item2vec-embeddings-exploration.py

def to_product_name(id, columns='product_name'):
    Return products_csv[products_csv.product_id==id][columns].values.tolist()[0]

def most_similar_readable(model, product_id, topn=10):
    similar_list = [(product_id, 1.0)] + model.wv.most_similar(str(product_id), 
                                                               topn=topn)
    return pd.DataFrame([( to_product_name(int(id)), int(id), similarity ) for 
                         (id, similarity) in similar_list],
                        columns=['product', 'product_id', 'similarity'])

for product_id in [13176, # Bag of Organic Bananas 
                   39180, # Organic Lowfat 1% Milk
                   2326]: # Organic Blueberry Waffles
    most_similar_readable(model, product_id)