def __read_data__()

in aiops/Pathformer_ICLR2024/data_provider/data_loader.py [0:0]

• 43 lines of code
• 7 McCabe index (conditional complexity)

    def __read_data__(self):
        self.scaler = StandardScaler()
        df_raw = pd.read_csv(os.path.join(self.root_path,
                                          self.data_path))

        '''
        df_raw.columns: ['date', ...(other features), target feature]
        '''
        cols = list(df_raw.columns)
        cols.remove(self.target)
        cols.remove('date')
        df_raw = df_raw[['date'] + cols + [self.target]]
        # print(cols)
        num_train = int(len(df_raw) * 0.7)
        num_test = int(len(df_raw) * 0.2)
        num_vali = len(df_raw) - num_train - num_test
        border1s = [0, num_train - self.seq_len, len(df_raw) - num_test - self.seq_len]
        border2s = [num_train, num_train + num_vali, len(df_raw)]
        border1 = border1s[self.set_type]
        border2 = border2s[self.set_type]

        if self.features == 'M' or self.features == 'MS':
            cols_data = df_raw.columns[1:]
            df_data = df_raw[cols_data]
        elif self.features == 'S':
            df_data = df_raw[[self.target]]

        if self.scale:
            train_data = df_data[border1s[0]:border2s[0]]
            self.scaler.fit(train_data.values)
            # print(self.scaler.mean_)
            # exit()
            data = self.scaler.transform(df_data.values)
        else:
            data = df_data.values

        df_stamp = df_raw[['date']][border1:border2]
        df_stamp['date'] = pd.to_datetime(df_stamp.date)
        if self.timeenc == 0:
            df_stamp['month'] = df_stamp.date.apply(lambda row: row.month, 1)
            df_stamp['day'] = df_stamp.date.apply(lambda row: row.day, 1)
            df_stamp['weekday'] = df_stamp.date.apply(lambda row: row.weekday(), 1)
            df_stamp['hour'] = df_stamp.date.apply(lambda row: row.hour, 1)
            data_stamp = df_stamp.drop(['date'], 1).values
        elif self.timeenc == 1:
            data_stamp = time_features(pd.to_datetime(df_stamp['date'].values), freq=self.freq)
            data_stamp = data_stamp.transpose(1, 0)

        self.data_x = data[border1:border2]
        self.data_y = data[border1:border2]
        self.data_stamp = data_stamp