{"cells":[{"cell_type":"markdown","id":"d3f50ad2","metadata":{},"source":"# MABe Mouse Behavior Detection - Inference Notebook\n\n**Generate Submission Using Trained Models**\n\nThis notebook loads trained models and generates predictions for the test set.\n"},{"cell_type":"markdown","id":"e3ddab8b","metadata":{},"source":"## Kaggle Setup\n\n**Note for Kaggle Users:**\n- This notebook automatically detects Kaggle environment\n- Add your trained models dataset to `/kaggle/input/` (update `MODEL_PATH` in configuration)\n- Submission will be saved to `/kaggle/working/submission.csv` (available for download)\n- Make sure the models dataset contains the `thresholds.pkl` file and all model files\n"},{"cell_type":"code","execution_count":null,"id":"85a3107f","metadata":{},"outputs":[],"source":"import argparse\nimport json\nimport os\nimport time\nimport warnings\nfrom collections import defaultdict\nfrom pathlib import Path\nimport joblib\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nimport optuna\nfrom optuna.pruners import MedianPruner\nfrom sklearn.model_selection import StratifiedGroupKFold\nfrom sklearn.metrics import f1_score, precision_score, recall_score\nfrom sklearn.base import clone\nfrom sklearn.impute import SimpleImputer\nfrom xgboost import XGBClassifier\nfrom tqdm import tqdm\n# from koolbox import Trainer  # Replaced with custom implementation below\nimport itertools\nimport glob\nimport gc\ntry:\n    from imblearn.over_sampling import SMOTE\n    SMOTE_AVAILABLE = True\nexcept ImportError:\n    SMOTE_AVAILABLE = False\n    print(\"Warning: imbalanced-learn not installed. Install with: pip install imbalanced-learn\")\n\ntry:\n    import wandb\n    WANDB_AVAILABLE = True\nexcept ImportError:\n    WANDB_AVAILABLE = False\n    print(\"Warning: wandb not installed. Install with: pip install wandb\")\n\noptuna.logging.set_verbosity(optuna.logging.WARNING)\nwarnings.filterwarnings('ignore')"},{"cell_type":"code","execution_count":null,"id":"638ad898","metadata":{},"outputs":[],"source":"# Custom Trainer class (koolbox replacement for Kaggle compatibility)\n# koolbox is not available on Kaggle, so we provide a custom implementation\n\nclass Trainer:\n    \"\"\"\n    Custom Trainer class to replace koolbox.Trainer\n    Performs cross-validation and stores out-of-fold predictions and trained models.\n    \"\"\"\n    def __init__(self, estimator, cv, cv_args=None, metric=None, task=\"binary\", \n                 verbose=False, save=False, save_path=None):\n        self.estimator = estimator\n        self.cv = cv\n        self.cv_args = cv_args or {}\n        self.metric = metric\n        self.task = task\n        self.verbose = verbose\n        self.save = save\n        self.save_path = save_path\n        self.oof_preds = None\n        self.estimators = []\n    \n    def fit(self, X, y):\n        \"\"\"Perform cross-validation and store OOF predictions and models\"\"\"\n        groups = self.cv_args.get('groups', None)\n        \n        # Initialize OOF predictions\n        if self.task == \"binary\":\n            self.oof_preds = np.zeros(len(X))\n        else:\n            n_classes = len(np.unique(y))\n            self.oof_preds = np.zeros((len(X), n_classes))\n        \n        # Perform cross-validation\n        for fold_idx, (train_idx, val_idx) in enumerate(self.cv.split(X, y, groups=groups)):\n            # Clone estimator for this fold\n            fold_estimator = clone(self.estimator)\n            \n            # Get fold data\n            X_train_fold = X.iloc[train_idx] if hasattr(X, 'iloc') else X[train_idx]\n            X_val_fold = X.iloc[val_idx] if hasattr(X, 'iloc') else X[val_idx]\n            y_train_fold = y[train_idx] if hasattr(y, 'iloc') else y[train_idx]\n            y_val_fold = y[val_idx] if hasattr(y, 'iloc') else y[val_idx]\n            \n            # Train model\n            fold_estimator.fit(X_train_fold, y_train_fold)\n            self.estimators.append(fold_estimator)\n            \n            # Get predictions\n            if hasattr(fold_estimator, 'predict_proba'):\n                if self.task == \"binary\":\n                    y_pred_proba = fold_estimator.predict_proba(X_val_fold)[:, 1]\n                else:\n                    y_pred_proba = fold_estimator.predict_proba(X_val_fold)\n            else:\n                y_pred_proba = fold_estimator.predict(X_val_fold)\n            \n            # Store OOF predictions\n            if self.task == \"binary\":\n                self.oof_preds[val_idx] = y_pred_proba\n            else:\n                self.oof_preds[val_idx] = y_pred_proba\n            \n            # Save model if requested\n            if self.save and self.save_path:\n                os.makedirs(self.save_path, exist_ok=True)\n                model_path = os.path.join(self.save_path, f\"fold_{fold_idx}_trainer_model.pkl\")\n                joblib.dump(fold_estimator, model_path)\n    \n    def predict(self, X):\n        \"\"\"Predict using ensemble of all CV models\"\"\"\n        if not self.estimators:\n            raise ValueError(\"Model must be fitted before prediction\")\n        \n        predictions = []\n        for estimator in self.estimators:\n            if hasattr(estimator, 'predict_proba'):\n                pred = estimator.predict_proba(X)\n            else:\n                pred = estimator.predict(X)\n            predictions.append(pred)\n        \n        # Average predictions across folds\n        return np.mean(predictions, axis=0)\n"},{"cell_type":"code","execution_count":null,"id":"8f26a52b","metadata":{},"outputs":[],"source":"# Configuration\nimport os\nfrom pathlib import Path\n\n# Detect Kaggle environment\nIS_KAGGLE = os.path.exists('/kaggle/input')\n\nif IS_KAGGLE:\n    # Kaggle paths\n    TRAIN_PATH = '/kaggle/input/MABe-mouse-behavior-detection/train.csv'\n    TEST_PATH = '/kaggle/input/MABe-mouse-behavior-detection/test.csv'\n    TRAIN_ANNOTATION_PATH = '/kaggle/input/MABe-mouse-behavior-detection/train_annotation'\n    TRAIN_TRACKING_PATH = '/kaggle/input/MABe-mouse-behavior-detection/train_tracking'\n    TEST_TRACKING_PATH = '/kaggle/input/MABe-mouse-behavior-detection/test_tracking'\n    MODEL_PATH = '/kaggle/input/social-action-recognition-in-mice-xgb-catboost'  # Update with your model dataset\n    MODEL_NAME = 'xgboost'\n    OUTPUT_DIR = '/kaggle/working'\nelse:\n    # Local paths (fallback)\n    TRAIN_PATH = 'train.csv'\n    TEST_PATH = 'test.csv'\n    TRAIN_ANNOTATION_PATH = 'train_annotation'\n    TRAIN_TRACKING_PATH = 'train_tracking'\n    TEST_TRACKING_PATH = 'test_tracking'\n    MODEL_PATH = 'xgboost'\n    MODEL_NAME = 'xgboost'\n    OUTPUT_DIR = '.'