energy-data-trans/utils/tmp_util/颗粒度变大.py

import os

import pandas as pd


def trans_time_granularity(read_dir: str, save_dir: str, time_str: str, time_granularity: str, group_by: list):
    for root, dirs, files in os.walk(read_dir):
        for file in files:
            file_path = os.path.join(root, file)
            df = pd.read_csv(file_path)
            # df = df.drop(index=0)
            df[time_str] = pd.to_datetime(df[time_str], errors='coerce')
            df[time_str] = df[time_str].dt.ceil(time_granularity)
            groupby_df = df.groupby(group_by).mean(numeric_only=True).reset_index()

            save_file = file_path.replace(read_dir, save_dir)
            if not os.path.exists(os.path.dirname(save_file)):
                os.makedirs(os.path.dirname(save_file))

            groupby_df.to_csv(save_file, index=False, encoding='utf-8')


if __name__ == '__main__':
    read_dir = r'D:\data\tmp_data\龙源\minute'
    save_dir = r'D:\data\tmp_data\龙源\minute12'

    trans_time_granularity(read_dir, save_dir, 'time_stamp', '20min', ['time_stamp'])