{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":102335,"databundleVersionId":12518947,"sourceType":"competition"},{"sourceId":242954653,"sourceType":"kernelVersion"}],"dockerImageVersionId":31041,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"**If you support the notebook, please upvote—I’d really appreciate it!**  \n**Also, if you have any questions, feel free to ask—I’ll be happy to answer. 😊**\n### UPDATE: Enhanced IMU Signal Processing with Gravity Removal & Dataset Split Adjustment\n\nThis version builds upon the enhancements from my previous notebook: **[LB 0.76 | IMU+THM/TOF | TF BiLSTM+GRU+Attention](https://www.kaggle.com/code/rktqwe/lb-0-76-imu-thm-tof-tf-bilstm-gru-attention)**. The key changes in *this* update are:\n\n1.  **Gravity Component Removal from Accelerometer Data (Key Improvement):**\n    *   **Purpose:** Raw accelerometer data measures both the device's linear acceleration (actual movement) and the constant pull of gravity. By isolating the linear acceleration, we aim to provide the model with cleaner, more motion-specific signals, potentially improving its ability to distinguish between subtle gestures.\n    *   **Method:**\n        *   We utilize quaternion rotation data (`rot_x`, `rot_y`, `rot_z`, `rot_w`) to determine the device's orientation in 3D space.\n        *   Using `scipy.spatial.transform.Rotation`, we project a standard gravity vector (`[0, 0, 9.81] m/s²`) from the world frame into the sensor's coordinate frame for each timestamp.\n        *   This estimated gravity component in the sensor's frame is then subtracted from the raw `acc_x`, `acc_y`, `acc_z` readings.\n    *   **New Features Derived:**\n        *   `linear_acc_x`, `linear_acc_y`, `linear_acc_z`: Accelerometer readings with gravity removed. These now form the base acceleration features.\n        *   `linear_acc_mag`: Magnitude of the linear acceleration.\n        *   `linear_acc_mag_jerk`: Derivative (jerk) of the linear acceleration magnitude.\n    *   **Impact:** The `imu_cols_base` now uses these `linear_acc_x/y/z` features instead of the raw `acc_x/y/z`. The original `acc_mag` (which includes gravity) is retained as it might still offer complementary information.\n\n2.  **Train/Validation Split Adjustment:**\n    *   The `train_test_split` ratio for creating training and validation sets was changed from `test_size=0.1` (90% train, 10% validation) to `test_size=0.2` (80% train, 20% validation). This provides a larger validation set for more robust evaluation during training.\n  \n\n\n**This solution was developed by building upon the foundational work of two key contributors:**\n\n- **CMI25 | IMU+THM/TOF |TF BiLSTM+GRU+Attention|LB.75** by [yukiZ](https://www.kaggle.com/code/hideyukizushi/cmi25-imu-thm-tof-tf-bilstm-gru-attention-lb-75)\n- **imu-tof** by [Erich von Mainstein](https://www.kaggle.com/code/vonmainstein/imu-tof)\n\n**Special recognition for the exceptional exploratory data analysis:**\n\n- **Sensor Pulse🧠| Viz & EDA for BFRB Detection** by [Tarun Mishra](https://www.kaggle.com/code/tarundirector/sensor-pulse-viz-eda-for-bfrb-detection)\n\n### Implemented Enhancements\n\n#### 1. IMU Signal Processing Optimization (Core Improvement)\n\n**Implemented Features:**\n- Derived kinematic metrics:\n  - Acceleration vector magnitude (`acc_mag`)\n  - Scalar rotation angle (`rot_angle`)\n  - Acceleration derivative (`acc_mag_jerk`)\n  - Angular velocity (`rot_angle_vel`)\n- Initial learning rate reduction from `1e-3` to `5e-4`\n- Implemented cosine decay scheduling:\n  - Parameters: `first_decay_steps = 15 × steps_per_epoch`\n\n**Unsuccessful Experiments (Reverted):**\n- Further LR Reduction: `LR_INIT = 2-e4` worsened score.