Pandas-数据操作-字符串型（二）：常用方法【lower、upper、len、startswith、endswith、strip、lstrip、replace、split、rsplit】

最新推荐文章于 2024-03-28 18:15:21 发布

u013250861

最新推荐文章于 2024-03-28 18:15:21 发布

阅读量755

点赞数 1

分类专栏： Pandas 文章标签： Pandas 字符串

本文链接：https://blog.csdn.net/u013250861/article/details/124112139

版权

Pandas 专栏收录该内容

45 篇文章 20 订阅

订阅专栏

一、字符串常用方法：lower，upper，len，startswith，endswith

import numpy as np
import pandas as pd

s = pd.Series(['A', 'b', 'bbhello', '123', np.nan])
print("s = \n", s)
print('-' * 200)
print("lower小写: s.str.lower() = \n", s.str.lower())
print('-' * 200)
print("upper大写: s.str.upper() = \n", s.str.upper())
print('-' * 200)
print("len字符长度: s.str.len() = \n", s.str.len())
print('-' * 200)
print("判断起始是否为b: s.str.startswith('b') = \n", s.str.startswith('b'))
print('-' * 200)
print("判断结束是否为3: s.str.endswith('3') = \n", s.str.endswith('3'))

打印结果：

s = 
0          A
1          b
2    bbhello
3        123
4        NaN
dtype: object
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
lower小写: s.str.lower() = 
0          a
1          b
2    bbhello
3        123
4        NaN
dtype: object
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
upper大写: s.str.upper() = 
 0          A
1          B
2    BBHELLO
3        123
4        NaN
dtype: object
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
len字符长度: s.str.len() = 
0    1.0
1    1.0
2    7.0
3    3.0
4    NaN
dtype: float64
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
判断起始是否为b: s.str.startswith('b') = 
0    False
1     True
2     True
3    False
4      NaN
dtype: object
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
判断结束是否为3: s.str.endswith('3') = 
0    False
1    False
2    False
3     True
4      NaN
dtype: object

Process finished with exit code 0

二、字符串常用方法：strip

import numpy as np
import pandas as pd

# 字符串常用方法（2） - strip

s = pd.Series([' jack', 'jill ', ' je sse ', 'frank'])
df = pd.DataFrame(np.random.randn(3, 2),
                  columns=[' Column A ', ' Column B '],
                  index=range(3))
print("s = \n", s)
print('-' * 200)
print("df = \n", df)
print('-' * 200)

# 去除字符串左右的空格
print("去除字符串左右的空格: s.str.strip() = \n", s.str.strip())
# 去除字符串中的左空格
print("去除字符串中的左空格: s.str.lstrip() = \n", s.str.lstrip())
# 去除字符串中的右空格
print("去除字符串中的右空格: s.str.rstrip() = \n", s.str.rstrip())

# 这里去掉了columns的前后空格，但没有去掉中间空格
df.columns = df.columns.str.strip()
print("df = \n", df)
print('-' * 200)

打印结果：

s = 
0        jack
1       jill 
2     je sse 
3       frank
dtype: object
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
df = 
     Column A    Column B 
0   -1.318646   -0.831649
1   -0.339870   -1.141231
2   -0.024364   -2.163961
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
去除字符串左右的空格: s.str.strip() = 
0      jack
1      jill
2    je sse
3     frank
dtype: object
去除字符串中的左空格: s.str.lstrip() = 
0       jack
1      jill 
2    je sse 
3      frank
dtype: object
去除字符串中的右空格: s.str.rstrip() = 
 0       jack
1       jill
2     je sse
3      frank
dtype: object
df = 
    Column A  Column B
0 -1.318646 -0.831649
1 -0.339870 -1.141231
2 -0.024364 -2.163961
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Process finished with exit code 0

三、字符串常用方法：replace

import numpy as np
import pandas as pd

# 字符串常用方法（3） - replace

df = pd.DataFrame(np.random.randn(3, 2),
                  columns=[' Column A ', ' Column B '],
                  index=range(3))
# 替换
df.columns = df.columns.str.replace(' ', '-')
print("df = \n", df)
print('-' * 200)

