import numpy as np
import sklearn
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler


feature_names = ["age_years", "annual_income", "monthly_visits"]

X_train = np.array(
    [
        [22, 38000, 4],
        [25, 42000, 5],
        [47, 88000, 7],
        [52, 92000, 8],
        [31, 58000, 6],
        [45, 76000, 7],
        [28, 54000, 5],
        [39, 69000, 6],
    ],
    dtype=float,
)
y_train = np.array([0, 0, 1, 1, 0, 1, 0, 1])

X_holdout = np.array([[34, 62000, 6]], dtype=float)

scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_holdout_scaled = scaler.transform(X_holdout)

model = LogisticRegression(max_iter=1000, random_state=0)
model.fit(X_train_scaled, y_train)
prediction = model.predict(X_holdout_scaled)


def display_zero(value):
    return 0.0 if abs(value) < 5e-12 else value


print(f"scikit-learn {sklearn.__version__}")
print("Scaler learned on training rows only:")
print(f"- rows_seen: {int(scaler.n_samples_seen_)}")
print(
    "- mean_: "
    + ", ".join(
        f"{name}={value:.2f}" for name, value in zip(feature_names, scaler.mean_)
    )
)
print(
    "- scale_: "
    + ", ".join(
        f"{name}={value:.2f}" for name, value in zip(feature_names, scaler.scale_)
    )
)
print()
print("Scaled training columns:")
for name, mean, std in zip(
    feature_names, X_train_scaled.mean(axis=0), X_train_scaled.std(axis=0)
):
    print(f"- {name}: mean={display_zero(mean):.6f}, std={std:.6f}")
print()
print("Scaled holdout row:")
for name, value in zip(feature_names, X_holdout_scaled[0]):
    print(f"- {name}: {value:.3f}")
print()
print(f"Holdout prediction from scaled features: {prediction.tolist()}")