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

# ── Sample data + model ────────────────────────────────────────────────
X, y = make_classification(n_samples=800, n_features=10, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42)
model = GradientBoostingClassifier(n_estimators=100, random_state=42)

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

train_mean = train_scores.mean(axis=1)
train_std = train_scores.std(axis=1)
val_mean = val_scores.mean(axis=1)
val_std = val_scores.std(axis=1)

# Diagnosis:
gap = train_mean[-1] - val_mean[-1]
level = val_mean[-1]

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