Cohort Analysis Python Packages

pycohortflow

Lightweight Cohort Flow Diagrams built on Matplotlib — with an interactive browser-based generator.

pat2vec

A comprehensive Python package for healthcare data engineering, designed to extract, transform, and feature engineer patient data from CogStack-based electronic health record (EHR) datalakes. It provides tools for cohort building, batch data processing, clinical note analysis, and creating machine learning-ready datasets.

lifestream

The fastest way to make sense of a transaction log.

f27-cohorts

cohorts.py makes generating cohort analysis from raw data a magical experience