Policlime

We trained a neural network to predict Canadian federal election results in Quebec based on weather station-derived climate variables, and it gives interesting results!

Comment 2

Our goal was to train a neural network to predict Canadian federal election results in Quebec based on weather station-derived climate variables.

We parsed climatedata.ca weather station data and open.canada.ca election results. We trained a neural network visualized results per election riding.

We increased our data mining, data parsing and neural network training skills and we learned that politics are difficult!

Built With

  • cartopy
  • geopandas
  • geopy
  • jupyter
  • keras
  • python
Share this project:

Updates