{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport re\nimport gc\nimport sys\nimport yaml\nimport copy\nimport random\nimport shutil\nimport typing as tp\nfrom pathlib import Path\n\nimport numpy as np\nimport pandas as pd\nfrom tqdm.notebook import tqdm\n\nimport cv2\nimport albumentations\nfrom albumentations.core.transforms_interface import ImageOnlyTransform, DualTransform\nfrom albumentations.pytorch import ToTensorV2\n\nimport torch\nfrom torch import nn\nfrom torch.utils import data\n\n\nsys.path.append(\"../input/iterative-stratification/iterative-stratification-master\")\nfrom iterstrat.ml_stratifiers import MultilabelStratifiedKFold\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport torch\n\ntrain = pd.read_pickle('../input/molecular-preprocessed/train2.pkl')\n\ndef get_train_file_path(image_id):\n    return \"../input/bms-molecular-translation/train/{}/{}/{}/{}.png\".format(\n        image_id[0], image_id[1], image_id[2], image_id \n    )\n\n#train['path'] = train['image_id'].apply(get_train_file_path)\n\nprint(f'train.shape: {train.shape}')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#train_ids,test_ids = train_test_split(train,test_size=0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#train['kfold'] = -1\n#train.loc[train_ids.index,'kfold'] = -1\n#train.loc[test_ids.index,'kfold'] = 0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_save = pd.read_csv('../input/moleculartraintestsplit/data.csv')\ntrain_save.to_csv('data.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"path_dict = {}\nimport os\nfor dirname, _, filenames in os.walk('../input/bms-molecular-translation/test'):\n    for filename in filenames:\n        path_dict[filename.replace('.png','')] = os.path.join(dirname, filename)\n        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_save.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample = pd.read_csv('../input/bms-molecular-translation/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample['path'] = sample.image_id.apply(lambda x:path_dict[x])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample.to_csv('sample_submission.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}