{"cells":[{"metadata":{},"cell_type":"markdown","source":"\nReference https://www.kaggle.com/tunguz/lightgbm-baseline/output"},{"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":"\nimport lightgbm as lgb   \nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.model_selection import GridSearchCV","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')\ndf_train = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')\ndf_vaild = pd.read_csv('/kaggle/input/Kannada-MNIST/Dig-MNIST.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_vaild.head()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = df_train['label']\nx_train = df_train.drop(['label'],axis=1)\ny_vaild = df_vaild['label']\nx_vaild = df_vaild.drop(['label'],axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lgb_params = {\n            \"objective\" : \"multiclass\",\n            \"metric\" : \"multi_logloss\",\n            \"num_class\" : 10,\n            \"max_depth\" : 5,\n            \"num_leaves\" : 30,\n            \"learning_rate\" : 0.1,\n            \"bagging_fraction\" : 0.4,\n            \"feature_fraction\" : 0.7,\n            \"lambda_l1\" : 0,\n            \"lambda_l2\" : 0,}\n\n\nlgtrain = lgb.Dataset(x_train, label=y_train)\nlgtest = lgb.Dataset(x_vaild, label=y_vaild)\nlgb_clf = lgb.train(lgb_params, lgtrain, 1000, \n                    valid_sets=[lgtrain, lgtest], \n                    early_stopping_rounds=5, \n                    verbose_eval=10)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"res = lgb_clf.predict(df_test).argmax(axis=1)\nsubmission = pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')\nsubmission['label'] = res\nsubmission.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}