nixtla_client_historic: Sequential version of 'nixtla_client_historic' This is a...

In nixtlar: A Software Development Kit for 'Nixtla''s 'TimeGPT'

Sequential version of 'nixtla_client_historic' This is a private function of 'nixtlar'

Description

Sequential version of 'nixtla_client_historic' This is a private function of 'nixtlar'

Usage

nixtla_client_historic(
  df,
  freq = NULL,
  id_col = NULL,
  time_col = "ds",
  target_col = "y",
  level = NULL,
  quantiles = NULL,
  finetune_steps = 0,
  finetune_loss = "default",
  clean_ex_first = TRUE,
  model = "timegpt-1"
)

Arguments

df	A tsibble or a data frame with time series data.
freq	Frequency of the data.
id_col	Column that identifies each series.
time_col	Column that identifies each timestep.
target_col	Column that contains the target variable.
level	The confidence levels (0-100) for the prediction intervals.
quantiles	Quantiles to forecast. Should be between 0 and 1.
finetune_steps	Number of steps used to finetune 'TimeGPT' in the new data.
finetune_loss	Loss function to use for finetuning. Options are: "default", "mae", "mse", "rmse", "mape", and "smape".
clean_ex_first	Clean exogenous signal before making the forecasts using 'TimeGPT'.
model	Model to use, either "timegpt-1" or "timegpt-1-long-horizon". Use "timegpt-1-long-horizon" if you want to forecast more than one seasonal period given the frequency of the data.

Value

'TimeGPT”s forecast for the in-sample period.

Examples

## Not run: 
  nixtlar::nixtla_set_api_key("YOUR_API_KEY")
  df <- nixtlar::electricity
  fcst <- nixtlar::nixtla_client_historic(df, id_col="unique_id", level=c(80,95))

## End(Not run)

nixtlar documentation built on Oct. 30, 2024, 5:07 p.m.