{"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\nI used a lot of code from Kaggle's starter notebook here: https://www.kaggle.com/code/ryanholbrook/getting-started-with-ai4code\n\nI replaced their model with a DistilBert model.","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":{"execution":{"iopub.execute_input":"2022-05-12T10:15:13.951478Z","iopub.status.busy":"2022-05-12T10:15:13.951066Z","iopub.status.idle":"2022-05-12T10:15:14.040387Z","shell.execute_reply":"2022-05-12T10:15:14.039667Z"},"papermill":{"duration":0.122804,"end_time":"2022-05-12T10:15:14.042970","exception":false,"start_time":"2022-05-12T10:15:13.920166","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"NUM_TRAIN = 10000\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":{"execution":{"iopub.execute_input":"2022-05-12T10:15:14.107207Z","iopub.status.busy":"2022-05-12T10:15:14.106538Z","iopub.status.idle":"2022-05-12T10:16:36.363191Z","shell.execute_reply":"2022-05-12T10:16:36.362516Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:36.857300Z","iopub.status.busy":"2022-05-12T10:16:36.857054Z","iopub.status.idle":"2022-05-12T10:16:36.878946Z","shell.execute_reply":"2022-05-12T10:16:36.878136Z"},"papermill":{"duration":0.270693,"end_time":"2022-05-12T10:16:36.882443","exception":false,"start_time":"2022-05-12T10:16:36.611750","status":"completed"},"tags":[]},"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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:37.381925Z","iopub.status.busy":"2022-05-12T10:16:37.381231Z","iopub.status.idle":"2022-05-12T10:16:39.965605Z","shell.execute_reply":"2022-05-12T10:16:39.964917Z"},"papermill":{"duration":2.835076,"end_time":"2022-05-12T10:16:39.967500","exception":false,"start_time":"2022-05-12T10:16:37.132424","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(df_orders.loc[\"002ba502bdac45\"])","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:16:40.463326Z","iopub.status.busy":"2022-05-12T10:16:40.463068Z","iopub.status.idle":"2022-05-12T10:16:40.470237Z","shell.execute_reply":"2022-05-12T10:16:40.469597Z"},"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_count":null,"outputs":[]},{"cell_type":"code","source":"cell_order = df_orders.loc[nb_id]\n\nprint(\"The ordered notebook:\")\nnb.loc[cell_order, :]","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:16:40.969105Z","iopub.status.busy":"2022-05-12T10:16:40.968534Z","iopub.status.idle":"2022-05-12T10:16:40.983288Z","shell.execute_reply":"2022-05-12T10:16:40.982229Z"},"papermill":{"duration":0.265934,"end_time":"2022-05-12T10:16:40.985710","exception":false,"start_time":"2022-05-12T10:16:40.719776","status":"completed"},"tags":[]},"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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:41.484544Z","iopub.status.busy":"2022-05-12T10:16:41.484286Z","iopub.status.idle":"2022-05-12T10:16:41.499438Z","shell.execute_reply":"2022-05-12T10:16:41.498718Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:42.068258Z","iopub.status.busy":"2022-05-12T10:16:42.068013Z","iopub.status.idle":"2022-05-12T10:16:44.751144Z","shell.execute_reply":"2022-05-12T10:16:44.750446Z"},"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_count":null,"outputs":[]},{"cell_type":"code","source":"df_ancestors = pd.read_csv(data_dir / 'train_ancestors.csv', index_col='id')\ndf_ancestors","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:16:45.254540Z","iopub.status.busy":"2022-05-12T10:16:45.254289Z","iopub.status.idle":"2022-05-12T10:16:45.444248Z","shell.execute_reply":"2022-05-12T10:16:45.443603Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:45.950324Z","iopub.status.busy":"2022-05-12T10:16:45.950078Z","iopub.status.idle":"2022-05-12T10:16:46.704117Z","shell.execute_reply":"2022-05-12T10:16:46.703426Z"},"papermill":{"duration":1.007951,"end_time":"2022-05-12T10:16:46.706260","exception":false,"start_time":"2022-05-12T10:16:45.698309","status":"completed"},"tags":[]},"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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:47.212537Z","iopub.status