{"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":"# 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":"2022-11-15T05:42:59.594321Z","iopub.execute_input":"2022-11-15T05:42:59.594730Z","iopub.status.idle":"2022-11-15T05:43:13.607372Z","shell.execute_reply.started":"2022-11-15T05:42:59.594648Z","shell.execute_reply":"2022-11-15T05:43:13.606152Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"root = '../input/vehicle/train/train'\ndata = []\nfor category in sorted(os.listdir(root)):\n    for file in sorted(os.listdir(os.path.join(root, category))):\n        data.append((category, os.path.join(root, category,  file)))\n\ndf = pd.DataFrame(data, columns=['class', 'file_path'])\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2022-11-15T05:56:06.821828Z","iopub.execute_input":"2022-11-15T05:56:06.822299Z","iopub.status.idle":"2022-11-15T05:56:06.934884Z","shell.execute_reply.started":"2022-11-15T05:56:06.822257Z","shell.execute_reply":"2022-11-15T05:56:06.933389Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nX = df[\"file_path\"].values\nclasses = dict()\nfor i, _class in enumerate(df[\"class\"].unique()):\n    classes[_class] = i\nY = df[\"class\"].apply(lambda x: classes[x]).values\n\nX_train, X_test, Y_train, Y_test = train_test_split( \\\n     X, Y, test_size=0.33, random_state=42)","metadata":{"execution":{"iopub.status.busy":"2022-11-15T06:00:38.154564Z","iopub.execute_input":"2022-11-15T06:00:38.154973Z","iopub.status.idle":"2022-11-15T06:00:38.178148Z","shell.execute_reply.started":"2022-11-15T06:00:38.154941Z","shell.execute_reply":"2022-11-15T06:00:38.176639Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.shape, X_test.shape, Y_train.shape,Y_test.shape","metadata":{"execution":{"iopub.status.busy":"2022-11-15T06:00:39.830512Z","iopub.execute_input":"2022-11-15T06:00:39.831713Z","iopub.status.idle":"2022-11-15T06:00:39.839136Z","shell.execute_reply.started":"2022-11-15T06:00:39.831660Z","shell.execute_reply":"2022-11-15T06:00:39.838140Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.shape[0]","metadata":{"execution":{"iopub.status.busy":"2022-11-15T06:07:36.687913Z","iopub.execute_input":"2022-11-15T06:07:36.688338Z","iopub.status.idle":"2022-11-15T06:07:36.696458Z","shell.execute_reply.started":"2022-11-15T06:07:36.688305Z","shell.execute_reply":"2022-11-15T06:07:36.695044Z"},"trusted":true},"execution_count":null,"outputs":[]}]}