This project was created as part of the [Flatiron School Data Science Fellowship in DC].(https://flatironschool.com/) The fellowships educational material can be found within the class repo. The analysis led me to the question of where demand for solar energy may exist but isn't being met.
The purpose of this project is to explore and better understand statistical modeling using the dataset created by the Standford Deepsolar Project Using the data, I created a classifier to target areas that have at least one solar panel. By looking at the false positive results from the model, we can find areas that meet demand criteria but don't have solar.
- Exploratory Data Analysis
- Data Engineering
- Data Visualization
- Cross-Industry Standard Process for Data Mining
- Modeling
- Logistic Regression
- Python
- Jupyter Notebook
- Anaconda to set up my computer.
- Clone this repo (for help see this tutorial).
- Raw Data is here, you'll need to open the csv and delete the first "," and re-save it before it will work with the code from this repo.
- Now if you'd like to repeat my work find the open the technical notebook and run the cells within.
- If you have questions you can tweet at me @Budsmaterial or reach out here(github) .