kmeans python 多维_使用 k-means 聚类算法对多维属性数据进行分类

数据形式如下：

前期数据整合：

import pandas as pd

import scipy

import scipy.cluster.hierarchy as sch

from scipy.cluster.vq import vq,kmeans,whiten

import numpy as np

import matplotlib.pylab as plt

df1 = pd.read_csv(r"D:\01RiverPro\01DATA\01Headwater\CSV\dem.csv")

df2 = pd.read_csv(r"D:\01RiverPro\01DATA\01Headwater\CSV\ndvi_mean.csv")

df3 = pd.read_csv(r"D:\01RiverPro\01DATA\01Headwater\CSV\pop_mean.csv")

result = pd.merge(df1, df2, how='inner', on=['GRIDCODE'])#取交集

result = pd.merge(result, df3, how='inner', on=['GRIDCODE'])

df=result[['GRIDCODE','dem_mean','ndvi_mean','pop_mean']]

#新增一列其他方法进行的分类标签

ishw = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1