{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":59093,"databundleVersionId":7469972,"sourceType":"competition"},{"sourceId":7392733,"sourceType":"datasetVersion","datasetId":4297749},{"sourceId":7392775,"sourceType":"datasetVersion","datasetId":4297782},{"sourceId":7402356,"sourceType":"datasetVersion","datasetId":4304475},{"sourceId":7403069,"sourceType":"datasetVersion","datasetId":4304949},{"sourceId":7447509,"sourceType":"datasetVersion","datasetId":4334995},{"sourceId":7450712,"sourceType":"datasetVersion","datasetId":4336944},{"sourceId":7581697,"sourceType":"datasetVersion","datasetId":4413439},{"sourceId":7581715,"sourceType":"datasetVersion","datasetId":4413451},{"sourceId":7581720,"sourceType":"datasetVersion","datasetId":4413454},{"sourceId":158958765,"sourceType":"kernelVersion"},{"sourceId":159333316,"sourceType":"kernelVersion"},{"sourceId":159396114,"sourceType":"kernelVersion"}],"dockerImageVersionId":30636,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Model 1","metadata":{}},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings('ignore', category=Warning)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:11:46.370052Z","iopub.execute_input":"2024-02-16T11:11:46.370561Z","iopub.status.idle":"2024-02-16T11:11:46.374983Z","shell.execute_reply.started":"2024-02-16T11:11:46.370523Z","shell.execute_reply":"2024-02-16T11:11:46.373971Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os, gc\nos.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0,1\"","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:11:47.155595Z","iopub.execute_input":"2024-02-16T11:11:47.155972Z","iopub.status.idle":"2024-02-16T11:11:47.160657Z","shell.execute_reply.started":"2024-02-16T11:11:47.155942Z","shell.execute_reply":"2024-02-16T11:11:47.159539Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nprint('TensorFlow version =',tf.__version__)\n\n\ngpus = tf.config.list_physical_devices('GPU')\nif len(gpus) <= 1: \n    strategy = tf.distribute.OneDeviceStrategy(device=\"/gpu:0\")\n    print(f'Using {len(gpus)} GPU')\nelse: \n    strategy = tf.distribute.MirroredStrategy()\n    print(f'Using {len(gpus)} GPUs')\n\nVER = 5\n\n# IF THIS EQUALS NONE, THEN WE TRAIN NEW MODELS\n# IF THIS EQUALS DISK PATH, THEN WE LOAD PREVIOUSLY TRAINED MODELS\nLOAD_MODELS_FROM = '/kaggle/input/brain-efficientnet-models-v3-v4-v5/'\n\nUSE_KAGGLE_SPECTROGRAMS = True\nUSE_EEG_SPECTROGRAMS = True","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:11:48.350968Z","iopub.execute_input":"2024-02-16T11:11:48.351342Z","iopub.status.idle":"2024-02-16T11:11:48.361636Z","shell.execute_reply.started":"2024-02-16T11:11:48.351312Z","shell.execute_reply":"2024-02-16T11:11:48.360591Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# USE MIXED PRECISION\nMIX = True\nif MIX:\n    tf.config.optimizer.set_experimental_options({\"auto_mixed_precision\": True})\n    print('Mixed precision enabled')\nelse:\n    print('Using full precision')","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:45:42.214354Z","iopub.execute_input":"2024-02-16T10:45:42.214705Z","iopub.status.idle":"2024-02-16T10:45:42.220362Z","shell.execute_reply.started":"2024-02-16T10:45:42.214678Z","shell.execute_reply":"2024-02-16T10:45:42.219431Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/hms-harmful-brain-activity-classification/train.csv')\nTARGETS = df.columns[-6:]\nprint('Train shape : ', df.shape )\nprint('Targets     :', list(TARGETS))\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:44:13.377212Z","iopub.execute_input":"2024-02-16T10:44:13.378289Z","iopub.status.idle":"2024-02-16T10:44:13.575986Z","shell.execute_reply.started":"2024-02-16T10:44:13.378232Z","shell.execute_reply":"2024-02-16T10:44:13.574982Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = df.groupby('eeg_id')[['spectrogram_id','spectrogram_label_offset_seconds']].agg(\n    {'spectrogram_id':'first','spectrogram_label_offset_seconds':'min'})\ntrain.columns = ['spec_id','min']\n\ntmp = df.groupby('eeg_id')[['spectrogram_id','spectrogram_label_offset_seconds']].agg(\n    {'spectrogram_label_offset_seconds':'max'})\ntrain['max'] = tmp\n\ntmp = df.groupby('eeg_id')[['patient_id']].agg('first')\ntrain['patient_id'] = tmp\n\ntmp = df.groupby('eeg_id')[TARGETS].agg('sum')\nfor t in TARGETS:\n    train[t] = tmp[t].values\n    \ny_data = train[TARGETS].values\ny_data = y_data / y_data.sum(axis=1,keepdims=True)\ntrain[TARGETS] = y_data\n\ntmp = df.groupby('eeg_id')[['expert_consensus']].agg('first')\ntrain['target'] = tmp\n\ntrain = train.reset_index()\nprint('Train non-overlapp eeg_id shape:', train.shape )\ntrain.