Machine Learning lab

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_breast_cancer
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler

data = load_breast_cancer()
X = data.data  # Features

scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

kmeans = KMeans(n_clusters=2, random_state=42, n_init=10)
clusters = kmeans.fit_predict(X_scaled)

pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_scaled)

centroids_original = kmeans.cluster_centers_
centroids_pca = pca.transform(centroids_original)  # Convert centroids to 2D

plt.figure(figsize=(8, 6))

for cluster, color in zip(range(2), ["red", "blue"]):
    plt.scatter(X_pca[clusters == cluster, 0], X_pca[clusters == cluster, 1],
                color=color, alpha=0.6, edgecolor="k", label=f"Cluster {cluster}")

plt.scatter(centroids_pca[:, 0], centroids_pca[:, 1],
            s=250, c='black', marker='X', label="Centroids")

plt.legend(loc="upper right")

plt.title("K-Means Clustering on Wisconsin Breast Cancer Dataset")
plt.xlabel("Principal Component 1")
plt.ylabel("Principal Component 2")
plt.show()