Analysis in Educational Data

Executive Summary Objective: Over the past few days, I've engaged with ChatGPT to gain insights into various topics, especially data processing, coding, and a deep dive into the HMDA dataset.

Data Analysis & Manipulation:

I learned how to perform intricate operations on Python dictionaries, like merging and iterating. I mastered the extraction of specific data fields from a JSON structure. I delved into the details of the HMDA dataset, focusing on mortgage rates, amounts, and denials. Datathon:

I participated in a Datathon this weekend and turned to ChatGPT for assistance and insights. I formulated concise talking points based on my weekend learnings. I also identified potential roadblocks and challenges I faced during the Datathon. Visual Representation:

I explored creating informative graphs using Python's Pandas and Seaborn libraries, specifically for the HMDA dataset. My visualizations concentrated on mortgage amounts, mortgage rates by loan type, denials by applicant sex, and population demographics across districts. Technical Inquiries:

I sought clarity on harnessing GPU capabilities and the potential for allocating VRAM. I also inquired about multi-threading and the possibility of increasing threads per worker. This summary captures the essence of my engagements and learnings with ChatGPT over the last couple of days.

Built With

• ai
• python