import pandas as pd
import numpy as np

#用pandas載入csv訓練數據，並解析第一列為日期格式
train=pd.read_csv(‘../input/train.csv‘, parse_dates = [‘Dates‘])
test=pd.read_csv(‘../input/test.csv‘, parse_dates = [‘Dates‘])
train

import pandas as pd
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn import
 
 preprocessing

#用LabelEncoder對不同的犯罪類型編號
leCrime = preprocessing.LabelEncoder()
crime = leCrime.fit_transform(train.Category)

#因子化星期幾，街區，小時等特征
days = pd.get_dummies(train.DayOfWeek)
district = pd.get_dummies(train.PdDistrict)
hour = train.Dates.dt.hour
hour = pd.get_dummies(hour) 

#組合特征
trainData = pd.concat([hour, days, district], axis=1)
trainData[
 
‘crime‘]=crime

#對於測試數據做同樣的處理
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=1)
trainData

from sklearn.cross_validation import train_test_split
from sklearn import
 
 preprocessing
from sklearn.metrics import log_loss
from sklearn.naive_bayes import BernoulliNB
from sklearn.linear_model import LogisticRegression
import time

# 只取星期幾和街區作為分類器輸入特征
features = [‘Monday‘, ‘Tuesday‘, ‘Wednesday‘, ‘Thursday‘, ‘Friday‘, ‘Saturday‘, ‘Sunday‘, ‘BAYVIEW‘, ‘CENTRAL‘, ‘INGLESIDE‘, ‘MISSION‘,
 ‘NORTHERN‘, ‘PARK‘, ‘RICHMOND‘, ‘SOUTHERN‘, ‘TARAVAL‘, ‘TENDERLOIN‘]

# 分割訓練集(3/5)和測試集(2/5)
training, validation = train_test_split(trainData, train_size=.60)

# 樸素貝葉斯建模，計算log_loss
model = BernoulliNB()
nbStart = time.time()
model.fit(training[features], training[‘crime‘])
nbCostTime = time.time() - nbStart
predicted = np.array(model.predict_proba(validation[features]))
print("樸素貝葉斯建模耗時 %f 秒" %(nbCostTime))
print("樸素貝葉斯log損失為 %f" %(log_loss(validation[‘crime‘], predicted)))

#邏輯回歸建模，計算log_loss
model = LogisticRegression(C=.01)
lrStart= time.time()
model.fit(training[features], training[‘crime‘])
lrCostTime = time.time() - lrStart
predicted = np.array(model.predict_proba(validation[features]))
log_loss(validation[‘crime‘], predicted)
print("邏輯回歸建模耗時 %f 秒" %(lrCostTime))
print("邏輯回歸log損失為 %f" %(log_loss(validation[‘crime‘], predicted))) 

Kaggle比賽之『舊金山犯罪分類預測』 demo