pandas文本处理

 import pandas as pd
 import numpy as np

 s = pd.Series(['A', 'b', 'c', 'bbhello', '', np.nan, 'hj'])
 df = pd.DataFrame({'key1': list('abcdef'),
                    'key2': ['hee', 'fv', 'w', 'hija', '', np.nan]})
 print(s)
 print('-'*8)
 print(df)
 print('-'*8)
 '''
 0          A
 1          b
 2          c
 3    bbhello
 4        123
 5        NaN
 6         hj
 dtype: object
 --------
   key1  key2
 0    a   hee
 1    b    fv
 2    c     w
 3    d  hija
 4    e   123
 5    f   NaN
 --------
 '''
 # 直接通过.str调用字符串方法，可以对Series、DataFrame使用，自动过滤NaN值
 print(s.str.count('b'))
 '''
 0    0.0
 1    1.0
 2    0.0
 3    2.0
 4    0.0
 5    NaN
 6    0.0
 dtype: float64
 '''
 print(df['key2'].str.upper())
 '''
 0     HEE
 1      FV
 2       W
 3    HIJA
 4     123
 5     NaN
 Name: key2, dtype: object
 '''
 # 将所有的列名改为大写
 df.columns = df.columns.str.upper()
 print(df)
 '''
   KEY1  KEY2
 0    a   hee
 1    b    fv
 2    c     w
 3    d  hija
 4    e   123
 5    f   NaN
 '''
 # 字符串常用方法 --lower，upper，len，starswith，endswith

 print('小写，lower()',s.str.lower())
 print('大写，upper()',s.str.upper())
 print('长度，len()',s.str.len())
 print('判断起始是否为b，startswith()',s.str.startswith('b'))
 print('判断结束是否为"o"，endswith()',s.str.endswith('o'))
 '''
 小写，lower() 0          a
 1          b
 2          c
 3    bbhello
 4        123
 5        NaN
 6         hj
 dtype: object
 大写，upper() 0          A
 1          B
 2          C
 3    BBHELLO
 4        123
 5        NaN
 6         HJ
 dtype: object
 长度，len() 0    1.0
 1    1.0
 2    1.0
 3    7.0
 4    3.0
 5    NaN
 6    2.0
 dtype: float64
 判断起始是否为b，startswith() 0    False
 1     True
 2    False
 3     True
 4    False
 5      NaN
 6    False
 dtype: object
 判断结束是否为"o"，endswith() 0    False
 1    False
 2    False
 3     True
 4    False
 5      NaN
 6    False
 dtype: object
 '''
 # 字符串常用方法 --strip

 s2 = pd.Series([' jack', 'jill ', ' jesse  '])
 df2 = pd.DataFrame(np.random.randn(3, 2), columns=[' A ', ' B'], index=range(3))
 print(s2)
 print('-'*8)
 print(df2)
 print('-'*8)
 '''
 0        jack
 1       jill
 2     jesse
 dtype: object
 --------
          A          B
 0 -0.333042 -0.467830
 1  0.605179 -0.658910
 2 -0.490881 -0.639754
 --------
 '''
 print(s2.str.strip())
 print('-'*8)
 print(s2.str.lstrip())
 print('-'*8)
 print(s2.str.rstrip())
 '''
 0     jack
 1     jill
 2    jesse
 dtype: object
 --------
 0       jack
 1      jill
 2    jesse
 dtype: object
 --------
 0      jack
 1      jill
 2     jesse
 dtype: object
 '''
 df2.columns = df2.columns.str.strip()
 print(df2)
 '''
           A         B
 0 -0.801508  1.650113
 1 -0.669556 -1.195999
 2  0.277338 -0.727100

 '''

 # 字符串常用方法  -- replace()
 df3 = pd.DataFrame(np.random.randn(3, 2), columns=[' A a', ' B  b'], index=range(3))
 df3.columns = df3.columns.str.replace(' ', '-', n=2)
 print(df3)
 '''
        -A-a     -B- b
 0 -1.225938  0.296270
 1  0.769037  2.794032
 2 -1.686818  0.109314
 '''
 # 字符串常用方法 -- spilt、rsplit
 s4 = pd.Series(['a,b,c', '1,2,3', ['a,,,c'], np.nan])
 print(s4)
 print(s4.str.split(','))
 '''
 0      a,b,c
 1      1,2,3
 2    [a,,,c]
 3        NaN
 dtype: object
 0    [a, b, c]
 1    [1, 2, 3]
 2          NaN
 3          NaN
 dtype: object
 '''
 # 直接索引得到一个list
 # 可以使用get或[]符号访问拆散列表中的元素
 print(s4.str.split(',').str[0])
 print(s4.str.split(',').str.get(0))
 '''
 0      a
 1      1
 2    NaN
 3    NaN
 dtype: object
 0      a
 1      1
 2    NaN
 3    NaN
 dtype: object
 '''

 # 可以使用expand可以轻松扩展此操作以返回DataFrame
 # n 参数限制分割数
 print(s4.str.split(','))
 print('-' * 8)
 print(s4.str.split(',', expand=True))
 '''
 0    [a, b, c]
 1    [1, 2, 3]
 2          NaN
 3          NaN
 dtype: object
 --------
      0    1    2
 0    a    b    c
 1    1    2    3
 2  NaN  NaN  NaN
 3  NaN  NaN  NaN
 '''
 print(s4.str.split(',', expand=True, n=1))
 '''
      0    1
 0    a  b,c
 1    1  2,3
 2  NaN  NaN
 3  NaN  NaN
 '''
 # rsplit类似于split，反向工作，即从字符串的末尾到字符串的开头
 print(s4.str.split(',', expand=True, n=1))
 print('-' * 8)
 print(s4.str.rsplit(',', expand=True, n=1))
 '''
      0    1
 0    a  b,c
 1    1  2,3
 2  NaN  NaN
 3  NaN  NaN
 --------
      0    1
 0  a,b    c
 1  1,2    3
 2  NaN  NaN
 3  NaN  NaN
 '''

 df4 = pd.DataFrame({'key1': ['a,b,c', '1,2,3', [':,,, ']],
                     'key2': ['a-b-c', '1-2-3', [':-.- ']]})
 print(df4)
 print('-'*8)
 print(df4['key2'].str.split('-'))
 '''
       key1     key2
 0    a,b,c    a-b-c
 1    1,2,3    1-2-3
 2  [:,,, ]  [:-.- ]
 --------
 0    [a, b, c]
 1    [1, 2, 3]
 2          NaN
 Name: key2, dtype: object
 '''
 # 通过索引获取分割后的元素
 df4['k201'] = df4['key2'].str.split('-').str[0]
 df4['k202'] = df4['key2'].str.split('-').str[1]
 df4['k203'] = df4['key2'].str.split('-').str[2]
 print(df4)
 '''
       key1     key2 k201 k202 k203
 0    a,b,c    a-b-c    a    b    c
 1    1,2,3    1-2-3    1    2    3
 2  [:,,, ]  [:-.- ]  NaN  NaN  NaN
 '''