\n\n# Model hyperparameters\nN_SPLITS = 3\nN_ESTIMATORS = 250\nLEARNING_RATE = 0.08\nMAX_DEPTH = 6\nMIN_CHILD_WEIGHT = 5\nSUBSAMPLE = 0.8\nCOLSAMPLE_BYTREE = 0.8\n\n# Hyperparameter optimization\nOPTIMIZE_HYPERPARAMS = True\nHYPEROPT_TRIALS = 50\nHYPEROPT_TIMEOUT = None\n\n# Threshold tuning\nN_TRIALS = 200\n\n# Class imbalance handling\nUSE_CLASS_WEIGHTS = True\nUSE_SMOTE = True\nSMOTE_THRESHOLD = 0.01\n\n# Early stopping\nUSE_EARLY_STOPPING = True\nEARLY_STOPPING_ROUNDS = 10\n\n# Adaptive optimization\nADAPTIVE_TRIALS = False\nMIN_TRIALS = 20\nUSE_SECTION_SPECIFIC_RANGES = True\n\n# GPU/CUDA support\nUSE_GPU = os.path.exists('/kaggle/input')  # Auto-detect on Kaggle\n\n# Weights & Biases logging (optional)\nUSE_WANDB = False  # Set to True and add WANDB_API_KEY to Kaggle secrets\nWANDB_PROJECT = 'mabe-mouse-behavior'\nWANDB_ENTITY = None\nWANDB_RUN_NAME = None\nPREVIOUS_RUN_ID = None\n\n# Create CFG-like object for compatibility\nclass CFG:\n    def __init__(self):\n        self.train_path = TRAIN_PATH\n        self.test_path = TEST_PATH\n        self.train_annotation_path = TRAIN_ANNOTATION_PATH\n        self.train_tracking_path = TRAIN_TRACKING_PATH\n        self.test_tracking_path = TEST_TRACKING_PATH\n        self.model_path = MODEL_PATH\n        self.model_name = MODEL_NAME\n        self.mode = 'submit'\n        self.n_splits = N_SPLITS\n        from sklearn.model_selection import StratifiedGroupKFold\n        self.cv = StratifiedGroupKFold(self.n_splits)\n        self.use_gpu = USE_GPU\n        self.n_trials = N_TRIALS\n        self.optimize_hyperparams = OPTIMIZE_HYPERPARAMS\n        self.hyperopt_trials = HYPEROPT_TRIALS\n        self.hyperopt_timeout = HYPEROPT_TIMEOUT\n        self.use_class_weights = USE_CLASS_WEIGHTS\n        self.use_smote = USE_SMOTE\n        self.smote_threshold = SMOTE_THRESHOLD\n        self.use_early_stopping = USE_EARLY_STOPPING\n        self.early_stopping_rounds = EARLY_STOPPING_ROUNDS\n        self.adaptive_trials = ADAPTIVE_TRIALS\n        self.min_trials = MIN_TRIALS\n        self.use_section_specific_ranges = USE_SECTION_SPECIFIC_RANGES\n        self.previous_run_id = PREVIOUS_RUN_ID\n        self.previous_best_scores = {}\n        \n        # Base XGBoost parameters\n        xgb_params = {\n            'verbosity': 0,\n            'random_state': 42,\n            'n_estimators': N_ESTIMATORS,\n            'learning_rate': LEARNING_RATE,\n            'max_depth': MAX_DEPTH,\n            'min_child_weight': MIN_CHILD_WEIGHT,\n            'subsample': SUBSAMPLE,\n            'colsample_bytree': COLSAMPLE_BYTREE\n        }\n        \n        if self.use_gpu:\n            xgb_params['device'] = 'cuda'\n        \n        self.base_xgb_params = xgb_params\n        from xgboost import XGBClassifier\n        self.model = XGBClassifier(**xgb_params)\n        self.optimized_params = {}\n\ncfg = CFG()\n\n# Initialize wandb if enabled\nif USE_WANDB:\n    try:\n        import wandb\n        import os\n        # Try to get API key from Kaggle secrets\n        if IS_KAGGLE:\n            try:\n                from kaggle_secrets import UserSecretsClient\n                user_secrets = UserSecretsClient()\n                wandb_api_key = user_secrets.get_secret(\"WANDB_API_KEY\")\n                os.environ[\"WANDB_API_KEY\"] = wandb_api_key\n            except:\n                print(\"Warning: Could not load WANDB_API_KEY from Kaggle secrets\")\n        \n        wandb.init(\n            project=WANDB_PROJECT,\n            entity=WANDB_ENTITY,\n            name=WANDB_RUN_NAME,\n            config={\n                'mode': cfg.mode,\n                'n_splits': cfg.n_splits,\n                'use_gpu': cfg.use_gpu,\n                'optimize_hyperparams': cfg.optimize_hyperparams,\n            }\n        )\n        print(f\"W&B logging enabled: {wandb.run.url}\")\n    except ImportError:\n        print(\"Warning: wandb not installed. Install with: pip install wandb\")\n"},{"cell_type":"markdown","id":"53893829","metadata":{},"source":"## F-Beta Scoring Functions"},{"cell_type":"code","execution_count":null,"id":"103ad0f4","metadata":{},"outputs":[],"source":"class HostVisibleError(Exception):\n    pass\n\n\n\ndef single_lab_f1(lab_solution: pl.DataFrame, lab_submission: pl.DataFrame, beta: float = 1) -> float:\n    label_frames: defaultdict[str, set[int]] = defaultdict(set)\n    prediction_frames: defaultdict[str, set[int]] = defaultdict(set)\n\n    for row in lab_solution.to_dicts():\n        label_frames[row['label_key']].update(range(row['start_frame'], row['stop_frame']))\n\n    for video in lab_solution['video_id'].unique():\n        active_labels: str = lab_solution.filter(pl.col('video_id') == video)['behaviors_labeled'].first()\n        active_labels: set[str] = set(json.loads(active_labels))\n        predicted_mouse_pairs: defaultdict[str, set[int]] = defaultdict(set)\n\n        for row in lab_submission.filter(pl.col('video_id') == video).to_dicts():\n            if ','.join([str(row['agent_id']), str(row['target_id']), row['action']]) not in active_labels:\n                continue\n\n            new_frames = set(range(row['start_frame'], row['stop_frame']))\n            new_frames = new_frames.difference(prediction_frames[row['prediction_key']])\n            prediction_pair = ','.join([str(row['agent_id']), str(row['target_id'])])\n            if predicted_mouse_pairs[prediction_pair].intersection(new_frames):\n                raise HostVisibleError('Multiple predictions for the same frame from one agent/target pair')\n            prediction_frames[row['prediction_key']].update(new_frames)\n            predicted_mouse_pairs[prediction_pair].update(new_frames)\n\n    tps = defaultdict(int)\n    fns = defaultdict(int)\n    fps = defaultdict(int)\n    for key, pred_frames in prediction_frames.items():\n        action = key.split('_')[-1]\n        matched_label_frames = label_frames[key]\n        tps[action] += len(pred_frames.intersection(matched_label_frames))\n        fns[action] += len(matched_label_frames.difference(pred_frames))\n        fps[action] += len(pred_frames.difference(matched_label_frames))\n\n    distinct_actions = set()\n    for key, frames in label_frames.items():\n        action = key.split('_')[-1]\n        distinct_actions.add(action)\n        if key not in prediction_frames:\n            fns[action] += len(frames)\n\n    action_f1s = []\n    for action in distinct_actions:\n        if tps[action] + fns[action] + fps[action] == 0:\n            action_f1s.append(0)\n        else:\n            action_f1s.append((1 + beta**2) * tps[action] / ((1 + beta**2) * tps[action] + beta**2 * fns[action] + fps[action]))\n    return sum(action_f1s) / len(action_f1s)\n\n\n\ndef mouse_fbeta(solution: pd.DataFrame, submission: pd.DataFrame, beta: float = 1) -> float:\n    if len(solution) == 0 or len(submission) == 0:\n        raise ValueError('Missing solution or submission data')\n\n    expected_cols = ['video_id', 'agent_id', 'target_id', 'action', 'start_frame', 'stop_frame']\n\n    for col in expected_cols:\n        if col not in solution.columns:\n            raise ValueError(f'Solution is missing column {col}')\n        if col not in submission.columns:\n            raise ValueError(f'Submission is missing column {col}')\n\n    solution: pl.DataFrame = pl.DataFrame(solution)\n    submission: pl.DataFrame = pl.DataFrame(submission)\n    assert (solution['start_frame'] <= solution['stop_frame']).all()\n    assert (submission['start_frame'] <= submission['stop_frame']).all()\n    solution_videos = set(solution['video_id'].unique())\n    submission = submission.filter(pl.col('video_id').is_in(solution_videos))\n\n    solution = solution.with_columns(\n        pl.concat_str(\n            [\n                pl.col('video_id').cast(pl.Utf8),\n                pl.col('agent_id').cast(pl.Utf8),\n                pl.col('target_id').cast(pl.Utf8),\n                pl.col('action'),\n            ],\n            separator='_',\n        ).alias('label_key'),\n    )\n    submission = submission.with_columns(\n        pl.concat_str(\n            [\n                pl.col('video_id').cast(pl.Utf8),\n                pl.col('agent_id').cast(pl.Utf8),\n                pl.col('target_id').cast(pl.Utf8),\n                pl.col('action'),\n            ],\n            separator='_',\n        ).alias('prediction_key'),\n    )\n\n    lab_scores = []\n    for lab in solution['lab_id'].unique():\n        lab_solution = solution.filter(pl.col('lab_id') == lab).clone()\n        lab_videos = set(lab_solution['video_id'].unique())\n        lab_submission = submission.filter(pl.col('video_id').is_in(lab_videos)).clone()\n        lab_scores.append(single_lab_f1(lab_solution, lab_submission, beta=beta))\n\n    return sum(lab_scores) / len(lab_scores)\n\n\n\ndef score(solution: pd.DataFrame, submission: pd.DataFrame, row_id_column_name: str, beta: float = 1) -> float:\n    \"\"\"F1 score for the MABe Challenge\"\"\"\n    solution = solution.drop(row_id_column_name, axis='columns', errors='ignore')\n    submission = submission.drop(row_id_column_name, axis='columns', errors='ignore')\n    return mouse_fbeta(solution, submission, beta=beta)\n\n"},{"cell_type":"markdown","id":"ee537cec","metadata":{},"source":"## Data Loading Functions"},{"cell_type":"code","execution_count":null,"id":"eb535fa6","metadata":{},"outputs":[],"source":"drop_body_parts = [\n    'headpiece_bottombackleft', 'headpiece_bottombackright', 'headpiece_bottomfrontleft', 'headpiece_bottomfrontright',\n    'headpiece_topbackleft', 'headpiece_topbackright', 'headpiece_topfrontleft', 'headpiece_topfrontright',\n    'spine_1', 'spine_2', 'tail_middle_1', 'tail_middle_2', 'tail_midpoint'\n]\n\ndef generate_mouse_data(dataset, traintest, cfg, traintest_directory=None, generate_single=True, generate_pair=True):\n    if traintest_directory is None:\n        if traintest == 'train':\n            traintest_directory = cfg.train_tracking_path\n        else:\n            traintest_directory = cfg.test_tracking_path\n        \n    for _, row in dataset.iterrows():\n        lab_id = row.lab_id\n        if lab_id.startswith('MABe22') or type(row.behaviors_labeled) != str:\n            continue\n        \n        video_id = row.video_id\n        path = f\"{traintest_directory}/{lab_id}/{video_id}.parquet\"\n        vid = pd.read_parquet(path)\n        if len(np.unique(vid.bodypart)) > 5:\n            vid = vid.query(\"~ bodypart.isin(@drop_body_parts)\")\n        pvid = vid.pivot(columns=['mouse_id', 'bodypart'], index='video_frame', values=['x', 'y'])\n        \n        del vid\n        gc.collect()\n        \n        pvid = pvid.reorder_levels([1, 2, 0], axis=1).T.sort_index().T\n        pvid /= row.pix_per_cm_approx\n\n        vid_behaviors = json.loads(row.behaviors_labeled)\n        