Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://github.com/LIAAD/yake_demo below:

GitHub - LIAAD/yake_demo

This project demonstrates the use of the YAKE (Yet Another Keyword Extractor) algorithm through an interactive Streamlit web application. YAKE is an unsupervised approach for automatic keyword extraction from text documents.

Make sure you are using Python 3.8 or higher.

1. Clone the repository:

   git clone https://github.com/LIAAD/yake_demo.git
   cd yake-streamlit-demo

2. Create a virtual environment (optional but recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install the dependencies:

   pip install -r packages.txt

The application requires the following packages:

• streamlit
• metadata
• yake
• pandas
• numpy
• wordcloud
• matplotlib
• spacy
• rematplotlib

You can install all dependencies using the requirements.txt file.

To run the Streamlit application:

streamlit run streamlit_app.py

The application will open in your default web browser.

The Streamlit application provides:

1. Interactive Parameter Selection:

   • Adjust max ngram size
   • Set deduplication threshold
   • Choose number of keywords to extract
   • Select deduplication algorithm

2. Multiple Visualization Options:

   • Text highlighting of extracted keywords
   • Word cloud generation
   • Tabular display of keywords with scores

3. Sample Texts:

   • Pre-loaded example texts for demonstration
   • Option to input custom text

YAKE (Yet Another Keyword Extractor) is an unsupervised, corpus-independent algorithm for extracting keywords from individual documents. It relies on statistical features such as:

• Term casing
• Term position
• Word frequency
• Word relatedness (contextual co-occurrence)
• Word dispersion across sentences

YAKE does not rely on dictionaries, thesauri, or training corpora, making it applicable to documents in different languages without additional knowledge.

Original paper: Campos, R., Mangaravite, V., Pasquali, A., Jorge, A., Nunes, C., & Jatowt, A. (2018). YAKE! Collection-Independent Automatic Keyword Extractor. Proceedings of ECIR, pp. 806–810. pdf

--demo

• streamlit_app.py: The main Streamlit application file
• packages.txt: Python package dependencies

--pke

• yake.py: pke package for yake

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4