Source code "Unsupervised Model Personalization while Preserving Privacy and Scalability: An Open Problem." @ CVPR2020

This project demonstrates the use of generic bi-directional LSTM models for predicting importance of words in a spoken dialgoue for understanding its meaning. The model operates on human-annotated corpus of word importance for its training and evaluation. The corpus can be downloaded from: http://latlab.ist.rit.edu/lrec2018

storage for thoughts, notes, etc.

Workflow to generate interactive html feature selection report for longitudinal and cross-sectional microbiome studies

Thesis titled "Geospatial Semantic Pattern Recognition in Volunteered Geographic Data Using the Random forest Algorithm" for the degree of Masters of Spatial Analysis at Ryerson University in 2016

This repository contains the implementation of ITErpretability, a new framework to benchmark treatment effect deep neural network estimators with interpretability. For more details, please read our NeurIPS 2022 paper: 'Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability'.

Code for Master Thesis

Companion code for walkthrough: http://amunategui.github.io/variable-importance-shuffler/

Scraping Rotten Tomatoes to Uncover Hidden Trends

Nonparametric variable importance assessment

An implementation of a decision tree classifier to predict the most present age in each urban area in the data set.

Variable importance through causal inference, with Alan Hubbard

Python module to calculate local variable importance with the global model