这里我参照的是http://blog.csdn.net/longxinchen_ml/article/details/50629613
这篇博客。
import pandas as pd
import numpy as np
###############读入数据#################
#用pandas载入csv训练数据,并解析第一列为日期格式
train=pd.read_csv('F://python3.5//Machine Learning//tensorflow//bynet//sf_crime_data//train.csv', parse_dates = ['Dates'])
test=pd.read_csv('F://python3.5//Machine Learning//tensorflow//bynet//sf_crime_data//test.csv', parse_dates = ['Dates'])
#print(train[:5])
#################数据和特征处理##########
import pandas as pd
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn import preprocessing
#用LabelEncoder对不同的犯罪类型编号
leCrime = preprocessing.LabelEncoder()
crime = leCrime.fit_transform(train.Category)
#因子化星期几,街区,小时等特征
days = pd.get_dummies(train.DayOfWeek)
district = pd.get_dummies(train.PdDistrict)
hour = train.Dates.dt.hour #######获取日期中的时间
hour = pd.get_dummies(hour)
# print(hour[:20])
#组合特征
trainData = pd.concat([hour, days, district], axis=1)
trainData['crime']=crime
# print(trainData[:20])
#对于测试数据做同样的处理
days = pd.get_dummies(test.DayOfWeek)
district = pd.get_dummies(test.PdDistrict)
hour = test.Dates.dt.hour
hour = pd.get_dummies(hour)
testData = pd.concat([hour, days, district], axis=