README: We have separated our code into separate notebooks to make things clearer for us, and hopefully for you. In this document we will outline what each notebook does. All code is documented, and we recommend you view our code in this order. California Data Exploration: Generates statistics from our wildfire dataset. Look here for visuals about our data before it was modeled. https://colab.research.google.com/drive/1rcAXrRVPpQEpInkBP9SiDRKULKBUVfys?usp=sharing Wildfire Preprocessing: Generates the output data for the machine learning models from wildfire dataset. Filters out incomplete data, divides fires into regions, determines number of fires each month in each region, and the total acreage burned each month in each region. These data are then fed into a classification method that ranks them 0-4 based on severity. This is the output data for our ML models. https://colab.research.google.com/drive/1akSOTcN5-izCLXW2goItoN_ct4Ec7wTI?usp=sharing Weather Preprocessing: Generates the input data for the machine learning models from the weather dataset. Filters out incomplete data, divides weather into regions, determines averages for temperature and precipitation over the past three months for each month for each region. This is the input data for our ML models. https://colab.research.google.com/drive/1bswqCdNeJrgfCVVBSD-AqI-dg_OIMhLb?usp=sharing Neural Network: This is the code for our neural network model. It takes the input and output generated by Wildfire Preprocessing and Weather Preprocessing. https://colab.research.google.com/drive/1-L_200hQHZB5HGObcbCsC6ojIE6JmIO2?usp=sharing Regression Models: This is the code for our regression models. They take the input and output generated by Wildfire Preprocessing and Weather Preprocessing. https://colab.research.google.com/drive/1rcAXrRVPpQEpInkBP9SiDRKULKBUVfys?usp=sharing