2bornot2b

Codes for the 'To be or what to be' Hacker Rank challenge. The goal is to predict the forms of the 'be' verb in a text.

algorithms

Solutions to the exercises of the Algorithms Coursera specialization by Stanford (https://www.coursera.org/specializations/algorithms)

aws_scripts

AWS server interaction bash scripts.

bees

Driven data bees classifier competition codes.

bnboost

datascribe

General csv files datasets exploration scripts and python utils.

docker-ubuntu-nlp

Dockerfile for the creation of an Ubuntu image with Python and the main natural language processing librairies.

dumbdumb

Dummy FastAPI API deployed with fly.io for testing

focus

Machine Learning model API providing predictions AND explanations

food4thought

Find strength and weaknesses of restaurants with the Yelp dataset.

gensim-data

Data repository for pretrained NLP models and NLP corpora.

labor-prediction

Predict delivery day likelihoods based on public data for the US.

nkthiebaut

nkthiebaut.github.io

nolearn

Abstractions around neural net libraries, most notably Lasagne.

obsidian-spaced-repetition

Fight the forgetting curve by reviewing flashcards & entire notes on Obsidian.md

pycharm-settings

PyCharm shared settings.

readthedocs.org

The source code that powers readthedocs.org

reinforcement-learning-lecture-notes

Lecture notes on reinforcement learning

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

serverless-template-gptj

serverless-template-stable-diffusion

Stable Diffusion v2.0 optimized for banana.dev

shap

A game theoretic approach to explain the output of any machine learning model.

sphinx

Main repository for the Sphinx documentation builder

template

Python package template with setup,readme and .gitignore files, as well as defined tree structure

zeugma

📝Natural language processing (NLP) utils: word embeddings (Word2Vec, GloVe, FastText, ...) and preprocessing transformers, compatible with scikit-learn Pipelines. 🛠