rara-subject-indexer 0.0.2

Automatically detect subject indices.

Subject Indexers

This repository provides two pipelines:

1. for processing text and label files in order to train and evaluate an Omikuji model. It includes text lemmatization, TF-IDF feature extraction, label binarization. The system is designed for extreme multilabel classification.
2. for processing text and extracting topic keywords using unsupervised methods. Optionally multiword keyword detection can be enabled by using a pretrained PhraserModel. Spelling mistakes can be automatically corrected by enabling SpellCorrector.

⚙️ Installation Guide

Click to expand

Preparing the Environment

1. Set Up Your Python Environment
   Ensure you have Python 3.10 or above installed.

2. Install Required Dependencies
   Install the required dependencies using:

   pip install -r requirements.txt
   

Installation via PyPI

1. Install the Package
   You can install the package using:

   pip install rara-subject-indexer
   

📚 Documentation

Click to expand

Documentation can be found here.

📝 Testing

Click to expand

Run the test suite:

python -m pytest -v tests