dsipts 1.1.5__py3-none-any.whl

dsipts/models/informer/attn.py

@@ -0,0 +1,185 @@
+import torch
+import torch.nn as nn
+
+
+import numpy as np
+
+from math import sqrt
+
+
+class TriangularCausalMask():
+    def __init__(self, B, L,device):
+        mask_shape = [B, 1, L, L]
+        with torch.no_grad():
+            self._mask = torch.triu(torch.ones(mask_shape, dtype=torch.bool), diagonal=1).to(device)
+
+    @property
+    def mask(self):
+        return self._mask
+
+class ProbMask():
+    def __init__(self, B, H, L, index, scores,device):
+        _mask = torch.ones(L, scores.shape[-1], dtype=torch.bool).triu(1).to(device)
+        _mask_ex = _mask[None, None, :].expand(B, H, L, scores.shape[-1])
+        indicator = _mask_ex[torch.arange(B)[:, None, None],torch.arange(H)[None, :, None],index, :]
+        self._mask = indicator.view(scores.shape)
+    
+    @property
+    def mask(self):
+        return self._mask   
+
+
+class FullAttention(nn.Module):
+    def __init__(self, mask_flag=True, factor=5, scale=None, attention_dropout=0.1, output_attention=False):
+        super(FullAttention, self).__init__()
+        self.scale = scale
+        self.mask_flag = mask_flag
+        self.output_attention = output_attention
+        self.dropout = nn.Dropout(attention_dropout)
+        
+    def forward(self, queries, keys, values, attn_mask):
+        B, L, H, E = queries.shape
+        _, S, _, D = values.shape
+        scale = self.scale or 1./sqrt(E)
+
+        scores = torch.einsum("blhe,bshe->bhls", queries, keys)
+        if self.mask_flag:
+            if attn_mask is None:
+                attn_mask = TriangularCausalMask(B, L, device=queries.device)
+
+            scores.masked_fill_(attn_mask.mask, -np.inf)
+
+        A = self.dropout(torch.softmax(scale * scores, dim=-1))
+        V = torch.einsum("bhls,bshd->blhd", A, values)
+        
+        if self.output_attention:
+            return (V.contiguous(), A)
+        else:
+            return (V.contiguous(), None)
+
+class ProbAttention(nn.Module):
+    def __init__(self, mask_flag=True, factor=5, scale=None, attention_dropout=0.1, output_attention=False):
+        super(ProbAttention, self).__init__()
+        self.factor = factor
+        self.scale = scale
+        self.mask_flag = mask_flag
+        self.output_attention = output_attention
+        self.dropout = nn.Dropout(attention_dropout)
+
+    def _prob_QK(self, Q, K, sample_k, n_top): # n_top: c*ln(L_q)
+        # Q [B, H, L, D]
+        B, H, L_K, E = K.shape
+        _, _, L_Q, _ = Q.shape
+
+        # calculate the sampled Q_K
+        K_expand = K.unsqueeze(-3).expand(B, H, L_Q, L_K, E)
+        index_sample = torch.randint(L_K, (L_Q, sample_k)) # real U = U_part(factor*ln(L_k))*L_q
+        K_sample = K_expand[:, :, torch.arange(L_Q).unsqueeze(1), index_sample, :]
+        Q_K_sample = torch.matmul(Q.unsqueeze(-2), K_sample.transpose(-2, -1)).squeeze(-2)
+
+        # find the Top_k query with sparisty measurement
+        M = Q_K_sample.max(-1)[0] - torch.div(Q_K_sample.sum(-1), L_K)
+        M_top = M.topk(n_top, sorted=False)[1]
+
+        # use the reduced Q to calculate Q_K
+        Q_reduce = Q[torch.arange(B)[:, None, None],
+                     torch.arange(H)[None, :, None],
+                     M_top, :] # factor*ln(L_q)
+        Q_K = torch.matmul(Q_reduce, K.transpose(-2, -1)) # factor*ln(L_q)*L_k
+
+        return Q_K, M_top
+
+    def _get_initial_context(self, V, L_Q):
+        B, H, L_V, D = V.shape
+        if not self.mask_flag:
+            # V_sum = V.sum(dim=-2)
+            V_sum = V.mean(dim=-2)
+            contex = V_sum.unsqueeze(-2).expand(B, H, L_Q, V_sum.shape[-1]).clone()
+        else: # use mask
+            assert(L_Q == L_V) # requires that L_Q == L_V, i.e. for self-attention only
+            contex = V.cumsum(dim=-2)
+        return contex
+
+    def _update_context(self, context_in, V, scores, index, L_Q, attn_mask):
