notebooks/06_dynamic_graph.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "afa53af3",
   "metadata": {},
   "source": [
    "# 06 — Dynamic-Graph iTransformer (v3)\n",
    "\n",
    "## v3 Improvements\n",
    "- **Cross-battery split** (no data leakage)\n",
    "- **18 features** per timestep (6 new physics-informed features)\n",
    "\n",
    "## Architecture\n",
    "- **iTransformer backbone** with inverted (feature-wise) attention\n",
    "- **Dynamic Graph Convolution** layer that learns inter-feature adjacency dynamically\n",
    "- Fuses local (graph) + global (attention) representations\n",
    "- Built with TensorFlow/Keras"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "20d26377",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-24T18:15:16.341799Z",
     "iopub.status.busy": "2026-02-24T18:15:16.341799Z",
     "iopub.status.idle": "2026-02-24T18:15:18.735982Z",
     "shell.execute_reply": "2026-02-24T18:15:18.735982Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TensorFlow: 2.20.0\n",
      "GPUs: []\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'root': WindowsPath('E:/VIT/aiBatteryLifecycle/artifacts/v3'),\n",
       " 'models_classical': WindowsPath('E:/VIT/aiBatteryLifecycle/artifacts/v3/models/classical'),\n",
       " 'models_deep': WindowsPath('E:/VIT/aiBatteryLifecycle/artifacts/v3/models/deep'),\n",
       " 'models_ensemble': WindowsPath('E:/VIT/aiBatteryLifecycle/artifacts/v3/models/ensemble'),\n",
       " 'scalers': WindowsPath('E:/VIT/aiBatteryLifecycle/artifacts/v3/scalers'),\n",
       " 'figures': WindowsPath('E:/VIT/aiBatteryLifecycle/artifacts/v3/figures'),\n",
       " 'results': WindowsPath('E:/VIT/aiBatteryLifecycle/artifacts/v3/results'),\n",
       " 'logs': WindowsPath('E:/VIT/aiBatteryLifecycle/artifacts/v3/logs')}"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import sys, os\n",
    "sys.path.insert(0, os.path.abspath(\"..\"))\n",
    "VERSION = \"3.0\"\n",
    "VERSION_DIR = f\"v{int(float(VERSION))}\"\n",
    "\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "import tensorflow as tf\n",
    "from src.models.deep.itransformer import build_dynamic_graph_itransformer\n",
    "from src.evaluation.metrics import regression_metrics, tolerance_accuracy\n",
    "from src.utils.plotting import save_fig\n",
    "from src.utils.config import (\n",
    "    ARTIFACTS_DIR, FIGURES_DIR, MODELS_DIR,\n",
    "    get_version_paths, ensure_version_dirs,\n",
    "    WINDOW_SIZE, BATCH_SIZE, MAX_EPOCHS, EARLY_STOP_PATIENCE,\n",
    "    TRANSFORMER_D_MODEL, TRANSFORMER_NHEAD, TRANSFORMER_LAYERS, DROPOUT,\n",
    ")\n",
    "\n",
    "print(f\"TensorFlow: {tf.__version__}\")\n",
    "print(f\"GPUs: {tf.config.list_physical_devices('GPU')}\")\n",
    "plt.style.use(\"seaborn-v0_8-whitegrid\")\n",
    "\n",
    "# version paths\n",
    "v3 = get_version_paths(VERSION_DIR)\n",
    "ensure_version_dirs(VERSION_DIR)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b806d3a",
   "metadata": {},
   "source": [
    "## 1. Load & Prepare Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "bdd1403f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-24T18:15:18.738372Z",
     "iopub.status.busy": "2026-02-24T18:15:18.738372Z",
     "iopub.status.idle": "2026-02-24T18:15:18.758405Z",
     "shell.execute_reply": "2026-02-24T18:15:18.758405Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train: (1444, 32, 18) | Test: (290, 32, 18)\n",
      "Overlap: NONE ✓\n"
     ]
    }
   ],
   "source": [
    "V3_FEATURES = v3[\"root\"] / \"features\"\n",
    "data = np.load(str(V3_FEATURES / \"battery_sequences.npz\"), allow_pickle=True)\n",
    "X_multi = data[\"X_multi\"]\n",
    "y_multi = data[\"y_multi\"]\n",
    "bids = data[\"bids_multi\"]\n",
    "\n",
    "# ── v3 FIX: Cross-battery grouped split ──\n",
    "unique_bids = np.unique(bids)\n",
    "rng = np.random.RandomState(42)\n",
    "shuffled = unique_bids.copy()\n",
    "rng.shuffle(shuffled)\n",
    "n_train = max(1, int(len(shuffled) * 0.8))\n",
    "train_bats = set(shuffled[:n_train])\n",
    "test_bats = set(shuffled[n_train:])\n",
    "\n",
    "train_mask = np.isin(bids, list(train_bats))\n",
    "test_mask = np.isin(bids, list(test_bats))\n",
    "\n",
    "X_train, y_train = X_multi[train_mask], y_multi[train_mask]\n",
    "X_test, y_test = X_multi[test_mask], y_multi[test_mask]\n",
