Please join us on October 21 for the next installment in the SCHARE Think-a-Thon series, where we will present Machine Learning with Python Libraries: From Data to Model Development.
This webinar, which will take place 2:00–4:30 p.m. Eastern Time, builds on the Python and data analysis skills developed in previous Think-a-Thons and introduces participants to Python libraries for machine learning and model development. Through a hands-on, research-focused example, participants will use scikit-learn and imbalanced-learn to prepare and engineer features, build predictive models, address imbalanced outcomes, validate and tune models, and combine these steps into reproducible machine learning pipelines. Participants will also explore feature importance and learn to generate synthetic data for model development and scalability testing, while considering the limitations of synthetic data in population health research.
Attendees will learn how to use Python libraries and code to:
- Understand the core concepts behind machine learning models
- Prepare and engineer features for machine learning using pandas and scikit-learn, including transformations and preprocessing of numerical and categorical variables
- Build predictive models with scikit-learn, progressing from Logistic Regression and Decision Trees to Random Forests
- Address imbalanced outcomes using imbalanced-learn and explore SMOTE as one approach for generating synthetic minority-class observations
- Generate and examine synthetic datasets for model development, workflow testing, and scalability experiments while recognizing their limitations
Registration Link: October registration link