vid_behaviors = sorted(list({b.replace(\"'\", \"\") for b in vid_behaviors}))\n        vid_behaviors = [b.split(',') for b in vid_behaviors]\n        vid_behaviors = pd.DataFrame(vid_behaviors, columns=['agent', 'target', 'action'])\n        \n        if traintest == 'train':\n            try:\n                annot = pd.read_parquet(path.replace('train_tracking', 'train_annotation'))\n            except FileNotFoundError:\n                continue\n\n        if generate_single:\n            vid_behaviors_subset = vid_behaviors.query(\"target == 'self'\")\n            for mouse_id_str in np.unique(vid_behaviors_subset.agent):\n                try:\n                    mouse_id = int(mouse_id_str[-1])\n                    vid_agent_actions = np.unique(vid_behaviors_subset.query(\"agent == @mouse_id_str\").action)\n                    single_mouse = pvid.loc[:, mouse_id]\n                    assert len(single_mouse) == len(pvid)\n                    single_mouse_meta = pd.DataFrame({\n                        'video_id': video_id,\n                        'agent_id': mouse_id_str,\n                        'target_id': 'self',\n                        'video_frame': single_mouse.index\n                    })\n                    if traintest == 'train':\n                        single_mouse_label = pd.DataFrame(0.0, columns=vid_agent_actions, index=single_mouse.index)\n                        annot_subset = annot.query(\"(agent_id == @mouse_id) & (target_id == @mouse_id)\")\n                        for i in range(len(annot_subset)):\n                            annot_row = annot_subset.iloc[i]\n                            single_mouse_label.loc[annot_row['start_frame']:annot_row['stop_frame'], annot_row.action] = 1.0\n                        yield 'single', single_mouse, single_mouse_meta, single_mouse_label\n                    else:\n                        yield 'single', single_mouse, single_mouse_meta, vid_agent_actions\n                except KeyError:\n                    pass\n\n        if generate_pair:\n            vid_behaviors_subset = vid_behaviors.query(\"target != 'self'\")\n            if len(vid_behaviors_subset) > 0:\n                for agent, target in itertools.permutations(np.unique(pvid.columns.get_level_values('mouse_id')), 2):\n                    agent_str = f\"mouse{agent}\"\n                    target_str = f\"mouse{target}\"\n                    vid_agent_actions = np.unique(vid_behaviors_subset.query(\"(agent == @agent_str) & (target == @target_str)\").action)\n                    mouse_pair = pd.concat([pvid[agent], pvid[target]], axis=1, keys=['A', 'B'])\n                    assert len(mouse_pair) == len(pvid)\n                    mouse_pair_meta = pd.DataFrame({\n                        'video_id': video_id,\n                        'agent_id': agent_str,\n                        'target_id': target_str,\n                        'video_frame': mouse_pair.index\n                    })\n                    if traintest == 'train':\n                        mouse_pair_label = pd.DataFrame(0.0, columns=vid_agent_actions, index=mouse_pair.index)\n                        annot_subset = annot.query(\"(agent_id == @agent) & (target_id == @target)\")\n                        for i in range(len(annot_subset)):\n                            annot_row = annot_subset.iloc[i]\n                            mouse_pair_label.loc[annot_row['start_frame']:annot_row['stop_frame'], annot_row.action] = 1.0\n                        yield 'pair', mouse_pair, mouse_pair_meta, mouse_pair_label\n                    else:\n                        yield 'pair', mouse_pair, mouse_pair_meta, vid_agent_actions\n\n"},{"cell_type":"markdown","id":"15b1a34f","metadata":{},"source":"## Feature Engineering"},{"cell_type":"code","execution_count":null,"id":"a88c1c34","metadata":{},"outputs":[],"source":"def safe_rolling(series, window, func, min_periods=None):\n    if min_periods is None:\n        min_periods = max(1, window // 4)\n    return series.rolling(window, min_periods=min_periods, center=True).apply(func, raw=True)\n\n\n\ndef _scale(n_frames_at_30fps, fps, ref=30.0):\n    return max(1, int(round(n_frames_at_30fps * float(fps) / ref)))\n\n\n\ndef _scale_signed(n_frames_at_30fps, fps, ref=30.0):\n    if n_frames_at_30fps == 0:\n        return 0\n    s = 1 if n_frames_at_30fps > 0 else -1\n    mag = max(1, int(round(abs(n_frames_at_30fps) * float(fps) / ref)))\n    return s * mag\n\n\n\ndef _fps_from_meta(meta_df, fallback_lookup, default_fps=30.0):\n    if 'frames_per_second' in meta_df.columns and pd.notnull(meta_df['frames_per_second']).any():\n        return float(meta_df['frames_per_second'].iloc[0])\n    vid = meta_df['video_id'].iloc[0]\n    return float(fallback_lookup.get(vid, default_fps))\n\n\n\ndef add_curvature_features(X, center_x, center_y, fps):\n    vel_x = center_x.diff()\n    vel_y = center_y.diff()\n    acc_x = vel_x.diff()\n    acc_y = vel_y.diff()\n\n    cross_prod = vel_x * acc_y - vel_y * acc_x\n    vel_mag = np.sqrt(vel_x**2 + vel_y**2)\n    curvature = np.abs(cross_prod) / (vel_mag**3 + 1e-6)\n\n    for w in [25, 50, 75]:\n        ws = _scale(w, fps)\n        X[f'curv_mean_{w}'] = curvature.rolling(ws, min_periods=max(1, ws // 5)).mean()\n\n    angle = np.arctan2(vel_y, vel_x)\n    angle_change = np.abs(angle.diff())\n    w = 30\n    ws = _scale(w, fps)\n    X[f'turn_rate_{w}'] = angle_change.rolling(ws, min_periods=max(1, ws // 5)).sum()\n\n    return X\n\n\n\ndef add_multiscale_features(X, center_x, center_y, fps):\n    speed = np.sqrt(center_x.diff()**2 + center_y.diff()**2) * float(fps)\n\n    scales = [20, 40, 60, 80]\n    for scale in scales:\n        ws = _scale(scale, fps)\n        if len(speed) >= ws:\n            X[f'sp_m{scale}'] = speed.rolling(ws, min_periods=max(1, ws // 4)).mean()\n            