[go: up one dir, main page]

Skip to content

Classifying Travel Mode choice in the Netherlands using KNN, XGBoost, RF and TabNet

Notifications You must be signed in to change notification settings

Wafama/Thesis_Code

Repository files navigation

Thesis

These notebooks are a part of the thesis titled 'Classifying Travel Mode Choice in the Netherlands using Random Forest, XGBoost, K-Nearest Neighbor, and TabNet: Exploring Spatial Lag Features and Explainable AI.

Due to its size exceeding 25MB, the Explainable AI notebook has been compressed into a zip file. Interested readers can access the notebook's contents by downloading this zip file and extracting it to obtain the Python notebook.

The main dataset used in this study (Dutch National Travel Survey) is not shared as it is downloaded with consent. Interested parties can download it from https://ssh.datastations.nl/dataset.xhtml?persistentId=doi:10.17026/SS/BXIK2X with the consent of the administrator (Dans). The other two datasets are freely available for download from the CBS website (https://www.cbs.nl/nl-nl/dossier/nederland-regionaal/geografische-data/wijk-en-buurtkaart-2022 and https://www.cbs.nl/nl-nl/dossier/nederland-regionaal/geografische-data/gegevens-per-postcode).