Updated electricity dataset and added dataset with exogenous variables.

R/data.R

@@ -1,13 +1,69 @@
-#' Electricity short dataset
+#' Electricity dataset
 #'
-#' Contains prices of different electricity markets
+#' Contains prices of different electricity markets.
 #'
 #' @format ## `electricity`
-#' A data frame with 3,600 rows and 3 columns:
+#' A data frame with 8400 rows and 3 columns:
 #' \describe{
-#'   \item{unique_id}{Unique identifiers of the electricity markets}
-#'   \item{ds}{Date in format YYYY:MM:DD hh:mm:ss}
-#'   \item{y}{Price for the given market and date}
+#'   \item{unique_id}{Unique identifiers of the electricity markets.}
+#'   \item{ds}{Date in format YYYY:MM:DD hh:mm:ss.}
+#'   \item{y}{Price for the given market and date.}
 #' }
 #' @source <https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/electricity-short.csv>
 "electricity"
+#'
+#' Electricity dataset with exogenous variables
+#'
+#' Contains prices of different electricity markets with exogenous variables.
+#'
+#' @format ## `electricity_exo_vars`
+#' A data frame with 8400 rows and 12 columns:
+#' \describe{
+#'   \item{unique_id}{Unique identifiers of the electricity markets.}
+#'   \item{ds}{Date in format YYYY:MM:DD hh:mm:ss.}
+#'   \item{y}{Price for the given market and date.}
+#'   \item{Exogenous1}{An external factor influencing prices. For all markets, some form of day-ahead load forecast.}
+#'   \item{Exogenous2}{An external factor influencing prices.
+#'   For "BE" and "FR" markets, the day-ahead generation forecast.
+#'   For "NP", the day-ahead wind generation forecast.
+#'   For "PJM", the day-ahead load forecast in a specific zone.
+#'   For "DE", the aggregated day-ahead wind and solar generation forecasts.
+#'   }
+#'   \item{day_0}{Binary variable indicating weekday.}
+#'   \item{day_1}{Binary variable indicating weekday.}
+#'   \item{day_2}{Binary variable indicating weekday.}
+#'   \item{day_3}{Binary variable indicating weekday.}
+#'   \item{day_4}{Binary variable indicating weekday.}
+#'   \item{day_5}{Binary variable indicating weekday.}
+#'   \item{day_6}{Binary variable indicating weekday.}
+#' }
+#' @source <https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/electricity-short.csv>
+"electricity_exo_vars"
+#'
+#' Future values for the electricity dataset with exogenous variables
+#'
+#' Contains the future values of the exogenous variables of the electricity dataset (24 steps-ahead). To be used with `electricity_exo_vars`.
+#'
+#' @format ## `electricity_future_exo_vars`
+#' A data frame with 120 rows and 11 columns:
+#' \describe{
+#'   \item{unique_id}{Unique identifiers of the electricity markets.}
+#'   \item{ds}{Date in format YYYY:MM:DD hh:mm:ss.}
+#'   \item{Exogenous1}{An external factor influencing prices. For all markets, some form of day-ahead load forecast.}
+#'   \item{Exogenous2}{An external factor influencing prices.
+#'   For "BE" and "FR" markets, the day-ahead generation forecast.
+#'   For "NP", the day-ahead wind generation forecast.
+#'   For "PJM", the day-ahead load forecast in a specific zone.
+#'   For "DE", the aggregated day-ahead wind and solar generation forecasts.
+#'   }
+#'   \item{day_0}{Binary variable indicating weekday.}
+#'   \item{day_1}{Binary variable indicating weekday.}
+#'   \item{day_2}{Binary variable indicating weekday.}
+#'   \item{day_3}{Binary variable indicating weekday.}
+#'   \item{day_4}{Binary variable indicating weekday.}
+#'   \item{day_5}{Binary variable indicating weekday.}
+#'   \item{day_6}{Binary variable indicating weekday.}
+#' }
+#' @source <https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/electricity-short-future-ex-vars.csv>
+"electricity_future_exo_vars"
+

R/validate_exogenous.R

@@ -11,7 +11,8 @@
 #'
 #' @examples
 #' \dontrun{
-#' Download df and X_df from https://docs.nixtla.io/docs/exogenous_variables and then run
+#' df <- nixtlar::electricity_exo_vars
+#' X_df <- nixtlar::electricity_future_exo_vars
 #' .validate_exogenous(df, h=24, X_df)
 #' }
 #'

README.Rmd

@@ -9,7 +9,7 @@ library(httptest2)
 .mockPaths("/tests/mocks")
 start_vignette(dir = "/tests/mocks")
 
-options("TIMEGPT_TOKEN"="dummy_token")
+options("NIXTLA_API_KEY"="dummy_api_key")
 options(digits=7)
 
 knitr::opts_chunk$set(
@@ -54,17 +54,17 @@ library(nixtlar)
 # Load sample dataset 
 df <- nixtlar::electricity # this can also be a tsibble!
 