\n- Dropout Rate Adjustments: No improvement over baseline dropout.\n- TOF/THEM Branch Architecture Change: Replacing simpler CNNs with `residual_se_cnn_blocks` was detrimental.","metadata":{}},{"cell_type":"markdown","source":"### 》》》**Importing the necessary Libraries**","metadata":{}},{"cell_type":"code","source":"import os, json, joblib, numpy as np, pandas as pd\nfrom pathlib import Path\nimport warnings \nwarnings.filterwarnings(\"ignore\")\n\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler, LabelEncoder\nfrom sklearn.utils.class_weight import compute_class_weight\n\nfrom tensorflow.keras.utils import Sequence, to_categorical, pad_sequences\nfrom tensorflow.keras.models import Model, load_model\nfrom tensorflow.keras.layers import (\n    Input, Conv1D, BatchNormalization, Activation, add, MaxPooling1D, Dropout,\n    Bidirectional, LSTM, GlobalAveragePooling1D, Dense, Multiply, Reshape,\n    Lambda, Concatenate, GRU, GaussianNoise\n)\nfrom tensorflow.keras.regularizers import l2\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom tensorflow.keras import backend as K\nimport tensorflow as tf\nimport polars as pl\nfrom sklearn.model_selection import StratifiedGroupKFold\nfrom scipy.spatial.transform import Rotation as R\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-18T19:11:39.158516Z","iopub.execute_input":"2025-06-18T19:11:39.158735Z","iopub.status.idle":"2025-06-18T19:11:52.872833Z","shell.execute_reply.started":"2025-06-18T19:11:39.158718Z","shell.execute_reply":"2025-06-18T19:11:52.872081Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 》》》**Fix Seed**","metadata":{}},{"cell_type":"code","source":"import random\ndef seed_everything(seed):\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    random.seed(seed)\n    np.random.seed(seed)\n    tf.random.set_seed(seed)\n    tf.experimental.numpy.random.seed(seed)\n    os.environ['TF_CUDNN_DETERMINISTIC'] = '1'\n    os.environ['TF_DETERMINISTIC_OPS'] = '1'\nseed_everything(seed=42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-18T19:11:52.874090Z","iopub.execute_input":"2025-06-18T19:11:52.874470Z","iopub.status.idle":"2025-06-18T19:11:52.879063Z","shell.execute_reply.started":"2025-06-18T19:11:52.874454Z","shell.execute_reply":"2025-06-18T19:11:52.878410Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 》》》**Configuration**","metadata":{}},{"cell_type":"code","source":"# (Competition metric will only be imported when TRAINing)\nTRAIN = True                     # ← set to True when you want to train\nRAW_DIR = Path(\"/kaggle/input/cmi-detect-behavior-with-sensor-data\")\nPRETRAINED_DIR = Path(\"/kaggle/input/pretrained-model\")  # used when TRAIN=False\nEXPORT_DIR = Path(\"./\")                                    # artefacts will be saved here\nBATCH_SIZE = 64\nPAD_PERCENTILE = 95\nLR_INIT = 5e-4\nWD = 3e-3\nMIXUP_ALPHA = 0.4\nEPOCHS = 160\nPATIENCE = 40\n\n\nprint(\"▶ imports ready · tensorflow\", tf.