数据重构6-18

数据的合并

1.concat方向链接
2.join
3.merge
4.append

import numpy as np
import pandas as pd

#载入数据
text_left_up = pd.read_csv(‘C:/Users/L/Desktop/da_data/part2/data/train-left-up.csv’)
text_right_up = pd.read_csv(‘C:/Users/L/Desktop/da_data/part2/data/train-right-up.csv’)
text_left_down = pd.read_csv(‘C:/Users/L/Desktop/da_data/part2/data/train-left-down.csv’)
text_right_down = pd.read_csv(‘C:/Users/L/Desktop/da_data/part2/data/train-right-down.csv’)

text_right_down.info()

#横向合并表 axis =1
list_up = [text_left_up,text_right_up]
result_up = pd.concat(list_up,axis = 1)
list_down = [text_left_down,text_right_down]
result_down = pd.concat(list_down,axis = 1)
#纵向合并表 axis = 0
result = pd.concat([result_up,result_down])
result.head()

result.to_csv(‘C:/Users/L/Desktop/da_data/part2/data/result.csv’)

将数据变为Series类型

text = pd.read_csv(‘C:/Users/L/Desktop/da_data/part2/data/result.csv’)
text.head()

unit_result = text.stack().head(20)
unit_result
#text

unit_result.to_csv(‘C:/Users/L/Desktop/da_data/part2/data/unit_result.csv’)

数据聚合与运算

text.head()

#计算男女平均票价
means = text.groupby(‘Sex’)[‘Fare’].mean()

#计算男女存活人数
survived_sex = text[‘Survived’].groupby(text[‘Sex’]).sum()
survived_sex

标准方式更简洁，只用写一次text(dataframe)

#计算客舱不同等级的存活人数
survived_pclass = text.groupby(‘Pclass’)[‘Survived’].sum()
survived_pclass

text.groupby([‘Pclass’,‘Age’])[‘Fare’].mean().head()

result = pd.concat([means,survived_sex],axis = 1)
result.to_csv(‘C:/Users/L/Desktop/da_data/part2/data/sex_fare_survived.csv’)

text[‘Age_band’] = pd.cut(text[‘Age’],5,labels = [‘1’,‘2’,‘3’,‘4’,‘5’])
survived_age_band = text.groupby(‘Age_band’)[‘Survived’].sum()
survived_age_band

#text[‘Age_band’] = pd.cut(text[‘Age’],5,labels = [‘1’,‘2’,‘3’,‘4’,‘5’])
survived_age = text.groupby(‘Age’)[‘Survived’].sum()
survived_age.head()

#找出最大值的年龄段
survived_age[survived_age.values == survived_age.max()]

#计算总人数
_sum = text[‘Survived’].sum()
precetn = survived_age.max()/_sum

print(‘最大存活率：’+str(precetn))