Projects

explainy is a library for generating machine learning models explanations in Python. It uses methods from Machine Learning Explainability and provides a standardized API to create feature importance explanations for samples. The API is inspired by scikit-learn and has three core methods. explainy comes with four different algorithms to create either global or local and contrastive or non-contrastive model explanations.

💻 Technologies: Python, Machine Learning Explainability, scikit-learn, SHAP, Python Packaging, GitHub Actions

📚 Repository: explainy

📄 Docs: https://explainy.readthedocs.io/en/latest/

MusicFlow is an music recommender API that use the Spotify's API to predict the number of future streams of song using the Spotify audio features and track metadata.

The MusicFlow API uses the personal Spotify streaming history to train a machine learning model that predicts the number of streams for a given song. The training dataset uses number of stream values between 0 and 30.

💻 Technologies: Python, FastAPI, Spotify API, Machine Learning, Docker, AWS Lambda, HTMX, CSS

📚 Repository: music-flow-api

📌 Website: https://musicflow.link/

LyricsTranslator is a Python module that allows you to download lyrics from the popular music lyrics website genius and translate them into a target language of your choice. The module uses the powerful 🤗hugging face library for translation, which provides state-of-the-art performance in natural language processing tasks.

💻 Technologies: Python, NLP, Hugging Face, Genius API

📚 Repository: lyrics-translator

📄 Docs: https://mauroluzzatto.github.io/lyrics-translator/

📌 Website: https://huggingface.co/spaces/maurol/lyrics-translator

This repository contains a TicTacToe-Environment based on the OpenAI Gym module. TicTacToe is a board game, where two players compete to place three stones of their color in parallel (horizontally or vertically) or diagonally to win the game.

💻 Technologies: Python, Reinforcement Learning, OpenAI Gym, Q-Learning

📚 Repository: OpenAI-Gym-TicTacToe-Environment

This repository contains a new method to measure the word ambiguity in legal corpora, based on a word2vec model. The code has been developed to measure the word ambiguity in the written text of opinions by the U.S. Supreme Court and the German Bundesgerichtshof, which are representative courts of the common-law and civil-law court systems.

💻 Technologies: Python, NLP, Text Embeddings, Gensim

📚 Repository: legal-entropy