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

方法1对于有nan的数据帧无效，因为pd.np.nan != pd.np.nan !我不确定这是否是最好的方法，但它可以避免

df1[~df1.astype(str).apply(tuple, 1).isin(df2.astype(str).apply(tuple, 1))]

它更慢，因为它需要将数据转换为字符串，但由于这个转换pd.np.nan == pd.np.nan。

让我们浏览一下代码。首先，我们将值转换为字符串，并将tuple函数应用于每一行。

df1.astype(str).apply(tuple, 1)
df2.astype(str).apply(tuple, 1)

多亏了这个，我们得到了pd。具有元组列表的系列对象。每个元组包含df1/df2的整行。 然后我们对df1应用isin方法来检查每个元组是否“在”df2中。 结果是pd。带有bool值的系列。如果tuple from df1在df2中，则为True。最后，我们用~符号对结果求反，并对df1进行滤波。长话短说，我们只能从df1中得到那些不在df2中的行。

为了使它更具可读性，我们可以这样写:

df1_str_tuples = df1.astype(str).apply(tuple, 1)
df2_str_tuples = df2.astype(str).apply(tuple, 1)
df1_values_in_df2_filter = df1_str_tuples.isin(df2_str_tuples)
df1_values_not_in_df2 = df1[~df1_values_in_df2_filter]

定义数据框架:

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

df2 = df1[df1.Name.isin(['John','Smith','Wale','Tom','Menda','Yuswa'])

df1

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

df2

    Name  Age
0   John   23
2  Smith   12
3   Wale   34
5    Tom   44
6  Menda   28
8  Yuswa   40

两者之间的区别是:

df1[~df1.isin(df2)].dropna()

    Name   Age
1   Mike  45.0
4  Marry  27.0
7   Bolt  39.0

地点:

isin(df2)返回df1中也在df2中的行。 ~(元素逻辑NOT)在表达式前面对结果求反，因此我们得到df1中不在df2中的元素——两者之间的差值。 .dropna()删除NaN显示所需输出的行

注意:这只适用于len(df1) >= len(df2)。如果df2比df1长，可以反转表达式:df2[~df2.isin(df1)].dropna()

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)

通过索引查找差异。假设df1是df2的一个子集，并且在进行子集设置时将索引前移

df1.loc[set(df1.index).symmetric_difference(set(df2.index))].dropna()

# Example

df1 = pd.DataFrame({"gender":np.random.choice(['m','f'],size=5), "subject":np.random.choice(["bio","phy","chem"],size=5)}, index = [1,2,3,4,5])

df2 =  df1.loc[[1,3,5]]

df1

 gender subject
1      f     bio
2      m    chem
3      f     phy
4      m     bio
5      f     bio

df2

  gender subject
1      f     bio
3      f     phy
5      f     bio

df3 = df1.loc[set(df1.index).symmetric_difference(set(df2.index))].dropna()

df3

  gender subject
2      m    chem
4      m     bio

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