COVID-19 Survival Project

• 

  Data Tree

• 

  Initial Graphs

• 

  Gender vs Age Graphs

covidSurvivalProject

What Inspired Us

_ Loading Quarantine Log _

█▁▁▁▁▁▁▁▁▁ 10%

███▁▁▁▁▁▁▁ 30%

█████▁▁▁▁▁ 50%

███████▁▁▁ 70%

██████████ 100%

_ Loading Complete _

Quarantine Day: 45 After being stuck inside for so long, many of us have probably wondered whether it was worth risking it all just to get a piece of our normalcy back. We're all probably dying to grab some boba, hit the gym, or even take a walk. Something along the lines of "I'm healthy. I won't catch it" has probably crossed your mind. What if you could know your chances of survival with just two simple questions? Would you take the gamble?

What We Learned As undergraduate students that have recently just started taking upper-division courses, being able to complete a machine learning project seemed far from plausible. Due to continuous efforts, however, each teammate was able to understand reading datasets, training a machine, and being able to write an algorithm that predicted the outcome of how likely someone is to survive COVID-19.

How We Built It We built our project in PyCharm and implemented the following python libraries: pandas, matplotlib, scikit. From visualizing the data, we were able to get a better sense of how the machine was able to learn off of the dataset.

Challenges You Faced Some challenges we faced were breaking down pieces of data. For instance, we weren't able to get our machine to learn off of symptoms to aid in the prediction of survival. Another difficulty we faced was the fact that our project had to coded in Python. As UCR students, we're originally taught C++. Although a challenge, we were still able to produce and present something.

Built With

• dataset
• linear-model
• machine-learning
• pandas
• poly-fit
• pycharm
• python