0008019753738279295
-0.0500503637977256,-0.029980393421298147,-0.020069970376427455
-0.0032551040880256,-0.004159641884839451,0.0009045377968138514
-0.0006720203919551,0.000695861307391559,-0.001367881699346659
-0.0140013434972624,-0.012330661500693965,-0.0016706819965684357
-0.0136746738089856,-0.01605569638030974,0.002381022571324139
-0.0029028424886419,-0.0023341567334053885,-0.0005686857552365115
-0.0002977300790917,0.0018160654458535613,-0.002113795524945261
-0.0004013312796635,0.000462792310109772,-0.000864123589773272
-0.001387036808518,-0.0002553521012893653,-0.0011316847072286348
-0.0032416418934662,-0.0034662863630390488,0.0002246444695728489
-0.0012865758997511,-0.001419939312063704,0.00013336341231260382
-0.000781489181828,0.0004714048460805055,-0.0012528940279085054
-0.0282740230807759,-0.01656459879962216,-0.011709424281153739
-0.0014462597918054,-0.001017996892076924,-0.00042826289972847597
-0.0009190994374579,-0.0030369363287297622,0.0021178368912718624
-0.0024183380949151,-0.0027257756235102245,0.0003074375285951245
-0.0080349039892428,-0.013922103226463197,0.005887199237220397
-0.0317498587484236,-0.04130074037606117,0.009550881627637571
-0.0028680506091303,-0.004243174200819291,0.0013751235916889906
-0.0327551701410487,-0.023406512064579634,-0.009348658076469066
-0.0002898009271785,-0.0003650281642084131,7.522723702991309e-05
-0.0049641733799332,-0.005214160126186096,0.00024998674625289607
-0.0005541404200699,0.0014239990341411483,-0.0019781394542110484
1 y_true y_pred residual
2 -0.0098010662183848 -0.011534131293699368 0.0017330650753145677
3 -0.0038113194658788 -0.004566781630798601 0.0007554621649198006
4 -0.0027310799449712 -0.002569043760932535 -0.0001620361840386649
5 -0.0100024342038305 -0.008113001885148158 -0.0018894323186823426
6 -0.0499253522341076 -0.05179401032427151 0.0018686580901639063
7 -0.001425202073237 -0.0027429307062308422 0.0013177286329938422
8 -0.0082152702385898 -0.005244392438185645 -0.002970877800404154
9 -0.030294940628359 -0.026941379068354337 -0.003353561560004662
10 -0.0003394669209404 0.0011920263930887208 -0.0015314933140291207
11 -0.0104094868935342 -0.02009314147825499 0.009683654584720789
12 -0.0007458704516273 -0.0006783343667398965 -6.753608488740351e-05
13 -0.0019926250153884 -0.0035238050937769078 0.001531180078388508
14 -0.0067094522111387 0.0045098371679258165 -0.011219289379064516
15 -0.0007713230369176 0.0009525966890204713 -0.0017239197259380713
16 -0.0009264786171953 -0.0010291487366641794 0.00010267011946887947
17 -0.0048682939239769 -0.008554456850656682 0.003686162926679782
18 -0.0015514429803847 -0.003701977800637113 0.002150534820252413
19 -0.0082797555491993 -0.010581044499564738 0.0023012889503654377
20 -0.0067435512728419 -0.03214833568118499 0.02540478440834309
21 -0.0002679427721747 0.0012861204508787876 -0.0015540632230534876
22 -0.0117102395891512 -0.011566111843574601 -0.00014412774557659956
23 -0.0038564225187403 -0.007016644417818661 0.0031602218990783608
24 -0.0043643611560866 -0.0037020847290705405 -0.0006622764270160595
25 -0.00690334164553 -0.006957646097004912 5.430445147491282e-05
26 -0.0032694837296735 -0.008033853112083723 0.0047643693824102225
27 -0.0065802327277111 -0.0029191448483979277 -0.003661087879313172
28 -0.0057609873946602 -0.005458264133573717 -0.0003027232610864827
29 -0.0978259601841187 -0.07722849901007466 -0.02059746117404404
30 -0.0012815473411189 -0.0006360341549186051 -0.0006455131862002948
31 -0.2116989856844677 -0.08524519557269143 -0.12645379011177627
32 -0.0005873182212224 0.00015120038122322824 -0.0007385186024456282
33 -0.0102808405040129 -0.013413515680865662 0.0031326751768527613
34 -0.0274808302842225 -0.021333224751441966 -0.006147605532780535
35 -0.0055843874647924 -0.004638268193139127 -0.0009461192716532733
36 -0.0936698604467179 -0.10583589880087134 0.012166038354153433
37 -0.0042383507360532 -0.006994619539973823 0.002756268803920623
38 -0.0064139601803737 -0.00721593555420163 0.0008019753738279295
39 -0.0500503637977256 -0.029980393421298147 -0.020069970376427455
40 -0.0032551040880256 -0.004159641884839451 0.0009045377968138514
41 -0.0006720203919551 0.000695861307391559 -0.001367881699346659
42 -0.0140013434972624 -0.012330661500693965 -0.0016706819965684357
43 -0.0136746738089856 -0.01605569638030974 0.002381022571324139
44 -0.0029028424886419 -0.0023341567334053885 -0.0005686857552365115
45 -0.0002977300790917 0.0018160654458535613 -0.002113795524945261
46 -0.0004013312796635 0.000462792310109772 -0.000864123589773272
47 -0.001387036808518 -0.0002553521012893653 -0.0011316847072286348
48 -0.0032416418934662 -0.0034662863630390488 0.0002246444695728489
49 -0.0012865758997511 -0.001419939312063704 0.00013336341231260382
50 -0.000781489181828 0.0004714048460805055 -0.0012528940279085054
51 -0.0282740230807759 -0.01656459879962216 -0.011709424281153739
52 -0.0014462597918054 -0.001017996892076924 -0.00042826289972847597
53 -0.0009190994374579 -0.0030369363287297622 0.0021178368912718624
54 -0.0024183380949151 -0.0027257756235102245 0.0003074375285951245
55 -0.0080349039892428 -0.013922103226463197 0.005887199237220397
56 -0.0317498587484236 -0.04130074037606117 0.009550881627637571
57 -0.0028680506091303 -0.004243174200819291 0.0013751235916889906
58 -0.0327551701410487 -0.023406512064579634 -0.009348658076469066
59 -0.0002898009271785 -0.0003650281642084131 7.522723702991309e-05
60 -0.0049641733799332 -0.005214160126186096 0.00024998674625289607
61 -0.0005541404200699 0.0014239990341411483 -0.0019781394542110484
FESurrogateModelTutorial/reports/predictions/mlp_predictions.csv
+61
View File
@@ -0,0 +1,61 @@
y_true,y_pred,residual
-0.0098010662183848,-0.012802577507486139,0.0030015112891013385
-0.0038113194658788,-0.0046515848170360155,0.0008402653511572155
-0.0027310799449712,-0.010083004760998512,0.007351924816027313
-0.0100024342038305,-0.020845283706657287,0.010842849502826787
-0.0499253522341076,-0.040221134519255825,-0.009704217714851776
-0.001425202073237,-0.009762081791064406,0.008336879717827405
-0.0082152702385898,-0.016983972468944918,0.008768702230355118
-0.030294940628359,-0.038763408487603644,0.008468467859244645
-0.0003394669209404,0.0035130197140065145,-0.0038524866349469145
-0.0104094868935342,-0.022486601392994278,0.012077114499460077
-0.0007458704516273,0.008186185488004654,-0.008932055939631955
-0.0019926250153884,-0.0024680978973060427,0.00047547288191764287
-0.0067094522111387,-0.00822713371747703,0.0015176815063383305
-0.0007713230369176,0.00270054572699867,-0.00347186876391627
-0.0009264786171953,0.010416977768376428,-0.011343456385571727
-0.0048682939239769,-0.011506092562164864,0.006637798638187964
-0.0015514429803847,-0.009492646984972703,0.007941204004588002
-0.0082797555491993,-0.021706863748004304,0.013427108198805004
-0.0067435512728419,-0.024564514477627017,0.017820963204785118
-0.0002679427721747,0.003440036938729933,-0.003707979710904633
-0.0117102395891512,-0.01948773259389725,0.007777493004746051
-0.0038564225187403,-0.009001834137222772,0.005145411618482472
-0.0043643611560866,-0.005807071720011332,0.0014427105639247323
