Python中如何删除DataFrame逗号分隔字符串的None并统计行内高频词汇

import pandas as pd
from collections import Counter

# 构造示例数据，实际使用时替换为你自己的DataFrame
df = pd.DataFrame({
    'Col': [
        'Car, None, None, Car, Bus, None',
        'None',
        'Bus, Bus, None, Car, Car, None',
        'None, None, None'
    ]
})

# 处理每行内容：拆分、过滤None、标记全None行
def parse_row(raw_str):
    word_list = [word.strip() for word in raw_str.split(',') if word.strip() != 'None']
    return word_list if word_list else None

df['temp_word_list'] = df['Col'].apply(parse_row)
# 删除全None行
df = df.dropna(subset=['temp_word_list']).reset_index(drop=True)
# 生成处理后的Col列
df['Col'] = df['temp_word_list'].apply(lambda x: ', '.join(x))

# 统计每行最高频词汇，支持并列最高
def get_top_count(word_list):
    count = Counter(word_list)
    max_count = max(count.values())
    top_list = [f"{word} ({num})" for word, num in count.items() if num == max_count]
    return ', '.join(top_list)

df['Most common words'] = df['temp_word_list'].apply(get_top_count)
# 移除临时辅助列
df = df.drop(columns=['temp_word_list'])

# 输出结果
print(df)

运行上述代码得到的输出完全匹配预期示例。

内容的提问来源于stack exchange，提问作者PSCM