{"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":"# Baseline for Pytorch Lightning based submission \n\n**Step 1: For generating spectrograms :** https://www.kaggle.com/code/nischaydnk/split-creating-melspecs-stage-1\n\n**Step 2: Training Notebook with Pytorch Lightning:** https://www.kaggle.com/code/nischaydnk/birdclef-2023-pytorch-lightning-training-w-cmap\n\nFeel free to reach out in comments incase you find bugs or have doubts!!","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport torch\nimport os\nimport pytorch_lightning as pl\nfrom torch.utils.data import Dataset, DataLoader\nfrom sklearn import model_selection\nimport torchvision.transforms as transforms\nimport torchvision.io \nimport librosa\nfrom PIL import Image\nimport albumentations as alb\nimport torch.multiprocessing as mp\nimport warnings\n\nwarnings.filterwarnings('ignore')\nfrom pytorch_lightning.callbacks import ModelCheckpoint, BackboneFinetuning, EarlyStopping\nimport torch.nn as nn\nfrom torch.nn.functional import cross_entropy\nimport torchmetrics\nimport timm\nfrom pathlib import Path\n","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:46:32.413078Z","iopub.execute_input":"2023-04-25T01:46:32.413522Z","iopub.status.idle":"2023-04-25T01:46:52.489477Z","shell.execute_reply.started":"2023-04-25T01:46:32.413483Z","shell.execute_reply":"2023-04-25T01:46:52.488101Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Config:\n    num_classes = 264\n    batch_size = 12\n    PRECISION = 16    \n    seed = 2023\n    model = \"tf_efficientnet_b1_ns\"\n    pretrained = False\n    use_mixup = False\n    mixup_alpha = 0.2   \n    DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')    \n\n    data_root = \"/kaggle/input/birdclef-2023/\"\n    train_images = \"/kaggle/input/split-creating-melspecs-stage-1/specs/train/\"\n    valid_images = \"/kaggle/input/split-creating-melspecs-stage-1/specs/valid/\"\n    train_path = \"/kaggle/input/bc2023-train-val-df/train.csv\"\n    valid_path = \"/kaggle/input/bc2023-train-val-df/valid.csv\"\n    \n    test_path = '/kaggle/input/birdclef-2023/test_soundscapes/'\n    SR = 32000\n    DURATION = 5\n    LR = 5e-4\n    \n    model_ckpt = '/kaggle/input/exp2-b1-maxs7/exp1/last.ckpt'","metadata":{"papermill":{"duration":0.099568,"end_time":"2022-04-22T06:00:18.542447","exception":false,"start_time":"2022-04-22T06:00:18.442879","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-04-25T01:46:52.491978Z","iopub.execute_input":"2023-04-25T01:46:52.492865Z","iopub.status.idle":"2023-04-25T01:46:52.501455Z","shell.execute_reply.started":"2023-04-25T01:46:52.492818Z","shell.execute_reply":"2023-04-25T01:46:52.499307Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pl.seed_everything(Config.seed, workers=True)","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:46:52.504595Z","iopub.execute_input":"2023-04-25T01:46:52.505489Z","iopub.status.idle":"2023-04-25T01:46:52.530319Z","shell.execute_reply.started":"2023-04-25T01:46:52.505445Z","shell.execute_reply":"2023-04-25T01:46:52.529322Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def config_to_dict(cfg):\n    return dict((name, getattr(cfg, name)) for name in dir(cfg) if not name.startswith('__'))","metadata":{"papermill":{"duration":0.033041,"end_time":"2022-04-22T06:00:18.664481","exception":false,"start_time":"2022-04-22T06:00:18.63144","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-04-25T01:46:52.533913Z","iopub.execute_input":"2023-04-25T01:46:52.534738Z","iopub.status.idle":"2023-04-25T01:46:52.540365Z","shell.execute_reply.started":"2023-04-25T01:46:52.534696Z","shell.execute_reply":"2023-04-25T01:46:52.539394Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def compute_melspec(y, sr, n_mels, fmin, fmax):\n    \"\"\"\n    Computes a mel-spectrogram and puts it at decibel scale\n    Arguments:\n        y {np array} -- signal\n        params {AudioParams} -- Parameters