{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# AI4Code Pytorch DistilBert Baseline\n\nThe training notebook can be found here: https://www.kaggle.com/code/yuanzhezhou/ai4code-distilbert-training-777\n\n\nI used a lot of code from Kaggle's starter notebook here: https://www.kaggle.com/code/ryanholbrook/getting-started-with-ai4code\nand here: https://www.kaggle.com/code/aerdem4/ai4code-pytorch-distilbert-baseline\n\nNote1 : If you try to use the weights from training notebook, please replace MarkdownModel by the one defined in training notebook, they are slightly different.","metadata":{"papermill":{"duration":0.031568,"end_time":"2022-05-12T10:15:13.890382","exception":false,"start_time":"2022-05-12T10:15:13.858814","status":"completed"},"tags":[]}},{"cell_type":"code","source":"import json\nfrom pathlib import Path\n\nimport numpy as np\nimport pandas as pd\nfrom scipy import sparse\nfrom tqdm import tqdm\n\npd.options.display.width = 180\npd.options.display.max_colwidth = 120\n\nBERT_PATH = \"../input/huggingface-bert-variants/distilbert-base-uncased/distilbert-base-uncased\"\n\ndata_dir = Path('../input/AI4Code')","metadata":{"papermill":{"duration":0.122804,"end_time":"2022-05-12T10:15:14.04297","exception":false,"start_time":"2022-05-12T10:15:13.920166","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:06.443889Z","iopub.execute_input":"2022-05-15T05:25:06.444596Z","iopub.status.idle":"2022-05-15T05:25:06.526903Z","shell.execute_reply.started":"2022-05-15T05:25:06.444503Z","shell.execute_reply":"2022-05-15T05:25:06.52619Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"NUM_TRAIN = 200\n\n\ndef read_notebook(path):\n    return (\n        pd.read_json(\n            path,\n            dtype={'cell_type': 'category', 'source': 'str'})\n        .assign(id=path.stem)\n        .rename_axis('cell_id')\n    )\n\n\npaths_train = list((data_dir / 'train').glob('*.json'))[:NUM_TRAIN]\nnotebooks_train = [\n    read_notebook(path) for path in tqdm(paths_train, desc='Train NBs')\n]\ndf = (\n    pd.concat(notebooks_train)\n    .set_index('id', append=True)\n    .swaplevel()\n    .sort_index(level='id', sort_remaining=False)\n)\n\ndf","metadata":{"papermill":{"duration":82.291505,"end_time":"2022-05-12T10:16:36.365197","exception":false,"start_time":"2022-05-12T10:15:14.073692","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:06.530392Z","iopub.execute_input":"2022-05-15T05:25:06.530618Z","iopub.status.idle":"2022-05-15T05:25:11.796504Z","shell.execute_reply.started":"2022-05-15T05:25:06.53059Z","shell.execute_reply":"2022-05-15T05:25:11.795802Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Get an example notebook\nnb_id = df.index.unique('id')[6]\nprint('Notebook:', nb_id)\n\nprint(\"The disordered notebook:\")\nnb = df.loc[nb_id, :]\ndisplay(nb)\nprint()","metadata":{"papermill":{"duration":0.270693,"end_time":"2022-05-12T10:16:36.882443","exception":false,"start_time":"2022-05-12T10:16:36.61175","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:11.798029Z","iopub.execute_input":"2022-05-15T05:25:11.798482Z","iopub.status.idle":"2022-05-15T05:25:11.817433Z","shell.execute_reply.started":"2022-05-15T05:25:11.798445Z","shell.execute_reply":"2022-05-15T05:25:11.816647Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_orders = pd.read_csv(\n    data_dir / 'train_orders.csv',\n    index_col='id',\n    squeeze=True,\n).str.split()  # Split the string representation of cell_ids into a