X[f'sp_s{scale}'] = speed.rolling(ws, min_periods=max(1, ws // 4)).std()\n\n    if len(scales) >= 2 and f'sp_m{scales[0]}' in X.columns and f'sp_m{scales[-1]}' in X.columns:\n        X['sp_ratio'] = X[f'sp_m{scales[0]}'] / (X[f'sp_m{scales[-1]}'] + 1e-6)\n\n    return X\n\n\n\ndef add_state_features(X, center_x, center_y, fps):\n    speed = np.sqrt(center_x.diff()**2 + center_y.diff()**2) * float(fps)\n    w_ma = _scale(15, fps)\n    speed_ma = speed.rolling(w_ma, min_periods=max(1, w_ma // 3)).mean()\n\n    try:\n        bins = [-np.inf, 0.5 * fps, 2.0 * fps, 5.0 * fps, np.inf]\n        speed_states = pd.cut(speed_ma, bins=bins, labels=[0, 1, 2, 3]).astype(float)\n\n        for window in [20, 40, 60, 80]:\n            ws = _scale(window, fps)\n            if len(speed_states) >= ws:\n                for state in [0, 1, 2, 3]:\n                    X[f's{state}_{window}'] = (\n                        (speed_states == state).astype(float)\n                        .rolling(ws, min_periods=max(1, ws // 5)).mean()\n                    )\n                state_changes = (speed_states != speed_states.shift(1)).astype(float)\n                X[f'trans_{window}'] = state_changes.rolling(ws, min_periods=max(1, ws // 5)).sum()\n    except Exception:\n        pass\n\n    return X\n\n\n\ndef add_longrange_features(X, center_x, center_y, fps):\n    for window in [30, 60, 120]:\n        ws = _scale(window, fps)\n        if len(center_x) >= ws:\n            X[f'x_ml{window}'] = center_x.rolling(ws, min_periods=max(5, ws // 6)).mean()\n            X[f'y_ml{window}'] = center_y.rolling(ws, min_periods=max(5, ws // 6)).mean()\n\n    for span in [30, 60, 120]:\n        s = _scale(span, fps)\n        X[f'x_e{span}'] = center_x.ewm(span=s, min_periods=1).mean()\n        X[f'y_e{span}'] = center_y.ewm(span=s, min_periods=1).mean()\n\n    speed = np.sqrt(center_x.diff()**2 + center_y.diff()**2) * float(fps)\n    for window in [30, 60, 120]:\n        ws = _scale(window, fps)\n        if len(speed) >= ws:\n            X[f'sp_pct{window}'] = speed.rolling(ws, min_periods=max(5, ws // 6)).rank(pct=True)\n\n    return X\n\n\n\ndef add_interaction_features(X, mouse_pair, avail_A, avail_B, fps):\n    if 'body_center' not in avail_A or 'body_center' not in avail_B:\n        return X\n\n    rel_x = mouse_pair['A']['body_center']['x'] - mouse_pair['B']['body_center']['x']\n    rel_y = mouse_pair['A']['body_center']['y'] - mouse_pair['B']['body_center']['y']\n    rel_dist = np.sqrt(rel_x**2 + rel_y**2)\n\n    A_vx = mouse_pair['A']['body_center']['x'].diff()\n    A_vy = mouse_pair['A']['body_center']['y'].diff()\n    B_vx = mouse_pair['B']['body_center']['x'].diff()\n    B_vy = mouse_pair['B']['body_center']['y'].diff()\n\n    A_lead = (A_vx * rel_x + A_vy * rel_y) / (np.sqrt(A_vx**2 + A_vy**2) * rel_dist + 1e-6)\n    B_lead = (B_vx * (-rel_x) + B_vy * (-rel_y)) / (np.sqrt(B_vx**2 + B_vy**2) * rel_dist + 1e-6)\n\n    for window in [30, 60]:\n        ws = _scale(window, fps)\n        X[f'A_ld{window}'] = A_lead.rolling(ws, min_periods=max(1, ws // 6)).mean()\n        X[f'B_ld{window}'] = B_lead.rolling(ws, min_periods=max(1, ws // 6)).mean()\n\n    approach = -rel_dist.diff()\n    chase = approach * B_lead\n    w = 30\n    ws = _scale(w, fps)\n    X[f'chase_{w}'] = chase.rolling(ws, min_periods=max(1, ws // 6)).mean()\n\n    for window in [60, 120]:\n        ws = _scale(window, fps)\n        A_sp = np.sqrt(A_vx**2 + A_vy**2)\n        B_sp = np.sqrt(B_vx**2 + B_vy**2)\n        X[f'sp_cor{window}'] = A_sp.rolling(ws, min_periods=max(1, ws // 6)).corr(B_sp)\n\n    return X\n\n\n\ndef transform_single(single_mouse, body_parts_tracked, fps):\n    available_body_parts = single_mouse.columns.get_level_values(0)\n\n    X = pd.DataFrame({\n        f\"{p1}+{p2}\": np.square(single_mouse[p1] - single_mouse[p2]).sum(axis=1, skipna=False)\n        for p1, p2 in itertools.combinations(body_parts_tracked, 2)\n        if p1 in available_body_parts and p2 in available_body_parts\n    })\n    X = X.reindex(columns=[f\"{p1}+{p2}\" for p1, p2 in itertools.combinations(body_parts_tracked, 2)], copy=False)\n\n    if all(p in single_mouse.columns for p in ['ear_left', 'ear_right', 'tail_base']):\n        lag = _scale(10, fps)\n        shifted = single_mouse[['ear_left', 'ear_right', 'tail_base']].shift(lag)\n        speeds = pd.DataFrame({\n            'sp_lf': np.square(single_mouse['ear_left'] - shifted['ear_left']).sum(axis=1, skipna=False),\n            'sp_rt': np.square(single_mouse['ear_right'] - shifted['ear_right']).sum(axis=1, skipna=False),\n            'sp_lf2': np.square(single_mouse['ear_left'] - shifted['tail_base']).sum(axis=1, skipna=False),\n            'sp_rt2': np.square(single_mouse['ear_right'] - shifted['tail_base']).sum(axis=1, skipna=False),\n        })\n        X = pd.concat([X, speeds], axis=1)\n\n    if 'nose+tail_base' in X.columns and 'ear_left+ear_right' in X.columns:\n        X['elong'] = X['nose+tail_base'] / (X['ear_left+ear_right'] + 1e-6)\n\n    if all(p in available_body_parts for p in ['nose', 'body_center', 'tail_base']):\n        v1 = single_mouse['nose'] - single_mouse['body_center']\n        v2 = single_mouse['tail_base'] - single_mouse['body_center']\n        X['body_ang'] = (v1['x'] * v2['x'] + v1['y'] * v2['y']) / (\n            np.sqrt(v1['x']**2 + v1['y']**2) * np.sqrt(v2['x']**2 + v2['y']**2) + 1e-6)\n\n    if 'body_center' in available_body_parts:\n        cx = single_mouse['body_center']['x']\n        cy = single_mouse['body_center']['y']\n\n        for w in [5, 15, 30, 60]:\n            ws = _scale(w, fps)\n            roll = dict(min_periods=1, center=True)\n            X[f'cx_m{w}'] = cx.rolling(ws, **roll).mean()\n            X[f'cy_m{w}'] = cy.rolling(ws, **roll).mean()\n            X[f'cx_s{w}'] = cx.rolling(ws, **roll).std()\n            