Data Science: A Scenic Date

SageMaker Jumpstart

My experience with Sageamker Jumpstart

Pipelines

Building custom preprocessing pipelines in scikit-learn

Small Molecule Drugs

Predicting FDA approval of small molecule drugs

Gangsta Score

Exploring Rap & Country music lyrics

Breast Cancer Survival

Predicting 5-year survival in breast cancer patients

Panda Tricks: Self-Joins

Self-join to extract information from two columns

NFL Elo Ranking

Predicting NFL Elo Rankings

Panda Tricks: Resampling

Resampling to align differentially-sampled time series data

NYC MTA Turnstile Data

Analyzing New York City's MTA turnstile data