+        B, H, L_V, D = V.shape
+
+        if self.mask_flag:
+            attn_mask = ProbMask(B, H, L_Q, index, scores, device=V.device)
+            scores.masked_fill_(attn_mask.mask, -np.inf)
+
+        attn = torch.softmax(scores, dim=-1) # nn.Softmax(dim=-1)(scores)
+
+        context_in[torch.arange(B)[:, None, None],
+                   torch.arange(H)[None, :, None],
+                   index, :] = torch.matmul(attn, V).type_as(context_in)
+        if self.output_attention:
+            attns = (torch.ones([B, H, L_V, L_V])/L_V).type_as(attn).to(attn.device)
+            attns[torch.arange(B)[:, None, None], torch.arange(H)[None, :, None], index, :] = attn
+            return (context_in, attns)
+        else:
+            return (context_in, None)
+
+    def forward(self, queries, keys, values, attn_mask):
+        B, L_Q, H, D = queries.shape
+        _, L_K, _, _ = keys.shape
+
+        queries = queries.transpose(2,1)
+        keys = keys.transpose(2,1)
+        values = values.transpose(2,1)
+
+        U_part = self.factor * np.ceil(np.log(L_K)).astype('int').item() # c*ln(L_k)
+        u = self.factor * np.ceil(np.log(L_Q)).astype('int').item() # c*ln(L_q) 
+
+        U_part = U_part if U_part<L_K else L_K
+        u = u if u<L_Q else L_Q
+        
+        scores_top, index = self._prob_QK(queries, keys, sample_k=U_part, n_top=u) 
+
+        # add scale factor
+        scale = self.scale or 1./sqrt(D)
+        if scale is not None:
+            scores_top = scores_top * scale
+        # get the context
+        context = self._get_initial_context(values, L_Q)
+        # update the context with selected top_k queries
+        context, attn = self._update_context(context, values, scores_top, index, L_Q, attn_mask)
+        
+        return context.transpose(2,1).contiguous(), attn
+
+
+class AttentionLayer(nn.Module):
+    def __init__(self, attention, d_model, n_heads, 
+                 d_keys=None, d_values=None, mix=False):
+        super(AttentionLayer, self).__init__()
+
+        d_keys = d_keys or (d_model//n_heads)
+        d_values = d_values or (d_model//n_heads)
+
+        self.inner_attention = attention
+        self.query_projection = nn.Linear(d_model, d_keys * n_heads)
+        self.key_projection = nn.Linear(d_model, d_keys * n_heads)
+        self.value_projection = nn.Linear(d_model, d_values * n_heads)
+        self.out_projection = nn.Linear(d_values * n_heads, d_model)
+        self.n_heads = n_heads
+        self.mix = mix
+
+    def forward(self, queries, keys, values, attn_mask):
+        B, L, _ = queries.shape
+        _, S, _ = keys.shape
+        H = self.n_heads
+
+        queries = self.query_projection(queries).view(B, L, H, -1)
+        keys = self.key_projection(keys).view(B, S, H, -1)
+        values = self.value_projection(values).view(B, S, H, -1)
+
+        out, attn = self.inner_attention(
+            queries,
+            keys,
+            values,
+            attn_mask
+        )
+        if self.mix:
+            out = out.transpose(2,1).contiguous()
+        out = out.view(B, L, -1)
+
+        return self.out_projection(out), attn

dsipts/models/informer/decoder.py

@@ -0,0 +1,50 @@
+import torch.nn as nn
+import torch.nn.functional as F
+
+class DecoderLayer(nn.Module):
+    def __init__(self, self_attention, cross_attention, d_model, d_ff=None,
+                 dropout=0.1, activation="relu"):
+        super(DecoderLayer, self).__init__()
+        d_ff = d_ff or 4*d_model
+        self.self_attention = self_attention
+        self.cross_attention = cross_attention
+        self.conv1 = nn.Conv1d(in_channels=d_model, out_channels=d_ff, kernel_size=1)
+        self.conv2 = nn.Conv1d(in_channels=d_ff, out_channels=d_model, kernel_size=1)
+        self.norm1 = nn.LayerNorm(d_model)
+        self.norm2 = nn.LayerNorm(d_model)
+        self.norm3 = nn.LayerNorm(d_model)
+        self.dropout = nn.Dropout(dropout)