to use for the spectrogram. Expected to have the attributes sr, n_mels, f_min, f_max\n    Returns:\n        np array -- Mel-spectrogram\n    \"\"\"\n    melspec = lb.feature.melspectrogram(\n        y=y, sr=sr, n_mels=n_mels, fmin=fmin, fmax=fmax,\n    )\n\n    melspec = lb.power_to_db(melspec).astype(np.float32)\n    return melspec\n\ndef mono_to_color(X, eps=1e-6, mean=None, std=None):\n    mean = mean or X.mean()\n    std = std or X.std()\n    X = (X - mean) / (std + eps)\n    \n    _min, _max = X.min(), X.max()\n\n    if (_max - _min) > eps:\n        V = np.clip(X, _min, _max)\n        V = 255 * (V - _min) / (_max - _min)\n        V = V.astype(np.uint8)\n    else:\n        V = np.zeros_like(X, dtype=np.uint8)\n\n    return V\n\ndef crop_or_pad(y, length, is_train=True, start=None):\n    if len(y) < length:\n        y = np.concatenate([y, np.zeros(length - len(y))])\n        \n        n_repeats = length // len(y)\n        epsilon = length % len(y)\n        \n        y = np.concatenate([y]*n_repeats + [y[:epsilon]])\n        \n    elif len(y) > length:\n        if not is_train:\n            start = start or 0\n        else:\n            start = start or np.random.randint(len(y) - length)\n\n        y = y[start:start + length]\n\n    return y\n","metadata":{"papermill":{"duration":58.466679,"end_time":"2022-04-22T06:01:17.158088","exception":false,"start_time":"2022-04-22T06:00:18.691409","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-04-25T01:46:52.541493Z","iopub.execute_input":"2023-04-25T01:46:52.542569Z","iopub.status.idle":"2023-04-25T01:46:52.555435Z","shell.execute_reply.started":"2023-04-25T01:46:52.542531Z","shell.execute_reply":"2023-04-25T01:46:52.554367Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = pd.read_csv(Config.train_path)\nConfig.num_classes = len(df_train.primary_label.unique())","metadata":{"papermill":{"duration":0.035353,"end_time":"2022-04-22T06:01:17.283888","exception":false,"start_time":"2022-04-22T06:01:17.248535","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-04-25T01:46:52.556606Z","iopub.execute_input":"2023-04-25T01:46:52.557514Z","iopub.status.idle":"2023-04-25T01:46:52.719156Z","shell.execute_reply.started":"2023-04-25T01:46:52.557476Z","shell.execute_reply":"2023-04-25T01:46:52.718030Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = pd.DataFrame(\n     [(path.stem, *path.stem.split(\"_\"), path) for path in Path(Config.test_path).glob(\"*.ogg\")],\n    columns = [\"filename\", \"name\" ,\"id\", \"path\"]\n)\nprint(df_test.shape)\ndf_test.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:46:52.720939Z","iopub.execute_input":"2023-04-25T01:46:52.721408Z","iopub.status.idle":"2023-04-25T01:46:52.751168Z","shell.execute_reply.started":"2023-04-25T01:46:52.721359Z","shell.execute_reply":"2023-04-25T01:46:52.749955Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_test = pd.concat([df_test,df_test,df_test]).reset_index(drop=True)","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:46:52.752735Z","iopub.execute_input":"2023-04-25T01:46:52.753110Z","iopub.status.idle":"2023-04-25T01:46:52.758736Z","shell.execute_reply.started":"2023-04-25T01:46:52.753074Z","shell.execute_reply":"2023-04-25T01:46:52.757236Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"import albumentations as A\ndef get_train_transform():\n    return A.Compose([\n        A.HorizontalFlip(p=0.5),\n        A.OneOf([\n                A.Cutout(max_h_size=5, max_w_size=16),\n                A.CoarseDropout(max_holes=4),\n            ], p=0.5),\n    ])","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:46:52.760674Z","iopub.execute_input":"2023-04-25T01:46:52.761462Z","iopub.status.idle":"2023-04-25T01:46:52.769008Z","shell.execute_reply.started":"2023-04-25T01:46:52.761423Z","shell.execute_reply":"2023-04-25T01:46:52.767845Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import librosa as lb\nimport