{"cells":[{"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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"df=pd.read_csv('../input/train.csv')\ny=df.iloc[:,[5]]\nX=df.drop(['scalar_coupling_constant','type','molecule_name','id'],axis=1)\ndf_type=pd.get_dummies(df['type'])\ndf_type=df_type.drop(['1JHC'],axis=1)\ndf_type.head()\nX=pd.concat([df_type,X],axis=1)\nX1=np.array(X)\ny1=np.array(y)\nfrom sklearn.linear_model import LinearRegression\nlg=LinearRegression()\nfrom sklearn.model_selection import train_test_split\nX_train,X_test,y_train,y_test=train_test_split(X1,y1,test_size=0.3)\nlg.fit(X_train,y_train)\nr2_score=lg.score(X_test,y_test)\nprint(r2_score)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test=pd.read_csv('../input/test.csv')\nX_test=df_test.drop(['id','molecule_name','type'],axis=1)\ntype_test=pd.get_dummies(df_test['type'])\n\ntype_test=type_test.drop(['1JHC'],axis=1)\nX_test_final=pd.concat([type_test,X_test],axis=1)\nX_test_arr=np.array(X_test_final)\ny_test_arr=lg.predict(X_test_arr)\nid_df=df_test.drop(['molecule_name','type','atom_index_0','atom_index_1'],axis=1)\ny_df=pd.DataFrame(y_test_arr)\nfinal_df=pd.concat([id_df,y_df],axis=1)\nfinal_df.columns=['id','scalar_coupling_constant']\n\nfinal_df.to_csv('mycsvfile.csv',index=False)\n","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}