-0.00690334164553,-0.012051489346343392,0.005148147700813392
-0.0032694837296735,-0.014340233862364537,0.011070750132691036
-0.0065802327277111,-0.023390501917222473,0.016810269189511375
-0.0057609873946602,-0.009722949790975566,0.003961962396315366
-0.0978259601841187,-0.04217063129833486,-0.05565532888578384
-0.0012815473411189,0.0006427388868981282,-0.001924286228017028
-0.2116989856844677,-0.03964152265257154,-0.17205746303189617
-0.0005873182212224,0.013045438142832844,-0.013632756364055244
-0.0102808405040129,-0.014460966326431212,0.004180125822418312
-0.0274808302842225,-0.020779704750440366,-0.006701125533782135
-0.0055843874647924,-0.011569739698444227,0.005985352233651826
-0.0936698604467179,-0.04673036973556968,-0.046939490711148224
-0.0042383507360532,-0.015102657835677205,0.010864307099624004
-0.0064139601803737,-0.021855516256323176,0.015441556075949476
-0.0500503637977256,-0.04096821507960851,-0.009082148718117092
-0.0032551040880256,-0.009473373379514092,0.006218269291488492
-0.0006720203919551,0.008151921529756209,-0.008823941921711308
-0.0140013434972624,-0.027026365760490362,0.013025022263227961
-0.0136746738089856,-0.018268174014002526,0.004593500205016926
-0.0029028424886419,-0.005384453894577489,0.0024816114059355893
-0.0002977300790917,0.01502494424731751,-0.01532267432640921
-0.0004013312796635,0.008176262367795053,-0.008577593647458553
-0.001387036808518,-0.0039136142664811455,0.002526577457963145
-0.0032416418934662,-0.0005496866955882595,-0.0026919551978779404
-0.0012865758997511,-0.0015485890387889768,0.00026201313903787666
-0.000781489181828,0.00021154768682392702,-0.000993036868651927
-0.0282740230807759,-0.0361710784496896,0.007897055368913702
-0.0014462597918054,0.0010447393076983297,-0.0024909990995037297
-0.0009190994374579,0.0005076838393030369,-0.001426783276760937
-0.0024183380949151,-0.005814615168676113,0.0033962770737610134
-0.0080349039892428,-0.017259202204240334,0.009224298214997534
-0.0317498587484236,-0.01979978011856444,-0.01195007862985916
-0.0028680506091303,-0.0025464659000482004,-0.00032158470908209965
-0.0327551701410487,-0.02888314308530364,-0.0038720270557450615
-0.0002898009271785,0.004474162373067482,-0.004763963300245982
-0.0049641733799332,-0.009564500114358745,0.004600326734425545
-0.0005541404200699,-0.008223453061769786,0.007669312641699886
1 y_true y_pred residual
2 -0.0098010662183848 -0.012802577507486139 0.0030015112891013385
3 -0.0038113194658788 -0.0046515848170360155 0.0008402653511572155
4 -0.0027310799449712 -0.010083004760998512 0.007351924816027313
5 -0.0100024342038305 -0.020845283706657287 0.010842849502826787
6 -0.0499253522341076 -0.040221134519255825 -0.009704217714851776
7 -0.001425202073237 -0.009762081791064406 0.008336879717827405
8 -0.0082152702385898 -0.016983972468944918 0.008768702230355118
9 -0.030294940628359 -0.038763408487603644 0.008468467859244645
10 -0.0003394669209404 0.0035130197140065145 -0.0038524866349469145
11 -0.0104094868935342 -0.022486601392994278 0.012077114499460077
12 -0.0007458704516273 0.008186185488004654 -0.008932055939631955
13 -0.0019926250153884 -0.0024680978973060427 0.00047547288191764287
14 -0.0067094522111387 -0.00822713371747703 0.0015176815063383305
15 -0.0007713230369176 0.00270054572699867 -0.00347186876391627
16 -0.0009264786171953 0.010416977768376428 -0.011343456385571727
17 -0.0048682939239769 -0.011506092562164864 0.006637798638187964
18 -0.0015514429803847 -0.009492646984972703 0.007941204004588002
19 -0.0082797555491993 -0.021706863748004304 0.013427108198805004
20 -0.0067435512728419 -0.024564514477627017 0.017820963204785118
21 -0.0002679427721747 0.003440036938729933 -0.003707979710904633
22 -0.0117102395891512 -0.01948773259389725 0.007777493004746051
23 -0.0038564225187403 -0.009001834137222772 0.005145411618482472
24 -0.0043643611560866 -0.005807071720011332 0.0014427105639247323
25 -0.00690334164553 -0.012051489346343392 0.005148147700813392
26 -0.0032694837296735 -0.014340233862364537 0.011070750132691036
27 -0.0065802327277111 -0.023390501917222473 0.016810269189511375
28 -0.0057609873946602 -0.009722949790975566 0.003961962396315366
29 -0.0978259601841187 -0.04217063129833486 -0.05565532888578384
30 -0.0012815473411189 0.0006427388868981282 -0.001924286228017028
31 -0.2116989856844677 -0.03964152265257154 -0.17205746303189617
32 -0.0005873182212224 0.013045438142832844 -0.013632756364055244
33 -0.0102808405040129 -0.014460966326431212 0.004180125822418312
34 -0.0274808302842225 -0.020779704750440366 -0.006701125533782135
35 -0.0055843874647924 -0.011569739698444227 0.005985352233651826
36 -0.0936698604467179 -0.04673036973556968 -0.046939490711148224
37 -0.0042383507360532 -0.015102657835677205 0.010864307099624004
38 -0.0064139601803737 -0.021855516256323176 0.015441556075949476
39 -0.0500503637977256 -0.04096821507960851 -0.009082148718117092
40 -0.0032551040880256 -0.009473373379514092 0.006218269291488492
41 -0.0006720203919551 0.008151921529756209 -0.008823941921711308
42 -0.0140013434972624 -0.027026365760490362 0.013025022263227961
43 -0.0136746738089856 -0.018268174014002526 0.004593500205016926
44 -0.0029028424886419 -0.005384453894577489 0.0024816114059355893
45 -0.0002977300790917 0.01502494424731751 -0.01532267432640921
46 -0.0004013312796635 0.008176262367795053 -0.008577593647458553
47 -0.001387036808518 -0.0039136142664811455 0.002526577457963145
48 -0.0032416418934662 -0.0005496866955882595 -0.0026919551978779404
49 -0.0012865758997511 -0.0015485890387889768 0.00026201313903787666
50 -0.000781489181828 0.00021154768682392702 -0.000993036868651927
51 -0.0282740230807759 -0.0361710784496896 0.007897055368913702
52 -0.0014462597918054 0.0010447393076983297 -0.0024909990995037297
53 -0.0009190994374579 0.0005076838393030369 -0.001426783276760937
54 -0.0024183380949151 -0.005814615168676113 0.0033962770737610134
55 -0.0080349039892428 -0.017259202204240334 0.009224298214997534
56 -0.0317498587484236 -0.01979978011856444 -0.01195007862985916
57 -0.0028680506091303 -0.0025464659000482004 -0.00032158470908209965
58 -0.0327551701410487 -0.02888314308530364 -0.0038720270557450615
59 -0.0002898009271785 0.004474162373067482 -0.004763963300245982
60 -0.0049641733799332 -0.009564500114358745 0.004600326734425545
61 -0.0005541404200699 -0.008223453061769786 0.007669312641699886
FESurrogateModelTutorial/reports/predictions/random_forest_predictions.csv
+61
View File
@@ -0,0 +1,61 @@
y_true,y_pred,residual
-0.0098010662183848,-0.013052973102582651,0.003251906884197851
-0.0038113194658788,-0.0030832217758694816,-0.0007280976900093184
-0.0027310799449712,-0.003443617119201804,0.0007125371742306044
-0.0100024342038305,-0.006389981087977729,-0.0036124531158527717
-0.0499253522341076,-0.015352738964269329,-0.03457261326983827
-0.001425202073237,-0.018459481777023584,0.017034279703786584
-0.0082152702385898,-0.004456616612166581,-0.003758653626423218
-0.030294940628359,-0.0233835822329406,-0.006911358395418399
-0.0003394669209404,-0.001335100166637542,0.000995633245697142
-0.0104094868935342,-0.029524370191124354,0.019114883297590153
-0.0007458704516273,-0.0010697310437712045,0.00032386059214390447
