sho | Small Hash Optimization - an optimization | Hashing library

def get_group_by_data(df1, name, parent_cols, child_cols, final_col_names):
    df_dict = {col_name: [] for col_name in final_col_names}  # for the final dataframe
    col_names_map = {
        'Type' : 'Type','SKU': 'SKU','WebName': 'Name','Published': 'Published',
        'Isfeatured': 'yes', 'Short Description': 'Name','Full Description' :'Full Description', 
        'Weight': 'Weight (kg)', 'height' : 'height',
        'RetailPriceEUR': 'Regular price', 
        'ImagePath': 'Images','ParentPartNumber': 'Parent',
        'Value_Size': 'Attribute 1 value(s)',
    }  # for mapping the output column names to input col names

    # extra row
#     print(df_dict)
    parent_comm_cols_n_elems = dict()
    df_dict['Type'].append('variable')
    df_dict['SKU'].append(str(name))
    df_dict['Published'].append(1)
    df_dict['Is featured?'].append('yes')
    df_dict['Parent'].append("")
    df_dict['Height'].append("") # added this 
    df_dict['Short Description'].append("") # added this
#     print(f"Parent cols: {parent_cols}")
    for col in parent_cols:
        parent_col_vals = list(dict.fromkeys(list(df1[col])).keys())  # using dictionary for ignoring the duplicate values and still retaining the order
        parent_comm_cols_n_elems[col] = len(parent_col_vals)
#         print(f"parent_cols: {parent_col_vals}")
        df_dict[col_names_map[col]].append(",".join(val for val in parent_col_vals if val == val))  # val == val for ignoring nan values
    for col in child_cols:
        df_dict[col_names_map[col]].append("")                      
    
    # for adding all the part numbers under parent part number 
    for idx, row in df1.iterrows():
        df_dict['Type'].append('variation')
        df_dict['SKU'].append(row['PartNumber'])
        df_dict['Short Description'].append(row['Short Description']) # added this
        df_dict['Published'].append(1)
        df_dict['Is featured?'].append(0)
        df_dict['Height'].append("") # added this
        df_dict['Parent'].append(str(name))
       
        for col in parent_cols:
            # in case of S,M,L,XL chile rows would have size populated,
            # but in case of 1 elem, like Honeycomb elastic, size not populated in child rows
            if parent_comm_cols_n_elems[col] > 1:
                df_dict[col_names_map[col]].append(row[col])
            else:
                df_dict[col_names_map[col]].append("")
        for col in  child_cols:
            df_dict[col_names_map[col]].append(row[col])
#     print(df_dict)
    return pd.DataFrame.from_dict(df_dict)