Project Overview

The real estate market is an ever-present feature of our lives, and beneath the surface is a rich source of economic factors that make it tick. It is, therefore, a highly important topic, which is interwoven with data elements, that affects all people from the CEO of a Fortune 500 company to your average home-owner. It is with this knowledge that we explore the United States Real Estate Market wiht the hopes of bringing insight into how the market has functioned in the past and continues through the present and into the future.

Exploration Questions:

  1. Does GDP effect the real estate market?
  2. How do home prices change with inflation?
  3. Is unemployment correlated with the performance of the real estate market?
  4. What geographies have been the most affected by fluctations in market factors?
  5. What periods of time have seen the most abnormalities?
  6. How can this information empower homeowners and prospective homeowners?

Real Estate Basics

Data Sources and Data Journey

Please see the links below to access our data sources:

Economic Factors that influence the Economy: Dataset Link

Home Price Values from Zillow Research(Select 'All Homes' under data type and 'State' under Geography): Dataset Link

Our Data Journey

We were able to find two robust csv datasets from 'Kaggle' and 'Zillow'. The former shows different economic metrics that are useful for analyzing the real estate market, and the latter shows home prices over time for each state.

The economic factors data come in a separate csv file for each metric with corresponding dates. After reading the data from each csv into python, a data frame was created from each and, subsequently merged by the common column of 'Date'. Also, the csvs have different dates, leaving some areas blank for different years. The merged data frame was shortened to 1987 to 2023 so that all columns had data. It appears some data was not collected for every date, but this did not impact our visualizations and was ignored. This dataframe was used for our plotly express macro trend visualizations.

The second data set included a date column, a column for each state, and values for home prices. The data we selected covers 2019-2023, as we aimed at focusing on current events. In order to make a dataframe with a date column, one state column with values of the State's name, and the home price, we utilized the pandas.melt to reorganize the dataframe with the shared column of 'Date'. By doing this, each row has a date, a state name, and it's the home price of that state at that date. This dataframe was used for our plotly express geographical visualizations.

Project Walkthrough and Code Overview

For a more in depth code walkthrough, please watch this video. See how we created dataframes, manipulted and cleaned data, created visualizations and more!

The video to the left is intended for a layperson to understand the coding aspects of this project. Please watch and learn more about how we analyzed our data.