X[f'cy_s{w}'] = cy.rolling(ws, **roll).std()\n            X[f'x_rng{w}'] = cx.rolling(ws, **roll).max() - cx.rolling(ws, **roll).min()\n            X[f'y_rng{w}'] = cy.rolling(ws, **roll).max() - cy.rolling(ws, **roll).min()\n            X[f'disp{w}'] = np.sqrt(cx.diff().rolling(ws, min_periods=1).sum()**2 +\n                                     cy.diff().rolling(ws, min_periods=1).sum()**2)\n            X[f'act{w}'] = np.sqrt(cx.diff().rolling(ws, min_periods=1).var() +\n                                   cy.diff().rolling(ws, min_periods=1).var())\n\n        X = add_curvature_features(X, cx, cy, fps)\n        X = add_multiscale_features(X, cx, cy, fps)\n        X = add_state_features(X, cx, cy, fps)\n        X = add_longrange_features(X, cx, cy, fps)\n\n    if all(p in available_body_parts for p in ['nose', 'tail_base']):\n        nt_dist = np.sqrt((single_mouse['nose']['x'] - single_mouse['tail_base']['x'])**2 +\n                          (single_mouse['nose']['y'] - single_mouse['tail_base']['y'])**2)\n        for lag in [10, 20, 40]:\n            l = _scale(lag, fps)\n            X[f'nt_lg{lag}'] = nt_dist.shift(l)\n            X[f'nt_df{lag}'] = nt_dist - nt_dist.shift(l)\n\n    if all(p in available_body_parts for p in ['ear_left', 'ear_right']):\n        ear_d = np.sqrt((single_mouse['ear_left']['x'] - single_mouse['ear_right']['x'])**2 +\n                        (single_mouse['ear_left']['y'] - single_mouse['ear_right']['y'])**2)\n        for off in [-30, -20, -10, 10, 20, 30]:\n            o = _scale_signed(off, fps)\n            X[f'ear_o{off}'] = ear_d.shift(-o)\n        w = _scale(30, fps)\n        X['ear_con'] = ear_d.rolling(w, min_periods=1, center=True).std() / \\\n                       (ear_d.rolling(w, min_periods=1, center=True).mean() + 1e-6)\n\n    return X.astype(np.float32, copy=False)\n\n\n\ndef transform_pair(mouse_pair, body_parts_tracked, fps):\n    avail_A = mouse_pair['A'].columns.get_level_values(0)\n    avail_B = mouse_pair['B'].columns.get_level_values(0)\n\n    X = pd.DataFrame({\n        f\"12+{p1}+{p2}\": np.square(mouse_pair['A'][p1] - mouse_pair['B'][p2]).sum(axis=1, skipna=False)\n        for p1, p2 in itertools.product(body_parts_tracked, repeat=2)\n        if p1 in avail_A and p2 in avail_B\n    })\n    X = X.reindex(columns=[f\"12+{p1}+{p2}\" for p1, p2 in itertools.product(body_parts_tracked, repeat=2)], copy=False)\n\n    if ('A', 'ear_left') in mouse_pair.columns and ('B', 'ear_left') in mouse_pair.columns:\n        lag = _scale(10, fps)\n        shA = mouse_pair['A']['ear_left'].shift(lag)\n        shB = mouse_pair['B']['ear_left'].shift(lag)\n        speeds = pd.DataFrame({\n            'sp_A': np.square(mouse_pair['A']['ear_left'] - shA).sum(axis=1, skipna=False),\n            'sp_AB': np.square(mouse_pair['A']['ear_left'] - shB).sum(axis=1, skipna=False),\n            'sp_B': np.square(mouse_pair['B']['ear_left'] - shB).sum(axis=1, skipna=False),\n        })\n        X = pd.concat([X, speeds], axis=1)\n\n    if 'nose+tail_base' in X.columns and 'ear_left+ear_right' in X.columns:\n        X['elong'] = X['nose+tail_base'] / (X['ear_left+ear_right'] + 1e-6)\n\n    if all(p in avail_A for p in ['nose', 'tail_base']) and all(p in avail_B for p in ['nose', 'tail_base']):\n        dir_A = mouse_pair['A']['nose'] - mouse_pair['A']['tail_base']\n        dir_B = mouse_pair['B']['nose'] - mouse_pair['B']['tail_base']\n        X['rel_ori'] = (dir_A['x'] * dir_B['x'] + dir_A['y'] * dir_B['y']) / (\n            np.sqrt(dir_A['x']**2 + dir_A['y']**2) * np.sqrt(dir_B['x']**2 + dir_B['y']**2) + 1e-6)\n\n    if all(p in avail_A for p in ['nose']) and all(p in avail_B for p in ['nose']):\n        cur = np.square(mouse_pair['A']['nose'] - mouse_pair['B']['nose']).sum(axis=1, skipna=False)\n        lag = _scale(10, fps)\n        shA_n = mouse_pair['A']['nose'].shift(lag)\n        shB_n = mouse_pair['B']['nose'].shift(lag)\n        past = np.square(shA_n - shB_n).sum(axis=1, skipna=False)\n        X['appr'] = cur - past\n\n    if 'body_center' in avail_A and 'body_center' in avail_B:\n        cd = np.sqrt((mouse_pair['A']['body_center']['x'] - mouse_pair['B']['body_center']['x'])**2 +\n                     (mouse_pair['A']['body_center']['y'] - mouse_pair['B']['body_center']['y'])**2)\n        X['v_cls'] = (cd < 5.0).astype(float)\n        X['cls'] = ((cd >= 5.0) & (cd < 15.0)).astype(float)\n        X['med'] = ((cd >= 15.0) & (cd < 30.0)).astype(float)\n        X['far'] = (cd >= 30.0).astype(float)\n\n    cd_full = None\n    if 'body_center' in avail_A and 'body_center' in avail_B:\n        cd_full = np.square(mouse_pair['A']['body_center'] - mouse_pair['B']['body_center']).sum(axis=1, skipna=False)\n\n        for w in [5, 15, 30, 60]:\n            ws = _scale(w, fps)\n            roll = dict(min_periods=1, center=True)\n            X[f'd_m{w}'] = cd_full.rolling(ws, **roll).mean()\n            X[f'd_s{w}'] = cd_full.rolling(ws, **roll).std()\n            X[f'd_mn{w}'] = cd_full.rolling(ws, **roll).min()\n            X[f'd_mx{w}'] = cd_full.rolling(ws, **roll).max()\n\n            d_var = cd_full.rolling(ws, **roll).var()\n            X[f'int{w}'] = 1 / (1 + d_var)\n\n            Axd = mouse_pair['A']['body_center']['x'].diff()\n            Ayd = mouse_pair['A']['body_center']['y'].diff()\n            Bxd = mouse_pair['B']['body_center']['x'].diff()\n            Byd = mouse_pair['B']['body_center']['y'].diff()\n            coord = Axd * Bxd + Ayd * Byd\n            X[f'co_m{w}'] = coord.rolling(ws, **roll).mean()\n            X[f'co_s{w}'] = coord.rolling(ws, **roll).std()\n\n    if 'nose' in avail_A and 'nose' in avail_B:\n        nn = np.sqrt((mouse_pair['A']['nose']['x'] - mouse_pair['B']['nose']['x'])**2 +\n                     (mouse_pair['A']['nose']['y'] - mouse_pair['B']['nose']['y'])**2)\n        