{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":41880,"databundleVersionId":5677426,"sourceType":"competition"},{"sourceId":121731966,"sourceType":"kernelVersion"}],"dockerImageVersionId":30408,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Copy from https://www.kaggle.com/code/mayukh18/pytorch-fog-end-to-end-baseline-lb-0-254\n![image.png](attachment:1297bb52-3816-4098-85ab-8f732651a64a.png)","metadata":{},"attachments":{"1297bb52-3816-4098-85ab-8f732651a64a.png":{"image/png":"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"}}},{"cell_type":"code","source":"import os                                                                      # 操作系統相關的功能，用於文件路徑等操作\nimport gc                                                                      # 垃圾回收模組，用於釋放不再需要的內存\nimport random                                                                  # 生成偽隨機數\nimport time                                                                    # 時間模組，用於計時等操作\nimport matplotlib.pyplot as plt\n\nimport json                                                                    # 處理 JSON 格式數據的模組\nfrom tqdm import tqdm                                                          # 進度條模組，用於顯示任務的進度\nimport glob                                                                    # 用於查找文件路徑的模組\nimport numpy as np                                                             # 處理數組和矩陣的數學庫\nimport pandas as pd                                                            # 數據處理庫，用於處理數據表格\n \nimport torch                                                                   # PyTorch 深度學習庫\nimport torch.nn as nn                                                          # PyTorch 中的神經網絡模組\n\n\nfrom torch.utils.data import Dataset, DataLoader                               # PyTorch 中用於處理數據集和數據加載的模組\nfrom torchvision import transforms                                             # PyTorch 中的圖像處理模組\n\nfrom sklearn.model_selection import train_test_split, StratifiedGroupKFold     # sklearn 中的數據劃分模組\nfrom sklearn.metrics import accuracy_score, average_precision_score            # sklearn 中的評估指標模組\n\nimport warnings                                                                # 警告處理模組，用於控制警告的輸出\nwarnings.filterwarnings(action='ignore')                                       # 忽略警告","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-04-05T18:27:24.317774Z","iopub.execute_input":"2024-04-05T18:27:24.318757Z","iopub.status.idle":"2024-04-05T18:27:29.033674Z","shell.execute_reply.started":"2024-04-05T18:27:24.318703Z","shell.execute_reply":"2024-04-05T18:27:29.032135Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Config","metadata":{}},{"cell_type":"code","source":"class Config:\n    train_dir1 = \"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/train/defog\"        #訓練的 dataset_1 路徑：defog\n    train_dir2 = \"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/train/tdcsfog\"      #訓練的 dataset_2 路徑：tdcsfog\n\n    batch_size = 1024                                                        #batch size大小\n    window_size = 32                                                         #每次Input的總時序資料長度\n    window_future = 8                                                        #取目標時間點後多少為Input\n    window_past = window_size - window_future                                #取目標時間點前多少為Input\n    \n    wx = 8                                                                   #資料padding長度的參數\n    \n    optimizer_name = \"Adam\"                                                  #optimizer\n    loss_function = \"BCEWithLogitsLoss\"                                      #loss function\n    \n    model_dropout = 0.2                                                      #dropout機率\n    model_hidden = 512                                                       #每層linear layer的神經元數\n    model_nblocks = 3                                                        #model內的block數\n    \n    lr = 0.00015                                                             #learning rate\n    num_epochs = 10                                                          #訓練的epochs數\n    device = 'cuda:0' if torch.cuda.is_available() else 'cpu'                #裝置(GPU)設定\n    \n    feature_list = ['AccV', 'AccML', 'AccAP']\n    label_list = ['StartHesitation', 'Turn', 'Walking']\n    \n    \ncfg = Config()","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:27:29.035957Z","iopub.execute_input":"2024-04-05T18:27:29.036545Z","iopub.status.idle":"2024-04-05T18:27:29.049582Z","shell.execute_reply.started":"2024-04-05T18:27:29.036503Z","shell.execute_reply":"2024-04-05T18:27:29.047896Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cfg.device","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:27:29.051700Z","iopub.execute_input":"2024-04-05T18:27:29.052635Z","iopub.status.idle":"2024-04-05T18:27:29.071760Z","shell.execute_reply.started":"2024-04-05T18:27:29.052574Z","shell.execute_reply":"2024-04-05T18:27:29.070108Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Stratified Group K Fold\n\nIt's mentioned in the data that the subjects are different in the train and test set and even different between the public/private splits of the test data. So we need to use Stratified Group K Fold. But since the positive instances in the sequences are very scarce, we need to pick up the best fold which will give us the best balance of the positive/negative instances.","metadata":{}},{"cell_type":"markdown","source":"### tdcsfog preprocessing","metadata":{}},{"cell_type":"code","source":"# Analysis of positive instances in each fold of our CV folds\n\nn1_sum = []\nn2_sum = []\nn3_sum = []\ncount = []\n\n# Here I am using the metadata file available during training. Since the code will run again during submission, if \n# I used the usual file from the competition folder, it would have been updated with the test files too.\nmetadata = pd.read_csv(\"/kaggle/input/copy-train-metadata/tdcsfog_metadata.csv\")\n\nfor f in tqdm(metadata['Id']):\n    fpath = f\"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/train/tdcsfog/{f}.csv\"\n    df = pd.read_csv(fpath)\n    \n    n1_sum.append(np.sum(df['StartHesitation']))\n    n2_sum.append(np.sum(df['Turn']))\n    n3_sum.append(np.sum(df['Walking']))\n    count.append(len(df))\n    \nprint(f\"32 files have positive values in all 3 classes\")\n\nmetadata['n1_sum'] = n1_sum\nmetadata['n2_sum'] = n2_sum\nmetadata['n3_sum'] = n3_sum\nmetadata['count'] = count\n\nsgkf = StratifiedGroupKFold(n_splits=5, random_state=42, shuffle=True)\nfor i, (train_index, valid_index) in enumerate(sgkf.split(X=metadata['Id'], y=[1]*len(metadata), groups=metadata['Subject'])):\n    print(f\"Fold = {i}\")\n    train_ids = metadata.loc[train_index, 'Id']\n    valid_ids = metadata.loc[valid_index, 'Id']\n    \n    print(f\"Length of Train = {len(train_index)}, Length of Valid = {len(valid_index)}\")\n    n1_sum = metadata.loc[train_index, 'n1_sum'].sum()\n    n2_sum = metadata.loc[train_index, 'n2_sum'].sum()\n    n3_sum = metadata.loc[train_index, 'n3_sum'].sum()\n    print(f\"Train classes: {n1_sum:,}, {n2_sum:,}, {n3_sum:,}\")\n    \n    n1_sum = metadata.loc[valid_index, 'n1_sum'].sum()\n    n2_sum = metadata.loc[valid_index, 'n2_sum'].sum()\n    n3_sum = metadata.loc[valid_index, 'n3_sum'].sum()\n    print(f\"Valid classes: {n1_sum:,}, {n2_sum:,}, {n3_sum:,}\")\n    \n# FOLD 2 is the most well balanced\n# The actual train-test split (based on Fold 2)\n\nmetadata = pd.read_csv(\"/kaggle/input/copy-train-metadata/tdcsfog_metadata.csv\")\nsgkf = StratifiedGroupKFold(n_splits=5, random_state=42, shuffle=True)\nfor i, (train_index, valid_index) in enumerate(sgkf.split(X=metadata['Id'], y=[1]*len(metadata), groups=metadata['Subject'])):\n    if i != 2:\n        continue\n    print(f\"Fold = {i}\")\n    train_ids = metadata.loc[train_index, 'Id']\n    valid_ids = metadata.loc[valid_index, 'Id']\n    print(f\"Length of Train = {len(train_ids)}, Length of Valid = {len(valid_ids)}\")\n    \n    if i == 2:\n        break\n        \ntrain_fpaths_tdcs = [f\"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/train/tdcsfog/{_id}.csv\" for _id in train_ids]\nvalid_fpaths_tdcs = [f\"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/train/tdcsfog/{_id}.csv\" for _id in valid_ids]","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:27:29.076908Z","iopub.execute_input":"2024-04-05T18:27:29.077972Z","iopub.status.idle":"2024-04-05T18:27:50.817558Z","shell.execute_reply.started":"2024-04-05T18:27:29.077910Z","shell.execute_reply":"2024-04-05T18:27:50.816157Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### defog preprocessing","metadata":{}},{"cell_type":"code","source":"# Analysis of positive instances in each fold of our CV folds\n\nn1_sum = []\nn2_sum = []\nn3_sum = []\ncount = []\n\n# Here I am using the metadata file available during training. Since the code will run again during submission, if \n# I used the usual file from the competition folder, it would have been updated with the test files too.\nmetadata = pd.read_csv(\"/kaggle/input/copy-train-metadata/defog_metadata.csv\")\nmetadata['n1_sum'] = 0\nmetadata['n2_sum'] = 0\nmetadata['n3_sum'] = 0\nmetadata['count'] = 0\n\nfor f in tqdm(metadata['Id']):\n    fpath = f\"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/train/defog/{f}.csv\"\n    if os.path.exists(fpath) == False:\n        continue\n        \n    df = pd.read_csv(fpath)\n    metadata.loc[metadata['Id'] == f, 'n1_sum'] = np.sum(df['StartHesitation'])\n    metadata.loc[metadata['Id'] == f, 'n2_sum'] = np.sum(df['Turn'])\n    metadata.loc[metadata['Id'] == f, 'n3_sum'] = np.sum(df['Walking'])\n    metadata.loc[metadata['Id'] == f, 'count'] = len(df)\n    \nmetadata = metadata[metadata['count'] > 0].reset_index()\n\nsgkf = StratifiedGroupKFold(n_splits=5, random_state=42, shuffle=True)\nfor i, (train_index, valid_index) in enumerate(sgkf.split(X=metadata['Id'], y=[1]*len(metadata), groups=metadata['Subject'])):\n    print(f\"Fold = {i}\")\n    train_ids = metadata.loc[train_index, 'Id']\n    valid_ids = metadata.loc[valid_index, 'Id']\n    \n    print(f\"Length of Train = {len(train_index)}, Length of Valid = {len(valid_index)}\")\n    n1_sum = metadata.loc[train_index, 'n1_sum'].sum()\n    n2_sum = metadata.loc[train_index, 'n2_sum'].sum()\n    n3_sum = metadata.loc[train_index, 'n3_sum'].sum()\n    print(f\"Train classes: {n1_sum:,}, {n2_sum:,}, {n3_sum:,}\")\n    \n    n1_sum = metadata.loc[valid_index, 'n1_sum'].sum()\n    n2_sum = metadata.loc[valid_index, 'n2_sum'].sum()\n    n3_sum = metadata.loc[valid_index, 'n3_sum'].sum()\n    print(f\"Valid classes: {n1_sum:,}, {n2_sum:,}, {n3_sum:,}\")\n    \n# FOLD 2 is the most well balanced\n# The actual train-test split (based on Fold 2)\n\nsgkf = StratifiedGroupKFold(n_splits=5, random_state=42, shuffle=True)\nfor i, (train_index, valid_index) in enumerate(sgkf.split(X=metadata['Id'], y=[1]*len(metadata), groups=metadata['Subject'])):\n    if i != 1:\n        continue\n    print(f\"Fold = {i}\")\n    train_ids = metadata.loc[train_index, 'Id']\n    valid_ids = metadata.loc[valid_index, 'Id']\n    print(f\"Length of Train = {len(train_ids)}, Length of Valid = {len(valid_ids)}\")\n    \n    if i == 2:\n        break\n        \ntrain_fpaths_de = [f\"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/train/defog/{_id}.csv\" for _id in train_ids]\nvalid_fpaths_de = [f\"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/train/defog/{_id}.csv\" for _id in valid_ids]","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:27:50.819375Z","iopub.execute_input":"2024-04-05T18:27:50.820235Z","iopub.status.idle":"2024-04-05T18:28:18.798968Z","shell.execute_reply.started":"2024-04-05T18:27:50.820179Z","shell.execute_reply":"2024-04-05T18:28:18.797578Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_fpaths = [(f, 'de') for f in train_fpaths_de] + [(f, 'tdcs') for f in train_fpaths_tdcs]\nvalid_fpaths = [(f, 'de') for f in valid_fpaths_de] + [(f, 'tdcs') for f in valid_fpaths_tdcs]","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:28:18.800855Z","iopub.execute_input":"2024-04-05T18:28:18.801633Z","iopub.status.idle":"2024-04-05T18:28:18.809720Z","shell.execute_reply.started":"2024-04-05T18:28:18.801585Z","shell.execute_reply":"2024-04-05T18:28:18.808029Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# DataLoader\n\nWe use a window comprised of past and future time Acc readings to form our dataset for a particular time instance. In case some portion of the window data is not available, we pad them with zeros.","metadata":{}},{"cell_type":"code","source":"class FOGDataset(Dataset):\n    def __init__(self, fpaths, scale=9.806, split=\"train\"):\n        super(FOGDataset, self).__init__()\n        tm = time.time()\n        self.split = split\n        self.scale = scale\n        \n        self.fpaths = fpaths\n        self.dfs = [self.read(f[0], f[1]) for f in fpaths]\n        self.f_ids = [os.path.basename(f[0])[:-4] for f in self.fpaths]\n        \n        self.end_indices = []\n        self.shapes = []\n        _length = 0\n        for df in self.dfs:\n            self.shapes.append(df.shape[0])\n            _length += df.shape[0]\n            self.end_indices.append(_length)\n        \n        self.dfs = np.concatenate(self.dfs, axis=0).astype(np.float16)\n        self.length = self.dfs.shape[0]\n        \n        shape1 = self.dfs.shape[1]\n        \n        self.dfs = np.concatenate([np.zeros((cfg.wx*cfg.window_past, shape1)), self.dfs, np.zeros((cfg.wx*cfg.window_future, shape1))], axis=0)\n        print(f\"Dataset initialized in {time.time() - tm} secs!\")\n        gc.collect()\n        \n    def read(self, f, _type):\n        df = pd.read_csv(f)\n        if self.split == \"test\":\n            return np.array(df)\n        \n        if _type ==\"tdcs\":\n            df['Valid'] = 1\n            df['Task'] = 1\n            df['tdcs'] = 1\n        else:\n            df['tdcs'] = 0\n        \n        return np.array(df)\n            \n    def __getitem__(self, index):\n        if self.split == \"train\":\n            row_idx = random.randint(0, self.length-1) + cfg.wx*cfg.window_past\n        elif self.split == \"test\":\n            for i,e in enumerate(self.end_indices):\n                if index >= e:\n                    continue\n                df_idx = i\n                break\n\n            row_idx_true = self.shapes[df_idx] - (self.end_indices[df_idx] - index)\n            _id = self.f_ids[df_idx] + \"_\" + str(row_idx_true)\n            row_idx = index + cfg.wx*cfg.window_past\n        else:\n            row_idx = index + cfg.wx*cfg.window_past\n            \n        #scale = 9.806 if self.dfs[row_idx, -1] == 1 else 1.0\n        x = self.dfs[row_idx - cfg.wx*cfg.window_past : row_idx + cfg.wx*cfg.window_future, 1:4]\n        x = x[::cfg.wx, :][::-1, :]\n        x = torch.tensor(x.astype('float'))#/scale\n        \n        t = self.dfs[row_idx, -3]*self.dfs[row_idx, -2]\n        \n        if self.split == \"test\":\n            return _id, x, t\n        \n        y = self.dfs[row_idx, 4:7].astype('float')\n        y = torch.tensor(y)\n        \n        return x, y, t\n    \n    def __len__(self):\n        # return self.length\n        if self.split == \"train\":\n            return 5_000_000\n        return self.length","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:28:18.811526Z","iopub.execute_input":"2024-04-05T18:28:18.811912Z","iopub.status.idle":"2024-04-05T18:28:18.840110Z","shell.execute_reply.started":"2024-04-05T18:28:18.811874Z","shell.execute_reply":"2024-04-05T18:28:18.838598Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"gc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:28:18.841835Z","iopub.execute_input":"2024-04-05T18:28:18.842370Z","iopub.status.idle":"2024-04-05T18:28:19.010219Z","shell.execute_reply.started":"2024-04-05T18:28:18.842319Z","shell.execute_reply":"2024-04-05T18:28:19.008559Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model","metadata":{}},{"cell_type":"code","source":"def _block(in_features, out_features, drop_rate):  # define 一個 _block function，此 function 用來定義模型中單層的結構，傳入的參數有（in_features = 32, out_features = 32, drop_rate = 0.2）\n    return nn.Sequential(                          # 單層即包含：全連接層（Linear）、批量正規化（BatchhNorm1d）、activation function（ReLU）和 Dropout，並組合成一個 nn.Sequential 對象\n        nn.Linear(in_features, out_features),      # 全連接層的輸入特徵維度（in_features）= 32；輸出特徵維度（out_features）= 32\n        nn.BatchNorm1d(out_features),              # Batch Normalization（對每一層輸入正規化，以減緩梯度消失等問題）的輸入特徵維度 = 32\n        nn.ReLU(),                                 # activation function 使用 ReLU\n        nn.Dropout(drop_rate)                      # Dropout（在模型的訓練過程中隨機丟棄一些神經元的輸出，以防止過度擬合）的比例 = 0.2\n    )\n\nclass FOGModel(nn.Module):                         # 創建一個 class 名字叫 FOGModel（子類），並繼承 nn.Module（父類），但此時僅能使用父類的成員函數\n    def __init__(self, p=cfg.model_dropout, dim=cfg.model_hidden, nblocks=cfg.model_nblocks): # FOGModel 的 Ctor，括號內定義 default argument，p = 0.2；dim = 32；nblocks = 1\n        super(FOGModel, self).__init__()           # 執行 nn.Module 的 Ctor，以此來使用父類的成員變數\n        self.dropout = nn.Dropout(p)               # 宣告 dropout 變數，並用 nn.Dropout 初始化為 0.2\n        self.in_layer = nn.Linear(cfg.window_size*3, dim) # 宣告 in_layer（第一層隱藏層）變數，並用 nn.Linear 初始化輸入特徵維度（in_features）= 96；輸出特徵維度（out_features）= 32\n        self.blocks = nn.Sequential(*[_block(dim, dim, p) for _ in range(nblocks)]) # 宣告 blocks（中間數層）變數，_block 即為單層，而層數由 nblocks（目前為1）控制，傳進 _blocks 的參數為 dim = 32；p = 0.2\n        self.out_layer = nn.Linear(dim, 3)         # 宣告 out_layer（輸出層）變數，並用 nn.Linear 初始化輸入特徵維度（in_features）= 32；輸出特徵維度（out_features，代表三種FOG：猶豫、轉彎、行走）= 3\n        \n                                                                                             \n    def forward(self, x):                          # 在 PyTorch 中，任何繼承自 nn.Module 的類都可以定義自己的 forward 函數，以實現自定義的前向計算邏輯。x為輸入資料，一開始 x.Size([1024,32,3]) \n        x = x.view(-1, cfg.window_size*3)          # 接下來將 x.Size 轉成 ([1024,96])，-1是 view 的特殊參數，他可以自動利用已知之總元素數 = 1024*32*3 及 cfg.window_size*3 = 96 去計算出-1該維度之實際值 = 1024\n        x = self.in_layer(x)                       # 將輸入 x 通過模型的 in_layer 層，此時 x.Size 會變成 ([1024,32])\n        for block in self.blocks:\n            x = block(x)                           # x 之後會通過多層的 blocks，此時 x.Size 仍是 ([1024,32])\n        x = self.out_layer(x)                      # 最後 x 會通過輸出層，此時 x.Size 變成為 ([1024,3])\n        return x                                   # 返回 x 通過輸出層所得的結果","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:28:19.012085Z","iopub.execute_input":"2024-04-05T18:28:19.012537Z","iopub.status.idle":"2024-04-05T18:28:19.028943Z","shell.execute_reply.started":"2024-04-05T18:28:19.012480Z","shell.execute_reply":"2024-04-05T18:28:19.027636Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def count_parameters(model):                                             # define 一個 count_parameters function，此 function 可以吃下一整個 model\n    return sum(p.numel() for p in model.parameters() if p.requires_grad) # 計算模型的可訓練參數數量","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:28:19.034371Z","iopub.execute_input":"2024-04-05T18:28:19.035547Z","iopub.status.idle":"2024-04-05T18:28:19.046436Z","shell.execute_reply.started":"2024-04-05T18:28:19.035457Z","shell.execute_reply":"2024-04-05T18:28:19.044908Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training","metadata":{}},{"cell_type":"code","source":"from torch.cuda.amp import GradScaler\n\ndef train_one_epoch(model, loader, optimizer, criterion):\n    loss_sum = 0.