# best = gscv.best_estimator_.fit(X, y) # y_pred = best.predict(X_pred) y_pred = best.predict(X_pred) #%% # Applicability Domain (inside: +1, outside: -1) from my_library import ad_knn_list iappd = 3 if(iappd == 1): y_appd = ad_knn(X, X_pred) elif(iappd == 2): y_appd = ad_ocsvm(X, X_pred) else: y_appd = ad_knn_list(X, X_pred, 10) data = [] for i in range(len(X_pred)): # temp = (f_pred[i], int(P_pred[i]), int(y_pred[i]), int(y_pred_db[i]), y_appd[i]) temp = (f_pred[i], int(P_pred[i]), int(y_pred[i]), int(y_pred_db[i])) data.append(temp) # properties=['formula','P', 'Tc(pred)', 'Tc(DB)','AD'] properties=['formula','P', 'Tc(pred)', 'Tc(DB)'] df = pd.DataFrame(data, columns=properties) # df.sort_values('Tc', ascending=False, inplace=True) # df.to_csv(output, index=False)
cv = ShuffleSplit(n_splits=n_splits, test_size=0.3) cv = KFold(n_splits=n_splits, shuffle=True) gscv = GridSearchCV(model, param_grid, cv=cv) gscv.fit(X_train, y_train) print_gscv_score_rgr(gscv, X_train, X_test, y_train, y_test, cv) #%% # Prediction y_pred = gscv.predict(X_test) # Applicability Domain (inside: +1, outside: -1) iappd = 1 if (iappd == 1): y_appd = ad_knn(X_train, X_test) else: y_appd = ad_ocsvm(X_train, X_test) data = [] for i in range(len(X_test)): temp = (f_test[i], int(X_test[i][0]), int(y_pred[i]), y_appd[i]) data.append(temp) properties = ['formula', 'P', 'Tc', 'AD'] df = pd.DataFrame(data, columns=properties) df.sort_values('Tc', ascending=False, inplace=True) # df.to_csv(output, index=False) df_in_ = df[df.AD == 1] df_in_.to_csv(output, index=False) print('Predicted Tc is written in file {}'.format(output))
print(gscv.best_estimator_.fit(X_test, y_test).get_params()) print(gscv.best_estimator_.fit(X, y).get_params()) # {... 'n_neighbors': 1, 'p': 2, 'weights': 'uniform'} # {... 'n_neighbors': 1, 'p': 2, 'weights': 'uniform'} # {... 'n_neighbors': 1, 'p': 2, 'weights': 'uniform'} # Re-learning with all data & best parameters -> Prediction y_pred = gscv.best_estimator_.fit(X, y).predict(X_pred) #%% # Applicability Domain (inside: +1, outside: -1) iappd = 1 if (iappd == 1): y_appd = ad_knn(X_train, X_pred) else: y_appd = ad_ocsvm(X_train, X_pred) data = [] for i in range(len(X_pred)): temp = (f_pred[i], int(P_pred[i]), int(y_pred[i]), y_appd[i]) data.append(temp) properties = ['formula', 'P', 'Tc', 'AD'] df = pd.DataFrame(data, columns=properties) df.sort_values('Tc', ascending=False, inplace=True) # df.to_csv(output, index=False) df_in_ = df[df.AD == 1] df_in_.to_csv(output, index=False) print('Predicted Tc is written in file {}'.format(output))