librosa.display as lbd\nimport soundfile as sf\nfrom  soundfile import SoundFile \n\nclass BirdDataset(Dataset):\n    def __init__(self, data, sr=Config.SR, n_mels=128, fmin=0, fmax=None, duration=Config.DURATION, step=None, res_type=\"kaiser_fast\", resample=True):\n        \n        self.data = data\n        \n        self.sr = sr\n        self.n_mels = n_mels\n        self.fmin = fmin\n        self.fmax = fmax or self.sr//2\n\n        self.duration = duration\n        self.audio_length = self.duration*self.sr\n        self.step = step or self.audio_length\n        \n        self.res_type = res_type\n        self.resample = resample\n\n    def __len__(self):\n        return len(self.data)\n    \n    @staticmethod\n    def normalize(image):\n        image = image.astype(\"float32\", copy=False) / 255.0\n        image = np.stack([image, image, image])\n        return image\n    \n    \n    def audio_to_image(self, audio):\n        melspec = compute_melspec(audio, self.sr, self.n_mels, self.fmin, self.fmax) \n        image = mono_to_color(melspec)\n        image = self.normalize(image)\n        return image\n\n    def read_file(self, filepath):\n        audio, orig_sr = sf.read(filepath, dtype=\"float32\")\n\n        if self.resample and orig_sr != self.sr:\n            audio = lb.resample(audio, orig_sr, self.sr, res_type=self.res_type)\n          \n        audios = []\n        for i in range(self.audio_length, len(audio) + self.step, self.step):\n            start = max(0, i - self.audio_length)\n            end = start + self.audio_length\n            audios.append(audio[start:end])\n            \n        if len(audios[-1]) < self.audio_length:\n            audios = audios[:-1]\n            \n        images = [self.audio_to_image(audio) for audio in audios]\n        images = np.stack(images)\n        \n        return images\n    \n        \n    def __getitem__(self, idx):\n        return self.read_file(self.data.loc[idx, \"path\"])","metadata":{"papermill":{"duration":0.039034,"end_time":"2022-04-22T06:01:17.350173","exception":false,"start_time":"2022-04-22T06:01:17.311139","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-04-25T01:46:52.774398Z","iopub.execute_input":"2023-04-25T01:46:52.774899Z","iopub.status.idle":"2023-04-25T01:46:52.853035Z","shell.execute_reply.started":"2023-04-25T01:46:52.774857Z","shell.execute_reply":"2023-04-25T01:46:52.851343Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ds_test = BirdDataset(\n    df_test, \n    sr = Config.SR,\n    duration = Config.DURATION,\n)\n\n","metadata":{"papermill":{"duration":0.036289,"end_time":"2022-04-22T06:01:17.539606","exception":false,"start_time":"2022-04-22T06:01:17.503317","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-04-25T01:46:52.854726Z","iopub.execute_input":"2023-04-25T01:46:52.855142Z","iopub.status.idle":"2023-04-25T01:46:52.862210Z","shell.execute_reply.started":"2023-04-25T01:46:52.855098Z","shell.execute_reply":"2023-04-25T01:46:52.860441Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ds_test[0].shape","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:46:52.863666Z","iopub.execute_input":"2023-04-25T01:46:52.864029Z","iopub.status.idle":"2023-04-25T01:47:10.899828Z","shell.execute_reply.started":"2023-04-25T01:46:52.863994Z","shell.execute_reply":"2023-04-25T01:47:10.898128Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def show_batch(img_ds, num_items, num_rows, num_cols, predict_arr=None):\n    fig = plt.figure(figsize=(12, 6))    \n    img_index = np.random.randint(0, len(img_ds), num_items)\n    for index, img_index in enumerate(img_index):  # list first 9 images\n        img = img_ds[img_index][0]   \n        \n        ax = fig.add_subplot(num_rows, num_cols, index + 1, xticks=[], yticks=[])\n        if isinstance(img, torch.Tensor):\n            img = img.detach().numpy()\n        if isinstance(img, np.ndarray):\n            img = img.transpose(1, 