    "\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "n_samples, seq_len, n_feat = X_train.shape\n",
    "scaler = StandardScaler().fit(X_train.reshape(-1, n_feat))\n",
    "X_train = scaler.transform(X_train.reshape(-1, n_feat)).reshape(n_samples, seq_len, n_feat)\n",
    "X_test = scaler.transform(X_test.reshape(-1, n_feat)).reshape(X_test.shape[0], seq_len, n_feat)\n",
    "\n",
    "print(f\"Train: {X_train.shape} | Test: {X_test.shape}\")\n",
    "print(f\"Overlap: {train_bats & test_bats if train_bats & test_bats else 'NONE ✓'}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "71722721",
   "metadata": {},
   "source": [
    "## 2. Build Dynamic-Graph iTransformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "06243bd4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-24T18:15:18.760606Z",
     "iopub.status.busy": "2026-02-24T18:15:18.759601Z",
     "iopub.status.idle": "2026-02-24T18:15:19.494309Z",
     "shell.execute_reply": "2026-02-24T18:15:19.494309Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From e:\\VIT\\aiBatteryLifecycle\\venv\\Lib\\site-packages\\keras\\src\\backend\\tensorflow\\core.py:232: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"DynamicGraph_iTransformer\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"DynamicGraph_iTransformer\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ input_layer (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">18</span>)         │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dyn_graph (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">DynamicGraphConv</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">18</span>)         │           <span style=\"color: #00af00; text-decoration-color: #00af00\">378</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ proj (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)         │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,216</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_feat_0 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">FeatureWiseMHA</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)         │         <span style=\"color: #00af00; text-decoration-color: #00af00\">8,480</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_token_0 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">TokenWiseMHA</span>)       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)         │        <span style=\"color: #00af00; text-decoration-color: #00af00\">16,768</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_ff_0 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv1DFeedForward</span>)     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)         │        <span style=\"color: #00af00; text-decoration-color: #00af00\">33,216</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_feat_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">FeatureWiseMHA</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)         │         <span style=\"color: #00af00; text-decoration-color: #00af00\">8,480</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_token_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">TokenWiseMHA</span>)       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)         │        <span style=\"color: #00af00; text-decoration-color: #00af00\">16,768</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_ff_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv1DFeedForward</span>)     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)         │        <span style=\"color: #00af00; text-decoration-color: #00af00\">33,216</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ global_average_pooling1d        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling1D</span>)        │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │         <span style=\"color: #00af00; text-decoration-color: #00af00\">8,320</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_10 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)            │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">129</span> │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ input_layer (\u001b[38;5;33mInputLayer\u001b[0m)        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m18\u001b[0m)         │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dyn_graph (\u001b[38;5;33mDynamicGraphConv\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m18\u001b[0m)         │           \u001b[38;5;34m378\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ proj (\u001b[38;5;33mDense\u001b[0m)                    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)         │         \u001b[38;5;34m1,216\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_feat_0 (\u001b[38;5;33mFeatureWiseMHA\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)         │         \u001b[38;5;34m8,480\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_token_0 (\u001b[38;5;33mTokenWiseMHA\u001b[0m)       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)         │        \u001b[38;5;34m16,768\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_ff_0 (\u001b[38;5;33mConv1DFeedForward\u001b[0m)     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)         │        \u001b[38;5;34m33,216\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_feat_1 (\u001b[38;5;33mFeatureWiseMHA\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)         │         \u001b[38;5;34m8,480\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_token_1 (\u001b[38;5;33mTokenWiseMHA\u001b[0m)       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)         │        \u001b[38;5;34m16,768\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dg_ff_1 (\u001b[38;5;33mConv1DFeedForward\u001b[0m)     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)         │        \u001b[38;5;34m33,216\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ global_average_pooling1d        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │             \u001b[38;5;34m0\u001b[0m │\n",
       "│ (\u001b[38;5;33mGlobalAveragePooling1D\u001b[0m)        │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │         \u001b[38;5;34m8,320\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_10 (\u001b[38;5;33mDropout\u001b[0m)            │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │           \u001b[38;5;34m129\u001b[0m │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">126,971</span> (495.98 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m126,971\u001b[0m (495.98 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">126,971</span> (495.98 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m126,971\u001b[0m (495.98 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Total parameters: 126,971\n"
     ]
    }
   ],
   "source": [
    "dg_model = build_dynamic_graph_itransformer(\n",
    "    seq_len=seq_len, n_features=n_feat,\n",
    "    d_model=TRANSFORMER_D_MODEL, n_heads=TRANSFORMER_NHEAD,\n",
    "    n_blocks=TRANSFORMER_LAYERS, dropout=DROPOUT,\n",
    ")\n",
    "dg_model.compile(optimizer=tf.keras.optimizers.Adam(1e-3), loss=\"mse\", metrics=[\"mae\"])\n",
    "dg_model.summary()\n",
    "print(f\"\\nTotal parameters: {dg_model.count_params():,}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f6d25fe4",
   "metadata": {},
   "source": [
    "## 3. Train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a5f69f03",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-24T18:15:19.496320Z",
     "iopub.status.busy": "2026-02-24T18:15:19.495314Z",
     "iopub.status.idle": "2026-02-24T18:15:53.431445Z",
     "shell.execute_reply": "2026-02-24T18:15:53.431445Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 32ms/step - loss: 3091.5396 - mae: 51.7391 - val_loss: 1808.4214 - val_mae: 40.1193 - learning_rate: 0.0010\n",
      "Epoch 2/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 793.2542 - mae: 23.6231 - val_loss: 371.9945 - val_mae: 15.9813 - learning_rate: 0.0010\n",
      "Epoch 3/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 428.0450 - mae: 14.9359 - val_loss: 315.3958 - val_mae: 14.0599 - learning_rate: 0.0010\n",
      "Epoch 4/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 296.4546 - mae: 12.0104 - val_loss: 282.2690 - val_mae: 12.6580 - learning_rate: 0.0010\n",
      "Epoch 5/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 181.8011 - mae: 9.7716 - val_loss: 184.7205 - val_mae: 9.8936 - learning_rate: 0.0010\n",
      "Epoch 6/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 153.6744 - mae: 8.8523 - val_loss: 205.1246 - val_mae: 10.5663 - learning_rate: 0.0010\n",
