Working with test document data this project will classify documents as spam or non-spam email. A training and validation set will be created and pushed into a decision tree and logistic regression model.

Determine proximity of geo-location data with MTA subway data and NYC public hospitals.

Using the lubridate package within the Tidyverse ensemble, I created examples exploring NYC Filming Permits data.

Example of sentiment analysis from Text Mining book and personal example using NY Times data

The New York Times (NYT), provides access to its data through the Times API. With it, data analysis and visualizations can be performed on trends or decisions made within their published articles.

Focuses on working with different types of files for analysis. I will be manually creating HTML, XML, and JSON formats that store three of my favorite books related to data science and programming.

Compare daily ridership between different modes of transportation against estimated pre-pandemic levels

Determine a frequency chart of which Pokemon fall into which types they are.

Look to see if there is a relationship between the percentage change in employment versus the percentage change in mean hourly wages.

Comparing Kobe Bryant and a simulated player to determine if Kobe had a 'hot hand' or if was he making shots as expected.

The objective is to be able to transform a wide format data structure into a long format where you have 'tidy' the data to perform the analysis easier. The data is flight arrival counts from two airlines in five different cities.

Transform chess tournament text data into CSV

Working with strings and regular expressions

Walt Hickey from FiveThirtyEight collected data from people within the United States to see if a risk-averse person would be more likely to order a steak well done. They found no evidence a person that was a higher risk taker would prefer their steaks rare.