In this post, I combine network analysis, topic modeling, and the psychology of extremism to uncover insights from the pro-ISIS Twitter network.

In this post, I develop 3 recommendation systems for restaurants based on item-based filtering, collaborative filtering, and market basket analysis.

In this post, I create and visualize 3 cohort analyses on a retail dataset to better understand the purchasing patterns and trends of users.

In this post, I explore trends between Myers-Briggs Personality Type Indicator (MBTI) personalities, use wordclouds to visualize common words for each personality type, and explore implications of text style transfer.

In this post, I implement a neural style transfer algorithm on my professional headshot and use NumPy docstrings to document each function that I use along the way.

In this post, I tackle Prudential's life insurance classification dataset and deanonymize the likely 8 health classes that were given.

In this post, I scrape lyrics from lyrics.com and generate fake lyrics for the Red Hot Chili Peppers.

This blog post shows my exploration of traffic patterns in Travis County. I use a dataset of traffic incidents from data.austintexas.gov and folium to create several maps as well as animated heatmaps of traffic to unearth patterns in accidents where I live.

In this post, I tell a classic story of selection bias, explain the significance to data science, and suggest methods to prevent selection bias in data science.

In this post, I show my entire process for my submission to the Kaggle competition for predicting house prices. I explore 80 variables to understand the Ames Housing dataset and use gradient boosting to predict sales prices.