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:44:22.538160Z","iopub.execute_input":"2024-02-16T10:44:22.538952Z","iopub.status.idle":"2024-02-16T10:44:22.645971Z","shell.execute_reply.started":"2024-02-16T10:44:22.538914Z","shell.execute_reply":"2024-02-16T10:44:22.645105Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nREAD_SPEC_FILES = False\n\n# READ ALL SPECTROGRAMS\nPATH = '/kaggle/input/hms-harmful-brain-activity-classification/train_spectrograms/'\nfiles = os.listdir(PATH)\nprint(f'There are {len(files)} spectrogram parquets')\n\nif READ_SPEC_FILES:    \n    spectrograms = {}\n    for i,f in enumerate(files):\n        if i%100==0: print(i,', ',end='')\n        tmp = pd.read_parquet(f'{PATH}{f}')\n        name = int(f.split('.')[0])\n        spectrograms[name] = tmp.iloc[:,1:].values\nelse:\n    spectrograms = np.load('/kaggle/input/brain-spectrograms/specs.npy', allow_pickle=True).item()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:44:38.492068Z","iopub.execute_input":"2024-02-16T10:44:38.492431Z","iopub.status.idle":"2024-02-16T10:45:36.869969Z","shell.execute_reply.started":"2024-02-16T10:44:38.492403Z","shell.execute_reply":"2024-02-16T10:45:36.869045Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nREAD_EEG_SPEC_FILES = False\n\nif READ_EEG_SPEC_FILES:\n    all_eegs = {}\n    for i, e in enumerate(train.eeg_id.values):\n        if i % 100 == 0: print(i,', ',end='')\n        x = np.load(f'/kaggle/input/brain-eeg-spectrograms/EEG_Spectrograms/{e}.npy')\n        all_eegs[e] = x\nelse:\n    all_eegs = np.load('/kaggle/input/brain-eeg-spectrograms/eeg_specs.npy', allow_pickle=True).item()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:45:51.418115Z","iopub.execute_input":"2024-02-16T10:45:51.418851Z","iopub.status.idle":"2024-02-16T10:47:02.429739Z","shell.execute_reply.started":"2024-02-16T10:45:51.418816Z","shell.execute_reply":"2024-02-16T10:47:02.428686Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import albumentations as albu\nTARS  = {'Seizure':0, 'LPD':1, 'GPD':2, 'LRDA':3, 'GRDA':4, 'Other':5}\nTARS2 = {x:y for y, x in TARS.items()}\n\nclass DataGenerator(tf.keras.utils.Sequence):\n    'Generates data for Keras'\n    def __init__(self, data, batch_size=32, shuffle=False, augment=False, mode='train',\n                 specs = spectrograms, eeg_specs = all_eegs): \n\n        self.data = data\n        self.batch_size = batch_size\n        self.shuffle = shuffle\n        self.augment = augment\n        self.mode = mode\n        self.specs = specs\n        self.eeg_specs = eeg_specs\n        self.on_epoch_end()\n        \n    def __len__(self):\n        'Denotes the number of batches per epoch'\n        ct = int( np.ceil( len(self.data) / self.batch_size ) )\n        return ct\n\n    def __getitem__(self, index):\n        'Generate one batch of data'\n        indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]\n        X, y = self.__data_generation(indexes)\n        if self.augment: X = self.__augment_batch(X) \n        return X, y\n\n    def on_epoch_end(self):\n        'Updates indexes after each epoch'\n        self.indexes = np.arange( len(self.data) )\n        if self.shuffle: np.random.shuffle(self.indexes)\n                        \n    def __data_generation(self, indexes):\n        'Generates data containing batch_size samples' \n        \n        X = np.zeros((len(indexes),128,256,8),dtype='float32')\n        y = np.zeros((len(indexes),6),dtype='float32')\n        img = np.ones((128,256),dtype='float32')\n        \n        for j,i in enumerate(indexes):\n            row = self.data.iloc[i]\n            if self.mode=='test': \n                r = 0\n            else: \n                r = int( (row['min'] + row['max'])//4 )\n\n            for k in range(4):\n                # EXTRACT 300 ROWS OF SPECTROGRAM\n                img = self.specs[row.spec_id][r:r+300,k*100:(k+1)*100].T\n                \n                # LOG TRANSFORM SPECTROGRAM\n                img = np.clip(img,np.exp(-4),np.exp(8))\n                img = np.log(img)\n                \n                # STANDARDIZE PER IMAGE\n                ep = 1e-6\n                m = np.nanmean(img.flatten())\n                s = np.nanstd(img.flatten())\n                img = (img-m)/(s+ep)\n                img = np.nan_to_num(img, nan=0.0)\n                \n                # CROP TO 256 TIME STEPS\n                X[j,14:-14,:,k] = img[:,22:-22] / 2.0\n        \n            # EEG SPECTROGRAMS\n            img = self.eeg_specs[row.eeg_id]\n            X[j,:,:,4:] = img\n                \n            if self.mode!='test':\n                y[j,] = row[TARGETS]\n            \n        return X,y\n    \n    def __random_transform(self, img):\n        composition = albu.Compose([\n            albu.HorizontalFlip(p=0.5),\n            #albu.CoarseDropout(max_holes=8,max_height=32,max_width=32,fill_value=0,p=0.5),\n        ])\n        return composition(image=img)['image']\n            \n    def __augment_batch(self, img_batch):\n        for i in range(img_batch.shape[0]):\n            img_batch[i, ] = self.