https://www.kaggle.com/kushal1996/customer-segmentation-k-means-analysis/notebook
導入包
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly as py
import plotly.graph_objs as go
from sklearn.cluster import KMeans
import warnings
import os
warnings.filterwarnings("ignore")
py.offline.init_notebook_mode(connected = True)
EDA
df = pd.read_csv(r'../聚類/Mall_Customers.csv')
df.head()
CustomerID | Gender | Age | Annual Income (k$) | Spending Score (1-100) | |
---|---|---|---|---|---|
0 | 1 | Male | 19 | 15 | 39 |
1 | 2 | Male | 21 | 15 | 81 |
2 | 3 | Female | 20 | 16 | 6 |
3 | 4 | Female | 23 | 16 | 77 |
4 | 5 | Female | 31 | 17 | 40 |
df.shape
(200, 5)
df.describe()
CustomerID | Age | Annual Income (k$) | Spending Score (1-100) | |
---|---|---|---|---|
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.dtypes
CustomerID int64
Gender object
Age int64
Annual Income (k$) int64
Spending Score (1-100) int64
dtype: object
df.isnull().sum()
CustomerID 0
Gender 0
Age 0
Annual Income (k$) 0
Spending Score (1-100) 0
dtype: int64
可視化
plt.style.use('fivethirtyeight')
柱狀圖
plt.figure(1 , figsize = (15 , 6))
n = 0
for x in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']:
n += 1
plt.subplot(1 , 3 , n)
plt.subplots_adjust(hspace =0.5 , wspace = 0.5)
sns.distplot(df[x] , bins = 20)
plt.title('Distplot of {}'.format(x))
plt.show()
性別比例
plt.figure(1 , figsize = (15 , 5))
sns.countplot(y = 'Gender' , data = df)
plt.show()
各連續變量相關圖
plt.figure(1 , figsize = (15 , 7))
n = 0
for x in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']:
for y in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']:
n += 1
plt.subplot(3 , 3 , n)
plt.subplots_adjust(hspace = 0.5 , wspace = 0.5)
sns.regplot(x = x , y = y , data = df)
plt.ylabel(y.split()[0]+' '+y.split()[1] if len(y.split()) > 1 else y )
plt.show()
plt.figure(1 , figsize = (15 , 6))
for gender in ['Male' , 'Female']:
plt.scatter(x = 'Age' , y = 'Annual Income (k$)' , data = df[df['Gender'] == gender] ,
s = 200 , alpha = 0.5 , label = gender)
plt.xlabel('Age'), plt.ylabel('Annual Income (k$)')
plt.title('Age vs Annual Income w.r.t Gender')
plt.legend()
plt.show()
plt.figure(1 , figsize = (15 , 6))
for gender in ['Male' , 'Female']:
plt.scatter(x = 'Annual Income (k$)',y = 'Spending Score (1-100)' ,
data = df[df['Gender'] == gender] ,s = 200 , alpha = 0.5 , label = gender)
plt.xlabel('Annual Income (k$)'), plt.ylabel('Spending Score (1-100)')
plt.title('Annual Income vs Spending Score w.r.t Gender')
plt.legend()
plt.show()
根據性別劃分年齡,年收入,消費得分
plt.figure(1 , figsize = (15 , 7))
n = 0
for cols in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']:
n += 1
plt.subplot(1 , 3 , n)
plt.subplots_adjust(hspace = 0.5 , wspace = 0.5)
sns.violinplot(x = cols , y = 'Gender' , data = df , palette = 'vlag')
sns.swarmplot(x = cols , y = 'Gender' , data = df)
plt.ylabel('Gender' if n == 1 else '')
plt.title('Boxplots & Swarmplots' if n == 2 else '')
plt.show()
K- means
k-means局部最優解的質量主要由初始值確定。1.初始類中心 2.類別個數
1. 用Age 和 Spending Score來劃分聚類
KMeans參數詳解:https://www.cnblogs.com/niniya/p/8784947.html
init:初始值選擇方式,可選值:‘k-means++’(用均值)、‘random’(隨機)、an ndarray(指定一個數組),默認爲’k-means++’。
k值的選擇方法:基於簇內誤差平方和,使用肘方法確定簇的最佳數量,肘方法的基本理念就是找出聚類偏差驟增的k值,通過畫出不同k值對應的聚類偏差圖,可以清楚看出。
X1 = df[['Age' , 'Spending Score (1-100)']].iloc[: , :].values
inertia = []
for n in range(1 , 11):
algorithm = (KMeans(n_clusters = n ,init='k-means++', n_init = 10 ,max_iter=300,
tol=0.0001, random_state= 111 , algorithm='elkan') )
algorithm.fit(X1)
inertia.append(algorithm.inertia_)
根據Inertia選擇聚類的類別數n
plt.figure(1 , figsize = (15 ,6))
plt.plot(np.arange(1 , 11) , inertia , 'o')
plt.plot(np.arange(1 , 11) , inertia , '-' , alpha = 0.5)
plt.xlabel('Number of Clusters') , plt.ylabel('Inertia')
plt.show()
algorithm = (KMeans(n_clusters = 4 ,init='k-means++', n_init = 10 ,max_iter=300,
tol=0.0001, random_state= 111 , algorithm='elkan') )
algorithm.fit(X1)
labels1 = algorithm.labels_
centroids1 = algorithm.cluster_centers_
labels1 #四個類別,分別用0,1,2,3表示
array([3, 1, 2, 1, 3, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 3, 3, 2, 1, 3, 1,
2, 1, 2, 1, 2, 3, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 0, 1, 0, 3,
2, 3, 0, 3, 3, 3, 0, 3, 3, 0, 0, 0, 0, 0, 3, 0, 0, 3, 0, 0, 0, 3,
0, 0, 3, 3, 0, 0, 0, 0, 0, 3, 0, 3, 3, 0, 0, 3, 0, 0, 3, 0, 0, 3,
3, 0, 0, 3, 0, 3, 3, 3, 0, 3, 0, 3, 3, 0, 0, 3, 0, 3, 0, 0, 0, 0,
0, 3, 3, 3, 3, 3, 0, 0, 0, 0, 3, 3, 3, 1, 3, 1, 0, 1, 2, 1, 2, 1,
3, 1, 2, 1, 2, 1, 2, 1, 2, 1, 3, 1, 2, 1, 0, 1, 2, 1, 2, 1, 2, 1,
2, 1, 2, 1, 2, 1, 0, 1, 2, 1, 2, 1, 2, 1, 2, 3, 2, 1, 2, 1, 2, 1,
2, 1, 2, 1, 2, 1, 2, 1, 3, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1,
2, 1])
centroids1 #類別中心,也就是最後不再迭代的中心
array([[55.70833333, 48.22916667],
[30.1754386 , 82.35087719],
[43.29166667, 15.02083333],
[27.61702128, 49.14893617]])
h = 0.02
x_min, x_max = X1[:, 0].min() - 1, X1[:, 0].max() + 1
y_min, y_max = X1[:, 1].min() - 1, X1[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
Z = algorithm.predict(np.c_[xx.ravel(), yy.ravel()])
Z
array([[2, 2, 2, ..., 2, 2, 2],
[2, 2, 2, ..., 2, 2, 2],
[2, 2, 2, ..., 2, 2, 2],
...,
[1, 1, 1, ..., 1, 1, 1],
[1, 1, 1, ..., 1, 1, 1],
[1, 1, 1, ..., 1, 1, 1]])
plt.figure(1 , figsize = (15 , 7) )
plt.clf()
Z = Z.reshape(xx.shape)
plt.imshow(Z , interpolation='nearest',
extent=(xx.min(), xx.max(), yy.min(), yy.max()),
cmap = plt.cm.Pastel2, aspect = 'auto', origin='lower')
plt.scatter( x = 'Age' ,y = 'Spending Score (1-100)' , data = df , c = labels1 ,
s = 200 )
plt.scatter(x = centroids1[: , 0] , y = centroids1[: , 1] , s = 300 , c = 'red' , alpha = 0.5)
plt.ylabel('Spending Score (1-100)') , plt.xlabel('Age')
plt.show()
2. 根據 Annual Income和Spending Score來劃分聚類
'''Annual Income and spending Score'''
X2 = df[['Annual Income (k$)' , 'Spending Score (1-100)']].iloc[: , :].values
inertia = []
for n in range(1 , 11):
algorithm = (KMeans(n_clusters = n ,init='k-means++', n_init = 10 ,max_iter=300,
tol=0.0001, random_state= 111 , algorithm='elkan') )
algorithm.fit(X2)
inertia.append(algorithm.inertia_)
plt.figure(1 , figsize = (15 ,6))
plt.plot(np.arange(1 , 11) , inertia , 'o')
plt.plot(np.arange(1 , 11) , inertia , '-' , alpha = 0.5)
plt.xlabel('Number of Clusters') , plt.ylabel('Inertia')
plt.show()
algorithm = (KMeans(n_clusters = 5 ,init='k-means++', n_init = 10 ,max_iter=300,
tol=0.0001, random_state= 111 , algorithm='elkan') )
algorithm.fit(X2)
labels2 = algorithm.labels_
centroids2 = algorithm.cluster_centers_
np.meshgrid:https://blog.csdn.net/lllxxq141592654/article/details/81532855
np.arange:ttps://blog.csdn.net/lanchunhui/article/details/49493633
h = 0.02
x_min, x_max = X2[:, 0].min() - 1, X2[:, 0].max() + 1
y_min, y_max = X2[:, 1].min() - 1, X2[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
Z2 = algorithm.predict(np.c_[xx.ravel(), yy.ravel()])
plt.figure(1 , figsize = (15 , 7) )
plt.clf()
Z2 = Z2.reshape(xx.shape)
plt.imshow(Z2 , interpolation='nearest',
extent=(xx.min(), xx.max(), yy.min(), yy.max()),
cmap = plt.cm.Pastel2, aspect = 'auto', origin='lower')
plt.scatter( x = 'Annual Income (k$)' ,y = 'Spending Score (1-100)' , data = df , c = labels2 ,
s = 200 )
plt.scatter(x = centroids2[: , 0] , y = centroids2[: , 1] , s = 300 , c = 'red' , alpha = 0.5)
plt.ylabel('Spending Score (1-100)') , plt.xlabel('Annual Income (k$)')
plt.show()