[FEA] Using advanced TF functionality in notebooks

Open
#400 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
35/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Stale
Tech stack
python, tensorflow
Domain
documentation, machine-learning

Research direction

Start with the Rossmann and using-feature-columns notebooks, reviewing their TensorFlow training and Description-column preprocessing. Clarify whether both enhancements are in scope, then determine whether the notebooks demonstrate DenseFeatures and multi-hot keyword support without breaking the existing NVTabular preprocessing example.

Written by the indexing model from the issue text.

Description

Ideally, the Rossmann notebook should be using NVTabular's DenseFeatures layer during the TensorFlow training portion. Unless this feels out of scope for what's supposed to be the simplest example.

I also think it would be valuable to show multi-hot support in the using-feature-columns notebook by doing something with the Description column (i.e. check for instances of keywords like "good", "cute", "playful", etc.), but since part of this notebook is showing how to replace the preprocessing with NVT, we would need to figure out how to do that tokenizing in a LambdaOp which is somewhat nontrivial (you can't do an applymap since the column is categorical, and doing something like col.str.split().groupby(level=0).agg(list) doesn't have agg support for the string columns).

Dominant language
Python
Stars
1.2k
Forks
149
No merged PRs in 30d

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from NVIDIA-Merlin/NVTabular

All issues in NVIDIA-Merlin/NVTabular

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.