In this repo we will focus on developping an end-to-end Machine Learning project for real estate using various techniques from Data ingestion ("Webscraping") and Data management by stocking our dataset in a Datalake hosted by Databricks. After acquiring our Dataset we then proceed to the ML part with
- Using Beautifulsoup librairy to webscrap our Dataset from "Craiglist"
- Cleaning & Pre-Processing phase
- Prediction phase using different regression models to forecast the real estate market
- Using Apache Spark for handling our Data and the models we will use to forecast You find further developpement in the work by checking the separate Notebooks one focused on Data analytics with Exploration Data Analysis and Data ingestion, then another notebook which will focus on the prediction side of the real estate.
This work was inspired by the work of "Kris Doenlen" issued in Meduim "https://medium.com/analytics-vidhya/how-to-find-good-apartment-deals-craigslist-f21967420059"