import pandas
from pandas import read_csv

data=read_csv(
    "C:\\Users\\Jw\\Desktop\\python_work\\Python数据挖掘实战课程课件\\4.4\\data.csv",
    encoding="utf-8")

data=data.dropna()

dummyColumns=()

data.shape

#首先处理字符类型和大小无关的字段
dummyColumns=[
    ‘Gender‘,‘Home Ownership‘,
    ‘Internet Connection‘, ‘Marital Status‘,
    ‘Movie Selector‘, ‘Prerec Format‘, ‘TV Signal‘]
    
for column in dummyColumns:
    data[column]=data[column].astype(‘category‘)
    

dummiesData=pandas.get_dummies(
        data,
        columns=dummyColumns,
        prefix=dummyColumns,
        prefix_sep=" ",  #列名和属性值之间的分割符号
        drop_first=True)  #根据特征列建模，为避免模型共轭，只选取一列

data.Gender.unique()   #去重

dummiesData.columns   #获取所有列

#有可比性，可进行大小比较
educationLevelDict={
    ‘Post-Doc‘: 9,
    ‘Doctorate‘: 8,
    ‘Master\‘s Degree‘: 7,
    ‘Bachelor\‘s Degree‘: 6,
    ‘Associate\‘s Degree‘: 5,
    ‘Some College‘: 4,
    ‘Trade School‘: 3,
    ‘High School‘: 2,
    ‘Grade School‘: 1
    }
    
#调用map一一映射，将离散型数据转化为数值型数据
dummiesData["Education Level Map"]=dummiesData[‘Education Level‘].map(educationLevelDict)


freqMap={
    ‘Never‘:0,
    ‘Rarely‘: 1,
    ‘Monthly‘: 2,
    ‘Weekly‘: 3,
    ‘Daily‘: 4}
    
dummiesData[‘PPV Freq Map‘]=dummiesData[‘PPV Freq‘].map(freqMap)
dummiesData[‘Theater Freq Map‘] = dummiesData[‘Theater Freq‘].map(freqMap)
dummiesData[‘TV Movie Freq Map‘] = dummiesData[‘TV Movie Freq‘].map(freqMap)
dummiesData[‘Prerec Buying Freq Map‘] = dummiesData[‘Prerec Buying Freq‘].map(freqMap)
dummiesData[‘Prerec Renting Freq Map‘] = dummiesData[‘Prerec Renting Freq‘].map(freqMap)
dummiesData[‘Prerec Viewing Freq Map‘] = dummiesData[‘Prerec Viewing Freq‘].map(freqMap)

 1 #选取自变量和因变量
 2 dummiesData.columns
 3 
 4 #先选取所有列，然后一一查看选择
 5 dummiesSelect = [
 6     ‘Age‘, ‘Num Bathrooms‘, ‘Num Bedrooms‘, ‘Num Cars‘, ‘Num Children‘, ‘Num TVs‘, 
 7     ‘Education Level Map‘, ‘PPV Freq Map‘, ‘Theater Freq Map‘, ‘TV Movie Freq Map‘, 
 8     ‘Prerec Buying Freq Map‘, ‘Prerec Renting Freq Map‘, ‘Prerec Viewing Freq Map‘, 
 9     ‘Gender Male‘,
10     ‘Internet Connection DSL‘, ‘Internet Connection Dial-Up‘, 
11     ‘Internet Connection IDSN‘, ‘Internet Connection No Internet Connection‘,
12     ‘Internet Connection Other‘, 
13     ‘Marital Status Married‘, ‘Marital Status Never Married‘, 
14     ‘Marital Status Other‘, ‘Marital Status Separated‘, 
15     ‘Movie Selector Me‘, ‘Movie Selector Other‘, ‘Movie Selector Spouse/Partner‘, 
16     ‘Prerec Format DVD‘, ‘Prerec Format Laserdisk‘, ‘Prerec Format Other‘, 
17     ‘Prerec Format VHS‘, ‘Prerec Format Video CD‘, 
18     ‘TV Signal Analog antennae‘, ‘TV Signal Cable‘, 
19     ‘TV Signal Digital Satellite‘, ‘TV Signal Don\‘t watch TV‘
20 ]
21 
22 inputData=dummiesData[dummiesSelect]   #自变量
23 
24 
25 outputData=dummiesData[["Home Ownership Rent"]]   #因变量

1 #建模、训练
2 from sklearn import linear_model
3 
4 lrModel=linear_model.LogisticRegression()
5 
6 lrModel.fit(inputData,outputData)
7 
8 lrModel.score(inputData,outputData)

 1 #因为逻辑回归所用的参数是经过虚拟变量处理过的，需对新的数据进行预测，要先处理新数据
 2 newData=read_csv(
 3     "C:\\Users\\Jw\\Desktop\\python_work\\Python数据挖掘实战课程课件\\4.4\\newData.csv",
 4     encoding="utf-8")
 5 
 6 for column in dummyColumns:
 7     newData[column]=newData[column].astype(
 8         "category",
 9         categories=data[column].cat.categories)
10     
11 newData=newData.dropna()
12 
13 
14 newData[‘Education Level Map‘] = newData[‘Education Level‘].map(educationLevelDict)
15 newData[‘PPV Freq Map‘] = newData[‘PPV Freq‘].map(freqMap)
16 newData[‘Theater Freq Map‘] = newData[‘Theater Freq‘].map(freqMap)
17 newData[‘TV Movie Freq Map‘] = newData[‘TV Movie Freq‘].map(freqMap)
18 newData[‘Prerec Buying Freq Map‘] = newData[‘Prerec Buying Freq‘].map(freqMap)
19 newData[‘Prerec Renting Freq Map‘] = newData[‘Prerec Renting Freq‘].map(freqMap)
20 newData[‘Prerec Viewing Freq Map‘] = newData[‘Prerec Viewing Freq‘].map(freqMap)
21 
22 
23 dummiesNewData=pandas.get_dummies (
24         newData,
25         columns=dummyColumns,
26         prefix=dummyColumns,
27         prefix_sep=" ",
28         drop_first=True)
29 
30 inputNewData = dummiesNewData[dummiesSelect]
31 
32 lrModel.predict(inputData)