KMeans聚类实战1

iris聚类–已知k值的情况

# 导入第三方模块
import pandas as pd
import numpy as np  
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn import metrics
import seaborn as sns

# 读取iris数据集
iris = pd.read_csv(r'iris.csv')

# 提取出用于建模的数据集X
X = iris.drop(labels = 'Species', axis = 1)
# 构建Kmeans模型
kmeans = KMeans(n_clusters = 3)
kmeans.fit(X)
# 聚类结果标签
X['cluster'] = kmeans.labels_
# 各类频数统计
print(X.cluster.value_counts())


# 三个簇的簇中心
centers = kmeans.cluster_centers_

# 增加一个辅助列，将不同的花种映射到0,1,2三种值，目的方便后面图形的对比
iris['Species_map'] = iris.Species.map({'virginica':0,'setosa':1,'versicolor':2})

# 绘制原始数据三个类别的散点图
sns.lmplot(x = 'Petal_Length', y = 'Petal_Width', hue = 'Species_map', data = iris, markers = ['^','s','o'],
           fit_reg = False, scatter_kws = {'alpha':0.8}, legend_out = False)
# 中文和负号的正常显示
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']
plt.rcParams['axes.unicode_minus'] = False
plt.xlabel('花瓣长度')
plt.ylabel('花瓣宽度')
# 图形显示
plt.show()

结果如下：

cluster
1    61
2    50
0    39
Name: count, dtype: int64