مقايضة التحيز والتباين وتحليل الأخطاء

from sklearn.model_selection import learning_curve, train_test_split
from sklearn.datasets import make_classification
from sklearn.ensemble import GradientBoostingClassifier
import matplotlib.pyplot as plt
import numpy as np

class="tok-comment"># ── Sample data + model ────────────────────────────────────────────────
X, y = make_classification(n_samples=class="tok-num">800, 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)

train_sizes, train_scores, val_scores = learning_curve(
    estimator=model,
    X=X_train, y=y_train,
    train_sizes=np.linspace(class="tok-num">0.1, class="tok-num">1.0, class="tok-num">10),
    cv=class="tok-num">5, scoring=class="tok-str">'roc_auc',
    n_jobs=-class="tok-num">1, shuffle=True
)

train_mean = train_scores.mean(axis=class="tok-num">1)
train_std = train_scores.std(axis=class="tok-num">1)
val_mean = val_scores.mean(axis=class="tok-num">1)
val_std = val_scores.std(axis=class="tok-num">1)

class="tok-comment"># Diagnosis:
gap = train_mean[-class="tok-num">1] - val_mean[-class="tok-num">1]
level = val_mean[-class="tok-num">1]

if level < class="tok-num">0.7:
    print(class="tok-str">"HIGH BIAS: increase model complexity or add features")
elif gap > class="tok-num">0.1:
    print(class="tok-str">"HIGH VARIANCE: add more data, regularization, or reduce complexity")
else:
    print(class="tok-str">"Good generalization — optimize hyperparameters")