\n    scaler = GradScaler()\n    \n    model.train()\n    for x,y,t in tqdm(loader):                               #從DataLoader中取得一個Batch size的資料\n        x = x.to(cfg.device).float()\n        y = y.to(cfg.device).float()\n        t = t.to(cfg.device).float()\n        \n        y_pred = model(x)                                    #將Input x丟入模型，得到y_pred\n        loss = criterion(y_pred, y)                          #計算預測結果y_pred與GT y的loss\n        loss = torch.mean(loss*t.unsqueeze(-1), dim=1)\n        \n        t_sum = torch.sum(t)\n        if t_sum > 0:\n            loss = torch.sum(loss)/t_sum\n        else:\n            loss = torch.sum(loss)*0.\n        \n        # loss.backward()\n        scaler.scale(loss).backward()                        #根據loss做反向傳播\n        # optimizer.step()\n        scaler.step(optimizer)                               #優化器優化模型參數\n        scaler.update()                                      \n        \n        optimizer.zero_grad()                                #優化器歸零\n        \n        loss_sum += loss.item()\n    \n    #print(f\"Train Loss: {(loss_sum/len(loader)):.04f}\")\n    train_loss = round(loss_sum/len(loader), 4)\n    print(\"Train Loss: {:.4f}\".format(train_loss))\n    return train_loss\n    \n\ndef validation_one_epoch(model, loader, criterion):\n    loss_sum = 0.\n    y_true_epoch = []\n    y_pred_epoch = []\n    t_valid_epoch = []\n    \n    model.eval()\n    for x,y,t in tqdm(loader):\n        x = x.to(cfg.device).float()\n        y = y.to(cfg.device).float()\n        t = t.to(cfg.device).float()\n        \n        with torch.no_grad():                                #沒有反向傳播\n            y_pred = model(x)\n            loss = criterion(y_pred, y)\n            loss = torch.mean(loss*t.unsqueeze(-1), dim=1)\n            \n            t_sum = torch.sum(t)\n            if t_sum > 0:\n                loss = torch.sum(loss)/t_sum\n            else:\n                loss = torch.sum(loss)*0.\n        \n        loss_sum += loss.item()\n        y_true_epoch.append(y.cpu().numpy())\n        y_pred_epoch.append(y_pred.cpu().numpy())\n        t_valid_epoch.append(t.cpu().numpy())\n        \n    y_true_epoch = np.concatenate(y_true_epoch, axis=0)\n    y_pred_epoch = np.concatenate(y_pred_epoch, axis=0)\n    \n    t_valid_epoch = np.concatenate(t_valid_epoch, axis=0)\n    y_true_epoch = y_true_epoch[t_valid_epoch > 0, :]\n    y_pred_epoch = y_pred_epoch[t_valid_epoch > 0, :]\n    \n    scores = [average_precision_score(y_true_epoch[:,i], y_pred_epoch[:,i]) for i in range(3)]\n    mean_score = np.mean(scores)\n    #print(f\"Validation Loss: {(loss_sum/len(loader)):.04f}, Validation Score: {mean_score:.03f}, ClassWise: {scores[0]:.03f},{scores[1]:.03f},{scores[2]:.03f}\")\n    \n    validation_loss = round(loss_sum/len(loader), 4)\n    print(f\"Validation Loss: {validation_loss:.4f}, Validation Score: {mean_score:.03f}, ClassWise: {scores[0]:.03f},{scores[1]:.03f},{scores[2]:.03f}\")\n    return validation_loss, mean_score","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:28:19.049016Z","iopub.execute_input":"2024-04-05T18:28:19.049422Z","iopub.status.idle":"2024-04-05T18:28:19.075163Z","shell.execute_reply.started":"2024-04-05T18:28:19.049374Z","shell.execute_reply":"2024-04-05T18:28:19.073806Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = FOGModel().to(cfg.device)\nprint(f\"Number of parameters in model - {count_parameters(model):,}\")\n\ntrain_dataset = FOGDataset(train_fpaths, split=\"train\")\nvalid_dataset = FOGDataset(valid_fpaths, split=\"valid\")\nprint(f\"lengths of datasets: train - {len(train_dataset)}, valid - {len(valid_dataset)}\")\n\ntrain_loader = DataLoader(train_dataset, batch_size=cfg.batch_size, num_workers=5, shuffle=True)\nvalid_loader = DataLoader(valid_dataset, batch_size=cfg.batch_size, num_workers=5)\n\noptimizer = getattr(torch.optim, cfg.optimizer_name)(model.parameters(), lr=cfg.lr)\ncriterion = getattr(torch.nn, cfg.loss_function)(reduction='none').to(cfg.device)\n# sched = torch.optim.lr_scheduler.StepLR(optimizer, step_size=1, gamma=0.85)\n\nmax_score = 0.0\ntrain_losses = []\nvalid_losses = []\nepoch_list = []\n\nprint(\"=\"*50)\nprint(cfg.model_nblocks)\nfor epoch in range(cfg.num_epochs):\n    epoch_list.append(epoch + 1)\n    print(f\"Epoch: {epoch}\")\n    TL = train_one_epoch(model, train_loader, optimizer, criterion)\n    VL, score = validation_one_epoch(model, valid_loader, criterion)\n    train_losses.append(TL)\n    valid_losses.append(VL)\n    # sched.step()\n\n    if score > max_score:\n        max_score = score\n        torch.save(model.state_dict(), \"best_model_state.h5\")      #儲存最好的模型參數\n        print(\"Saving Model ...