import os
import numpy as np
import pandas as pd

import torch
from torch.utils.data import Dataset, DataLoader
# from sklearn.preprocessing import StandardScaler

from utils.tools import StandardScaler
from utils.timefeatures import time_features

import warnings
warnings.filterwarnings('ignore')


class Dataset_bikeshare(Dataset):
    def __init__(self, root_path, flag='train', size=None, 
                 features='M', data_path='informer_dataset.csv', 
                 target='demand', scale=True, inverse=False, timeenc=0, freq='h', cols=None):
        # size [seq_len, label_len, pred_len]
        # info
        if size == None:
            self.seq_len = 720
            self.label_len = 336
            self.pred_len = 336
        else:
            self.seq_len = size[0]
            self.label_len = size[1]
            self.pred_len = size[2]
        # init
        assert flag in ['train', 'test', 'val']
        type_map = {'train':0, 'val':1, 'test':2}
        self.set_type = type_map[flag]
        
        self.features = features
        self.target = target
        self.scale = scale
        self.inverse = inverse
        self.timeenc = timeenc
        self.freq = freq
        
        self.root_path = root_path
        self.data_path = data_path
        self.__read_data__()

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

        border1s = [0, 33600 - 1488, 33600]
        border2s = [33600, 33600, 33600 + 1488]
        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)
            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)
        data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq)

        self.data_x = data[border1:border2]
        if self.inverse:
            self.data_y = df_data.values[border1:border2]
        else:
            self.data_y = data[border1:border2]
        self.data_stamp = data_stamp
    
    def __getitem__(self, index):
        s_begin = index
        s_end = s_begin + self.seq_len
        r_begin = s_end - self.label_len 
        r_end = r_begin + self.label_len + self.pred_len

        seq_x = self.data_x[s_begin:s_end]
        if self.inverse:
            seq_y = np.concatenate([self.data_x[r_begin:r_begin+self.label_len], self.data_y[r_begin+self.label_len:r_end]], 0)
        else:
            seq_y = self.data_y[r_begin:r_end]
        seq_x_mark = self.data_stamp[s_begin:s_end]
        seq_y_mark = self.data_stamp[r_begin:r_end]

        return seq_x, seq_y, seq_x_mark, seq_y_mark
    
    def __len__(self):
        return len(self.data_x) - self.seq_len- self.pred_len + 1

    def inverse_transform(self, data):
        return self.scaler.inverse_transform(data)
    
    
class Dataset_ETT_hour(Dataset):
    def __init__(self, root_path, flag='train', size=None, 
                 features='S', data_path='ETTh1.csv', 
                 target='OT', scale=True, inverse=False, timeenc=0, freq='h', cols=None):
        # size [seq_len, label_len, pred_len]
        # info
        if size == None:
            self.seq_len = 24*4*4
            self.label_len = 24*4
            self.pred_len = 24*4
        else:
            self.seq_len = size[0]
            self.label_len = size[1]
            self.pred_len = size[2]
        # init
        assert flag in ['train', 'test', 'val']
        type_map = {'train':0, 'val':1, 'test':2}
        self.set_type = type_map[flag]
        
        self.features = features
        self.target = target
        self.scale = scale
        self.inverse = inverse
        self.timeenc = timeenc
        self.freq = freq
        
        self.root_path = root_path
        self.data_path = data_path
        self.__read_data__()

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

        border1s = [0, 12*30*24 - self.seq_len, 12*30*24+4*30*24 - self.seq_len]
        border2s = [12*30*24, 12*30*24+4*30*24, 12*30*24+8*30*24]
        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)
            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)
        data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq)

        self.data_x = data[border1:border2]
        if self.inverse:
            self.data_y = df_data.values[border1:border2]
        else:
            self.data_y = data[border1:border2]
        self.data_stamp = data_stamp
    
    def __getitem__(self, index):
        s_begin = index
        s_end = s_begin + self.seq_len
        r_begin = s_end - self.label_len 
        r_end = r_begin + self.label_len + self.pred_len