__random_transform(img_batch[i, ])\n        return img_batch","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:48:08.780731Z","iopub.execute_input":"2024-02-16T10:48:08.781089Z","iopub.status.idle":"2024-02-16T10:48:10.963540Z","shell.execute_reply.started":"2024-02-16T10:48:08.781060Z","shell.execute_reply":"2024-02-16T10:48:10.962702Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"gen     = DataGenerator(train, batch_size=32, shuffle=False)\nROWS    = 2\nCOLS    = 3\nBATCHES = 2\n\nfor i,(x,y) in enumerate(gen):\n    plt.figure(figsize=(20,8))\n    for j in range(ROWS):\n        for k in range(COLS):\n            plt.subplot(ROWS,COLS,j*COLS+k+1)\n            t = y[j*COLS+k]\n            img = x[j*COLS+k,:,:,0][::-1,]\n            mn = img.flatten().min()\n            mx = img.flatten().max()\n            img = (img-mn)/(mx-mn)\n            plt.imshow(img)\n            tars = f'[{t[0]:0.2f}'\n            for s in t[1:]: tars += f', {s:0.2f}'\n            eeg = train.eeg_id.values[i*32+j*COLS+k]\n            plt.title(f'EEG = {eeg}\\nTarget = {tars}',size=12)\n            plt.yticks([])\n            plt.ylabel('Frequencies (Hz)',size=14)\n            plt.xlabel('Time (sec)',size=16)\n    plt.show()\n    if i==BATCHES-1: break","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:48:48.532364Z","iopub.execute_input":"2024-02-16T10:48:48.532992Z","iopub.status.idle":"2024-02-16T10:48:51.169658Z","shell.execute_reply.started":"2024-02-16T10:48:48.532961Z","shell.execute_reply":"2024-02-16T10:48:51.168708Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import math\nLR_START          = 1e-6\nLR_MAX            = 1e-3\nLR_MIN            = 1e-6\nLR_RAMPUP_EPOCHS  = 0\nLR_SUSTAIN_EPOCHS = 0\nEPOCHS2           = 10\n\ndef lrfn(epoch):\n    if epoch < LR_RAMPUP_EPOCHS:\n        lr = (LR_MAX - LR_START) / LR_RAMPUP_EPOCHS * epoch + LR_START\n    elif epoch < LR_RAMPUP_EPOCHS + LR_SUSTAIN_EPOCHS:\n        lr = LR_MAX\n    else:\n        decay_total_epochs = EPOCHS2 - LR_RAMPUP_EPOCHS - LR_SUSTAIN_EPOCHS - 1\n        decay_epoch_index = epoch - LR_RAMPUP_EPOCHS - LR_SUSTAIN_EPOCHS\n        phase = math.pi * decay_epoch_index / decay_total_epochs\n        cosine_decay = 0.5 * (1 + math.cos(phase))\n        lr = (LR_MAX - LR_MIN) * cosine_decay + LR_MIN\n    return lr\n\nrng = [i for i in range(EPOCHS2)]\nlr_y = [lrfn(x) for x in rng]\nplt.figure(figsize=(10, 4))\nplt.plot(rng, lr_y, '-o')\nplt.xlabel('epoch',size=14); plt.ylabel('learning rate',size=14)\nplt.title('Cosine Training Schedule',size=16); plt.show()\n\nLR2 = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose = True)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:50:12.126779Z","iopub.execute_input":"2024-02-16T10:50:12.127536Z","iopub.status.idle":"2024-02-16T10:50:12.350368Z","shell.execute_reply.started":"2024-02-16T10:50:12.127504Z","shell.execute_reply":"2024-02-16T10:50:12.349330Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"LR_START          = 1e-4\nLR_MAX            = 1e-3\nLR_RAMPUP_EPOCHS  = 0\nLR_SUSTAIN_EPOCHS = 1\nLR_STEP_DECAY     = 0.1\nEVERY             = 1\nEPOCHS            = 4\n\ndef lrfn(epoch):\n    if epoch < LR_RAMPUP_EPOCHS:\n        lr = (LR_MAX - LR_START) / LR_RAMPUP_EPOCHS * epoch + LR_START\n    elif epoch < LR_RAMPUP_EPOCHS + LR_SUSTAIN_EPOCHS:\n        lr = LR_MAX\n    else:\n        lr = LR_MAX * LR_STEP_DECAY**((epoch - LR_RAMPUP_EPOCHS - LR_SUSTAIN_EPOCHS)//EVERY)\n    return lr\n\nrng = [i for i in range(EPOCHS)]\ny = [lrfn(x) for x in rng]\nplt.figure(figsize=(10, 4))\nplt.plot(rng, y, 'o-'); \nplt.xlabel('epoch',size=14); plt.ylabel('learning rate',size=14)\nplt.title('Step Training Schedule',size=16); plt.show()\n\nLR = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose = True)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:50:54.410227Z","iopub.execute_input":"2024-02-16T10:50:54.410593Z","iopub.status.idle":"2024-02-16T10:50:54.688901Z","shell.execute_reply.started":"2024-02-16T10:50:54.410565Z","shell.execute_reply":"2024-02-16T10:50:54.688039Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install --no-index --find-links=/kaggle/input/tf-efficientnet-whl-files /kaggle/input/tf-efficientnet-whl-files/efficientnet-1.1.1-py3-none-any.whl","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:50:59.827471Z","iopub.execute_input":"2024-02-16T10:50:59.827823Z","iopub.status.idle":"2024-02-16T10:51:13.387799Z","shell.execute_reply.started":"2024-02-16T10:50:59.827794Z","shell.execute_reply":"2024-02-16T10:51:13.386665Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import efficientnet.tfkeras as efn\n\ndef build_model():\n    \n    inp = tf.keras.Input(shape=(128, 256, 8))\n    base_model = efn.EfficientNetB0(include_top=False, weights=None, input_shape=None)\n    