.busy":"2022-05-12T10:16:47.212264Z","iopub.status.idle":"2022-05-12T10:16:47.819116Z","shell.execute_reply":"2022-05-12T10:16:47.818438Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:48.327211Z","iopub.status.busy":"2022-05-12T10:16:48.326953Z","iopub.status.idle":"2022-05-12T10:16:49.967047Z","shell.execute_reply":"2022-05-12T10:16:49.966291Z"},"papermill":{"duration":1.895199,"end_time":"2022-05-12T10:16:49.969199","exception":false,"start_time":"2022-05-12T10:16:48.074000","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"val_df.head()","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:16:50.481746Z","iopub.status.busy":"2022-05-12T10:16:50.480937Z","iopub.status.idle":"2022-05-12T10:16:50.493747Z","shell.execute_reply":"2022-05-12T10:16:50.493090Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:51.003368Z","iopub.status.busy":"2022-05-12T10:16:51.003105Z","iopub.status.idle":"2022-05-12T10:16:51.009908Z","shell.execute_reply":"2022-05-12T10:16:51.009235Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:51.526351Z","iopub.status.busy":"2022-05-12T10:16:51.526097Z","iopub.status.idle":"2022-05-12T10:16:51.636666Z","shell.execute_reply":"2022-05-12T10:16:51.635871Z"},"papermill":{"duration":0.372005,"end_time":"2022-05-12T10:16:51.638630","exception":false,"start_time":"2022-05-12T10:16:51.266625","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"val_df[\"cell_type\"].value_counts()","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:16:52.147988Z","iopub.status.busy":"2022-05-12T10:16:52.147364Z","iopub.status.idle":"2022-05-12T10:16:52.163980Z","shell.execute_reply":"2022-05-12T10:16:52.163314Z"},"papermill":{"duration":0.27416,"end_time":"2022-05-12T10:16:52.165630","exception":false,"start_time":"2022-05-12T10:16:51.891470","status":"completed"},"tags":[]},"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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:52.680079Z","iopub.status.busy":"2022-05-12T10:16:52.679814Z","iopub.status.idle":"2022-05-12T10:16:52.795202Z","shell.execute_reply":"2022-05-12T10:16:52.794472Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:16:53.327455Z","iopub.status.busy":"2022-05-12T10:16:53.327148Z","iopub.status.idle":"2022-05-12T10:16:53.347913Z","shell.execute_reply":"2022-05-12T10:16:53.347144Z"},"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_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        return x","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:16:53.867396Z","iopub.status.busy":"2022-05-12T10:16:53.867026Z","iopub.status.idle":"2022-05-12T10:17:00.755019Z","shell.execute_reply":"2022-05-12T10:17:00.754230Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:17:01.267069Z","iopub.status.busy":"2022-05-12T10:17:01.266762Z","iopub.status.idle":"2022-05-12T10:17:01.485207Z","shell.execute_reply":"2022-05-12T10:17:01.484511Z"},"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_count":null,"outputs":[]},{"cell_type":"code","source":"val_df_mark.iloc[0]","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:17:02.052167Z","iopub.status.busy":"2022-05-12T10:17:02.051918Z","iopub.status.idle":"2022-05-12T10:17:02.059316Z","shell.execute_reply":"2022-05-12T10:17:02.058546Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:17:02.572769Z","iopub.status.busy":"2022-05-12T10:17:02.572288Z","iopub.status.idle":"2022-05-12T10:17:02.578527Z","shell.execute_reply":"2022-05-12T10:17:02.577866Z"},"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_count":null,"outputs":[]},{"cell_type":"code","source":"BS = 32\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":{"execution":{"iopub.execute_input":"2022-05-12T10:17:03.122159Z","iopub.status.busy":"2022-05-12T10:17:03.121905Z","iopub.status.idle":"2022-05-12T10:17:03.130177Z","shell.execute_reply":"2022-05-12T10:17:03.128980Z"},"papermill":{"duration":0.298424,"end_time":"2022-05-12T10:17:03.132000","exception":false,"start_time":"2022-05-12T10:17:02.833576","status":"completed"},"tags":[]},"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\nmodel = MarkdownModel()\nmodel = model.cuda()\nmodel, y_pred = train(model, train_loader, val_loader, epochs=1)","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:17:03.645561Z","iopub.status.busy":"2022-05-12T10:17:03.645246Z","iopub.status.idle":"2022-05-12T10:33:30.545823Z","shell.execute_reply":"2022-05-12T10:33:30.544945Z"},"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_count":null,"outputs":[]},{"cell_type":"code","source":"val_df[\"pred\"] = val_df.groupby([\"id\", \"cell_type\"])[\"rank\"].rank(pct=True)\nval_df.loc[val_df[\"cell_type\"] == \"markdown\", \"pred\"] = y_pred","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:33:37.232049Z","iopub.status.busy":"2022-05-12T10:33:37.231781Z","iopub.status.idle":"2022-05-12T10:33:37.303811Z","shell.execute_reply":"2022-05-12T10:33:37.303003Z"},"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_count":null,"outputs":[]},{"cell_type":"code","source":"y_dummy = val_df.sort_values(\"pred\").groupby('id')['cell_id'].apply(list)\nkendall_tau(df_orders.loc[y_dummy.index], y_dummy)","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:33:43.390186Z","iopub.status.busy":"2022-05-12T10:33:43.389931Z","iopub.status.idle":"2022-05-12T10:33:43.543850Z","shell.execute_reply":"2022-05-12T10:33:43.543029Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:33:49.924192Z","iopub.status.busy":"2022-05-12T10:33:49.923570Z","iopub.status.idle":"2022-05-12T10:33:49.984243Z","shell.execute_reply":"2022-05-12T10:33:49.983564Z"},"papermill":{"duration":3.156008,"end_time":"2022-05-12T10:33:49.987070","exception":false,"start_time":"2022-05-12T10:33:46.831062","status":"completed"},"tags":[]},"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":{"execution":{"iopub.execute_input":"2022-05-12T10:33:56.636374Z","iopub.status.busy":"2022-05-12T10:33:56.636106Z","iopub.status.idle":"2022-05-12T10:33:56.646610Z","shell.execute_reply":"2022-05-12T10:33:56.645878Z"},"papermill":{"duration":3.580422,"end_time":"2022-05-12T10:33:56.648552","exception":false,"start_time":"2022-05-12T10:33:53.068130","status":"completed"},"tags":[]},"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":{"execution":{"iopub.execute_input":"2022-05-12T10:34:03.064167Z","iopub.status.busy":"2022-05-12T10:34:03.063599Z","iopub.status.idle":"2022-05-12T10:34:03.118189Z","shell.execute_reply":"2022-05-12T10:34:03.117474Z"},"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_count":null,"outputs":[]},{"cell_type":"code","source":"_, y_test = validate(model, test_loader)","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:34:09.531888Z","iopub.status.busy":"2022-05-12T10:34:09.531617Z","iopub.status.idle":"2022-05-12T10:34:10.220439Z","shell.execute_reply":"2022-05-12T10:34:10.219586Z"},"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_count":null,"outputs":[]},{"cell_type":"code","source":"test_df.loc[test_df[\"cell_type\"] == \"markdown\", \"pred\"] = y_test","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:34:16.407465Z","iopub.status.busy":"2022-05-12T10:34:16.407177Z","iopub.status.idle":"2022-05-12T10:34:16.413170Z","shell.execute_reply":"2022-05-12T10:34:16.412390Z"},"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_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":{"execution":{"iopub.execute_input":"2022-05-12T10:34:22.810371Z","iopub.status.busy":"2022-05-12T10:34:22.810115Z","iopub.status.idle":"2022-05-12T10:34:22.824886Z","shell.execute_reply":"2022-05-12T10:34:22.824116Z"},"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_count":null,"outputs":[]},{"cell_type":"code","source":"sub_df.to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.execute_input":"2022-05-12T10:34:29.520229Z","iopub.status.busy":"2022-05-12T10:34:29.519950Z","iopub.status.idle":"2022-05-12T10:34:29.526990Z","shell.execute_reply":"2022-05-12T10:34:29.526314Z"},"papermill":{"duration":3.551878,"end_time":"2022-05-12T10:34:29.528868","exception":false,"start_time":"2022-05-12T10:34:25.976990","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","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":[]},"execution_count":null,"outputs":[]}]}