pandas中，对某列应用正则表达式

1.str.contains()，类似re.search()，检查是否包含特定字符串

import pandas as pd

# 示例数据
data = {'col1': ['apple', 'banana', 'cherry', 'pineapple', 'grape']}
df = pd.DataFrame(data)

# 查找包含字母 'a' 的行
pattern = r'a'
df['contains_a'] = df['col1'].str.contains(pattern)

print(df)


col1  contains_a
0      apple        True
1     banana        True
2     cherry       False
3  pineapple        True
4      grape        True

2.str.match()，类似re.match()，检查是否以特定字符串开始

import pandas as pd

# 示例数据
data = {'col1': ['apple', 'banana', 'cherry', 'pineapple', 'grape']}
df = pd.DataFrame(data)

# 完全匹配以 'a' 开头的行
pattern = r'^a'  # 匹配以 'a' 开头的字符串
df['starts_with_a'] = df['col1'].str.match(pattern)

print(df)


col1  starts_with_a
0      apple            True
1     banana           False
2     cherry           False
3  pineapple           False
4      grape           False

3.str.replace()，类似re.sub()，查找特定字符串，并替换

import pandas as pd

# 示例数据
data = {'col1': ['apple', 'banana', 'cherry', 'pineapple', 'grape']}
df = pd.DataFrame(data)

# 替换 'a' 为 '@'
df['replaced'] = df['col1'].str.replace(r'a', '@', regex=True)

print(df)


col1     replaced
0      apple      @pple
1     banana     b@n@n@
2     cherry     cherry
3  pineapple  pine@pple
4      grape      gr@pe

4.str.extract()，类似match.groups()，查找特定字符串，并提取出来

import pandas as pd

# 示例数据
data = {'col1': ['apple123', 'banana456', 'cherry789', 'pineapple000', 'grape987']}
df = pd.DataFrame(data)

# 提取数字部分
pattern = r'(\d+)'  # 匹配数字
df['numbers'] = df['col1'].str.extract(pattern)

print(df)


col1 numbers
0    apple123     123
1   banana456     456
2   cherry789     789
3  pineapple000   000
4    grape987     987

5.str.findall()，类似re.findall()，查找所有匹配的字符串，返回列表

import pandas as pd

# 示例数据
data = {'col1': ['apple123', 'banana456', 'cherry789', 'pineapple000', 'grape987']}
df = pd.DataFrame(data)

# 查找所有数字
pattern = r'(\d+)'  # 匹配数字
df['all_numbers'] = df['col1'].str.findall(pattern)

print(df)


col1   all_numbers
0    apple123         [123]
1   banana456         [456]
2   cherry789         [789]
3  pineapple000     [000]
4    grape987         [987]