Sklearn Random Forest: Python에서 분류와 회귀를 위한 완벽 가이드

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, accuracy_score
from sklearn.datasets import load_wine
 
# Load dataset
wine = load_wine()
X, y = wine.data, wine.target
feature_names = wine.feature_names
 
print(f"Dataset: {X.shape[0]} samples, {X.shape[1]} features")
print(f"Classes: {wine.target_names}")
 
# Split data
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)
 
# Train Random Forest
rf = RandomForestClassifier(
    n_estimators=100,
    max_depth=None,
    min_samples_split=2,
    min_samples_leaf=1,
    random_state=42,
    n_jobs=-1
)
rf.fit(X_train, y_train)
 
# Evaluate
y_pred = rf.predict(X_test)
print(f"\nAccuracy: {accuracy_score(y_test, y_pred):.4f}")
print(f"\nClassification Report:")
print(classification_report(y_test, y_pred, target_names=wine.target_names))

from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split
 
wine = load_wine()
X_train, X_test, y_train, y_test = train_test_split(
    wine.data, wine.target, test_size=0.2, random_state=42, stratify=wine.target
)
 
rf = RandomForestClassifier(
    n_estimators=200,
    oob_score=True,
    random_state=42,
    n_jobs=-1
)
rf.fit(X_train, y_train)
 
print(f"OOB Score:  {rf.oob_score_:.4f}")
print(f"Test Score: {rf.score(X_test, y_test):.4f}")

from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
from sklearn.datasets import fetch_california_housing
import numpy as np
 
# Load California housing dataset
housing = fetch_california_housing()
X, y = housing.data, housing.target
feature_names = housing.feature_names
 
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)
 
# Train regressor
rf_reg = RandomForestRegressor(
    n_estimators=200,
    max_depth=20,
    min_samples_leaf=5,
    random_state=42,
    n_jobs=-1
)
rf_reg.fit(X_train, y_train)
y_pred = rf_reg.predict(X_test)
 
# Evaluation metrics
r2 = r2_score(y_test, y_pred)
rmse = np.sqrt(mean_squared_error(y_test, y_pred))
mae = mean_absolute_error(y_test, y_pred)
 
print(f"R-squared: {r2:.4f}")
print(f"RMSE:      {rmse:.4f}")
print(f"MAE:       {mae:.4f}")

from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor
from sklearn.linear_model import LinearRegression, Ridge
from sklearn.tree import DecisionTreeRegressor
from sklearn.model_selection import cross_val_score, train_test_split
from sklearn.datasets import fetch_california_housing
import numpy as np
 
housing = fetch_california_housing()
X_train, X_test, y_train, y_test = train_test_split(
    housing.data, housing.target, test_size=0.2, random_state=42
)
 
regressors = {
    'Linear Regression': LinearRegression(),
    'Ridge': Ridge(alpha=1.0),
    'Decision Tree': DecisionTreeRegressor(max_depth=10, random_state=42),
    'Random Forest': RandomForestRegressor(n_estimators=100, max_depth=20, random_state=42, n_jobs=-1),
    'Gradient Boosting': GradientBoostingRegressor(n_estimators=100, max_depth=5, random_state=42),
}
 
print(f"{'Model':<25} {'CV R² (mean)':>12} {'CV R² (std)':>12}")
print("-" * 52)
 
for name, model in regressors.items():
    scores = cross_val_score(model, X_train, y_train, cv=5, scoring='r2', n_jobs=-1)
    print(f"{name:<25} {scores.mean():>12.4f} {scores.std():>12.4f}")

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV, train_test_split
from sklearn.datasets import load_wine
 
wine = load_wine()
X_train, X_test, y_train, y_test = train_test_split(
    wine.data, wine.target, test_size=0.2, random_state=42, stratify=wine.target
)
 
param_grid = {
    'n_estimators': [100, 200, 300],
    'max_depth': [None, 10, 20],
    'min_samples_split': [2, 5, 10],
    'min_samples_leaf': [1, 2, 4],
}
 
rf = RandomForestClassifier(random_state=42, n_jobs=-1)
grid_search = GridSearchCV(
    rf,
    param_grid,
    cv=5,
    scoring='accuracy',
    n_jobs=-1,
    verbose=1
)
grid_search.fit(X_train, y_train)
 
print(f"Best Parameters: {grid_search.best_params_}")
print(f"Best CV Score:   {grid_search.best_score_:.4f}")
print(f"Test Score:      {grid_search.score(X_test, y_test):.4f}")

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import RandomizedSearchCV, train_test_split
from sklearn.datasets import load_wine
from scipy.stats import randint, uniform
 
wine = load_wine()
X_train, X_test, y_train, y_test = train_test_split(
    wine.data, wine.target, test_size=0.2, random_state=42, stratify=wine.target
)
 
param_distributions = {
    'n_estimators': randint(50, 500),
    'max_depth': [None, 5, 10, 15, 20, 30],
    'min_samples_split': randint(2, 20),
    'min_samples_leaf': randint(1, 10),
    'max_features': ['sqrt', 'log2', 0.3, 0.5, 0.7],
    'bootstrap': [True, False],
}
 
rf = RandomForestClassifier(random_state=42, n_jobs=-1)
random_search = RandomizedSearchCV(
    rf,
    param_distributions,
    n_iter=100,
    cv=5,
    scoring='accuracy',
    random_state=42,
    n_jobs=-1,
    verbose=1
)
random_search.fit(X_train, y_train)
 
print(f"Best Parameters: {random_search.best_params_}")
print(f"Best CV Score:   {random_search.best_score_:.4f}")
print(f"Test Score:      {random_search.score(X_test, y_test):.4f}")

from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import numpy as np
 
wine = load_wine()
X_train, X_test, y_train, y_test = train_test_split(
    wine.data, wine.target, test_size=0.2, random_state=42, stratify=wine.target
)
 
rf = RandomForestClassifier(n_estimators=200, random_state=42, n_jobs=-1)
rf.fit(X_train, y_train)
 
# Get feature importances
importances = rf.feature_importances_
feature_names = wine.feature_names
indices = np.argsort(importances)[::-1]
 
# Print ranked features
print("Feature Ranking:")
for i, idx in enumerate(indices):
    print(f"  {i+1}. {feature_names[idx]:25s} ({importances[idx]:.4f})")
 
# Plot
plt.figure(figsize=(10, 6))
plt.barh(range(len(indices)), importances[indices[::-1]], align='center')
plt.yticks(range(len(indices)), [feature_names[i] for i in indices[::-1]])
plt.xlabel('Feature Importance (Gini)')
plt.title('Random Forest Feature Importance - Wine Dataset')
plt.tight_layout()
plt.savefig('rf_feature_importance.png', dpi=150)
plt.show()

from sklearn.ensemble import RandomForestClassifier
from sklearn.inspection import permutation_importance
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import numpy as np
 
wine = load_wine()
X_train, X_test, y_train, y_test = train_test_split(
    wine.data, wine.target, test_size=0.2, random_state=42, stratify=wine.target
)
 
rf = RandomForestClassifier(n_estimators=200, random_state=42, n_jobs=-1)
rf.fit(X_train, y_train)
 
# Compute permutation importance on the test set
perm_imp = permutation_importance(
    rf, X_test, y_test,
    n_repeats=30,
    random_state=42,
    n_jobs=-1
)
 
# Sort and display
sorted_idx = perm_imp.importances_mean.argsort()[::-1]
 
print("Permutation Importance (test set):")
for idx in sorted_idx:
    mean = perm_imp.importances_mean[idx]
    std = perm_imp.importances_std[idx]
    print(f"  {wine.feature_names[idx]:25s}: {mean:.4f} +/- {std:.4f}")
 
# Plot with error bars
plt.figure(figsize=(10, 6))
plt.barh(
    range(len(sorted_idx)),
    perm_imp.importances_mean[sorted_idx[::-1]],
    xerr=perm_imp.importances_std[sorted_idx[::-1]],
    align='center'
)
plt.yticks(range(len(sorted_idx)), [wine.feature_names[i] for i in sorted_idx[::-1]])
plt.xlabel('Decrease in Accuracy')
plt.title('Permutation Importance - Wine Dataset')
plt.tight_layout()
plt.savefig('rf_permutation_importance.png', dpi=150)
plt.show()