-0.0019926250153884,-0.0020536291218114233,6.1004106423023525e-05
-0.0067094522111387,-0.014557394629973457,0.007847942418834757
-0.0007713230369176,-0.0012499540750173254,0.0004786310380997254
-0.0009264786171953,-0.0012898747386864487,0.0003633961214911487
-0.0048682939239769,-0.010281716791039721,0.005413422867062821
-0.0015514429803847,-0.006064928713181127,0.004513485732796427
-0.0082797555491993,-0.01020851915611972,0.0019287636069204202
-0.0067435512728419,-0.05887513385526359,0.05213158258242169
-0.0002679427721747,-0.0014368826831020398,0.0011689399109273398
-0.0117102395891512,-0.00897904191064286,-0.002731197678508341
-0.0038564225187403,-0.007064039332542149,0.0032076168138018488
-0.0043643611560866,-0.0038693413391170145,-0.0004950198169695855
-0.00690334164553,-0.0038950530678037608,-0.003008288577726239
-0.0032694837296735,-0.006531726228139853,0.003262242498466353
-0.0065802327277111,-0.01746332239669454,0.010883089668983442
-0.0057609873946602,-0.0042079257092469515,-0.0015530616854132484
-0.0978259601841187,-0.06427351865985945,-0.03355244152425925
-0.0012815473411189,-0.00131837298277374,3.6825641654840034e-05
-0.2116989856844677,-0.07299885186088179,-0.13870013382358592
-0.0005873182212224,-0.0008764204060906751,0.00028910218486827516
-0.0102808405040129,-0.025656683515613517,0.015375843011600616
-0.0274808302842225,-0.0233500781934777,-0.004130752090744802
-0.0055843874647924,-0.00360254423169254,-0.0019818432330998602
-0.0936698604467179,-0.06835084136803436,-0.025319019078683544
-0.0042383507360532,-0.008322436707289365,0.004084085971236165
-0.0064139601803737,-0.007978798272136524,0.0015648380917628237
-0.0500503637977256,-0.029134230073410976,-0.020916133724314626
-0.0032551040880256,-0.0038575984824836713,0.0006024943944580715
-0.0006720203919551,-0.0008321139785327232,0.0001600935865776232
-0.0140013434972624,-0.009220030597946776,-0.004781312899315625
-0.0136746738089856,-0.012918969755213044,-0.000755704053772557
-0.0029028424886419,-0.007061520705634288,0.004158678216992388
-0.0002977300790917,-0.0008244792974268024,0.0005267492183351024
-0.0004013312796635,-0.0006335738388530976,0.00023224255918959758
-0.001387036808518,-0.0022687878733974104,0.0008817510648794103
-0.0032416418934662,-0.0031708494223524506,-7.079247111374922e-05
-0.0012865758997511,-0.0020774063656214905,0.0007908304658703904
-0.000781489181828,-0.004022832924982734,0.003241343743154734
-0.0282740230807759,-0.023201264759851178,-0.005072758320924721
-0.0014462597918054,-0.0021273945521054927,0.0006811347603000928
-0.0009190994374579,-0.0011891624177935518,0.0002700629803356518
-0.0024183380949151,-0.002935912586886879,0.0005175744919717791
-0.0080349039892428,-0.012493932904864844,0.004459028915622044
-0.0317498587484236,-0.02917403551090198,-0.0025758232375216183
-0.0028680506091303,-0.002477127846164984,-0.00039092276296531607
-0.0327551701410487,-0.020574378594002435,-0.012180791547046266
-0.0002898009271785,-0.0030515507112431066,0.0027617497840646066
-0.0049641733799332,-0.005639149529924011,0.0006749761499908113
-0.0005541404200699,-0.0033415931535627887,0.0027874527334928885
1 y_true y_pred residual
2 -0.0098010662183848 -0.013052973102582651 0.003251906884197851
3 -0.0038113194658788 -0.0030832217758694816 -0.0007280976900093184
4 -0.0027310799449712 -0.003443617119201804 0.0007125371742306044
5 -0.0100024342038305 -0.006389981087977729 -0.0036124531158527717
6 -0.0499253522341076 -0.015352738964269329 -0.03457261326983827
7 -0.001425202073237 -0.018459481777023584 0.017034279703786584
8 -0.0082152702385898 -0.004456616612166581 -0.003758653626423218
9 -0.030294940628359 -0.0233835822329406 -0.006911358395418399
10 -0.0003394669209404 -0.001335100166637542 0.000995633245697142
11 -0.0104094868935342 -0.029524370191124354 0.019114883297590153
12 -0.0007458704516273 -0.0010697310437712045 0.00032386059214390447
13 -0.0019926250153884 -0.0020536291218114233 6.1004106423023525e-05
14 -0.0067094522111387 -0.014557394629973457 0.007847942418834757
15 -0.0007713230369176 -0.0012499540750173254 0.0004786310380997254
16 -0.0009264786171953 -0.0012898747386864487 0.0003633961214911487
17 -0.0048682939239769 -0.010281716791039721 0.005413422867062821
18 -0.0015514429803847 -0.006064928713181127 0.004513485732796427
19 -0.0082797555491993 -0.01020851915611972 0.0019287636069204202
20 -0.0067435512728419 -0.05887513385526359 0.05213158258242169
21 -0.0002679427721747 -0.0014368826831020398 0.0011689399109273398
22 -0.0117102395891512 -0.00897904191064286 -0.002731197678508341
23 -0.0038564225187403 -0.007064039332542149 0.0032076168138018488
24 -0.0043643611560866 -0.0038693413391170145 -0.0004950198169695855
25 -0.00690334164553 -0.0038950530678037608 -0.003008288577726239
26 -0.0032694837296735 -0.006531726228139853 0.003262242498466353
27 -0.0065802327277111 -0.01746332239669454 0.010883089668983442
28 -0.0057609873946602 -0.0042079257092469515 -0.0015530616854132484
29 -0.0978259601841187 -0.06427351865985945 -0.03355244152425925
30 -0.0012815473411189 -0.00131837298277374 3.6825641654840034e-05
31 -0.2116989856844677 -0.07299885186088179 -0.13870013382358592
32 -0.0005873182212224 -0.0008764204060906751 0.00028910218486827516
33 -0.0102808405040129 -0.025656683515613517 0.015375843011600616
34 -0.0274808302842225 -0.0233500781934777 -0.004130752090744802
35 -0.0055843874647924 -0.00360254423169254 -0.0019818432330998602
36 -0.0936698604467179 -0.06835084136803436 -0.025319019078683544
37 -0.0042383507360532 -0.008322436707289365 0.004084085971236165
38 -0.0064139601803737 -0.007978798272136524 0.0015648380917628237
39 -0.0500503637977256 -0.029134230073410976 -0.020916133724314626
40 -0.0032551040880256 -0.0038575984824836713 0.0006024943944580715
41 -0.0006720203919551 -0.0008321139785327232 0.0001600935865776232
42 -0.0140013434972624 -0.009220030597946776 -0.004781312899315625
43 -0.0136746738089856 -0.012918969755213044 -0.000755704053772557
44 -0.0029028424886419 -0.007061520705634288 0.004158678216992388
45 -0.0002977300790917 -0.0008244792974268024 0.0005267492183351024
46 -0.0004013312796635 -0.0006335738388530976 0.00023224255918959758
47 -0.001387036808518 -0.0022687878733974104 0.0008817510648794103
48 -0.0032416418934662 -0.0031708494223524506 -7.079247111374922e-05
49 -0.0012865758997511 -0.0020774063656214905 0.0007908304658703904
50 -0.000781489181828 -0.004022832924982734 0.003241343743154734
51 -0.0282740230807759 -0.023201264759851178 -0.005072758320924721
52 -0.0014462597918054 -0.0021273945521054927 0.0006811347603000928
53 -0.0009190994374579 -0.0011891624177935518 0.0002700629803356518
54 -0.0024183380949151 -0.002935912586886879 0.0005175744919717791
55 -0.0080349039892428 -0.012493932904864844 0.004459028915622044
56 -0.0317498587484236 -0.02917403551090198 -0.0025758232375216183
57 -0.0028680506091303 -0.002477127846164984 -0.00039092276296531607
58 -0.0327551701410487 -0.020574378594002435 -0.012180791547046266
59 -0.0002898009271785 -0.0030515507112431066 0.0027617497840646066
60 -0.0049641733799332 -0.005639149529924011 0.0006749761499908113
