import pandas as pd
# given
df1 = pd.DataFrame({'Name':['John','Mike','Smith','Wale','Marry','Tom','Menda','Bolt','Yuswa',],
    'Age':[23,45,12,34,27,44,28,39,40]})
df2 = pd.DataFrame({'Name':['John','Smith','Wale','Tom','Menda','Yuswa',],
    'Age':[23,12,34,44,28,40]})

# find elements in df1 that are not in df2
df_1notin2 = df1[~(df1['Name'].isin(df2['Name']) & df1['Age'].isin(df2['Age']))].reset_index(drop=True)

# output:
print('df1\n', df1)
print('df2\n', df2)
print('df_1notin2\n', df_1notin2)

# df1
#     Age   Name
# 0   23   John
# 1   45   Mike
# 2   12  Smith
# 3   34   Wale
# 4   27  Marry
# 5   44    Tom
# 6   28  Menda
# 7   39   Bolt
# 8   40  Yuswa
# df2
#     Age   Name
# 0   23   John
# 1   12  Smith
# 2   34   Wale
# 3   44    Tom
# 4   28  Menda
# 5   40  Yuswa
# df_1notin2
#     Age   Name
# 0   45   Mike
# 1   27  Marry
# 2   39   Bolt

import pandas as pd
# given
df1 = pd.DataFrame({'Name':['John','Mike','Smith','Wale','Marry','Tom','Menda','Bolt','Yuswa',],
    'Age':[23,45,12,34,27,44,28,39,40]})
df2 = pd.DataFrame({'Name':['John','Smith','Wale','Tom','Menda','Yuswa',],
    'Age':[23,12,34,44,28,40]})

# find elements in df1 that are not in df2
df_1notin2 = df1[~(df1['Name'].isin(df2['Name']) & df1['Age'].isin(df2['Age']))].reset_index(drop=True)

# output:
print('df1\n', df1)
print('df2\n', df2)
print('df_1notin2\n', df_1notin2)

# df1
#     Age   Name
# 0   23   John
# 1   45   Mike
# 2   12  Smith
# 3   34   Wale
# 4   27  Marry
# 5   44    Tom
# 6   28  Menda
# 7   39   Bolt
# 8   40  Yuswa
# df2
#     Age   Name
# 0   23   John
# 1   12  Smith
# 2   34   Wale
# 3   44    Tom
# 4   28  Menda
# 5   40  Yuswa
# df_1notin2
#     Age   Name
# 0   45   Mike
# 1   27  Marry
# 2   39   Bolt

Pandas现在提供了一个新的API来处理数据帧差异:Pandas . datafframe .compare

df.compare(df2)
  col1       col3
  self other self other
0    a     c  NaN   NaN
2  NaN   NaN  3.0   4.0

也许是一个简单的单行程序，具有相同或不同的列名。即使df2['Name2']包含重复的值也能正常工作。

newDf = df1.set_index('Name1')
           .drop(df2['Name2'], errors='ignore')
           .reset_index(drop=False)

对称差分

如果你只对其中一个数据帧中的行感兴趣，而不是两个数据帧中的行，你在寻找集的差异:

pd.concat([df1,df2]).drop_duplicates(keep=False)

⚠️只有在两个数据帧都不包含任何重复的情况下才有效。

设置差分/关系代数差分

如果你对关系代数差异/集差异感兴趣，即df1-df2或df1\df2:

pd.concat([df1,df2,df2]).drop_duplicates(keep=False) 

⚠️只有在两个数据帧都不包含任何重复的情况下才有效。

对于行，尝试这样做，其中Name是联合索引列(可以是多个公共列的列表，或者指定left_on和right_on):

m = df1.merge(df2, on='Name', how='outer', suffixes=['', '_'], indicator=True)

indicator=True设置很有用，因为它添加了一个名为_merge的列，其中包含df1和df2之间的所有更改，分为3种可能的类型:“left_only”，“right_only”或“both”。

对于列，试试这个:

set(df1.columns).symmetric_difference(df2.columns)