timesNet.py

# python3
# Create data: 2023-10-27
# Reference: https://github.com/thuml/Time-Series-Library/blob/main/models/TimesNet.py
# Func: Times Net
# ==========================================================================================

import torch
from torch import nn
from torch.nn import functional as F
from torch import fft 
from Embed import DataEmbedding
from Conv_Blocks import Inception_Block_V1


def FFT_for_Period(x, k=2):
    # [B, T, c]
    xf = torch.fft.rfft(x, dim=1)
    # find period by amplitudes
    freq_list = abs(xf).mean(0).mean(-1)
    freq_list[0] = 0
    _, top_list = torch.topk(freq_list, k)
    top_list = top_list.detach().cpu().numpy()
    period = x.shape[1] // top_list
    return period, abs(xf).mean(-1)[:, top_list]


class TimesBlock(nn.Module):
    def __init__(self, configs):
        super(TimesBlock, self).__init__()
        self.seq_len = configs.seq_len
        self.pred_len = configs.pred_len
        self.k = configs.top_k
        # parameter-efficient design
        self.conv = nn.Sequential(
            Inception_Block_V1(configs.d_model, configs.d_ff, 
                               num_kernels=configs.num_kernels),
            nn.GELU(),
            Inception_Block_V1(configs.d_ff, configs.d_model, 
                               num_kernels=configs.num_kernels)
        )
    
    def forward(self, x):
        B, T, N = x.size()
        period_list, period_weight = FFT_for_Period(x, self.k)
        res = []
        for i in range(self.k):
            period = period_list[i]
            # padding
            if (self.seq_len + self.pred_len) % period != 0:
                length = ( 
                          ((self.seq_len + self.pred_len) // period) + 1) * period
                padding = torch.zeros([x.shape[0], (length - (self.seq_len + self.pred_len)), 
                                       x.shape[2]]).to(x.device)
                out = torch.cat([x, padding], dim=1)
            else:
                length = self.seq_len + self.pred_len
                out = x 
            
            ## Reshape  1D -> 2D 
            ### [B, one-period series-len, period-dim, N-feature dim] ->
            ### [B, N-feature dim, one-period series-len, period-dim]
            out = out.reshape(B, length // period, period, N).permute(0, 3, 1, 2).contiguous()
            # Inception: 2D conv: from 1d varation to 2d variation
            ## channel first   conv on  pic-(one-period series-len, period-dim)
            # channel[d_model] -> 6-conv, stack, mean -> channel[d_ff]  -> GELU
            # channel[d_ff]    -> 6-conv, stack, mean -> channel[d_model] 
            out = self.conv(out)
            # reshape back
            out = out.permute(0, 2, 3, 1).reshape(B, -1, N)
            res.append(out[:, :(self.seq_len + self.pred_len), :])
        res = torch.stack(res, dim=-1)
        # adaptive aggregation
        period_weight = F.softmax(period_weight, dim=1)
        period_weight = period_weight.unsqueeze(1).unsqueeze(1).repeat(1, T, N, 1)
        res = torch.sum(res * period_weight, -1)
        # residual connection
        return res + x


class Model(nn.Module):
    """
    Paper link: https://openreview.net/pdf?id=ju_Uqw384Oq
    """
    def __init__(self, configs):
        super(Model, self).__init__()
        self.configs = configs
        self.task_name = configs.task_name
        self.seq_len = configs.seq_len
        self.label_len = configs.label_len
        self.pred_len = configs.pred_len
        self.model = nn.ModuleList([TimesBlock(configs) for _ in range(configs.e_layers)])
        self.enc_embedding = DataEmbedding(configs.enc_in, configs.d_model, configs.embed, configs.freq, configs.dropout)
        self.layer = configs.e_layers
        self.layer_norm = nn.LayerNorm(configs.d_model)
        if self.task_name in ['long_term_forecast', 'short_term_forecast']:
            # forcast  his + future
            self.predict_linear = nn.Linear(
                self.seq_len, self.pred_len + self.seq_len)
            self.projection = nn.Linear(
                configs.d_model, configs.c_out, bias=True)
        if self.task_name in ['imputation', 'anomaly_detection']:
           self.projection = nn.Linear(
                configs.d_model, configs.c_out, bias=True)
        if self.task_name == 'classification':
            self.act = F.gelu
            self.dropout = nn.Dropout(configs.dropout)
            self.projection = nn.Linear(
                configs.d_model * configs.seq_len, configs.num_class)

    def forecast(self, x_enc, x_mark_enc, x_dec, x_mark_dec):
        # Normalization from Non-stationart Transformer
        means = x_enc.mean(1, keepdim=True).detach()
        x_enc = x_enc - means
        stdev = torch.sqrt(
            torch.var(x_enc, dim=1, keepdim=True, unbiased=False) + 1e-5
        )
        x_enc /= stdev
        # embedding
        enc_out = self.enc_embedding(x_enc, x_mark_enc)
        # operate in timeseries
        enc_out = self.predict_linear(enc_out.permute(0, 2, 1)).permute(0, 2, 1)
        # TimesNet
        for i in range(self.layer):
            enc_out = self.layer_norm(self.model[i](enc_out))
        
