Add GIP-MI reliability framework example reference

reliability/GIP-MI-demo/GCN-Informer/README.md

@@ -0,0 +1,32 @@
+# GCN-Informer
+
+本目录包含 GCN-Informer 的训练/验证/测试代码，以及配套的 CPU / Memory / Response Time 数据集样例。
+
+## 目录结构
+
+- `train_gcn_informer.py`：训练/验证/测试入口（默认使用 `data/myData/2024-05-5_train_constant.csv`）
+- `data/myData/`：数据集 CSV
+- `models/`：模型组件（Informer + GCN）
+- `utils/`：mask 与指标计算
+- `checkpoints/`：默认保存 `checkpoints/gcn_informer/best_model.pt`
+- `results/`：默认输出 `results/gcn_informer/test_predictions.csv`
+
+## 安装依赖
+
+```bash
+pip install -r requirements.txt
+```
+
+## 运行
+
+默认训练（结束后会跑 test 并导出预测 CSV）：
+
+```bash
+python train_gcn_informer.py
+```
+
+指定数据文件：
+
+```bash
+python train_gcn_informer.py --data_path data/myData/2024-07-08_train_non-constant.csv
+```

reliability/GIP-MI-demo/GCN-Informer/models/attn.py

@@ -0,0 +1,163 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+import numpy as np
+
+from math import sqrt
+from utils.masking import TriangularCausalMask, ProbMask
+
+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

reliability/GIP-MI-demo/GCN-Informer/models/decoder.py

@@ -0,0 +1,51 @@
+import torch
+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

reliability/GIP-MI-demo/GCN-Informer/models/embed.py

@@ -0,0 +1,131 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+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__()
+        # torch.__version__ can be like "2.1.0+cu121"; avoid lexicographic compare (e.g. "1.10" vs "1.5").
+        version_core = torch.__version__.split("+", 1)[0]
+        major_minor = version_core.split(".", 2)[:2]
+        try:
+            major, minor = (int(major_minor[0]), int(major_minor[1]))
+        except Exception:
+            major, minor = (0, 0)
+        padding = 1 if (major, minor) >= (1, 5) 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='t'):
+        super(TemporalEmbedding, self).__init__()
+        self.freq = freq
+        # 根据频率定义输入特征维度（与 create_time 的输出维度匹配）
+        self.input_features = 5  # second_sin, second_cos, minute_sin, minute_cos
+        # 使用线性层将时间特征映射到 d_model
+        self.linear = nn.Linear(self.input_features, d_model)
+
+    def forward(self, x):
+        # x 的形状为 (batch_size, seq_len, input_features)
+        return self.linear(x)
+
+
+# class TemporalEmbedding(nn.Module):
+#     def __init__(self, d_model, embed_type='fixed', freq='t'):
+#         super(TemporalEmbedding, self).__init__()
+#
+#         minute_size = 60;
+#         hour_size = 24;
+#         second_size = 60
+#
+#         Embed = FixedEmbedding if embed_type == 'fixed' else nn.Embedding
+#         self.minute_embed = Embed(minute_size, d_model)
+#         self.hour_embed = Embed(hour_size, d_model)
+#         self.second_embed = Embed(second_size, d_model)
+#
+#     def forward(self, x):
+#         x = x.long()
+#         second_x = self.second_embed(x[:, :, 0])
+#         minute_x = self.minute_embed(x[:, :, 1]) if hasattr(self, 'minute_embed') else 0.
+#         hour_x = self.hour_embed(x[:, :, 2])
+#         return second_x + minute_x + hour_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, 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)
+        # 统一使用 TemporalEmbedding
+        self.temporal_embedding = TemporalEmbedding(d_model=d_model, freq=freq)
+        self.dropout = nn.Dropout(p=dropout)
+
+    def forward(self, x, x_mark):
+        x1 = self.value_embedding(x)
+        x2 = self.position_embedding(x)
+        x3 = self.temporal_embedding(x_mark)  # x_mark 来自 create_time 的输出
+        x = x1 + x2 + x3
+        x = x1 + x2 + x3
+        return self.dropout(x)