This repository is for my project on analysing and predicting real estate land properties in Lahore.
zameen.com was scraped for all plot holdings in Lahore. The python file for this is All Properties Scrape.pdf
The scrape was saved as a csv file, imported into STATA, and cleaned and prepared for analysis.
The STATA .do file is zameen_allproperties_cleaning.do The STATA dta file with the cleaned dataset is zameen_allproperties_cleaning.dta The cleaned CSV file is zameen_allproperties_scrape_clean.csv
This CSV file was imported back into python and then a predictor was created to try and predict prices based on the other variables. After a predictor was created, the listings were mapped with both real and predicted prices. These maps can be interacted with in the following html file of the python project: Real Estate Data.html
All the graphs are uploaded as pngs.
The presentation with all the analysis and maps is uploaded as Lahore Real Estate Analyis & Predictions.pdf