giacbrd/ShallowLearn

An experiment about re-implementing supervised learning models based on shallow neural network approaches (e.g. fastText) with some additional exclusive features and nice API. Written in Python and fully compatible with Scikit-learn.

48
/ 100
Emerging

Implements both Gensim-optimized and native fastText variants with support for hierarchical softmax, negative sampling, and feature hashing via the hashing trick for efficient online learning. Offers exclusive persistence features leveraging Gensim's SaveLoad interface with compression control, and includes pre-training of word embeddings via `fit_embeddings()`. Benchmarks demonstrate competitive speed on text classification while supporting incremental learning through `partial_fit()`.

198 stars and 12 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m No Dependents
Maintenance 0 / 25
Adoption 13 / 25
Maturity 18 / 25
Community 17 / 25

How are scores calculated?

Stars

198

Forks

29

Language

Python

License

LGPL-3.0

Last pushed

Aug 08, 2017

Monthly downloads

12

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/giacbrd/ShallowLearn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.