立即學習:https://edu.csdn.net/course/play/6861/326776?utm_source=blogtoedu
數據的合併與連接
數據合併
《從零開始學python數據分析與挖掘》
import pandas as pd
df1 = pd.DataFrame({'name':['張三','王五','李四'],'age':[12,13,43],'gender':['男','女','男']})
df2 = pd.DataFrame({'name':['二哈','二蛋','二丫'],'age':[23,43,23],'gender':['女','女','男']})
df1
df2
pd.concat([df1,df2],keys=['df1','df2']).reset_index().drop(labels='level_1',axis=1).rename(columns={'level_0':'f'})
df2 = pd.DataFrame({'Name':['狗娃','牛蛙'],'age':[21,32],'gender':['女','女']})
df2
pd.concat([df1,df2])#name和Name 不能合併 所以合併的時候變量名稱要一致
df2.rename(columns={'Name':'name'},inplace=True)
pd.concat([df1,df2])#name和Name 不能合併 所以合併的時候變量名稱要一致
數據的鏈接
import pandas as pd
df3 = pd.DataFrame({'id':[1,2,3,4,5],'name':['張三','李四','王二','王二麻子','趙五'],'age':[21,32,44,2,43],'gender':['女','男','女','男','男']})
df4 = pd.DataFrame({'Id':[1,2,2,4,4,4,5],'score':[21,32,44,33,22,32,33],'kemu':['科目1','科目1','科目2','科目1','科目2','科目3','科目1']})
df5 = pd.DataFrame({'id':[1,3,5],'name':['張三','王二','趙五'],'income':[21,32,44]})
print(df3)
print(df4)
print(df5)
#先鏈接df3和df4
merge1 = pd.merge(left=df3,right=df4,how='left',left_on='id',right_on='Id')
merge1
#再鏈接和df5
merge2 = pd.merge(left=merge1,right=df5,how='left')
merge2