from sklearn import __version__ as sklearn_version
from sklearn.datasets import load_iris
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
from sklearn.preprocessing import StandardScaler


iris = load_iris()

X_train, X_test, y_train, y_test = train_test_split(
    iris.data,
    iris.target,
    test_size=0.25,
    stratify=iris.target,
    random_state=42,
)

model = Pipeline(
    steps=[
        ("scale", StandardScaler()),
        ("select", SelectKBest(score_func=f_classif, k=2)),
        ("classify", LogisticRegression(C=0.8, max_iter=300)),
    ]
)

model.fit(X_train, y_train)

predictions = model.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
selected_features = model[:-1].get_feature_names_out(iris.feature_names)
sample_prediction = model.predict(X_test[[0]])[0]
sample_probability = model.predict_proba(X_test[[0]])[0]
probability_map = {
    str(iris.target_names[index]): round(float(probability), 3)
    for index, probability in enumerate(sample_probability)
}

print(f"scikit-learn {sklearn_version}")
print(f"pipeline steps: {list(model.named_steps)}")
print(f"selected features: {selected_features.tolist()}")
print(f"classifier C: {model.named_steps['classify'].C}")
print(f"held-out accuracy: {accuracy:.3f}")
print(f"first prediction: {iris.target_names[sample_prediction]}")
print(f"first probabilities: {probability_map}")