Random Forest: Ensemble Learning

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import (
    train_test_split, cross_val_score, 
    StratifiedKFold, learning_curve
)
from sklearn.metrics import (
    accuracy_score, precision_score, recall_score,
    f1_score, roc_auc_score, confusion_matrix,
    classification_report, roc_curve
)
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
import warnings
warnings.filterwarnings('ignore')

# =============================================
# 1. LOAD & PERSIAPAN DATA
# =============================================
data = load_breast_cancer()
X = pd.DataFrame(data.data, columns=data.feature_names)
y = pd.Series(data.target, name='target')

print("=" * 60)
print("DATASET BREAST CANCER")
print("=" * 60)
print(f"Jumlah samples: {X.shape[0]}")
print(f"Jumlah fitur: {X.shape[1]}")
print(f"Kelas: {dict(zip(data.target_names, np.bincount(y)))}")
print(f"\n5 baris pertama:")
print(X.head())

# Train-test split
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)
print(f"\nTrain size: {X_train.shape[0]}")
print(f"Test size: {X_test.shape[0]}")

# =============================================
# 2. TRAINING RANDOM FOREST
# =============================================
rf_model = RandomForestClassifier(
    n_estimators=300,        # Jumlah tree
    max_features='sqrt',     # Fitur per split (sqrt untuk klasifikasi)
    max_depth=None,          # Tanpa batas kedalaman
    min_samples_split=2,     # Minimum sample untuk split
    min_samples_leaf=1,      # Minimum sample di leaf
    bootstrap=True,          # Gunakan bootstrap
    oob_score=True,          # Aktifkan OOB scoring
    random_state=42,
    n_jobs=-1,               # Gunakan semua CPU core
    class_weight='balanced'  # Handle class imbalance
)
rf_model.fit(X_train, y_train)

# =============================================
# 3. EVALUASI MODEL
# =============================================
y_pred = rf_model.predict(X_test)
y_prob = rf_model.predict_proba(X_test)[:, 1]

print("\n" + "=" * 60)
print("EVALUASI MODEL")
print("=" * 60)
print(f"OOB Score: {rf_model.oob_score_:.4f}")
print(f"Test Accuracy: {accuracy_score(y_test, y_pred):.4f}")
print(f"Precision: {precision_score(y_test, y_pred):.4f}")
print(f"Recall: {recall_score(y_test, y_pred):.4f}")
print(f"F1-Score: {f1_score(y_test, y_pred):.4f}")
print(f"ROC AUC: {roc_auc_score(y_test, y_prob):.4f}")
print(f"\nClassification Report:")
print(classification_report(y_test, y_pred, target_names=data.target_names))

# =============================================
# 4. CROSS VALIDATION
# =============================================
cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
cv_scores = cross_val_score(rf_model, X, y, cv=cv, scoring='accuracy')

print("=" * 60)
print("CROSS VALIDATION (5-Fold)")
print("=" * 60)
print(f"Scores: {cv_scores}")
print(f"Mean: {cv_scores.mean():.4f} ± {cv_scores.std():.4f}")

# =============================================
# 5. VISUALISASI
# =============================================
fig, axes = plt.subplots(2, 2, figsize=(14, 12))

# 5a. Confusion Matrix
cm = confusion_matrix(y_test, y_pred)
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',
            xticklabels=data.target_names,
            yticklabels=data.target_names, ax=axes[0, 0])
axes[0, 0].set_title('Confusion Matrix')
axes[0, 0].set_xlabel('Prediksi')
axes[0, 0].set_ylabel('Aktual')

# 5b. ROC Curve
fpr, tpr, _ = roc_curve(y_test, y_prob)
axes[0, 1].plot(fpr, tpr, 'b-', linewidth=2,
                label=f'RF (AUC = {roc_auc_score(y_test, y_prob):.3f})')
axes[0, 1].plot([0, 1], [0, 1], 'k--', alpha=0.5)
axes[0, 1].set_title('ROC Curve')
axes[0, 1].set_xlabel('False Positive Rate')
axes[0, 1].set_ylabel('True Positive Rate')
axes[0, 1].legend()

# 5c. Feature Importance (Top 15)
importances = rf_model.feature_importances_
indices = np.argsort(importances)[::-1][:15]
axes[1, 0].barh(range(15), importances[indices][::-1])
axes[1, 0].set_yticks(range(15))
axes[1, 0].set_yticklabels([data.feature_names[i] for i in indices][::-1])
axes[1, 0].set_title('Top 15 Feature Importance')

# 5d. Learning Curve
train_sizes, train_scores, val_scores = learning_curve(
    rf_model, X_train, y_train, cv=5,
    train_sizes=np.linspace(0.1, 1.0, 10),
    scoring='accuracy', n_jobs=-1
)
axes[1, 1].plot(train_sizes, train_scores.mean(axis=1), 'o-', label='Training')
axes[1, 1].plot(train_sizes, val_scores.mean(axis=1), 'o-', label='Validation')
axes[1, 1].fill_between(train_sizes,
                         train_scores.mean(axis=1) - train_scores.std(axis=1),
                         train_scores.mean(axis=1) + train_scores.std(axis=1), alpha=0.2)
axes[1, 1].fill_between(train_sizes,
                         val_scores.mean(axis=1) - val_scores.std(axis=1),
                         val_scores.mean(axis=1) + val_scores.std(axis=1), alpha=0.2)
axes[1, 1].set_title('Learning Curve')
axes[1, 1].set_xlabel('Training Set Size')
axes[1, 1].set_ylabel('Accuracy')
axes[1, 1].legend()

plt.suptitle('Random Forest — Analisis Hasil', fontsize=14, y=1.02)
plt.tight_layout()
plt.show()