Models accompanying the publicaton doi: https://doi.org/10.1016/j.envpol.2020.114587
Applying Machine Learning Methods to better understand, model and estimate mass concentrations of traffic-related pollutants at a typical street canyon
.
├── data # Data for modelling
├── results # Results
├── scripts # Automated tests and run as .py
├── src # Source, models, tools, utilities
├── LICENSE
└── README.md
The code is set up as follows:
src
has all the modules necessary for modelling
src/config.py
has the configurations used bysrc/models.py
src/preprocessing.py
is used bysrc/models.py
to preprocess the data partiallysrc/feat_utils.py
has some supporting functions and datascripts/run.py
is the script for running the code
The original data can be downloaded from: https://zenodo.org/record/3694131
A preprocessed and imputed data files is present in the "data" folder
data/preprocessed.csv
|
For running the script, a conda environment is recommended (or other Python distributions).
Conda installation:
https://docs.conda.io/projects/conda/en/latest/user-guide/install/
Once Conda is installed the environment for running this script can be created as follows:
conda create -n envpol python=3.6 scikit-learn=0.22 eli5 numpy pandas
In the scripts
folder, the experiment
python run.py