-# Set TIMEGPT Token 
-nixtlar::nixtla_set_token("TIMEGPT TOKEN")
+# Set API key
+nixtlar::nixtla_set_api_key("Your API here")
 
 # Forecast the next 8 steps using TimeGPT
-fcst <- nixtlar::timegpt_forecast(df, h = 8, id_col = "unique_id", level = c(80,95))
+fcst <- nixtlar::nixtla_client_forecast(df, h = 8, id_col = "unique_id", level = c(80,95))
 
 # Plot TimeGPT forecast 
-nixtlar::timegpt_plot(df, fcst, h = 8, id_col = "unique_id", max_insample_length = 100)
+nixtlar::nixtla_client_plot(df, fcst, h = 8, id_col = "unique_id", max_insample_length = 100)
 ```
 
-Using TimeGPT through `nixtlar` requires a token provided by Nixtla. To see how to obtain it and learn about different ways to set it up, please read the [Get Started](https://nixtla.github.io/nixtlar/articles/get-started.html) guide. Here, you can also find a more detailed explanation of how the forecast and plot functions work.
+Using TimeGPT through `nixtlar` requires an API key provided by Nixtla. To see how to obtain it and learn about different ways to set it up, please read the [Get Started](https://nixtla.github.io/nixtlar/articles/get-started.html) guide. Here, you can also find a more detailed explanation of how the forecast and plot functions work.
 
 ### Main features of `nixtlar`
 

README.md

@@ -44,19 +44,19 @@ library(nixtlar)
 # Load sample dataset 
 df <- nixtlar::electricity # this can also be a tsibble!
 
-# Set TIMEGPT Token 
-nixtlar::nixtla_set_token("TIMEGPT TOKEN")
+# Set API key
+nixtlar::nixtla_set_api_key("Your API here")
 
 # Forecast the next 8 steps using TimeGPT
-fcst <- nixtlar::timegpt_forecast(df, h = 8, id_col = "unique_id", level = c(80,95))
+fcst <- nixtlar::nixtla_client_forecast(df, h = 8, id_col = "unique_id", level = c(80,95))
 
 # Plot TimeGPT forecast 
-nixtlar::timegpt_plot(df, fcst, h = 8, id_col = "unique_id", max_insample_length = 100)
+nixtlar::nixtla_client_plot(df, fcst, h = 8, id_col = "unique_id", max_insample_length = 100)
 ```
 
-Using TimeGPT through `nixtlar` requires a token provided by Nixtla. To
-see how to obtain it and learn about different ways to set it up, please
-read the [Get
+Using TimeGPT through `nixtlar` requires an API key provided by Nixtla.
+To see how to obtain it and learn about different ways to set it up,
+please read the [Get
 Started](https://nixtla.github.io/nixtlar/articles/get-started.html)
 guide. Here, you can also find a more detailed explanation of how the
 forecast and plot functions work.

_pkgdown.yml

@@ -17,7 +17,7 @@ navbar:
       menu:
         - text: "Anomaly Detection"
         - href: articles/anomaly-detection.html
-        - text: "Cross validation"
+        - text: "Cross-Validation"
         - href: articles/cross-validation.html
         - text: "Historical Forecast"
         - href: articles/historical-forecast.html

data-raw/electricity.R

@@ -2,6 +2,5 @@
 # Electricity dataset
 
 electricity <- read.csv("https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/electricity-short.csv")
-electricity$y <- round(electricity$y, 5)
 
 usethis::use_data(electricity, overwrite = TRUE)

data-raw/electricity_exo_vars.R

@@ -0,0 +1,6 @@
+
+## Electricity dataset with exogenous variables
+
+electricity_exo_vars <- read.csv('https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/electricity-short-with-ex-vars.csv')
+
+usethis::use_data(electricity_exo_vars, overwrite = TRUE)

data-raw/electricity_future_exo_vars.R

@@ -0,0 +1,5 @@
+## code to prepare `electricity_future_exo_vars` dataset goes here
+
+electricity_future_exo_vars <- read.csv('https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/electricity-short-future-ex-vars.csv')
+
+usethis::use_data(electricity_future_exo_vars, overwrite = TRUE)