Description Usage Arguments Details See Also Examples
View source: R/retrofit_controller.R
This function filters for model with lowest CV-RMSE value given a nested list of model result.
1 2 | best_worst_model(inter_result, bdbid = NA, energy, fiscal_year = NA,
n = NA, prepost = 1)
|
inter_result |
A list containing information about parameters such as slopes, change-points, and stats such as RMSE. |
bdbid |
Building id, which identifies the building or the dataset. Defaults to |
energy |
A character string. Energy Type, either 'Elec' or 'Fuel'. |
fiscal_year |
Fiscal year. Defaults to |
n |
number of observed points (independent variable) in utility data frame of a building. Defaults to |
prepost |
A numeric value. Defaults to be 1. This indicates if it is unretrofit or retrofit (pre or post). See |
If some models pass all of shape test, t-test, and population test but do not meet threshold CV-RMSE, the model will the lowest CV-RMSE will be selected as the best model. If none of the model passes all of shape test, t-test, and population test, it will return NULL
.
main_best_model_func
, run_model
, and run_model_retrofit
1 2 3 4 5 6 | ## Not run:
retrofit_util = subset(retrofit_utility, retrofit_utility$bdbid == 846152
& retrofit_utility$energy_type == 'Elec') #retrofit data
retrofit_result = run_model_retrofit(retrofit_util)
retrofit_best_result = best_worst_model(retrofit_result$post, bdbid = 846152, 'Elec', prepost = 3)
## End(Not run)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.