Pinned Repositories
AUC_is_all_you_need
Analyzing different ML model comparison metrics
chexpertplusplus
Source implementation and pointer to pre-trained models for Chexpert++, a BERT-based approximation to CheXpert for radiology report labeling.
comprehensive_MTL_EHR
Source code for a comprehensive analysis of MTL over EHR timeseries data.
CWR-GAN
The code for the cycle wasserstein regression generative adversarial network model for semi supervised bi-directional regression.
EventStreamGPT
Dataset and modelling infrastructure for modelling "event streams": sequences of continuous time, multivariate events with complex internal dependencies.
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_Tabular_AutoML
Limited automatic tabular ML pipelines for generic MEDS datasets.
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.
structure_inducing_pre-training
mmcdermott's Repositories
mmcdermott/EventStreamGPT
Dataset and modelling infrastructure for modelling "event streams": sequences of continuous time, multivariate events with complex internal dependencies.
mmcdermott/comprehensive_MTL_EHR
Source code for a comprehensive analysis of MTL over EHR timeseries data.
mmcdermott/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)
mmcdermott/MEDS_transforms
A simple set of MEDS polars-based ETL and transformation functions
mmcdermott/structure_inducing_pre-training
mmcdermott/AUC_is_all_you_need
Analyzing different ML model comparison metrics
mmcdermott/MIMICIV_FMs_public
Sample end-to-end pipeline over MIMIC-IV demonstrating the Event Stream GPT code base.
mmcdermott/MEDS_Tabular_AutoML
Limited automatic tabular ML pipelines for generic MEDS datasets.
mmcdermott/MEDS-DEV
Platform for Inductive Experiments over Medical Data
mmcdermott/nested_ragged_tensors
Utilities for efficiently working with, saving, and loading, collections of connected nested ragged tensors in PyTorch
mmcdermott/rc_files
RC Files
mmcdermott/gpt4_prompts
Prompts and recipes for GPT-4 usage for academics
mmcdermott/Medical_T0pp
For assessing T0pp's medical abilities
mmcdermott/MEDS_pytorch_dataset
A template PyTorch dataset for structured data in the MEDS format. Best paired with https://github.com/mmcdermott/MEDS_polars_functions
mmcdermott/MEDS_TAB_MIMIC_IV
Auto Tabularization for MIMIC-IV
mmcdermott/ML_mixins
Useful Python Mixins for ML
mmcdermott/pytorch_lognormal_mixture
An easily installable version of the PyTorch Lognormal Mixture Model from https://github.com/shchur/ifl-tpp
mmcdermott/MEDS_TAB_EICU
mmcdermott/arXiv_scan
Search through arXiv via LLMs and simpler tools for instances of a claim being made
mmcdermott/bigtree
Tree Implementation and Methods for Python, integrated with list, dictionary, pandas and polars DataFrame.
mmcdermott/datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
mmcdermott/df_parser_matcher
A simple library for a safe, expressive, config-file friendly, and readable DSL for encoding simple dataframe operations.
mmcdermott/hydra
Hydra is a framework for elegantly configuring complex applications
mmcdermott/hydra_profiler
A simple package to help profile hydra jobs via a simple config modification.
mmcdermott/ifl-tpp
Implementation of "Intensity-Free Learning of Temporal Point Processes" (Spotlight @ ICLR 2020)
mmcdermott/MEDS_TPPs
ESGPT style temporal point process transformers for generative modeling (and relatedly for supervised training) over MEDS or event-stream style data.
mmcdermott/polars
Fast multi-threaded, hybrid-out-of-core DataFrame library in Rust | Python | Node.js
mmcdermott/synthetic_models
Utilities for generating synthetic scores and labels given target performance characteristics
mmcdermott/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
mmcdermott/useful_hydra_resolvers
A collection of useful Hydra (hydra.cc) resolvers for building CLI applications