File size: 8,684 Bytes
e1ccef5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.fft
from layers.Embed import DataEmbedding
from layers.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
    frequency_list = abs(xf).mean(0).mean(-1)
    frequency_list[0] = 0
    _, top_list = torch.topk(frequency_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
            out = out.reshape(B, length // period, period,
                              N).permute(0, 3, 1, 2).contiguous()
            # 2D conv: from 1d Variation to 2d Variation
            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
        res = res + x
        return res


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 == 'long_term_forecast' or self.task_name == 'short_term_forecast':
            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 == 'imputation' or self.task_name == '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-stationary 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)  # [B,T,C]
        enc_out = self.predict_linear(enc_out.permute(0, 2, 1)).permute(
            0, 2, 1)  # align temporal dimension
        # TimesNet
        for i in range(self.layer):
            enc_out = self.layer_norm(self.model[i](enc_out))
        # porject 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-stationary Transformer
        means = torch.sum(x_enc, dim=1) / torch.sum(mask == 1, dim=1)
        means = means.unsqueeze(1).detach()
        x_enc = x_enc - means
        x_enc = x_enc.masked_fill(mask == 0, 0)
        stdev = torch.sqrt(torch.sum(x_enc * x_enc, dim=1) /
                           torch.sum(mask == 1, dim=1) + 1e-5)
        stdev = stdev.unsqueeze(1).detach()
        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))
        # porject 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-stationary 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, None)  # [B,T,C]
        # TimesNet
        for i in range(self.layer):
            enc_out = self.layer_norm(self.model[i](enc_out))
        # porject 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 don't 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 == 'long_term_forecast' or self.task_name == '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