开始之前，导入numpy、pandas包和数据
import numpy as np
import pandas as pd
df = pd.read_csv('./data/train-left-up.csv')
df.head()
PassengerIdSurvivedPclassName0103Braund, Mr. Owen Harris1211Cumings, Mrs. John Bradley (Florence Briggs Th…2313Heikkinen, Miss. Laina3411Futrelle, Mrs. Jacques Heath (Lily May Peel)4503Allen, Mr. William Henry
2.4 数据的合并
text_left_up = pd.read_csv("./data/train-left-up.csv")
text_left_down = pd.read_csv("./data/train-left-down.csv")
text_right_up = pd.read_csv("./data/train-right-up.csv")
text_right_down = pd.read_csv("./data/train-right-down.csv")
text_left_up.head(2)
PassengerIdSurvivedPclassName0103Braund, Mr. Owen Harris1211Cumings, Mrs. John Bradley (Florence Briggs Th…
text_left_down.head(2)
PassengerIdSurvivedPclassName044002Kvillner, Mr. Johan Henrik Johannesson144112Hart, Mrs. Benjamin (Esther Ada Bloomfield)
text_right_up.head(2)
SexAgeSibSpParchTicketFareCabinEmbarked0male22.010A/5 211717.2500NaNS1female38.010PC 1759971.2833C85C
text_right_down.head(2)
SexAgeSibSpParchTicketFareCabinEmbarked0male31.000C.A. 1872310.50NaNS1female45.011F.C.C. 1352926.25NaNS
list_up1 = [text_left_up,text_right_up]
result_up1 = pd.concat(list_up1,axis=1)
result_up1.head(2)
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked0103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS1211Cumings, Mrs. John Bradley (Florence Briggs Th…female38.010PC 1759971.2833C85C
result_up2 = text_left_up.join(text_right_up)
result_up2.head(2)
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked0103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS1211Cumings, Mrs. John Bradley (Florence Briggs Th…female38.010PC 1759971.2833C85C
result_up3 = pd.merge(text_left_up,text_right_up,left_index=True,right_index=True)
result_up3.head(2)
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked0103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS1211Cumings, Mrs. John Bradley (Florence Briggs Th…female38.010PC 1759971.2833C85C
list_down = [text_left_down,text_right_down]
result_down = pd.concat(list_down1,axis=1)
list = [result_up1,result_down1]
result1 = pd.concat(list,axis=0)
result1.head(2)
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked0103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS1211Cumings, Mrs. John Bradley (Florence Briggs Th…female38.010PC 1759971.2833C85C
result2 = result_up1.append(result_down)
result2.head(2)
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked0103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS1211Cumings, Mrs. John Bradley (Florence Briggs Th…female38.010PC 1759971.2833C85C
result2.to_csv("result.csv")
2.5 换一种角度看数据
text = pd.read_csv('result.csv')
text.head()
Unnamed: 0PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked00103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS11211Cumings, Mrs. John Bradley (Florence Briggs Th…female38.010PC 1759971.2833C85C22313Heikkinen, Miss. Lainafemale26.000STON/O2. 31012827.9250NaNS33411Futrelle, Mrs. Jacques Heath (Lily May Peel)female35.01011380353.1000C123S44503Allen, Mr. William Henrymale35.0003734508.0500NaNS
unit_result=text.stack().head(20)
unit_result
0 Unnamed: 0 0
PassengerId 1
Survived 0
Pclass 3
Name Braund, Mr. Owen Harris
Sex male
Age 22
SibSp 1
Parch 0
Ticket A/5 21171
Fare 7.25
Embarked S
1 Unnamed: 0 1
PassengerId 2
Survived 1
Pclass 1
Name Cumings, Mrs. John Bradley (Florence Briggs Th...
Sex female
Age 38
SibSp 1
dtype: object
unit_result.to_csv('unit_result.csv')
test = pd.read_csv('unit_result.csv')
test
0Unnamed: 00.100PassengerId110Survived020Pclass330NameBraund, Mr. Owen Harris40Sexmale50Age22.060SibSp170Parch080TicketA/5 2117190Fare7.25100EmbarkedS111Unnamed: 01121PassengerId2131Survived1141Pclass1151NameCumings, Mrs. John Bradley (Florence Briggs Th…161Sexfemale171Age38.0181SibSp1
Original: https://blog.csdn.net/qq_46378251/article/details/122832248
Author: 卡拉比丘流形
Title: （五）pandas开源课程学习笔记——数据的合并
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/699178/
转载文章受原作者版权保护。转载请注明原作者出处！