为每行中最常用的单词写一个新列

import pandas as pd
from collections import Counter
import re

# 假设我们有一个DataFrame，其中包含一列文本数据
data = {
    'text': [
        "This is a sample sentence.",
        "Another example of a sentence with more words.",
        "Short one."
    ]
}
df = pd.DataFrame(data)

# 定义一个函数来找出每行中最常用的单词
def most_common_word(text):
    # 使用正则表达式移除标点符号并分割单词
    words = re.findall(r'\w+', text.lower())
    # 计算每个单词的出现次数
    word_counts = Counter(words)
    # 返回出现次数最多的单词
    return word_counts.most_common(1)[0][0]

# 应用函数到每一行，并创建一个新列
df['most_common_word'] = df['text'].apply(most_common_word)

print(df)

                                      text most_common_word
0                        This is a sample sentence.           is
1  Another example of a sentence with more words.        a
2                                Short one.             one

pip install pandas