import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import load_breast_cancer
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import StratifiedKFold, cross_val_score
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler

X, y = load_breast_cancer(return_X_y=True)

cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
models = {
    "LogReg (L2)": make_pipeline(
        StandardScaler(),
        LogisticRegression(max_iter=2000, penalty="l2", C=1.0, solver="lbfgs"),
    ),
    "LogReg (ElasticNet)": make_pipeline(
        StandardScaler(),
        LogisticRegression(
            max_iter=2000,
            penalty="elasticnet",
            solver="saga",
            C=1.0,
            l1_ratio=0.4,
        ),
    ),
    "RandomForest": RandomForestClassifier(
        n_estimators=200, max_depth=6, random_state=42
    ),
}

means = []
stds = []
labels = []
for name, model in models.items():
    scores = cross_val_score(model, X, y, cv=cv, scoring="roc_auc")
    means.append(scores.mean())
    stds.append(scores.std())
    labels.append(name)

y_pos = np.arange(len(labels))

fig, ax = plt.subplots(figsize=(6.5, 3.8))
ax.barh(y_pos, means, xerr=stds, color="#2563eb", alpha=0.8)
ax.set_yticks(y_pos)
ax.set_yticklabels(labels)
ax.set_xlabel("ROC-AUC (5-fold mean ± std)")
ax.set_xlim(0.9, 1.0)
ax.set_title("Cross-validation comparison across models")
ax.grid(axis="x", alpha=0.3)
plt.tight_layout()