Matthew McDermott's repositories
EventStreamGPT
Dataset and modelling infrastructure for modelling "event streams": sequences of continuous time, multivariate events with complex internal dependencies.
comprehensive_MTL_EHR
Source code for a comprehensive analysis of MTL over EHR timeseries data.
How-to-PhD
A collection of resources and information for concrete skills that are helpful when pursuing a PhD in computer science (specifically in ML/AI or related disciplines)
MEDS_transforms
A simple set of MEDS polars-based ETL and transformation functions
MIMICIV_FMs_public
Sample end-to-end pipeline over MIMIC-IV demonstrating the Event Stream GPT code base.
AUC_is_all_you_need
Analyzing different ML model comparison metrics
MEDS_Tabular_AutoML
Limited automatic tabular ML pipelines for generic MEDS datasets.
nested_ragged_tensors
Utilities for efficiently working with, saving, and loading, collections of connected nested ragged tensors in PyTorch
Medical_T0pp
For assessing T0pp's medical abilities
MEDS_pytorch_dataset
A template PyTorch dataset for structured data in the MEDS format. Best paired with https://github.com/mmcdermott/MEDS_polars_functions
MEDS_TAB_MIMIC_IV
Auto Tabularization for MIMIC-IV
pytorch_lognormal_mixture
An easily installable version of the PyTorch Lognormal Mixture Model from https://github.com/shchur/ifl-tpp
arXiv_scan
Search through arXiv via LLMs and simpler tools for instances of a claim being made
bigtree
Tree Implementation and Methods for Python, integrated with list, dictionary, pandas and polars DataFrame.
df_parser_matcher
A simple library for a safe, expressive, config-file friendly, and readable DSL for encoding simple dataframe operations.
gene_expression_modelling_public
Public version of Gene Expression Modelling Utilities referenced in https://github.com/mmcdermott/cnn_graph/blob/master/dx_and_drug_classification.ipynb
gpt4_prompts
Prompts and recipes for GPT-4 usage for academics
hydra_profiler
A simple package to help profile hydra jobs via a simple config modification.
synthetic_models
Utilities for generating synthetic scores and labels given target performance characteristics
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
useful_hydra_resolvers
A collection of useful Hydra (hydra.cc) resolvers for building CLI applications