# 依赖: scikit-learn, numpy
import numpy as np
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler

rng = np.random.default_rng(0)
X = np.vstack([rng.normal(0, 1, (30, 6)), rng.normal(3, 1, (30, 6))])

Xs = StandardScaler().fit_transform(X)      # 少样本情形先做 KMO 与 Bartlett 检验
pca = PCA(n_components=2).fit(Xs)
print('解释方差比 =', pca.explained_variance_ratio_.round(3))

Z = pca.transform(Xs)
labels = KMeans(n_clusters=2, n_init=10, random_state=0).fit_predict(Z)
print('各簇样本数 =', np.bincount(labels))