Publications by Michael Ippolito

CUNY - DATA607 - Project4

Project 4 - Spam/Ham Classification Overview The assignment was to use a set of email messages and build a classifier to separate them into spam or ham. I used a set of messages from Kaggle (Wessel van Lit, https://www.kaggle.com/veleon/ham-and-spam-dataset, 2019). I used a manual Bayesian model to gain a better understanding of how the process ...

2112 sym R (14786 sym/17 pcs) 5 img

SPWG Sentiment Analysis

Assignment 10 - Tidytext Scrape data I wrote a python script to convert each writer’s docx files into plain text. Then I iterated through each writer’s directory, which contained folders for each book he or she has written. Each book’s containing folder holds a series of sections, which roughly correspond to chapters. This code reads those...

2840 sym R (15653 sym/40 pcs) 16 img

CUNY - Data607 - Assignment11

Assignment 11 - Recommender Systems Overview Sweetwater.com is a site that caters to musicians, producers, performers, and studio engineers, offering a huge catalogue of music-related products for both production and performance. My approach to this assignment was as follows: Perform a scenario design analysis. Discern how the recommender syste...

4963 sym R (3300 sym/4 pcs) 5 img 2 tbl