from sklearn.preprocessing import MinMaxScaler
def rec_items(customer_key, mf_train, user_vecs, item_vecs, customer_list, item_list, item_lookup, num_items = 10):
'''
This function will return the top recommended items to our users
parameters:
customer_key - Input the customer's id number that you want to get recommendations for
mf_train - The training matrix you used for matrix factorization fitting
user_vecs - the user vectors from your fitted matrix factorization
item_vecs - the item vectors from your fitted matrix factorization
customer_list - an array of the customer's ID numbers that make up the rows of your ratings matrix
(in order of matrix)
item_list - an array of the products that make up the columns of your ratings matrix
(in order of matrix)
item_lookup - A simple pandas dataframe of the unique product ID/product descriptions available
num_items - The number of items you want to recommend in order of best recommendations. Default is 10.
returns:
- The top n recommendations chosen based on the user/item vectors for items never interacted with/purchased
'''
cust_ind = np.where(customer_list == customer_key)[0][0] # Returns the index row of our customer id
pref_vec = mf_train[cust_ind,:].toarray() # Get the ratings from the training set ratings matrix
pref_vec = pref_vec.reshape(-1) + 1 # Add 1 to everything, so that items not purchased yet become equal to 1
pref_vec[pref_vec > 1] = 0 # Make everything already purchased zero
rec_vector = user_vecs[cust_ind,:].dot(item_vecs.T) # Get dot product of user vector and all item vectors
# Scale this recommendation vector between 0 and 1
min_max = MinMaxScaler()
rec_vector_scaled = min_max.fit_transform(rec_vector.reshape(-1,1))[:,0]
recommend_vector = pref_vec*rec_vector_scaled
# Items already purchased have their recommendation multiplied by zero
product_idx = np.argsort(recommend_vector)[::-1][:num_items] # Sort the indices of the items into order
# of best recommendations
rec_list = [] # start empty list to store items
for index in product_idx:
code = item_list[index]
rec_list.append([code, item_lookup.EnglishProductName.loc[item_lookup.ProductKey == code].iloc[0]])
# Append our descriptions to the list
codes = [item[0] for item in rec_list]
descriptions = [item[1] for item in rec_list]
final_frame = pd.DataFrame({'ProductKey': codes, 'EnglishProductName': descriptions}) # Create a dataframe
return final_frame[['ProductKey', 'EnglishProductName']] # Switch order of columns around
rec_items(11001, product_train, user_vecs, item_vecs, customers_arr, products_arr, item_lookup,
num_items = 10)
Back