{"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":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":"# Notes","metadata":{}},{"cell_type":"code","source":"\"\"\"\nModel 1 is from our good friend Chris Deotte:\nhttps://www.kaggle.com/code/cdeotte/efficientnetb0-starter-lb-0-43\n\nModel 2 is the work of yunsuxiaozi\nhttps://www.kaggle.com/code/yunsuxiaozi/hms-baseline-resnet34d-512-512-inference-6-models\n\nBoth are fantastic notebooks that absolutely deserve credit and your \ntime! \n\nThe strategy behind this notebook is a simple blended average of the \nbaseline resnet34d and the efficientnetB0. There is plenty of room for\ngrowth in both of these models and a number of key insights I am sure \nwe have yet to find! The purpose of this notebook is to highlight just\nhow much diverse models can impact LB in this competition and to serve \nas ahow to for ensembling in this competition as its not as simple as \na basic tabular comp.\n\nModel 1: 0.43\nModel 2: 0.45\n\nEnsemble: 0.39\n\"\"\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-30T12:09:09.399136Z","iopub.execute_input":"2024-12-30T12:09:09.399441Z","iopub.status.idle":"2024-12-30T12:09:09.412941Z","shell.execute_reply.started":"2024-12-30T12:09:09.399403Z","shell.execute_reply":"2024-12-30T12:09:09.411993Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Model 1","metadata":{}},{"cell_type":"code","source":"import os, gc\nos.environ[\"CUDA_VISIBLE_DEVICES\"]=\"0,1\"\nimport tensorflow as tf\nimport pandas as pd, numpy as np\nimport matplotlib.pyplot as plt\nprint('TensorFlow version =',tf.__version__)\n\n# USE MULTIPLE GPUS\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":"2024-12-30T12:09:09.415045Z","iopub.execute_input":"2024-12-30T12:09:09.415304Z","iopub.status.idle":"2024-12-30T12:09:22.413716Z","shell.execute_reply.started":"2024-12-30T12:09:09.415284Z","shell.execute_reply":"2024-12-30T12:09:22.412827Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:09:22.415170Z","iopub.execute_input":"2024-12-30T12:09:22.415832Z","iopub.status.idle":"2024-12-30T12:09:22.421080Z","shell.execute_reply.started":"2024-12-30T12:09:22.415796Z","shell.execute_reply":"2024-12-30T12:09:22.420263Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:09:22.422029Z","iopub.execute_input":"2024-12-30T12:09:22.422291Z","iopub.status.idle":"2024-12-30T12:09:22.671985Z","shell.execute_reply.started":"2024-12-30T12:09:22.422271Z","shell.execute_reply":"2024-12-30T12:09:22.671137Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:09:22.673215Z","iopub.execute_input":"2024-12-30T12:09:22.673550Z","iopub.status.idle":"2024-12-30T12:09:22.755396Z","shell.execute_reply.started":"2024-12-30T12:09:22.673519Z","shell.execute_reply":"2024-12-30T12:09:22.754569Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:09:22.757598Z","iopub.execute_input":"2024-12-30T12:09:22.757847Z","iopub.status.idle":"2024-12-30T12:10:19.279168Z","shell.execute_reply.started":"2024-12-30T12:09:22.757826Z","shell.execute_reply":"2024-12-30T12:10:19.278245Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:10:19.280376Z","iopub.execute_input":"2024-12-30T12:10:19.281015Z","iopub.status.idle":"2024-12-30T12:11:38.861560Z","shell.execute_reply.started":"2024-12-30T12:10:19.280981Z","shell.execute_reply":"2024-12-30T12:11:38.860559Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:11:38.862697Z","iopub.execute_input":"2024-12-30T12:11:38.862991Z","iopub.status.idle":"2024-12-30T12:11:40.846124Z","shell.execute_reply.started":"2024-12-30T12:11:38.862968Z","shell.execute_reply":"2024-12-30T12:11:40.845420Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"gen = DataGenerator(train, batch_size=32, shuffle=False)\nROWS=2; COLS=3; BATCHES=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":"2024-12-30T12:11:40.847418Z","iopub.execute_input":"2024-12-30T12:11:40.848034Z","iopub.status.idle":"2024-12-30T12:11:43.123687Z","shell.execute_reply.started":"2024-12-30T12:11:40.848002Z","shell.execute_reply":"2024-12-30T12:11:43.122793Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:11:43.124816Z","iopub.execute_input":"2024-12-30T12:11:43.125132Z","iopub.status.idle":"2024-12-30T12:11:43.358815Z","shell.execute_reply.started":"2024-12-30T12:11:43.125086Z","shell.execute_reply":"2024-12-30T12:11:43.357985Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:11:43.360019Z","iopub.execute_input":"2024-12-30T12:11:43.360349Z","iopub.status.idle":"2024-12-30T12:11:43.606039Z","shell.execute_reply.started":"2024-12-30T12:11:43.360327Z","shell.execute_reply":"2024-12-30T12:11:43.605152Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:11:43.607184Z","iopub.execute_input":"2024-12-30T12:11:43.607452Z","iopub.status.idle":"2024-12-30T12:11:53.750715Z","shell.execute_reply.started":"2024-12-30T12:11:43.607429Z","shell.execute_reply":"2024-12-30T12:11:53.749528Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:11:53.752440Z","iopub.execute_input":"2024-12-30T12:11:53.752808Z","iopub.status.idle":"2024-12-30T12:11:53.774014Z","shell.execute_reply.started":"2024-12-30T12:11:53.752775Z","shell.execute_reply":"2024-12-30T12:11:53.773081Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:11:53.775272Z","iopub.execute_input":"2024-12-30T12:11:53.775582Z","iopub.status.idle":"2024-12-30T12:14:39.674225Z","shell.execute_reply.started":"2024-12-30T12:11:53.775553Z","shell.execute_reply":"2024-12-30T12:14:39.673422Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:14:39.675881Z","iopub.execute_input":"2024-12-30T12:14:39.676129Z","iopub.status.idle":"2024-12-30T12:14:39.757183Z","shell.execute_reply.started":"2024-12-30T12:14:39.676110Z","shell.execute_reply":"2024-12-30T12:14:39.754015Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:14:39.758604Z","iopub.execute_input":"2024-12-30T12:14:39.758980Z","iopub.status.idle":"2024-12-30T12:14:39.991044Z","shell.execute_reply.started":"2024-12-30T12:14:39.758907Z","shell.execute_reply":"2024-12-30T12:14:39.990155Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:14:39.992286Z","iopub.execute_input":"2024-12-30T12:14:39.992607Z","iopub.status.idle":"2024-12-30T12:14:40.280001Z","shell.execute_reply.started":"2024-12-30T12:14:39.992579Z","shell.execute_reply":"2024-12-30T12:14:40.279161Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:14:40.284920Z","iopub.execute_input":"2024-12-30T12:14:40.285290Z","iopub.status.idle":"2024-12-30T12:14:40.303619Z","shell.execute_reply.started":"2024-12-30T12:14:40.285256Z","shell.execute_reply":"2024-12-30T12:14:40.302739Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:14:40.304714Z","iopub.execute_input":"2024-12-30T12:14:40.305037Z","iopub.status.idle":"2024-12-30T12:14:49.849685Z","shell.execute_reply.started":"2024-12-30T12:14:40.305006Z","shell.execute_reply":"2024-12-30T12:14:49.848827Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:14:49.850983Z","iopub.execute_input":"2024-12-30T12:14:49.851950Z","iopub.status.idle":"2024-12-30T12:14:56.945486Z","shell.execute_reply.started":"2024-12-30T12:14:49.851916Z","shell.execute_reply":"2024-12-30T12:14:56.944612Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:14:56.946696Z","iopub.execute_input":"2024-12-30T12:14:56.947522Z","iopub.status.idle":"2024-12-30T12:14:56.960972Z","shell.execute_reply.started":"2024-12-30T12:14:56.947486Z","shell.execute_reply":"2024-12-30T12:14:56.959836Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds_combine = pred\npreds_combine","metadata":{"execution":{"iopub.status.busy":"2024-12-30T12:14:56.962319Z","iopub.execute_input":"2024-12-30T12:14:56.963079Z","iopub.status.idle":"2024-12-30T12:14:56.974998Z","shell.execute_reply.started":"2024-12-30T12:14:56.963048Z","shell.execute_reply":"2024-12-30T12:14:56.974130Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# SANITY CHECK TO CONFIRM PREDICTIONS SUM TO ONE\nsub1.iloc[:,-6:].sum(axis=1)","metadata":{"execution":{"iopub.status.busy":"2024-12-30T12:14:56.976130Z","iopub.execute_input":"2024-12-30T12:14:56.976448Z","iopub.status.idle":"2024-12-30T12:14:56.989616Z","shell.execute_reply.started":"2024-12-30T12:14:56.976419Z","shell.execute_reply":"2024-12-30T12:14:56.988771Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Model 2","metadata":{}},{"cell_type":"code","source":"#https://www.kaggle.com/code/ttahara/hms-hbac-resnet34d-baseline-training\n#https://www.kaggle.com/code/ttahara/hms-hbac-resnet34d-baseline-inference\n#necessary\nimport pandas as pd#导入csv文件的库\nimport numpy as np#进行矩阵运算的库\nimport torch #一个深度学习的库Pytorch\nimport torch.nn as nn#neural network,神经网络\nimport torch.nn.functional as F#神经网络函数库\nimport torchvision.transforms