        seq_x = self.data_x[s_begin:s_end]
        if self.inverse:
            seq_y = np.concatenate([self.data_x[r_begin:r_begin+self.label_len], self.data_y[r_begin+self.label_len:r_end]], 0)
        else:
            seq_y = self.data_y[r_begin:r_end]
        seq_x_mark = self.data_stamp[s_begin:s_end]
        seq_y_mark = self.data_stamp[r_begin:r_end]

        return seq_x, seq_y, seq_x_mark, seq_y_mark
    
    def __len__(self):
        return len(self.data_x) - self.seq_len- self.pred_len + 1

    def inverse_transform(self, data):
        return self.scaler.inverse_transform(data)

class Dataset_ETT_minute(Dataset):
    def __init__(self, root_path, flag='train', size=None, 
                 features='S', data_path='ETTm1.csv', 
                 target='OT', scale=True, inverse=False, timeenc=0, freq='t', cols=None):
        # size [seq_len, label_len, pred_len]
        # info
        if size == None:
            self.seq_len = 24*4*4
            self.label_len = 24*4
            self.pred_len = 24*4
        else:
            self.seq_len = size[0]
            self.label_len = size[1]
            self.pred_len = size[2]
        # init
        assert flag in ['train', 'test', 'val']
        type_map = {'train':0, 'val':1, 'test':2}
        self.set_type = type_map[flag]
        
        self.features = features
        self.target = target
        self.scale = scale
        self.inverse = inverse
        self.timeenc = timeenc
        self.freq = freq
        
        self.root_path = root_path
        self.data_path = data_path
        self.__read_data__()

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

        border1s = [0, 12*30*24*4 - self.seq_len, 12*30*24*4+4*30*24*4 - self.seq_len]
        border2s = [12*30*24*4, 12*30*24*4+4*30*24*4, 12*30*24*4+8*30*24*4]
        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)
            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)
        data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq)
        
        self.data_x = data[border1:border2]
        if self.inverse:
            self.data_y = df_data.values[border1:border2]
        else:
            self.data_y = data[border1:border2]
        self.data_stamp = data_stamp
    
    def __getitem__(self, index):
        s_begin = index
        s_end = s_begin + self.seq_len
        r_begin = s_end - self.label_len
        r_end = r_begin + self.label_len + self.pred_len

        seq_x = self.data_x[s_begin:s_end]
        if self.inverse:
            seq_y = np.concatenate([self.data_x[r_begin:r_begin+self.label_len], self.data_y[r_begin+self.label_len:r_end]], 0)
        else:
            seq_y = self.data_y[r_begin:r_end]
        seq_x_mark = self.data_stamp[s_begin:s_end]
        seq_y_mark = self.data_stamp[r_begin:r_end]

        return seq_x, seq_y, seq_x_mark, seq_y_mark
    
    def __len__(self):
        return len(self.data_x) - self.seq_len - self.pred_len + 1

    def inverse_transform(self, data):
        return self.scaler.inverse_transform(data)


class Dataset_Custom(Dataset):
    def __init__(self, root_path, flag='train', size=None, 
                 features='S', data_path='ETTh1.csv', 
                 target='OT', scale=True, inverse=False, timeenc=0, freq='h', cols=None):
        # size [seq_len, label_len, pred_len]
        # info
        if size == None:
            self.seq_len = 24*4*4
            self.label_len = 24*4
            self.pred_len = 24*4
        else:
            self.seq_len = size[0]
            self.label_len = size[1]
            self.pred_len = size[2]
        # init
        assert flag in ['train', 'test', 'val']
        type_map = {'train':0, 'val':1, 'test':2}
        self.set_type = type_map[flag]
        
        self.features = features
        self.target = target
        self.scale = scale
        self.inverse = inverse
        self.timeenc = timeenc
        self.freq = freq
        self.cols=cols
        self.root_path = root_path
        self.data_path = data_path
        self.__read_data__()

    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); 
        if self.cols:
            cols=self.cols.copy()
            cols.remove(self.target)
        else:
            cols = list(df_raw.columns); cols.remove(self.target); cols.remove('date')
        df_raw = df_raw[['date']+cols+[self.target]]