2, 0)\n            ax.imshow(img)        \n            \n        title = f\"Spec\"\n        ax.set_title(title)  ","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:47:10.901852Z","iopub.execute_input":"2023-04-25T01:47:10.903478Z","iopub.status.idle":"2023-04-25T01:47:10.916154Z","shell.execute_reply.started":"2023-04-25T01:47:10.903416Z","shell.execute_reply":"2023-04-25T01:47:10.914695Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"show_batch(ds_test, 2, 2, 1)","metadata":{"papermill":{"duration":0.584852,"end_time":"2022-04-22T06:01:18.338238","exception":false,"start_time":"2022-04-22T06:01:17.753386","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-04-25T01:47:10.918367Z","iopub.execute_input":"2023-04-25T01:47:10.919347Z","iopub.status.idle":"2023-04-25T01:47:18.709489Z","shell.execute_reply.started":"2023-04-25T01:47:10.919290Z","shell.execute_reply":"2023-04-25T01:47:18.708154Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from torch.optim.lr_scheduler import CosineAnnealingLR, CosineAnnealingWarmRestarts, ReduceLROnPlateau, OneCycleLR\n\ndef get_optimizer(lr, params):\n    model_optimizer = torch.optim.Adam(\n            filter(lambda p: p.requires_grad, params), \n            lr=lr,\n            weight_decay=Config.weight_decay\n        )\n    interval = \"epoch\"\n    \n    lr_scheduler = CosineAnnealingWarmRestarts(\n                            model_optimizer, \n                            T_0=Config.epochs, \n                            T_mult=1, \n                            eta_min=1e-6, \n                            last_epoch=-1\n                        )\n\n    return {\n        \"optimizer\": model_optimizer, \n        \"lr_scheduler\": {\n            \"scheduler\": lr_scheduler,\n            \"interval\": interval,\n            \"monitor\": \"val_loss\",\n            \"frequency\": 1\n        }\n    }","metadata":{"papermill":{"duration":0.048043,"end_time":"2022-04-22T06:01:22.109544","exception":false,"start_time":"2022-04-22T06:01:22.061501","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-04-25T01:47:18.711241Z","iopub.execute_input":"2023-04-25T01:47:18.712109Z","iopub.status.idle":"2023-04-25T01:47:18.721713Z","shell.execute_reply.started":"2023-04-25T01:47:18.712054Z","shell.execute_reply":"2023-04-25T01:47:18.720516Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import sklearn.metrics\n\ndef padded_cmap(solution, submission, padding_factor=5):\n    solution = solution#.drop(['row_id'], axis=1, errors='ignore')\n    submission = submission#.drop(['row_id'], axis=1, errors='ignore')\n    new_rows = []\n    for i in range(padding_factor):\n        new_rows.append([1 for i in range(len(solution.columns))])\n    new_rows = pd.DataFrame(new_rows)\n    new_rows.columns = solution.columns\n    padded_solution = pd.concat([solution, new_rows]).reset_index(drop=True).copy()\n    padded_submission = pd.concat([submission, new_rows]).reset_index(drop=True).copy()\n    score = sklearn.metrics.average_precision_score(\n        padded_solution.values,\n        padded_submission.values,\n        average='macro',\n    )\n    return score\n\ndef map_score(solution, submission):\n    solution = solution#.drop(['row_id'], axis=1, errors='ignore')\n    submission = submission#.drop(['row_id'], axis=1, errors='ignore')\n    score = sklearn.metrics.average_precision_score(\n        solution.values,\n        submission.values,\n        average='micro',\n    )\n    return score","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:47:18.722965Z","iopub.execute_input":"2023-04-25T01:47:18.724934Z","iopub.status.idle":"2023-04-25T01:47:18.736318Z","shell.execute_reply.started":"2023-04-25T01:47:18.724891Z","shell.execute_reply":"2023-04-25T01:47:18.735185Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class BirdClefModel(pl.LightningModule):\n    def __init__(self, model_name=Config.model, num_classes = Config.num_classes, pretrained = Config.pretrained):\n        super().