Dataset: My project is the MOMA archive analysis report. I get a JSON file from MOMA GitHub. It has many different variables, ‘title’, ‘Nationality’, ‘Gender’, ‘medium’, etc. Each class has those variables. Interest: I’m curious about which artist has the most amount of works collected by the MOMA library? What material is the most popular…

Read more →

For this final project, I conducted a sentiment analysis on the top 40 songs from five of my favorite artists – Drake, Ariana Grande, Mariah Carey, Ne-Yo, and Rihanna. A sentiment analysis is the process of determining wether writing is positive, negative, or neutral. I thought that it would be particularly interesting to see how…

Read more →

This project uses publicly available Census Bureau data to explore the correlation between response rate and resource allocation as tied to the decennial U.S. Census and American Community Survey (ACS), with an eye specifically on different populations at the state and then national level. Of course, the process of allocating funds is complex, with many…

Read more →

This project examines data provided by the Columbia University School of Journalism’s Stabile Center for Investigative Journalism. Compelled by the lack of available information on EJKs by the Philippine government, Stabile Center attempted to verify deaths under the anti-drug campaign and released their data and research as a downloadable Microsoft excel files for three cities,…

Read more →

GOALS: To understand the popularity, price stability and premium value of the Adidas Yeezy and Nike Jordan Team Size: 1 Time Frame: 2 weeks Tools: Python, Selenium, MongoDB, Flask, Plotly, (Heroku) My Role: Data Engineering, Data Visualization If the answer is YES; you’re interested in reselling or buying; Here’s the interesting findings in StockX where…

Read more →

This project was done in conjunction with INFO 628 Data Librarianship. It takes the popular science podcast Radiolab and converts the entities mentioned in the podcast to RDF to analyze whether Linked Open Data could be used to connect the general public with scholarly research at the places where they are already accessing it..

Project Description The Project attempts to create maps of three types of restaurants in the New York City based on their price settings. And analyze is based on what reflect on the maps. All the data sources are requested through the Yelp API. The project has two parts: a Python script that makes an API…

Read more →

A visual, and quantitative analysis of Google Vision, Amazon Rekognition, and Human generated tags for the collection highlights of the Metropolitan Musuem of New York. With artificial intelligences’ increasing influence over the way we search for and interpret content in digital domains it can be difficult to dissect where the qualities of labels and associations…

Read more →

“It Seems I Hit the Squirrel Jackpot!” is a project that explores data from the 2018 Squirrel Census of Central Park. Census takers counted every single squirrel in park and recorded a number of observations that, when put together, provide a comprehensive picture of both Central Park’s squirrels and its people. This project, which was…

Read more →

The SAAM API Artists Project extrapolates demographic data from the American Art API in the hopes of illuminating the work of under represented artists. Using the .get request I gathered information from the API (GetSAAMData.py) and transformed it into structured data (SAAMFinal.py). The next step in my project was an attempt to gather ethnicity or…

Read more →