        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)
            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)
        data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq)

        self.data_x = data[border1:border2]
        if self.inverse:
            self.data_y = df_data.values[border1:border2]
        else:
            self.data_y = data[border1:border2]
        self.data_stamp = data_stamp
    
    def __getitem__(self, index):
        s_begin = index
        s_end = s_begin + self.seq_len
        r_begin = s_end - self.label_len 
        r_end = r_begin + self.label_len + self.pred_len

        seq_x = self.data_x[s_begin:s_end]
        if self.inverse:
            seq_y = np.concatenate([self.data_x[r_begin:r_begin+self.label_len], self.data_y[r_begin+self.label_len:r_end]], 0)
        else:
            seq_y = self.data_y[r_begin:r_end]
        seq_x_mark = self.data_stamp[s_begin:s_end]
        seq_y_mark = self.data_stamp[r_begin:r_end]

        return seq_x, seq_y, seq_x_mark, seq_y_mark
    
    def __len__(self):
        return len(self.data_x) - self.seq_len- self.pred_len + 1

    def inverse_transform(self, data):
        return self.scaler.inverse_transform(data)

class Dataset_Pred(Dataset):
    def __init__(self, root_path, flag='pred', size=None, 
                 features='S', data_path='ETTh1.csv', 
                 target='OT', scale=True, inverse=False, timeenc=0, freq='15min', cols=None):
        # size [seq_len, label_len, pred_len]
        # info
        if size == None:
            self.seq_len = 24*4*4
            self.label_len = 24*4
            self.pred_len = 24*4
        else:
            self.seq_len = size[0]
            self.label_len = size[1]
            self.pred_len = size[2]
        # init
        assert flag in ['pred']
        
        self.features = features
        self.target = target
        self.scale = scale
        self.inverse = inverse
        self.timeenc = timeenc
        self.freq = freq
        self.cols=cols

        self.root_path = root_path
        self.data_path = data_path
        self.__read_data__()

    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]
        '''

            
        if self.cols:
            cols=self.cols.copy()
            cols.remove(self.target)
        else:
            print(f"df_raw.columns : {df_raw.columns}")
            print(f"self.target : {self.target}")
            cols = list(df_raw.columns); cols.remove(self.target); cols.remove('date')
        
        df_raw = df_raw[['date']+cols+[self.target]]
        
        border1 = len(df_raw)-self.seq_len
        border2 = len(df_raw)
        
        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]]
 
        self.prediction_data = df_data[border1:border2]
    
#         print(f"df_data.values : {df_data.values}")

        if self.scale:
            self.scaler.fit(df_data.values)
            data = self.scaler.transform(df_data.values)
        else:
            data = df_data.values
            
        tmp_stamp = df_raw[['date']][border1:border2]
        
        self.df_stamp = tmp_stamp
        
        tmp_stamp['date'] = pd.to_datetime(tmp_stamp.date)
        pred_dates = pd.date_range(tmp_stamp.date.values[-1], periods=self.pred_len+1, freq=self.freq)
        
        df_stamp = pd.DataFrame(columns = ['date'])
        df_stamp.date = list(tmp_stamp.date.values) + list(pred_dates[1:])
        data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq[-1:])

        self.data_x = data[border1:border2]
        if self.inverse:
            self.data_y = df_data.values[border1:border2]
        else:
            self.data_y = data[border1:border2]
        self.data_stamp = data_stamp
    
    def __getitem__(self, index):
        s_begin = index
        s_end = s_begin + self.seq_len
        r_begin = s_end - self.label_len
        r_end = r_begin + self.label_len + self.pred_len

        seq_x = self.data_x[s_begin:s_end]
        if self.inverse:
            seq_y = self.data_x[r_begin:r_begin+self.label_len]
        else:
            seq_y = self.data_y[r_begin:r_begin+self.label_len]
        seq_x_mark = self.data_stamp[s_begin:s_end]
        seq_y_mark = self.data_stamp[r_begin:r_end]
        
        return seq_x, seq_y, seq_x_mark, seq_y_mark, r_begin
    
    def __len__(self):
        return len(self.data_x) - self.seq_len + 1

    def inverse_transform(self, data):
        return self.scaler.inverse_transform(data)