K-Means Clustering Suicide Data

Inspiration

We wanted to see what we could do with the data set we found for social good, and decided to try and let the computer find trends for us.

What it does

Our project found clusters in the dataset based on how many we were looking for and the variables we were looking at. We tested suicides per 100k population for the countries that had data for 2014 along with factors such as HDI and GDP per capita.

How I built it

We used Jupyter Notebooks and various Python libraries.

Challenges I ran into

We don't know any machine learning

Accomplishments that I'm proud of

We got a simple unsupervised machine learning method to work with the data and found somewhat cool trends

What I learned

A bunch of python

What's next for K-Means Clustering Suicide Data

Different kinds of data to find some more meaningful trends

Built With

• numpy
• pandas
• python
• scikit-learn