Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Changes from upstream #1

Merged
merged 9 commits into from
Oct 9, 2019
Merged

Conversation

strawberrypie
Copy link
Owner

No description provided.

strawberrypie and others added 9 commits October 3, 2019 14:27
* Option for DeepAR and DeepState to allow an embedding vector instead of
the same value for all categorical features.

By default, if no argument, automatically use the heuristic given by
Jermey Howard of fast.Ai [1]

Each categorical features with size cat_sz, will be associated with a
vector with length defined as below.

emb_szs = [(c, min(50, (c+1)//2)) for _, c in cat_sz]

By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your choice.

[1]
https://github.com/fastai/fastai/blob/master/courses/dl1/lesson3-rossman.ipynb

* #315
Ran "python setup.py type_check" - passed
Ran "black src" for proper formatting

* Ensuring embedding dimension is not None
* Fixes for serializing sets and numpy numbers in SerDe

* Tests for changes in SerDe. Fixes for JSON and code serializations
* fix flaky sampling test

* removing useless import
@strawberrypie strawberrypie merged commit 7eb9353 into strawberrypie:master Oct 9, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants