Hello, I'm Yash

# Advanced Machine Learning Pipeline with Scikit-learn

import numpy as np
import joblib
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report

# Load dataset
data = load_breast_cancer()
X, y = data.data, data.target

# Train-test split
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25, random_state=42, stratify=y
)

# Build pipeline (scaling + model)
pipeline = Pipeline([
    ("scaler", StandardScaler()),
    ("clf", RandomForestClassifier(random_state=42))
])

# Hyperparameter tuning
param_grid = {
    "clf__n_estimators": [100, 200, 300],
    "clf__max_depth": [None, 5, 10, 20],
    "clf__min_samples_split": [2, 5, 10],
}

grid = GridSearchCV(
    estimator=pipeline,
    param_grid=param_grid,
    cv=5,
    n_jobs=-1,
    scoring="accuracy",
)

# Train optimized model
grid.fit(X_train, y_train)

# Best model from GridSearch
best_model = grid.best_estimator_

print("Best Parameters:", grid.best_params_)

# Prediction
y_pred = best_model.predict(X_test)

# Evaluation
accuracy = accuracy_score(y_test, y_pred)
print(f"\nTest Accuracy: {accuracy:.4f}\n")
print(classification_report(y_test, y_pred))

# Feature importance (from RandomForest)
rf = best_model.named_steps["clf"]
importances = rf.feature_importances_

print("Top 5 Important Features:")
top_idx = np.argsort(importances)[-5:][::-1]
for idx in top_idx:
    print(f"{data.feature_names[idx]}: {importances[idx]:.4f}")

# Save model
joblib.dump(best_model, "optimized_random_forest.pkl")
print("\nModel saved as optimized_random_forest.pkl")