item2vec-data-preparation.py

order_ds = orders_csv.merge(order_products_csv, 
                            left_on='order_id',
                            right_index=True)

# Creating sequences based on transactions
order_product_list = order_ds.sort_values(
                         ['user_id','order_id','add_to_cart_order'])
                         [['order_id','product_id']].values.tolist()

# Each entry of a corpus is one order represented by 
# a chronologically sorted sequence of product IDs.
product_corpus = []     
sentence = []
new_order_id = order_product_list[0][0]

for (order_id, product_id) in order_product_list:
    if new_order_id != order_id:
        product_corpus.append(sentence)
        sentence = []
        new_order_id = order_id
    sentence.append(str(product_id))