Pandas进行文本数据处理的全面指南

import pandas as pd

# 创建示例数据
data = {'Name': ['Alice Smith', 'Bob Johnson', 'Charlie Brown'],
        'Email': ['alice@example.com', 'bob@test.org', 'charlie@demo.net']}
df = pd.DataFrame(data)

# 使用str访问器
df['Name_Upper'] = df['Name'].str.upper()
print("大写姓名:\n", df['Name_Upper'])

# 创建示例数据
s = pd.Series(['a', 'b', 'c'])

# 简单连接
result = s.str.cat(sep=',')
print("\n简单连接结果:", result)

# 与另一Series连接
s2 = pd.Series(['1', '2', '3'])
result = s.str.cat(s2, sep='-')
print("\nSeries间连接:\n", result)

# 连接DataFrame中的多列
df['Name_Email'] = df['Name'].str.cat(df['Email'], sep=' <')
print("\n连接两列结果:\n", df['Name_Email'])

# 分割姓名
split_names = df['Name'].str.split(' ')
print("\n分割姓名:\n", split_names)

# 获取分割后的第一部分
first_names = df['Name'].str.split(' ').str[0]
print("\n名字部分:\n", first_names)

# 扩展分割结果为多列
df[['First_Name', 'Last_Name']] = df['Name'].str.split(' ', expand=True)
print("\n扩展分割结果:\n", df[['First_Name', 'Last_Name']])

# 替换域名
df['New_Email'] = df['Email'].str.replace(r'\.\w+$', '.com', regex=True)
print("\n替换域名后:\n", df['New_Email'])

# 使用正则表达式替换
df['Initials'] = df['Name'].str.replace(r'(\w)\w*\s(\w)\w*', r'\1\2', regex=True)
print("\n姓名首字母:\n", df['Initials'])

# 从Email中提取用户名和域名
extracted = df['Email'].str.extract(r'(?P<Username>\w+)@(?P<Domain>\w+)\.\w+')
print("\n提取结果:\n", extracted)

# 提取名字中的元音字母
vowels = df['Name'].str.extractall(r'([aeiouAEIOU])')
print("\n元音字母:\n", vowels)

# 重复字符串
repeated = df['First_Name'].str.repeat(2)
print("\n重复名字:\n", repeated)

# 按不同次数重复
repeated = df['First_Name'].str.repeat([1, 2, 3])
print("\n按次数重复:\n", repeated)

# 计算字符串长度
df['Name_Length'] = df['Name'].str.len()
print("\n姓名长度:\n", df['Name_Length'])

# 检查是否包含特定字符串
contains_bob = df['Name'].str.contains('Bob')
print("\n包含Bob:\n", contains_bob)

# 检查是否以特定字符串开始/结束
starts_with_a = df['Name'].str.startswith('A')
print("\n以A开头:\n", starts_with_a)

# 字符串填充
padded = df['First_Name'].str.pad(width=10, side='right', fillchar='_')
print("\n填充结果:\n", padded)

# 去除空白
df['Name'] = [' Alice ', 'Bob ', ' Charlie']
df['Name_Clean'] = df['Name'].str.strip()
print("\n去除空白后:\n", df['Name_Clean'])

# 使用apply进行复杂处理
def extract_vowels(name):
    return ''.join([c for c in name if c.lower() in 'aeiou'])

df['Vowels'] = df['Name'].apply(extract_vowels)
print("\n提取元音:\n", df['Vowels'])

# 向量化字符串操作
df['Name_Lower'] = df['Name'].str.lower()
df['Name_Title'] = df['Name'].str.title()
print("\n大小写转换:\n", df[['Name_Lower', 'Name_Title']])

# 比较向量化操作和循环的性能
import timeit

# 向量化操作
def vectorized():
    return df['Name'].str.upper()

# 循环操作
def loop():
    return [name.upper() for name in df['Name']]

print("\n向量化操作时间:", timeit.timeit(vectorized, number=1000))
print("循环操作时间:", timeit.timeit(loop, number=1000))