__init__()\n        self.num_classes = num_classes\n\n        self.backbone = timm.create_model(model_name, pretrained=pretrained)\n\n        if 'res' in model_name:\n            self.in_features = self.backbone.fc.in_features\n            self.backbone.fc = nn.Linear(self.in_features, num_classes)\n        elif 'dense' in model_name:\n            self.in_features = self.backbone.classifier.in_features\n            self.backbone.classifier = nn.Linear(self.in_features, num_classes)\n        elif 'efficientnet' in model_name:\n            self.in_features = self.backbone.classifier.in_features\n            self.backbone.classifier = nn.Sequential(\n                nn.Linear(self.in_features, num_classes)\n            )\n        \n        self.loss_function = nn.BCEWithLogitsLoss() \n\n    def forward(self,images):\n        logits = self.backbone(images)\n        return logits\n        \n    def configure_optimizers(self):\n        return get_optimizer(lr=Config.LR, params=self.parameters())\n\n    def training_step(self, batch, batch_idx):\n        image, target = batch        \n\n        y_pred = self(image)\n        loss = self.loss_function(y_pred,target)\n\n        self.log(\"train_loss\", loss, on_step=True, on_epoch=True, prog_bar=True)\n        return loss        \n\n    def validation_step(self, batch, batch_idx):\n        image, target = batch     \n        y_pred = self(image)\n        val_loss = self.loss_function(y_pred, target)\n        self.log(\"val_loss\", val_loss, on_step=True, on_epoch=True, logger=True, prog_bar=True)\n        \n        return {\"val_loss\": val_loss, \"logits\": y_pred, \"targets\": target}\n    \n    def train_dataloader(self):\n        return self._train_dataloader \n    \n    def validation_dataloader(self):\n        return self._validation_dataloader\n    \n    def validation_epoch_end(self,outputs):\n        avg_loss = torch.stack([x['val_loss'] for x in outputs]).mean()\n        output_val = torch.cat([x['logits'] for x in outputs],dim=0).sigmoid().cpu().detach().numpy()\n        target_val = torch.cat([x['targets'] for x in outputs],dim=0).cpu().detach().numpy()\n        \n        # print(output_val.shape)\n        val_df = pd.DataFrame(target_val, columns = birds)\n        pred_df = pd.DataFrame(output_val, columns = birds)\n        \n        avg_score = padded_cmap(val_df, pred_df, padding_factor = 5)\n        avg_score2 = padded_cmap(val_df, pred_df, padding_factor = 3)\n        avg_score3 = sklearn.metrics.label_ranking_average_precision_score(target_val,output_val)\n        \n#         competition_metrics(output_val,target_val)\n        print(f'epoch {self.current_epoch} validation loss {avg_loss}')\n        print(f'epoch {self.current_epoch} validation C-MAP score pad 5 {avg_score}')\n        print(f'epoch {self.current_epoch} validation C-MAP score pad 3 {avg_score2}')\n        print(f'epoch {self.current_epoch} validation AP score {avg_score3}')\n        \n        \n        val_df.to_pickle('val_df.pkl')\n        pred_df.to_pickle('pred_df.pkl')\n        \n        \n        return {'val_loss': avg_loss,'val_cmap':avg_score}\n    \n    \n    \n    ","metadata":{"papermill":{"duration":0.156714,"end_time":"2022-04-22T06:01:22.301564","exception":false,"start_time":"2022-04-22T06:01:22.14485","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-04-25T01:47:18.738223Z","iopub.execute_input":"2023-04-25T01:47:18.739050Z","iopub.status.idle":"2023-04-25T01:47:18.759445Z","shell.execute_reply.started":"2023-04-25T01:47:18.738996Z","shell.execute_reply":"2023-04-25T01:47:18.758384Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def predict(data_loader, model):\n        \n    model.to('cpu')\n    model.eval()    \n    predictions = []\n    for en in range(len(ds_test)):\n        print(en)\n        images = torch.from_numpy(ds_test[en])\n        