This is a case study to help better understand the Melbourne property market and to explore factors that influence on pricing of real estate. This repository contains python scripts using pandas, numpy, matplotlib, seaborn, pyplot, quandl, statsmodels, and scklearn libraries to conduct exploratory, regression, clustering, and time-series analysis on the data sets.
-
Project Information document contains information about the data source, cleaning procedures executed, data profile, and initial questions to explore within the analysis.
-
Scripts folder contains python scripts on data cleaning, exploratory visual analysis, linear regression analysis, k-means cluster analysis, and time-series analysis.
-
Sent to client folder contains the final deliverable presented in Tableau Storyboard detailing the analysis, results, and next steps.
Following open source data sets were used to carry out this project:
- Melbourne House Prices - It contains data including the sold date, property location, property type, sold price, distance from CBD, property size, number of bedrooms, bathrooms, and car spaces.
- Melbourne.geojson - It contains the Melbourne Suburbs GPS coordinates.
Citation: “Melbourne House Prices 2018”, Accessed from https://www.kaggle.com/datasets/mihirhalai/sydney-house-prices. “Melbourne.geojson 2015”, Accessed from https://github.com/codeforgermany/click_that_hood/blob/main/public/data/melbourne.geojson.
Python: 3.9.7
Amy Yip