#dataframe = read_csv(url, names=names) array = df_test.values X_FS = array[:,0:25] Y_FS = array[:,25] # feature extraction model = LogisticRegression(solver='lbfgs') rfe = RFE(model, 15) fit = rfe.fit(X_FS,Y_FS) print("Num Features: %d" % fit.n_features_) print("Selected Features: %s" % fit.support_) print("Feature Ranking: %s" % fit.ranking_) #Creating a dataframe for selected 15 columns rfe=pd.DataFrame(df_test) rfe.drop(['Hospital Id','ccs_diagnosis_code','ccs_procedure_code','Tot_charg', 'Tot_cost','Area_Service', 'Hospital County', 'Hospital Name', 'apr_drg_description','Abortion',],inplace=True,axis=1) rfe.columns rfe.shape X_rfe=rfe.iloc[:,0:15] Y_rfe= rfe.iloc[:,15] ################################################################################# #Function used to plot confusion matrix def plot_confusion_matrix(cm, classes, normalize=False, title='Confusion matrix', cmap=plt.cm.Blues): """ This function prints and plots the confusion matrix. Normalization can be applied by setting `normalize=True`. """