Random Forest: الگوریتم قدرتمند یادگیری ماشین برای طبقه‌بندی و پیش‌بینی

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report
import numpy as np
import pandas as pd

# بارگذاری داده
# فرض کنید X شامل ویژگی‌ها و y شامل برچسب‌ها است
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# ایجاد مدل Random Forest
rf_model = RandomForestClassifier(
    n_estimators=100,
    max_depth=10,
    min_samples_split=5,
    min_samples_leaf=2,
    max_features='sqrt',
    random_state=42,
    n_jobs=-1  # استفاده از تمام هسته‌های CPU
)
# آموزش مدل
rf_model.fit(X_train, y_train)
# پیش‌بینی
y_pred = rf_model.predict(X_test)
# ارزیابی
accuracy = accuracy_score(y_test, y_pred)
print(f"دقت مدل: {accuracy:.4f}")
print("\nگزارش طبقه‌بندی:")
print(classification_report(y_test, y_pred))
# نمایش اهمیت ویژگی‌ها
feature_importance = pd.DataFrame({
    'feature': X.columns,
    'importance': rf_model.feature_importances_
}).sort_values('importance', ascending=False)
print("\nاهمیت ویژگی‌ها:")
print(feature_importance.head(10))

from sklearn.model_selection import GridSearchCV

param_grid = {
    'n_estimators': [100, 200, 300],
    'max_depth': [10, 20, 30, None],
    'min_samples_split': [2, 5, 10],
    'min_samples_leaf': [1, 2, 4],
    'max_features': ['sqrt', 'log2']
}
grid_search = GridSearchCV(
    RandomForestClassifier(random_state=42),
    param_grid,
    cv=5,
    scoring='accuracy',
    n_jobs=-1
)
grid_search.fit(X_train, y_train)
best_model = grid_search.best_estimator_

# انتخاب ویژگی‌های مهم
important_features = feature_importance[feature_importance['importance'] > 0.01]['feature'].tolist()
X_selected = X[important_features]

from sklearn.model_selection import cross_val_score

scores = cross_val_score(rf_model, X_train, y_train, cv=5, scoring='accuracy')
print(f"میانگین دقت: {scores.mean():.4f} (+/- {scores.std():.4f})")

import joblib

# ذخیره مدل
joblib.dump(rf_model, 'random_forest_model.pkl')
# بارگذاری مدل
loaded_model = joblib.load('random_forest_model.pkl')

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.impute import SimpleImputer

# ایجاد Pipeline
pipeline = Pipeline([
    ('imputer', SimpleImputer(strategy='median')),
    ('scaler', StandardScaler()),
    ('classifier', RandomForestClassifier(n_estimators=200, random_state=42))
])
# آموزش Pipeline
pipeline.fit(X_train, y_train)
# پیش‌بینی
y_pred = pipeline.predict(X_test)