Pandas:根据层次结构删除重复的值

import pandas as pd

# 创建一个包含重复值的DataFrame
data = {
    'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar'],
    'B': ['one', 'one', 'two', 'two', 'one', 'one'],
    'C': [1, 1, 2, 2, 1, 1]
}
df = pd.DataFrame(data)

# 判断重复的行
duplicated_rows = df.duplicated()

print(duplicated_rows)

0    False
1    False
2    False
3    False
4     True
5     True
dtype: bool

import pandas as pd

# 创建一个包含重复值的DataFrame
data = {
    'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar'],
    'B': ['one', 'one', 'two', 'two', 'one', 'one'],
    'C': [1, 1, 2, 2, 1, 1]
}
df = pd.DataFrame(data)

# 删除重复的行
df_drop_duplicates = df.drop_duplicates()

print(df_drop_duplicates)

     A    B  C
0  foo  one  1
1  bar  one  1
2  foo  two  2
3  bar  two  2