energy-data-trans/utils/df_utils/util.py

# -*- coding: utf-8 -*-
# @Time    : 2024/6/21
# @Author  : 魏志亮
import datetime

import pandas as pd


def get_time_space(df, time_str):
    """
    :return: 查询时间间隔
    """
    begin = datetime.datetime.now()
    df1 = pd.DataFrame(df[time_str])
    df1['chazhi'] = df1[time_str].shift(-1) - df1[time_str]
    result = df1.sample(int(df1.shape[0] / 100))['chazhi'].value_counts().idxmax().seconds
    del df1
    print(datetime.datetime.now() - begin)
    return result


def get_time_space_count(start_time: datetime.datetime, end_time: datetime.datetime, time_space=1):
    """
    获取俩个时间之间的个数
    :return: 查询时间间隔
    """
    delta = end_time - start_time
    total_seconds = delta.days * 24 * 60 * 60 + delta.seconds

    return int(total_seconds / time_space) + 1


if __name__ == '__main__':
    df = pd.read_csv(r"D:\trans_data\01.csv")
    df['time_stamp'] = pd.to_datetime(df['time_stamp'])
    space = get_time_space(df, 'time_stamp')
    min = df['time_stamp'].min()
    max = df['time_stamp'].max()
    result = get_time_space_count(min, max, space)
    print(df.shape)
    print(space, min, max, result)