{"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)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data Import"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"structures = pd.read_csv('../input/structures.csv')\ntrain = pd.read_csv('../input/train.csv')\ntest= pd.read_csv('../input/test.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data Engineering"},{"metadata":{"trusted":true},"cell_type":"code","source":"def map_atom_info(df, atom_idx):\n    df = pd.merge(df, structures, how = 'left',\n                  left_on  = ['molecule_name', f'atom_index_{atom_idx}'],\n                  right_on = ['molecule_name',  'atom_index'])\n    \n    df = df.drop('atom_index', axis=1)\n    df = df.rename(columns={'atom': f'atom_{atom_idx}',\n                            'x': f'x_{atom_idx}',\n                            'y': f'y_{atom_idx}',\n                            'z': f'z_{atom_idx}'})\n    return df\n\ntrain = map_atom_info(train, 0)\ntrain = map_atom_info(train, 1)\n\ntest = map_atom_info(test, 0)\ntest = map_atom_info(test, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_p_0 = train[['x_0', 'y_0', 'z_0']].values\ntrain_p_1 = train[['x_1', 'y_1', 'z_1']].values\ntest_p_0 = test[['x_0', 'y_0', 'z_0']].values\ntest_p_1 = test[['x_1', 'y_1', 'z_1']].values\n\ntrain['dist'] = np.linalg.norm(train_p_0 - train_p_1, axis=1)\ntest['dist'] = np.linalg.norm(test_p_0 - test_p_1, axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"GroupedBy = structures.groupby(by='molecule_name')\n\nmolecule_count = GroupedBy.count().drop(['atom_index','x','y','z'],axis=1)\nmolecule_count = molecule_count.rename(columns={'atom':'molecule_size'})\n\nmolecule_mean = GroupedBy.mean().drop(['atom_index'],axis=1)\nmolecule_mean = molecule_mean.rename(columns={'x':'x_mean','y':'y_mean','z':'z_mean'})\n\nmolecule_max = GroupedBy.max().drop(['atom_index','atom'],axis=1)\nmolecule_max = molecule_max.rename(columns={'x':'x_max','y':'y_max','z':'z_max'})\n\nmolecule_min = GroupedBy.min().drop(['atom_index','atom'],axis=1)\nmolecule_min = molecule_min.rename(columns={'x':'x_min','y':'y_min','z':'z_min'})\n\nmolecule_std = GroupedBy.std().drop(['atom_index'],axis=1)\nmolecule_std = molecule_std.rename(columns={'x':'x_std','y':'y_std','z':'z_std'})\n\natom_count=pd.get_dummies(structures.rename(columns={'atom':'atom_count'}),columns=['atom_count']).drop(['atom_index','x','y','z'],axis=1)\natom_count=atom_count.groupby('molecule_name').sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def add_features_1(df):\n    df2 = df[['molecule_name','type']].rename(columns={'type':'type_count'})\n    type_count=pd.get_dummies(df2,columns=['type_count']).groupby('molecule_name').sum()\n    \n    df = pd.merge(df, molecule_count, how = 'left',left_on  = ['molecule_name'],right_on = ['molecule_name'])\n    df = pd.merge(df,molecule_mean,how='left',left_on  = ['molecule_name'],right_on = ['molecule_name'])\n    df = pd.merge(df,molecule_min,how='left',left_on  = ['molecule_name'],right_on = ['molecule_name'])\n    df = pd.merge(df,molecule_max,how='left',left_on  = ['molecule_name'],right_on = ['molecule_name'])\n    df = pd.merge(df,molecule_std,how='left',left_on  = ['molecule_name'],right_on = ['molecule_name'])\n    df = pd.merge(df,atom_count,how='left',left_on  = ['molecule_name'],right_on = ['molecule_name'])\n    df = pd.merge(df,type_count,how='left',left_on = ['molecule_name'],right_on = ['molecule_name'])\n    return(df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train=add_features_1(train)\ntest=add_features_1(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#print(test['atom_0'].value_counts())\n#train = train.drop(['atom_0'],axis=1)\n#test = test.drop(['atom_0'],axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#condition = ((train.type=='2JHH') | (train.type=='3JHH'))\n#train[condition].head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def add_features_2(df):\n    df['couples_number'] = df.groupby(['molecule_name'])['id'].transform('count')\n    df['avg_dist']=df.groupby(['molecule_name'])['dist'].transform('mean')\n    df['min_dist']=df.groupby(['molecule_name'])['dist'].transform('min')\n    df['max_dist']=df.groupby(['molecule_name'])['dist'].transform('max')\n    