__version__)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-18T19:11:52.879913Z","iopub.execute_input":"2025-06-18T19:11:52.880184Z","iopub.status.idle":"2025-06-18T19:11:52.942377Z","shell.execute_reply.started":"2025-06-18T19:11:52.880161Z","shell.execute_reply":"2025-06-18T19:11:52.941727Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 》》》**Utility Functions**","metadata":{}},{"cell_type":"code","source":"#Tensor Manipulations\ndef time_sum(x):\n    return K.sum(x, axis=1)\n\ndef squeeze_last_axis(x):\n    return tf.squeeze(x, axis=-1)\n\ndef expand_last_axis(x):\n    return tf.expand_dims(x, axis=-1)\n\ndef se_block(x, reduction=8):\n    ch = x.shape[-1]\n    se = GlobalAveragePooling1D()(x)\n    se = Dense(ch // reduction, activation='relu')(se)\n    se = Dense(ch, activation='sigmoid')(se)\n    se = Reshape((1, ch))(se)\n    return Multiply()([x, se])\n\n# Residual CNN Block with SE\ndef residual_se_cnn_block(x, filters, kernel_size, pool_size=2, drop=0.3, wd=1e-4):\n    shortcut = x\n    for _ in range(2):\n        x = Conv1D(filters, kernel_size, padding='same', use_bias=False,\n                   kernel_regularizer=l2(wd))(x)\n        x = BatchNormalization()(x)\n        x = Activation('relu')(x)\n    x = se_block(x)\n    if shortcut.shape[-1] != filters:\n        shortcut = Conv1D(filters, 1, padding='same', use_bias=False,\n                          kernel_regularizer=l2(wd))(shortcut)\n        shortcut = BatchNormalization()(shortcut)\n    x = add([x, shortcut])\n    x = Activation('relu')(x)\n    x = MaxPooling1D(pool_size)(x)\n    x = Dropout(drop)(x)\n    return x\n\ndef attention_layer(inputs):\n    score = Dense(1, activation='tanh')(inputs)\n    score = Lambda(squeeze_last_axis)(score)\n    weights = Activation('softmax')(score)\n    weights = Lambda(expand_last_axis)(weights)\n    context = Multiply()([inputs, weights])\n    context = Lambda(time_sum)(context)\n    return context","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-18T19:11:52.943875Z","iopub.execute_input":"2025-06-18T19:11:52.944117Z","iopub.status.idle":"2025-06-18T19:11:52.959681Z","shell.execute_reply.started":"2025-06-18T19:11:52.944101Z","shell.execute_reply":"2025-06-18T19:11:52.959182Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 》》》**Data Helpers**","metadata":{}},{"cell_type":"code","source":"# Normalizes and cleans the time series sequence. \n\ndef preprocess_sequence(df_seq: pd.DataFrame, feature_cols: list[str], scaler: StandardScaler):\n    mat = df_seq[feature_cols].ffill().bfill().fillna(0).values\n    return scaler.transform(mat).astype('float32')\n\n# MixUp the data argumentation in order to regularize the neural network. \n\nclass MixupGenerator(Sequence):\n    def __init__(self, X, y, batch_size, alpha=0.2):\n        self.X, self.y = X, y\n        self.batch = batch_size\n        self.alpha = alpha\n        self.indices = np.arange(len(X))\n    def __len__(self):\n        return int(np.ceil(len(self.X) / self.batch))\n    def __getitem__(self, i):\n        idx = self.indices[i*self.batch:(i+1)*self.batch]\n        Xb, yb = self.X[idx], self.y[idx]\n        lam = np.random.beta(self.alpha, self.alpha)\n        perm = np.random.permutation(len(Xb))\n        X_mix = lam * Xb + (1-lam) * Xb[perm]\n        y_mix = lam * yb + (1-lam) * yb[perm]\n        return X_mix, y_mix\n    def on_epoch_end(self):\n        np.random.shuffle(self.indices)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-18T19:11:52.960359Z","iopub.execute_input":"2025-06-18T19:11:52.960539Z","iopub.status.idle":"2025-06-18T19:11:52.979064Z","shell.execute_reply.started":"2025-06-18T19:11:52.960507Z","shell.execute_reply":"2025-06-18T19:11:52.978450Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def