      "Epoch 7/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 100.8296 - mae: 7.2005 - val_loss: 371.5007 - val_mae: 12.6232 - learning_rate: 0.0010\n",
      "Epoch 8/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 79.6129 - mae: 6.2091 - val_loss: 291.8404 - val_mae: 11.5495 - learning_rate: 0.0010\n",
      "Epoch 9/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 67.0881 - mae: 5.8151 - val_loss: 368.3191 - val_mae: 12.4728 - learning_rate: 0.0010\n",
      "Epoch 10/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 62.7399 - mae: 5.5084 - val_loss: 275.5745 - val_mae: 11.3943 - learning_rate: 0.0010\n",
      "Epoch 11/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 53.1554 - mae: 5.1777 - val_loss: 108.5394 - val_mae: 7.6967 - learning_rate: 0.0010\n",
      "Epoch 12/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 53.2685 - mae: 5.1074 - val_loss: 88.6493 - val_mae: 6.4917 - learning_rate: 0.0010\n",
      "Epoch 13/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 52.3831 - mae: 5.0360 - val_loss: 247.1583 - val_mae: 9.8650 - learning_rate: 0.0010\n",
      "Epoch 14/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 50.9874 - mae: 4.9830 - val_loss: 335.2363 - val_mae: 11.0505 - learning_rate: 0.0010\n",
      "Epoch 15/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 26ms/step - loss: 55.7953 - mae: 4.9635 - val_loss: 233.2992 - val_mae: 12.1112 - learning_rate: 0.0010\n",
      "Epoch 16/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 52.3018 - mae: 4.8491 - val_loss: 244.8007 - val_mae: 9.7996 - learning_rate: 0.0010\n",
      "Epoch 17/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 50.3325 - mae: 4.8027 - val_loss: 302.4027 - val_mae: 10.1342 - learning_rate: 0.0010\n",
      "Epoch 18/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 41.4454 - mae: 4.4929 - val_loss: 162.1327 - val_mae: 9.9863 - learning_rate: 0.0010\n",
      "Epoch 19/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 36.1780 - mae: 4.4173 - val_loss: 467.9168 - val_mae: 13.5968 - learning_rate: 0.0010\n",
      "Epoch 20/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 42.3492 - mae: 4.7240 - val_loss: 337.6486 - val_mae: 11.4763 - learning_rate: 0.0010\n",
      "Epoch 21/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 36.9329 - mae: 4.3181 - val_loss: 571.6833 - val_mae: 14.1304 - learning_rate: 0.0010\n",
      "Epoch 22/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 36.7739 - mae: 4.2882\n",
      "Epoch 22: ReduceLROnPlateau reducing learning rate to 0.0005000000237487257.\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 26ms/step - loss: 41.6395 - mae: 4.4906 - val_loss: 541.0283 - val_mae: 13.3043 - learning_rate: 0.0010\n",
      "Epoch 23/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 31.8018 - mae: 4.2254 - val_loss: 302.2568 - val_mae: 9.9343 - learning_rate: 5.0000e-04\n",
      "Epoch 24/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 30.6312 - mae: 4.1102 - val_loss: 518.4423 - val_mae: 13.3769 - learning_rate: 5.0000e-04\n",
      "Epoch 25/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 27.9765 - mae: 3.9918 - val_loss: 523.5897 - val_mae: 14.2088 - learning_rate: 5.0000e-04\n",
      "Epoch 26/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 29.5072 - mae: 4.0083 - val_loss: 479.3758 - val_mae: 13.5527 - learning_rate: 5.0000e-04\n",
      "Epoch 27/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 28.3697 - mae: 3.9926 - val_loss: 371.6014 - val_mae: 11.7160 - learning_rate: 5.0000e-04\n",
      "Epoch 28/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 27.9337 - mae: 3.9476 - val_loss: 301.0792 - val_mae: 10.6979 - learning_rate: 5.0000e-04\n",
      "Epoch 29/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 25ms/step - loss: 26.6725 - mae: 3.8834 - val_loss: 296.4895 - val_mae: 10.6628 - learning_rate: 5.0000e-04\n",
      "Epoch 30/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 27.9124 - mae: 3.9884 - val_loss: 288.4537 - val_mae: 10.5616 - learning_rate: 5.0000e-04\n",
      "Epoch 31/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 25.1379 - mae: 3.7949 - val_loss: 329.1453 - val_mae: 11.5604 - learning_rate: 5.0000e-04\n",
      "Epoch 32/150\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 27.1272 - mae: 3.9326\n",
      "Epoch 32: ReduceLROnPlateau reducing learning rate to 0.0002500000118743628.\n",
