GridSearchCV — How n_jobs=-1 Crashed Our Training Cluster

from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_iris

# io.thecodeforge: Professional Grid Search Implementation
def optimize_forge_model():
    iris = load_iris()
    X, y = iris.data, iris.target

    # Initialize the base estimator
    rf = RandomForestClassifier(random_state=42)

    # Define the parameter grid (the 'knobs' to turn)
    param_grid = {
        'n_estimators': [50, 100, 200],
        'max_depth': [None, 10, 20],
        'min_samples_split': [2, 5]
    }

    # Initialize GridSearchCV with 5-fold cross-validation
    # n_jobs=-1 utilizes all available CPU cores
    grid_search = GridSearchCV(estimator=rf, param_grid=param_grid, cv=5, scoring='accuracy', n_jobs=-1)

    # Fit the grid search to find the best combination
    grid_search.fit(X, y)

    print(f"Best Parameters: {grid_search.best_params_}")
    print(f"Best Cross-Validation Score: {grid_search.best_score_:.4f}")
    return grid_search.best_estimator_

optimize_forge_model()

-- io.thecodeforge: Recording the outcome of a GridSearchCV run
INSERT INTO io.thecodeforge.hyperparameter_audit (
    model_key,
    best_params_json,
    best_accuracy,
    search_duration_seconds,
    optimized_at
) VALUES (
    'customer_segmentation_rf',
    '{"n_estimators": 100, "max_depth": 10, "min_samples_split": 2}',
    0.9667,
    452,
    CURRENT_TIMESTAMP
);

# io.thecodeforge: High-performance optimization image
FROM python:3.11-slim

WORKDIR /app

# Scikit-Learn optimization often requires thread-safe BLAS libraries
RUN apt-get update && apt-get install -y libopenblas-dev && rm -rf /var/lib/apt/lists/*

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY . .

# Run the optimization script
CMD ["python", "ForgeGridSearch.py"]

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC

# io.thecodeforge: Tuning within a Pipeline to prevent leakage
forge_pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('svc', SVC())
])

# Use 'stepname__parameter' syntax for the grid
param_grid = {
    'svc__C': [0.1, 1, 10],
    'svc__kernel': ['linear', 'rbf']
}

grid_search = GridSearchCV(forge_pipeline, param_grid, cv=3)
grid_search.fit(X_train, y_train)

# io.thecodeforge: Analyze grid search results for production readiness
import pandas as pd

def analyze_cv_results(grid_search):
    results = pd.DataFrame(grid_search.cv_results_)
    # Create a stability metric: negative mean_test_score + std_test_score
    # Lower is better and more stable
    results['stability_score'] = -(results['mean_test_score'] - results['std_test_score'])
    results_sorted = results.sort_values('stability_score', ascending=False)
    
    # Check for overfitting
    results_sorted['overfit_gap'] = results_sorted['mean_train_score'] - results_sorted['mean_test_score']
    
    print("Top 5 stable parameter combos:")
    print(results_sorted[['params', 'mean_test_score', 'std_test_score', 'overfit_gap']].head())
    
    # Flag combos where overfit_gap > 0.05
    risky = results_sorted[results_sorted['overfit_gap'] > 0.05]
    if not risky.empty:
        print("\nWARNING: The following combos show significant overfitting:")
        print(risky[['params', 'overfit_gap']])

# Usage after fitting
analyze_cv_results(grid_search)