remove_gravity_from_acc(acc_data, rot_data):\n\n    if isinstance(acc_data, pd.DataFrame):\n        acc_values = acc_data[['acc_x', 'acc_y', 'acc_z']].values\n    else:\n        acc_values = acc_data\n\n    if isinstance(rot_data, pd.DataFrame):\n        quat_values = rot_data[['rot_x', 'rot_y', 'rot_z', 'rot_w']].values\n    else:\n        quat_values = rot_data\n\n    num_samples = acc_values.shape[0]\n    linear_accel = np.zeros_like(acc_values)\n    \n    gravity_world = np.array([0, 0, 9.81])\n\n    for i in range(num_samples):\n        if np.all(np.isnan(quat_values[i])) or np.all(np.isclose(quat_values[i], 0)):\n            linear_accel[i, :] = acc_values[i, :] \n            continue\n\n        try:\n            rotation = R.from_quat(quat_values[i])\n            gravity_sensor_frame = rotation.apply(gravity_world, inverse=True)\n            linear_accel[i, :] = acc_values[i, :] - gravity_sensor_frame\n        except ValueError:\n             linear_accel[i, :] = acc_values[i, :]\n             \n    return linear_accel","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-18T19:11:52.979674Z","iopub.execute_input":"2025-06-18T19:11:52.979832Z","iopub.status.idle":"2025-06-18T19:11:52.995890Z","shell.execute_reply.started":"2025-06-18T19:11:52.979819Z","shell.execute_reply":"2025-06-18T19:11:52.995213Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 》》》**Model Definition - Two Branch Architecture**","metadata":{}},{"cell_type":"code","source":"def build_two_branch_model(pad_len, imu_dim, tof_dim, n_classes, wd=1e-4):\n    inp = Input(shape=(pad_len, imu_dim+tof_dim))\n    imu = Lambda(lambda t: t[:, :, :imu_dim])(inp)\n    tof = Lambda(lambda t: t[:, :, imu_dim:])(inp)\n\n    # IMU deep branch\n    x1 = residual_se_cnn_block(imu, 64, 3, drop=0.1, wd=wd)\n    x1 = residual_se_cnn_block(x1, 128, 5, drop=0.1, wd=wd)\n\n    # TOF/Thermal lighter branch\n    x2 = Conv1D(64, 3, padding='same', use_bias=False, kernel_regularizer=l2(wd))(tof)\n    x2 = BatchNormalization()(x2); x2 = Activation('relu')(x2)\n    x2 = MaxPooling1D(2)(x2); x2 = Dropout(0.2)(x2)\n    x2 = Conv1D(128, 3, padding='same', use_bias=False, kernel_regularizer=l2(wd))(x2)\n    x2 = BatchNormalization()(x2); x2 = Activation('relu')(x2)\n    x2 = MaxPooling1D(2)(x2); x2 = Dropout(0.2)(x2)\n\n    merged = Concatenate()([x1, x2])\n\n    xa = Bidirectional(LSTM(128, return_sequences=True, kernel_regularizer=l2(wd)))(merged)\n    xb = Bidirectional(GRU(128, return_sequences=True, kernel_regularizer=l2(wd)))(merged)\n    xc = GaussianNoise(0.09)(merged)\n    xc = Dense(16, activation='elu')(xc)\n    \n    x = Concatenate()([xa, xb, xc])\n    x = Dropout(0.4)(x)\n    x = attention_layer(x)\n\n    for units, drop in [(256, 0.5), (128, 0.3)]:\n        x = Dense(units, use_bias=False, kernel_regularizer=l2(wd))(x)\n        x = BatchNormalization()(x); x = Activation('relu')(x)\n        x = Dropout(drop)(x)\n\n    out = Dense(n_classes, activation='softmax', kernel_regularizer=l2(wd))(x)\n    return Model(inp, out)\n\ntmp_model = build_two_branch_model(127,7,325,18)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-18T19:11:53.431400Z","iopub.execute_input":"2025-06-18T19:11:53.432182Z","iopub.status.idle":"2025-06-18T19:11:56.214383Z","shell.execute_reply.started":"2025-06-18T19:11:53.432160Z","shell.execute_reply":"2025-06-18T19:11:56.213802Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 》》》**Training / Inference