Out of this world planetary report

Inspiration

We wanted to look at exoplanets because they can tell us things about how planets and solar systems work (including our own) and because the search for potential life outside our system relies on plants for that life to live on.

What it does

Our project uses data from NASA and exoplanets.eu to find and highlight trends around exoplanets and the human search for them through visualizations. It also uses the same data to train a machine learning algorithm to predict whether or not a system is likely to have a planet in its habitable zone.

How we built it

We used the Seaborn python library to create our visualizations and the sklearn library to make our machine learning model. We also used the Pandas library to hold and access our data sets.

Challenges we ran into

Making the visualizations legible was an ongoing challenge throughout the process. We did a lot of refining and experimentation. We also ended up having to synthesize data on star luminosity in order to calculate the habitable zones of stars so we could train our machine learning model.

Accomplishments that we're proud of

We are very happy with the final product that we created. We feel we have done well to answer the questions we set out with at the beginning of this project.

What we learned

On top of demonstrating and further honing our skills in computer programming for data science, we all learned some neat things about the universe and those balls of stuff that hang around the stars in it which sometimes (at least once) end up with part of them becoming things that move and ask questions and such.