{"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":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-05-22T03:35:15.469430Z","iopub.execute_input":"2022-05-22T03:35:15.469914Z","iopub.status.idle":"2022-05-22T03:35:15.500759Z","shell.execute_reply.started":"2022-05-22T03:35:15.469800Z","shell.execute_reply":"2022-05-22T03:35:15.499853Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import bson\nimport io\nfrom PIL import Image\nimport struct\nimport pickle","metadata":{"execution":{"iopub.status.busy":"2022-05-22T03:35:15.502861Z","iopub.execute_input":"2022-05-22T03:35:15.503439Z","iopub.status.idle":"2022-05-22T03:35:15.561726Z","shell.execute_reply.started":"2022-05-22T03:35:15.503384Z","shell.execute_reply":"2022-05-22T03:35:15.560854Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_file = \"/kaggle/input/cdiscount-image-classification-challenge/train.bson\"\nIDS_mapping = {}\noffset = 0\nlength_size = 4\ni = 0\ncat = {}\np = 0\nwith open(train_file , \"rb\") as f:\n    while True:\n        f.seek(offset)\n        item_length_bytes = f.read(length_size) \n        if len(item_length_bytes) == 0:\n            break\n        length = struct.unpack(\"<i\", item_length_bytes)[0]\n        f.seek(offset)\n        item_data = f.read(length)\n        item = bson.BSON.decode(item_data)\n        ca = int(item[\"category_id\"])\n        if ca not in cat.keys():\n            cat[ca] = p\n            p += 1\n        for j in range(len(item[\"imgs\"])):\n            IDS_mapping[i + j] = (offset , length , j , cat[ca])\n        i += len(item[\"imgs\"])\n        offset += length","metadata":{"execution":{"iopub.status.busy":"2022-05-22T03:35:15.564577Z","iopub.execute_input":"2022-05-22T03:35:15.565137Z","iopub.status.idle":"2022-05-22T03:45:47.865662Z","shell.execute_reply.started":"2022-05-22T03:35:15.565103Z","shell.execute_reply":"2022-05-22T03:45:47.864146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"a_file = open(\"mappings.pkl\" , \"wb\")\npickle.dump(IDS_mapping , a_file)\na_file.close()","metadata":{"execution":{"iopub.status.busy":"2022-05-22T03:45:58.153233Z","iopub.execute_input":"2022-05-22T03:45:58.153542Z","iopub.status.idle":"2022-05-22T03:46:10.904065Z","shell.execute_reply.started":"2022-05-22T03:45:58.153511Z","shell.execute_reply":"2022-05-22T03:46:10.903171Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"os.listdir()","metadata":{"execution":{"iopub.status.busy":"2022-05-22T03:46:51.514124Z","iopub.execute_input":"2022-05-22T03:46:51.514958Z","iopub.status.idle":"2022-05-22T03:46:51.524226Z","shell.execute_reply.started":"2022-05-22T03:46:51.514912Z","shell.execute_reply":"2022-05-22T03:46:51.523322Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}