+        self.activation = F.relu if activation == "relu" else F.gelu
+
+    def forward(self, x, cross, x_mask=None, cross_mask=None):
+        x = x + self.dropout(self.self_attention(
+            x, x, x,
+            attn_mask=x_mask
+        )[0])
+        x = self.norm1(x)
+
+        x = x + self.dropout(self.cross_attention(
+            x, cross, cross,
+            attn_mask=cross_mask
+        )[0])
+
+        y = x = self.norm2(x)
+        y = self.dropout(self.activation(self.conv1(y.transpose(-1,1))))
+        y = self.dropout(self.conv2(y).transpose(-1,1))
+
+        return self.norm3(x+y)
+
+class Decoder(nn.Module):
+    def __init__(self, layers, norm_layer=None):
+        super(Decoder, self).__init__()
+        self.layers = nn.ModuleList(layers)
+        self.norm = norm_layer
+
+    def forward(self, x, cross, x_mask=None, cross_mask=None):
+        for layer in self.layers:
+            x = layer(x, cross, x_mask=x_mask, cross_mask=cross_mask)
+
+        if self.norm is not None:
+            x = self.norm(x)
+
+        return x

dsipts/models/informer/embed.py

@@ -0,0 +1,125 @@
+import torch
+import torch.nn as nn
+
+import math
+
+class PositionalEmbedding(nn.Module):
+    def __init__(self, d_model, max_len=5000):
+        super(PositionalEmbedding, self).__init__()
+        # Compute the positional encodings once in log space.
+        pe = torch.zeros(max_len, d_model).float()
+        pe.require_grad = False
+
+        position = torch.arange(0, max_len).float().unsqueeze(1)
+        div_term = (torch.arange(0, d_model, 2).float() * -(math.log(10000.0) / d_model)).exp()
+
+        pe[:, 0::2] = torch.sin(position * div_term)
+        pe[:, 1::2] = torch.cos(position * div_term)
+
+        pe = pe.unsqueeze(0)
+        self.register_buffer('pe', pe)
+
+    def forward(self, x):
+        return self.pe[:, :x.size(1)]
+
+class TokenEmbedding(nn.Module):
+    def __init__(self, c_in, d_model):
+        super(TokenEmbedding, self).__init__()
+        padding = 1 if torch.__version__>='1.5.0' else 2
+        self.tokenConv = nn.Conv1d(in_channels=c_in, out_channels=d_model, 
+                                    kernel_size=3, padding=padding, padding_mode='circular')
+        for m in self.modules():
+            if isinstance(m, nn.Conv1d):
+                nn.init.kaiming_normal_(m.weight,mode='fan_in',nonlinearity='leaky_relu')
+
+    def forward(self, x):
+        x = self.tokenConv(x.permute(0, 2, 1)).transpose(1,2)
+        return x
+
+class FixedEmbedding(nn.Module):
+    def __init__(self, c_in, d_model):
+        super(FixedEmbedding, self).__init__()
+
+        w = torch.zeros(c_in, d_model).float()
+        w.require_grad = False
+
+        position = torch.arange(0, c_in).float().unsqueeze(1)
+        div_term = (torch.arange(0, d_model, 2).float() * -(math.log(10000.0) / d_model)).exp()
+
+        w[:, 0::2] = torch.sin(position * div_term)
+        w[:, 1::2] = torch.cos(position * div_term)
+
+        self.emb = nn.Embedding(c_in, d_model)
+        self.emb.weight = nn.Parameter(w, requires_grad=False)
+
+    def forward(self, x):
+        return self.emb(x).detach()
+
+class TemporalEmbedding(nn.Module):
+    def __init__(self, d_model, embed_type='fixed', freq='h'):
+        super(TemporalEmbedding, self).__init__()
+
+        minute_size = 4
+        hour_size = 24
+        weekday_size = 7
+        day_size = 32
+        month_size = 13
+
+        Embed = FixedEmbedding if embed_type=='fixed' else nn.Embedding
+        if freq=='t':
+            self.minute_embed = Embed(minute_size, d_model)
+        self.hour_embed = Embed(hour_size, d_model)
+        self.weekday_embed = Embed(weekday_size, d_model)
+        self.day_embed = Embed(day_size, d_model)
+        self.month_embed = Embed(month_size, d_model)
+    
+    def forward(self, x):
+        x = x.long()
+        
+        minute_x = self.minute_embed(x[:,:,4]) if hasattr(self, 'minute_embed') else 0.