Pipeline**","metadata":{}},{"cell_type":"code","source":"if TRAIN:\n    print(\"▶ TRAIN MODE – loading dataset …\")\n    df = pd.read_csv(RAW_DIR / \"train.csv\")\n\n    train_dem_df = pd.read_csv(RAW_DIR / \"train_demographics.csv\")\n    df_for_groups = pd.merge(df.copy(), train_dem_df, on='subject', how='left')\n\n    le = LabelEncoder()\n    df['gesture_int'] = le.fit_transform(df['gesture'])\n    np.save(EXPORT_DIR / \"gesture_classes.npy\", le.classes_)\n    gesture_classes = le.classes_\n\n    print(\"  Calculating base engineered IMU features (magnitude, angle)...\")\n    df['acc_mag'] = np.sqrt(df['acc_x']**2 + df['acc_y']**2 + df['acc_z']**2)\n    df['rot_angle'] = 2 * np.arccos(df['rot_w'].clip(-1, 1))\n    \n    print(\"  Calculating engineered IMU derivatives (jerk, angular velocity) for original acc_mag...\")\n    df['acc_mag_jerk'] = df.groupby('sequence_id')['acc_mag'].diff().fillna(0)\n    df['rot_angle_vel'] = df.groupby('sequence_id')['rot_angle'].diff().fillna(0)\n\n    print(\"  Removing gravity and calculating linear acceleration features...\")\n    \n    linear_accel_list = []\n    for _, group in df.groupby('sequence_id'):\n        acc_data_group = group[['acc_x', 'acc_y', 'acc_z']]\n        rot_data_group = group[['rot_x', 'rot_y', 'rot_z', 'rot_w']]\n        linear_accel_group = remove_gravity_from_acc(acc_data_group, rot_data_group)\n        linear_accel_list.append(pd.DataFrame(linear_accel_group, columns=['linear_acc_x', 'linear_acc_y', 'linear_acc_z'], index=group.index))\n    \n    df_linear_accel = pd.concat(linear_accel_list)\n    df = pd.concat([df, df_linear_accel], axis=1)\n\n    df['linear_acc_mag'] = np.sqrt(df['linear_acc_x']**2 + df['linear_acc_y']**2 + df['linear_acc_z']**2)\n    df['linear_acc_mag_jerk'] = df.groupby('sequence_id')['linear_acc_mag'].diff().fillna(0)\n\n    meta_cols = { ... }\n\n    imu_cols_base = ['linear_acc_x', 'linear_acc_y', 'linear_acc_z']\n    imu_cols_base.extend([c for c in df.columns if c.startswith('rot_') and c not in ['rot_angle', 'rot_angle_vel']])\n    \n    imu_engineered_features = [\n        'acc_mag', 'rot_angle',\n        'acc_mag_jerk', 'rot_angle_vel',\n        'linear_acc_mag', 'linear_acc_mag_jerk'\n    ]\n    imu_cols = imu_cols_base + imu_engineered_features\n    imu_cols = list(dict.fromkeys(imu_cols))\n\n    thm_cols_original = [c for c in df.columns if c.startswith('thm_')]\n    \n    tof_aggregated_cols_template = []\n    for i in range(1, 6):\n        tof_aggregated_cols_template.extend([f'tof_{i}_mean', f'tof_{i}_std', f'tof_{i}_min', f'tof_{i}_max'])\n\n    final_feature_cols = imu_cols + thm_cols_original + tof_aggregated_cols_template\n    imu_dim_final = len(imu_cols)\n    tof_thm_aggregated_dim_final = len(thm_cols_original) + len(tof_aggregated_cols_template)\n    \n    print(f\"  IMU (incl. engineered & derivatives) {imu_dim_final} | THM + Aggregated TOF {tof_thm_aggregated_dim_final} | total {len(final_feature_cols)} features\")\n    np.save(EXPORT_DIR / \"feature_cols.npy\", np.array(final_feature_cols))\n\n    print(\"  Building sequences with aggregated TOF and preparing data for scaler...