list\n\ndf_orders","metadata":{"papermill":{"duration":2.835076,"end_time":"2022-05-12T10:16:39.9675","exception":false,"start_time":"2022-05-12T10:16:37.132424","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:11.818673Z","iopub.execute_input":"2022-05-15T05:25:11.820443Z","iopub.status.idle":"2022-05-15T05:25:14.60146Z","shell.execute_reply.started":"2022-05-15T05:25:11.820402Z","shell.execute_reply":"2022-05-15T05:25:14.600772Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(df_orders.loc[\"002ba502bdac45\"])","metadata":{"papermill":{"duration":0.257536,"end_time":"2022-05-12T10:16:40.472139","exception":false,"start_time":"2022-05-12T10:16:40.214603","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:14.603964Z","iopub.execute_input":"2022-05-15T05:25:14.604817Z","iopub.status.idle":"2022-05-15T05:25:14.613474Z","shell.execute_reply.started":"2022-05-15T05:25:14.604775Z","shell.execute_reply":"2022-05-15T05:25:14.612528Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cell_order = df_orders.loc[nb_id]\n\nprint(\"The ordered notebook:\")\nnb.loc[cell_order, :]","metadata":{"papermill":{"duration":0.265934,"end_time":"2022-05-12T10:16:40.98571","exception":false,"start_time":"2022-05-12T10:16:40.719776","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:14.614839Z","iopub.execute_input":"2022-05-15T05:25:14.615285Z","iopub.status.idle":"2022-05-15T05:25:14.632773Z","shell.execute_reply.started":"2022-05-15T05:25:14.615244Z","shell.execute_reply":"2022-05-15T05:25:14.632022Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_ranks(base, derived):\n    return [base.index(d) for d in derived]\n\ncell_ranks = get_ranks(cell_order, list(nb.index))\nnb.insert(0, 'rank', cell_ranks)\n\nnb","metadata":{"papermill":{"duration":0.265625,"end_time":"2022-05-12T10:16:41.501618","exception":false,"start_time":"2022-05-12T10:16:41.235993","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:14.634378Z","iopub.execute_input":"2022-05-15T05:25:14.635044Z","iopub.status.idle":"2022-05-15T05:25:14.651102Z","shell.execute_reply.started":"2022-05-15T05:25:14.634992Z","shell.execute_reply":"2022-05-15T05:25:14.650205Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_orders_ = df_orders.to_frame().join(\n    df.reset_index('cell_id').groupby('id')['cell_id'].apply(list),\n    how='right',\n)\n\nranks = {}\nfor id_, cell_order, cell_id in df_orders_.itertuples():\n    ranks[id_] = {'cell_id': cell_id, 'rank': get_ranks(cell_order, cell_id)}\n\ndf_ranks = (\n    pd.DataFrame\n    .from_dict(ranks, orient='index')\n    .rename_axis('id')\n    .apply(pd.Series.explode)\n    .set_index('cell_id', append=True)\n)\n\ndf_ranks","metadata":{"papermill":{"duration":2.967892,"end_time":"2022-05-12T10:16:44.752979","exception":false,"start_time":"2022-05-12T10:16:41.785087","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:14.652735Z","iopub.execute_input":"2022-05-15T05:25:14.653059Z","iopub.status.idle":"2022-05-15T05:25:14.746658Z","shell.execute_reply.started":"2022-05-15T05:25:14.653012Z","shell.execute_reply":"2022-05-15T05:25:14.745971Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_ancestors = pd.read_csv(data_dir / 'train_ancestors.csv', index_col='id')\ndf_ancestors","metadata":{"papermill":{"duration":0.44203,"end_time":"2022-05-12T10:16:45.446006","exception":false,"start_time":"2022-05-12T10:16:45.003976","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:14.747863Z","iopub.execute_input":"2022-05-15T05:25:14.748632Z","iopub.status.idle":"2022-05-15T05:25:14.955137Z","shell.execute_reply.started":"2022-05-15T05:25:14.748594Z","shell.execute_reply":"2022-05-15T05:25:14.954485Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = df.reset_index().merge(df_ranks, on=[\"id\", \"cell_id\"]).merge(df_ancestors, on=[\"id\"])\ndf","metadata":{"papermill":{"duration":1.007951,"end_time":"2022-05-12T10:16:46.70626","exception":false,"start_time":"2022-05-12T10:16:45.698309","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:14.956333Z","iopub.execute_input":"2022-05-15T05:25:14.956587Z","iopub.status.idle":"2022-05-15T05:25:15.024069Z","shell.execute_reply.started":"2022-05