Skip to main content

Phase 2 Deliverable Individual Response

·383 words·2 mins
Author
Paulo Martinez-Amezaga
I am a rising second year at Northeastern studying Biology & Data Science
Table of Contents

Phase 2 Deliverable
#

I am extremely happy with the progress Sam and I made on the datascience side of the project. We went from just proof that we can call our apis. To saving, cleaning, and merging the datsets. As well as performing meaningful EDA for all our data.

Personally, I worked on the GINI Index Data, as well as the Longterm Interest Rate Data and Unemployment Data.

My biggest challenge was creating the Megaframe. Our biggest challenge was merging all the individual dataframes as they all had different column names. Once I got that figured out it only got worse. The GINI index was only for 4 specific countries we chose, so we had to add the rest of our GINI index data to a csv then load it into the dataframe. However once we did that, certain countries were missing data in some columns completely and when we cleaned them, it would make our dataframe only three countries. Therefore we decided to just remove those specific countries to have a more complete dataframe. I then just dropped all NaN values and duplicates, and it finally worked. It was super rewarding working on this and I am extremely happy we got it done.

(there were more git commits throughout all of it, but these are the finalized and most meaninful ones)

What I’ve learned in class(Phase 2)
#

Class has been ramping up. I finally learned how linear algebra and differentiation are machine learning. And then I learned how to perform effective EDA, and all the models I’ve been shown in class and the theory behind them. It is extremely fast paced, but working on the project alongside class and immediately applying the theory, has taught me extremely well.

Outside of class(Phase 2)
#

Outside of class has been awesome too. I cannot complain, I have visited Antwerp and just explored a lot more. I have been getting really into photography and have loved taken pictures of everything I have seen. I am excited for more, but this project is really one of the highlights. Although it isn’t easy bonding with my team over this difficult time period, has made some meaningful connections that I seek highly. This makes experiencing stuff outside of class that much more special.