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import cross_val_score
from sklearn.datasets import load_wine
 
wine = load_wine()
X, y = wine.data, wine.target
 
rf = RandomForestClassifier(n_estimators=200, random_state=42, n_jobs=-1)
scores = cross_val_score(rf, X, y, cv=5, scoring='accuracy')
 
print(f"CV Accuracy: {scores.mean():.4f} (+/- {scores.std():.4f})")
print(f"Per-fold:    {scores}")

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import StratifiedKFold, cross_val_score
from sklearn.datasets import load_wine
import numpy as np
 
wine = load_wine()
X, y = wine.data, wine.target
 
# Stratified 10-fold cross-validation
skf = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)
rf = RandomForestClassifier(n_estimators=200, random_state=42, n_jobs=-1)
 
scores = cross_val_score(rf, X, y, cv=skf, scoring='accuracy')
print(f"Stratified 10-Fold Accuracy: {scores.mean():.4f} (+/- {scores.std():.4f})")
 
# Multiple metrics
from sklearn.model_selection import cross_validate
 
results = cross_validate(
    rf, X, y, cv=skf,
    scoring=['accuracy', 'f1_weighted', 'precision_weighted', 'recall_weighted'],
    n_jobs=-1
)
 
for metric in ['test_accuracy', 'test_f1_weighted', 'test_precision_weighted', 'test_recall_weighted']:
    vals = results[metric]
    name = metric.replace('test_', '')
    print(f"{name:>20s}: {vals.mean():.4f} (+/- {vals.std():.4f})")

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.datasets import make_classification
 
# Create imbalanced dataset (95% class 0, 5% class 1)
X, y = make_classification(
    n_samples=2000,
    n_features=20,
    weights=[0.95, 0.05],
    flip_y=0,
    random_state=42
)
 
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42, stratify=y
)
 
# Without class weight
rf_default = RandomForestClassifier(n_estimators=200, random_state=42, n_jobs=-1)
rf_default.fit(X_train, y_train)
print("=== Without class_weight ===")
print(classification_report(y_test, rf_default.predict(X_test)))
 
# With balanced class weight
rf_balanced = RandomForestClassifier(
    n_estimators=200,
    class_weight='balanced',
    random_state=42,
    n_jobs=-1
)
rf_balanced.fit(X_train, y_train)
print("=== With class_weight='balanced' ===")
print(classification_report(y_test, rf_balanced.predict(X_test)))

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.datasets import make_classification
from imblearn.over_sampling import SMOTE
from imblearn.pipeline import Pipeline as ImbPipeline
 
# Create imbalanced dataset
X, y = make_classification(
    n_samples=2000,
    n_features=20,
    weights=[0.95, 0.05],
    flip_y=0,
    random_state=42
)
 
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42, stratify=y
)
 
# SMOTE + Random Forest pipeline
pipeline = ImbPipeline([
    ('smote', SMOTE(random_state=42)),
    ('rf', RandomForestClassifier(n_estimators=200, random_state=42, n_jobs=-1))
])
pipeline.fit(X_train, y_train)
 
print("=== SMOTE + Random Forest ===")
print(classification_report(y_test, pipeline.predict(X_test)))

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import (
    classification_report, confusion_matrix,
    ConfusionMatrixDisplay, accuracy_score
)
from sklearn.datasets import load_wine
import matplotlib.pyplot as plt
 
wine = load_wine()
X_train, X_test, y_train, y_test = train_test_split(
    wine.data, wine.target, test_size=0.2, random_state=42, stratify=wine.target
)
 
rf = RandomForestClassifier(n_estimators=200, random_state=42, n_jobs=-1)
rf.fit(X_train, y_train)
y_pred = rf.predict(X_test)
 
# Metrics
print(f"Accuracy: {accuracy_score(y_test, y_pred):.4f}")
print(f"\n{classification_report(y_test, y_pred, target_names=wine.target_names)}")
 
