文本数据

import pandas as pd
import numpy as np

pd.Series([1,'1.']).astype('str').astype('string')

0     1
1    1.
dtype: string

pd.Series([1,2]).astype('str').astype('string')

0    1
1    2
dtype: string

pd.Series([True,False]).astype('str').astype('string')

0     True
1    False
dtype: string

s = pd.Series(['a_b_c', 'c_d_e', np.nan, 'f_g_h'], dtype="string")
s

0    a_b_c
1    c_d_e
2     <NA>
3    f_g_h
dtype: string

s.str.split('_')

0    [a, b, c]
1    [c, d, e]
2         <NA>
3    [f, g, h]
dtype: object

s.str.split('_').str[1]

0       b
1       d
2    <NA>
3       g
dtype: object

pd.Series(['a_b_c', ['a','b','c']], dtype="object").str[1]
#第一个元素先转为['a','_','b','_','c']

0    _
1    b
dtype: object

s.str.split('_',expand=True)

	0	1	2
0	a	b	c
1	c	d	e
2	<NA>	<NA>	<NA>
3	f	g	h

s.str.split('_',n=1)

0    [a, b_c]
1    [c, d_e]
2        <NA>
3    [f, g_h]
dtype: object

s.str.split('_',expand=True,n=1)

	0	1
0	a	b_c
1	c	d_e
2	<NA>	<NA>
3	f	g_h

s = pd.Series(['ab',None,'d'],dtype='string')
s

0      ab
1    <NA>
2       d
dtype: string

s.str.cat()

'abd'

s.str.cat(sep=',')

'ab,d'

s.str.cat(sep=',',na_rep='*')

'ab,*,d'

s2 = pd.Series(['24',None,None],dtype='string')
s2

0      24
1    <NA>
2    <NA>
dtype: string

s.str.cat(s2)

0    ab24
1    <NA>
2    <NA>
dtype: string

s.str.cat(s2,sep=',',na_rep='*')

0    ab,24
1      *,*
2      d,*
dtype: string

s.str.cat(pd.DataFrame({0:['1','3','5'],1:['5','b',None]},dtype='string'),na_rep='*')

0    ab15
1     *3b
2     d5*
dtype: string

s.str.cat([s+'0',s*2])

0    abab0abab
1         <NA>
2        dd0dd
dtype: string