61 -0.0005541404200699 -0.0033415931535627887 0.0027874527334928885
FESurrogateModelTutorial/reports/predictions/rsm_predictions.csv
+61
View File
@@ -0,0 +1,61 @@
y_true,y_pred,residual
-0.0098010662183848,-0.008063708243651395,-0.0017373579747334052
-0.0038113194658788,-0.0036842415434730005,-0.0001270779224057995
-0.0027310799449712,0.0015855198478710482,-0.0043165997928422475
-0.0100024342038305,-0.020768772136692537,0.010766337932862037
-0.0499253522341076,-0.08634072145899263,0.03641536922488503
-0.001425202073237,0.009057330651376155,-0.010482532724613155
-0.0082152702385898,-0.01623359805579585,0.00801832781720605
-0.030294940628359,-0.05494634739863705,0.024651406770278047
-0.0003394669209404,0.0003057217392075026,-0.0006451886601479026
-0.0104094868935342,-0.025186470928988097,0.014776984035453897
-0.0007458704516273,0.005123479401716775,-0.0058693498533440745
-0.0019926250153884,0.006483277853635958,-0.008475902869024358
-0.0067094522111387,-0.004951368629097145,-0.0017580835820415544
-0.0007713230369176,0.002431470422207911,-0.003202793459125511
-0.0009264786171953,0.002098379150773981,-0.0030248577679692808
-0.0048682939239769,0.0023269502345097445,-0.007195244158486645
-0.0015514429803847,0.0054304376400158855,-0.006981880620400585
-0.0082797555491993,-0.011235438686456989,0.0029556831372576885
-0.0067435512728419,-0.01513640141753062,0.00839285014468872
-0.0002679427721747,0.005023227034898421,-0.005291169807073121
-0.0117102395891512,-0.021353175562886392,0.009642935973735191
-0.0038564225187403,0.0024523028133941953,-0.006308725332134495
-0.0043643611560866,0.0018118523029535282,-0.006176213459040129
-0.00690334164553,-0.011090572616019383,0.004187230970489383
-0.0032694837296735,-0.0010327942129321746,-0.0022366895167413255
-0.0065802327277111,-0.010449659009701765,0.0038694262819906657
-0.0057609873946602,-0.004202124085317911,-0.0015588633093422885
-0.0978259601841187,-0.07849009051035474,-0.019335869673763953
-0.0012815473411189,0.0045897836777313485,-0.005871331018850248
-0.2116989856844677,-0.11236685970490985,-0.09933212597955786
-0.0005873182212224,-0.0038346423165307834,0.0032473240953083834
-0.0102808405040129,-0.011514380677840113,0.001233540173827213
-0.0274808302842225,-0.03997989882186454,0.01249906853764204
-0.0055843874647924,-0.007827865894016085,0.0022434784292236845
-0.0936698604467179,-0.07675546207236617,-0.01691439837435174
-0.0042383507360532,0.0005673146824279073,-0.004805665418481108
-0.0064139601803737,-0.011035615882888063,0.004621655702514363
-0.0500503637977256,-0.07016141645387532,0.020111052656149715
-0.0032551040880256,0.00548188417318066,-0.008736988261206259
-0.0006720203919551,0.0009801902763272793,-0.0016522106682823794
-0.0140013434972624,-0.025223749239703955,0.011222405742441554
-0.0136746738089856,-0.033649129185114264,0.019974455376128665
-0.0029028424886419,0.0016175132552921486,-0.004520355743934048
-0.0002977300790917,-0.012343066428881081,0.012045336349789382
-0.0004013312796635,-0.0019906728761898054,0.0015893415965263053
-0.001387036808518,0.014394621344358304,-0.015781658152876302
-0.0032416418934662,-0.0017551803377404158,-0.001486461555725784
-0.0012865758997511,0.011086934940341958,-0.012373510840093058
-0.000781489181828,0.009985914013305923,-0.010767403195133923
-0.0282740230807759,-0.03956474679869234,0.01129072371791644
-0.0014462597918054,0.0017128674505823053,-0.0031591272423877052
-0.0009190994374579,0.008880594747871942,-0.009799694185329841
-0.0024183380949151,0.006026571466815343,-0.008444909561730444
-0.0080349039892428,-0.012179467818523977,0.004144563829281177
-0.0317498587484236,-0.03552887414112901,0.0037790153927054135
-0.0028680506091303,0.0019507691371565064,-0.004818819746286807
-0.0327551701410487,-0.06483928482330545,0.03208411468225675
-0.0002898009271785,0.0050500589361993,-0.0053398598633778
-0.0049641733799332,-0.001537216194153125,-0.003426957185780075
-0.0005541404200699,0.015848580403955245,-0.016402720824025146
1 y_true y_pred residual
2 -0.0098010662183848 -0.008063708243651395 -0.0017373579747334052
3 -0.0038113194658788 -0.0036842415434730005 -0.0001270779224057995
4 -0.0027310799449712 0.0015855198478710482 -0.0043165997928422475
5 -0.0100024342038305 -0.020768772136692537 0.010766337932862037
6 -0.0499253522341076 -0.08634072145899263 0.03641536922488503
7 -0.001425202073237 0.009057330651376155 -0.010482532724613155
8 -0.0082152702385898 -0.01623359805579585 0.00801832781720605
9 -0.030294940628359 -0.05494634739863705 0.024651406770278047
10 -0.0003394669209404 0.0003057217392075026 -0.0006451886601479026
11 -0.0104094868935342 -0.025186470928988097 0.014776984035453897
12 -0.0007458704516273 0.005123479401716775 -0.0058693498533440745
13 -0.0019926250153884 0.006483277853635958 -0.008475902869024358
14 -0.0067094522111387 -0.004951368629097145 -0.0017580835820415544
15 -0.0007713230369176 0.002431470422207911 -0.003202793459125511
16 -0.0009264786171953 0.002098379150773981 -0.0030248577679692808
17 -0.0048682939239769 0.0023269502345097445 -0.007195244158486645
18 -0.0015514429803847 0.0054304376400158855 -0.006981880620400585
19 -0.0082797555491993 -0.011235438686456989 0.0029556831372576885
20 -0.0067435512728419 -0.01513640141753062 0.00839285014468872
21 -0.0002679427721747 0.005023227034898421 -0.005291169807073121
22 -0.0117102395891512 -0.021353175562886392 0.009642935973735191
23 -0.0038564225187403 0.0024523028133941953 -0.006308725332134495
24 -0.0043643611560866 0.0018118523029535282 -0.006176213459040129
25 -0.00690334164553 -0.011090572616019383 0.004187230970489383
26 -0.0032694837296735 -0.0010327942129321746 -0.0022366895167413255
27 -0.0065802327277111 -0.010449659009701765 0.0038694262819906657
28 -0.0057609873946602 -0.004202124085317911 -0.0015588633093422885
29 -0.0978259601841187 -0.07849009051035474 -0.019335869673763953
30 -0.0012815473411189 0.0045897836777313485 -0.005871331018850248
31 -0.2116989856844677 -0.11236685970490985 -0.09933212597955786
32 -0.0005873182212224 -0.0038346423165307834 0.0032473240953083834
33 -0.0102808405040129 -0.011514380677840113 0.001233540173827213
34 -0.0274808302842225 -0.03997989882186454 0.01249906853764204
35 -0.0055843874647924 -0.007827865894016085 0.0022434784292236845
36 -0.0936698604467179 -0.07675546207236617 -0.01691439837435174
37 -0.0042383507360532 0.0005673146824279073 -0.004805665418481108
38 -0.0064139601803737 -0.011035615882888063 0.004621655702514363
39 -0.0500503637977256 -0.07016141645387532 0.020111052656149715
40 -0.0032551040880256 0.00548188417318066 -0.008736988261206259
41 -0.0006720203919551 0.0009801902763272793 -0.0016522106682823794
42 -0.0140013434972624 -0.025223749239703955 0.011222405742441554
43 -0.0136746738089856 -0.033649129185114264 0.019974455376128665
44 -0.0029028424886419 0.0016175132552921486 -0.004520355743934048
45 -0.0002977300790917 -0.012343066428881081 0.012045336349789382
46 -0.0004013312796635 -0.0019906728761898054 0.0015893415965263053
47 -0.001387036808518 0.014394621344358304 -0.015781658152876302
48 -0.0032416418934662 -0.0017551803377404158 -0.001486461555725784
