This repository contains a few NLP and Clustering analysis of a dataset containing ~6400 Brazilian Ordinary Laws. The Source Code is in a Jupyter Notebook file.
Also, read the Medium Article related with this repository.
Main contents:
-
A PT-BR dataset ready-to-use in folder 📂 data
-
Feature Extraction with TF-IDF and Clustering with K-Means
-
TF-IDF visualizations to better data understanding
-
Creation of informative/visual plots like this:
