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.