refactor: Major reorganization of optimization_engine module structure

BREAKING CHANGE: Module paths have been reorganized for better maintainability.
Backwards compatibility aliases with deprecation warnings are provided.

New Structure:
- core/           - Optimization runners (runner, intelligent_optimizer, etc.)
- processors/     - Data processing
  - surrogates/   - Neural network surrogates
- nx/             - NX/Nastran integration (solver, updater, session_manager)
- study/          - Study management (creator, wizard, state, reset)
- reporting/      - Reports and analysis (visualizer, report_generator)
- config/         - Configuration management (manager, builder)
- utils/          - Utilities (logger, auto_doc, etc.)
- future/         - Research/experimental code

Migration:
- ~200 import changes across 125 files
- All __init__.py files use lazy loading to avoid circular imports
- Backwards compatibility layer supports old import paths with warnings
- All existing functionality preserved

To migrate existing code:
  OLD: from optimization_engine.nx_solver import NXSolver
  NEW: from optimization_engine.nx.solver import NXSolver

  OLD: from optimization_engine.runner import OptimizationRunner
  NEW: from optimization_engine.core.runner import OptimizationRunner

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
2025-12-29 12:30:59 -05:00
parent 82f36689b7
commit eabcc4c3ca
120 changed files with 1127 additions and 637 deletions

View File

@@ -0,0 +1,44 @@
"""
Reporting & Analysis
====================
Report generation and results analysis.
Modules:
- report_generator: HTML/PDF report generation
- markdown_report: Markdown report format
- results_analyzer: Comprehensive results analysis
- visualizer: Plotting and visualization
- landscape_analyzer: Design space analysis
"""
# Lazy imports to avoid import errors
def __getattr__(name):
if name == 'generate_optimization_report':
from .report_generator import generate_optimization_report
return generate_optimization_report
elif name == 'generate_markdown_report':
from .markdown_report import generate_markdown_report
return generate_markdown_report
elif name == 'MarkdownReportGenerator':
from .markdown_report import MarkdownReportGenerator
return MarkdownReportGenerator
elif name == 'ResultsAnalyzer':
from .results_analyzer import ResultsAnalyzer
return ResultsAnalyzer
elif name == 'Visualizer':
from .visualizer import Visualizer
return Visualizer
elif name == 'LandscapeAnalyzer':
from .landscape_analyzer import LandscapeAnalyzer
return LandscapeAnalyzer
raise AttributeError(f"module 'optimization_engine.reporting' has no attribute '{name}'")
__all__ = [
'generate_optimization_report',
'generate_markdown_report',
'MarkdownReportGenerator',
'ResultsAnalyzer',
'Visualizer',
'LandscapeAnalyzer',
]

