精通特征工程

非线性特征化与

k

-

均值模型堆叠

｜

97

例

7-1

　

生成

k

-

均值示例的代码

>>> import numpy as np

>>> from sklearn.cluster import KMeans

>>> from sklearn.datasets import make_blobs

>>> import matplotlib.pyplot as plt

>>> n_data = 1000

>>> seed = 1

>>> n_clusters = 4

# 生成符合高斯随机分布的点团，并运行k-均值算法

>>> blobs, blob_labels = make_blobs(n_samples=n_data, n_features=2,

... centers=n_centers, random_state=seed)

>>> clusters_blob = KMeans(n_clusters=n_centers, random_state=seed).fit_

predict(blobs)

# 生成完全随机的数据，并运行k-均值算法

>>> uniform = np.random.rand(n_data, 2)

>>> clusters_uniform = KMeans(n_clusters=n_clusters,

... random_state=seed).fit_predict(uniform)

# 对结果进行可视化的Matplotlib代码

>>> figure ...