-15T05:25:14.956553Z","shell.execute_reply":"2022-05-15T05:25:15.023363Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df[\"pct_rank\"] = df[\"rank\"] / df.groupby(\"id\")[\"cell_id\"].transform(\"count\")\n\ndf[\"pct_rank\"].hist(bins=10)","metadata":{"papermill":{"duration":0.862186,"end_time":"2022-05-12T10:16:47.820945","exception":false,"start_time":"2022-05-12T10:16:46.958759","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:15.025141Z","iopub.execute_input":"2022-05-15T05:25:15.025954Z","iopub.status.idle":"2022-05-15T05:25:15.259467Z","shell.execute_reply.started":"2022-05-15T05:25:15.025914Z","shell.execute_reply":"2022-05-15T05:25:15.258808Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import GroupShuffleSplit\n\nNVALID = 0.1  # size of validation set\n\nsplitter = GroupShuffleSplit(n_splits=1, test_size=NVALID, random_state=0)\n\ntrain_ind, val_ind = next(splitter.split(df, groups=df[\"ancestor_id\"]))\n\ntrain_df = df.loc[train_ind].reset_index(drop=True)\nval_df = df.loc[val_ind].reset_index(drop=True)","metadata":{"papermill":{"duration":1.895199,"end_time":"2022-05-12T10:16:49.969199","exception":false,"start_time":"2022-05-12T10:16:48.074","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:15.260777Z","iopub.execute_input":"2022-05-15T05:25:15.261156Z","iopub.status.idle":"2022-05-15T05:25:15.937265Z","shell.execute_reply.started":"2022-05-15T05:25:15.261122Z","shell.execute_reply":"2022-05-15T05:25:15.936483Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"val_df.head()","metadata":{"papermill":{"duration":0.27219,"end_time":"2022-05-12T10:16:50.495502","exception":false,"start_time":"2022-05-12T10:16:50.223312","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:15.938565Z","iopub.execute_input":"2022-05-15T05:25:15.93881Z","iopub.status.idle":"2022-05-15T05:25:15.950537Z","shell.execute_reply.started":"2022-05-15T05:25:15.938779Z","shell.execute_reply":"2022-05-15T05:25:15.949868Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from bisect import bisect\n\n\ndef count_inversions(a):\n    inversions = 0\n    sorted_so_far = []\n    for i, u in enumerate(a):\n        j = bisect(sorted_so_far, u)\n        inversions += i - j\n        sorted_so_far.insert(j, u)\n    return inversions\n\n\ndef kendall_tau(ground_truth, predictions):\n    total_inversions = 0\n    total_2max = 0  # twice the maximum possible inversions across all instances\n    for gt, pred in zip(ground_truth, predictions):\n        ranks = [gt.index(x) for x in pred]  # rank predicted order in terms of ground truth\n        total_inversions += count_inversions(ranks)\n        n = len(gt)\n        total_2max += n * (n - 1)\n    return 1 - 4 * total_inversions / total_2max","metadata":{"papermill":{"duration":0.262837,"end_time":"2022-05-12T10:16:51.011588","exception":false,"start_time":"2022-05-12T10:16:50.748751","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:15.954573Z","iopub.execute_input":"2022-05-15T05:25:15.955014Z","iopub.status.idle":"2022-05-15T05:25:15.963529Z","shell.execute_reply.started":"2022-05-15T05:25:15.954953Z","shell.execute_reply":"2022-05-15T05:25:15.962673Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_dummy = val_df.groupby('id')['cell_id'].apply(list)\nkendall_tau(df_orders.loc[y_dummy.index], y_dummy)","metadata":{"papermill":{"duration":0.372005,"end_time":"2022-05-12T10:16:51.63863","exception":false,"start_time":"2022-05-12T10:16:51.266625","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:15.964786Z","iopub.execute_input":"2022-05-15T05:25:15.965056Z","iopub.status.idle":"2022-05-15T05:25:15.979735Z","shell.execute_reply.started":"2022-05-15T05:25:15.965016Z","shell.execute_reply":"2022-05-15T05:25:15.978867Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"val_df[\"cell_type\"].value_counts()","metadata":{"papermill":{"duration":0.27416,"end_time":"2022-05-12T10:16:52.16563","exception":false,"start_time":"2022-05-12T10:16:51.89147","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:15.982129Z","iopub.execute_input":"2022-05-15T05:25:15.982528Z","iopub.status.idle":"2022-05-15T05:25:15.991331Z","shell.execute_reply.started":"2022-05-15T05:25:15.982493Z","shell.execute_reply":"2022-05-15T05:25:15.990473Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df_mark = train_df[train_df[\"cell_type\"] == \"markdown\"].reset_index(drop=True)\n\nval_df_mark = val_df[val_df[\"cell_type\"] == \"markdown\"].reset_index(drop=True)","metadata":{"papermill":{"duration":0.371916,"end_time":"2022-05-12T10:16:52.797271","exception":false,"start_time":"2022-05-12T10:16:52.425355","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:15.992716Z","iopub.execute_input":"2022-05-15T05:25:15.993086Z","iopub.status.idle":"2022-05-15T05:25:16.003032Z","shell.execute_reply.started":"2022-05-15T05:25:15.993011Z","shell.execute_reply":"2022-05-15T05:25:16.002235Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import mean_squared_error\n\nmean_squared_error(val_df_mark[\"pct_rank\"], np.ones(val_df_mark.shape[0])*train_df_mark[\"pct_rank\"].mean())","metadata":{"papermill":{"duration":0.280778,"end_time":"2022-05-12T10:16:53.349877","exception":false,"start_time":"2022-05-12T10:16:53.069099","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:16.004556Z","iopub.execute_input":"2022-05-15T05:25:16.004851Z","iopub.status.idle":"2022-05-15T05:25:16.015101Z","shell.execute_reply.started":"2022-05-15T05:25:16.004815Z","shell.execute_reply":"2022-05-15T05:25:16.014251Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tqdm import tqdm\nimport sys, os\nfrom transformers import DistilBertModel, DistilBertTokenizer\nimport torch.nn.functional as F\nimport torch.nn as nn\nimport torch\n\nMAX_LEN = 128\n\nclass MarkdownModel(nn.Module):\n    def __init__(self):\n        super(MarkdownModel, self).__init__()\n        self.distill_bert = DistilBertModel.from_pretrained(BERT_PATH)\n        self.top = nn.Linear(768, 1)\n        \n    def forward(self, ids, mask):\n        x = self.distill_bert(ids, mask)[0]\n        x = self.top(x[:, 0, :])\n        x = torch.sigmoid(x)\n        return x","metadata":{"papermill":{"duration":7.145711,"end_time":"2022-05-12T10:17:00.757077","exception":false,"start_time":"2022-05-12T10:16:53.611366","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:16.016537Z","iopub.execute_input":"2022-05-15T05:25:16.017408Z","iopub.status.idle":"2022-05-15T05:25:21.957621Z","shell.execute_reply.started":"2022-05-15T05:25:16.01737Z","shell.execute_reply":"2022-05-15T05:25:21.956768Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from torch.utils.data import DataLoader, Dataset\n\n\n\nclass MarkdownDataset(Dataset):\n    \n    def __init__(self, df, max_len):\n        super().__init__()\n        self.df = df.reset_index(drop=True)\n        self.max_len = max_len\n        self.tokenizer = DistilBertTokenizer.from_pretrained(BERT_PATH, do_lower_case=True)\n\n    def __getitem__(self, index):\n        row = self.df.iloc[index]\n        \n        inputs = self.tokenizer.encode_plus(\n            row.source,\n            None,\n            add_special_tokens=True,\n            max_length=self.max_len,\n            padding=\"max_length\",\n            return_token_type_ids=True,\n            truncation=True\n        )\n        ids = torch.LongTensor(inputs['input_ids'])\n        mask = torch.LongTensor(inputs['attention_mask'])\n\n        return ids, mask, torch.FloatTensor([row.pct_rank])\n\n    def __len__(self):\n        return self.df.shape[0]\n    \ntrain_ds = MarkdownDataset(train_df_mark, max_len=MAX_LEN)\nval_ds = MarkdownDataset(val_df_mark, max_len=MAX_LEN)\n\nval_ds[0]","metadata":{"papermill":{"duration":0.474499,"end_time":"2022-05-12T10:17:01.487031","exception":false,"start_time":"2022-05-12T10:17:01.012532","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:21.959132Z","iopub.execute_input":"2022-05-15T05:25:21.959538Z","iopub.status.idle":"2022-05-15T05:25:22.128255Z","shell.execute_reply.started":"2022-05-15T05:25:21.959455Z","shell.execute_reply":"2022-05-15T05:25:22.127484Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"val_df_mark.iloc[0]","metadata":{"papermill":{"duration":0.317331,"end_time":"2022-05-12T10:17:02.061139","exception":false,"start_time":"2022-05-12T10:17:01.743808","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:22.129833Z","iopub.execute_input":"2022-05-15T05:25:22.130119Z","iopub.status.idle":"2022-05-15T05:25:22.139582Z","shell.execute_reply.started":"2022-05-15T05:25:22.130084Z","shell.execute_reply":"2022-05-15T05:25:22.138644Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def adjust_lr(optimizer, epoch):\n    if epoch < 1:\n        lr = 5e-5\n    elif epoch < 2:\n        lr = 1e-3\n    elif epoch < 5:\n        lr = 1e-4\n    else:\n        lr = 1e-5\n\n    for p in optimizer.param_groups:\n        p['lr'] = lr\n    return lr\n    \ndef get_optimizer(net):\n    optimizer = torch.optim.Adam(filter(lambda p: p.requires_grad, net.parameters()), lr=3e-4, betas=(0.9, 0.999),\n                                 eps=1e-08)\n    return optimizer","metadata":{"papermill":{"duration":0.265988,"end_time":"2022-05-12T10:17:02.580374","exception":false,"start_time":"2022-05-12T10:17:02.314386","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:22.141145Z","iopub.execute_input":"2022-05-15T05:25:22.141919Z","iopub.status.idle":"2022-05-15T05:25:22.149497Z","shell.execute_reply.started":"2022-05-15T05:25:22.141859Z","shell.execute_reply":"2022-05-15T05:25:22.148597Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"BS = 128\nNW = 8\n\ntrain_loader = DataLoader(train_ds, batch_size=BS, shuffle=True, num_workers=NW,\n                          pin_memory=False, drop_last=True)\nval_loader = DataLoader(val_ds, batch_size=BS, shuffle=False, num_workers=NW,\n                          pin_memory=False, drop_last=False)","metadata":{"papermill":{"duration":0.298424,"end_time":"2022-05-12T10:17:03.132","exception":false,"start_time":"2022-05-12T10:17:02.833576","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:22.15124Z","iopub.execute_input":"2022-05-15T05:25:22.152228Z","iopub.status.idle":"2022-05-15T05:25:22.164034Z","shell.execute_reply.started":"2022-05-15T05:25:22.152174Z","shell.execute_reply":"2022-05-15T05:25:22.162924Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def read_data(data):\n    return tuple(d.cuda() for d in data[:-1]), data[-1].cuda()\n\n\ndef validate(model, val_loader):\n    model.eval()\n    \n    tbar = tqdm(val_loader, file=sys.stdout)\n    \n    preds = []\n    labels = []\n\n    with torch.no_grad():\n        for idx, data in enumerate(tbar):\n            inputs, target = read_data(data)\n\n            pred = model(inputs[0], inputs[1])\n\n            preds.append(pred.detach().cpu().numpy().ravel())\n            labels.append(target.detach().cpu().numpy().ravel())\n    \n    return np.concatenate(labels), np.concatenate(preds)\n\ndef train(model, train_loader, val_loader, epochs):\n    np.random.seed(0)\n    \n    optimizer = get_optimizer(model)\n\n    criterion = torch.nn.MSELoss()\n    \n    for e in range(epochs):   \n        model.train()\n        tbar = tqdm(train_loader, file=sys.stdout)\n        \n        lr = adjust_lr(optimizer, e)\n        \n        loss_list = []\n        preds = []\n        labels = []\n\n        for idx, data in enumerate(tbar):\n            inputs, target = read_data(data)\n\n            optimizer.zero_grad()\n            pred = model(inputs[0], inputs[1])\n\n            loss = criterion(pred, target)\n            loss.backward()\n            optimizer.step()\n            \n            loss_list.append(loss.detach().cpu().item())\n            preds.append(pred.detach().cpu().numpy().ravel())\n            labels.append(target.detach().cpu().numpy().ravel())\n            \n            avg_loss = np.round(np.mean(loss_list), 4)\n\n            tbar.set_description(f\"Epoch {e+1} Loss: {avg_loss} lr: {lr}\")\n            \n        y_val, y_pred = validate(model, val_loader)\n            \n        print(\"Validation MSE:\", np.round(mean_squared_error(y_val, y_pred), 4))\n        print()\n    return model, y_pred\n\n# model = MarkdownModel()\n# model = model.cuda()\n# # model, y_pred = train(model, train_loader, val_loader, epochs=1)\n# model.load_state_dict(torch.load('../input/mymodels2022v2/my_own_model_markdown_file_0_0.78085.bin'))\n\n","metadata":{"papermill":{"duration":987.160977,"end_time":"2022-05-12T10:33:30.548236","exception":false,"start_time":"2022-05-12T10:17:03.387259","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:22.165823Z","iopub.execute_input":"2022-05-15T05:25:22.166779Z","iopub.status.idle":"2022-05-15T05:25:22.183796Z","shell.execute_reply.started":"2022-05-15T05:25:22.16674Z","shell.execute_reply":"2022-05-15T05:25:22.182995Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# val_df[\"pred\"] = val_df.groupby([\"id\", \"cell_type\"])[\"rank\"].rank(pct=True)\n# val_df.loc[val_df[\"cell_type\"] == \"markdown\", \"pred\"] = y_pred","metadata":{"papermill":{"duration":3.695855,"end_time":"2022-05-12T10:33:37.305989","exception":false,"start_time":"2022-05-12T10:33:33.610134","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:22.185088Z","iopub.execute_input":"2022-05-15T05:25:22.185472Z","iopub.status.idle":"2022-05-15T05:25:22.195636Z","shell.execute_reply.started":"2022-05-15T05:25:22.185433Z","shell.execute_reply":"2022-05-15T05:25:22.194819Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# y_dummy = val_df.sort_values(\"pred\").groupby('id')['cell_id'].apply(list)\n# kendall_tau(df_orders.loc[y_dummy.index], y_dummy)","metadata":{"papermill":{"duration":3.230655,"end_time":"2022-05-12T10:33:43.545936","exception":false,"start_time":"2022-05-12T10:33:40.315281","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:22.198404Z","iopub.execute_input":"2022-05-15T05:25:22.198738Z","iopub.status.idle":"2022-05-15T05:25:22.206648Z","shell.execute_reply.started":"2022-05-15T05:25:22.198703Z","shell.execute_reply":"2022-05-15T05:25:22.20588Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"paths_test = list((data_dir / 'test').glob('*.json'))\nnotebooks_test = [\n    read_notebook(path) for path in tqdm(paths_test, desc='Test NBs')\n]\ntest_df = (\n    pd.concat(notebooks_test)\n    .set_index('id', append=True)\n    .swaplevel()\n    .sort_index(level='id', sort_remaining=False)\n).reset_index()","metadata":{"papermill":{"duration":3.156008,"end_time":"2022-05-12T10:33:49.98707","exception":false,"start_time":"2022-05-12T10:33:46.831062","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:22.207995Z","iopub.execute_input":"2022-05-15T05:25:22.208213Z","iopub.status.idle":"2022-05-15T05:25:22.262617Z","shell.execute_reply.started":"2022-05-15T05:25:22.208183Z","shell.execute_reply":"2022-05-15T05:25:22.261658Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df[\"rank\"] = test_df.groupby([\"id\", \"cell_type\"]).cumcount()\ntest_df[\"pred\"] = test_df.groupby([\"id\", \"cell_type\"])[\"rank\"].rank(pct=True)","metadata":{"papermill":{"duration":3.580422,"end_time":"2022-05-12T10:33:56.648552","exception":false,"start_time":"2022-05-12T10:33:53.06813","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:22.264092Z","iopub.execute_input":"2022-05-15T05:25:22.264344Z","iopub.status.idle":"2022-05-15T05:25:22.279751Z","shell.execute_reply.started":"2022-05-15T05:25:22.26431Z","shell.execute_reply":"2022-05-15T05:25:22.279Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df[\"pct_rank\"] = 