{"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\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":"2021-09-06T20:18:18.808991Z","iopub.execute_input":"2021-09-06T20:18:18.809357Z","iopub.status.idle":"2021-09-06T20:18:18.813502Z","shell.execute_reply.started":"2021-09-06T20:18:18.809328Z","shell.execute_reply":"2021-09-06T20:18:18.812756Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## list of the data files we have here\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n","metadata":{"execution":{"iopub.status.busy":"2021-09-06T20:18:45.485222Z","iopub.execute_input":"2021-09-06T20:18:45.485601Z","iopub.status.idle":"2021-09-06T20:18:45.494468Z","shell.execute_reply.started":"2021-09-06T20:18:45.485569Z","shell.execute_reply":"2021-09-06T20:18:45.493393Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## lets load the traininng data set \ndf = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\nprint(\"Shape of the data\", df.shape)\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2021-09-06T20:19:38.709141Z","iopub.execute_input":"2021-09-06T20:19:38.709474Z","iopub.status.idle":"2021-09-06T20:19:42.517201Z","shell.execute_reply.started":"2021-09-06T20:19:38.709445Z","shell.execute_reply":"2021-09-06T20:19:42.516124Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## this data has  label as target , 784 pixels == 28*28 gray image\nimport seaborn as sns \nimport matplotlib.pyplot as plt\n\nplt.title(\"Label distribution in the dataset\")\nsns.countplot(y =df['label']) \n# we have 10 classes - 10 digits so it becomes a mutilclass-classification","metadata":{"execution":{"iopub.status.busy":"2021-09-06T20:21:58.190292Z","iopub.execute_input":"2021-09-06T20:21:58.190690Z","iopub.status.idle":"2021-09-06T20:21:58.388750Z","shell.execute_reply.started":"2021-09-06T20:21:58.190654Z","shell.execute_reply":"2021-09-06T20:21:58.387670Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}