dkn22/embedder
Embed categorical variables via neural networks.
When building predictive models, this tool helps you automatically convert categorical data (like product categories or customer segments) into numerical 'embeddings' using neural networks. It takes your raw dataset with categorical columns and outputs optimized numerical representations that improve model performance. Data scientists and machine learning engineers will find this useful for streamlining their feature engineering workflow.
No commits in the last 6 months.
Use this if you need to transform high-cardinality categorical variables into meaningful numerical features for your machine learning models without extensive manual engineering.
Not ideal if you prefer to manually define and fine-tune every aspect of your neural network architecture and embedding layers.
Stars
59
Forks
12
Language
Python
License
—
Category
Last pushed
Mar 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/dkn22/embedder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MilaNLProc/contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings...
vinid/cade
Compass-aligned Distributional Embeddings. Align embeddings from different corpora
spcl/ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics
criteo-research/CausE
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
vintasoftware/entity-embed
PyTorch library for transforming entities like companies, products, etc. into vectors to support...