Predicting bike rentals with additional data, multiple models, basic gridsearch and stacking

bike sharing predictions, here’s the interesting stuff you can find inside:

  • Random Forest hyperparameter optimization using GridSearch

  • gathering more weather data using meteostat

  • testing various regression models, KernelRidge, ElasticNet, Lasso, few gradient boosting models, MLP

  • small steps into stacking models:

    • averaging predictions of multiple models

    • using neural network as a meta model

  • plus a few nice visuals

  • feedback always welcome

project on Github

hmm. says the file is too big to upload it to post (4mb limit, well that’s a first!)

I really enjoy your scatter plots… I was struggling to make something as visually appealing, so I hope you don’t mind if I copy some of your visualizations! :smiley:

1 Like