dalian-university/劳店分区/data_analyse.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# time: 2023/4/12 18:57
# file: data_analyse.py
# author: David
# company: shenyang JY
import sys
import numpy as np
import pandas as pd


class data_analyse(object):
    def __init__(self, opt, logger, process):
        self.opt = opt
        self.logger = logger
        self.ds = process

    def dq_acc(self):
        excel_data_path = self.opt.csv_data_path
        data_format = self.opt.data_format
        dq_path = excel_data_path + data_format["dq"]
        dq_columns = ['C_TIME', 'C_ABLE_VALUE']
        dq = pd.read_csv(dq_path, usecols=dq_columns)
        dq['C_TIME'] = dq['C_TIME'].astype(float)/1000
        dq['C_TIME'] = pd.to_datetime(dq['C_TIME'], unit='s')
        return dq

    def cdq_acc(self):
        excel_data_path = self.opt.excel_data_path
        data_format = self.opt.data_format
        dq_path = excel_data_path + data_format["cdq"]
        dq_columns = ['C_TIME', 'C_ABLE_VALUE']
        cdq = pd.read_excel(dq_path, usecols=dq_columns)
        cdq['C_TIME'] = pd.to_datetime(cdq['C_TIME'], format='%Y-%m-%d %H:%M:%S')
        return cdq

    def calculate_acc(self, label_data, predict_data):
        loss = np.sum((label_data - predict_data) ** 2) / len(label_data)  # mse
        loss_sqrt = np.sqrt(loss)  # rmse
        loss_acc = 1 - loss_sqrt / self.opt.cap
        return loss_acc

    def calculate_acc_307(self, label_data, predict_data):
        p1 = label_data - predict_data
        p2 = p1 / self.opt.cap
        p3 = p2 ** 2
        p4 = np.sum(p3)
        p5 = p4 / len(label_data)
        p6 = np.sqrt(p5)
        p7 = 1 - p6
        return p7

    def get_16_points(self, results):
        # results为模型预测的一维数组，遍历，取每16个点的最后一个点
        preds = []
        for res in results:
            preds.append(res.iloc[-1].values)
        return np.array(preds)

    def predict_acc(self, predict_data, dfy, predict_all=False):
        if predict_all is True:
            predict_data = predict_data * self.ds.std['SUM'] + self.ds.mean['SUM']
        else:
            predict_data0 = predict_data[0]
            predict_data1 = predict_data[1]
            predict_data0 = predict_data0 * self.ds.std['C_ACTIVE_POWER1'] + self.ds.mean['C_ACTIVE_POWER1']
            predict_data1 = predict_data1 * self.ds.std['C_ACTIVE_POWER2'] + self.ds.mean['C_ACTIVE_POWER2']
            predict_data = predict_data0 + predict_data1
            # predict_data = predict_data[2] * self.ds.std['C_REAL_VALUE'] + self.ds.mean['C_REAL_VALUE']

        # dfs = dfy[0]
        # for i in range(1, len(dfy)):
        #     dfs.extend(dfy[i])
        for i, df in enumerate(dfy):
            df["PREDICT"] = predict_data[i]
            dfy[i] = df
        data = self.get_16_points(dfy)
        df = pd.DataFrame(data, columns=['C_TIME', 'C_ACTIVE_POWER1', 'C_ACTIVE_POWER2', 'SUM', 'C_REAL_VALUE', 'PREDICT'])
        # label_data = label_data.reshape((-1, self.opt.output_size))
        # label_data 要进行反归一化
        dq = self.dq_acc()
        df = pd.merge(df, dq, on='C_TIME')
        # df.to_csv(self.opt.excel_data_path + "nwp+rp+环境（LSTM+CNN）.csv")
        # label_name = [self.opt.feature_columns[i] for i in self.opt.label_in_feature_index]

        loss_norm = self.calculate_acc(df['SUM'], df['PREDICT'])
        self.logger.info("The mean squared error of power {} is ".format('power') + str(loss_norm))

        loss_norm = self.calculate_acc(df['C_REAL_VALUE'], df['C_ABLE_VALUE'])
        self.logger.info("The mean squared error of power {} is ".format('CDQ') + str(loss_norm))