      "\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 28.0986 - mae: 3.9903 - val_loss: 253.3443 - val_mae: 10.0560 - learning_rate: 5.0000e-04\n",
      "Epoch 32: early stopping\n",
      "Restoring model weights from the end of the best epoch: 12.\n",
      "\n",
      "Best epoch: 12\n",
      "Best val loss: 88.649292\n"
     ]
    }
   ],
   "source": [
    "callbacks = [\n",
    "    tf.keras.callbacks.EarlyStopping(\n",
    "        monitor=\"val_loss\", patience=EARLY_STOP_PATIENCE,\n",
    "        restore_best_weights=True, verbose=1,\n",
    "    ),\n",
    "    tf.keras.callbacks.ReduceLROnPlateau(\n",
    "        monitor=\"val_loss\", factor=0.5, patience=10, verbose=1,\n",
    "    ),\n",
    "]\n",
    "\n",
    "history = dg_model.fit(\n",
    "    X_train, y_train,\n",
    "    validation_data=(X_test, y_test),\n",
    "    epochs=MAX_EPOCHS, batch_size=BATCH_SIZE,\n",
    "    callbacks=callbacks, verbose=1,\n",
    ")\n",
    "\n",
    "best_epoch = np.argmin(history.history[\"val_loss\"]) + 1\n",
    "print(f\"\\nBest epoch: {best_epoch}\")\n",
    "print(f\"Best val loss: {min(history.history['val_loss']):.6f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b88c6b3a",
   "metadata": {},
   "source": [
    "## 4. Evaluate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "12650600",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-24T18:15:53.433453Z",
     "iopub.status.busy": "2026-02-24T18:15:53.433453Z",
     "iopub.status.idle": "2026-02-24T18:15:54.126753Z",
     "shell.execute_reply": "2026-02-24T18:15:54.126753Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dynamic-Graph iTransformer Results (v3):\n",
      "  MAE  = 6.4917\n",
      "  RMSE = 9.4154\n",
      "  R²   = 0.7596\n",
      "  MAPE = 15.23%\n",
      "  Tol.Acc (±2%) = 19.66%\n",
      "  Tol.Acc (±5%) = 54.14%\n",
      "Model saved.\n"
     ]
    }
   ],
   "source": [
    "y_pred = dg_model.predict(X_test, verbose=0).flatten()\n",
    "metrics = regression_metrics(y_test, y_pred)\n",
    "metrics[\"tol_2pct\"] = tolerance_accuracy(y_test, y_pred, 2.0)\n",
    "metrics[\"tol_5pct\"] = tolerance_accuracy(y_test, y_pred, 5.0)\n",
    "\n",
    "print(\"Dynamic-Graph iTransformer Results (v3):\")\n",
    "print(f\"  MAE  = {metrics['MAE']:.4f}\")\n",
    "print(f\"  RMSE = {metrics['RMSE']:.4f}\")\n",
    "print(f\"  R²   = {metrics['R2']:.4f}\")\n",
    "print(f\"  MAPE = {metrics['MAPE']:.2f}%\")\n",
    "print(f\"  Tol.Acc (±2%) = {metrics['tol_2pct']:.2%}\")\n",
    "print(f\"  Tol.Acc (±5%) = {metrics['tol_5pct']:.2%}\")\n",
    "\n",
    "dg_model.save(str(v3[\"models_deep\"] / \"dynamic_graph_itransformer.keras\"))\n",
    "print(\"Model saved.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5c7a78fc",
   "metadata": {},
   "source": [
    "## 5. Training Curves"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "77842c13",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-24T18:15:54.128764Z",
     "iopub.status.busy": "2026-02-24T18:15:54.128764Z",
     "iopub.status.idle": "2026-02-24T18:15:54.402919Z",
     "shell.execute_reply": "2026-02-24T18:15:54.402919Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(1, 2, figsize=(14, 5))\n",
    "\n",
    "# Loss\n",
    "axes[0].plot(history.history[\"loss\"], \"b-\", linewidth=1.5, label=\"Train\")\n",
    "axes[0].plot(history.history[\"val_loss\"], \"r-\", linewidth=1.5, label=\"Validation\")\n",
    "axes[0].axvline(x=best_epoch-1, color=\"green\", linestyle=\"--\", alpha=0.7, label=f\"Best: {best_epoch}\")\n",
    "axes[0].set_xlabel(\"Epoch\"); axes[0].set_ylabel(\"MSE Loss\")\n",
    "axes[0].set_title(\"Loss Curve\", fontweight=\"bold\")\n",
    "axes[0].legend(); axes[0].grid(True, alpha=0.3)\n",
    "\n",
    "# MAE\n",
    "if \"mae\" in history.history:\n",
    "    axes[1].plot(history.history[\"mae\"], \"b-\", linewidth=1.5, label=\"Train\")\n",
    "    axes[1].plot(history.history[\"val_mae\"], \"r-\", linewidth=1.5, label=\"Validation\")\n",
    "    axes[1].set_ylabel(\"MAE\")\n",
    "else:\n",
    "    axes[1].plot(history.history[\"loss\"], \"b-\", linewidth=1.5, label=\"Train Loss\")\n",
    "    axes[1].set_ylabel(\"Loss\")\n",
    "axes[1].set_xlabel(\"Epoch\")\n",
    "axes[1].set_title(\"MAE Metric\", fontweight=\"bold\")\n",
    "axes[1].legend(); axes[1].grid(True, alpha=0.3)\n",
    "\n",
