import pandas as pd
# 读取Excel文件
df = pd.read_csv(r'C:\Users\win10\Documents\WXWork\1688855780474743\Cache\File\2023-03\us_thinktank_art.csv')
# 创建一个空的DataFrame来保存结果
result_df = pd.DataFrame(columns=['think_tank_name', 'word_count_range', 'count'])
# 定义篇幅范围
ranges = [(0, 500), (501, 1000), (1001, 1500), (2001, float('inf'))]
# 对每个智库和篇幅分类计数
for think_tank_name in df['think_tank_name'].unique():
for word_count_range in ranges:
count = ((df['think_tank_name'] == think_tank_name) &
(df['art_content'].str.len().between(word_count_range[0], word_count_range[1])) &
(df['art_content'].str.len() >= 50)).sum()
result_df = result_df.append({'think_tank_name': think_tank_name,
'word_count_range': f"{word_count_range[0]}-{word_count_range[1]}",
'count': count},
ignore_index=True)
# 将结果写入新的Excel文件
result_df.to_csv(r'C:\Users\win10\Documents\WXWork\1688855780474743\Cache\File\2023-03\us_thinktank_art.csv', index=False)
用python把excel不同不同字数的文章分类,并统计数量
于 2023-04-06 17:31:16 首次发布