Clustering Project Read Me
The Purpose of this project was to find what the biggest driver of log error was, and how to predict it
- The tax value and location would be signifigant factors in log error
- The amount of people per county would determine how accurate the zestimate was, thus predicting log error
Using a SQL query/ csv file to gather the data
Cleaning and filtering the data
Finding features and graphs that find corrolation
Creating a model that would accuratly predict log error
- env.py
- acquire.py
- prepare.py
- explore.py
- model.py
- split_scale.py
- working_notebook.ipynb
- david_explore.ipynb
- working_notebook.ipynb