    "plt.suptitle(\"Dynamic-Graph iTransformer — Training (v3)\", fontsize=14, fontweight=\"bold\")\n",
    "plt.tight_layout(); save_fig(fig, \"dg_itransformer_training\", directory=v3[\"figures\"]); plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3460b623",
   "metadata": {},
   "source": [
    "## 6. Actual vs Predicted"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "7578a82d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-24T18:15:54.404452Z",
     "iopub.status.busy": "2026-02-24T18:15:54.404452Z",
     "iopub.status.idle": "2026-02-24T18:15:54.670860Z",
     "shell.execute_reply": "2026-02-24T18:15:54.670860Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(1, 2, figsize=(14, 5))\n",
    "\n",
    "# Scatter\n",
    "axes[0].scatter(y_test, y_pred, s=8, alpha=0.4, c=\"steelblue\")\n",
    "lims = [min(y_test.min(), y_pred.min()), max(y_test.max(), y_pred.max())]\n",
    "axes[0].plot(lims, lims, \"r--\", linewidth=1.5)\n",
    "axes[0].annotate(f\"R² = {metrics['R2']:.4f}\", xy=(0.05, 0.9), xycoords=\"axes fraction\",\n",
    "                 fontsize=12, fontweight=\"bold\", bbox=dict(boxstyle=\"round\", facecolor=\"lightyellow\"))\n",
    "axes[0].set_xlabel(\"Actual SOH (%)\"); axes[0].set_ylabel(\"Predicted SOH (%)\")\n",
    "axes[0].set_title(\"Actual vs Predicted\", fontweight=\"bold\")\n",
    "axes[0].set_aspect(\"equal\"); axes[0].grid(True, alpha=0.3)\n",
    "\n",
    "# Residuals\n",
    "residuals = y_test - y_pred\n",
    "axes[1].scatter(y_pred, residuals, s=8, alpha=0.4, c=\"coral\")\n",
    "axes[1].axhline(y=0, color=\"black\", linewidth=1)\n",
    "axes[1].set_xlabel(\"Predicted SOH (%)\"); axes[1].set_ylabel(\"Residual (Actual - Predicted)\")\n",
    "axes[1].set_title(\"Residual Plot\", fontweight=\"bold\"); axes[1].grid(True, alpha=0.3)\n",
    "\n",
    "plt.suptitle(\"Dynamic-Graph iTransformer — Predictions (v3)\", fontsize=14, fontweight=\"bold\")\n",
    "plt.tight_layout(); save_fig(fig, \"dg_itransformer_predictions\", directory=v3[\"figures\"]); plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cd602cc6",
   "metadata": {},
   "source": [
    "## 7. Learned Adjacency Matrix Visualization\n",
    "Visualizing the learned inter-feature adjacency (if exposed by the model)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ff82778a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-24T18:15:54.672868Z",
     "iopub.status.busy": "2026-02-24T18:15:54.672868Z",
     "iopub.status.idle": "2026-02-24T18:15:54.677055Z",
     "shell.execute_reply": "2026-02-24T18:15:54.677055Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Adjacency matrix not directly accessible; model uses softmax(QK^T) for dynamic graphs.\n",
      "Architecture relies on implicit feature correlations via attention.\n",
      "Results + predictions saved to v3\n"
     ]
    }
   ],
   "source": [
    "# Attempt to extract adjacency matrix from DynamicGraphConv layers\n",
    "adj_found = False\n",
    "for layer in dg_model.layers:\n",
    "    if hasattr(layer, \"adj\"):\n",
    "        adj = layer.adj.numpy()\n",
    "        adj_found = True\n",
    "        fig, ax = plt.subplots(figsize=(8, 7))\n",
    "        im = ax.imshow(adj, cmap=\"viridis\", aspect=\"auto\")\n",
    "        ax.set_xlabel(\"Feature j\"); ax.set_ylabel(\"Feature i\")\n",
    "        ax.set_title(\"Learned Dynamic Adjacency Matrix (v3)\", fontsize=13, fontweight=\"bold\")\n",
    "        plt.colorbar(im, ax=ax)\n",
    "        save_fig(fig, \"dg_adjacency_matrix\", directory=v3[\"figures\"])\n",
    "        plt.show()\n",
    "        break\n",
    "\n",
    "if not adj_found:\n",
    "    print(\"Adjacency matrix not directly accessible; model uses softmax(QK^T) for dynamic graphs.\")\n",
    "    print(\"Architecture relies on implicit feature correlations via attention.\")\n",
    "\n",
    "# Save metrics\n",
    "import json\n",
    "with open(v3[\"results\"] / \"dg_itransformer_results.json\", \"w\") as f:\n",
    "    json.dump({k: float(v) for k, v in metrics.items()}, f, indent=2)\n",
    "\n",
    "# v3: save raw predictions\n",
    "np.savez_compressed(\n",
    "    str(v3[\"results\"] / \"dg_predictions.npz\"),\n",
    "    y_test=y_test, y_pred=y_pred,\n",
    ")\n",
    "print(\"Results + predictions saved to v3\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}