+        hour_x = self.hour_embed(x[:,:,3])
+        weekday_x = self.weekday_embed(x[:,:,2])
+        day_x = self.day_embed(x[:,:,1])
+        month_x = self.month_embed(x[:,:,0])
+        
+        return hour_x + weekday_x + day_x + month_x + minute_x
+
+class TimeFeatureEmbedding(nn.Module):
+    def __init__(self, d_model, embed_type='timeF', freq='h'):
+        super(TimeFeatureEmbedding, self).__init__()
+
+        freq_map = {'h':4, 't':5, 's':6, 'm':1, 'a':1, 'w':2, 'd':3, 'b':3}
+        d_inp = freq_map[freq]
+        self.embed = nn.Linear(d_inp, d_model)
+    
+    def forward(self, x):
+        return self.embed(x)
+
+
+    
+class DataEmbedding(nn.Module):
+    def __init__(self, c_in, d_model, embs, dropout=0.1):
+        super(DataEmbedding, self).__init__()
+
+        self.value_embedding = TokenEmbedding(c_in=c_in, d_model=d_model)
+        self.position_embedding = PositionalEmbedding(d_model=d_model)
+        #self.temporal_embedding = TemporalEmbedding(d_model=d_model, freq=freq)
+        self.emb_list = nn.ModuleList()
+        if embs is not None:
+            for k in embs:
+                self.emb_list.append(nn.Embedding(k+1,d_model))
+        
+        self.dropout = nn.Dropout(p=dropout)
+
+    def forward(self, x, x_mark):
+        tot = None
+        for i in range(len(self.emb_list)):
+            if tot is None:
+                tot = self.emb_list[i](x_mark[:,:,i])
+            else:
+                tot += self.emb_list[i](x_mark[:,:,i])
+        if tot is not None:
+            x = self.value_embedding(x) + tot + self.position_embedding(x)
+        else:
+            x = self.value_embedding(x) +  self.position_embedding(x)
+        return self.dropout(x)

dsipts/models/informer/encoder.py

@@ -0,0 +1,100 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+class ConvLayer(nn.Module):
+    def __init__(self, c_in):
+        super(ConvLayer, self).__init__()
+        padding = 1 if torch.__version__>='1.5.0' else 2
+        self.downConv = nn.Conv1d(in_channels=c_in,
+                                  out_channels=c_in,
+                                  kernel_size=3,
+                                  padding=padding,
+                                  padding_mode='circular')
+        self.norm = nn.BatchNorm1d(c_in)
+        self.activation = nn.ELU()
+        self.maxPool = nn.MaxPool1d(kernel_size=3, stride=2, padding=1)
+
+    def forward(self, x):
+        x = self.downConv(x.permute(0, 2, 1))
+        x = self.norm(x)
+        x = self.activation(x)
+        x = self.maxPool(x)
+        x = x.transpose(1,2)
+        return x
+
+class EncoderLayer(nn.Module):
+    def __init__(self, attention, d_model, d_ff=None, dropout=0.1, activation="relu"):
+        super(EncoderLayer, self).__init__()
+        d_ff = d_ff or 4*d_model
+        self.attention = attention
+        self.conv1 = nn.Conv1d(in_channels=d_model, out_channels=d_ff, kernel_size=1)
+        self.conv2 = nn.Conv1d(in_channels=d_ff, out_channels=d_model, kernel_size=1)
+        self.norm1 = nn.LayerNorm(d_model)
+        self.norm2 = nn.LayerNorm(d_model)
+        self.dropout = nn.Dropout(dropout)
+        self.activation = F.relu if activation == "relu" else F.gelu
+
+    def forward(self, x, attn_mask=None):
+        # x [B, L, D]
+        # x = x + self.dropout(self.attention(
+        #     x, x, x,
+        #     attn_mask = attn_mask
+        # ))
+        new_x, attn = self.attention(
+            x, x, x,
+            attn_mask = attn_mask
+        )
+        x = x + self.dropout(new_x)
+
