def generate_products()

in datasets/thelook_ecommerce/pipelines/_images/run_thelook_kub/fake.py [0:0]

• 82 lines of code
• 11 McCabe index (conditional complexity)

def generate_products() -> typing.List[dict]:
    product_brand_dict = {}  # products partitioned by brand - unused
    product_category_dict = {}  # product partitioned by cateogry - unused
    gender_category_dict = {}  # products partitioned by gender and category - unused
    product_id_dict = {}  # products to generate events table - unused
    product_gender_dict = {}  # product partitioned by gender
    product_by_id_dict = {}  # products partitioned by product ID

    products = collections.defaultdict(list)
    with open(
        f"{os.environ['SOURCE_DIR']}/products.csv", encoding="utf-8"
    ) as productcsv:
        csv_reader = csv.DictReader(productcsv)
        for rows in csv_reader:
            for k, v in rows.items():
                products[k].append(v)

    product_id = products["id"]
    brands = products["brand"]
    name = products["name"]
    cost = products["cost"]
    category = products["category"]
    department = products["department"]
    sku = products["sku"]
    retail_price = products["retail_price"]
    distribution_center_id = products["distribution_center_id"]
    for _ in range(len(brands)):
        product_brand_dict[brands[_]] = []
        product_category_dict[category[_]] = []
        product_id_dict[product_id[_]] = []
        product_by_id_dict[product_id[_]] = []
        if department[_] == "Men":
            product_gender_dict["M"] = []
            gender_category_dict["M" + category[_]] = []
        if department[_] == "Women":
            product_gender_dict["F"] = []
            gender_category_dict["F" + category[_]] = []
    for col in list(
        zip(
            product_id,
            brands,
            name,
            cost,
            category,
            department,
            sku,
            retail_price,
            distribution_center_id,
        )
    ):
        product_id = col[0]
        brand = col[1]
        name = col[2]
        cost = col[3]
        category = col[4]
        department = col[5]
        sku = col[6]
        retail_price = col[7]
        distribution_center_id = col[8]

        product_by_id_dict[product_id] = {
            "brand": brand,
            "name": name,
            "cost": cost,
            "category": category,
            "department": department,
            "sku": sku,
            "retail_price": retail_price,
            "distribution_center_id": distribution_center_id,
        }
        product_brand_dict[brand].append(col)
        product_category_dict[category].append(col)
        if department == "Men":
            product_gender_dict["M"].append(col)
            gender_category_dict["M" + category].append(col)
        if department == "Women":
            product_gender_dict["F"].append(col)
            gender_category_dict["F" + category].append(col)

    # helper dict to generate events
    for col in list(zip(product_id, brands, category, department)):
        product_id_dict[col[0]] = {
            "brand": col[1],
            "category": col[2],
            "department": col[3],
        }
    return product_gender_dict, product_by_id_dict, products