以商圈为例,进行层次聚类,k-means聚类,T-SNE,PCA降维
data的地址:链接: https://pan.baidu.com/s/1A95Dg1O3ovnkpST1c1EFLw 密码: i3cc
1.读取数据
import pandas as pd
df = pd.read_excel("business_circle.xls")
1.1归一化
for i in range(1,5):
df[i] = (df.iloc[:,i] - df.iloc[:,i].mean())/(df.iloc[:,i].std())
2.层次聚类
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import scipy.cluster.hierarchy as sch #用于进行层次聚类,画层次聚类图的工具包
import scipy.spatial.distance as ssd
from scipy.cluster.vq import vq,kmeans,whiten