View File

@@ -0,0 +1,386 @@
"""
Landscape Analyzer - Automatic optimization problem characterization.
This module analyzes the characteristics of an optimization landscape to inform
intelligent strategy selection. It computes metrics like smoothness, multimodality,
parameter correlation, and noise level.
Part of Protocol 10: Intelligent Multi-Strategy Optimization (IMSO)
"""
import numpy as np
from typing import Dict, List, Optional
from scipy.stats import spearmanr, variation
from scipy.spatial.distance import pdist, squareform
from sklearn.cluster import DBSCAN
import optuna
class LandscapeAnalyzer:
"""Analyzes optimization landscape characteristics from trial history."""
def __init__(self, min_trials_for_analysis: int = 10, verbose: bool = True):
"""
Args:
min_trials_for_analysis: Minimum trials needed for reliable analysis
verbose: Whether to print diagnostic messages
"""
self.min_trials = min_trials_for_analysis
self.verbose = verbose
def analyze(self, study: optuna.Study) -> Dict:
"""
Analyze optimization landscape characteristics.
STUDY-AWARE: Uses study.trials directly for analysis.
Args:
study: Optuna study with completed trials
Returns:
Dictionary with landscape characteristics:
- smoothness: 0-1, how smooth the objective landscape is
- multimodal: boolean, multiple local optima detected
- n_modes: estimated number of local optima
- parameter_correlation: dict of correlation scores
- noise_level: estimated noise in evaluations
- dimensionality: number of design variables
- landscape_type: classification (smooth/rugged/multimodal)
"""
# Get completed trials
completed_trials = [t for t in study.trials if t.state == optuna.trial.TrialState.COMPLETE]
if len(completed_trials) < self.min_trials:
return {
'ready': False,
'total_trials': len(completed_trials),
'message': f'Need {self.min_trials - len(completed_trials)} more trials for landscape analysis'
}
# Check if this is a multi-objective study
# Multi-objective studies have trial.values (plural), not trial.value
is_multi_objective = len(study.directions) > 1
if is_multi_objective:
return {
'ready': False,
'total_trials': len(completed_trials),
'message': 'Landscape analysis not supported for multi-objective optimization'
}
# Extract data
X = [] # Parameter values
y = [] # Objective values
param_names = []
for trial in completed_trials:
X.append(list(trial.params.values()))
y.append(trial.value)
if not param_names:
param_names = list(trial.params.keys())
X = np.array(X)
y = np.array(y)
# Compute characteristics
smoothness = self._compute_smoothness(X, y)
multimodal, n_modes = self._detect_multimodality(X, y)
correlation_scores = self._compute_parameter_correlation(X, y, param_names)
noise_level = self._estimate_noise(X, y)
landscape_type = self._classify_landscape(smoothness, multimodal, noise_level, n_modes)
# Compute parameter ranges for coverage metrics
param_ranges = self._compute_parameter_ranges(completed_trials)
return {
'ready': True,
'total_trials': len(completed_trials),
'dimensionality': X.shape[1],
'parameter_names': param_names,
'smoothness': smoothness,
'multimodal': multimodal,
'n_modes': n_modes,
'parameter_correlation': correlation_scores,
'noise_level': noise_level,
'landscape_type': landscape_type,
'parameter_ranges': param_ranges,
'objective_statistics': {
'mean': float(np.mean(y)),
'std': float(np.std(y)),
'min': float(np.min(y)),
'max': float(np.max(y)),
'range': float(np.max(y) - np.min(y))
}
}
def _compute_smoothness(self, X: np.ndarray, y: np.ndarray) -> float:
"""
Compute landscape smoothness score.
High smoothness = nearby points have similar objective values
Low smoothness = nearby points have very different values (rugged)
Method: Compare objective differences vs parameter distances
"""
if len(y) < 3:
return 0.5 # Unknown
# Normalize parameters to [0, 1] for fair distance computation
X_norm = (X - X.min(axis=0)) / (X.max(axis=0) - X.min(axis=0) + 1e-10)
# Compute pairwise distances in parameter space
param_distances = pdist(X_norm, metric='euclidean')
# Compute pairwise differences in objective space
objective_diffs = pdist(y.reshape(-1, 1), metric='euclidean')
# Smoothness = correlation between distance and objective difference
# Smooth landscape: nearby points → similar objectives (high correlation)
# Rugged landscape: nearby points → very different objectives (low correlation)
if len(param_distances) > 0 and len(objective_diffs) > 0:
# Filter out zero distances to avoid division issues
mask = param_distances > 1e-6
if np.sum(mask) > 5:
param_distances = param_distances[mask]
objective_diffs = objective_diffs[mask]
# Compute correlation
correlation, _ = spearmanr(param_distances, objective_diffs)
# Convert to smoothness score: high correlation = smooth
# Handle NaN from constant arrays
if np.isnan(correlation):
smoothness = 0.5
else:
smoothness = max(0.0, min(1.0, (correlation + 1.0) / 2.0))
else:
smoothness = 0.5
else:
smoothness = 0.5
return smoothness
def _detect_multimodality(self, X: np.ndarray, y: np.ndarray) -> tuple:
"""
Detect multiple local optima using clustering.
Returns:
(is_multimodal, n_modes)
"""
if len(y) < 10:
return False, 1
# Find good trials (bottom 30%)
threshold = np.percentile(y, 30)
good_trials_mask = y <= threshold
if np.sum(good_trials_mask) < 3:
return False, 1
X_good = X[good_trials_mask]
# Normalize for clustering
X_norm = (X_good - X.min(axis=0)) / (X.max(axis=0) - X.min(axis=0) + 1e-10)
# Use DBSCAN to find clusters of good solutions
# If they're spread across multiple regions → multimodal
try:
clustering = DBSCAN(eps=0.2, min_samples=2).fit(X_norm)
n_clusters = len(set(clustering.labels_)) - (1 if -1 in clustering.labels_ else 0)
is_multimodal = n_clusters > 1
n_modes = max(1, n_clusters)
except:
is_multimodal = False
n_modes = 1
return is_multimodal, n_modes
def _compute_parameter_correlation(self, X: np.ndarray, y: np.ndarray, param_names: List[str]) -> Dict:
"""
Compute correlation between each parameter and objective.
Returns dict of {param_name: correlation_score}
High absolute correlation → parameter strongly affects objective
"""
correlations = {}
for i, param_name in enumerate(param_names):
param_values = X[:, i]
# Spearman correlation (handles nonlinearity)
corr, p_value = spearmanr(param_values, y)
if np.isnan(corr):
corr = 0.0
correlations[param_name] = {
'correlation': float(corr),
'abs_correlation': float(abs(corr)),
'p_value': float(p_value) if not np.isnan(p_value) else 1.0
}
# Compute overall correlation strength
avg_abs_corr = np.mean([v['abs_correlation'] for v in correlations.values()])
correlations['overall_strength'] = float(avg_abs_corr)
return correlations
def _estimate_noise(self, X: np.ndarray, y: np.ndarray) -> float:
"""
Estimate noise level in objective evaluations.
For deterministic FEA simulations, this should be very low.
High noise would suggest numerical issues or simulation instability.
Method: Look at local variations - similar inputs should give similar outputs.
Wide exploration range (high CV) is NOT noise.
"""
if len(y) < 10:
return 0.0
# Calculate pairwise distances in parameter space
from scipy.spatial.distance import pdist, squareform
# Normalize X to [0,1] for distance calculation
X_norm = (X - X.min(axis=0)) / (X.max(axis=0) - X.min(axis=0) + 1e-10)
# Compute pairwise distances
param_distances = squareform(pdist(X_norm, 'euclidean'))
objective_diffs = np.abs(y[:, np.newaxis] - y[np.newaxis, :])
# Find pairs that are close in parameter space (distance < 0.1)
close_pairs_mask = (param_distances > 1e-6) & (param_distances < 0.1)
if np.sum(close_pairs_mask) < 5:
# Not enough close pairs to assess noise
return 0.0
# For close pairs, measure objective variation
# True noise: close inputs give very different outputs
# Smooth function: close inputs give similar outputs
close_objective_diffs = objective_diffs[close_pairs_mask]
close_param_dists = param_distances[close_pairs_mask]
# Normalize by expected difference based on smoothness
# Noise = unexpected variation for nearby points
expected_diff = np.median(close_objective_diffs / (close_param_dists + 1e-10))
actual_std = np.std(close_objective_diffs / (close_param_dists + 1e-10))
# Coefficient of variation of local gradients
if expected_diff > 1e-6:
local_cv = actual_std / expected_diff
noise_score = min(1.0, local_cv / 2.0)
else:
noise_score = 0.0
return float(noise_score)
def _classify_landscape(self, smoothness: float, multimodal: bool, noise: float, n_modes: int = 1) -> str:
"""
Classify landscape type for strategy selection.
Args:
smoothness: Smoothness score (0-1)
multimodal: Whether multiple modes detected
noise: Noise level (0-1)
n_modes: Number of modes detected
Returns one of:
- 'smooth_unimodal': Single smooth bowl (best for CMA-ES, GP-BO)
- 'smooth_multimodal': Multiple smooth regions (good for GP-BO, TPE)
- 'rugged_unimodal': Single rugged region (TPE, hybrid)
- 'rugged_multimodal': Multiple rugged regions (TPE, evolutionary)
- 'noisy': High noise level (robust methods)
"""
# IMPROVEMENT: Detect false multimodality from smooth continuous manifolds
# If only 2 modes detected with high smoothness and low noise,
# it's likely a continuous smooth surface, not true multimodality
if multimodal and n_modes == 2 and smoothness > 0.6 and noise < 0.2:
if self.verbose:
print(f"[LANDSCAPE] Reclassifying: 2 modes with smoothness={smoothness:.2f}, noise={noise:.2f}")
print(f"[LANDSCAPE] This appears to be a smooth continuous manifold, not true multimodality")
multimodal = False # Override: treat as unimodal
if noise > 0.5:
return 'noisy'
if smoothness > 0.6:
if multimodal:
return 'smooth_multimodal'
else:
return 'smooth_unimodal'
else:
if multimodal:
return 'rugged_multimodal'
else:
return 'rugged_unimodal'
def _compute_parameter_ranges(self, trials: List) -> Dict:
"""Compute explored parameter ranges."""
if not trials:
return {}
param_names = list(trials[0].params.keys())
ranges = {}
for param in param_names:
values = [t.params[param] for t in trials]
distribution = trials[0].distributions[param]
ranges[param] = {
'explored_min': float(np.min(values)),
'explored_max': float(np.max(values)),
'explored_range': float(np.max(values) - np.min(values)),
'bounds_min': float(distribution.low),
'bounds_max': float(distribution.high),
'bounds_range': float(distribution.high - distribution.low),
'coverage': float((np.max(values) - np.min(values)) / (distribution.high - distribution.low))
}
return ranges
def print_landscape_report(landscape: Dict, verbose: bool = True):
"""Print formatted landscape analysis report."""
if not verbose:
return
# Handle None (multi-objective studies)
if landscape is None:
print(f"\n [LANDSCAPE ANALYSIS] Skipped for multi-objective optimization")
return
if not landscape.get('ready', False):
print(f"\n [LANDSCAPE ANALYSIS] {landscape.get('message', 'Not ready')}")
return
print(f"\n{'='*70}")
print(f" LANDSCAPE ANALYSIS REPORT")
print(f"{'='*70}")
print(f" Total Trials Analyzed: {landscape['total_trials']}")
print(f" Dimensionality: {landscape['dimensionality']} parameters")
print(f"\n LANDSCAPE CHARACTERISTICS:")
print(f" Type: {landscape['landscape_type'].upper()}")
print(f" Smoothness: {landscape['smoothness']:.2f} {'(smooth)' if landscape['smoothness'] > 0.6 else '(rugged)'}")
print(f" Multimodal: {'YES' if landscape['multimodal'] else 'NO'} ({landscape['n_modes']} modes)")
print(f" Noise Level: {landscape['noise_level']:.2f} {'(low)' if landscape['noise_level'] < 0.3 else '(high)'}")
print(f"\n PARAMETER CORRELATIONS:")
for param, info in landscape['parameter_correlation'].items():
if param != 'overall_strength':
corr = info['correlation']
strength = 'strong' if abs(corr) > 0.5 else 'moderate' if abs(corr) > 0.3 else 'weak'
direction = 'positive' if corr > 0 else 'negative'
print(f" {param}: {corr:+.3f} ({strength} {direction})")
print(f"\n OBJECTIVE STATISTICS:")
stats = landscape['objective_statistics']
print(f" Best: {stats['min']:.6f}")
print(f" Mean: {stats['mean']:.6f}")
print(f" Std: {stats['std']:.6f}")
print(f" Range: {stats['range']:.6f}")
print(f"{'='*70}\n")

