python对站点类型聚类

有10个excel文件，记录了每个站点每个时间的进出站人数，统计上下班时间段进站日均人数、上下班时间段出站日均人数、非上下班时间段进站日均人数、非上下班时间段出站日均人数 四个变量。使用这4个变量做kmean聚类：

#coding=utf-8
import pandas as pd
from pandas import Series,DataFrame
import random
import numpy as np
from datetime import date
import datetime as dt
from numpy import nan as NA
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingRegressor

import warnings
warnings.filterwarnings("ignore")

def GetExcelData(Path,IDFlag):
#读取excel数据
data=pd.read_excel(Path)

#去掉最后3行，最后3行是总计、统计
data = data[:data.shape[0]-3]
#print(data.columns.values)
#print(data.shape)

data['V1'] = 0
data['V2'] = 0

#统计工作时间、非工作时间人数
data['V1']=data['4:00-5:00']+\
data['5:00-6:00']+\
data['10:00-11:00']+\
data['11:00-12:00']+\
data['12:00-13:00']+\
data['13:00-14:00']+\
data['14:00-15:00']+\
data['15:00-16:00']+\
data['19:00-20:00']+\
data['20:00-21:00']+\
data['21:00-22:00']+\
data['22:00-23:00']+\
data['23:00-24:00']+\
data['24:00-1:00']+\
data['1:00-2:00']+\
data['2:00-3:00']+\
data['3:00-4:00']

data['V2']=data['7:00-8:00']+\
data['8:00-9:00']+\
data['9:00-10:00']+\
data['16:00-17:00']+\
data['17:00-18:00']+\
data['18:00-19:00']

IDNum = data.shape[0]/2
IDNum = int(IDNum)
#print(IDNum)
df1=pd.DataFrame({'ID':np.random.randn(IDNum)})
for i in range(IDNum):
df1.ID[i] = IDFlag+str(i+1)
df1['V1'] = 0#非工作时间进
df1['V2'] = 0#非工作时间出
df1['V3'] = 0#工作时间进
df1['V4'] = 0#工作时间出

for i in range(IDNum):
df1.V1[i] = data.V1[2*i]
df1.V2[i] = data.V1[2*i+1]
df1.V3[i] = data.V2[2*i]
df1.V4[i] = data.V2[2*i+1]

#print(df1)

return df1

data1 = GetExcelData(u'2015xxxx/1.xls','a')
print(data1.shape)
print(data1)

data2 = GetExcelData(u'2015xxxx/2.xls','b')
data3 = GetExcelData(u'2015xxxx/3.xls','c')
data4 = GetExcelData(u'2015xxxx/4.xls','d')
data5 = GetExcelData(u'2015xxxx/5.xls','e')
data6 = GetExcelData(u'2015xxxx/6.xls','f')
data7 = GetExcelData(u'2015xxxx/7.xls','g')
data8 = GetExcelData(u'2015xxxx/8.xls','j')
data9 = GetExcelData(u'2015xxxx/9.xls','i')
data10 = GetExcelData(u'2015xxxx/10.xls','j')

#把10个结果加一起
data = data1
print(data.shape)
#print(data)
data = data.append(data2)
data = data.append(data3)
data = data.append(data4)
data = data.append(data5)
data = data.append(data6)
data = data.append(data7)
data = data.append(data8)
data = data.append(data9)
data = data.append(data10)
data = data.reset_index(drop=True)#重新计算下索引
#print(data.shape)
#print(data)

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

X = data[['V1','V2','V3','V4']].values
estimator = KMeans(n_clusters=3)#构造聚类器
estimator.fit(X)#聚类
label_pred = estimator.labels_ #获取聚类标签

print(label_pred)

最后的聚类结果：

[0 2 0 2 2 1 2 2 1 2 1 0 0 2 2 1 1 2 2 0 0 0 2 1 1 2 0 2 2 2 2 2 2 2 0 2 0

0 0 1 2 2 1 2 1 2 2 0 0 0 2 2 2 1 2 2 0 0 2 0 0 0 0 0 0 0 0 0 0 1 0 0 0 2

2 2 0 0 0 0 0 0 0 0 2 0 2 0 0 0 2 0 2 0 2 0 0 2 2 1 0 0 0 2 1 2 0 2 2 2 0

2 2 0 0 0 0 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 0 0 2

0 0 0 0 0 0 0 0 2]