+        y = x = self.norm1(x)
+        y = self.dropout(self.activation(self.conv1(y.transpose(-1,1))))
+        y = self.dropout(self.conv2(y).transpose(-1,1))
+
+        return self.norm2(x+y), attn
+
+class Encoder(nn.Module):
+    def __init__(self, attn_layers, conv_layers=None, norm_layer=None):
+        super(Encoder, self).__init__()
+        self.attn_layers = nn.ModuleList(attn_layers)
+        self.conv_layers = nn.ModuleList(conv_layers) if conv_layers is not None else None
+        self.norm = norm_layer
+
+    def forward(self, x, attn_mask=None):
+        # x [B, L, D]
+        attns = []
+        if self.conv_layers is not None:
+            for attn_layer, conv_layer in zip(self.attn_layers, self.conv_layers):
+                x, attn = attn_layer(x, attn_mask=attn_mask)
+                x = conv_layer(x)
+                attns.append(attn)
+            x, attn = self.attn_layers[-1](x, attn_mask=attn_mask)
+            attns.append(attn)
+        else:
+            for attn_layer in self.attn_layers:
+                x, attn = attn_layer(x, attn_mask=attn_mask)
+                attns.append(attn)
+
+        if self.norm is not None:
+            x = self.norm(x)
+
+        return x, attns
+
+class EncoderStack(nn.Module):
+    def __init__(self, encoders, inp_lens):
+        super(EncoderStack, self).__init__()
+        self.encoders = nn.ModuleList(encoders)
+        self.inp_lens = inp_lens
+
+    def forward(self, x, attn_mask=None):
+        # x [B, L, D]
+        x_stack = []
+        attns = []
+        for i_len, encoder in zip(self.inp_lens, self.encoders):
+            inp_len = x.shape[1]//(2**i_len)
+            x_s, attn = encoder(x[:, -inp_len:, :])
+            x_stack.append(x_s)
+            attns.append(attn)
+        x_stack = torch.cat(x_stack, -2)
+        
+        return x_stack, attns

dsipts/models/itransformer/Embed.py

@@ -0,0 +1,142 @@
+import torch
+import torch.nn as nn
+import math
+
+
+class PositionalEmbedding(nn.Module):
+    def __init__(self, d_model, max_len=5000):
+        super(PositionalEmbedding, self).__init__()
+        # Compute the positional encodings once in log space.
+        pe = torch.zeros(max_len, d_model).float()
+        pe.require_grad = False
+
+        position = torch.arange(0, max_len).float().unsqueeze(1)
+        div_term = (torch.arange(0, d_model, 2).float()
+                    * -(math.log(10000.0) / d_model)).exp()
+
+        pe[:, 0::2] = torch.sin(position * div_term)
+        pe[:, 1::2] = torch.cos(position * div_term)
+
+        pe = pe.unsqueeze(0)
+        self.register_buffer('pe', pe)
+
+    def forward(self, x):
+        return self.pe[:, :x.size(1)]
+
+
+class TokenEmbedding(nn.Module):
+    def __init__(self, c_in, d_model):
+        super(TokenEmbedding, self).__init__()
+        padding = 1 if torch.__version__ >= '1.5.0' else 2
+        self.tokenConv = nn.Conv1d(in_channels=c_in, out_channels=d_model,
+                                   kernel_size=3, padding=padding, padding_mode='circular', bias=False)
+        for m in self.modules():
+            if isinstance(m, nn.Conv1d):
+                nn.init.kaiming_normal_(
+                    m.weight, mode='fan_in', nonlinearity='leaky_relu')
+
+    def forward(self, x):
+        x = self.tokenConv(x.permute(0, 2, 1)).transpose(1, 2)
+        return x
+
+
+class FixedEmbedding(nn.Module):
+    def __init__(self, c_in, d_model):
+        super(FixedEmbedding, self).__init__()
+
+        w = torch.zeros(c_in, d_model).float()
+        w.require_grad = False
+