View File

@@ -0,0 +1,569 @@
"""
Generate comprehensive markdown optimization reports with graphs.
Uses Optuna's built-in visualization library for professional-quality plots.
"""
import json
import sys
from pathlib import Path
from typing import Dict, Any, List, Optional
import numpy as np
import matplotlib
matplotlib.use('Agg') # Non-interactive backend
import matplotlib.pyplot as plt
import optuna
from optuna.visualization import (
plot_optimization_history,
plot_parallel_coordinate,
plot_param_importances,
plot_slice,
plot_contour
)
def create_confidence_progression_plot(confidence_history: List[Dict], phase_transitions: List[Dict], output_dir: Path) -> Optional[str]:
"""Create confidence progression plot showing confidence metrics over trials."""
if not confidence_history:
return None
trial_numbers = [c['trial_number'] for c in confidence_history]
overall = [c['confidence_metrics']['overall_confidence'] for c in confidence_history]
convergence = [c['confidence_metrics']['convergence_score'] for c in confidence_history]
coverage = [c['confidence_metrics']['exploration_coverage'] for c in confidence_history]
stability = [c['confidence_metrics']['prediction_stability'] for c in confidence_history]
plt.figure(figsize=(12, 7))
plt.plot(trial_numbers, overall, 'b-', linewidth=2.5, label='Overall Confidence')
plt.plot(trial_numbers, convergence, 'g--', alpha=0.7, label='Convergence Score')
plt.plot(trial_numbers, coverage, 'orange', linestyle='--', alpha=0.7, label='Exploration Coverage')
plt.plot(trial_numbers, stability, 'purple', linestyle='--', alpha=0.7, label='Prediction Stability')
# Mark phase transitions
for transition in phase_transitions:
trial_num = transition['trial_number']
plt.axvline(x=trial_num, color='red', linestyle='-', linewidth=2, alpha=0.8)
plt.text(trial_num, 0.95, f' Exploitation Phase', rotation=90,
verticalalignment='top', fontsize=10, color='red', fontweight='bold')
# Mark confidence threshold
plt.axhline(y=0.65, color='gray', linestyle=':', linewidth=1.5, alpha=0.6, label='Confidence Threshold (65%)')
plt.xlabel('Trial Number', fontsize=11)
plt.ylabel('Confidence Score (0-1)', fontsize=11)
plt.title('Surrogate Confidence Progression', fontsize=13, fontweight='bold')
plt.legend(loc='lower right', fontsize=9)
plt.grid(True, alpha=0.3)
plt.ylim(0, 1.05)
plt.tight_layout()
plot_file = output_dir / 'confidence_progression.png'
plt.savefig(plot_file, dpi=150)
plt.close()
return plot_file.name
def create_convergence_plot(history: List[Dict], target: Optional[float], output_dir: Path) -> str:
"""Create convergence plot showing best objective over trials."""
trial_numbers = [t['trial_number'] for t in history]
objectives = [t['objective'] for t in history]
# Calculate cumulative best
cumulative_best = []
current_best = float('inf')
for obj in objectives:
current_best = min(current_best, obj)
cumulative_best.append(current_best)
plt.figure(figsize=(10, 6))
plt.plot(trial_numbers, objectives, 'o-', alpha=0.5, label='Trial objective')
plt.plot(trial_numbers, cumulative_best, 'r-', linewidth=2, label='Best so far')
if target is not None:
plt.axhline(y=0, color='g', linestyle='--', linewidth=2, label=f'Target (error = 0)')
plt.xlabel('Trial Number')
plt.ylabel('Objective Value (Error from Target)')
plt.title('Optimization Convergence')
plt.legend()
plt.grid(True, alpha=0.3)
plt.tight_layout()
plot_file = output_dir / 'convergence_plot.png'
plt.savefig(plot_file, dpi=150)
plt.close()
return plot_file.name
def create_design_space_plot(history: List[Dict], output_dir: Path) -> str:
"""Create 2D design space exploration plot."""
first_trial = history[0]
var_names = list(first_trial['design_variables'].keys())
if len(var_names) != 2:
return None # Only works for 2D problems
var1_name, var2_name = var_names
var1_values = [t['design_variables'][var1_name] for t in history]
var2_values = [t['design_variables'][var2_name] for t in history]
objectives = [t['objective'] for t in history]
plt.figure(figsize=(10, 8))
scatter = plt.scatter(var1_values, var2_values, c=objectives, s=100,
cmap='viridis', alpha=0.6, edgecolors='black')
plt.colorbar(scatter, label='Objective Value')
plt.xlabel(var1_name.replace('_', ' ').title())
plt.ylabel(var2_name.replace('_', ' ').title())
plt.title('Design Space Exploration')
plt.grid(True, alpha=0.3)
plt.tight_layout()
plot_file = output_dir / 'design_space_plot.png'
plt.savefig(plot_file, dpi=150)
plt.close()
return plot_file.name
def create_parameter_sensitivity_plot(history: List[Dict], output_dir: Path) -> str:
"""Create parameter sensitivity plots."""
first_trial = history[0]
var_names = list(first_trial['design_variables'].keys())
fig, axes = plt.subplots(1, len(var_names), figsize=(6*len(var_names), 5))
if len(var_names) == 1:
axes = [axes]
for idx, var_name in enumerate(var_names):
var_values = [t['design_variables'][var_name] for t in history]
objectives = [t['objective'] for t in history]
axes[idx].scatter(var_values, objectives, alpha=0.6, s=50)
axes[idx].set_xlabel(var_name.replace('_', ' ').title())
axes[idx].set_ylabel('Objective Value')
axes[idx].set_title(f'Sensitivity to {var_name.replace("_", " ").title()}')
axes[idx].grid(True, alpha=0.3)
plt.tight_layout()
plot_file = output_dir / 'parameter_sensitivity.png'
plt.savefig(plot_file, dpi=150)
plt.close()
return plot_file.name
def create_optuna_plots(study: optuna.Study, output_dir: Path) -> Dict[str, str]:
"""
Create professional Optuna visualization plots.
Args:
study: Optuna study object
output_dir: Directory to save plots
Returns:
Dictionary mapping plot names to filenames
"""
plots = {}
try:
# 1. Parallel Coordinate Plot - shows parameter interactions
fig = plot_parallel_coordinate(study)
if fig is not None:
plot_file = output_dir / 'optuna_parallel_coordinate.png'
fig.write_image(str(plot_file), width=1200, height=600)
plots['parallel_coordinate'] = plot_file.name
except Exception as e:
print(f"Warning: Could not create parallel coordinate plot: {e}")
try:
# 2. Optimization History - convergence over trials
fig = plot_optimization_history(study)
if fig is not None:
plot_file = output_dir / 'optuna_optimization_history.png'
fig.write_image(str(plot_file), width=1000, height=600)
plots['optimization_history'] = plot_file.name
except Exception as e:
print(f"Warning: Could not create optimization history plot: {e}")
try:
# 3. Parameter Importances - which parameters matter most
fig = plot_param_importances(study)
if fig is not None:
plot_file = output_dir / 'optuna_param_importances.png'
fig.write_image(str(plot_file), width=800, height=500)
plots['param_importances'] = plot_file.name
except Exception as e:
print(f"Warning: Could not create parameter importance plot: {e}")
try:
# 4. Slice Plot - individual parameter effects
fig = plot_slice(study)
if fig is not None:
plot_file = output_dir / 'optuna_slice.png'
fig.write_image(str(plot_file), width=1000, height=600)
plots['slice'] = plot_file.name
except Exception as e:
print(f"Warning: Could not create slice plot: {e}")
try:
# 5. Contour Plot - parameter interaction heatmap (2D only)
if len(study.best_params) == 2:
fig = plot_contour(study)
if fig is not None:
plot_file = output_dir / 'optuna_contour.png'
fig.write_image(str(plot_file), width=800, height=800)
plots['contour'] = plot_file.name
except Exception as e:
print(f"Warning: Could not create contour plot: {e}")
return plots
def generate_markdown_report(history_file: Path, target_value: Optional[float] = None,
tolerance: float = 0.1, reports_dir: Optional[Path] = None,
study: Optional[optuna.Study] = None) -> str:
"""Generate comprehensive markdown optimization report with graphs."""
# Load history
with open(history_file) as f:
history = json.load(f)
if not history:
return "# Optimization Report\n\nNo optimization history found."
# Graphs should be saved to 3_reports/ folder (same as markdown file)
study_dir = history_file.parent.parent
study_name = study_dir.name
if reports_dir is None:
reports_dir = study_dir / "3_reports"
reports_dir.mkdir(parents=True, exist_ok=True)
# Load phase transition and confidence history if available
results_dir = study_dir / "2_results"
phase_transitions = []
confidence_history = []
phase_transition_file = results_dir / "phase_transitions.json"
confidence_history_file = results_dir / "confidence_history.json"
if phase_transition_file.exists():
try:
with open(phase_transition_file) as f:
phase_transitions = json.load(f)
except Exception:
pass
if confidence_history_file.exists():
try:
with open(confidence_history_file) as f:
confidence_history = json.load(f)
except Exception:
pass
# Generate plots in reports folder
convergence_plot = create_convergence_plot(history, target_value, reports_dir)
design_space_plot = create_design_space_plot(history, reports_dir)
sensitivity_plot = create_parameter_sensitivity_plot(history, reports_dir)
# Generate confidence progression plot if data available
confidence_plot = None
if confidence_history:
print(" Generating confidence progression plot...")
confidence_plot = create_confidence_progression_plot(confidence_history, phase_transitions, reports_dir)
# Generate Optuna plots if study object provided
optuna_plots = {}
if study is not None:
print(" Generating Optuna visualization plots...")
optuna_plots = create_optuna_plots(study, reports_dir)
print(f" Generated {len(optuna_plots)} Optuna plots")
# Build markdown report
lines = []
lines.append(f"# {study_name.replace('_', ' ').title()} - Optimization Report")
lines.append("")
lines.append(f"**Total Trials**: {len(history)}")
lines.append("")
# Study information
lines.append("## Study Information")
lines.append("")
first_trial = history[0]
design_vars = list(first_trial['design_variables'].keys())
lines.append(f"- **Design Variables**: {', '.join([v.replace('_', ' ').title() for v in design_vars])}")
lines.append(f"- **Number of Trials**: {len(history)}")
lines.append("")
# Adaptive optimization strategy information
if phase_transitions or confidence_history:
lines.append("## Adaptive Optimization Strategy")
lines.append("")
lines.append("This study used adaptive surrogate-based optimization with confidence-driven phase transitions.")