as transforms#Pytorch下面的图像处理库,用于对图像进行数据增强\n#设置随机种子\nimport random\nimport warnings#避免一些可以忽略的报错\nwarnings.filterwarnings('ignore')#filterwarnings()方法是用于设置警告过滤器的方法，它可以控制警告信息的输出方式和级别。","metadata":{"execution":{"iopub.status.busy":"2024-12-30T12:14:56.990563Z","iopub.execute_input":"2024-12-30T12:14:56.990792Z","iopub.status.idle":"2024-12-30T12:14:59.138700Z","shell.execute_reply.started":"2024-12-30T12:14:56.990772Z","shell.execute_reply":"2024-12-30T12:14:59.137989Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:14:59.139590Z","iopub.execute_input":"2024-12-30T12:14:59.140172Z","iopub.status.idle":"2024-12-30T12:14:59.144382Z","shell.execute_reply.started":"2024-12-30T12:14:59.140147Z","shell.execute_reply":"2024-12-30T12:14:59.143420Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:14:59.145369Z","iopub.execute_input":"2024-12-30T12:14:59.145609Z","iopub.status.idle":"2024-12-30T12:15:06.036558Z","shell.execute_reply.started":"2024-12-30T12:14:59.145584Z","shell.execute_reply":"2024-12-30T12:15:06.035111Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def seed_everything(seed):\n    torch.backends.cudnn.deterministic = True#将cuda加速的随机数生成器设为确定性模式\n    torch.backends.cudnn.benchmark = True#关闭CuDNN框架的自动寻找最优卷积算法的功能，以避免不同的算法对结果产生影响\n    torch.manual_seed(seed)#pytorch的随机种子\n    np.random.seed(seed)#numpy的随机种子\n    random.seed(seed)#python内置的随机种子\nseed_everything(Config.seed)","metadata":{"execution":{"iopub.status.busy":"2024-12-30T12:15:06.038257Z","iopub.execute_input":"2024-12-30T12:15:06.038683Z","iopub.status.idle":"2024-12-30T12:15:06.050634Z","shell.execute_reply.started":"2024-12-30T12:15:06.038645Z","shell.execute_reply":"2024-12-30T12:15:06.049648Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:15:06.052012Z","iopub.execute_input":"2024-12-30T12:15:06.052694Z","iopub.status.idle":"2024-12-30T12:15:06.100548Z","shell.execute_reply.started":"2024-12-30T12:15:06.052647Z","shell.execute_reply":"2024-12-30T12:15:06.099619Z"},"trusted":true},"outputs":[],"execution_count":null},{"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    #这里最小值是0,故用-1填充.第一列是时间列,故去掉 ,行是不同列,列是时间\n    data = data.fillna(-1).values[:,1:].T\n    #选取一段时间的数据进行训练\n    data=data[:,0:300]#(400,300)\n    data=np.clip(data,np.exp(-6),np.exp(10))#最大值为89209464.0\n    data= np.log(data)#对数变换\n    #对数据进行归一化\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":"2024-12-30T12:15:06.101664Z","iopub.execute_input":"2024-12-30T12:15:06.101952Z","iopub.status.idle":"2024-12-30T12:15:07.852253Z","shell.execute_reply.started":"2024-12-30T12:15:06.101929Z","shell.execute_reply":"2024-12-30T12:15:07.851113Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2024-12-30T12:15:07.853317Z","iopub.execute_input":"2024-12-30T12:15:07.853596Z","iopub.status.idle":"2024-12-30T12:15:07.869529Z","shell.execute_reply.started":"2024-12-30T12:15:07.853566Z","shell.execute_reply":"2024-12-30T12:15:07.868619Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Subission","metadata":{}},{"cell_type":"code","source":"preds_combine","metadata":{"execution":{"iopub.status.busy":"2024-12-30T12:15:07.871573Z","iopub.execute_input":"2024-12-30T12:15:07.871816Z","iopub.status.idle":"2024-12-30T12:15:07.877787Z","shell.execute_reply.started":"2024-12-30T12:15:07.871795Z","shell.execute_reply":"2024-12-30T12:15:07.876987Z"},"trusted":true},"outputs":[],"execution_count":null},{"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] + preds_combine[:, i])/2\nsubmission.to_csv(\"submission.csv\",index=None)\ndisplay(submission.head())","metadata":{"execution":{"iopub.status.busy":"2024-12-30T12:15:07.879591Z","iopub.execute_input":"2024-12-30T12:15:07.879833Z","iopub.status.idle":"2024-12-30T12:15:07.902783Z","shell.execute_reply.started":"2024-12-30T12:15:07.879812Z","shell.execute_reply":"2024-12-30T12:15:07.901940Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# SANITY CHECK TO CONFIRM PREDICTIONS SUM TO ONE\nsubmission.iloc[:,-6:].sum(axis=1)","metadata":{"execution":{"iopub.status.busy":"2024-12-30T12:15:07.904027Z","iopub.execute_input":"2024-12-30T12:15:07.904897Z","iopub.status.idle":"2024-12-30T12:15:07.911564Z","shell.execute_reply.started":"2024-12-30T12:15:07.904866Z","shell.execute_reply":"2024-12-30T12:15:07.910726Z"},"trusted":true},"outputs":[],"execution_count":null}]}