#?-*-?coding:?utf-8?-*-
“““
Created?on?Tue?Nov??6?13:29:41?2018

@author:?28770
“““

import?pandas?as?pd

excelFile=r‘ML_data2.xlsx‘
train_df?=?pd.Dataframe（pd.read_excel（excelFilesheet_name=0））??#讀取指定路徑的表格的sheet0為文件并轉(zhuǎn)換到結(jié)構(gòu)框格式
test_df=?pd.Dataframe（pd.read_excel（excelFilesheet_name=1））?#讀取指定路徑的表格的sheet1為文件并轉(zhuǎn)換到結(jié)構(gòu)框格式

‘‘‘
#workClass_loss用于返回train_df中‘workClass‘這一列中的確實(shí)項(xiàng)，缺失數(shù)據(jù)處為True
workClass_loss=train_df[‘workClass‘].isnull（）??#.notnull（）效果與其相反。
‘‘‘

‘‘‘
缺失值填充步驟：（使用缺失值上一行的數(shù)據(jù)填充缺失值處）
對train_df中的缺失值進(jìn)行填充，其中.mode（）是用這一列的眾數(shù)填充，mean（）使用列平均值填充。
其中，由于可能某一列有多個(gè)相同的眾數(shù)，因此.mode（）返回的是一個(gè)series不像mean（）一樣返回
的是一個(gè)數(shù)值，因此，采用.mode（）[0]自動將其填充為第一個(gè)眾數(shù)。
‘‘‘
train_df_fill=train_df.fillna（method=“ffill“）
test_df_fill=test_df.fillna（method=“ffill“）

‘‘‘
刪除重復(fù)的列信息
‘‘‘
train_df_fill=train_df_fill.drop（[‘education‘]1）
test_df_fill=test_df_fill.drop（[‘education‘]1）

‘‘‘
離散特征映射
‘‘‘
salary_mapping={‘<=50K‘:0‘>50K‘:1}
train_df_fill[‘salary‘]=train_df_fill[‘salary‘].map（salary_mapping）
test_df_fill[‘salary‘]=test_df_fill[‘salary‘].map（salary_mapping）

Discrete_attribute=[‘workClass‘‘education‘‘marital_status‘‘occupation‘
????????????????????‘relationship‘‘race‘‘sex‘‘native_country‘]

for?attribute?in?Discrete_attribute:
????attribute_mapping?=?{lab:idx?for?idxlab?in?enumerate（set（train_df_fill[attribute]））}?
????train_df_fill[attribute]?=?train_df_fill[attribute].map（attribute_mapping）??
????test_df_fill[attribute]?=?test_df_fill[attribute].map（attribute_mapping）

‘‘‘
workClass_mapping?=?{lab:idx?for?idxlab?in?enumerate（set（train_df_fill[‘workClass‘]））}?
train_df_fill[‘workClass‘]?=?train_df_fill[‘workClass‘].map（workClass_mapping）??
test_df_fill[‘workClass‘]?=?test_df_fill[‘workClass‘].map（workClass_mapping）?

education_mapping?=?{lab:idx?for?idxlab?in?enumerate（set（train_df_fill[‘education‘]））}?
train_df_fill[‘education‘]?=?train_df_fill[‘education‘].map（education_mapping）??
test_df_fill[‘education‘]?=?test_df_fill[‘education‘].map（education_mapping）?

marital_status_mapping?=?{lab:idx?for?idxlab?in?enumerate（set（train_df_fill[‘marital_status‘]））}?
train_df_fill[‘marital_status‘]?=?train_df_fill[‘marital_status‘].map（marital_status_mapping）??
test_df_fill[‘marital_status‘]?=?test_df_fill[‘marital_status‘].map（marital_status_mapping）?

occupation_mapping?=?{lab:idx?for?idxlab?in?enumerate（set（train_df_fill[‘occupation‘]））}?
train_df_fill[‘occupation‘]?=?train_df_fill[‘occupation‘].map（occupation_mapping）??
test_df_fill[‘occupation‘]?=?test_df_fill[‘occupation‘].map（occupation_mapping）?

relationship_mapping?=?{lab:idx?for?idxlab?in?enumerate（set（train_df_fill[‘relationship‘]））}?
train_df_fill[‘relationship‘]?=?train_df_fill[‘relationship‘].map（relationship_mapping）??
test_df_fill[‘relationship‘]?=?test_df_fill[‘relationship‘].map（relationship_mapping）?

race_mapping?=?{lab:idx?for?idxlab?in?enumerate（set（train_df_fill[‘race‘]））}?
train_df_fill[‘race‘]?=?train_df_fill[‘race‘].map（race_mapping）??
test_df_

?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----

?????文件???????4575??2018-11-13?23:33??Random_Forest\excel_change.py

?????文件???????1589??2018-11-13?20:55??Random_Forest\Matlab_xlr\excel_run.m

?????文件????2677491??2018-11-06?20:50??Random_Forest\Matlab_xlr\ML_data2_trans.xlsx

?????文件????2918697??2018-11-01?21:57??Random_Forest\ML_data2.xlsx

?????文件?????642592??2018-11-08?10:55??Random_Forest\ML_data2_test.csv

?????文件????1285749??2018-11-08?10:55??Random_Forest\ML_data2_train.csv

?????文件????2677491??2018-11-06?20:50??Random_Forest\ML_data2_trans.xlsx

?????文件?????642435??2018-11-08?10:59??Random_Forest\Random?Forest\ML_data2_test.csv

?????文件????1285592??2018-11-08?10:59??Random_Forest\Random?Forest\ML_data2_train.csv

?????文件????2677491??2018-11-06?20:50??Random_Forest\Random?Forest\ML_data2_trans.xlsx

?????文件??????10260??2018-11-14?13:26??Random_Forest\Random?Forest\Random_Forest.py

?????文件?????642435??2018-11-08?10:59??Random_Forest\RF_sklearn\ML_data2_test.csv

?????文件????1285592??2018-11-08?10:59??Random_Forest\RF_sklearn\ML_data2_train.csv

?????文件????2677491??2018-11-06?20:50??Random_Forest\RF_sklearn\ML_data2_trans.xlsx

?????文件???????1259??2018-11-14?14:15??Random_Forest\RF_sklearn\RF_sklearn.py

?????文件????????214??2018-11-14?13:51??Random_Forest\文本描述（首先閱讀）.txt

?????目錄??????????0??2018-12-14?10:51??Random_Forest\Matlab_xlr

?????目錄??????????0??2018-12-14?10:51??Random_Forest\Random?Forest

?????目錄??????????0??2018-12-14?10:51??Random_Forest\RF_sklearn

?????目錄??????????0??2018-12-14?10:51??Random_Forest

-----------?---------??----------?-----??----

?????????????19430953????????????????????20