49 -0.0012865758997511 0.011086934940341958 -0.012373510840093058
50 -0.000781489181828 0.009985914013305923 -0.010767403195133923
51 -0.0282740230807759 -0.03956474679869234 0.01129072371791644
52 -0.0014462597918054 0.0017128674505823053 -0.0031591272423877052
53 -0.0009190994374579 0.008880594747871942 -0.009799694185329841
54 -0.0024183380949151 0.006026571466815343 -0.008444909561730444
55 -0.0080349039892428 -0.012179467818523977 0.004144563829281177
56 -0.0317498587484236 -0.03552887414112901 0.0037790153927054135
57 -0.0028680506091303 0.0019507691371565064 -0.004818819746286807
58 -0.0327551701410487 -0.06483928482330545 0.03208411468225675
59 -0.0002898009271785 0.0050500589361993 -0.0053398598633778
60 -0.0049641733799332 -0.001537216194153125 -0.003426957185780075
61 -0.0005541404200699 0.015848580403955245 -0.016402720824025146
FESurrogateModelTutorial/reports/results/.gitkeep
+1
View File
@@ -0,0 +1 @@
FESurrogateModelTutorial/reports/results/gpr_metrics.json
+9
View File
@@ -0,0 +1,9 @@
{
"model_name": "gpr",
"target_column": "tip_uy_m",
"rmse": 0.0102275703149458,
"mae": 0.004887524852501009,
"r2": 0.8984149766904297,
"fit_time_s": 0.15534250007476658,
"predict_time_s": 0.0016494999872520566
}
FESurrogateModelTutorial/reports/results/gradient_boosting_metrics.json
+9
View File
@@ -0,0 +1,9 @@
{
"model_name": "gradient_boosting",
"target_column": "tip_uy_m",
"rmse": 0.017503204254034725,
"mae": 0.0056308989929006875,
"r2": 0.7024774700809826,
"fit_time_s": 0.4196564999874681,
"predict_time_s": 0.0021611000411212444
}
FESurrogateModelTutorial/reports/results/mlp_metrics.json
+9
View File
@@ -0,0 +1,9 @@
{
"model_name": "mlp",
"target_column": "tip_uy_m",
"rmse": 0.02540606802811113,
"mae": 0.011091159933185777,
"r2": 0.3731557450209999,
"fit_time_s": 0.114232899970375,
"predict_time_s": 0.0020921999821439385
}
FESurrogateModelTutorial/reports/results/model_comparison.csv
+6
View File
@@ -0,0 +1,6 @@
model_name,target_column,rmse,mae,r2,fit_time_s,predict_time_s
gpr,tip_uy_m,0.0102275703149458,0.004887524852501009,0.8984149766904297,0.15534250007476658,0.0016494999872520566
rsm,tip_uy_m,0.01692421409745107,0.00986868711451997,0.7218354651088679,0.008010599995031953,0.0015782000264152884
gradient_boosting,tip_uy_m,0.017503204254034725,0.0056308989929006875,0.7024774700809826,0.4196564999874681,0.0021611000411212444
random_forest,tip_uy_m,0.021182094831369028,0.008076487480895672,0.5642648925820651,0.6153512999881059,0.08771130000241101
mlp,tip_uy_m,0.02540606802811113,0.011091159933185777,0.3731557450209999,0.114232899970375,0.0020921999821439385
1 model_name target_column rmse mae r2 fit_time_s predict_time_s
2 gpr tip_uy_m 0.0102275703149458 0.004887524852501009 0.8984149766904297 0.15534250007476658 0.0016494999872520566
3 rsm tip_uy_m 0.01692421409745107 0.00986868711451997 0.7218354651088679 0.008010599995031953 0.0015782000264152884
4 gradient_boosting tip_uy_m 0.017503204254034725 0.0056308989929006875 0.7024774700809826 0.4196564999874681 0.0021611000411212444
5 random_forest tip_uy_m 0.021182094831369028 0.008076487480895672 0.5642648925820651 0.6153512999881059 0.08771130000241101
6 mlp tip_uy_m 0.02540606802811113 0.011091159933185777 0.3731557450209999 0.114232899970375 0.0020921999821439385
FESurrogateModelTutorial/reports/results/random_forest_metrics.json
+9
View File
@@ -0,0 +1,9 @@
{
"model_name": "random_forest",
"target_column": "tip_uy_m",
"rmse": 0.021182094831369028,
"mae": 0.008076487480895672,
"r2": 0.5642648925820651,
"fit_time_s": 0.6153512999881059,
"predict_time_s": 0.08771130000241101
}
FESurrogateModelTutorial/reports/results/rsm_metrics.json
+9
View File
@@ -0,0 +1,9 @@
{
"model_name": "rsm",
"target_column": "tip_uy_m",
"rmse": 0.01692421409745107,
"mae": 0.00986868711451997,
"r2": 0.7218354651088679,
"fit_time_s": 0.008010599995031953,
"predict_time_s": 0.0015782000264152884
}
FESurrogateModelTutorial/scripts/execute.py
+417
View File
@@ -0,0 +1,417 @@
#!/usr/bin/env python3
"""
Harness Step Executor — phase 내 step을 순차 실행하고 자가 교정한다.
Usage:
python scripts/execute.py <phase-dir> [--push]
"""
import argparse
import contextlib
import json
import os
import subprocess
import sys
import threading
import time
import types
from datetime import datetime, timezone, timedelta
from pathlib import Path
from typing import Optional
ROOT = Path(__file__).resolve().parent.parent
@contextlib.contextmanager
def progress_indicator(label: str):
"""터미널 진행 표시기. with 문으로 사용하며 .elapsed 로 경과 시간을 읽는다."""
frames = "◐◓◑◒"
stop = threading.Event()
t0 = time.monotonic()
def _animate():
idx = 0
while not stop.wait(0.12):
sec = int(time.monotonic() - t0)
sys.stderr.write(f"\r{frames[idx % len(frames)]} {label} [{sec}s]")
sys.stderr.flush()
idx += 1
sys.stderr.write("\r" + " " * (len(label) + 20) + "\r")
sys.stderr.flush()
th = threading.Thread(target=_animate, daemon=True)
th.start()
info = types.SimpleNamespace(elapsed=0.0)
try:
yield info
finally:
stop.set()
th.join()
info.elapsed = time.monotonic() - t0
class StepExecutor:
"""Phase 디렉토리 안의 step들을 순차 실행하는 하네스."""
MAX_RETRIES = 3
FEAT_MSG = "feat({phase}): step {num} — {name}"
CHORE_MSG = "chore({phase}): step {num} output"
TZ = timezone(timedelta(hours=9))
def __init__(self, phase_dir_name: str, *, auto_push: bool = False):
self._root = str(ROOT)
self._phases_dir = ROOT / "phases"
self._phase_dir = self._phases_dir / phase_dir_name
self._phase_dir_name = phase_dir_name
self._top_index_file = self._phases_dir / "index.json"
self._auto_push = auto_push
if not self._phase_dir.is_dir():
print(f"ERROR: {self._phase_dir} not found")
sys.exit(1)
self._index_file = self._phase_dir / "index.json"
if not self._index_file.exists():
print(f"ERROR: {self._index_file} not found")
sys.exit(1)
idx = self._read_json(self._index_file)
self._project = idx.get("project", "project")
self._phase_name = idx.get("phase", phase_dir_name)
self._total = len(idx["steps"])
def run(self):
self._print_header()
self._check_blockers()
self._checkout_branch()
guardrails = self._load_guardrails()
self._ensure_created_at()
self._execute_all_steps(guardrails)
self._finalize()
# --- timestamps ---
def _stamp(self) -> str:
return datetime.now(self.TZ).strftime("%Y-%m-%dT%H:%M:%S%z")
# --- JSON I/O ---
@staticmethod
def _read_json(p: Path) -> dict:
return json.loads(p.read_text(encoding="utf-8"))
@staticmethod
def _write_json(p: Path, data: dict):
p.write_text(json.dumps(data, indent=2, ensure_ascii=False), encoding="utf-8")
# --- git ---
def _run_git(self, *args) -> subprocess.CompletedProcess:
cmd = ["git"] + list(args)
return subprocess.run(cmd, cwd=self._root, capture_output=True, text=True)
def _checkout_branch(self):
branch = f"feat-{self._phase_name}"
r = self._run_git("rev-parse", "--abbrev-ref", "HEAD")
if r.returncode != 0:
print(f" ERROR: git을 사용할 수 없거나 git repo가 아닙니다.")
print(f" {r.stderr.strip()}")
sys.exit(1)
if r.stdout.strip() == branch:
return
r = self._run_git("rev-parse", "--verify", branch)
r = self._run_git("checkout", branch) if r.returncode == 0 else self._run_git("checkout", "-b", branch)
if r.returncode != 0:
print(f" ERROR: 브랜치 '{branch}' checkout 실패.")