\")\n\n    print(\"=\"*50)\n    \nplt.figure()\nplt.title('Loss Cruve')\nplt.xlabel('Epochs')\nplt.ylabel('Loss')\nplt.plot(epoch_list, train_losses, marker = 'o')\nplt.plot(epoch_list, valid_losses, marker = 'o')\nplt.legend(['train', 'valid'], loc='upper left')\n\nfor i in range(len(epoch_list)):\n    plt.text(epoch_list[i], train_losses[i], f\"{train_losses[i]:.4f}\", ha='right')\n    plt.text(epoch_list[i], valid_losses[i], f\"{valid_losses[i]:.4f}\", ha='right')\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-04-05T18:28:19.076921Z","iopub.execute_input":"2024-04-05T18:28:19.077312Z","iopub.status.idle":"2024-04-05T20:10:12.526094Z","shell.execute_reply.started":"2024-04-05T18:28:19.077275Z","shell.execute_reply":"2024-04-05T20:10:12.524551Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submission","metadata":{}},{"cell_type":"code","source":"model = FOGModel().to(cfg.device)\nmodel.load_state_dict(torch.load(\"/kaggle/working/best_model_state.h5\"))             #取得最好的模型參數\nmodel.eval()\n\ntest_defog_paths = glob.glob(\"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/test/defog/*.csv\")\ntest_tdcsfog_paths = glob.glob(\"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/test/tdcsfog/*.csv\")\ntest_fpaths = [(f, 'de') for f in test_defog_paths] + [(f, 'tdcs') for f in test_tdcsfog_paths]\n\ntest_dataset = FOGDataset(test_fpaths, split=\"test\")\ntest_loader = DataLoader(test_dataset, batch_size=cfg.batch_size, num_workers=5)\n\nids = []\npreds = []\n\nfor _id, x, _ in tqdm(test_loader):\n    x = x.to(cfg.device).float()\n    with torch.no_grad():\n        y_pred = model(x)*0.1\n    \n    ids.extend(_id)\n    preds.extend(list(np.nan_to_num(y_pred.cpu().numpy())))","metadata":{"execution":{"iopub.status.busy":"2024-04-05T20:10:12.528309Z","iopub.execute_input":"2024-04-05T20:10:12.528737Z","iopub.status.idle":"2024-04-05T20:10:22.800637Z","shell.execute_reply.started":"2024-04-05T20:10:12.528697Z","shell.execute_reply":"2024-04-05T20:10:22.799210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission = pd.read_csv(\"/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/sample_submission.csv\")\nsample_submission.shape","metadata":{"execution":{"iopub.status.busy":"2024-04-05T20:10:22.802439Z","iopub.execute_input":"2024-04-05T20:10:22.802892Z","iopub.status.idle":"2024-04-05T20:10:23.196023Z","shell.execute_reply.started":"2024-04-05T20:10:22.802844Z","shell.execute_reply":"2024-04-05T20:10:23.194525Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds = np.array(preds)\nsubmission = pd.DataFrame({'Id': ids, 'StartHesitation': np.round(preds[:,0],5), \\\n                           'Turn': np.round(preds[:,1],5), 'Walking': np.round(preds[:,2],5)})\n\nsubmission = pd.merge(sample_submission[['Id']], submission, how='left', on='Id').fillna(0.0)\nsubmission.to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2024-04-05T20:10:23.199538Z","iopub.execute_input":"2024-04-05T20:10:23.200002Z","iopub.status.idle":"2024-04-05T20:10:25.359899Z","shell.execute_reply.started":"2024-04-05T20:10:23.199952Z","shell.execute_reply":"2024-04-05T20:10:25.358438Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(submission.shape)\nsubmission.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-05T20:10:25.361669Z","iopub.execute_input":"2024-04-05T20:10:25.363088Z","iopub.status.idle":"2024-04-05T20:10:25.392621Z","shell.execute_reply.started":"2024-04-05T20:10:25.363023Z","shell.execute_reply":"2024-04-05T20:10:25.391241Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}