ml_pipeline_2.py

# pre-processsing step
# Drop the columns - 
# Impute the missing values in column Item_Weight by mean
# Scale the data in the column Item_MRP
pre_process = ColumnTransformer(remainder='passthrough',
                                transformers=[('drop_columns', 'drop', ['Item_Identifier',
                                                                        'Outlet_Identifier',
                                                                        'Item_Fat_Content',
                                                                        'Item_Type',
                                                                        'Outlet_Identifier',
                                                                        'Outlet_Size',
                                                                        'Outlet_Location_Type',
                                                                        'Outlet_Type'
                                                                       ]),
                                              ('impute_item_weight', SimpleImputer(strategy='mean'), ['Item_Weight']),
                                              ('scale_data', StandardScaler(),['Item_MRP'])])