import numpy as np
import pandas as pd
import os
from sklearn import datasets, linear_model
import argparse


class GasAnalyzer():
    def __init__(self, folderPath):
        self.folderPath = folderPath

    def read_data(self):
        path_list = os.listdir(self.folderPath)
        self.validFiles = []
        for filename in path_list:
            if os.path.splitext(filename)[1] == '.txt':
                self.validFiles.append(filename)

        # 这两个循环可以合并优化，但不确定是否可以提高性能
        names = locals()
        self.rowCountsBackup = []
        for i, filename in enumerate(self.validFiles):
            names[f'df_{i}'] = pd.read_csv(self.folderPath + "\\" + filename, skiprows=1, sep=',')
            self.rowCountsBackup.append(names[f'df_{i}'].shape[0])

        for x in range(len(self.rowCountsBackup)):
            if(x==0):
                self.df_total = names[f'df_{0}']
            else:
                self.df_total = pd.concat([self.df_total, names[f'df_{x}']])

        if(sum(self.rowCountsBackup) != self.df_total.shape[0]):
            print("拼接气体分析仪数据失败！拼接前后行数不一致！")
            return 1

        return 0

    def write_data(self):
        a = 1

    def merge_data(self, MeteorologicalStation):
        a = 1


class MeteorologicalStation():
    def __init__(self, folderPath):
        self.folderPath = folderPath

    def read_data(self):
        path_list = os.listdir(self.folderPath)
        self.validFiles = []
        for filename in path_list:
            if os.path.splitext(filename)[1] == '.dat':
                self.validFiles.append(filename)

        # 这两个循环可以合并优化，但不确定是否可以提高性能
        names = locals()
        self.rowCountsBackup = []
        for i, filename in enumerate(self.validFiles):
            names[f'df_{i}'] = pd.read_csv(self.folderPath + "\\" + filename, header=None, sep=',')
            self.rowCountsBackup.append(names[f'df_{i}'].shape[0])

        for x in range(len(self.rowCountsBackup)):
            if(x==0):
                self.df_total = names[f'df_{0}']
            else:
                self.df_total = pd.concat([self.df_total, names[f'df_{x}']])

        if(sum(self.rowCountsBackup) != self.df_total.shape[0]):
            print("拼接气体分析仪数据失败！拼接前后行数不一致！")
            return 1

        return 0


if __name__ == "__main__":
    # parser = argparse.ArgumentParser()
    # parser.add_argument("csv_path", help="Path of csv file which contains wavelength.")
    # parser.add_argument("start_row", help="Start row of coning 410 sensor.")
    # args = parser.parse_args()

    # row_bin1, wave_bin1, row_bin2, wave_bin2 = read_data(args.csv_path, int(args.start_row))

    GasAnalyzer_folderPath = r"D:\PycharmProjects\weatherInstrument\2022neimengdata\气体分析仪\2022-08-13"

    MeteorologicalStation_folderPath = r"D:\PycharmProjects\weatherInstrument\2022neimengdata\气象站\2022_08_13"

    tmp1 = GasAnalyzer(GasAnalyzer_folderPath)
    tmp1.read_data()

    tmp2 = MeteorologicalStation(MeteorologicalStation_folderPath)
    tmp2.read_data()

    print("completed!!")