{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceType":"competition","sourceId":35297,"databundleVersionId":3589144}],"dockerImageVersionId":31287,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2026-03-03T22:31:26.896804Z","iopub.execute_input":"2026-03-03T22:31:26.897391Z","iopub.status.idle":"2026-03-03T22:31:27.18567Z","shell.execute_reply.started":"2026-03-03T22:31:26.89736Z","shell.execute_reply":"2026-03-03T22:31:27.185062Z"}},"outputs":[{"name":"stdout","text":"/kaggle/input/competitions/energy-anomaly-detection/sample_submission.csv\n/kaggle/input/competitions/energy-anomaly-detection/train.csv\n/kaggle/input/competitions/energy-anomaly-detection/test.csv\n/kaggle/input/competitions/energy-anomaly-detection/train_features.csv\n/kaggle/input/competitions/energy-anomaly-detection/test_features.csv\n","output_type":"stream"}],"execution_count":1},{"cell_type":"code","source":"# =========================================================\n# 0. IMPORTS\n# =========================================================\nimport os\nimport warnings\nwarnings.filterwarnings(\"ignore\")\n\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\n\nimport torch\nfrom torch import nn, optim\nfrom torch.utils.data import DataLoader, TensorDataset\n\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.metrics import (\n    roc_auc_score,\n    average_precision_score,\n    precision_score,\n    recall_score,\n    roc_curve,\n    precision_recall_curve\n)\nfrom sklearn.model_selection import KFold\n\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\nprint(\"Device:\", device)\ntorch.cuda.empty_cache()\n\n# =========================================================\n# 1. DATA PREPARATION\n# =========================================================\nSEQ_LEN = 16\nDIFF_STEPS = 50\nDIFF_T = 15\n\ndef prepare_data(path):\n    df = pd.read_csv(path)\n\n    df[\"timestamp\"] = pd.to_datetime(df[\"timestamp\"], format=\"mixed\", errors=\"coerce\")\n    df = df.dropna(subset=[\"timestamp\"])\n    df = df.sort_values([\"building_id\", \"timestamp\"])\n\n    df[\"meter_log\"] = np.log1p(df[\"meter_reading\"])\n    df[\"hour\"] = df[\"timestamp\"].dt.hour\n    df[\"dow\"] = df[\"timestamp\"].dt.dayofweek\n\n    norm = (\n        df[df[\"anomaly\"] == 0]\n        .groupby([\"building_id\", \"dow\", \"hour\"])[\"meter_log\"]\n        .agg([\"median\", \"std\"])\n        .reset_index()\n    )\n    norm.columns = [\"building_id\", \"dow\", \"hour\", \"h_med\", \"h_std\"]\n    df = df.merge(norm, on=[\"building_id\", \"dow\", \"hour\"], how=\"left\")\n\n    df[\"h_med\"] = df[\"h_med\"].fillna(\n        df.groupby(\"building_id\")[\"meter_log\"].transform(\"median\")\n    )\n\n    df[\"temp_inertia\"] = (\n        df.groupby(\"building_id\")[\"air_temperature\"]\n        .transform(lambda x: x.rolling(6, min_periods=1).mean())\n    )\n\n    df[\"thermal_p\"] = df[\"air_temperature\"] - df[\"temp_inertia\"]\n\n    df[\"shock\"] = df[\"meter_log\"] - df[\"h_med\"]\n    df[\"shock_v\"] = df.groupby(\"building_id\")[\"shock\"].diff().fillna(0)\n    df[\"kinetic_s\"] = df.groupby(\"building_id\")[\"shock_v\"].diff().fillna(0)\n\n    df[\"shock_scaled\"] = df.groupby(\"building_id\")[\"shock\"].transform(\n        lambda x: (x - x.median()) /\n        (x.quantile(0.75) - x.quantile(0.25) + 1e-6)\n    )\n\n    feat_cols = [\"shock_scaled\", \"thermal_p\", \"kinetic_s\", \"air_temperature\"]\n    df[feat_cols] = df[feat_cols].replace([np.inf, -np.inf], 0).fillna(0)\n\n    le_b, le_s, le_u = LabelEncoder(), LabelEncoder(), LabelEncoder()\n    df[\"b_idx\"] = le_b.fit_transform(df[\"building_id\"])\n    df[\"s_idx\"] = le_s.fit_transform(df[\"site_id\"])\n    df[\"u_idx\"] = le_u.fit_transform(df[\"primary_use\"])\n\n    return df, feat_cols, le_b, le_s, le_u\n\n# =========================================================\n# 2. SEQUENCE WINDOWING\n# =========================================================\ndef create_sequences(df, feat_cols):\n    X, b, s, u, y, bid = [], [], [], [], [], []\n\n    for building_id, group in df.groupby(\"building_id\"):\n        group = group.sort_values(\"timestamp\")\n\n        feats = group[feat_cols].values\n        labels = group[\"anomaly\"].values\n        b_idx = group[\"b_idx\"].values\n        s_idx = group[\"s_idx\"].values\n        u_idx = group[\"u_idx\"].values\n\n        for i in range(len(group) - SEQ_LEN):\n            