目录
很好的参考博客文章Kmeans与GMM高斯混合模型
KMeans
sklearn.cluster.KMeans
from sklearn.cluster import KMeans
kmeans = KMeans(4, random_state=0)
kmeans.fit(X).predict(X)
简单实用举例
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
import numpy as np
# Generate some data
from sklearn.datasets.samples_generator import make_blobs
X, y_true = make_blobs(n_samples=400, centers=4,
cluster_std=0.60, random_state=0)
X = X[:, ::-1] # flip axes for better plotting
# Plot the data with K Means Labels
from sklearn.cluster import KMeans
kmeans = KMeans(4, random_state=0)
labels = kmeans.fit(X).predict(X)
plt.scatter(X[:, 0], X[:, 1], c=labels, s=40, cmap='viridis')
plt.show()
Kmeans性能评估与可视化
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 # 标准化
def bench_k_means(estimator, name, data):
t0 = time()
estimator.fit(data)
print