lines.append("")
if phase_transitions:
lines.append("### Phase Transitions")
lines.append("")
for transition in phase_transitions:
trial_num = transition['trial_number']
conf = transition['confidence_metrics']['overall_confidence']
lines.append(f"- **Trial #{trial_num}**: EXPLORATION → EXPLOITATION")
lines.append(f" - Confidence at transition: {conf:.1%}")
lines.append(f" - Convergence score: {transition['confidence_metrics']['convergence_score']:.1%}")
lines.append(f" - Exploration coverage: {transition['confidence_metrics']['exploration_coverage']:.1%}")
lines.append(f" - Prediction stability: {transition['confidence_metrics']['prediction_stability']:.1%}")
lines.append("")
else:
lines.append("### Phase Transitions")
lines.append("")
lines.append("No phase transitions occurred - optimization remained in exploration phase.")
lines.append("This may indicate:")
lines.append("- Insufficient trials to build surrogate confidence")
lines.append("- Poor exploration coverage of the design space")
lines.append("- Unstable convergence behavior")
lines.append("")
if confidence_plot:
lines.append("### Confidence Progression")
lines.append("")
lines.append(f"![Confidence Progression]({confidence_plot})")
lines.append("")
lines.append("This plot shows how the surrogate model confidence evolved over the optimization.")
lines.append("The red vertical line (if present) marks the transition to exploitation phase.")
lines.append("")
lines.append("")
# Best result
objectives = [t['objective'] for t in history]
best_idx = np.argmin(objectives)
best_trial = history[best_idx]
lines.append("## Best Result")
lines.append("")
lines.append(f"- **Trial**: #{best_trial['trial_number']}")
lines.append("")
# Show actual results FIRST (what the client cares about)
lines.append("### Achieved Performance")
for result, value in best_trial['results'].items():
metric_name = result.replace('_', ' ').title()
lines.append(f"- **{metric_name}**: {value:.4f}")
# Show target comparison if available
if target_value is not None and 'frequency' in result.lower():
error = abs(value - target_value)
lines.append(f" - Target: {target_value:.4f}")
lines.append(f" - Error: {error:.4f} ({(error/target_value*100):.2f}%)")
lines.append("")
# Then design parameters that achieved it
lines.append("### Design Parameters")
for var, value in best_trial['design_variables'].items():
lines.append(f"- **{var.replace('_', ' ').title()}**: {value:.4f}")
lines.append("")
# Technical objective last (for engineers)
lines.append("<details>")
lines.append("<summary>Technical Details (Objective Function)</summary>")
lines.append("")
lines.append(f"- **Objective Value (Error)**: {best_trial['objective']:.6f}")
lines.append("")
lines.append("</details>")
lines.append("")
# Success assessment
if target_value is not None:
lines.append("## Success Assessment")
lines.append("")
best_objective = min(objectives)
if best_objective <= tolerance:
lines.append(f"### ✅ TARGET ACHIEVED")
lines.append("")
lines.append(f"Target value {target_value} was achieved within tolerance {tolerance}!")
lines.append(f"- **Best Error**: {best_objective:.6f}")
else:
lines.append(f"### ⚠️ TARGET NOT YET ACHIEVED")
lines.append("")
lines.append(f"Target value {target_value} not achieved within tolerance {tolerance}")
lines.append(f"- **Best Error**: {best_objective:.6f}")
lines.append(f"- **Required Improvement**: {best_objective - tolerance:.6f}")
lines.append(f"- **Recommendation**: Continue optimization with more trials")
lines.append("")
# Top 5 trials - show ACTUAL METRICS not just objective
lines.append("## Top 5 Trials")
lines.append("")
sorted_history = sorted(history, key=lambda x: x['objective'])
# Extract result column names (e.g., "first_frequency")
result_cols = list(sorted_history[0]['results'].keys())
result_col_names = [r.replace('_', ' ').title() for r in result_cols]
# Build header with results AND design vars
header_cols = ["Rank", "Trial"] + result_col_names + [v.replace('_', ' ').title() for v in design_vars]
lines.append("| " + " | ".join(header_cols) + " |")
lines.append("|" + "|".join(["-"*max(6, len(c)) for c in header_cols]) + "|")
for i, trial in enumerate(sorted_history[:5], 1):
result_vals = [f"{trial['results'][r]:.2f}" for r in result_cols]
var_vals = [f"{trial['design_variables'][v]:.2f}" for v in design_vars]
row_data = [str(i), f"#{trial['trial_number']}"] + result_vals + var_vals
lines.append("| " + " | ".join(row_data) + " |")
lines.append("")
# Statistics
lines.append("## Statistics")
lines.append("")
lines.append(f"- **Mean Objective**: {np.mean(objectives):.6f}")
lines.append(f"- **Std Deviation**: {np.std(objectives):.6f}")
lines.append(f"- **Best Objective**: {np.min(objectives):.6f}")
lines.append(f"- **Worst Objective**: {np.max(objectives):.6f}")
lines.append("")
# Design variable ranges
lines.append("### Design Variable Ranges")
lines.append("")
for var in design_vars:
values = [t['design_variables'][var] for t in history]
lines.append(f"**{var.replace('_', ' ').title()}**:")
lines.append(f"- Min: {min(values):.6f}")
lines.append(f"- Max: {max(values):.6f}")
lines.append(f"- Mean: {np.mean(values):.6f}")
lines.append("")
# Convergence plot
lines.append("## Convergence Plot")
lines.append("")
lines.append(f"![Convergence Plot]({convergence_plot})")
lines.append("")
lines.append("This plot shows how the optimization converged over time. The blue line shows each trial's objective value, while the red line shows the best objective found so far.")
lines.append("")
# Design space plot
if design_space_plot:
lines.append("## Design Space Exploration")
lines.append("")
lines.append(f"![Design Space Plot]({design_space_plot})")
lines.append("")
lines.append("This plot shows which regions of the design space were explored. Darker colors indicate better objective values.")
lines.append("")
# Sensitivity plot
lines.append("## Parameter Sensitivity")
lines.append("")
lines.append(f"![Parameter Sensitivity]({sensitivity_plot})")
lines.append("")
lines.append("These plots show how each design variable affects the objective value. Steeper slopes indicate higher sensitivity.")
lines.append("")
# Optuna Advanced Visualizations
if optuna_plots:
lines.append("## Advanced Optimization Analysis (Optuna)")
lines.append("")
lines.append("The following plots leverage Optuna's professional visualization library to provide deeper insights into the optimization process.")
lines.append("")
# Parallel Coordinate Plot
if 'parallel_coordinate' in optuna_plots:
lines.append("### Parallel Coordinate Plot")
lines.append("")
lines.append(f"![Parallel Coordinate]({optuna_plots['parallel_coordinate']})")
lines.append("")
lines.append("This interactive plot shows how different parameter combinations lead to different objective values. Each line represents one trial, colored by objective value. You can see parameter interactions and identify promising regions.")
lines.append("")
# Optimization History
if 'optimization_history' in optuna_plots:
lines.append("### Optimization History")
lines.append("")
lines.append(f"![Optimization History]({optuna_plots['optimization_history']})")
lines.append("")
lines.append("Professional visualization of convergence over trials, showing both individual trial performance and best value progression.")
lines.append("")
# Parameter Importance
if 'param_importances' in optuna_plots:
lines.append("### Parameter Importance Analysis")
lines.append("")
lines.append(f"![Parameter Importance]({optuna_plots['param_importances']})")
lines.append("")
lines.append("This analysis quantifies which design variables have the most impact on the objective. Based on fANOVA (functional ANOVA) or other importance metrics.")
lines.append("")
# Slice Plot
if 'slice' in optuna_plots:
lines.append("### Parameter Slice Analysis")
lines.append("")
lines.append(f"![Slice Plot]({optuna_plots['slice']})")
lines.append("")
lines.append("Shows how changing each parameter individually affects the objective value, with other parameters held constant.")
lines.append("")
# Contour Plot
if 'contour' in optuna_plots:
lines.append("### Parameter Interaction Contour")
lines.append("")
lines.append(f"![Contour Plot]({optuna_plots['contour']})")
lines.append("")
lines.append("2D heatmap showing how combinations of two parameters affect the objective. Reveals interaction effects and optimal regions.")
lines.append("")
# Trial history table - show actual results
lines.append("## Complete Trial History")
lines.append("")
lines.append("<details>")
lines.append("<summary>Click to expand full trial history</summary>")
lines.append("")
# Build complete history table with results
history_header = ["Trial"] + result_col_names + [v.replace('_', ' ').title() for v in design_vars]
lines.append("| " + " | ".join(history_header) + " |")
lines.append("|" + "|".join(["-"*max(6, len(c)) for c in history_header]) + "|")
for trial in history:
result_vals = [f"{trial['results'][r]:.2f}" for r in result_cols]
var_vals = [f"{trial['design_variables'][v]:.2f}" for v in design_vars]
row_data = [f"#{trial['trial_number']}"] + result_vals + var_vals
lines.append("| " + " | ".join(row_data) + " |")
lines.append("")
lines.append("</details>")
lines.append("")
# Footer
lines.append("---")
lines.append("")
lines.append(f"*Report generated automatically by Atomizer optimization system*")
return '\n'.join(lines)
def main():
"""Command-line interface."""
if len(sys.argv) < 2:
print("Usage: python generate_report_markdown.py <history_file> [target_value] [tolerance]")
sys.exit(1)
history_file = Path(sys.argv[1])
if not history_file.exists():
print(f"Error: History file not found: {history_file}")
sys.exit(1)
target_value = float(sys.argv[2]) if len(sys.argv) > 2 else None
tolerance = float(sys.argv[3]) if len(sys.argv) > 3 else 0.1
# Generate report
report = generate_markdown_report(history_file, target_value, tolerance)
# Save report
report_file = history_file.parent / 'OPTIMIZATION_REPORT.md'
with open(report_file, 'w', encoding='utf-8') as f:
f.write(report)
print(f"Report saved to: {report_file}")
if __name__ == '__main__':
main()

