数据预处理完整代码

import pandas as pd
import numpy as np
from datetime import datetime

class DataPreprocessor:
    def __init__(self, data_path):
        self.data = pd.read_csv(data_path)
    
    def clean_data(self):
        # 去除重复和空值
        self.data.drop_duplicates(inplace=True)
        self.data.dropna(subset=['content', 'user_id'], inplace=True)
        
    def transform_dates(self):
        # 时间格式转换
        self.data['post_time'] = pd.to_datetime(self.data['post_time'])
        
    def extract_features(self):
        # 提取文本特征
        self.data['content_length'] = self.data['content'].str.len()
        self.data['has_image'] = self.data['media_type'].apply(
            lambda x: 1 if 'image' in str(x) else 0
        )

# 使用示例
if __name__ == "__main__":
    # 初始化数据预处理器
    preprocessor = DataPreprocessor("weibo_data.csv")
    
    # 执行数据清洗
    preprocessor.clean_data()
    
    # 转换日期格式
    preprocessor.transform_dates()
    
    # 提取特征
    preprocessor.extract_features()
    
    # 保存处理后的数据
    preprocessor.data.to_csv("processed_data.csv", index=False)