Progress
Currently we are still trying to effectively get the zoobooks for 2015-2025 properly processed and cleaned. We are about 75% of the way there to getting all of them processed and cleaned. We are storing our data on a google sheets. We have also started using Social explorer to get our data about poverty rates of cities in the US.
Problems
Getting the data from each zoobook is challenging and trying to get the data properly processed has been challenging but we still get it done. We want to see if there are any easier ways to properly process the data and clean it.
We are also having some trouble figuring out how we can make thoughtful data visualizations but we can continue out discussions and figure out what data visualizations will give us a good representation of out data. We think that once we get all of our data processed and cleaned a proper data visualization will be decided on.
We won’t change our original plan because the data cleaning is mainly done so we do not need to change our original timeline.
Tools
We are using AI to process out data since it would be way too time consuming to write down every high school and city of each student over the past 10 years. We also got our poverty data from Social Explorer and want to connect it with out zoobook data. We also are going to use Flourish to create data visualizations that will help illustrate Carleton student financial demographics.
Timeline
We will be a little behind in the process of data cleaning but I think that it won’t make us too far behind our proposed timeline as long as we finish data processing within the next couple of days.
- Week 1: Scrap data and clean it(75%)
- Week 2: Create data visualizations
- Week 3: Clean up data visualizations and create our presentation
Personal Message
Reed: I helped figure out how we will implement social explorer within the project with Ngelek. Additionally, I ensured that all deliverables this week successfully followed all instructions and included each required element.
Khizar: I helped look for poverty data on Social Explorer and met with the group to ensure we were making some progress in our project. I also made sure to help with our data analysis so that we would be close to making deadlines.
Dylan: I ensured group communicated about meeting due-dates, and scheduled meeting times given group schedules. Collaborated with team when continuing to do preliminary analysis of data in order to ensure project goals are met and are meaningful.
Ngelek: I helped with data processing using AI and cleaning the data using excel. I now want to try and connect my data to poverty data and make meaningful data analysis.
4 thoughts on “Final Project Update”
Leave a Reply
This site uses Akismet to reduce spam. Learn how your comment data is processed.
The data cleaning sounds like a long process, it makes sense that you’re using AI to help speed that along to still meet the deadlines. That being said, how are you checking the AI’s work for possible errors?
It sounds like you’re making great progress, especially when dealing with such a big amount of data.Once the data is fully cleaned, I’m sure your visualizations will come together naturally. I look forward to seeing how you connect the zoobook data with poverty rates.
Hi! Thank you for your interesting post! Your team is making great progress! Using AI to process zoobook data and integrating Social Explorer for poverty analysis is a solid approach. Since data cleaning is almost done, what criteria will you use to decide on the most effective visualizations? Also, how do you plan to ensure that the connection between zoobook data and poverty rates provides meaningful insights? Looking forward to seeing how Flourish helps illustrate Carleton’s student financial demographics!
Hi! I think your project is very meaningful, and I really appreciate your use of AI to handle large datasets—I’m confident it will be effective! I especially like your idea of combining Zoobooks data with poverty rates from Social Explorer. However, I’m also curious whether you’ve implemented any checking measures to ensure the accuracy of the AI-processed data? Dealing with missing or unclear data is indeed challenging, so good luck in determining the most suitable visualization approach. Overall, this is a fantastic project, and I’m very excited to see your final visualizations!