View File

@@ -0,0 +1,152 @@
"""
Generate human-readable optimization reports from incremental history JSON.
This script should be run automatically at the end of optimization, or manually
to generate a report for any completed optimization study.
"""
import json
import sys
from pathlib import Path
from typing import Dict, Any, List
import numpy as np
def generate_optimization_report(history_file: Path, target_value: float = None, tolerance: float = 0.1) -> str:
"""
Generate a comprehensive human-readable optimization report.
Args:
history_file: Path to optimization_history_incremental.json
target_value: Target objective value (if applicable)
tolerance: Acceptable tolerance for success (default 0.1)
Returns:
Report text as a string
"""
# Load history
with open(history_file) as f:
history = json.load(f)
if not history:
return "No optimization history found."
report = []
report.append('=' * 80)
report.append('OPTIMIZATION REPORT')
report.append('=' * 80)
report.append('')
# Study information
study_dir = history_file.parent.parent.parent
study_name = study_dir.name
report.append('STUDY INFORMATION')
report.append('-' * 80)
report.append(f'Study: {study_name}')
report.append(f'Total trials: {len(history)}')
report.append('')
# Design variables
first_trial = history[0]
design_vars = list(first_trial['design_variables'].keys())
report.append('DESIGN VARIABLES')
report.append('-' * 80)
for var in design_vars:
values = [t['design_variables'][var] for t in history]
report.append(f' {var}:')
report.append(f' Range: {min(values):.4f} - {max(values):.4f}')
report.append(f' Mean: {np.mean(values):.4f}')
report.append('')
# Objective results
results = list(first_trial['results'].keys())
report.append('OBJECTIVE RESULTS')
report.append('-' * 80)
for result in results:
values = [t['results'][result] for t in history]
report.append(f' {result}:')
report.append(f' Range: {min(values):.4f} - {max(values):.4f}')
report.append(f' Mean: {np.mean(values):.4f}')
report.append(f' Std dev: {np.std(values):.4f}')
report.append('')
# Best trial
objectives = [t['objective'] for t in history]
best_trial = history[np.argmin(objectives)]
report.append('BEST TRIAL')
report.append('-' * 80)
report.append(f'Trial #{best_trial["trial_number"]}')
report.append(f' Objective value: {best_trial["objective"]:.4f}')
report.append(' Design variables:')
for var, value in best_trial['design_variables'].items():
report.append(f' {var}: {value:.4f}')
report.append(' Results:')
for result, value in best_trial['results'].items():
report.append(f' {result}: {value:.4f}')
report.append('')
# Top 5 trials
report.append('TOP 5 TRIALS (by objective value)')
report.append('-' * 80)
sorted_history = sorted(history, key=lambda x: x['objective'])
for i, trial in enumerate(sorted_history[:5], 1):
report.append(f'{i}. Trial #{trial["trial_number"]}: Objective = {trial["objective"]:.4f}')
vars_str = ', '.join([f'{k}={v:.2f}' for k, v in trial['design_variables'].items()])
report.append(f' {vars_str}')
report.append('')
# Success assessment (if target provided)
if target_value is not None:
report.append('SUCCESS ASSESSMENT')
report.append('-' * 80)
best_objective = min(objectives)
error = abs(best_objective - target_value)
if error <= tolerance:
report.append(f'[SUCCESS] Target {target_value} achieved within tolerance {tolerance}!')
report.append(f' Best objective: {best_objective:.4f}')
report.append(f' Error: {error:.4f}')
else:
report.append(f'[INCOMPLETE] Target {target_value} not achieved')
report.append(f' Best objective: {best_objective:.4f}')
report.append(f' Error: {error:.4f}')
report.append(f' Need {error - tolerance:.4f} improvement')
report.append('')
report.append('=' * 80)
return '\n'.join(report)
def main():
"""Command-line interface for report generation."""
if len(sys.argv) < 2:
print("Usage: python generate_report.py <history_file> [target_value] [tolerance]")
print("Example: python generate_report.py studies/my_study/2_substudies/results/optimization_history_incremental.json 115.0 0.1")
sys.exit(1)
history_file = Path(sys.argv[1])
if not history_file.exists():
print(f"Error: History file not found: {history_file}")
sys.exit(1)
target_value = float(sys.argv[2]) if len(sys.argv) > 2 else None
tolerance = float(sys.argv[3]) if len(sys.argv) > 3 else 0.1
# Generate report
report = generate_optimization_report(history_file, target_value, tolerance)
# Save report
report_file = history_file.parent / 'OPTIMIZATION_REPORT.txt'
with open(report_file, 'w') as f:
f.write(report)
# Print to console
print(report)
print()
print(f"Report saved to: {report_file}")
if __name__ == '__main__':
main()