base_model.load_weights('/kaggle/input/tf-efficientnet-imagenet-weights/efficientnet-b0_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5')\n    \n    # RESHAPE INPUT 128x256x8 => 512x512x3 MONOTONE IMAGE\n    # KAGGLE SPECTROGRAMS\n    x1 = [inp[:,:,:,i:i+1] for i in range(4)]\n    x1 = tf.keras.layers.Concatenate(axis=1)(x1)\n    # EEG SPECTROGRAMS\n    x2 = [inp[:, :, :,i+4:i+5] for i in range(4)]\n    x2 = tf.keras.layers.Concatenate(axis=1)(x2)\n    # MAKE 512X512X3\n    if USE_KAGGLE_SPECTROGRAMS & USE_EEG_SPECTROGRAMS:\n        x = tf.keras.layers.Concatenate(axis=2)([x1,x2])\n    elif USE_EEG_SPECTROGRAMS: x = x2\n    else: x = x1\n    x = tf.keras.layers.Concatenate(axis=3)([x,x,x])\n    \n    # OUTPUT\n    x = base_model(x)\n    x = tf.keras.layers.GlobalAveragePooling2D()(x)\n    x = tf.keras.layers.Dense(6, activation='softmax', dtype='float32')(x)\n        \n    # COMPILE MODEL\n    model = tf.keras.Model(inputs=inp, outputs=x)\n    opt = tf.keras.optimizers.Adam(learning_rate = 1e-3)\n    loss = tf.keras.losses.KLDivergence()\n\n    model.compile(loss=loss, optimizer = opt) \n        \n    return model","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:56:54.837736Z","iopub.execute_input":"2024-02-16T10:56:54.838140Z","iopub.status.idle":"2024-02-16T10:56:54.849097Z","shell.execute_reply.started":"2024-02-16T10:56:54.838109Z","shell.execute_reply":"2024-02-16T10:56:54.848055Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import KFold, GroupKFold\nimport tensorflow.keras.backend as K, gc\n\nall_oof  = []\nall_true = []\n\ngkf = GroupKFold(n_splits=5)\nfor i, (train_index, valid_index) in enumerate(gkf.split(train, train.target, train.patient_id)):  \n    \n    print('#'*25)\n    print(f'### Fold {i+1}')\n    \n    train_gen = DataGenerator(train.iloc[train_index], shuffle=True, batch_size=32, augment=False)\n    valid_gen = DataGenerator(train.iloc[valid_index], shuffle=False, batch_size=64, mode='valid')\n    \n    print(f'### train size {len(train_index)}, valid size {len(valid_index)}')\n    print('#'*25)\n    \n    K.clear_session()\n    with strategy.scope():\n        model = build_model()\n    if LOAD_MODELS_FROM is None:\n        model.fit(train_gen, verbose=1,\n              validation_data = valid_gen,\n              epochs=EPOCHS, callbacks = [LR])\n        model.save_weights(f'EffNet_v{VER}_f{i}.h5')\n    else:\n        model.load_weights(f'{LOAD_MODELS_FROM}EffNet_v{VER}_f{i}.h5')\n        \n    oof = model.predict(valid_gen, verbose=1)\n    all_oof.append(oof)\n    all_true.append(train.iloc[valid_index][TARGETS].values)\n    \n    del model, oof\n    gc.collect()\n    \nall_oof  = np.concatenate(all_oof)\nall_true = np.concatenate(all_true)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T10:57:00.344685Z","iopub.execute_input":"2024-02-16T10:57:00.345372Z","iopub.status.idle":"2024-02-16T10:59:54.004363Z","shell.execute_reply.started":"2024-02-16T10:57:00.345336Z","shell.execute_reply":"2024-02-16T10:59:54.003558Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import sys\nsys.path.append('/kaggle/input/kaggle-kl-div')\nfrom kaggle_kl_div import score\n\noof = pd.DataFrame(all_oof.copy())\noof['id'] = np.arange(len(oof))\n\ntrue = pd.DataFrame(all_true.copy())\ntrue['id'] = np.arange(len(true))\n\ncv = score(solution=true, submission=oof, row_id_column_name='id')\nprint('CV Score KL-Div for EfficientNetB2 =', cv)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:00:09.128702Z","iopub.execute_input":"2024-02-16T11:00:09.131792Z","iopub.status.idle":"2024-02-16T11:00:09.211484Z","shell.execute_reply.started":"2024-02-16T11:00:09.131740Z","shell.execute_reply":"2024-02-16T11:00:09.210545Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del all_eegs, spectrograms; gc.collect()\ntest = pd.read_csv('/kaggle/input/hms-harmful-brain-activity-classification/test.csv')\nprint('Test shape',test.shape)\ntest.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:00:12.424780Z","iopub.execute_input":"2024-02-16T11:00:12.425436Z","iopub.status.idle":"2024-02-16T11:00:12.815878Z","shell.execute_reply.started":"2024-02-16T11:00:12.425406Z","shell.execute_reply":"2024-02-16T11:00:12.814840Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# READ ALL SPECTROGRAMS\nPATH2 = '/kaggle/input/hms-harmful-brain-activity-classification/test_spectrograms/'\nfiles2 = os.listdir(PATH2)\nprint(f'There are {len(files2)} test spectrogram parquets')\n    \nspectrograms2 = {}\nfor i,f in enumerate(files2):\n    if i%100==0: print(i,', ',end='')\n    tmp = pd.read_parquet(f'{PATH2}{f}')\n    name = int(f.split('.')