from collections import Counter

import numpy as np
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import balanced_accuracy_score, classification_report
from sklearn.model_selection import train_test_split
from sklearn.utils.class_weight import compute_class_weight


X, y = make_classification(
    n_samples=1200,
    n_features=6,
    n_informative=4,
    n_redundant=0,
    weights=[0.92, 0.08],
    class_sep=0.65,
    flip_y=0.02,
    random_state=42,
)

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

classes = np.unique(y_train)
class_weights = compute_class_weight(
    class_weight="balanced",
    classes=classes,
    y=y_train,
)
weight_map = {
    int(label): round(float(weight), 3)
    for label, weight in zip(classes, class_weights)
}
class_counts = {
    int(label): int(count)
    for label, count in sorted(Counter(y_train).items())
}

print(f"Training class counts: {class_counts}")
print(f"Balanced class weights: {weight_map}")

models = {
    "unweighted": LogisticRegression(max_iter=1000, random_state=42),
    "balanced": LogisticRegression(
        class_weight="balanced",
        max_iter=1000,
        random_state=42,
    ),
}

for name, model in models.items():
    model.fit(X_train, y_train)
    predictions = model.predict(X_test)
    score = balanced_accuracy_score(y_test, predictions)
    print()
    print(f"{name} classifier")
    print(f"class_weight: {model.get_params()['class_weight']}")
    print(f"balanced accuracy: {score:.3f}")
    print(
        classification_report(
            y_test,
            predictions,
            target_names=["majority 0", "minority 1"],
            digits=3,
            zero_division=0,
        )
    )