In this project I focuses on predicting house sale prices in California using supervised machine learning techniques. The model leverages various property features to make accurate price forecasts, aiding buyers, sellers, and real estate professionals in data-driven decision-making.
The following key attributes were selected as input variables for the model:
Area Size: Total land area of the property (in square feet).
Size of Living Space: Usable interior living area (in square feet).
Age of Property: Time since the property was originally constructed.
Zipcode: Location indicator to capture regional price influences.
Number of Bathrooms: Total number of bathrooms in the property.
Number of Bedrooms: Total number of bedrooms.
Total Years of Renovation: Number of years since the last major renovation.
Size of Basement: Basement area (in square feet), if present.
Overall House Grade: An aggregated score representing the construction quality and interior finishes.
To install the libraries used in this project, follow the below steps
pip install numpy
pip install pandas
pip install matplotlib.pyplot
pip install seaborn
pip install pickle
pip intall flask
To run a Flask deployment tests, run the following command
python main.pyTo run a Heroku deployment tests, run the following link
python main.pySteps To Deploy The App:
prepare your dataset:
1. Data Extraction
2. Exploratory Data Analysis(EDA)
3. Feature Engineering
4. Model Building and Tuning
5. Building Flask API
6. Pushing code to Github
7. Connecting to your Heroku account
8. Deploy App