energy-data-trans/tmp_file/张崾先统计缺失率.py

import multiprocessing
import os
import sys

sys.path.insert(0, os.path.abspath(__file__).split("tmp_file")[0])

import pandas as pd

from utils.file.trans_methods import read_file_to_df


def save_percent(value, save_decimal=7):
    return round(value, save_decimal) * 100


def read_and_select(file_path, read_cols):
    result_df = pd.DataFrame()
    df = read_file_to_df(file_path, read_cols=read_cols)
    wind_name = os.path.basename(file_path).split('.')[0]
    df['风机号'] = wind_name
    df = df.query("(Time>='2024-06-01 00:00:00') & (Time<'2024-12-01 00:00:00')")
    count = 15811200  # 1秒数据  半年
    repeat_time_count = df.shape[0] - len(df['Time'].unique())
    print(wind_name, count, repeat_time_count)
    result_df['风机号'] = [wind_name]
    result_df['重复率'] = [save_percent(repeat_time_count / count)]
    result_df['重复次数'] = [repeat_time_count]
    result_df['总记录数'] = [count]

    for read_col in read_cols:

        if read_col != 'Time':
            df[read_col] = pd.to_numeric(df[read_col], errors='coerce')
        else:
            df[read_col] = pd.to_datetime(df[read_col], errors='coerce')

    group_df = df.groupby(by=['风机号']).count()
    group_df.reset_index(inplace=True)
    count_df = pd.DataFrame(group_df)
    total_count = count_df[read_cols].values[0].sum()
    print(wind_name, total_count, count * len(read_cols))
    result_df['平均缺失率,单位%'] = [save_percent(1 - total_count / (count * len(read_cols)))]
    result_df['缺失数值'] = ['-'.join([str(count - i) for i in count_df[read_cols].values[0]])]
    del group_df

    fengsu_count = 0
    fengsu_cols = [i for i in read_cols if '风速' in i]
    fengsu_str = ''
    for col in fengsu_cols:
        now_count = df.query("(" + col + " < 0) | (" + col + " > 80)").shape[0]
        fengsu_count = fengsu_count + now_count
        fengsu_str = fengsu_str + ',' + col + ':' + str(fengsu_count)
    result_df['风速异常'] = [fengsu_str]

    gonglv_cols = ['有功功率', '瞬时功率', '当前理论可发最大功率']
    gonglv_count = 0
    gonglv_str = ''
    for col in gonglv_cols:
        now_count = df.query("(" + col + " < -200) | (" + col + " > 3000)").shape[0]
        gonglv_count = gonglv_count + now_count
        gonglv_str = gonglv_str + ',' + col + ':' + str(gonglv_count)
    result_df['功率异常'] = [gonglv_str]

    result_df['平均异常率'] = [
        save_percent((fengsu_count + fengsu_count) / ((len(fengsu_cols) + len(gonglv_cols)) * count))]

    return result_df


if __name__ == '__main__':
    read_cols = ['Time', '设备主要状态', '功率曲线风速', '湍流强度', '实际风速', '有功功率', '桨叶角度A', '桨叶角度B',
                 '桨叶角度C', '机舱内温度', '机舱外温度', '绝对风向', '机舱绝对位置', '叶轮转速', '发电机转速',
                 '瞬时风速',
                 '有功设定反馈', '当前理论可发最大功率', '空气密度', '偏航误差', '发电机扭矩', '瞬时功率', '风向1s',
                 '偏航压力', '桨叶1速度', '桨叶2速度', '桨叶3速度', '桨叶1角度给定', '桨叶2角度给定', '桨叶3角度给定',
                 '轴1电机电流', '轴2电机电流', '轴3电机电流', '轴1电机温度', '轴2电机温度', '轴3电机温度', '待机',
                 '启动',
                 '偏航', '并网', '限功率', '正常发电', '故障', '计入功率曲线', '运行发电机冷却风扇1',
                 '运行发电机冷却风扇2',
                 '激活偏航解缆阀', '激活偏航刹车阀', '激活风轮刹车阀', '激活顺时针偏航', '激活逆时针偏航', '电缆扭角']

    read_dir = r'/data/download/collection_data/1进行中/张崾先风电场-陕西-华电/清理数据/点检表以外测点儿-20241210'

    files = os.listdir(read_dir)

    with multiprocessing.Pool(4) as pool:
        dfs = pool.starmap(read_and_select, [(os.path.join(read_dir, i), read_cols) for i in files])

    df = pd.concat(dfs, ignore_index=True)
    df.sort_values(by=['风机号'], inplace=True)

    df.to_csv("张崾先统计-秒.csv", encoding='utf8', index=False)