数据转换

import numpy as np
import pandas as pd

重复数据

df_obj = pd.DataFrame({'data1' : ['a'] * 4 + ['b'] * 4,
                       'data2' : np.random.randint(0, 4, 8)})
df_obj

df_obj.duplicated()

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

df_obj.drop_duplicates()

df_obj.drop_duplicates('data2')

map函数

ser_obj = pd.Series(np.random.randint(0,10,10))
ser_obj

0    5
1    9
2    3
3    9
4    6
5    1
6    5
7    4
8    1
9    3
dtype: int32

ser_obj.map(lambda x : x ** 2)

0    25
1    81
2     9
3    81
4    36
5     1
6    25
7    16
8     1
9     9
dtype: int64

数据替换repalce

# 替换单个值
ser_obj.replace(0, -100)

0    5
1    9
2    3
3    9
4    6
5    1
6    5
7    4
8    1
9    3
dtype: int32

# 替换多个值
ser_obj.replace([0, 2], -100)

0    5
1    9
2    3
3    9
4    6
5    1
6    5
7    4
8    1
9    3
dtype: int32

# 替换多个值
ser_obj.replace([0, 2], [-100, -200])

0    5
1    9
2    3
3    9
4    6
5    1
6    5
7    4
8    1
9    3
dtype: int32