\")\n    seq_gp = df.groupby('sequence_id') \n    \n    all_steps_for_scaler_list = []\n    X_list_unscaled, y_list_int_for_stratify, lens = [], [], [] \n\n    for seq_id, seq_df_orig in seq_gp:\n        seq_df = seq_df_orig.copy()\n\n        for i in range(1, 6):\n            pixel_cols_tof = [f\"tof_{i}_v{p}\" for p in range(64)]\n            tof_sensor_data = seq_df[pixel_cols_tof].replace(-1, np.nan)\n            seq_df[f'tof_{i}_mean'] = tof_sensor_data.mean(axis=1)\n            seq_df[f'tof_{i}_std']  = tof_sensor_data.std(axis=1)\n            seq_df[f'tof_{i}_min']  = tof_sensor_data.min(axis=1)\n            seq_df[f'tof_{i}_max']  = tof_sensor_data.max(axis=1)\n        \n        mat_unscaled = seq_df[final_feature_cols].ffill().bfill().fillna(0).values.astype('float32')\n        \n        all_steps_for_scaler_list.append(mat_unscaled)\n        X_list_unscaled.append(mat_unscaled)\n        y_list_int_for_stratify.append(seq_df['gesture_int'].iloc[0])\n        lens.append(len(mat_unscaled))\n\n    print(\"  Fitting StandardScaler...\")\n    all_steps_concatenated = np.concatenate(all_steps_for_scaler_list, axis=0)\n    scaler = StandardScaler().fit(all_steps_concatenated)\n    joblib.dump(scaler, EXPORT_DIR / \"scaler.pkl\")\n    del all_steps_for_scaler_list, all_steps_concatenated\n\n    print(\"  Scaling and padding sequences...\")\n    X_scaled_list = [scaler.transform(x_seq) for x_seq in X_list_unscaled]\n    del X_list_unscaled\n\n    pad_len = int(np.percentile(lens, PAD_PERCENTILE))\n    np.save(EXPORT_DIR / \"sequence_maxlen.npy\", pad_len)\n    \n    X = pad_sequences(X_scaled_list, maxlen=pad_len, padding='post', truncating='post', dtype='float32')\n    del X_scaled_list\n    \n    y_int_for_stratify = np.array(y_list_int_for_stratify)\n    y = to_categorical(y_int_for_stratify, num_classes=len(le.classes_))\n\n    print(\"  Splitting data and preparing for training...\")\n    X_tr, X_val, y_tr, y_val = train_test_split(X, y, test_size=0.2, random_state=82, stratify=y_int_for_stratify)\n\n    cw_vals = compute_class_weight('balanced', classes=np.arange(len(le.classes_)), y=y_int_for_stratify)\n    class_weight = dict(enumerate(cw_vals))\n\n    model = build_two_branch_model(pad_len, imu_dim_final, tof_thm_aggregated_dim_final, len(le.classes_), wd=WD)\n    \n    steps = len(X_tr) // BATCH_SIZE\n    lr_sched = tf.keras.optimizers.schedules.CosineDecayRestarts(5e-4, first_decay_steps=15 * steps) \n    \n    model.compile(optimizer=Adam(lr_sched),\n                  loss=tf.keras.losses.CategoricalCrossentropy(label_smoothing=0.1),\n                  metrics=['accuracy'])\n\n    train_gen = MixupGenerator(X_tr, y_tr, batch_size=BATCH_SIZE, alpha=MIXUP_ALPHA)\n    cb = EarlyStopping(patience=PATIENCE, restore_best_weights=True, verbose=1, monitor='val_accuracy', mode='max')\n    \n    print(\"  Starting model training...\")\n    model.fit(train_gen, epochs=EPOCHS, validation_data=(X_val, y_val),\n              class_weight=class_weight, callbacks=[cb], verbose=1)\n\n    model.save(EXPORT_DIR / \"gesture_two_branch_mixup.h5\")\n    print(\"✔ Training done – artefacts saved in\", EXPORT_DIR)\n\n    from cmi_2025_metric_copy_for_import import CompetitionMetric\n    preds_val = model.predict(X_val).argmax(1)\n    true_val_int  = y_val.argmax(1)\n    \n    h_f1 = CompetitionMetric().calculate_hierarchical_f1(\n        pd.DataFrame({'gesture': le.classes_[true_val_int]}),\n        pd.DataFrame({'gesture': le.classes_[preds_val]}))\n    print(\"Hold‑out H‑F1 =\", round(h_f1, 4))\n\nelse:\n    print(\"▶ INFERENCE MODE – loading artefacts from\", PRETRAINED_DIR)\n    final_feature_cols = np.load(PRETRAINED_DIR / \"feature_cols.npy\", allow_pickle=True).tolist()\n    pad_len        = int(np.load(PRETRAINED_DIR / \"sequence_maxlen.npy\"))\n    scaler         = joblib.load(PRETRAINED_DIR / \"scaler.pkl\")\n    gesture_classes = np.load(PRETRAINED_DIR / \"gesture_classes.npy\", allow_pickle=True)\n\n    temp_imu_cols = [c for c in final_feature_cols if c.startswith('acc_') or c.startswith('rot_')]\n    imu_dim_final = len(temp_imu_cols)\n    tof_thm_aggregated_dim_final = len(final_feature_cols) - imu_dim_final\n\n    custom_objs = {\n        'time_sum': time_sum,\n        'squeeze_last_axis': squeeze_last_axis,\n        'expand_last_axis': expand_last_axis,\n        'se_block': se_block,\n        'residual_se_cnn_block': residual_se_cnn_block,\n        'attention_layer': attention_layer,\n    }\n    model = load_model(PRETRAINED_DIR / \"gesture_two_branch_mixup.h5\",\n                       compile=False, custom_objects=custom_objs)\n    print(\"  Model, scaler, feature_cols, pad_len loaded – ready for evaluation\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-18T19:11:56.966773Z","iopub.execute_input":"2025-06-18T19:11:56.967046Z","iopub.status.idle":"2025-06-18T19:25:24.251973Z","shell.execute_reply.started":"2025-06-18T19:11:56.967027Z","shell.execute_reply":"2025-06-18T19:25:24.251384Z"},"scrolled":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 》》》**Predict**","metadata":{}},{"cell_type":"code","source":"def predict(sequence: pl.DataFrame, demographics: pl.DataFrame) -> str:\n    df_seq = sequence.to_pandas()\n\n    df_seq['acc_mag'] = np.sqrt(df_seq['acc_x']**2 + df_seq['acc_y']**2 + df_seq['acc_z']**2)\n    df_seq['rot_angle'] = 2 * np.arccos(df_seq['rot_w'].clip(-1, 1))\n    df_seq['acc_mag_jerk'] = df_seq['acc_mag'].diff().fillna(0)\n    df_seq['rot_angle_vel'] = df_seq['rot_angle'].diff().fillna(0)\n\n    acc_cols_for_gravity_removal = ['acc_x', 'acc_y', 'acc_z']\n    rot_cols_for_gravity_removal = ['rot_x', 'rot_y', 'rot_z', 'rot_w']\n\n    if not all(col in df_seq.columns for col in acc_cols_for_gravity_removal + rot_cols_for_gravity_removal):\n        print(f\"Warning: Missing raw acc/rot columns for gravity removal in predict for sequence. Using raw acc as linear.\")\n        df_seq['linear_acc_x'] = df_seq.get('acc_x', 0)\n        df_seq['linear_acc_y'] = df_seq.get('acc_y', 0)\n        df_seq['linear_acc_z'] = df_seq.get('acc_z', 0)\n    else:\n        acc_data_seq = df_seq[acc_cols_for_gravity_removal]\n        rot_data_seq = df_seq[rot_cols_for_gravity_removal]\n        linear_accel_seq_arr = remove_gravity_from_acc(acc_data_seq, rot_data_seq)\n        \n        df_seq['linear_acc_x'] = linear_accel_seq_arr[:, 0]\n        df_seq['linear_acc_y'] = linear_accel_seq_arr[:, 1]\n        df_seq['linear_acc_z'] = linear_accel_seq_arr[:, 2]\n    \n    df_seq['linear_acc_mag'] = np.sqrt(df_seq['linear_acc_x']**2 + df_seq['linear_acc_y']**2 + df_seq['linear_acc_z']**2)\n    df_seq['linear_acc_mag_jerk'] = df_seq['linear_acc_mag'].diff().fillna(0)\n    \n    for i in range(1, 6): \n        pixel_cols_tof = [f\"tof_{i}_v{p}\" for p in range(64)]\n        if not all(col in df_seq.columns for col in pixel_cols_tof):\n            print(f\"Warning: Missing some TOF pixel columns for tof_{i} in predict. Filling aggregates with 0.