10、数字数据集上的K-均值聚类（PCA约简数据）
from time import time
import numpy as np
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import KMeans
from sklearn.datasets import load_digits
from sklearn.decomposition import PCA
from sklearn.preprocessing import scale
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
np.random.seed(42)
X_digits, y_digits = load_digits(return_X_y=True)
data = scale(X_digits)
n_samples, n_features = data.shape
n_digits = len(np.unique(y_digits))
labels = y_digits
sample_size = 300
print("n_digits: %d, \t n_samples %d, \t n_features %d"
% (n_digits, n_samples, n_features))
print(82 * '_')
print('init\t\ttime\tinertia\thomo\tcompl\tv-meas\tARI\tAMI\tsilhouette')
def bench_k_means(estimator, name, data):
t0 = time()
estimator.fit(data)
print('%-9s\t%.2fs\t%i\t%.3f\t%.3f\t%.3f\t%.3f\t%.3f\t%.3f'
% (name, (time() - t0), estimator.inertia_,
metrics.homogeneity_score(labels, estimator.labels_),
metrics.completeness_score(labels, estimator.labels_),
metrics.v_measure_score(labels, estimator.labels_),
metrics.adjusted_rand_score(labels, estimator.labels_),
metrics.adjusted_mutual_info_score(labels, estimator.labels_),
metrics.silhouette_score(data, estimator.labels_,
metric='euclidean',
sample_size=sample_size)))
bench_k_means(KMeans(init='k-means++', n_clusters=n_digits, n_init=10),
name="k-means++", data=data)
bench_k_means(KMeans(init='random', n_clusters=n_digits, n_init=10),
name="random", data=data)
# 运行kmeans算法n_init=1只一次
pca = PCA(n_components=n_digits).fit(data)
bench_k_means(KMeans(init=pca.components_, n_clusters=n_digits, n_init=1),
name="PCA-based",
data=data)
print(82 * '_')
# 在PCA缩减数据上可视化结果
reduced_data = PCA(n_components=2).fit_transform(data)
kmeans = KMeans(init='k-means++', n_clusters=n_digits, n_init=10)
kmeans.fit(reduced_data)
# 网格的步长减少，以增加VQ的质量。
h = .02 # 网格中的点[x_min,x_max]x[y_min,y_max]。
# 绘制决策边界并且配色
x_min, x_max = reduced_data[:, 0].min() - 1, reduced_data[:, 0].max() + 1
y_min, y_max = reduced_data[:, 1].min() - 1, reduced_data[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
# 获取网格中每个点的标签。使用上次训练的模型。
Z = kmeans.predict(np.c_[xx.ravel(), yy.ravel()])
# 将结果放入彩色图中
Z = Z.reshape(xx.shape)
plt.figure(1)
plt.clf()
plt.imshow(Z, interpolation='nearest',
extent=(xx.min(), xx.max(), yy.min(), yy.max()),
cmap=plt.cm.Paired,
aspect='auto', origin='lower')
plt.plot(reduced_data[:, 0], reduced_data[:, 1], 'k.', markersize=2)
# 用白色X画出中心体
centroids = kmeans.cluster_centers_
plt.scatter(centroids[:, 0], centroids[:, 1],
marker='x', s=169, linewidths=3,
color='w', zorder=10)
plt.title('数字数据集上的K-均值聚类（PCA约简数据）')
plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
plt.xticks(())
plt.yticks(())
plt.show()