from sklearn.model_selection import cross_val_score, KFold
from sklearn.ensemble import RandomForestClassifier
import numpy as np

# إنشاء نموذج
model = RandomForestClassifier(n_estimators=100, random_state=42)

# تطبيق 5-Fold Cross Validation
kfold = KFold(n_splits=5, shuffle=True, random_state=42)
cv_scores = cross_val_score(model, X, y, cv=kfold, scoring='accuracy')

print(f"دقة كل fold: {cv_scores}")
print(f"متوسط الدقة: {cv_scores.mean():.3f} ± {cv_scores.std():.3f}")

# النتيجة المتوقعة:
# دقة كل fold: [0.92  0.895 0.91  0.905 0.88 ]
# متوسط الدقة: 0.902 ± 0.014
                

from sklearn.model_selection import StratifiedKFold

# للبيانات غير المتوازنة
stratified_kfold = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
stratified_scores = cross_val_score(model, X, y, cv=stratified_kfold, scoring='accuracy')

print(f"Stratified CV الدقة: {stratified_scores.mean():.3f} ± {stratified_scores.std():.3f}")
                

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

# تحديد المعاملات للبحث
param_grid = {
    'n_estimators': [50, 100, 200],
    'max_depth': [3, 5, 7, None],
    'min_samples_split': [2, 5, 10],
    'min_samples_leaf': [1, 2, 4]
}

# إنشاء Grid Search
grid_search = GridSearchCV(
    estimator=RandomForestClassifier(random_state=42),
    param_grid=param_grid,
    cv=5,  # 5-fold cross validation
    scoring='accuracy',
    n_jobs=-1,  # استخدام جميع المعالجات
    verbose=1   # إظهار التقدم
)

# تدريب وإيجاد أفضل معاملات
grid_search.fit(X_train, y_train)

print(f"أفضل معاملات: {grid_search.best_params_}")
print(f"أفضل دقة: {grid_search.best_score_:.3f}")
                

from sklearn.model_selection import RandomizedSearchCV
from scipy.stats import randint

# تحديد توزيعات المعاملات
param_distributions = {
    'n_estimators': randint(50, 500),
    'max_depth': [3, 5, 7, 10, None],
    'min_samples_split': randint(2, 20),
    'min_samples_leaf': randint(1, 10)
}

# إنشاء Random Search
random_search = RandomizedSearchCV(
    estimator=RandomForestClassifier(random_state=42),
    param_distributions=param_distributions,
    n_iter=100,  # عدد التجارب
    cv=5,
    scoring='accuracy',
    n_jobs=-1,
    random_state=42
)

random_search.fit(X_train, y_train)
print(f"أفضل معاملات: {random_search.best_params_}")
                

from sklearn.ensemble import RandomForestClassifier

# إنشاء Random Forest
rf = RandomForestClassifier(
    n_estimators=200,    # عدد الأشجار
    max_depth=10,        # عمق كل شجرة
    min_samples_split=5, # الحد الأدنى للتقسيم
    random_state=42
)

rf.fit(X_train, y_train)
rf_score = rf.score(X_test, y_test)
print(f"دقة Random Forest: {rf_score:.3f}")
                

from sklearn.ensemble import GradientBoostingClassifier

# إنشاء Gradient Boosting
gb = GradientBoostingClassifier(
    n_estimators=100,
    learning_rate=0.1,
    max_depth=3,
    random_state=42
)

gb.fit(X_train, y_train)
gb_score = gb.score(X_test, y_test)
print(f"دقة Gradient Boosting: {gb_score:.3f}")
                

from sklearn.ensemble import VotingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC

# إنشاء نماذج متعددة
lr = LogisticRegression(random_state=42)
svm = SVC(probability=True, random_state=42)
rf = RandomForestClassifier(random_state=42)

# دمجها في Voting Classifier
voting_clf = VotingClassifier(
    estimators=[('lr', lr), ('svm', svm), ('rf', rf)],
    voting='soft'  # استخدام الاحتماليات
)

voting_clf.fit(X_train, y_train)
voting_score = voting_clf.score(X_test, y_test)
print(f"دقة Voting Classifier: {voting_score:.3f}")