"""
Compare Decision Tree, Naive Bayes (supervised) and K-Means (unsupervised)
on the Iris and Digits datasets using the same metrics.
"""

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.cluster import KMeans
from sklearn.metrics import accuracy_score, classification_report, adjusted_rand_score
import numpy as np


def kmeans_accuracy(X, y, n_classes):
    """
    Map each cluster to its majority true label, then compute accuracy.
    This function handles the cluster→label mapping via majority vote.
    Each cluster gets assigned the most common true label in it.
    """
    kmeans = KMeans(n_clusters=n_classes, init="k-means++", n_init=10, random_state=42)
    kmeans.fit(X)

    labels = np.zeros_like(kmeans.labels_)
    for i in range(n_classes):
        mask = kmeans.labels_ == i
        if mask.sum() > 0:
            labels[mask] = np.bincount(y[mask]).argmax()
    return labels, kmeans


def evaluate(name, dataset, target_names):
    """
    Evaluate unsupervised and supervised ML algorithms on the same dataset, split with the train_test_split function.
    Use the classification_report to evaluate the function.
    """
    print(f"\n{'=' * 60}")
    print(f" {name}")
    print(f"{'=' * 60}")

    X_train, X_test, y_train, y_test = train_test_split(
        dataset.data, dataset.target, test_size=0.3, random_state=42
    )

    # supervised
    for clf_name, clf in [
        ("Decision Tree", DecisionTreeClassifier(random_state=42)),
        ("Naive Bayes", GaussianNB()),
    ]:
        clf.fit(X_train, y_train)
        y_pred = clf.predict(X_test)
        print(f"\n--- {clf_name} ---")
        print(f"Accuracy: {accuracy_score(y_test, y_pred):.3f}")
        print(f"Adj. Rand: {adjusted_rand_score(y_test, y_pred):.3f}")
        print(classification_report(y_test, y_pred, target_names=target_names))

    # unsupervised (evaluated on full dataset)
    n_classes = len(target_names)
    mapped_labels, kmeans = kmeans_accuracy(dataset.data, dataset.target, n_classes)
    print(f"\n--- K-Means (mapped) ---")
    print(f"Accuracy: {accuracy_score(dataset.target, mapped_labels):.3f}")
    print(f"Adj. Rand: {adjusted_rand_score(dataset.target, kmeans.labels_):.3f}")
    print(
        classification_report(dataset.target, mapped_labels, target_names=target_names)
    )


iris = datasets.load_iris()
evaluate("IRIS", iris, list(iris.target_names))

digits = datasets.load_digits()
evaluate("DIGITS", digits, [str(n) for n in digits.target_names])