df['dist_std']=df.groupby(['molecule_name'])['dist'].transform('std')\n    \n    \n    df_p_0 = df[['x_0', 'y_0', 'z_0']].values\n    df_p_1 = df[['x_1', 'y_1', 'z_1']].values\n    df_p_mean = df[['x_mean','y_mean','z_mean']].values\n\n    df['dist_0_to_mean'] = np.linalg.norm(df_p_0 - df_p_mean, axis=1)\n    df['dist_1_to_mean'] = np.linalg.norm(df_p_1 - df_p_mean, axis=1)\n    return(df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train=add_features_2(train)\ntest= add_features_2(test)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data Exploration"},{"metadata":{"trusted":true},"cell_type":"code","source":"#sns.distplot(train.scalar_coupling_constant)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#sns.countplot(molecule_count.molecule_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#sns.countplot(train.type)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#sns.countplot(train['atom_1'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#sns.boxplot(x=train.atom_1,y=train.scalar_coupling_constant,palette='rainbow')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#sns.boxplot(x=train.type,y=train.scalar_coupling_constant,palette='rainbow')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#sns.distplot(train.dist)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#plt.scatter(train.dist,train.scalar_coupling_constant)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#plt.scatter(train.molecule_size,train.scalar_coupling_constant)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Predicting"},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train.drop(['molecule_name','scalar_coupling_constant','id'],axis=1)\nX= pd.get_dummies(X)\n\nY= train['scalar_coupling_constant']\n\nid_test = test['id']\nX_test = test.drop(['molecule_name','id'],axis=1)\nX_test = pd.get_dummies(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Get missing columns in the training test\nmissing_cols = set( X.columns ) - set( X_test.columns )\n# Add a missing column in test set with default value equal to 0\nfor c in missing_cols:\n    X_test[c] = 0\n# Ensure the order of column in the test set is in the same order than in train set\nX_test = X_test[X.columns]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.model_selection import KFold\nfrom sklearn.ensemble import GradientBoostingRegressor\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.ensemble import AdaBoostRegressor\nfrom sklearn.metrics import mean_absolute_error\n\ngroups = train['type']\n\ndef group_mean_log_mae(y_true, y_pred, groups, floor=1e-9):\n    maes = (y_true-y_pred).abs().groupby(groups).mean()\n    return np.log(maes.map(lambda x: max(x, floor))).mean()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#model=GradientBoostingRegressor()\n#scores = cross_val_score(model,X,Y,cv=5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#X_train, X_val, Y_train, Y_val = train_test_split(X[:1000000],Y[:1000000],test_size=0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#model=RandomForestRegressor(n_estimators=10,max_features = 0.3,max_depth=20, verbose=1)\n#model.fit(X_train,Y_train)\n#pred= model.predict(X_val)\n#group_mean_log_mae(Y_val,pred,groups)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#importances = model.feature_importances_\n#indices = np.argsort(importances)[::-1]\n\n#plt.figure(figsize=(10,5))\n#plt.title(\"Feature importances\")\n#plt.bar(range(X.shape[1]), importances[indices],color=\"r\", align=\"center\")\n#plt.xticks(range(X.shape[1]), X.columns[indices],rotation='vertical')\n#plt.xlim([-1, X.shape[1]])\n#plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#importances","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Output"},{"metadata":{"trusted":true},"cell_type":"code","source":"model=RandomForestRegressor(n_estimators=10,max_features =0.3,max_depth=15, verbose=1)\n#model=AdaBoostRegressor(n_estimators=60,verbose=1)\nmodel.fit(X,Y)\npred=model.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_output = pd.DataFrame({\"id\" : id_test,\"scalar_coupling_constant\": pred})\ntest_output.set_index(\"id\", inplace=True)\ntest_output.to_csv(\"prediction2.csv\")","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}