使用MiniBatchKMeans加速kmenas聚类算法的计算
MiniBatchKMeans batch_size控制每个批次中样本的数量
# 加速keans算法的计算
from sklearn import datasets
from sklearn.preprocessing import StandardScaler
from sklearn.cluster import MiniBatchKMeans
iris = datasets.load_iris()
features = iris.data
scaler = StandardScaler()
features_std = scaler.fit_transform(features)
# MiniBatchKMeans batch_size控制每个批次中样本的数量
cluster = MiniBatchKMeans(n_clusters=3, random_state=0, batch_size=100)
model = cluster.fit(features_std)
model.labels_
array([1, 1, 1, 1, 1, 1, 1, 1