View File

@@ -0,0 +1,393 @@
"""
Comprehensive Results Analyzer
Performs thorough introspection of OP2, F06, and other Nastran output files
to discover ALL available results, not just what we expect.
This helps ensure we don't miss important data that's actually in the output files.
"""
from pathlib import Path
from typing import Dict, Any, List, Optional
import json
from dataclasses import dataclass, asdict
from pyNastran.op2.op2 import OP2
@dataclass
class OP2Contents:
"""Complete inventory of OP2 file contents."""
file_path: str
subcases: List[int]
# Displacement results
displacement_available: bool
displacement_subcases: List[int]
# Stress results (by element type)
stress_results: Dict[str, List[int]] # element_type -> [subcases]
# Strain results (by element type)
strain_results: Dict[str, List[int]]
# Force results
force_results: Dict[str, List[int]]
# Other results
other_results: Dict[str, Any]
# Grid point forces/stresses
grid_point_forces: List[int]
spc_forces: List[int]
mpc_forces: List[int]
# Summary
total_result_types: int
element_types_with_results: List[str]
@dataclass
class F06Contents:
"""Complete inventory of F06 file contents."""
file_path: str
has_displacement: bool
has_stress: bool
has_strain: bool
has_forces: bool
element_types_found: List[str]
error_messages: List[str]
warning_messages: List[str]
class ComprehensiveResultsAnalyzer:
"""
Analyzes ALL Nastran output files to discover available results.
This is much more thorough than just checking expected results.
"""
def __init__(self, output_dir: Path):
"""
Initialize analyzer.
Args:
output_dir: Directory containing Nastran output files (.op2, .f06, etc.)
"""
self.output_dir = Path(output_dir)
def analyze_op2(self, op2_file: Path) -> OP2Contents:
"""
Comprehensively analyze OP2 file contents.
Args:
op2_file: Path to OP2 file
Returns:
OP2Contents with complete inventory
"""
print(f"\n[OP2 ANALYSIS] Reading: {op2_file.name}")
model = OP2()
model.read_op2(str(op2_file))
# Discover all subcases
all_subcases = set()
# Check displacement
displacement_available = hasattr(model, 'displacements') and len(model.displacements) > 0
displacement_subcases = list(model.displacements.keys()) if displacement_available else []
all_subcases.update(displacement_subcases)
print(f" Displacement: {'YES' if displacement_available else 'NO'}")
if displacement_subcases:
print(f" Subcases: {displacement_subcases}")
# Check ALL stress results by scanning attributes
stress_results = {}
element_types_with_stress = []
# List of known stress attribute names (safer than scanning all attributes)
stress_attrs = [
'cquad4_stress', 'ctria3_stress', 'ctetra_stress', 'chexa_stress', 'cpenta_stress',
'cbar_stress', 'cbeam_stress', 'crod_stress', 'conrod_stress', 'ctube_stress',
'cshear_stress', 'cbush_stress', 'cgap_stress', 'celas1_stress', 'celas2_stress',
'celas3_stress', 'celas4_stress'
]
for attr_name in stress_attrs:
if hasattr(model, attr_name):
try:
stress_obj = getattr(model, attr_name)
if isinstance(stress_obj, dict) and len(stress_obj) > 0:
element_type = attr_name.replace('_stress', '')
subcases = list(stress_obj.keys())
stress_results[element_type] = subcases
element_types_with_stress.append(element_type)
all_subcases.update(subcases)
print(f" Stress [{element_type}]: YES")
print(f" Subcases: {subcases}")
except Exception as e:
# Skip attributes that cause errors
pass
if not stress_results:
print(f" Stress: NO stress results found")
# Check ALL strain results
strain_results = {}
strain_attrs = [attr.replace('_stress', '_strain') for attr in stress_attrs]
for attr_name in strain_attrs:
if hasattr(model, attr_name):
try:
strain_obj = getattr(model, attr_name)
if isinstance(strain_obj, dict) and len(strain_obj) > 0:
element_type = attr_name.replace('_strain', '')
subcases = list(strain_obj.keys())
strain_results[element_type] = subcases
all_subcases.update(subcases)
print(f" Strain [{element_type}]: YES")
print(f" Subcases: {subcases}")
except Exception as e:
pass
if not strain_results:
print(f" Strain: NO strain results found")
# Check ALL force results
force_results = {}
force_attrs = [attr.replace('_stress', '_force') for attr in stress_attrs]
for attr_name in force_attrs:
if hasattr(model, attr_name):
try:
force_obj = getattr(model, attr_name)
if isinstance(force_obj, dict) and len(force_obj) > 0:
element_type = attr_name.replace('_force', '')
subcases = list(force_obj.keys())
force_results[element_type] = subcases
all_subcases.update(subcases)
print(f" Force [{element_type}]: YES")
print(f" Subcases: {subcases}")
except Exception as e:
pass
if not force_results:
print(f" Force: NO force results found")
# Check grid point forces
grid_point_forces = list(model.grid_point_forces.keys()) if hasattr(model, 'grid_point_forces') else []
if grid_point_forces:
print(f" Grid Point Forces: YES")
print(f" Subcases: {grid_point_forces}")
all_subcases.update(grid_point_forces)
# Check SPC/MPC forces
spc_forces = list(model.spc_forces.keys()) if hasattr(model, 'spc_forces') else []
mpc_forces = list(model.mpc_forces.keys()) if hasattr(model, 'mpc_forces') else []
if spc_forces:
print(f" SPC Forces: YES")
print(f" Subcases: {spc_forces}")
all_subcases.update(spc_forces)
if mpc_forces:
print(f" MPC Forces: YES")
print(f" Subcases: {mpc_forces}")
all_subcases.update(mpc_forces)
# Check for other interesting results
other_results = {}
interesting_attrs = ['eigenvalues', 'eigenvectors', 'thermal_load_vectors',
'load_vectors', 'contact', 'glue', 'slide_lines']
for attr_name in interesting_attrs:
if hasattr(model, attr_name):
obj = getattr(model, attr_name)
if obj and (isinstance(obj, dict) and len(obj) > 0) or (not isinstance(obj, dict)):
other_results[attr_name] = str(type(obj))
print(f" {attr_name}: YES")
# Collect all element types that have any results
all_element_types = set()
all_element_types.update(stress_results.keys())
all_element_types.update(strain_results.keys())
all_element_types.update(force_results.keys())
total_result_types = (
len(stress_results) +
len(strain_results) +
len(force_results) +
(1 if displacement_available else 0) +
(1 if grid_point_forces else 0) +
(1 if spc_forces else 0) +
(1 if mpc_forces else 0) +
len(other_results)
)
print(f"\n SUMMARY:")
print(f" Total subcases: {len(all_subcases)}")
print(f" Total result types: {total_result_types}")
print(f" Element types with results: {sorted(all_element_types)}")
return OP2Contents(
file_path=str(op2_file),
subcases=sorted(all_subcases),
displacement_available=displacement_available,
displacement_subcases=displacement_subcases,
stress_results=stress_results,
strain_results=strain_results,
force_results=force_results,
other_results=other_results,
grid_point_forces=grid_point_forces,
spc_forces=spc_forces,
mpc_forces=mpc_forces,
total_result_types=total_result_types,
element_types_with_results=sorted(all_element_types)
)
def analyze_f06(self, f06_file: Path) -> F06Contents:
"""
Analyze F06 file for available results.
Args:
f06_file: Path to F06 file
Returns:
F06Contents with inventory
"""
print(f"\n[F06 ANALYSIS] Reading: {f06_file.name}")
if not f06_file.exists():
print(f" F06 file not found")
return F06Contents(
file_path=str(f06_file),
has_displacement=False,
has_stress=False,
has_strain=False,
has_forces=False,
element_types_found=[],
error_messages=[],
warning_messages=[]
)
# Read F06 file
with open(f06_file, 'r', encoding='latin-1', errors='ignore') as f:
content = f.read()
# Search for key sections
has_displacement = 'D I S P L A C E M E N T' in content
has_stress = 'S T R E S S E S' in content
has_strain = 'S T R A I N S' in content
has_forces = 'F O R C E S' in content
print(f" Displacement: {'YES' if has_displacement else 'NO'}")
print(f" Stress: {'YES' if has_stress else 'NO'}")
print(f" Strain: {'YES' if has_strain else 'NO'}")
print(f" Forces: {'YES' if has_forces else 'NO'}")
# Find element types mentioned
element_keywords = ['CQUAD4', 'CTRIA3', 'CTETRA', 'CHEXA', 'CPENTA', 'CBAR', 'CBEAM', 'CROD']
element_types_found = []
for elem_type in element_keywords:
if elem_type in content:
element_types_found.append(elem_type)
if element_types_found:
print(f" Element types: {element_types_found}")
# Extract errors and warnings
error_messages = []
warning_messages = []
for line in content.split('\n'):
line_upper = line.upper()
if 'ERROR' in line_upper or 'FATAL' in line_upper:
error_messages.append(line.strip())
elif 'WARNING' in line_upper or 'WARN' in line_upper:
warning_messages.append(line.strip())
if error_messages:
print(f" Errors found: {len(error_messages)}")
for err in error_messages[:5]: # Show first 5
print(f" {err}")
if warning_messages:
print(f" Warnings found: {len(warning_messages)}")
for warn in warning_messages[:5]: # Show first 5
print(f" {warn}")
return F06Contents(
file_path=str(f06_file),
has_displacement=has_displacement,
has_stress=has_stress,
has_strain=has_strain,
has_forces=has_forces,
element_types_found=element_types_found,
error_messages=error_messages[:20], # Keep first 20
warning_messages=warning_messages[:20]
)
def analyze_all(self, op2_pattern: str = "*.op2", f06_pattern: str = "*.f06") -> Dict[str, Any]:
"""
Analyze all OP2 and F06 files in directory.
Args:
op2_pattern: Glob pattern for OP2 files
f06_pattern: Glob pattern for F06 files
Returns:
Dict with complete analysis results
"""
print("="*80)
print("COMPREHENSIVE NASTRAN RESULTS ANALYSIS")
print("="*80)
print(f"\nDirectory: {self.output_dir}")
results = {
'directory': str(self.output_dir),
'op2_files': [],
'f06_files': []
}
# Find and analyze all OP2 files
op2_files = list(self.output_dir.glob(op2_pattern))
print(f"\nFound {len(op2_files)} OP2 file(s)")
for op2_file in op2_files:
op2_contents = self.analyze_op2(op2_file)
results['op2_files'].append(asdict(op2_contents))
# Find and analyze all F06 files
f06_files = list(self.output_dir.glob(f06_pattern))
print(f"\nFound {len(f06_files)} F06 file(s)")
for f06_file in f06_files:
f06_contents = self.analyze_f06(f06_file)
results['f06_files'].append(asdict(f06_contents))
print("\n" + "="*80)
print("ANALYSIS COMPLETE")
print("="*80)
return results
if __name__ == '__main__':
import sys
if len(sys.argv) > 1:
output_dir = Path(sys.argv[1])
else:
output_dir = Path.cwd()
analyzer = ComprehensiveResultsAnalyzer(output_dir)
results = analyzer.analyze_all()
# Save results to JSON
output_file = output_dir / "comprehensive_results_analysis.json"
with open(output_file, 'w', encoding='utf-8') as f:
json.dump(results, f, indent=2)
print(f"\nResults saved to: {output_file}")

