f04634f2d427763d3b51af4ad6213fe5ad37fbf7,python-package/mlbox/preprocessing/reader.py,Reader,train_test_split,#Reader#Any#Any#,271

Before Change

                print("number of test samples : " + str(df_test.shape[0]))
                print("")
                print("Top 5 sparse features (% missing values on train set):")
                print(np.round((df_train.isnull().sum()*100./df_train.shape[0]).sort_values(ascending=False)[:5],1))
                
            ////////////////////////////////////////////////////////////////////////////////////////////////////////////
            //////////////////////////////////// encoding target ////////////////////////////////////
            ////////////////////////////////////////////////////////////////////////////////////////////////////////////

After Change

                print("number of training samples : " + str(df_train.shape[0]))
                print("number of test samples : " + str(df_test.shape[0]))
                
                if(sparse):
                    print("")
                    print("Top sparse features (% missing values on train set):")
                    print(np.round(sparse_features[sparse_features>0.0][:5],1))
                    
                else:
                    print("")
                    print("you have no missing values on train set...")
                
            ////////////////////////////////////////////////////////////////////////////////////////////////////////////
            //////////////////////////////////// encoding target ////////////////////////////////////
            ////////////////////////////////////////////////////////////////////////////////////////////////////////////

            task = "regression"

            if (y_train.nunique() <= 2):
                task = "classification"

Instances