[0])\n    spectrograms2[name] = tmp.iloc[:,1:].values\n    \n# RENAME FOR DATALOADER\ntest = test.rename({'spectrogram_id':'spec_id'},axis=1)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:00:21.324772Z","iopub.execute_input":"2024-02-16T11:00:21.325847Z","iopub.status.idle":"2024-02-16T11:00:21.699000Z","shell.execute_reply.started":"2024-02-16T11:00:21.325805Z","shell.execute_reply":"2024-02-16T11:00:21.698020Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pywt, librosa\n\nUSE_WAVELET = None \n\nNAMES = ['LL','LP','RP','RR']\n\nFEATS = [['Fp1','F7','T3','T5','O1'],\n         ['Fp1','F3','C3','P3','O1'],\n         ['Fp2','F8','T4','T6','O2'],\n         ['Fp2','F4','C4','P4','O2']]\n\n# DENOISE FUNCTION\ndef maddest(d, axis=None):\n    return np.mean(np.absolute(d - np.mean(d, axis)), axis)\n\ndef denoise(x, wavelet='haar', level=1):    \n    coeff = pywt.wavedec(x, wavelet, mode=\"per\")\n    sigma = (1/0.6745) * maddest(coeff[-level])\n\n    uthresh = sigma * np.sqrt(2*np.log(len(x)))\n    coeff[1:] = (pywt.threshold(i, value=uthresh, mode='hard') for i in coeff[1:])\n\n    ret=pywt.waverec(coeff, wavelet, mode='per')\n    \n    return ret\n\ndef spectrogram_from_eeg(parquet_path, display=False):\n    \n    # LOAD MIDDLE 50 SECONDS OF EEG SERIES\n    eeg = pd.read_parquet(parquet_path)\n    middle = (len(eeg)-10_000)//2\n    eeg = eeg.iloc[middle:middle+10_000]\n    \n    # VARIABLE TO HOLD SPECTROGRAM\n    img = np.zeros((128,256,4),dtype='float32')\n    \n    if display: plt.figure(figsize=(10,7))\n    signals = []\n    for k in range(4):\n        COLS = FEATS[k]\n        \n        for kk in range(4):\n        \n            # COMPUTE PAIR DIFFERENCES\n            x = eeg[COLS[kk]].values - eeg[COLS[kk+1]].values\n\n            # FILL NANS\n            m = np.nanmean(x)\n            if np.isnan(x).mean()<1: x = np.nan_to_num(x,nan=m)\n            else: x[:] = 0\n\n            # DENOISE\n            if USE_WAVELET:\n                x = denoise(x, wavelet=USE_WAVELET)\n            signals.append(x)\n\n            # RAW SPECTROGRAM\n            mel_spec = librosa.feature.melspectrogram(y=x, sr=200, hop_length=len(x)//256, \n                  n_fft=1024, n_mels=128, fmin=0, fmax=20, win_length=128)\n\n            # LOG TRANSFORM\n            width = (mel_spec.shape[1]//32)*32\n            mel_spec_db = librosa.power_to_db(mel_spec, ref=np.max).astype(np.float32)[:,:width]\n\n            # STANDARDIZE TO -1 TO 1\n            mel_spec_db = (mel_spec_db+40)/40 \n            img[:,:,k] += mel_spec_db\n                \n        # AVERAGE THE 4 MONTAGE DIFFERENCES\n        img[:,:,k] /= 4.0\n        \n        if display:\n            plt.subplot(2,2,k+1)\n            plt.imshow(img[:,:,k],aspect='auto',origin='lower')\n            plt.title(f'EEG {eeg_id} - Spectrogram {NAMES[k]}')\n            \n    if display: \n        plt.show()\n        plt.figure(figsize=(10,5))\n        offset = 0\n        for k in range(4):\n            if k>0: offset -= signals[3-k].min()\n            plt.plot(range(10_000),signals[k]+offset,label=NAMES[3-k])\n            offset += signals[3-k].max()\n        plt.legend()\n        plt.title(f'EEG {eeg_id} Signals')\n        plt.show()\n        print(); print('#'*25); print()\n        \n    return img","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:00:56.307432Z","iopub.execute_input":"2024-02-16T11:00:56.308319Z","iopub.status.idle":"2024-02-16T11:00:56.334705Z","shell.execute_reply.started":"2024-02-16T11:00:56.308273Z","shell.execute_reply":"2024-02-16T11:00:56.333739Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# READ ALL EEG SPECTROGRAMS\nPATH2 = '/kaggle/input/hms-harmful-brain-activity-classification/test_eegs/'\nDISPLAY = 1\nEEG_IDS2 = test.eeg_id.unique()\nall_eegs2 = {}\n\nprint('Converting Test EEG to Spectrograms...'); print()\nfor i,eeg_id in enumerate(EEG_IDS2):\n        \n    # CREATE SPECTROGRAM FROM EEG PARQUET\n    img = spectrogram_from_eeg(f'{PATH2}{eeg_id}.parquet', i<DISPLAY)\n    all_eegs2[eeg_id] = img","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:01:06.274765Z","iopub.execute_input":"2024-02-16T11:01:06.275561Z","iopub.status.idle":"2024-02-16T11:01:17.458371Z","shell.execute_reply.started":"2024-02-16T11:01:06.275522Z","shell.execute_reply":"2024-02-16T11:01:17.457319Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# INFER EFFICIENTNET ON TEST\npreds = []\nmodel = build_model()\ntest_gen = DataGenerator(test, shuffle=False, batch_size=64, mode='test',\n                         specs = spectrograms2, eeg_specs = all_eegs2)\n\nfor i in range(5):\n    print(f'Fold {i+1}')\n    if LOAD_MODELS_FROM:\n        model.load_weights(f'{LOAD_MODELS_FROM}EffNet_v{VER}_f{i}.h5')\n    else:\n        model.load_weights(f'EffNet_v{VER}_f{i}.h5')\n    pred = model.predict(test_gen, verbose=1)\n    preds.append(pred)\npred = np.mean(preds,axis=0)\nprint()\nprint('Test preds shape',pred.shape)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:02:24.858912Z","iopub.execute_input":"2024-02-16T11:02:24.859640Z","iopub.status.idle":"2024-02-16T11:02:32.114331Z","shell.execute_reply.started":"2024-02-16T11:02:24.859606Z","shell.execute_reply":"2024-02-16T11:02:32.113313Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub1 = pd.DataFrame({'eeg_id':test.eeg_id.values})\nsub1[TARGETS] = pred\nprint('Submission shape',sub1.shape)\nsub1.