\")\n            df_seq[f'tof_{i}_mean'] = 0\n            df_seq[f'tof_{i}_std']  = 0\n            df_seq[f'tof_{i}_min']  = 0\n            df_seq[f'tof_{i}_max']  = 0\n            continue\n\n        tof_sensor_data = df_seq[pixel_cols_tof].replace(-1, np.nan)\n        df_seq[f'tof_{i}_mean'] = tof_sensor_data.mean(axis=1)\n        df_seq[f'tof_{i}_std']  = tof_sensor_data.std(axis=1)\n        df_seq[f'tof_{i}_min']  = tof_sensor_data.min(axis=1)\n        df_seq[f'tof_{i}_max']  = tof_sensor_data.max(axis=1)\n        \n    if 'tof_range_across_sensors' in final_feature_cols:\n        tof_mean_cols_for_contrast = [f'tof_{i}_mean' for i in range(1, 6) if f'tof_{i}_mean' in df_seq.columns]\n        thm_cols_for_contrast = [f'thm_{i}' for i in range(1, 6) if f'thm_{i}' in df_seq.columns]\n\n        if tof_mean_cols_for_contrast:\n            tof_values_for_contrast = df_seq[tof_mean_cols_for_contrast]\n            df_seq['tof_range_across_sensors'] = tof_values_for_contrast.max(axis=1) - tof_values_for_contrast.min(axis=1)\n            df_seq['tof_std_across_sensors'] = tof_values_for_contrast.std(axis=1)\n        else:\n            df_seq['tof_range_across_sensors'] = 0\n            df_seq['tof_std_across_sensors'] = 0\n\n        if thm_cols_for_contrast:\n            thm_values_for_contrast = df_seq[thm_cols_for_contrast]\n            df_seq['thm_range_across_sensors'] = thm_values_for_contrast.max(axis=1) - thm_values_for_contrast.min(axis=1)\n            df_seq['thm_std_across_sensors'] = thm_values_for_contrast.std(axis=1)\n        else:\n            df_seq['thm_range_across_sensors'] = 0\n            df_seq['thm_std_across_sensors'] = 0\n        \n    df_seq_final_features = pd.DataFrame(index=df_seq.index)\n    for col_name in final_feature_cols:\n        if col_name in df_seq.columns:\n            df_seq_final_features[col_name] = df_seq[col_name]\n        else:\n            print(f\"CRITICAL ERROR IN PREDICT: Feature '{col_name}' expected by model (from final_feature_cols) was NOT generated in df_seq. Filling with 0. THIS IS LIKELY A BUG.\")\n            df_seq_final_features[col_name] = 0 \n            \n    mat_unscaled = df_seq_final_features.ffill().bfill().fillna(0).values.astype('float32')\n    \n    mat_scaled = scaler.transform(mat_unscaled)\n    \n    pad_input = pad_sequences([mat_scaled], maxlen=pad_len, padding='post', truncating='post', dtype='float32')\n    \n    idx = int(model.predict(pad_input, verbose=0).argmax(1)[0])\n    return str(gesture_classes[idx])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-18T19:25:24.253101Z","iopub.execute_input":"2025-06-18T19:25:24.253314Z","iopub.status.idle":"2025-06-18T19:25:24.267068Z","shell.execute_reply.started":"2025-06-18T19:25:24.253298Z","shell.execute_reply":"2025-06-18T19:25:24.266430Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 》》》**Submit Inference server**","metadata":{}},{"cell_type":"code","source":"import kaggle_evaluation.cmi_inference_server\ninference_server = kaggle_evaluation.cmi_inference_server.CMIInferenceServer(predict)\n\nif os.getenv('KAGGLE_IS_COMPETITION_RERUN'):\n    inference_server.serve()\nelse:\n    inference_server.run_local_gateway(\n        data_paths=(\n            '/kaggle/input/cmi-detect-behavior-with-sensor-data/test.csv',\n            '/kaggle/input/cmi-detect-behavior-with-sensor-data/test_demographics.csv',\n        )\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-18T19:25:24.267687Z","iopub.execute_input":"2025-06-18T19:25:24.267941Z","iopub.status.idle":"2025-06-18T19:25:26.130811Z","shell.execute_reply.started":"2025-06-18T19:25:24.267921Z","shell.execute_reply":"2025-06-18T19:25:26.130248Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}