DSPP Mini-Capstone

Scraping workshop

Here are the materials for the scraping workshop. Scraping.ipynb contains additional scraping logic not demoed in-class.

Detailed item info

UPDATE: Sainsbury's data added; Morrisons' unit price data, missing from the cross-section, have been added to the detailed item info.

Embeddings

A group mentioned they were interested in embeddings. We have uploaded embeddings for titles and descriptions of products at stores 1, 2, 3, 4, and 8.

There are also embeddings for some comparison terms.

We have also prepared a simple notebook to demonstrate a basic use of embeddings..

There is no expectation to use embeddings in your project, and this isn't an endorsement of one approach over another.



Any other data-related questions?