        # project back
        dec_out = self.projection(enc_out)
        
        # De-Normalization from Non-stationary Transformer
        dec_out = dec_out * stdev[:, 0, :].unsqueeze(1).repeat(1, self.pred_len + self.seq_len, 1)
        dec_out = dec_out + means[:, 0, :].unsqueeze(1).repeat(1, self.pred_len + self.seq_len, 1)
        return dec_out

    def imputation(self, x_enc, x_mark_enc, x_dec, x_mark_dec, mask):
        # Normalization from Non-stationart Trabsformer
        means = x_enc.mean(1, keepdim=True).detach()
        x_enc = x_enc - means
        stdev = torch.sqrt(
            torch.var(x_enc, dim=1, keepdim=True, unbiased=False) + 1e-5
        )
        x_enc /= stdev
        # embedding
        enc_out = self.enc_embedding(x_enc, x_mark_enc) # [B, T, C]
        # TimesNet
        for i in range(self.layer):
            enc_out = self.layer_norm(self.model[i](enc_out))
        
        # project back
        dec_out = self.projection(enc_out)
        
        # De-Normalization from Non-stationary Transformer
        dec_out = dec_out * stdev[:, 0, :].unsqueeze(1).repeat(1, self.pred_len + self.seq_len, 1)
        dec_out = dec_out + means[:, 0, :].unsqueeze(1).repeat(1, self.pred_len + self.seq_len, 1)
        return dec_out

    def anomaly_detection(self, x_enc):
        # Normalization from Non-stationart Trabsformer
        means = x_enc.mean(1, keepdim=True).detach()
        x_enc = x_enc - means
        stdev = torch.sqrt(
            torch.var(x_enc, dim=1, keepdim=True, unbiased=False) + 1e-5
        )
        x_enc /= stdev
        # embedding
        enc_out = self.enc_embedding(x_enc, None) # [B, T, C]
        # TimesNet
        for i in range(self.layer):
            enc_out = self.layer_norm(self.model[i](enc_out))
        
        # project back
        dec_out = self.projection(enc_out)
        # De-Normalization from Non-stationary Transformer
        dec_out = dec_out * stdev[:, 0, :].unsqueeze(1).repeat(1, self.pred_len + self.seq_len, 1)
        dec_out = dec_out + means[:, 0, :].unsqueeze(1).repeat(1, self.pred_len + self.seq_len, 1)
        return dec_out

    def classification(self, x_enc, x_mark_enc):
        # embedding
        enc_out = self.enc_embedding(x_enc, None)  # [B,T,C]
        # TimesNet
        for i in range(self.layer):
            enc_out = self.layer_norm(self.model[i](enc_out))
        
        # Output
        # the output transformer encoder/decoder embeddings dont include non-linearity
        output = self.act(enc_out)
        output = self.dropout(output)
        # zero-out padding embeddings
        output = output * x_mark_enc.unsqueeze(-1)
        # (batch_size, seq_length * d_model)
        output = output.reshape(output.shape[0], -1)
        output = self.projection(output) # (batch_size, num_classes)
        return output
    
    def forward(self, x_enc, x_mark_enc, x_dec, x_mark_dec, mask=None):
        if self.task_name in ['long_term_forecast', 'short_term_forecast']:
            dec_out = self.forecast(x_enc, x_mark_enc, x_dec, x_mark_dec)
            return dec_out[:, -self.pred_len:, :]  # [B, L, D]
        if self.task_name == 'imputation':
            dec_out = self.imputation(
                x_enc, x_mark_enc, x_dec, x_mark_dec, mask)
            return dec_out  # [B, L, D]
        if self.task_name == 'anomaly_detection':
            dec_out = self.anomaly_detection(x_enc)
            return dec_out  # [B, L, D]
        if self.task_name == 'classification':
            dec_out = self.classification(x_enc, x_mark_enc)
            return dec_out  # [B, N]
        return None