# n：替换个数
df.columns = df.columns.str.replace('-', '*', n=1)
print("df = \n", df)

打印结果：

df = 
    -Column-A-  -Column-B-
0    0.704728   -0.835929
1    1.478930   -2.708538
2    0.585825   -1.395908
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
df = 
    *Column-A-  *Column-B-
0    0.704728   -0.835929
1    1.478930   -2.708538
2    0.585825   -1.395908

Process finished with exit code 0

四、字符串常用方法：split、rsplit

import numpy as np
import pandas as pd

# 字符串常用方法（4） - split、rsplit


s = pd.Series(['a,b,c', '1,2,3', ['a,,,c'], np.nan])
print("s = \n", s)
print('-' * 200)

# 类似字符串的split
data1 = s.str.split(',')
print("data1 = s.str.split(',') = \n{0} \ntype(data1) = {1}".format(data1, type(data1)))
print('-' * 100)

# 直接索引得到一个list
data2 = data1[0]
print("data2 = data1[0] = s.str.split(',')[0] = \n{0} \ntype(data2) = {1}".format(data2, type(data2)))
print('-' * 100)

# 可以使用get或[]符号访问拆分列表中的元素
data3 = s.str.split(',').str.get(1)
print("data3 = s.str.split(',').str.get(1) = \n{0} \ntype(data3) = {1}".format(data3, type(data3)))
print('-' * 200)

# 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
# rsplit类似于split，反向工作，即从字符串的末尾到字符串的开头
data4 = s.str.split(',', expand=True)
print("data4 = s.str.split(',', expand=True) = \n{0} \ntype(data4) = {1}".format(data4, type(data4)))
print('-' * 100)
data5 = s.str.split(',', expand=True, n=1)
print("data5 = s.str.split(',', expand=True, n=1) = \n{0} \ntype(data5) = {1}".format(data5, type(data5)))
print('-' * 100)
data6 = s.str.rsplit(',', expand=True, n=1)
print("data6 = s.str.rsplit(',', expand=True, n=1) = \n{0} \ntype(data6) = {1}".format(data6, type(data6)))
print('-' * 200)

# Dataframe使用split
df = pd.DataFrame({'key1': ['a,b,c', '1,2,3', [':,., ']],
                   'key2': ['a-b-c', '1-2-3', [':-.- ']]})
print("df = \n", df)
print('-' * 100)
data7 = df['key2'].str.split('-')
print("data7 = df['key2'].str.split('-') = \n{0} \ntype(data7) = {1}".format(data7, type(data7)))
print('-' * 200)

打印结果：

s = 
0      a,b,c
1      1,2,3
2    [a,,,c]
3        NaN
dtype: object
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
data1 = s.str.split(',') = 
0    [a, b, c]
1    [1, 2, 3]
2          NaN
3          NaN
dtype: object 
type(data1) = <class 'pandas.core.series.Series'>
----------------------------------------------------------------------------------------------------
data2 = data1[0] = s.str.split(',')[0] = 
['a', 'b', 'c'] 
type(data2) = <class 'list'>
----------------------------------------------------------------------------------------------------
data3 = s.str.split(',').str.get(1) = 
0      b
1      2
2    NaN
3    NaN
dtype: object 
type(data3) = <class 'pandas.core.series.Series'>
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
data4 = s.str.split(',', expand=True) = 
     0    1    2
0    a    b    c
1    1    2    3
2  NaN  NaN  NaN
3  NaN  NaN  NaN 
type(data4) = <class 'pandas.core.frame.DataFrame'>
----------------------------------------------------------------------------------------------------
data5 = s.str.split(',', expand=True, n=1) = 
     0    1
0    a  b,c
1    1  2,3
2  NaN  NaN
3  NaN  NaN 
type(data5) = <class 'pandas.core.frame.DataFrame'>
----------------------------------------------------------------------------------------------------
data6 = s.str.rsplit(',', expand=True, n=1) = 
     0    1
0  a,b    c
1  1,2    3
2  NaN  NaN
3  NaN  NaN 
type(data6) = <class 'pandas.core.frame.DataFrame'>
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
df = 
       key1     key2
0    a,b,c    a-b-c
1    1,2,3    1-2-3
2  [:,., ]  [:-.- ]
----------------------------------------------------------------------------------------------------
data7 = df['key2'].str.split('-') = 
0    [a, b, c]
1    [1, 2, 3]
2          NaN
Name: key2, dtype: object 
type(data7) = <class 'pandas.core.series.Series'>
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Process finished with exit code 0