删除重复行和原始行- Pandas

import pandas as pd

# 创建一个包含重复行的DataFrame
data = {'col1': [1, 2, 3, 3, 4, 5],
        'col2': ['a', 'b', 'c', 'c', 'd', 'e']}
df = pd.DataFrame(data)

# 判断重复行
duplicated_rows = df.duplicated()

# 删除重复行
df.drop_duplicates(inplace=True)

print(df)

   col1 col2
0     1    a
1     2    b
2     3    c
4     4    d
5     5    e

import pandas as pd

# 创建一个包含重复行的DataFrame
data = {'col1': [1, 2, 3, 3, 4, 5],
        'col2': ['a', 'b', 'c', 'c', 'd', 'e'],
        'col3': ['x', 'y', 'z', 'z', 'w', 'w']}
df = pd.DataFrame(data)

# 判断重复行
duplicated_rows = df.duplicated(subset=['col1', 'col2'])

# 删除重复行
df.drop_duplicates(subset=['col1', 'col2'], inplace=True)

print(df)

   col1 col2 col3
0     1    a    x
1     2    b    y
2     3    c    z
4     4    d    w
5     5    e    w

import pandas as pd

# 创建一个包含重复行的DataFrame
data = {'col1': [1, 2, 3, 3, 4, 5],
        'col2': ['a', 'b', 'c', 'c', 'd', 'e']}
df = pd.DataFrame(data)

# 判断重复行
duplicated_rows = df.duplicated()

# 删除重复行，保留最后一次出现的行
df.drop_duplicates(keep='last', inplace=True)

print(df)

   col1 col2
0     1    a
1     2    b
2     3    c
4     4    d
5     5    e