Building Production Recommendation Systems in Python and JAX by Bryan Bischof and Hector Yee

Author:Bryan Bischof and Hector Yee
Language: eng
Format: mobi, epub
Publisher: O'Reilly Media, Inc.
Published: 2023-05-03T00:00:00+00:00

python3 random_item_recommender.py

--input_file=STL-Dataset/fashion-cat.json --output_html=output.xhtml

After completion you can open the output.xhtml file with your web browser and see some random items from the catalog. A sample of this can be seen in Figure 5-1.

Figure 5-1. Random Item Recommender

The fashion-catalog.json contains descriptions of products and their Pinterest ID while fashion.json contains pairings of a scene with a recommended product.

Next, we’ll look at how we can recommend multiple new items for a single scene by training a machine learning model on scene-product pairings.

It is generally a good idea to create a random item recommender the first time you encounter a corpus just so you have an idea of what kind of items are in the corpus and you have a baseline to compare to.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.