X.append(feats[i:i+SEQ_LEN])\n            y.append(labels[i+SEQ_LEN-1])\n            b.append(b_idx[i+SEQ_LEN-1])\n            s.append(s_idx[i+SEQ_LEN-1])\n            u.append(u_idx[i+SEQ_LEN-1])\n            bid.append(building_id)\n\n    return (\n        torch.tensor(np.array(X), dtype=torch.float32),\n        torch.tensor(b),\n        torch.tensor(s),\n        torch.tensor(u),\n        np.array(y),\n        np.array(bid)\n    )\n\n# =========================================================\n# 3. TRANSFORMER AUTOENCODER\n# =========================================================\nclass TransformerAE(nn.Module):\n    def __init__(self, input_dim):\n        super().__init__()\n\n        self.input_proj = nn.Linear(input_dim, 64)\n\n        encoder_layer = nn.TransformerEncoderLayer(\n            d_model=64,\n            nhead=4,\n            dim_feedforward=128,\n            dropout=0.1,\n            batch_first=True\n        )\n        self.encoder = nn.TransformerEncoder(encoder_layer, num_layers=2)\n\n        self.decoder = nn.Sequential(\n            nn.Linear(64, 128),\n            nn.SiLU(),\n            nn.Linear(128, input_dim)\n        )\n\n    def forward(self, x):\n        x = self.input_proj(x)\n        z = self.encoder(x)\n        last = z[:, -1, :]\n        out = self.decoder(last)\n        return torch.nan_to_num(out)\n\n# =========================================================\n# 4. TRAINING + DIFFUSION\n# =========================================================\ndef train_kfold(X, b, s, u, y, bid):\n\n    kf = KFold(n_splits=3, shuffle=True, random_state=42)\n    ensemble_scores = np.zeros(len(y))\n\n    alphas = torch.linspace(1e-4, 0.02, DIFF_STEPS).to(device)\n\n    for fold, (train_idx, val_idx) in enumerate(kf.split(X)):\n        print(f\"\\n🔥 Fold {fold+1}\")\n\n        model = TransformerAE(X.shape[2]).to(device)\n        opt = optim.AdamW(model.parameters(), lr=1e-3)\n\n        best_pr = 0\n        patience = 5\n        counter = 0\n\n        normal_mask = y[train_idx] == 0\n        X_train = X[train_idx][normal_mask]\n\n        train_loader = DataLoader(\n            TensorDataset(X_train),\n            batch_size=512,\n            shuffle=True\n        )\n\n        for epoch in range(25):\n            model.train()\n            for (xb,) in train_loader:\n                xb = xb.to(device)\n                target = xb[:, -1, :]\n\n                t = torch.randint(0, DIFF_STEPS, (xb.size(0),), device=device)\n                noise = torch.randn_like(target)\n                alpha = alphas[t].unsqueeze(1)\n\n                noisy_last = torch.sqrt(1 - alpha)*target + torch.sqrt(alpha)*noise\n                xb_noisy = xb.clone()\n                xb_noisy[:, -1, :] = noisy_last\n\n                pred = model(xb_noisy)\n                loss = nn.MSELoss()(pred, target)\n\n                if torch.isfinite(loss):\n                    opt.zero_grad()\n                    loss.backward()\n                    torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)\n                    opt.step()\n\n            # VALIDATION\n            model.eval()\n            val_loader = DataLoader(\n                TensorDataset(X[val_idx]),\n                batch_size=512,\n                shuffle=False\n            )\n\n            val_err = []\n            with torch.no_grad():\n                for (xb,) in val_loader:\n                    xb = xb.to(device)\n                    target = xb[:, -1, :]\n\n                    t = torch.full((xb.size(0),), DIFF_T, device=device)\n                    noise = torch.randn_like(target)\n                    alpha = alphas[t].unsqueeze(1)\n\n                    noisy_last = torch.sqrt(1 - alpha)*target + torch.sqrt(alpha)*noise\n                    xb_noisy = xb.clone()\n                    xb_noisy[:, -1, :] = noisy_last\n\n                    pred = model(xb_noisy)\n\n                    err = (\n                        (pred[:,0]-target[:,0])**2 +\n                        0.75*(pred[:,2]-target[:,2])**2 +\n                        0.5*(pred[:,1]-target[:,1])**2\n                    )\n\n                    val_err.append(err.cpu())\n\n            val_err = torch.cat(val_err).numpy()\n            val_err = np.nan_to_num(val_err)\n\n            pr = average_precision_score(y[val_idx], val_err)\n            print(f\"Epoch {epoch+1} | PR: {pr:.4f}\")\n\n            if pr > best_pr:\n                best_pr = pr\n                best_state = model.state_dict()\n                counter = 0\n            else:\n                counter += 1\n\n            if counter >= patience:\n                print(\"Early stopping\")\n                break\n\n        model.load_state_dict(best_state)\n\n        # FULL INFERENCE\n        full_loader = DataLoader(\n            TensorDataset(X),\n            batch_size=512,\n            shuffle=False\n        )\n\n        fold_scores = []\n        with torch.no_grad():\n            for (xb,) in full_loader:\n                xb = xb.to(device)\n                target = xb[:, -1, :]\n\n                t = torch.full((xb.size(0),), DIFF_T, device=device)\n                noise = torch.randn_like(target)\n                alpha = alphas[t].unsqueeze(1)\n\n                noisy_last = torch.sqrt(1 - alpha)*target + torch.sqrt(alpha)*noise\n                xb_noisy = xb.clone()\n                xb_noisy[:, -1, :] = noisy_last\n\n                pred = model(xb_noisy)\n\n                err = (\n                    (pred[:,0]-target[:,0])**2 +\n                    0.75*(pred[:,2]-target[:,2])**2 +\n                    0.5*(pred[:,1]-target[:,1])**2\n                )\n\n                fold_scores.append(err.cpu())\n\n        fold_scores = torch.cat(fold_scores).numpy()\n        fold_scores = np.nan_to_num(fold_scores)\n\n        ensemble_scores += fold_scores / 3\n\n    return ensemble_scores\n\n# =========================================================\n# 5. EVALUATION\n# =========================================================\ndef evaluate(scores, y, bid):\n\n    scores = np.log1p(np.nan_to_num(scores))\n\n    auc = roc_auc_score(y, scores)\n    pr = average_precision_score(y, scores)\n\n    thresh = np.percentile(scores, 95)\n    preds = (scores > thresh).astype(int)\n\n    precision = precision_score(y, preds)\n    recall = recall_score(y, preds)\n    fpr = np.sum((preds==1)&(y==0)) / np.sum(y==0)\n\n    print(\"\\n🏆 FINAL RESULTS\")\n    print(\"ROC-AUC :\", auc)\n    print(\"PR-AUC  :\", pr)\n    print(\"Precision:\", precision)\n    print(\"Recall:\", recall)\n    print(\"TPR:\", recall)\n    print(\"FPR:\", fpr)\n\n    fpr_c, tpr_c, _ = roc_curve(y, scores)\n    plt.plot(fpr_c, tpr_c)\n    plt.title(\"ROC Curve\")\n    plt.show()\n\n    p_c, r_c, _ = precision_recall_curve(y, scores)\n    plt.plot(r_c, p_c)\n    plt.title(\"PR Curve\")\n    plt.show()\n\n    sample = bid[0]\n    mask = (bid == sample)\n\n    plt.figure(figsize=(12,5))\n    plt.plot(scores[mask], label=\"Predicted\")\n    plt.scatter(np.where(y[mask]==1), scores[mask][y[mask]==1],\n                color=\"red\", label=\"Actual Anomaly\")\n    plt.legend()\n    plt.title(f\"Building {sample}\")\n    plt.show()\n\n# =========================================================\n# RUN\n# =========================================================\npath = \"/kaggle/input/competitions/energy-anomaly-detection/train_features.csv\"\n\ndf, feats, le_b, le_s, le_u = prepare_data(path)\nX, b, s, u, y, bid = create_sequences(df, feats)\n\nscores = train_kfold(X, b, s, u, y, bid)\nevaluate(scores, y, bid)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-03T22:32:07.256369Z","iopub.execute_input":"2026-03-03T22:32:07.25703Z","iopub.status.idle":"2026-03-03T22:41:13.453888Z","shell.execute_reply.started":"2026-03-03T22:32:07.257002Z","shell.execute_reply":"2026-03-03T22:41:13.453083Z"}},"outputs":[{"name":"stdout","text":"Device: cuda\n\n🔥 Fold 1\nEpoch 1 | PR: 0.2727\nEpoch 2 | PR: 0.2727\nEpoch 3 | PR: 0.2727\nEpoch 4 | PR: 0.2727\nEpoch 5 | PR: 0.2727\nEpoch 6 | PR: 0.2727\nEarly stopping\n\n🔥 Fold 2\nEpoch 1 | PR: 0.2744\nEpoch 2 | PR: 0.2744\nEpoch 3 | PR: 0.2744\nEpoch 4 | PR: 0.2744\nEpoch 5 | PR: 0.2744\nEpoch 6 | PR: 0.2744\nEarly stopping\n\n🔥 Fold 3\nEpoch 1 | PR: 0.2705\nEpoch 2 | PR: 0.2705\nEpoch 3 | PR: 0.2705\nEpoch 4 | PR: 0.2705\nEpoch 5 | PR: 0.2705\nEpoch 6 | PR: 0.2705\nEarly stopping\n\n🏆 FINAL RESULTS\nROC-AUC : 0.8025143174507948\nPR-AUC  : 0.27246682476743117\nPrecision: 0.21619423924869724\nRecall: 0.5090609999460655\nTPR: 0.5090609999460655\nFPR: 0.04004067371396878\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 1200x500 with 1 Axes>","image/png":"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\n"},"metadata":{}}],"execution_count":2}]}