Do we need more bikes?

Project in Machine Learning

By Caleb Caulk, Olivia Buhr, Daniel Breki Baldursson, Dániel Veress

We are given a dataset and the goal of predicting whether the number of bikes should be increased or not.

Our tasks:

1. data analysis
2. process the data
3. implement models
   • Logistic regression
   • Discriminant analysis
   • K-nearest neighbor
   • Tree-based methods
   • Boosting
4. tune models
5. test and compare models
6. writing report

Setup (env creation and package install)

python -m venv env

source env/bin/activate

pip install -r requirements.txt

Saving new packages into requirements.txt

pip freeze > requirements.txt