{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\n\nimport matplotlib.pyplot as plt\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_digits = pd.read_csv('../input/digit-recognizer/train.csv')\ntest_digits = pd.read_csv('../input/digit-recognizer/test.csv')\nsample = pd.read_csv('../input/digit-recognizer/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_digits.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_digits.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fours = train_digits.iloc[3,1:]\nfours.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fours = fours.values.reshape(28, 28)\nplt.imshow(fours, cmap='gray')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(fours[5:-5,5:-5])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"description = train_digits.describe()\ndescription","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"num_class = len(train_digits.iloc[:,0].unique())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = train_digits.iloc[:,1:]\ny_train = train_digits.iloc[:,0]\n\nX_test = test_digits.values\ny_test =test_digits.iloc[:,0]\n\nfrom sklearn.preprocessing import scale\nX_train = scale(X_train)\nX_test = scale(X_test)\n\nprint(X_train.shape)\nprint(X_test.shape)\nprint(y_train.shape)\nprint(y_test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import lightgbm as lgb\nprint('Training lightgbm')\n\nlgtrain = lgb.Dataset(X_train,y_train)\nlgval = lgb.Dataset(X_test, y_test)\n\nparams = {\n    \"objective\": \"multiclass\",\n    \"max_depth\": -1,\n    \"num_classes\":num_class,\n    \"learning_rate\":0.01,\n    \n    \"verbosity\": -1\n}\nmodel = lgb.train(params, lgtrain, 500, valid_sets=[lgtrain, lgval], early_stopping_rounds=750, verbose_eval=200)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = model.predict(X_test)\n\nresults = np.argmax(results, axis=1)\n\nresults = pd.Series(results, name='Label')\n\nsubmission = pd.concat([pd.Series(range(1, 28001), name=\"ImageId\"), results],axis=1)\n\nsubmission.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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":4}