Published July 12, 2022 | Version v1

Data from the paper "Learning to clusterize urban areas: two competitive approaches and an empirical validation"

Description

Data for urban clustering used in the paper "Learning to clusterize urban areas: two competitive approaches and an empirical validation". We release two datasets for urban clustering based on data acquired in Santiago de Chile. The first dataset is computed at the level of urban blocks. The second dataset is computed at the level of individuals using a uniform sample of Santiago inhabitants. Both datasets comprises features based on social characteristics (e.g., SES), land use, and aesthetic visual perception of the city. The features of each data unit (blocks or individuals) are provided using row packing (each row is a data unit) in CSV files. We release PCA (Principal Components Analysis) features for both datasets.

Files

Data_MinMaxScaler_PCA_block_224.zip

Files (377.1 MB)

Name Size
md5:a699fbb89750778eda9e0e2856489f77
3.3 MB Preview Download
md5:c2b75ebad5a9d5693b4b61ee47ad98d5
373.9 MB Preview Download