تقييم النماذج والمقاييس

from sklearn.metrics import (
    classification_report, roc_auc_score, f1_score,
    average_precision_score, matthews_corrcoef,
    confusion_matrix
)
from sklearn.model_selection import StratifiedKFold, train_test_split
from sklearn.datasets import make_classification
from sklearn.ensemble import GradientBoostingClassifier
import numpy as np

class="tok-comment"># ── Sample data + model ────────────────────────────────────────────────
X, y = make_classification(n_samples=class="tok-num">1000, n_features=class="tok-num">10, random_state=class="tok-num">42)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=class="tok-num">0.2, random_state=class="tok-num">42)
model = GradientBoostingClassifier(n_estimators=class="tok-num">100, random_state=class="tok-num">42)

skf = StratifiedKFold(n_splits=class="tok-num">5, shuffle=True, random_state=class="tok-num">42)
oof_probs = np.zeros(len(y_train))

for fold, (tr_idx, val_idx) in enumerate(skf.split(X_train, y_train)):
    model.fit(X_train[tr_idx], y_train[tr_idx])
    oof_probs[val_idx] = model.predict_proba(X_train[val_idx])[:, class="tok-num">1]
    print(fclass="tok-str">"Fold {fold+class="tok-num">1} AUC: {roc_auc_score(y_train[val_idx], oof_probs[val_idx]):.4f}")

class="tok-comment"># Full OOF evaluation
print(fclass="tok-str">"\nOOF AUC: {roc_auc_score(y_train, oof_probs):.4f}")
print(fclass="tok-str">"OOF AUC-PR: {average_precision_score(y_train, oof_probs):.4f}")
print(fclass="tok-str">"MCC: {matthews_corrcoef(y_train, oof_probs > class="tok-num">0.5):.4f}")

class="tok-comment"># Optimal threshold by F1
thresholds = np.linspace(class="tok-num">0.01, class="tok-num">0.99, class="tok-num">200)
f1s = [f1_score(y_train, oof_probs > t) for t in thresholds]
best_threshold = thresholds[np.argmax(f1s)]
print(fclass="tok-str">"Optimal threshold: {best_threshold:.3f}, F1: {max(f1s):.4f}")