print(f" {r.stderr.strip()}")
print(f" Hint: 변경사항을 stash하거나 commit한 후 다시 시도하세요.")
sys.exit(1)
print(f" Branch: {branch}")
def _commit_step(self, step_num: int, step_name: str):
output_rel = f"phases/{self._phase_dir_name}/step{step_num}-output.json"
index_rel = f"phases/{self._phase_dir_name}/index.json"
self._run_git("add", "-A")
self._run_git("reset", "HEAD", "--", output_rel)
self._run_git("reset", "HEAD", "--", index_rel)
if self._run_git("diff", "--cached", "--quiet").returncode != 0:
msg = self.FEAT_MSG.format(phase=self._phase_name, num=step_num, name=step_name)
r = self._run_git("commit", "-m", msg)
if r.returncode == 0:
print(f" Commit: {msg}")
else:
print(f" WARN: 코드 커밋 실패: {r.stderr.strip()}")
self._run_git("add", "-A")
if self._run_git("diff", "--cached", "--quiet").returncode != 0:
msg = self.CHORE_MSG.format(phase=self._phase_name, num=step_num)
r = self._run_git("commit", "-m", msg)
if r.returncode != 0:
print(f" WARN: housekeeping 커밋 실패: {r.stderr.strip()}")
# --- top-level index ---
def _update_top_index(self, status: str):
if not self._top_index_file.exists():
return
top = self._read_json(self._top_index_file)
ts = self._stamp()
for phase in top.get("phases", []):
if phase.get("dir") == self._phase_dir_name:
phase["status"] = status
ts_key = {"completed": "completed_at", "error": "failed_at", "blocked": "blocked_at"}.get(status)
if ts_key:
phase[ts_key] = ts
break
self._write_json(self._top_index_file, top)
# --- guardrails & context ---
def _load_guardrails(self) -> str:
sections = []
agents_md = ROOT / "AGENTS.md"
if agents_md.exists():
sections.append(f"## 프로젝트 규칙 (AGENTS.md)\n\n{agents_md.read_text(encoding='utf-8')}")
docs_dir = ROOT / "docs"
if docs_dir.is_dir():
for doc in sorted(docs_dir.glob("*.md")):
sections.append(f"## {doc.stem}\n\n{doc.read_text(encoding='utf-8')}")
return "\n\n---\n\n".join(sections) if sections else ""
@staticmethod
def _build_step_context(index: dict) -> str:
lines = [
f"- Step {s['step']} ({s['name']}): {s['summary']}"
for s in index["steps"]
if s["status"] == "completed" and s.get("summary")
]
if not lines:
return ""
return "## 이전 Step 산출물\n\n" + "\n".join(lines) + "\n\n"
def _build_preamble(self, guardrails: str, step_context: str,
prev_error: Optional[str] = None) -> str:
commit_example = self.FEAT_MSG.format(
phase=self._phase_name, num="N", name="<step-name>"
)
retry_section = ""
if prev_error:
retry_section = (
f"\n## ⚠ 이전 시도 실패 — 아래 에러를 반드시 참고하여 수정하라\n\n"
f"{prev_error}\n\n---\n\n"
)
return (
f"당신은 {self._project} 프로젝트의 개발자입니다. 아래 step을 수행하세요.\n\n"
f"{guardrails}\n\n---\n\n"
f"{step_context}{retry_section}"
f"## 작업 규칙\n\n"
f"1. 이전 step에서 작성된 코드를 확인하고 일관성을 유지하라.\n"
f"2. 이 step에 명시된 작업만 수행하라. 추가 기능이나 파일을 만들지 마라.\n"
f"3. 기존 테스트를 깨뜨리지 마라.\n"
f"4. AC(Acceptance Criteria) 검증을 직접 실행하라.\n"
f"5. /phases/{self._phase_dir_name}/index.json의 해당 step status를 업데이트하라:\n"
f" - AC 통과 → \"completed\" + \"summary\" 필드에 이 step의 산출물을 한 줄로 요약\n"
f" - {self.MAX_RETRIES}회 수정 시도 후에도 실패 → \"error\" + \"error_message\" 기록\n"
f" - 사용자 개입이 필요한 경우 (API 키, 인증, 수동 설정 등) → \"blocked\" + \"blocked_reason\" 기록 후 즉시 중단\n"
f"6. 모든 변경사항을 커밋하라:\n"
f" {commit_example}\n\n---\n\n"
)
# --- Codex 호출 ---
def _invoke_codex(self, step: dict, preamble: str) -> dict:
step_num, step_name = step["step"], step["name"]
step_file = self._phase_dir / f"step{step_num}.md"
if not step_file.exists():
print(f" ERROR: {step_file} not found")
sys.exit(1)
prompt = preamble + step_file.read_text(encoding="utf-8")
result = subprocess.run(
["codex", "exec", "--dangerously-bypass-approvals-and-sandbox", "--json", prompt],
cwd=self._root, capture_output=True, text=True, timeout=1800,
)
if result.returncode != 0:
print(f"\n WARN: Codex가 비정상 종료됨 (code {result.returncode})")
if result.stderr:
print(f" stderr: {result.stderr[:500]}")
output = {
"step": step_num, "name": step_name,
"exitCode": result.returncode,
"stdout": result.stdout, "stderr": result.stderr,
}
out_path = self._phase_dir / f"step{step_num}-output.json"
with open(out_path, "w", encoding="utf-8") as f:
json.dump(output, f, indent=2, ensure_ascii=False)
return output
# --- 헤더 & 검증 ---
def _print_header(self):
print(f"\n{'='*60}")
print(f" Harness Step Executor")
print(f" Phase: {self._phase_name} | Steps: {self._total}")
if self._auto_push:
print(f" Auto-push: enabled")
print(f"{'='*60}")
def _check_blockers(self):
index = self._read_json(self._index_file)
for s in reversed(index["steps"]):
if s["status"] == "error":
print(f"\n ✗ Step {s['step']} ({s['name']}) failed.")
print(f" Error: {s.get('error_message', 'unknown')}")
print(f" Fix and reset status to 'pending' to retry.")
sys.exit(1)
if s["status"] == "blocked":
print(f"\n ⏸ Step {s['step']} ({s['name']}) blocked.")
print(f" Reason: {s.get('blocked_reason', 'unknown')}")
print(f" Resolve and reset status to 'pending' to retry.")
sys.exit(2)
if s["status"] != "pending":
break
def _ensure_created_at(self):
index = self._read_json(self._index_file)
if "created_at" not in index:
index["created_at"] = self._stamp()
self._write_json(self._index_file, index)
# --- 실행 루프 ---
def _execute_single_step(self, step: dict, guardrails: str) -> bool:
"""단일 step 실행 (재시도 포함). 완료되면 True, 실패/차단이면 False."""
step_num, step_name = step["step"], step["name"]
done = sum(1 for s in self._read_json(self._index_file)["steps"] if s["status"] == "completed")
prev_error = None
for attempt in range(1, self.MAX_RETRIES + 1):
index = self._read_json(self._index_file)
step_context = self._build_step_context(index)
preamble = self._build_preamble(guardrails, step_context, prev_error)
tag = f"Step {step_num}/{self._total - 1} ({done} done): {step_name}"
if attempt > 1:
tag += f" [retry {attempt}/{self.MAX_RETRIES}]"
with progress_indicator(tag) as pi:
self._invoke_codex(step, preamble)
elapsed = int(pi.elapsed)
index = self._read_json(self._index_file)
status = next((s.get("status", "pending") for s in index["steps"] if s["step"] == step_num), "pending")
ts = self._stamp()
if status == "completed":
for s in index["steps"]:
if s["step"] == step_num:
s["completed_at"] = ts
self._write_json(self._index_file, index)
self._commit_step(step_num, step_name)
print(f" ✓ Step {step_num}: {step_name} [{elapsed}s]")
return True
if status == "blocked":
for s in index["steps"]:
if s["step"] == step_num:
s["blocked_at"] = ts
self._write_json(self._index_file, index)
reason = next((s.get("blocked_reason", "") for s in index["steps"] if s["step"] == step_num), "")
print(f" ⏸ Step {step_num}: {step_name} blocked [{elapsed}s]")
print(f" Reason: {reason}")
self._update_top_index("blocked")
sys.exit(2)
err_msg = next(
(s.get("error_message", "Step did not update status") for s in index["steps"] if s["step"] == step_num),
"Step did not update status",
)
if attempt < self.MAX_RETRIES:
for s in index["steps"]:
if s["step"] == step_num:
s["status"] = "pending"
s.pop("error_message", None)
self._write_json(self._index_file, index)
prev_error = err_msg
print(f" ↻ Step {step_num}: retry {attempt}/{self.MAX_RETRIES} — {err_msg}")
else:
for s in index["steps"]:
if s["step"] == step_num:
s["status"] = "error"
s["error_message"] = f"[{self.MAX_RETRIES}회 시도 후 실패] {err_msg}"
s["failed_at"] = ts
self._write_json(self._index_file, index)
self._commit_step(step_num, step_name)
print(f" ✗ Step {step_num}: {step_name} failed after {self.MAX_RETRIES} attempts [{elapsed}s]")
print(f" Error: {err_msg}")
self._update_top_index("error")
sys.exit(1)
return False # unreachable
def _execute_all_steps(self, guardrails: str):
while True:
index = self._read_json(self._index_file)
pending = next((s for s in index["steps"] if s["status"] == "pending"), None)
if pending is None:
print("\n All steps completed!")
return
step_num = pending["step"]
for s in index["steps"]:
if s["step"] == step_num and "started_at" not in s:
s["started_at"] = self._stamp()
self._write_json(self._index_file, index)
break
self._execute_single_step(pending, guardrails)
def _finalize(self):
index = self._read_json(self._index_file)
index["completed_at"] = self._stamp()
self._write_json(self._index_file, index)
self._update_top_index("completed")
self._run_git("add", "-A")
if self._run_git("diff", "--cached", "--quiet").returncode != 0:
msg = f"chore({self._phase_name}): mark phase completed"
r = self._run_git("commit", "-m", msg)
if r.returncode == 0:
print(f" ✓ {msg}")
if self._auto_push:
branch = f"feat-{self._phase_name}"
r = self._run_git("push", "-u", "origin", branch)
if r.returncode != 0:
print(f"\n ERROR: git push 실패: {r.stderr.strip()}")
sys.exit(1)
print(f" ✓ Pushed to origin/{branch}")
print(f"\n{'='*60}")
print(f" Phase '{self._phase_name}' completed!")
print(f"{'='*60}")
def main():
parser = argparse.ArgumentParser(description="Harness Step Executor")
parser.add_argument("phase_dir", help="Phase directory name (e.g. 0-mvp)")
parser.add_argument("--push", action="store_true", help="Push branch after completion")
args = parser.parse_args()
StepExecutor(args.phase_dir, auto_push=args.push).run()
if __name__ == "__main__":
main()
FESurrogateModelTutorial/src/femsurrogate/__init__.py
+3
View File
@@ -0,0 +1,3 @@
"""FEM surrogate tutorial package."""
__version__ = "0.1.0"
FESurrogateModelTutorial/src/femsurrogate/data/__init__.py
+1
View File
@@ -0,0 +1 @@
"""Dataset generation helpers for FEM surrogate tutorials."""
FESurrogateModelTutorial/src/femsurrogate/data/bounds.py
+16
View File
@@ -0,0 +1,16 @@
from dataclasses import dataclass
@dataclass(frozen=True)
class ParameterBound:
lower: float
upper: float
DEFAULT_PARAMETER_BOUNDS = {
"L_m": ParameterBound(lower=1.0, upper=3.0),
"b_m": ParameterBound(lower=0.02, upper=0.08),
"h_m": ParameterBound(lower=0.04, upper=0.16),
"E_pa": ParameterBound(lower=100e9, upper=220e9),
"P_n": ParameterBound(lower=100.0, upper=2000.0),
}
FESurrogateModelTutorial/src/femsurrogate/data/dataset.py
+106
View File
@@ -0,0 +1,106 @@
from collections.abc import Mapping
from dataclasses import asdict
import pandas as pd
from femsurrogate.data.schema import (
DENSITY_KG_M3,
DERIVED_COLUMNS,
PARAMETER_COLUMNS,
TARGET_COLUMNS,
AnalysisResult,
BeamParameters,
)
from femsurrogate.fea.model import Beam, BeamModel, NodalLoad, Node
from femsurrogate.fea.solver import solve_linear_static
N_CANTILEVER_NODES = 6
def _section_area(params: BeamParameters) -> float:
return params.b_m * params.h_m
def _section_izz(params: BeamParameters) -> float:
return params.b_m * params.h_m**3 / 12.0
def _coerce_parameters(params: BeamParameters | Mapping[str, float]) -> BeamParameters:
if isinstance(params, BeamParameters):
return params
return BeamParameters(**{column: float(params[column]) for column in PARAMETER_COLUMNS})
def _make_cantilever_model(params: BeamParameters) -> BeamModel:
area = _section_area(params)
izz = _section_izz(params)
iyy = params.h_m * params.b_m**3 / 12.0
nodes = {
node_id: Node(
id=node_id,
x=params.L_m * (node_id - 1) / (N_CANTILEVER_NODES - 1),
y=0.0,
)
for node_id in range(1, N_CANTILEVER_NODES + 1)
}
beams = tuple(
Beam(id=beam_id, node_i=beam_id, node_j=beam_id + 1)
for beam_id in range(1, N_CANTILEVER_NODES)
)
return BeamModel(
metadata={
"Area": area,
"J": iyy + izz,
"Iyy": iyy,
"Izz": izz,
"ElasticModulus": params.E_pa,
"Poisson'sRatio": 0.3,
},
nodes=nodes,
beams=beams,
fixed_nodes=(1,),
nodal_loads={
N_CANTILEVER_NODES: NodalLoad(
node_id=N_CANTILEVER_NODES,
fx=0.0,
fy=-params.P_n,
mz=0.0,
)
},
)
def run_beam2d_case(params: BeamParameters | Mapping[str, float]) -> AnalysisResult:
beam_params = _coerce_parameters(params)
area = _section_area(beam_params)
izz = _section_izz(beam_params)
model = _make_cantilever_model(beam_params)
solution = solve_linear_static(model)
tip_uy = solution[N_CANTILEVER_NODES].uy
max_moment = abs(beam_params.P_n) * beam_params.L_m
max_abs_bending_stress = max_moment * (beam_params.h_m / 2.0) / izz
mass = DENSITY_KG_M3 * area * beam_params.L_m
compliance = -beam_params.P_n * tip_uy
return AnalysisResult(
tip_uy_m=tip_uy,
max_abs_bending_stress_pa=max_abs_bending_stress,
mass_kg=mass,
compliance_j=compliance,
)
def build_dataset(samples: pd.DataFrame) -> pd.DataFrame:
rows: list[dict[str, float]] = []
for sample in samples.to_dict(orient="records"):
params = _coerce_parameters(sample)
result = run_beam2d_case(params)
row = dict(sample)
row["A_m2"] = _section_area(params)
row["I_m4"] = _section_izz(params)
row.update(asdict(result))
rows.append(row)
return pd.DataFrame(rows, columns=[*samples.columns, *DERIVED_COLUMNS, *TARGET_COLUMNS])
FESurrogateModelTutorial/src/femsurrogate/data/sampling.py
+18
View File
@@ -0,0 +1,18 @@
import pandas as pd
from scipy.stats import qmc
from femsurrogate.data.bounds import ParameterBound
def generate_lhs_samples(bounds: dict[str, ParameterBound], n: int, seed: int) -> pd.DataFrame:
if n <= 0:
raise ValueError("n must be positive")
columns = list(bounds)
sampler = qmc.LatinHypercube(d=len(columns), seed=seed)
unit_samples = sampler.random(n)
lower = [bounds[column].lower for column in columns]
upper = [bounds[column].upper for column in columns]
samples = qmc.scale(unit_samples, lower, upper)
return pd.DataFrame(samples, columns=columns)
FESurrogateModelTutorial/src/femsurrogate/data/schema.py
+24
View File
@@ -0,0 +1,24 @@
from dataclasses import dataclass
DEFAULT_RANDOM_SEED = 20260521
DENSITY_KG_M3 = 7850.0
PARAMETER_COLUMNS = ("L_m", "b_m", "h_m", "E_pa", "P_n")
DERIVED_COLUMNS = ("A_m2", "I_m4")
TARGET_COLUMNS = ("tip_uy_m", "max_abs_bending_stress_pa", "mass_kg", "compliance_j")
@dataclass(frozen=True)
class BeamParameters:
L_m: float
b_m: float
h_m: float
E_pa: float
P_n: float
@dataclass(frozen=True)
class AnalysisResult:
tip_uy_m: float
max_abs_bending_stress_pa: float
mass_kg: float
compliance_j: float
FESurrogateModelTutorial/src/femsurrogate/fea/__init__.py
+1
View File
@@ -0,0 +1 @@
"""Finite element helpers for 2D beam/frame examples."""
