This function retrieves the best run information for a Finn agent after the forecast iteration process is complete.
get_best_agent_run(
agent_info,
full_run_info = FALSE,
parallel_processing = NULL,
num_cores = NULL
)Agent info from set_agent_info()
A logical indicating whether to load all input settings from each run into the final output table
Default of NULL runs no parallel processing and loads each time series forecast one after another. 'local_machine' leverages all cores on current machine Finn is running on. 'spark' runs time series in parallel on a spark cluster in Azure Databricks or Azure Synapse.
Number of cores to use for parallel processing. If NULL, defaults to the number of available cores.
A tibble containing the best run information for the agent.
if (FALSE) { # \dontrun{
# load example data
hist_data <- timetk::m4_monthly %>%
dplyr::filter(date >= "2013-01-01") %>%
dplyr::rename(Date = date) %>%
dplyr::mutate(id = as.character(id))
# set up Finn project
project <- set_project_info(
project_name = "Demo_Project",
combo_variables = c("id"),
target_variable = "value",
date_type = "month"
)
# set up LLM
driver_llm <- ellmer::chat_azure_openai(model = "gpt-4o-mini")
# set up agent info
agent_info <- set_agent_info(
project_info = project,
driver_llm = driver_llm,
input_data = hist_data,
forecast_horizon = 6
)
# run the forecast iteration process
iterate_forecast(
agent_info = agent_info,
max_iter = 3,
weighted_mape_goal = 0.03
)
# get the best run information for the agent
best_run_info <- get_best_agent_run(agent_info = agent_info, full_run_info = TRUE)
} # }