bike

machine learning on bike sharing data data and description from https://archive.ics.uci.edu/ml/datasets/Bike+Sharing+Dataset

Setup

git clone https://github.com/mar-volk/bike

conda env create --file environment.yml
conda install pytorch torchvision cudatoolkit=10.0 -c pytorch

copy the raw data from above mentioned website (i.e. day.csv, hour.csv) to data/raw/.

Usage

conda env update --file environment.yml
source activate bike
jupyter notebook

Run "src/prep/train_val_test_split.py" to prepare splitted, production-like data.