import sklearn
from sklearn.datasets import load_breast_cancer
from sklearn.feature_selection import SelectKBest, f_classif
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline


dataset = load_breast_cancer()
X = dataset.data
y = dataset.target
feature_names = dataset.feature_names

X_train, X_test, y_train, y_test = train_test_split(
    X,
    y,
    test_size=0.25,
    stratify=y,
    random_state=42,
)

selector = SelectKBest(score_func=f_classif, k=8)
classifier = LogisticRegression(max_iter=5000)
model = Pipeline(
    steps=[
        ("select", selector),
        ("classify", classifier),
    ]
)

model.fit(X_train, y_train)

fitted_selector = model.named_steps["select"]
selected_indices = fitted_selector.get_support(indices=True)
selected_names = fitted_selector.get_feature_names_out(feature_names)
scores = fitted_selector.scores_[selected_indices]
ranked_features = sorted(
    zip(selected_indices, selected_names, scores),
    key=lambda item: item[2],
    reverse=True,
)

X_train_selected = fitted_selector.transform(X_train)
X_test_selected = fitted_selector.transform(X_test)
y_pred = model.predict(X_test)

print(f"scikit-learn {sklearn.__version__}")
print(f"original training shape: {X_train.shape}")
print(f"selected training shape: {X_train_selected.shape}")
print(f"selected test shape: {X_test_selected.shape}")
print()
print("selected features by score:")
for index, name, score in ranked_features:
    print(f"{index:2d}  {name:<24} score={score:.2f}")
print()
print(f"held-out accuracy: {accuracy_score(y_test, y_pred):.3f}")