K-means

from sklearn.cluster import KMeans, MiniBatchKMeans
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
import numpy as np

# 테스트 데이터 생성
X, y_true = make_blobs(n_samples=1000, centers=4, cluster_std=0.6, random_state=42)

# 데이터 정규화
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Elbow Method로 최적 K 찾기
def find_optimal_k(X, max_k=10):
    inertias = []
    for k in range(1, max_k + 1):
        kmeans = KMeans(n_clusters=k, random_state=42, n_init='auto')
        kmeans.fit(X)
        inertias.append(kmeans.inertia_)

    # 기울기 변화가 가장 큰 지점 찾기
    diffs = np.diff(inertias)
    second_diffs = np.diff(diffs)
    optimal_k = np.argmax(np.abs(second_diffs)) + 2
    return optimal_k, inertias

optimal_k, inertias = find_optimal_k(X_scaled)
print(f"추천 K: {optimal_k}")

# 대용량 데이터용 MiniBatchKMeans
kmeans = MiniBatchKMeans(
    n_clusters=optimal_k,
    batch_size=256,     # 미니배치 크기
    random_state=42,
    n_init='auto'
)
labels = kmeans.fit_predict(X_scaled)

# 결과 시각화
plt.figure(figsize=(10, 4))
plt.subplot(1, 2, 1)
plt.plot(range(1, 11), inertias, 'bo-')
plt.axvline(x=optimal_k, color='r', linestyle='--', label=f'K={optimal_k}')
plt.xlabel('K'); plt.ylabel('Inertia'); plt.title('Elbow Method')
plt.subplot(1, 2, 2)
plt.scatter(X_scaled[:, 0], X_scaled[:, 1], c=labels, cmap='viridis', alpha=0.6)
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1],
            c='red', marker='X', s=200, label='Centroids')
plt.title('K-means Clustering'); plt.legend()
plt.tight_layout(); plt.show()