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:02:34.662404Z","iopub.execute_input":"2024-02-16T11:02:34.663322Z","iopub.status.idle":"2024-02-16T11:02:34.680207Z","shell.execute_reply.started":"2024-02-16T11:02:34.663288Z","shell.execute_reply":"2024-02-16T11:02:34.679071Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds_combine = pred\npreds_combine","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:02:36.074697Z","iopub.execute_input":"2024-02-16T11:02:36.075063Z","iopub.status.idle":"2024-02-16T11:02:36.081484Z","shell.execute_reply.started":"2024-02-16T11:02:36.075035Z","shell.execute_reply":"2024-02-16T11:02:36.080527Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# SANITY CHECK TO CONFIRM PREDICTIONS SUM TO ONE\nsub1.iloc[:,-6:].sum(axis=1)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:02:37.268807Z","iopub.execute_input":"2024-02-16T11:02:37.269678Z","iopub.status.idle":"2024-02-16T11:02:37.278096Z","shell.execute_reply.started":"2024-02-16T11:02:37.269645Z","shell.execute_reply":"2024-02-16T11:02:37.277234Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model 2","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport torch \nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torchvision.transforms as transforms\nimport random\n\nimport warnings\nwarnings.filterwarnings('ignore')","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:04:50.176233Z","iopub.execute_input":"2024-02-16T11:04:50.177316Z","iopub.status.idle":"2024-02-16T11:04:54.398017Z","shell.execute_reply.started":"2024-02-16T11:04:50.177254Z","shell.execute_reply":"2024-02-16T11:04:54.397007Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Config:\n    seed=2024\n    image_transform=transforms.Resize((512, 512))\n    num_folds=5","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:04:54.402908Z","iopub.execute_input":"2024-02-16T11:04:54.403587Z","iopub.status.idle":"2024-02-16T11:04:54.408227Z","shell.execute_reply.started":"2024-02-16T11:04:54.403558Z","shell.execute_reply":"2024-02-16T11:04:54.407314Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"models=[]\nfor i in range(Config.num_folds):\n    model = torch.load(f'/kaggle/input/hms-baseline-resnet34d-512-512-training-5-folds/HMS_resnet_fold{i}.pth')\n    models.append(model)\nmodel = torch.load(\"/kaggle/input/hms-baseline-resnet34d-512-512-training/HMS_resnet.pth\")\nmodels.append(model)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:04:59.805208Z","iopub.execute_input":"2024-02-16T11:04:59.806433Z","iopub.status.idle":"2024-02-16T11:05:06.275223Z","shell.execute_reply.started":"2024-02-16T11:04:59.806387Z","shell.execute_reply":"2024-02-16T11:05:06.274348Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def seed_everything(seed):\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = True\n    torch.manual_seed(seed)\n    np.random.seed(seed)\n    random.seed(seed)\nseed_everything(Config.seed)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:05:27.832950Z","iopub.execute_input":"2024-02-16T11:05:27.833822Z","iopub.status.idle":"2024-02-16T11:05:27.845077Z","shell.execute_reply.started":"2024-02-16T11:05:27.833776Z","shell.execute_reply":"2024-02-16T11:05:27.844219Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/test.csv\")\nsubmission = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/sample_submission.csv\")\nsubmission = submission.merge(test_df,on='eeg_id',how='left')\nsubmission['path'] = submission['spectrogram_id'].apply(lambda x: \"/kaggle/input/hms-harmful-brain-activity-classification/test_spectrograms/\"+str(x)+\".parquet\" )\nsubmission.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:05:48.131298Z","iopub.execute_input":"2024-02-16T11:05:48.132162Z","iopub.status.idle":"2024-02-16T11:05:48.171362Z","shell.execute_reply.started":"2024-02-16T11:05:48.132131Z","shell.execute_reply":"2024-02-16T11:05:48.170466Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"paths=submission['path'].values\ntest_preds=[]\nfor path in paths:\n    eps=1e-6\n    data=pd.read_parquet(path)\n\n    data = data.fillna(-1).values[:,1:].T\n\n    data = data[:,0:300] #(400,300)\n    data = np.clip(data,np.exp(-6),np.exp(10))\n    data = np.log(data)\n\n    data_mean=data.mean(axis=(0,1))\n    data_std=data.std(axis=(0,1))\n    data=(data-data_mean)/(data_std+eps)\n    data_tensor = torch.unsqueeze(torch.Tensor(data), dim=0)\n    data=Config.image_transform(data_tensor)\n    test_pred=[]\n    for model in