for lag in [10, 20, 40]:\n            l = _scale(lag, fps)\n            X[f'nn_lg{lag}'] = nn.shift(l)\n            X[f'nn_ch{lag}'] = nn - nn.shift(l)\n            is_cl = (nn < 10.0).astype(float)\n            X[f'cl_ps{lag}'] = is_cl.rolling(l, min_periods=1).mean()\n\n    if 'body_center' in avail_A and 'body_center' in avail_B and cd_full is not None:\n        Avx = mouse_pair['A']['body_center']['x'].diff()\n        Avy = mouse_pair['A']['body_center']['y'].diff()\n        Bvx = mouse_pair['B']['body_center']['x'].diff()\n        Bvy = mouse_pair['B']['body_center']['y'].diff()\n        val = (Avx * Bvx + Avy * Bvy) / (np.sqrt(Avx**2 + Avy**2) * np.sqrt(Bvx**2 + Bvy**2) + 1e-6)\n\n        for off in [-30, -20, -10, 0, 10, 20, 30]:\n            o = _scale_signed(off, fps)\n            X[f'va_{off}'] = val.shift(-o)\n\n        w = _scale(30, fps)\n        X['int_con'] = cd_full.rolling(w, min_periods=1, center=True).std() / \\\n                       (cd_full.rolling(w, min_periods=1, center=True).mean() + 1e-6)\n\n        X = add_interaction_features(X, mouse_pair, avail_A, avail_B, fps)\n\n    return X.astype(np.float32, copy=False)\n\n"},{"cell_type":"markdown","id":"0bcde390","metadata":{},"source":"## Prediction and Submission Functions"},{"cell_type":"code","execution_count":null,"id":"a5fec5d0","metadata":{},"outputs":[],"source":"def robustify(submission, dataset, traintest, cfg, traintest_directory=None):\n    if traintest_directory is None:\n        if traintest == 'train':\n            traintest_directory = cfg.train_tracking_path\n        else:\n            traintest_directory = cfg.test_tracking_path\n\n    old_submission = submission.copy()\n    submission = submission[submission.start_frame < submission.stop_frame]\n    if len(submission) != len(old_submission):\n        print(\"ERROR: Dropped frames with start >= stop\")\n    \n    old_submission = submission.copy()\n    group_list = []\n    for _, group in submission.groupby(['video_id', 'agent_id', 'target_id']):\n        group = group.sort_values('start_frame')\n        mask = np.ones(len(group), dtype=bool)\n        last_stop_frame = 0\n        for i, (_, row) in enumerate(group.iterrows()):\n            if row['start_frame'] < last_stop_frame:\n                mask[i] = False\n            else:\n                last_stop_frame = row['stop_frame']\n        group_list.append(group[mask])\n        \n    submission = pd.concat(group_list)\n    \n    if len(submission) != len(old_submission):\n        print(\"ERROR: Dropped duplicate frames\")\n        \n    s_list = []\n    for idx, row in dataset.iterrows():\n        lab_id = row['lab_id']\n        if lab_id.startswith('MABe22'):\n            continue\n        \n        video_id = row['video_id']\n        if (submission.video_id == video_id).any():\n            continue\n        \n        if type(row.behaviors_labeled) != str:\n            continue\n\n        print(f\"Video {video_id} has no predictions.\")\n        \n        path = f\"{traintest_directory}/{lab_id}/{video_id}.parquet\"\n        vid = pd.read_parquet(path)\n    \n        vid_behaviors = json.loads(row['behaviors_labeled'])\n        vid_behaviors = sorted(list({b.replace(\"'\", \"\") for b in vid_behaviors}))\n        vid_behaviors = [b.split(',') for b in vid_behaviors]\n        vid_behaviors = pd.DataFrame(vid_behaviors, columns=['agent', 'target', 'action'])\n    \n        start_frame = vid.video_frame.min()\n        stop_frame = vid.video_frame.max() + 1\n    \n        for (agent, target), actions in vid_behaviors.groupby(['agent', 'target']):\n            batch_length = int(np.ceil((stop_frame - start_frame) / len(actions)))\n            for i, (_, action_row) in enumerate(actions.iterrows()):\n                batch_start = start_frame + i * batch_length\n                batch_stop = min(batch_start + batch_length, stop_frame)\n                s_list.append((video_id, agent, target, action_row['action'], batch_start, batch_stop))\n\n    if len(s_list) > 0:\n        submission = pd.concat([\n            submission,\n            pd.DataFrame(s_list, columns=['video_id', 'agent_id', 'target_id', 'action', 'start_frame', 'stop_frame'])\n        ])\n        print(\"ERROR: Filled empty videos\")\n\n    submission = submission.reset_index(drop=True)\n    return submission\n\n\n\ndef predict_multiclass(pred, meta, thresholds):\n    ama = np.argmax(pred.values, axis=1)\n    max_proba = pred.max(axis=1).values\n\n    threshold_array = np.array([thresholds.get(col, 0.27) for col in pred.columns])\n    action_thresholds = threshold_array[ama]\n\n    ama = np.where(max_proba >= action_thresholds, ama, -1)\n    ama = pd.Series(ama, index=meta.video_frame)\n    \n    changes_mask = (ama != ama.shift(1)).values\n    ama_changes = ama[changes_mask]\n    meta_changes = meta[changes_mask]\n    \n    mask = ama_changes.values >= 0\n    mask[-1] = False\n    \n    submission_part = pd.DataFrame({\n        'video_id': meta_changes['video_id'][mask].values,\n        'agent_id': meta_changes['agent_id'][mask].values,\n        'target_id': meta_changes['target_id'][mask].values,\n        'action': pred.columns[ama_changes[mask].values],\n        'start_frame': ama_changes.index[mask],\n        'stop_frame': ama_changes.index[1:][mask[:-1]]\n    })\n    \n    stop_video_id = meta_changes['video_id'][1:][mask[:-1]].values\n    stop_agent_id = meta_changes['agent_id'][1:][mask[:-1]].values\n    stop_target_id = meta_changes['target_id'][1:][mask[:-1]].values\n    for i in range(len(submission_part)):\n        video_id = submission_part.video_id.iloc[i]\n        agent_id = submission_part.agent_id.iloc[i]\n        target_id = submission_part.target_id.iloc[i]\n        if stop_video_id[i] != video_id or stop_agent_id[i] != agent_id or stop_target_id[i] != target_id:\n            