{"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","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# essential tools\nimport pandas as pd\nimport numpy as np\nimport pickle\nfrom sklearn.ensemble import RandomForestClassifier\nfrom datetime import datetime\n\ndata = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')\nX = data[data.columns[1:]]\ny = data[data.columns[0]]\nrandomforest1 = RandomForestClassifier(n_estimators=10,\n                                      max_features='sqrt',\n                                      bootstrap=True,\n                                      n_jobs=1,\n                                      random_state=0)\nstart=datetime.now() # 2021-04-30 16:42:43.157194\nrandomforest1.fit(X,y)\nend=datetime.now() # 2021-04-30 16:42:48.094273\nprint(end-start) # 0:00:04.937079\n\ntest_data = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')\ntest_ids = test_data[test_data.columns[0]]\nX_test = test_data[test_data.columns[1:]]\n\ntest_predictions = randomforest1.predict(X_test)\ntest_predictions = pd.DataFrame({'id': test_ids,\n                                 'label': test_predictions})\n\ntest_predictions.to_csv('submission.csv',\n                        header=['id', 'label'],\n                        index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}