https://github.com/autonomio/signs

A suite of tools for text preparation, vectorization and processing for deep learning with Keras.
https://github.com/autonomio/signs

embeddings fasttext gensim glove keras spacy word2vec

Last synced: 3 months ago
JSON representation

A suite of tools for text preparation, vectorization and processing for deep learning with Keras.

• Host: GitHub
• URL: https://github.com/autonomio/signs
• Owner: autonomio
• License: mit
• Created: 2018-06-22T10:23:32.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2023-07-29T11:17:01.000Z (over 1 year ago)
• Last Synced: 2024-10-01T14:50:04.549Z (4 months ago)
• Topics: embeddings, fasttext, gensim, glove, keras, spacy, word2vec
• Language: Python
• Homepage:
• Size: 129 KB
• Stars: 13
• Watchers: 4
• Forks: 3
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        


  


  

  




Computational Text Processing for Humans




  

    

  

  

    

  





  Signs •

  Key Features •

  Examples •

  Install •

  Support •

  Docs •

  Issues •

  License •

  Download







If you want the simplest possible way to generate embeddings for deep learning models without sacrificing the power of state-of-the-art vector models, Signs is for you.









### Signs

Signs is a set of tools for text preparation, vectorization and processing and radically simplifies raw text to Keras embeddings workflow. Signs unifies Gensim and SpaCy vectorization backends for Keras users and provides an easy-to-use vectorization solution to manage otherwise complex workflows. Signs provides a meaningful replacement for dozens of lines of redundant code that are currently required to transform raw text into a a Keras Embeds layer. 

### Key Features

- unifies Gensim and SpaCy vectorization backends

- supports using common vector models: [GloVe](https://nlp.stanford.edu/projects/glove/), [Fasttext](https://fasttext.cc/docs/en/english-vectors.html), and [word2vec](https://en.wikipedia.org/wiki/Word2vec)

- removes NLP learning curve

- adds no more than a few lines of code to your worflow

- From text to Keras embedding layer in a single command

- Train, save, and load custom vectors

- Evaluate results after training a Keras prediction model

- Powerful text preprocessing features

- Allows completely automated text preprocessing

### Examples

[get source](https://gist.github.com/mikkokotila/ad0138788c93bef2b71eaccc9c95701b) for the below example.



Several example notebooks with common workflows can be found [here](https://github.com/autonomio/signs/tree/master/examples).

### Install

Stable version:

#### `pip install signs`

Daily development version:

#### `pip install git+https://github.com/autonomio/signs.git@daily-dev`

### Support

If you want ask a **"how can I use Signs to..."** question, the right place is [StackOverflow](https://stackoverflow.com/questions/ask).

If you found a bug or want to suggest a feature, check the [issues](https://github.com/autonomio/signs/issues) or [create](https://github.com/autonomio/signs/issues/new/choose) a new issue.

### License

[MIT License](https://github.com/autonomio/signs/blob/master/LICENSE)