new_stop_frame = meta.query(\"(video_id == @video_id)\").video_frame.max() + 1\n            submission_part.iat[i, submission_part.columns.get_loc('stop_frame')] = new_stop_frame\n\n    return submission_part\n\n\n\ndef submit(body_parts_tracked_str, switch_tr, section, thresholds, cfg, test):\n    body_parts_tracked = json.loads(body_parts_tracked_str)\n    if len(body_parts_tracked) > 5:\n        body_parts_tracked = [b for b in body_parts_tracked if b not in drop_body_parts]\n        \n    test_subset = test[test.body_parts_tracked == body_parts_tracked_str]\n    generator = generate_mouse_data(\n        test_subset,\n        'test',\n        cfg,\n        generate_single=(switch_tr == 'single'),\n        generate_pair=(switch_tr == 'pair')\n    )\n\n    fps_lookup = (\n        test_subset[['video_id', 'frames_per_second']]\n        .drop_duplicates('video_id')\n        .set_index('video_id')['frames_per_second']\n        .to_dict()\n    )\n\n    submission_list = []\n    for switch_te, data_te, meta_te, actions_te in generator:\n        assert switch_te == switch_tr\n        try:\n            fps_i = _fps_from_meta(meta_te, fps_lookup, default_fps=30.0)\n            \n            if switch_te == 'single':\n                X_te = transform_single(data_te, body_parts_tracked, fps_i)\n            else:\n                X_te = transform_pair(data_te, body_parts_tracked, fps_i)\n            del data_te\n            gc.collect()\n    \n            pred = pd.DataFrame(index=meta_te.video_frame)\n            for action in actions_te:\n                files = glob.glob(f\"{cfg.model_path}/{cfg.model_name}/{section}/{action}/*_trainer_*.pkl\")\n                if len(files) == 1:\n                    trainer = joblib.load(files[0])\n                    pred[action] = trainer.predict(X_te)\n                \n                    del trainer\n                    gc.collect()\n                \n            del X_te\n            gc.collect()\n\n            if pred.shape[1] != 0:\n                submission_part = predict_multiclass(pred, meta_te, thresholds)\n                submission_list.append(submission_part)\n                \n        except KeyError:\n            del data_te\n            gc.collect()\n            \n    return submission_list\n\n"},{"cell_type":"markdown","id":"106fefbd","metadata":{},"source":"## Load Models and Thresholds"},{"cell_type":"code","execution_count":null,"id":"4eedc928","metadata":{},"outputs":[],"source":"# Load thresholds\nthresholds = joblib.load(f\"{cfg.model_path}/{cfg.model_name}/thresholds.pkl\")\nprint(f\"Loaded thresholds from {cfg.model_path}/{cfg.model_name}/thresholds.pkl\")\n\n# Load test data\ntest = pd.read_csv(cfg.test_path)\nbody_parts_tracked_list = list(np.unique(test.body_parts_tracked))\nprint(f\"Loaded test data: {len(test)} videos\")\nprint(f\"Body parts configurations: {len(body_parts_tracked_list) - 1} sections\")\n"},{"cell_type":"markdown","id":"72a33809","metadata":{},"source":"## Main Inference Loop"},{"cell_type":"code","execution_count":null,"id":"cc462ad1","metadata":{},"outputs":[],"source":"# Main inference loop\nsubmission_list = []\ntotal_sections = len(body_parts_tracked_list) - 1\n\nfor section in range(1, len(body_parts_tracked_list)):\n    body_parts_tracked_str = body_parts_tracked_list[section]\n    try:\n        body_parts_tracked = json.loads(body_parts_tracked_str)\n        print(f\"{section}/{total_sections} Processing videos with: {body_parts_tracked}\\n\")\n        \n        if len(body_parts_tracked) > 5:\n            body_parts_tracked = [b for b in body_parts_tracked if b not in drop_body_parts]\n        \n        # Process single mouse predictions\n        if f\"{section}\" in thresholds.get(\"single\", {}):\n            temp_submission_list = submit(\n                body_parts_tracked_str, 'single', section, \n                thresholds[\"single\"][f\"{section}\"], cfg, test\n            )\n            submission_list.extend(temp_submission_list)\n            del temp_submission_list\n            gc.collect()\n        \n        # Process mouse pair predictions\n        if f\"{section}\" in thresholds.get(\"pair\", {}):\n            temp_submission_list = submit(\n                body_parts_tracked_str, 'pair', section,\n                thresholds[\"pair\"][f\"{section}\"], cfg, test\n            )\n            submission_list.extend(temp_submission_list)\n            del temp_submission_list\n            gc.collect()\n            \n    except Exception as e:\n        print(f\"\\tError in section {section}: {e}\")\n        import traceback\n        traceback.print_exc()\n    print()\n"},{"cell_type":"markdown","id":"01a1198c","metadata":{},"source":"## Save Submission"},{"cell_type":"code","execution_count":null,"id":"fd94bdf6","metadata":{},"outputs":[],"source":"# Combine and save submission\nif len(submission_list) > 0:\n    submission = pd.concat(submission_list)\nelse:\n    # Fallback empty submission\n    submission = pd.DataFrame(\n        dict(\n            video_id=438887472,\n            agent_id='mouse1',\n            target_id='self',\n            action='rear',\n            start_frame='278',\n            stop_frame='500'\n        ), index=[44])\n\nsubmission_robust = robustify(submission, test, 'test', cfg)\nsubmission_robust.index.name = 'row_id'\nsubmission_robust.to_csv('submission.csv')\nprint(f\"\\nSubmission saved to submission.csv\")\nprint(f\"Submission shape: {submission_robust.shape}\")\nprint(submission_robust.head())\n"}],"metadata":{"kaggle":{"accelerator":"none","dataSources":["mabe-mouse-behavior-detection"],"dockerImageVersionId":31089,"isGpuEnabled":false,"isInternetEnabled":false,"language":"python","sourceType":"notebook"},"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.11.13"}},"nbformat":4,"nbformat_minor":5}