In this project, boston housing pricing dataset which was collected in 1978 is used. It uses some basic machine learning concepts. Firstly, the project explores the important features of the dataset. Secondly, the data is split into training and testing subsets. Then, a suitable performance metric is used to evaluate our model.
In this project, various performance graphs are used to analyze our learning algorithm. The final test of this optimal model is made on a new sample and predicted prizes are then compared to our statistical values.
This project uses the following software and Python libraries:
The project is built in an iPython notebook and a notebook application such as 'iPython' or 'Jupyter Notebook' is required for running the project. To run the project, open the '.ipynb' file with a notebook application and run all the cells. The analysis of the dataset can also be seen in the '.html' file without actually running the project.