0\ntest_ds = MarkdownDataset(test_df[test_df[\"cell_type\"] == \"markdown\"].reset_index(drop=True), max_len=MAX_LEN)\ntest_loader = DataLoader(test_ds, batch_size=BS, shuffle=False, num_workers=NW,\n                          pin_memory=False, drop_last=False)\n\nlen(test_ds), test_ds[0]","metadata":{"papermill":{"duration":3.130783,"end_time":"2022-05-12T10:34:03.120038","exception":false,"start_time":"2022-05-12T10:33:59.989255","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:22.28178Z","iopub.execute_input":"2022-05-15T05:25:22.282283Z","iopub.status.idle":"2022-05-15T05:25:22.334618Z","shell.execute_reply.started":"2022-05-15T05:25:22.282246Z","shell.execute_reply":"2022-05-15T05:25:22.33382Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = MarkdownModel()\nmodel = model.cuda()\nmodel.load_state_dict(torch.load('../input/mymodels2022v3/my_own_model_markdown_file_0_0.78169.bin'))\ny_test = validate(model, test_loader)[1]\n\n# model = MarkdownModel()\n# model = model.cuda()\n# model.load_state_dict(torch.load('../input/mymodels2022v3/my_own_model_markdown_file_1_0.74917.bin'))\n# y_test += validate(model, test_loader)[1]/3\n\n# model = MarkdownModel()\n# model = model.cuda()\n# model.load_state_dict(torch.load('../input/mymodels2022v3/my_own_model_markdown_file_2_0.75551.bin'))\n# y_test += validate(model, test_loader)[1]/3\n","metadata":{"papermill":{"duration":4.00212,"end_time":"2022-05-12T10:34:10.223448","exception":false,"start_time":"2022-05-12T10:34:06.221328","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:27:41.865165Z","iopub.execute_input":"2022-05-15T05:27:41.865833Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df.loc[test_df[\"cell_type\"] == \"markdown\", \"pred\"] = y_test\n","metadata":{"papermill":{"duration":3.164567,"end_time":"2022-05-12T10:34:16.415308","exception":false,"start_time":"2022-05-12T10:34:13.250741","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:44.497268Z","iopub.status.idle":"2022-05-15T05:25:44.498151Z","shell.execute_reply.started":"2022-05-15T05:25:44.497887Z","shell.execute_reply":"2022-05-15T05:25:44.497912Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub_df = test_df.sort_values(\"pred\").groupby(\"id\")[\"cell_id\"].apply(lambda x: \" \".join(x)).reset_index()\nsub_df.rename(columns={\"cell_id\": \"cell_order\"}, inplace=True)\nsub_df.head()","metadata":{"papermill":{"duration":3.093752,"end_time":"2022-05-12T10:34:22.827853","exception":false,"start_time":"2022-05-12T10:34:19.734101","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:44.499424Z","iopub.status.idle":"2022-05-15T05:25:44.499831Z","shell.execute_reply.started":"2022-05-15T05:25:44.499614Z","shell.execute_reply":"2022-05-15T05:25:44.499636Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub_df.to_csv(\"submission.csv\", index=False)","metadata":{"papermill":{"duration":3.551878,"end_time":"2022-05-12T10:34:29.528868","exception":false,"start_time":"2022-05-12T10:34:25.97699","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-15T05:25:44.501272Z","iopub.status.idle":"2022-05-15T05:25:44.50203Z","shell.execute_reply.started":"2022-05-15T05:25:44.501768Z","shell.execute_reply":"2022-05-15T05:25:44.501793Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Please upvote if you like it! :D","metadata":{"papermill":{"duration":3.030555,"end_time":"2022-05-12T10:34:35.897014","exception":false,"start_time":"2022-05-12T10:34:32.866459","status":"completed"},"tags":[]}}]}