models:\n        model.eval()\n        with torch.no_grad():\n            pred=F.softmax(model(data.unsqueeze(0)))[0]\n            pred=pred.detach().cpu().numpy()\n        test_pred.append(pred)\n    test_pred=np.array(test_pred).mean(axis=0)\n    test_preds.append(test_pred)\ntest_preds=np.array(test_preds)\ntest_preds","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:06:19.386348Z","iopub.execute_input":"2024-02-16T11:06:19.386765Z","iopub.status.idle":"2024-02-16T11:06:21.311488Z","shell.execute_reply.started":"2024-02-16T11:06:19.386732Z","shell.execute_reply":"2024-02-16T11:06:21.310481Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub2   = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/sample_submission.csv\")\nlabels = ['seizure','lpd','gpd','lrda','grda','other']\nfor i in range(len(labels)):\n    sub2[f'{labels[i]}_vote']=test_preds[:,i]\nsub2.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:06:33.200189Z","iopub.execute_input":"2024-02-16T11:06:33.200933Z","iopub.status.idle":"2024-02-16T11:06:33.219578Z","shell.execute_reply.started":"2024-02-16T11:06:33.200897Z","shell.execute_reply":"2024-02-16T11:06:33.218730Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model 3","metadata":{}},{"cell_type":"code","source":"# Importing essential libraries\nimport gc\nimport os\nimport random\nimport warnings\nimport numpy as np\nimport pandas as pd\nfrom IPython.display import display\n\n# PyTorch for deep learning\nimport timm\nimport torch\nimport torch.nn as nn  \nimport torch.optim as optim\nimport torch.nn.functional as F\n\n# torchvision for image processing and augmentation\nimport torchvision.transforms as transforms\n\n# Reclaim memory no longer in use.\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:07:21.746092Z","iopub.execute_input":"2024-02-16T11:07:21.746486Z","iopub.status.idle":"2024-02-16T11:07:22.342468Z","shell.execute_reply.started":"2024-02-16T11:07:21.746456Z","shell.execute_reply":"2024-02-16T11:07:22.341563Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Config:\n    seed=42\n    image_transform=transforms.Resize((512, 512))\n    num_folds=5\n    \n# Set the seed for reproducibility across multiple libraries\ndef set_seed(seed):\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = True\n    torch.manual_seed(seed)\n    np.random.seed(seed)\n    random.seed(seed)\n    \nset_seed(Config.seed)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:07:23.547365Z","iopub.execute_input":"2024-02-16T11:07:23.547713Z","iopub.status.idle":"2024-02-16T11:07:23.555190Z","shell.execute_reply.started":"2024-02-16T11:07:23.547689Z","shell.execute_reply":"2024-02-16T11:07:23.554111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load and store the trained models for each fold into a list\nmodels = []\n\n# Load ResNet34d\nfor i in range(Config.num_folds):\n    # Create the same model architecture as during training\n    model_resnet = timm.create_model('resnet34d', pretrained = False, num_classes = 6, in_chans=1)\n    \n    # Load the trained weights from the corresponding file\n    model_resnet.load_state_dict(torch.load(f'/kaggle/input/resnet34d/hms-train-resnet34d/resnet34d_fold{i}.pth', map_location=torch.device('cpu')))\n    \n    # Append the loaded model to the models list\n    models.append(model_resnet)\n\n# Reclaim memory no longer in use.\ngc.collect()\n\n# Load EfficientNetB0\nfor j in range(Config.num_folds):\n    # Create the same model architecture as during training\n    model_effnet_b0 = timm.create_model('efficientnet_b0', pretrained=False, num_classes=6, in_chans=1)\n    \n    # Load the trained weights from the corresponding file\n    model_effnet_b0.load_state_dict(torch.load(f'/kaggle/input/efficientnetb0/hms-train-efficientnetb0/efficientnet_b0_fold{j}.pth', map_location=torch.device('cpu')))\n    \n    # Append the loaded model to the models list\n    models.append(model_effnet_b0)\n    \n# Reclaim memory no longer in use.\ngc.collect()\n    \n# Load EfficientNetB1\nfor k in range(Config.num_folds):\n    # Create the same model architecture as during training\n    model_effnet_b1 = timm.create_model('efficientnet_b1', pretrained=False, num_classes=6, in_chans=1)\n    \n    # Load the trained weights from the corresponding file\n    model_effnet_b1.load_state_dict(torch.load(f'/kaggle/input/efficientnetb1/hms-train-efficientnetb1/efficientnet_b1_fold{k}.pth', map_location=torch.device('cpu')))\n    \n    # Append the loaded model to the models list\n    models.append(model_effnet_b1)\n\n# Reclaim memory no longer in use.