Published: 17-01-2021| Version 1 | DOI: 10.17632/bjt77zr55c.1
Edgar Avalos Gauna


This repository contains data used for the "A gentrification study on Mexico City’s neighborhoods using different machine learning classification techniques" paper The data used comes from a variety of sources, all sources underwent through a heavy process of pre-processing. Firstly, it was necessary to match the different tables in terms of having the same geographical location. Then a manual features selection was carried out to retain only relevant attributes for this study. Features such as the name of the neighborhood among others were discarded. Also, features with missing values from one year to other were removed. The final dataset comprises of 1451 records corresponding to the number of neighborhoods in Mexico City. Each record accounts for 37 features as principal descriptors.


Steps to reproduce

Source -> Observations -> Records -> Features Inventario Nacional de Viviendas 2016: National inventory of living quarters, 64281, 3 Censo de Poblaciónn y Vivienda: National census in Mexico made by INEGI, 63239, 195 SCINCE: System to query the census information, 1816 237 DENUE: National directory of economic activities, 452347 41 Softec: Private database with information 10202 108 regarding the cost of the square meter. Shapefiles: Different shapefiles for the geographical 58227 10 units in Mexico City