Q1) You are provided with the following datasets:

olist_order_items_dataset.csv: order_id, order_item_id, product_id, price

olist_products_dataset.csv: product_id, product_category_name, product_weight_g, product_length_cm, product_height_cm, product_width_cm

product_category_name_translation.csv: product_category_name, product_category_name_english

Your task is to use these datasets to find association rules among the products.

Note: The transaction is of the form:

Order ID Order_Item_ID Product_ID Price

b8bfa12431142333 a0c84802f9529d87 1 765a8070ece0f138 3d0f5faf913dfb9b 81

b8bfa12431142333 a0c84802f9529d87 2 a41e356c76fab663 34f36de622ecbd3a 99.3

Here, the same order_ID corresponds to the same transaction. So the transaction would be 765a8070ece0f1383d0f5faf913dfb9b, a41e356c76fab66334f36de622ecbd3a (products bought under the same Order ID makes up one transaction) You will need to match the product_ID to their name in spanish and match that to the name of the product in English. The final rules should have the product names in English. You may choose three values for the minsup and minconf as you see fit for the dataset. For the various values

you select, accumulate 5 rules for each case with the highest lift value in a table that looks like the following for each value that you select: Example 1: minsup = x%, minconf = y%

Rule support confidence lift

Example 2: minsup = a%, minconf = b%

Rule support confidence lift