print(images.shape)\n        with torch.no_grad():\n            outputs = model(images).sigmoid().detach().cpu().numpy()\n            print(outputs.shape)\n#             pred_batch.extend(outputs.detach().cpu().numpy())\n#         pred_batch = np.vstack(pred_batch)\n        predictions.append(outputs)\n            \n    \n    return predictions","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:47:18.761141Z","iopub.execute_input":"2023-04-25T01:47:18.761871Z","iopub.status.idle":"2023-04-25T01:47:18.778127Z","shell.execute_reply.started":"2023-04-25T01:47:18.761810Z","shell.execute_reply":"2023-04-25T01:47:18.776748Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import gc\n\nprint(f\"Create Dataloader...\")\n\nds_test = BirdDataset(\n    df_test, \n    sr = Config.SR,\n    duration = Config.DURATION,\n)\n\n\naudio_model = BirdClefModel()\n\nprint(\"Model Creation\")\n\nmodel = BirdClefModel.load_from_checkpoint(Config.model_ckpt, train_dataloader=None,validation_dataloader=None) \nprint(\"Running Inference..\")\n\npreds = predict(ds_test, model)   \n\ngc.collect()\ntorch.cuda.empty_cache()\n","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:47:18.780582Z","iopub.execute_input":"2023-04-25T01:47:18.781062Z","iopub.status.idle":"2023-04-25T01:47:33.537776Z","shell.execute_reply.started":"2023-04-25T01:47:18.781016Z","shell.execute_reply":"2023-04-25T01:47:33.536163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"filenames = df_test.filename.values.tolist()\n\nbird_cols = list(pd.get_dummies(df_train['primary_label']).columns)\nsub_df = pd.DataFrame(columns=['row_id']+bird_cols)","metadata":{"papermill":{"duration":0.052364,"end_time":"2022-04-22T06:01:22.708806","exception":false,"start_time":"2022-04-22T06:01:22.656442","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-04-25T01:47:33.541602Z","iopub.execute_input":"2023-04-25T01:47:33.542894Z","iopub.status.idle":"2023-04-25T01:47:33.568858Z","shell.execute_reply.started":"2023-04-25T01:47:33.542833Z","shell.execute_reply":"2023-04-25T01:47:33.567109Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub_df","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:47:33.570513Z","iopub.execute_input":"2023-04-25T01:47:33.570933Z","iopub.status.idle":"2023-04-25T01:47:33.593869Z","shell.execute_reply.started":"2023-04-25T01:47:33.570894Z","shell.execute_reply":"2023-04-25T01:47:33.592357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Generate Submission csv","metadata":{}},{"cell_type":"code","source":"for i, file in enumerate(filenames):\n    pred = preds[i]\n    num_rows = len(pred)\n    row_ids = [f'{file}_{(i+1)*5}' for i in range(num_rows)]\n    df = pd.DataFrame(columns=['row_id']+bird_cols)\n    \n    df['row_id'] = row_ids\n    df[bird_cols] = pred\n    \n    sub_df = pd.concat([sub_df,df]).reset_index(drop=True)\n    ","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:47:33.595588Z","iopub.execute_input":"2023-04-25T01:47:33.596119Z","iopub.status.idle":"2023-04-25T01:47:33.717802Z","shell.execute_reply.started":"2023-04-25T01:47:33.596068Z","shell.execute_reply":"2023-04-25T01:47:33.716491Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub_df","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:47:33.719421Z","iopub.execute_input":"2023-04-25T01:47:33.719828Z","iopub.status.idle":"2023-04-25T01:47:33.760068Z","shell.execute_reply.started":"2023-04-25T01:47:33.719790Z","shell.execute_reply":"2023-04-25T01:47:33.758723Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub_df.to_csv('submission.csv',index=False)","metadata":{"execution":{"iopub.status.busy":"2023-04-25T01:47:33.761686Z","iopub.execute_input":"2023-04-25T01:47:33.762160Z","iopub.status.idle":"2023-04-25T01:47:33.807832Z","shell.execute_reply.started":"2023-04-25T01:47:33.762122Z","shell.execute_reply":"2023-04-25T01:47:33.806373Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}