KMeans算法实践

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans

font = {
   'family':'SimHei', 'size':'20'}
plt.rc('font', **font)

df = pd.read_csv('data.csv')
df.head()

	CustomerID	Gender	Age	Annual Income (k$)	Spending Score (1-100)
0	1	Male	19	15	39
1	2	Male	21	15	81
2	3	Female	20	16	6
3	4	Female	23	16	77
4	5	Female	31	17	40

df.columns

Index(['CustomerID', 'Gender', 'Age', 'Annual Income (k$)',
       'Spending Score (1-100)'],
      dtype='object')

df.columns = ['用户ID', '性别', '年龄', '年收入', '支出']
df.head()

	用户ID	性别	年龄	年收入	支出
0	1	Male	19	15	39
1	2	Male	21	15	81
2	3	Female	20	16	6
3	4	Female	23	16	77
4	5	Female	31	17	40

df.isnull().sum()

用户ID    0
性别      0
年龄      0
年收入     0
支出      0
dtype: int64

df.describe()

	用户ID	年龄	年收入	支出
count	200.000000	200.000000	200.000000	200.000000
mean	100.500000	38.850000	60.560000	50.200000
std	57.879185	13.969007	26.264721	25.823522
min	1.000000	18.000000	15.000000	1.000000
25%	50.750000	28.750000	41.500000	34.750000
50%	100.500000	36.000000	61.500000	50.000000
75%	150.250000	49.000000	78.000000	73.000000
max	200.000000	70.000000	137.000000	99.000000

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 200 entries, 0 to 199
Data columns (total 5 columns):
用户ID    200 non-null int64
性别      200 non-null object
年龄      200 non-null int64
年收入     200 non-null int64
支出      200 non-null int64
dtypes: int64(4), object(1)
memory usage: 7.9+ KB

查看数据分布

fig = plt.figure(figsize=(20,8))
fig.suptitle('各指标数据分布')

# 第一个子图
ax1 = fig.add_subplot(221)
# 查看年龄分布
ax1.hist(df['年龄'])
ax1.title.set_text('年龄分布')

# 第二个子图
ax2 = fig.add_subplot(222)
# 查看性别比例
male, female = (df['性别'] == 'Male').sum(), (df