Transformer for Time Series Prediction完整代码

时序预测小白，看到很多Transfirmer在时间序列预测上应用的代码，一头雾水，很烦，所以想自己记录一下，以求真正把Transformer怎么用在时间序列预测上讲清楚，捋明白。

我直接用代码来讲，用一个公开数据集(ETTh1)来做例子。

我把这个数据集提前归一化处理了，命名为ETTh1_standardization.csv，需要数据集的可以私信我。

首先导包并设定随即种子

import argparse
import os
import torch
import torch.nn as nn
import torch.nn.functional as F
import math
import time
import numpy as np
import pandas as pd
from torch.utils.data import Dataset, DataLoader
from typing import List
from pandas.tseries import offsets
from pandas.tseries.frequencies import to_offset
import matplotlib.pyplot as plt
fix_seed = 2024
torch.manual_seed(fix_seed)

这些包的作用后面都会有。

然后传入参数

parser = argparse.ArgumentParser(description='Transformer')
parser.add_argument('--model', type=str, required=False, default='Transformer', help='model of experiment')
parser.add_argument('--data', type=str, required=False, default='ETTh1', help='dataset')
parser.add_argument('--root_path', type=str, default='./data/', help='root path of the data file')
parser.add_argument('--data_path', type=str, default='ETTh1_standardization.csv', help='data file')
parser.add_argument('--features', type=str, default='MS', help='forecasting task, options:[M, S, MS]; M:multivariate predict multivariate, S:univariate predict univariate, MS:multivariate predict univariate')
parser.add_argument('--target', type=str, default='OT', help='target feature in S or MS task')
parser.add_argument('--freq', type=str, default='h', help='freq for time features encoding, options:[s:secondly, t:minutely, h:hourly, d:daily, b:business days, w:weekly, m:monthly]')
parser.add_argument('--seq_len', type=int, default=96, help='input sequence length of Transformer encoder')
parser.add_argument('--label_len', type=int, default=48, help='start token length of Transformer decoder')
parser.add_argument('--pred_len', type=int, default=24, help='prediction sequence length')
parser.add_argument('--enc_in', type=int, default=7, help='encoder input size')
parser.add_argument('--dec_in', type=int, default=7, help='decoder input size')
parser.add_argument('--c_out', type=int, default=1, help='output size')
parser.add_argument('--d_model', type=int, default=512, help='dimension of model')
parser.add_argument('--n_heads', type=int, default=8, help='num of heads')
parser.add_argument('--e_layers', type=int, default=2, help='num of encoder layers')
parser.add_argument('--d_layers', type=int, default=1, help='num of decoder layers')
parser.add_argument('--d_ff', type=int, default=2048, help='dimension of fcn')
parser.add_argument('--padding', type=int, default=0, help='padding type')
parser.add_argument('--dropout', type=float, default=0.05, help='dropout')
parser.add_argument('--activation', type=str, default='gelu', help='activation')
parser.add_argument('--output_attention', action='store_true', help='whether to output attention in encoder')
parser.add_argument('--num_workers', type=int, default=0, help='data loader num workers')
parser.add_argument('--train_epochs', type=int, default=1, help='number of train epochs')
parser.add_argument('--batch_size', type=int, default=32, help='batch size of train input data')
parser.add_argument('--patience', type=int, default=3, help='early stopping patience')
parser.add_argument('--learning_rate', type=float, default=0.0001, help='optimizer learning rate')
parser.add_argument('--loss', type=str, default='mse', help='loss function')
parser.add_argument('--lradj', type=str, default='type1', help='adjust learning rate')
parser.add_argument('--use_gpu', type=bool, default=True, help='use gpu')
parser.add_argument('--gpu', type=int, default=0, help='gpu')
args = parser.parse_args()
args.use_gpu = True if torch.cuda.is_available() and args.use_gpu else False
print('Args in experiment:')
print(args)

可以看出我们设置的一些默认参数

然后下面就开始写类和函数了，共有12个类和9个函数。

首先是TimeFeature类和它的8个子类

class TimeFeature:
    def __init__(self):
        pass

    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
        pass

    def __repr__(self):
        return self.__class__.__name__ + "()"

class SecondOfMinute(TimeFeature):
    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
        return index.second / 59.0 - 0.5

class MinuteOfHour(TimeFeature):
    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
        return index.minute / 59.0 - 0.5

class HourOfDay(TimeFeature):
    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
        return index.hour / 23.0 - 0.5

class DayOfWeek(TimeFeature):
    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
        return index.dayofweek / 6.0 - 0.5

class DayOfMonth(TimeFeature):
    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
        return (index.day - 1) / 30.0 - 0.5

class DayOfYear(TimeFeature):
    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
        return (index.dayofyear - 1) / 365.0 - 0.5

class MonthO