View File

@@ -0,0 +1,555 @@
"""
Optimization Visualization System
Generates publication-quality plots for optimization results:
- Convergence plots
- Design space exploration
- Parallel coordinate plots
- Parameter sensitivity heatmaps
- Constraint violation tracking
"""
from pathlib import Path
from typing import Dict, List, Any, Optional
import json
import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl
from matplotlib.figure import Figure
import pandas as pd
from datetime import datetime
# Configure matplotlib for publication quality
mpl.rcParams['figure.dpi'] = 150
mpl.rcParams['savefig.dpi'] = 300
mpl.rcParams['font.size'] = 10
mpl.rcParams['font.family'] = 'sans-serif'
mpl.rcParams['axes.labelsize'] = 10
mpl.rcParams['axes.titlesize'] = 11
mpl.rcParams['xtick.labelsize'] = 9
mpl.rcParams['ytick.labelsize'] = 9
mpl.rcParams['legend.fontsize'] = 9
class OptimizationVisualizer:
"""
Generate comprehensive visualizations for optimization studies.
Automatically creates:
- Convergence plot (objective vs trials)
- Design space exploration (parameter evolution)
- Parallel coordinate plot (high-dimensional view)
- Sensitivity heatmap (correlations)
- Constraint violation tracking
"""
def __init__(self, substudy_dir: Path):
"""
Initialize visualizer for a substudy.
Args:
substudy_dir: Path to substudy directory containing history.json
"""
self.substudy_dir = Path(substudy_dir)
self.plots_dir = self.substudy_dir / 'plots'
self.plots_dir.mkdir(exist_ok=True)
# Load data
self.history = self._load_history()
self.config = self._load_config()
self.df = self._history_to_dataframe()
def _load_history(self) -> List[Dict]:
"""Load optimization history from JSON."""
history_file = self.substudy_dir / 'history.json'
if not history_file.exists():
raise FileNotFoundError(f"History file not found: {history_file}")
with open(history_file, 'r') as f:
return json.load(f)
def _load_config(self) -> Dict:
"""Load optimization configuration."""
# Try to find config in parent directories
for parent in [self.substudy_dir, self.substudy_dir.parent, self.substudy_dir.parent.parent]:
config_files = list(parent.glob('*config.json'))
if config_files:
with open(config_files[0], 'r') as f:
return json.load(f)
# Return minimal config if not found
return {'design_variables': {}, 'objectives': [], 'constraints': []}
def _history_to_dataframe(self) -> pd.DataFrame:
"""Convert history to flat DataFrame for analysis."""
rows = []
for entry in self.history:
row = {
'trial': entry.get('trial_number'),
'timestamp': entry.get('timestamp'),
'total_objective': entry.get('total_objective')
}
# Add design variables
for var, val in entry.get('design_variables', {}).items():
row[f'dv_{var}'] = val
# Add objectives
for obj, val in entry.get('objectives', {}).items():
row[f'obj_{obj}'] = val
# Add constraints
for const, val in entry.get('constraints', {}).items():
row[f'const_{const}'] = val
rows.append(row)
return pd.DataFrame(rows)
def generate_all_plots(self, save_formats: List[str] = ['png', 'pdf']) -> Dict[str, List[Path]]:
"""
Generate all visualization plots.
Args:
save_formats: List of formats to save plots in (png, pdf, svg)
Returns:
Dictionary mapping plot type to list of saved file paths
"""
saved_files = {}
print(f"Generating plots in: {self.plots_dir}")
# 1. Convergence plot
print(" - Generating convergence plot...")
saved_files['convergence'] = self.plot_convergence(save_formats)
# 2. Design space exploration
print(" - Generating design space exploration...")
saved_files['design_space'] = self.plot_design_space(save_formats)
# 3. Parallel coordinate plot
print(" - Generating parallel coordinate plot...")
saved_files['parallel_coords'] = self.plot_parallel_coordinates(save_formats)
# 4. Sensitivity heatmap
print(" - Generating sensitivity heatmap...")
saved_files['sensitivity'] = self.plot_sensitivity_heatmap(save_formats)
# 5. Constraint violations (if constraints exist)
if any('const_' in col for col in self.df.columns):
print(" - Generating constraint violation plot...")
saved_files['constraints'] = self.plot_constraint_violations(save_formats)
# 6. Objective breakdown (if multi-objective)
obj_cols = [col for col in self.df.columns if col.startswith('obj_')]
if len(obj_cols) > 1:
print(" - Generating objective breakdown...")
saved_files['objectives'] = self.plot_objective_breakdown(save_formats)
print(f"SUCCESS: All plots saved to: {self.plots_dir}")
return saved_files
def plot_convergence(self, save_formats: List[str] = ['png']) -> List[Path]:
"""
Plot optimization convergence: objective value vs trial number.
Shows both individual trials and running best.
"""
fig, ax = plt.subplots(figsize=(10, 6))
trials = self.df['trial'].values
objectives = self.df['total_objective'].values
# Calculate running best
running_best = np.minimum.accumulate(objectives)
# Plot individual trials
ax.scatter(trials, objectives, alpha=0.6, s=30, color='steelblue',
label='Trial objective', zorder=2)
# Plot running best
ax.plot(trials, running_best, color='darkred', linewidth=2,
label='Running best', zorder=3)
# Highlight best trial
best_idx = np.argmin(objectives)
ax.scatter(trials[best_idx], objectives[best_idx],
color='gold', s=200, marker='*', edgecolors='black',
linewidths=1.5, label='Best trial', zorder=4)
ax.set_xlabel('Trial Number')
ax.set_ylabel('Total Objective Value')
ax.set_title('Optimization Convergence')
ax.legend(loc='best')
ax.grid(True, alpha=0.3)
# Add improvement annotation
improvement = (objectives[0] - objectives[best_idx]) / objectives[0] * 100
ax.text(0.02, 0.98, f'Improvement: {improvement:.1f}%\nBest trial: {trials[best_idx]}',
transform=ax.transAxes, verticalalignment='top',
bbox=dict(boxstyle='round', facecolor='wheat', alpha=0.5))
plt.tight_layout()
return self._save_figure(fig, 'convergence', save_formats)
def plot_design_space(self, save_formats: List[str] = ['png']) -> List[Path]:
"""
Plot design variable evolution over trials.
Shows how parameters change during optimization.
"""
dv_cols = [col for col in self.df.columns if col.startswith('dv_')]
n_vars = len(dv_cols)
if n_vars == 0:
print(" Warning: No design variables found, skipping design space plot")
return []
# Create subplots
fig, axes = plt.subplots(n_vars, 1, figsize=(10, 3*n_vars), sharex=True)
if n_vars == 1:
axes = [axes]
trials = self.df['trial'].values
objectives = self.df['total_objective'].values
best_idx = np.argmin(objectives)
for idx, col in enumerate(dv_cols):
ax = axes[idx]
var_name = col.replace('dv_', '')
values = self.df[col].values
# Color points by objective value (normalized)
norm = mpl.colors.Normalize(vmin=objectives.min(), vmax=objectives.max())
colors = plt.cm.viridis_r(norm(objectives)) # reversed so better = darker
# Plot evolution
scatter = ax.scatter(trials, values, c=colors, s=40, alpha=0.7,
edgecolors='black', linewidths=0.5)
# Highlight best trial
ax.scatter(trials[best_idx], values[best_idx],
color='gold', s=200, marker='*', edgecolors='black',
linewidths=1.5, zorder=10)
# Get units from config
units = self.config.get('design_variables', {}).get(var_name, {}).get('units', '')
ylabel = f'{var_name}'
if units:
ylabel += f' [{units}]'
ax.set_ylabel(ylabel)
ax.grid(True, alpha=0.3)
# Add colorbar for first subplot
if idx == 0:
cbar = plt.colorbar(mpl.cm.ScalarMappable(norm=norm, cmap='viridis_r'),
ax=ax, orientation='horizontal', pad=0.1)
cbar.set_label('Objective Value (darker = better)')
axes[-1].set_xlabel('Trial Number')
fig.suptitle('Design Space Exploration', fontsize=12, y=1.0)
plt.tight_layout()
return self._save_figure(fig, 'design_space_evolution', save_formats)
def plot_parallel_coordinates(self, save_formats: List[str] = ['png']) -> List[Path]:
"""
Parallel coordinate plot showing high-dimensional design space.
Each line represents one trial, colored by objective value.
"""
# Get design variables and objective
dv_cols = [col for col in self.df.columns if col.startswith('dv_')]
if len(dv_cols) == 0:
print(" Warning: No design variables found, skipping parallel coordinates plot")
return []
# Prepare data: normalize all columns to [0, 1]
plot_data = self.df[dv_cols + ['total_objective']].copy()
# Normalize each column
normalized = pd.DataFrame()
for col in plot_data.columns:
col_min = plot_data[col].min()
col_max = plot_data[col].max()
if col_max > col_min:
normalized[col] = (plot_data[col] - col_min) / (col_max - col_min)
