DataNalysis/DataMiss/missingRate.py

import pandas as pd
import numpy as np

def calculate_missing_rate(file_path):
    # 读取CSV文件
    df = pd.read_csv(file_path)

    # 确保C_TIME列的格式是字符串并转换为datetime对象
    df['C_TIME'] = pd.to_datetime(df['C_TIME'], format='%Y-%m-%d %H:%M:%S')

    # 提取年月信息作为分组依据
    df['YearMonth'] = df['C_TIME'].dt.to_period('M')

    # 按月份分组处理数据
    grouped = df.groupby('YearMonth')

    # 结果字典保存每月缺失率和缺失的时间点
    missing_rates = {}

    for period, group in grouped:
        # 获取该月的最小和最大时间
        start_time = group['C_TIME'].min()
        end_time = group['C_TIME'].max()

        # 生成该月所有的15分钟时间点
        full_time_range = pd.date_range(start=start_time, end=end_time, freq='15T')

        # 找到该月的时间点缺失部分
        missing_times = full_time_range.difference(group['C_TIME'])

        # 计算缺失率：缺失时间点的数量 / 全部应该有的时间点数量
        missing_rate = len(missing_times) / len(full_time_range)

        # 保存结果
        missing_rates[period] = {
            'missing_rate': missing_rate,
            'missing_times': missing_times
        }

    # 输出结果
    for period, data in missing_rates.items():
        print(f"Month: {period}, Missing Rate: {data['missing_rate']:.2%}")
        if len(data['missing_times']) > 0:
            print(f"  Missing Time Points:")
            for missing_time in data['missing_times']:
                print(f"    {missing_time}")
        else:
            print("  No missing time points")

# 调用函数，假设文件路径是'tower-1-process.csv'
file_path = 'weather-1-process.csv'
calculate_missing_rate(file_path)