A first look at coal data
I used the 2015 Coal production data from the U.S. Energy Information Administration’s (EIA) as an exercise for regression by random forest.( Note a few differences between classification and regression random forests). The EIA uses the data for coal supply analyses and in short-term modeling efforts, which produce forecasts of coal supply and prices requested by Congress. The forecast data also appear in the Short-Term Energy Outlook and the Annual Energy Outlook.
- Data Source: http://www.eia.gov/coal/data.php#production
- Data Split: (70% 30%)
- Model: Random Forest Regression
- Model evalaution: R^2, Mean Absolute Error, Mean Squared Error, and explained variance score