\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:08:09.914562Z","iopub.execute_input":"2024-02-16T11:08:09.915519Z","iopub.status.idle":"2024-02-16T11:08:21.380824Z","shell.execute_reply.started":"2024-02-16T11:08:09.915474Z","shell.execute_reply":"2024-02-16T11:08:21.379866Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load test data and sample submission dataframe\ntest_df = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/test.csv\")\nsubmission = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/sample_submission.csv\")\n\n# Merge the submission dataframe with the test data on EEG IDs\nsubmission = submission.merge(test_df, on='eeg_id', how='left')\n\n# Generate file paths for each spectrogram based on the EEG data in the submission dataframe\nsubmission['path'] = submission['spectrogram_id'].apply(lambda x: f\"/kaggle/input/hms-harmful-brain-activity-classification/test_spectrograms/{x}.parquet\")\n\n# Display the first few rows of the submission dataframe\ndisplay(submission.head())\n\n# Reclaim memory no longer in use\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:08:32.815103Z","iopub.execute_input":"2024-02-16T11:08:32.816010Z","iopub.status.idle":"2024-02-16T11:08:33.374135Z","shell.execute_reply.started":"2024-02-16T11:08:32.815972Z","shell.execute_reply":"2024-02-16T11:08:33.373176Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define the weights for each model\nweight_resnet34d = 0.25\nweight_effnetb0  = 0.42\nweight_effnetb1  = 0.33\n\n# Get file paths for test spectrograms\npaths = submission['path'].values\ntest_predss = []\n\n# Generate predictions for each spectrogram using all models\nfor path in paths:\n    eps = 1e-6\n    # Read and preprocess spectrogram data\n    data = pd.read_parquet(path)\n    data = data.fillna(-1).values[:, 1:].T\n    data = np.clip(data, np.exp(-6), np.exp(10))\n    data = np.log(data)\n    \n    # Normalize the data\n    data_mean = data.mean(axis=(0, 1))\n    data_std = data.std(axis=(0, 1))\n    data = (data - data_mean) / (data_std + eps)\n    data_tensor = torch.unsqueeze(torch.Tensor(data), dim=0)\n    data = Config.image_transform(data_tensor)\n\n    test_pred = []\n    \n    # Generate predictions using all models\n    for model in models:\n        model.eval()\n        with torch.no_grad():\n            pred = F.softmax(model(data.unsqueeze(0)))[0]\n            pred = pred.detach().cpu().numpy()\n        test_pred.append(pred)\n        \n    # Combine predictions from all models using weighted voting\n    weighted_pred = weight_resnet34d * np.mean(test_pred[:Config.num_folds], axis=0) + \\\n                    weight_effnetb0  * np.mean(test_pred[Config.num_folds: 2*Config.num_folds], axis=0) + \\\n                    weight_effnetb1  * np.mean(test_pred[2*Config.num_folds:], axis=0)\n    \n    test_predss.append(weighted_pred)\n\n# Convert the list of predictions to a NumPy array for further processing\ntest_predss = np.array(test_predss)\n\n# Reclaim memory no longer in use\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:09:21.449868Z","iopub.execute_input":"2024-02-16T11:09:21.450578Z","iopub.status.idle":"2024-02-16T11:09:25.094241Z","shell.execute_reply.started":"2024-02-16T11:09:21.450527Z","shell.execute_reply":"2024-02-16T11:09:25.093297Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_predss","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:09:28.755847Z","iopub.execute_input":"2024-02-16T11:09:28.756253Z","iopub.status.idle":"2024-02-16T11:09:28.763397Z","shell.execute_reply.started":"2024-02-16T11:09:28.756221Z","shell.execute_reply":"2024-02-16T11:09:28.762337Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submission","metadata":{}},{"cell_type":"code","source":"preds_combine","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:09:31.494402Z","iopub.execute_input":"2024-02-16T11:09:31.495093Z","iopub.status.idle":"2024-02-16T11:09:31.501556Z","shell.execute_reply.started":"2024-02-16T11:09:31.495060Z","shell.execute_reply":"2024-02-16T11:09:31.500543Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/sample_submission.csv\")\nlabels     = ['seizure','lpd','gpd','lrda','grda','other']\nfor i in range(len(labels)):\n    submission[f'{labels[i]}_vote'] =( test_preds[:,i]*0.18 + preds_combine[:, i]*0.35 + test_predss[:, i]*0.47)\nsubmission.to_csv(\"submission.csv\",index=None)\ndisplay(submission.head())","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:10:11.826477Z","iopub.execute_input":"2024-02-16T11:10:11.826829Z","iopub.status.idle":"2024-02-16T11:10:11.849916Z","shell.execute_reply.started":"2024-02-16T11:10:11.826806Z","shell.execute_reply":"2024-02-16T11:10:11.848890Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.iloc[:,-6:].sum(axis=1)","metadata":{"execution":{"iopub.status.busy":"2024-02-16T11:10:12.931765Z","iopub.execute_input":"2024-02-16T11:10:12.932138Z","iopub.status.idle":"2024-02-16T11:10:12.941218Z","shell.execute_reply.started":"2024-02-16T11:10:12.932110Z","shell.execute_reply":"2024-02-16T11:10:12.940124Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}