{"cells":[{"metadata":{},"cell_type":"markdown","source":"This is a copy of the following notebook from the MNIST dataset: https://www.kaggle.com/tanreinama/lightgbm-baseline\nIf you find this script useful, please upvote the above notebook as well."},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \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 \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split\n\ndf = pd.read_csv('../input/Kannada-MNIST/train.csv')\ncol = ['pixel%d'%i for i in range(784)]\n\nlgb_params = {\n    \"objective\" : \"multiclass\",\n    \"metric\" : \"multi_logloss\",\n    \"num_class\" : 10,\n    \"max_depth\" : 12,\n    \"num_leaves\" : 15,\n    \"learning_rate\" : 0.05,\n    \"bagging_fraction\" : 0.9,\n    \"feature_fraction\" : 0.9,\n    \"lambda_l1\" : 0.01,\n    \"lambda_l2\" : 0.0,\n}\n\nX_train, X_test, Y_train, Y_test = train_test_split(df[col], df['label'], test_size=0.1)\n\nlgtrain = lgb.Dataset(X_train, label=Y_train)\nlgtest = lgb.Dataset(X_test, label=Y_test)\nlgb_clf = lgb.train(lgb_params, lgtrain, 1500, \n                    valid_sets=[lgtrain, lgtest], \n                    early_stopping_rounds=10, \n                    verbose_eval=20)\n\ndf = pd.read_csv('../input/Kannada-MNIST/test.csv')\nres = lgb_clf.predict( df[col] ).argmax(axis=1)\n\ndf = pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')\ndf['label'] = res\ndf.to_csv('submission.csv', index=False)","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":1}