Python数据分析:从汽车之家评论提取用户评价
import pandas as pd
import re
# 读取Excel文件
df = pd.read_excel('C:\Users\86186\Desktop\汽车之家_秦plus_评论.xls')
# 初始化字典列表
sentences = []
# 遍历每一行数据
for index, row in df.iterrows():
if pd.notnull(row['用户昵称']) and pd.notnull(row['最满意']):
sentence_dict = {}
# 提取最满意的内容并按逗号分句
max_satisfaction = str(row['最满意'])
max_satisfaction = re.split(r'[,,]', max_satisfaction)
sentence_dict['最满意'] = [sentence.strip() for sentence in max_satisfaction]
# 提取最不满意的内容并按逗号分句
if pd.notnull(row['最不满意']):
min_satisfaction = str(row['最不满意'])
min_satisfaction = re.split(r'[,,]', min_satisfaction)
sentence_dict['最不满意'] = [sentence.strip() for sentence in min_satisfaction]
else:
sentence_dict['最不满意'] = []
# 提取智能化的内容
if pd.notnull(df.iloc[index+1]['智能化']):
intelligence = str(df.iloc[index+1]['智能化'])
intelligence = re.split(r'[,,]', intelligence)
sentence_dict['智能化'] = [sentence.strip() for sentence in intelligence]
else:
sentence_dict['智能化'] = []
# 添加到字典列表中
sentences.append(sentence_dict)
# 将结果赋值给sentences0209
sentences0209 = sentences
# 保存结果到文件
with open('打印结果.txt', 'w', encoding='utf-8') as file:
file.write('sentences0209 = ' + str(sentences0209))
# 打印结果
for sentence_dict in sentences0209:
print(sentence_dict)
原文地址: https://www.cveoy.top/t/topic/S6y 著作权归作者所有。请勿转载和采集!