jcatanza's Stars
adam-p/markdown-here
Google Chrome, Firefox, and Thunderbird extension that lets you write email in Markdown and render it before sending.
CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
facebookresearch/fastText
Library for fast text representation and classification.
d2l-ai/d2l-en
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
karpathy/minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
fastai/numerical-linear-algebra
Free online textbook of Jupyter notebooks for fast.ai Computational Linear Algebra course
huggingface/tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
fastai/course-nlp
A Code-First Introduction to NLP course
lilipads/gradient_descent_viz
interactive visualization of 5 popular gradient descent methods with step-by-step illustration and hyperparameter tuning UI
VKCOM/YouTokenToMe
Unsupervised text tokenizer focused on computational efficiency
fastai/fastai_dev
fast.ai early development experiments
oguiza/fastai_extensions
Code you can use jointly with fastai
betanalpha/stan_intro
Draft introduction to probability and inference aimed at the Stan manual.
jcatanza/Fastai-Deep-Learning-From-the-Foundations-TWiML-Study-Group
Review materials for the TWiML Study Group. Contains annotated versions of the original Jupyter noteboooks (look for names like *_jcat.ipynb ), slide decks from weekly Zoom meetups, etc.
jcatanza/Fastai-A-Code-First-Introduction-To-Natural-Language-Processing-TWiML-Study-Group
For the TWiML NLP Study Group. We review the fast.ai course "A Code-First Introduction to Natural Language Processing", created by Rachel Thomas, of The Data Institute | University of San Francisco. This repository contains the original Jupyter notebooks, plus annotated versions (with suffix `_jcat.ipynb`), as well as other materials I am developing for the Study Group, such as slide decks for the weekly Zoom meetups.
elenacuoco/Avazu
Avazu Kaggle competition
christopherburke/KeplerPORTs
Q1-Q16 Kepler Planet Occurrence Rate Tools
Ifeoluwa-hub/Heart-Failure-Prediction-and-Deployment-with-Flask-and-Heroku
Cardiovascular diseases are the number 1 cause of death globally, taking an estimated 17.9 million lives each year, which accounts for 31% of all deaths worlwide. Early detection, and managment of cardiovascular diseases can be a great way to manage the fatality rate associated with cardiovascular diseases, and this is where a machine learning model comes in. For the purpose of predicting the risk of a heart failure in patients, I used the Support Vector Classifier to build a machine learning model, and deployed it using Flask and Heroku
dfm/exopop
Inferring the population of exoplanets
Make-School-Courses/QL-1.1-Quantitative-Reasoning
QL 1.1: Mathematical Thinking and Quantitative Reasoning
jcatanza/fastai_notebooks
Experiments with fastai
jcatanza/Logistic-Regression
The Logic of Logistic Regression: A Tutorial
jcatanza/seattle-911
In this mini data science tutorial our task is to predict reasons for 911 calls, given a fictitious 911 calls database. We'll build and test a Random Forest model using Python and scikit-learn.
mshabram/PyStan_Kepler_Exoplanet_Populations
Developing code to compare Kepler exoplanet candidate occurrence rate calculation methodologies. Incorporating planet radius measurement uncertainty into exoplanet occurrence rate calculations.
jcatanza/COVID-19
Download, plot and explore daily COVID-19 time series data for confirmed cases and deaths, from Johns Hopkins University repository.
jcatanza/Data-Exercise
A brief exercise in exploratory data analysis and modeling
jcatanza/Fastai-Practical-Deep-Learning-For-Coders-TWiML-Study-Group
Annotated, refactored notebooks and other materials created for the Fastai course; also has the original notebooks pulled from Fastai's git repository on 1/07/2020
jcatanza/seattle-911-md-gist
Gist to convert the Jupyter notebook from the seattle-911 repository to a Medium post. Available at https://medium.com/@jcatanz/call-911-ab79e31690f6.
jcatanza/Stan_Kepler_Populations
pyStan Hierarchical Bayesian Model that incorporates planet radius uncertainty into exoplanet occurrence rate calculations. Code prior to Sept 2016 was primarily developed by Joseph Catanzarite.
mshabram/exoplanet_experiments