else:
normalized[col] = 0.5 # If constant, put in middle
# Create figure
fig, ax = plt.subplots(figsize=(12, 6))
# Setup x-axis
n_vars = len(normalized.columns)
x_positions = np.arange(n_vars)
# Color by objective value
objectives = self.df['total_objective'].values
norm = mpl.colors.Normalize(vmin=objectives.min(), vmax=objectives.max())
colormap = plt.cm.viridis_r
# Plot each trial as a line
for idx in range(len(normalized)):
values = normalized.iloc[idx].values
color = colormap(norm(objectives[idx]))
ax.plot(x_positions, values, color=color, alpha=0.3, linewidth=1)
# Highlight best trial
best_idx = np.argmin(objectives)
best_values = normalized.iloc[best_idx].values
ax.plot(x_positions, best_values, color='gold', linewidth=3,
label='Best trial', zorder=10, marker='o', markersize=8,
markeredgecolor='black', markeredgewidth=1.5)
# Setup axes
ax.set_xticks(x_positions)
labels = [col.replace('dv_', '').replace('_', '\n') for col in dv_cols] + ['Objective']
ax.set_xticklabels(labels, rotation=0, ha='center')
ax.set_ylabel('Normalized Value [0-1]')
ax.set_title('Parallel Coordinate Plot - Design Space Overview')
ax.set_ylim(-0.05, 1.05)
ax.grid(True, alpha=0.3, axis='y')
ax.legend(loc='best')
# Add colorbar
sm = mpl.cm.ScalarMappable(cmap=colormap, norm=norm)
sm.set_array([])
cbar = plt.colorbar(sm, ax=ax, orientation='vertical', pad=0.02)
cbar.set_label('Objective Value (darker = better)')
plt.tight_layout()
return self._save_figure(fig, 'parallel_coordinates', save_formats)
def plot_sensitivity_heatmap(self, save_formats: List[str] = ['png']) -> List[Path]:
"""
Correlation heatmap showing sensitivity between design variables and objectives.
"""
# Get numeric columns
dv_cols = [col for col in self.df.columns if col.startswith('dv_')]
obj_cols = [col for col in self.df.columns if col.startswith('obj_')]
if not dv_cols or not obj_cols:
print(" Warning: Insufficient data for sensitivity heatmap, skipping")
return []
# Calculate correlation matrix
analysis_cols = dv_cols + obj_cols + ['total_objective']
corr_matrix = self.df[analysis_cols].corr()
# Extract DV vs Objective correlations
sensitivity = corr_matrix.loc[dv_cols, obj_cols + ['total_objective']]
# Create heatmap
fig, ax = plt.subplots(figsize=(10, max(6, len(dv_cols) * 0.6)))
im = ax.imshow(sensitivity.values, cmap='RdBu_r', vmin=-1, vmax=1, aspect='auto')
# Set ticks
ax.set_xticks(np.arange(len(sensitivity.columns)))
ax.set_yticks(np.arange(len(sensitivity.index)))
# Labels
x_labels = [col.replace('obj_', '').replace('_', ' ') for col in sensitivity.columns]
y_labels = [col.replace('dv_', '').replace('_', ' ') for col in sensitivity.index]
ax.set_xticklabels(x_labels, rotation=45, ha='right')
ax.set_yticklabels(y_labels)
# Add correlation values as text
for i in range(len(sensitivity.index)):
for j in range(len(sensitivity.columns)):
value = sensitivity.values[i, j]
color = 'white' if abs(value) > 0.5 else 'black'
ax.text(j, i, f'{value:.2f}', ha='center', va='center',
color=color, fontsize=9)
ax.set_title('Parameter Sensitivity Analysis\n(Correlation: Design Variables vs Objectives)')
# Colorbar
cbar = plt.colorbar(im, ax=ax)
cbar.set_label('Correlation Coefficient', rotation=270, labelpad=20)
plt.tight_layout()
return self._save_figure(fig, 'sensitivity_heatmap', save_formats)
def plot_constraint_violations(self, save_formats: List[str] = ['png']) -> List[Path]:
"""
Plot constraint violations over trials.
"""
const_cols = [col for col in self.df.columns if col.startswith('const_')]
if not const_cols:
return []
fig, ax = plt.subplots(figsize=(10, 6))
trials = self.df['trial'].values
for col in const_cols:
const_name = col.replace('const_', '').replace('_', ' ')
values = self.df[col].values
# Plot constraint value
ax.plot(trials, values, marker='o', markersize=4,
label=const_name, alpha=0.7, linewidth=1.5)
ax.axhline(y=0, color='red', linestyle='--', linewidth=2,
label='Feasible threshold', zorder=1)
ax.set_xlabel('Trial Number')
ax.set_ylabel('Constraint Value (< 0 = satisfied)')
ax.set_title('Constraint Violations Over Trials')
ax.legend(loc='best')
ax.grid(True, alpha=0.3)
plt.tight_layout()
return self._save_figure(fig, 'constraint_violations', save_formats)
def plot_objective_breakdown(self, save_formats: List[str] = ['png']) -> List[Path]:
"""
Stacked area plot showing individual objective contributions.
"""
obj_cols = [col for col in self.df.columns if col.startswith('obj_')]
if len(obj_cols) < 2:
return []
fig, ax = plt.subplots(figsize=(10, 6))
trials = self.df['trial'].values
# Normalize objectives for stacking
obj_data = self.df[obj_cols].values.T
ax.stackplot(trials, *obj_data,
labels=[col.replace('obj_', '').replace('_', ' ') for col in obj_cols],
alpha=0.7)
# Also plot total
ax.plot(trials, self.df['total_objective'].values,
color='black', linewidth=2, linestyle='--',
label='Total objective', zorder=10)
ax.set_xlabel('Trial Number')
ax.set_ylabel('Objective Value')
ax.set_title('Multi-Objective Breakdown')
ax.legend(loc='best')
ax.grid(True, alpha=0.3)
plt.tight_layout()
return self._save_figure(fig, 'objective_breakdown', save_formats)
def _save_figure(self, fig: Figure, name: str, formats: List[str]) -> List[Path]:
"""
Save figure in multiple formats.
Args:
fig: Matplotlib figure
name: Base filename (without extension)
formats: List of file formats (png, pdf, svg)
Returns:
List of saved file paths
"""
saved_paths = []
for fmt in formats:
filepath = self.plots_dir / f'{name}.{fmt}'
fig.savefig(filepath, bbox_inches='tight')
saved_paths.append(filepath)
plt.close(fig)
return saved_paths
def generate_plot_summary(self) -> Dict[str, Any]:
"""
Generate summary statistics for inclusion in reports.
Returns:
Dictionary with key statistics and insights
"""
objectives = self.df['total_objective'].values
trials = self.df['trial'].values
best_idx = np.argmin(objectives)
best_trial = int(trials[best_idx])
best_value = float(objectives[best_idx])
initial_value = float(objectives[0])
improvement_pct = (initial_value - best_value) / initial_value * 100
# Convergence metrics
running_best = np.minimum.accumulate(objectives)
improvements = np.diff(running_best)
significant_improvements = np.sum(improvements < -0.01 * initial_value) # >1% improvement
# Design variable ranges
dv_cols = [col for col in self.df.columns if col.startswith('dv_')]
dv_exploration = {}
for col in dv_cols:
var_name = col.replace('dv_', '')
values = self.df[col].values
dv_exploration[var_name] = {
'min_explored': float(values.min()),
'max_explored': float(values.max()),
'best_value': float(values[best_idx]),
'range_coverage': float((values.max() - values.min()))
}
summary = {
'total_trials': int(len(trials)),
'best_trial': best_trial,
'best_objective': best_value,
'initial_objective': initial_value,
'improvement_percent': improvement_pct,
'significant_improvements': int(significant_improvements),
'design_variable_exploration': dv_exploration,
'convergence_rate': float(np.mean(np.abs(improvements[:10]))) if len(improvements) > 10 else 0.0,
'timestamp': datetime.now().isoformat()
}
# Save summary
summary_file = self.plots_dir / 'plot_summary.json'
with open(summary_file, 'w') as f:
json.dump(summary, f, indent=2)
return summary
def generate_plots_for_substudy(substudy_dir: Path, formats: List[str] = ['png', 'pdf']):
"""
Convenience function to generate all plots for a substudy.
Args:
substudy_dir: Path to substudy directory
formats: List of save formats
Returns:
OptimizationVisualizer instance
"""
visualizer = OptimizationVisualizer(substudy_dir)
visualizer.generate_all_plots(save_formats=formats)
summary = visualizer.generate_plot_summary()
print(f"\n{'='*60}")
print(f"VISUALIZATION SUMMARY")
print(f"{'='*60}")
print(f"Total trials: {summary['total_trials']}")
print(f"Best trial: {summary['best_trial']}")
print(f"Improvement: {summary['improvement_percent']:.2f}%")
print(f"Plots saved to: {visualizer.plots_dir}")
print(f"{'='*60}\n")
return visualizer
if __name__ == '__main__':
import sys
if len(sys.argv) < 2:
print("Usage: python visualizer.py <substudy_directory> [formats...]")
print("Example: python visualizer.py studies/beam/substudies/opt1 png pdf")
sys.exit(1)
substudy_path = Path(sys.argv[1])
formats = sys.argv[2:] if len(sys.argv) > 2 else ['png', 'pdf']
generate_plots_for_substudy(substudy_path, formats)