FESurrogateModelTutorial/src/femsurrogate/fea/assembly.py
+60
View File
@@ -0,0 +1,60 @@
import math
import numpy as np
from scipy.sparse import csr_matrix, lil_matrix
from femsurrogate.fea.element import local_frame_stiffness, transformation_matrix
from femsurrogate.fea.model import BeamModel
def node_ids(model: BeamModel) -> tuple[int, ...]:
return tuple(sorted(model.nodes))
def dof_index(model: BeamModel, node_id: int, local_dof: int) -> int:
node_position = node_ids(model).index(node_id)
return node_position * 3 + local_dof
def node_dofs(model: BeamModel, node_id: int) -> tuple[int, int, int]:
base = dof_index(model, node_id, 0)
return (base, base + 1, base + 2)
def constrained_dofs(model: BeamModel) -> tuple[int, ...]:
return tuple(dof for node_id in sorted(model.fixed_nodes) for dof in node_dofs(model, node_id))
def assemble_global_stiffness(model: BeamModel) -> csr_matrix:
size = 3 * len(model.nodes)
stiffness = lil_matrix((size, size), dtype=float)
E = model.metadata["ElasticModulus"]
A = model.metadata["Area"]
Izz = model.metadata["Izz"]
for beam in model.beams:
node_i = model.nodes[beam.node_i]
node_j = model.nodes[beam.node_j]
length = math.hypot(node_j.x - node_i.x, node_j.y - node_i.y)
local_stiffness = local_frame_stiffness(E=E, A=A, Izz=Izz, L=length)
transform = transformation_matrix(node_i.x, node_i.y, node_j.x, node_j.y)
element_stiffness = transform.T @ local_stiffness @ transform
element_dofs = (*node_dofs(model, beam.node_i), *node_dofs(model, beam.node_j))
for row_local, row_global in enumerate(element_dofs):
for col_local, col_global in enumerate(element_dofs):
stiffness[row_global, col_global] += element_stiffness[row_local, col_local]
return stiffness.tocsr()
def assemble_load_vector(model: BeamModel) -> np.ndarray:
loads = np.zeros(3 * len(model.nodes), dtype=float)
for node_id, load in model.nodal_loads.items():
ux_dof, uy_dof, rz_dof = node_dofs(model, node_id)
loads[ux_dof] += load.fx
loads[uy_dof] += load.fy
loads[rz_dof] += load.mz
return loads
FESurrogateModelTutorial/src/femsurrogate/fea/benchmark.py
+2
View File
@@ -0,0 +1,2 @@
def cantilever_tip_displacement(*, force_y: float, length: float, E: float, Izz: float) -> float:
return force_y * length**3 / (3.0 * E * Izz)
FESurrogateModelTutorial/src/femsurrogate/fea/element.py
+46
View File
@@ -0,0 +1,46 @@
import math
import numpy as np
def local_frame_stiffness(*, E: float, A: float, Izz: float, L: float) -> np.ndarray:
"""Return local frame stiffness with Rz positive clockwise."""
axial = E * A / L
b12 = 12.0 * E * Izz / L**3
b6 = 6.0 * E * Izz / L**2
b4 = 4.0 * E * Izz / L
b2 = 2.0 * E * Izz / L
return np.array(
[
[axial, 0.0, 0.0, -axial, 0.0, 0.0],
[0.0, b12, -b6, 0.0, -b12, -b6],
[0.0, -b6, b4, 0.0, b6, b2],
[-axial, 0.0, 0.0, axial, 0.0, 0.0],
[0.0, -b12, b6, 0.0, b12, b6],
[0.0, -b6, b2, 0.0, b6, b4],
],
dtype=float,
)
def transformation_matrix(x1: float, y1: float, x2: float, y2: float) -> np.ndarray:
dx = x2 - x1
dy = y2 - y1
length = math.hypot(dx, dy)
c = dx / length
s = dy / length
block = np.array(
[
[c, s, 0.0],
[-s, c, 0.0],
[0.0, 0.0, 1.0],
],
dtype=float,
)
matrix = np.zeros((6, 6), dtype=float)
matrix[:3, :3] = block
matrix[3:, 3:] = block
return matrix
FESurrogateModelTutorial/src/femsurrogate/fea/io.py
+70
View File
@@ -0,0 +1,70 @@
import re
from pathlib import Path
from femsurrogate.fea.model import Beam, BeamModel, Displacement, NodalLoad, Node
def _tokens(line: str) -> list[str]:
return [token for token in re.split(r"[,\s]+", line.strip()) if token]
def read_beam_example(path: str | Path) -> BeamModel:
metadata: dict[str, float] = {}
nodes: dict[int, Node] = {}
beams: list[Beam] = []
fixed_nodes: list[int] = []
nodal_loads: dict[int, NodalLoad] = {}
for raw_line in Path(path).read_text(encoding="utf-8").splitlines():
line = raw_line.strip()
if not line or line.startswith("#"):
continue
parts = _tokens(line)
keyword = parts[0]
if keyword == "Node":
node_id = int(parts[1])
nodes[node_id] = Node(id=node_id, x=float(parts[2]), y=float(parts[3]))
elif keyword == "Beam":
beams.append(Beam(id=int(parts[1]), node_i=int(parts[2]), node_j=int(parts[3])))
elif keyword == "Fix":
fixed_nodes.append(int(parts[1]))
elif keyword == "NodeLoad":
node_id = int(parts[1])
nodal_loads[node_id] = NodalLoad(
node_id=node_id,
fx=float(parts[2]),
fy=float(parts[3]),
mz=float(parts[4]),
)
else:
metadata[keyword] = float(parts[1])
return BeamModel(
metadata=metadata,
nodes=nodes,
beams=tuple(beams),
fixed_nodes=tuple(fixed_nodes),
nodal_loads=nodal_loads,
)
def read_expected_displacements(path: str | Path) -> dict[int, Displacement]:
displacements: dict[int, Displacement] = {}
for raw_line in Path(path).read_text(encoding="utf-8").splitlines():
line = raw_line.strip()
if not line or line.startswith("#"):
continue
parts = _tokens(line)
node_id = int(parts[0])
displacements[node_id] = Displacement(
node_id=node_id,
ux=float(parts[1]),
uy=float(parts[2]),
rz=float(parts[3]),
)
return displacements
FESurrogateModelTutorial/src/femsurrogate/fea/model.py
+40
View File
@@ -0,0 +1,40 @@
from dataclasses import dataclass
@dataclass(frozen=True)
class Node:
id: int
x: float
y: float
@dataclass(frozen=True)
class Beam:
id: int
node_i: int
node_j: int
@dataclass(frozen=True)
class NodalLoad:
node_id: int
fx: float
fy: float
mz: float
@dataclass(frozen=True)
class Displacement:
node_id: int
ux: float
uy: float
rz: float
@dataclass(frozen=True)
class BeamModel:
metadata: dict[str, float]
nodes: dict[int, Node]
beams: tuple[Beam, ...]
fixed_nodes: tuple[int, ...]
nodal_loads: dict[int, NodalLoad]
FESurrogateModelTutorial/src/femsurrogate/fea/solver.py
+33
View File
@@ -0,0 +1,33 @@
import numpy as np
from scipy.sparse.linalg import spsolve
from femsurrogate.fea.assembly import (
assemble_global_stiffness,
assemble_load_vector,
constrained_dofs,
node_ids,
)
from femsurrogate.fea.model import BeamModel, Displacement
def solve_linear_static(model: BeamModel) -> dict[int, Displacement]:
stiffness = assemble_global_stiffness(model)
loads = assemble_load_vector(model)
fixed = np.array(constrained_dofs(model), dtype=int)
all_dofs = np.arange(loads.size)
free = np.setdiff1d(all_dofs, fixed, assume_unique=True)
displacements = np.zeros_like(loads)
displacements[free] = spsolve(stiffness[free][:, free], loads[free])
result: dict[int, Displacement] = {}
for position, node_id in enumerate(node_ids(model)):
base = position * 3
result[node_id] = Displacement(
node_id=node_id,
ux=float(displacements[base]),
uy=float(displacements[base + 1]),
rz=float(displacements[base + 2]),
)
return result
FESurrogateModelTutorial/src/femsurrogate/plotting/__init__.py
+1
View File
@@ -0,0 +1 @@
"""Plotting helpers for diagnostics and model comparison."""

Some files were not shown because too many files have changed in this diff Show More