+        position = torch.arange(0, c_in).float().unsqueeze(1)
+        div_term = (torch.arange(0, d_model, 2).float()
+                    * -(math.log(10000.0) / d_model)).exp()
+
+        w[:, 0::2] = torch.sin(position * div_term)
+        w[:, 1::2] = torch.cos(position * div_term)
+
+        self.emb = nn.Embedding(c_in, d_model)
+        self.emb.weight = nn.Parameter(w, requires_grad=False)
+
+    def forward(self, x):
+        return self.emb(x).detach()
+
+
+class TemporalEmbedding(nn.Module):
+    def __init__(self, d_model, embed_type='fixed', freq='h'):
+        super(TemporalEmbedding, self).__init__()
+
+        minute_size = 4
+        hour_size = 24
+        weekday_size = 7
+        day_size = 32
+        month_size = 13
+
+        Embed = FixedEmbedding if embed_type == 'fixed' else nn.Embedding
+        if freq == 't':
+            self.minute_embed = Embed(minute_size, d_model)
+        self.hour_embed = Embed(hour_size, d_model)
+        self.weekday_embed = Embed(weekday_size, d_model)
+        self.day_embed = Embed(day_size, d_model)
+        self.month_embed = Embed(month_size, d_model)
+
+    def forward(self, x):
+        x = x.long()
+        minute_x = self.minute_embed(x[:, :, 4]) if hasattr(
+            self, 'minute_embed') else 0.
+        hour_x = self.hour_embed(x[:, :, 3])
+        weekday_x = self.weekday_embed(x[:, :, 2])
+        day_x = self.day_embed(x[:, :, 1])
+        month_x = self.month_embed(x[:, :, 0])
+
+        return hour_x + weekday_x + day_x + month_x + minute_x
+
+
+class TimeFeatureEmbedding(nn.Module):
+    def __init__(self, d_model, embed_type='timeF', freq='h'):
+        super(TimeFeatureEmbedding, self).__init__()
+
+        freq_map = {'h': 4, 't': 5, 's': 6,
+                    'm': 1, 'a': 1, 'w': 2, 'd': 3, 'b': 3}
+        d_inp = freq_map[freq]
+        self.embed = nn.Linear(d_inp, d_model, bias=False)
+
+    def forward(self, x):
+        return self.embed(x)
+
+
+class DataEmbedding(nn.Module):
+    def __init__(self, c_in, d_model, embed_type='fixed', freq='h', dropout=0.1):
+        super(DataEmbedding, self).__init__()
+
+        self.value_embedding = TokenEmbedding(c_in=c_in, d_model=d_model)
+        self.position_embedding = PositionalEmbedding(d_model=d_model)
+        self.temporal_embedding = TemporalEmbedding(d_model=d_model, embed_type=embed_type,
+                                                    freq=freq) if embed_type != 'timeF' else TimeFeatureEmbedding(
+            d_model=d_model, embed_type=embed_type, freq=freq)
+        self.dropout = nn.Dropout(p=dropout)
+
+    def forward(self, x, x_mark):
+        if x_mark is None:
+            x = self.value_embedding(x) + self.position_embedding(x)
+        else:
+            x = self.value_embedding(
+                x) + self.temporal_embedding(x_mark) + self.position_embedding(x)
+        return self.dropout(x)
+
+
+class DataEmbedding_inverted(nn.Module):
+    def __init__(self, c_in, d_model, embed_type='fixed', freq='h', dropout=0.1):
+        super(DataEmbedding_inverted, self).__init__()
+        self.value_embedding = nn.Linear(c_in, d_model)
+        self.dropout = nn.Dropout(p=dropout)
+
+    def forward(self, x, x_mark):
+        x = x.permute(0, 2, 1)
+        # x: [Batch Variate Time]
+        if x_mark is None:
+            x = self.value_embedding(x)
+        else:
+            # the potential to take covariates (e.g. timestamps) as tokens
+            x = self.value_embedding(torch.cat([x, x_mark.permute(0, 2, 1)], 1)) 
+        # x: [Batch Variate d_model]
+        return self.dropout(x)