# Confusion matrix plot
cm = confusion_matrix(y_test, y_pred)
disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=wine.target_names)
disp.plot(cmap='Blues')
plt.title('Random Forest - Wine Classification')
plt.tight_layout()
plt.savefig('rf_confusion_matrix.png', dpi=150)
plt.show()

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_curve, roc_auc_score, RocCurveDisplay
from sklearn.datasets import load_breast_cancer
import matplotlib.pyplot as plt
 
cancer = load_breast_cancer()
X_train, X_test, y_train, y_test = train_test_split(
    cancer.data, cancer.target, test_size=0.2, random_state=42, stratify=cancer.target
)
 
rf = RandomForestClassifier(n_estimators=200, random_state=42, n_jobs=-1)
rf.fit(X_train, y_train)
 
# Predict probabilities
y_prob = rf.predict_proba(X_test)[:, 1]
auc = roc_auc_score(y_test, y_prob)
 
# Plot ROC curve
RocCurveDisplay.from_estimator(rf, X_test, y_test)
plt.title(f'Random Forest ROC Curve (AUC = {auc:.4f})')
plt.tight_layout()
plt.savefig('rf_roc_curve.png', dpi=150)
plt.show()

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split, cross_val_score, StratifiedKFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.datasets import load_breast_cancer
import numpy as np
import pandas as pd
 
# Load and prepare data
cancer = load_breast_cancer()
df = pd.DataFrame(cancer.data, columns=cancer.feature_names)
df['target'] = cancer.target
 
# Introduce some missing values to simulate real data
np.random.seed(42)
mask = np.random.random(df.shape) < 0.05
df_missing = df.mask(mask.astype(bool))
df_missing['target'] = cancer.target  # Keep target clean
 
X = df_missing.drop('target', axis=1)
y = df_missing['target']
 
# Split
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)
 
# Build preprocessing + model pipeline
numeric_features = X.columns.tolist()
numeric_transformer = Pipeline([
    ('imputer', SimpleImputer(strategy='median')),
    ('scaler', StandardScaler()),
])
 
preprocessor = ColumnTransformer(
    transformers=[
        ('num', numeric_transformer, numeric_features),
    ]
)
 
pipeline = Pipeline([
    ('preprocessor', preprocessor),
    ('classifier', RandomForestClassifier(
        n_estimators=300,
        max_depth=20,
        min_samples_leaf=2,
        class_weight='balanced',
        random_state=42,
        n_jobs=-1
    ))
])
 
# Cross-validation
skf = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
cv_scores = cross_val_score(pipeline, X_train, y_train, cv=skf, scoring='accuracy')
print(f"Cross-validation accuracy: {cv_scores.mean():.4f} (+/- {cv_scores.std():.4f})")
 
# Train final model
pipeline.fit(X_train, y_train)
y_pred = pipeline.predict(X_test)
 
# Evaluation
print(f"\nTest Set Results:")
print(classification_report(y_test, y_pred, target_names=cancer.target_names))
 
# Make predictions on new data
sample = X_test.iloc[:3]
predictions = pipeline.predict(sample)
probabilities = pipeline.predict_proba(sample)
 
print(f"\nSample Predictions:")
for i, (pred, prob) in enumerate(zip(predictions, probabilities)):
    class_name = cancer.target_names[pred]
    confidence = prob[pred]
    print(f"  Sample {i+1}: {class_name} (confidence: {confidence:.2%})")

import joblib
 
# Save the trained pipeline
joblib.dump(pipeline, 'rf_pipeline.joblib')
 
# Load and use later
loaded_pipeline = joblib.load('rf_pipeline.joblib')
new_predictions = loaded_pipeline.predict(X_test[:5])
print(f"Loaded model predictions: {new_predictions}")

import pandas as pd
import pygwalker as pyg
 
# Build a results DataFrame
results = pd.DataFrame(X_test.values, columns=cancer.feature_names)
results['actual'] = y_test.values
results['predicted'] = y_pred
results['correct'] = y_test.values == y_pred
results['prob_malignant'] = pipeline.predict_proba(X_test)[:, 0]
results['prob_benign'] = pipeline.predict_proba(X_test)[:, 1]
 
# Launch interactive exploration
walker = pyg.walk(results)