ओवरफ़िटिंग और सीखने की वक्र: डेटा रिसाव के बिना अंतर समझें

import numpy as np
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import StratifiedKFold, learning_curve
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler

# Illustrative synthetic classification data.
X, y = make_classification(
    n_samples=500, n_features=20,
    n_informative=5, n_redundant=5, random_state=42
)
model = make_pipeline(
    StandardScaler(), LogisticRegression(max_iter=1000)
)
cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
sizes, training_scores, validation_scores = learning_curve(
    model, X, y, cv=cv,
    train_sizes=np.linspace(0.2, 1.0, 5), scoring="accuracy"
)
print(sizes)
print(training_scores.mean(axis=1))
print(validation_scores.mean(axis=1))