Joseph Catanzarite's repositories
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.
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.
kaggle-Avazu-Clickthrough-Rate-Prediction
Python kernels for exploratory data analysis, feature engineering, modeling and evaluation, using two different approaches: gradient boosting machines with LightGBM, and logistic regression.
fastai_notebooks
Experiments with fastai
Logistic-Regression
The Logic of Logistic Regression: A Tutorial
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.
Data-Exercise
A brief exercise in exploratory data analysis and modeling
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
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.
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.
good_wines_bad_wines
classifying wines with machine learning
gradient_boosting_regression
In this notebook, we'll build from scratch a gradient boosted trees regression model that includes a learning rate hyperparameter, and then use it to fit a noisy nonlinear function.
causalML
A course on causal machine learning.
course-nlp
A Code-First Introduction to NLP course
course-v4-working
a sandbox to play with the notebooks
e2e-ml-app-pytorch
🚀 An end-to-end ML applications using PyTorhc, W&B, FastAPI, Docker, Streamlit and Heroku → https://e2e-ml-app-pytorch.herokuapp.com/ (may take few minutes to spin up occasionally).
MakeIntensiveJan2021
Materials for MakeIntensive January 2021
malaria-imaging-investigation
Investigative data science/machine learning guided tutorial on Kaggle malaria imaging dataset.
modern-slavery-statements-research
A collection of resources and inquiries advancing the research on modern slavery statements published by global commercial organisations
scientific-visualization-book
An open access book on scientific visualization using python and matplotlib
utilities
utility notebooks