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, 1, 1, 1, 1, 1, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
df['Headwater_label'] = ishw
#转为array
dataset = df.values
points = dataset [:,1:4]#第2列到第4属性列
ishw_label = dataset[:,-1]
#print("points:\n",points)
# k-means聚类
#将原始数据做归一化处理
data=whiten(points)
#使用kmeans函数进行聚类,输入第一维为数据,第二维为聚类个数k.
#有些时候我们可能不知道最终究竟聚成多少类,一个办法是用层次聚类的结果进行初始化.当然也可以直接输入某个数值.
#k-means最后输出的结果其实是两维的,第一维是聚类中心,第二维是损失distortion,我们在这里只取第一维,所以最后有个[0]
#centroid = kmeans(data,max(cluster))[0]
centroid = kmeans(data,2)[0]#分为2类
print(centroid)#输出中心
#使用vq函数根据聚类中心对所有数据进行分类,vq的输出也是两维的,[0]表示的是所有数据的label
label=vq(data,centroid)[0]
label
#输出两类的数量
num = [0,0]
for i in label:
if(i == 0):
num[0] = num[0] + 1
else:
num[1] = num[1] + 1
print('num =',num)
#输出符合预期的比例等
print("Final clustering by k-means:\n",label)
result = np.subtract(label,ishw_label)
print("result:\n",result)
count = [0,0]
for i in result:
if(i == 0):
count[0] = count[0] + 1
else:
count[1] = count[1] + 1
print(count)
print(float(count[0])/(count[0]+count[1]))
