# Drop irrelevant columns
df = df.drop(['price', 'number_available_in_stock', 'customers_who_bought_this_item_also_bought',
              'items_customers_buy_after_viewing_this_item', 'customer_questions_and_answers', 'sellers'], axis=1)

# Drop rows with essential missing data
df.dropna(subset=['product_information', 'price_value', 'description', 'amazon_category_and_sub_category'], how='any', inplace=True)