Fixed CRAN dependencies

DESCRIPTION

@@ -1,49 +1,57 @@
-Package: gratis
 Type: Package
-Title: Generating Time Series with Diverse and Controllable Characteristics
+Package: gratis
+Title: Generating Time Series with Diverse and Controllable
+    Characteristics
 Version: 1.0.5
 Authors@R: c(
-    person("Yanfei", "Kang", role = c("aut"), email = "yanfeikang@buaa.edu.cn", comment = c(ORCID = "0000-0001-8769-6650")),
-    person("Feng", "Li", role = c("aut", "cre"), email = "feng.li@cufe.edu.cn", comment = c(ORCID = "0000-0002-4248-9778")),
-    person("Rob", "Hyndman", role = c("aut"), email = "rob.hyndman@monash.edu", comment = c(ORCID = "0000-0002-2140-5352")),
-    person("Mitchell", "O'Hara-Wild", role = "ctb", email = "mail@mitchelloharawild.com", comment = c(ORCID = "0000-0001-6729-7695")),
-    person("Bocong", "Zhao", role = "ctb", email = "bocongzhao@163.com", comment = c(ORCID = "0000-0001-8434-9047"))
-    )
-Description:
-  Generates synthetic time series based on various univariate time series models
-  including MAR and ARIMA processes. Kang, Y., Hyndman, R.J., Li, F.(2020) <doi:10.1002/sam.11461>.
-LazyLoad: yes
-Repository: CRAN
+    person("Yanfei", "Kang", , "yanfeikang@buaa.edu.cn", role = "aut",
+           comment = c(ORCID = "0000-0001-8769-6650")),
+    person("Feng", "Li", , "feng.li@cufe.edu.cn", role = c("aut", "cre"),
+           comment = c(ORCID = "0000-0002-4248-9778")),
+    person("Rob", "Hyndman", , "rob.hyndman@monash.edu", role = "aut",
+           comment = c(ORCID = "0000-0002-2140-5352")),
+    person("Mitchell", "O'Hara-Wild", , "mail@mitchelloharawild.com", role = "ctb",
+           comment = c(ORCID = "0000-0001-6729-7695")),
+    person("Bocong", "Zhao", , "bocongzhao@163.com", role = "ctb",
+           comment = c(ORCID = "0000-0001-8434-9047"))
+  )
+Description: Generates synthetic time series based on various univariate
+    time series models including MAR and ARIMA processes. Kang, Y.,
+    Hyndman, R.J., Li, F.(2020) <doi:10.1002/sam.11461>.
+License: GPL-3
 URL: https://github.com/ykang/gratis
 BugReports: https://github.com/ykang/gratis/issues/
-Depends: R (>= 3.5.0)
+Depends:
+    R (>= 3.5.0)
 Imports:
-  doRNG,
-  dplyr,
-  foreach,
-  forecast (>= 8.16),
-  GA,
-  generics,
-  magrittr,
-  methods,
-  mvtnorm,
-  polynom,
-  purrr,
-  stats,
-  tibble,
-  tsfeatures,
-  tsibble,
-  utils,
-  shiny
+    doRNG,
+    dplyr,
+    feasts,
+    fGarch,
+    foreach,
+    forecast (>= 8.16),
+    GA,
+    generics,
+    magrittr,
+    methods,
+    mvtnorm,
+    polynom,
+    purrr,
+    shiny,
+    stats,
+    tibble,
+    tsfeatures,
+    tsibble,
+    utils
 Suggests:
-  feasts,
-  fGarch,
-  knitr,
-  rmarkdown,
-  rlang,
-  shinydashboard
-NeedsCompilation: no
-License: GPL-3
+    knitr,
+    rlang,
+    rmarkdown,
+    shinydashboard
+VignetteBuilder:
+    knitr
 Encoding: UTF-8
-RoxygenNote: 7.2.3
-VignetteBuilder: knitr
+LazyLoad: yes
+NeedsCompilation: no
+Repository: CRAN
+RoxygenNote: 7.3.1

NAMESPACE

@@ -18,6 +18,8 @@ export(pi_coefficients)
 export(rmixnorm)
 export(rmixnorm_ts)
 export(simulate_target)
+import(fGarch)
+import(feasts)
 import(shiny)
 importFrom(GA,ga)
 importFrom(GA,gaControl)

R/arima_model.R

@@ -220,11 +220,11 @@ pi_coefficients <- function(ar = 0, d = 0L, ma = 0, sar = 0, D = 0L, sma = 0, m
   }
 
   n <- 500L
-  theta <- -c(coef(ma * sma))[-1]
+  theta <- -c(stats::coef(ma * sma))[-1]
   if (length(theta) == 0L) {
     theta <- 0
   }
-  phi <- -c(coef(ar * sar)[-1], numeric(n))
+  phi <- -c(stats::coef(ar * sar)[-1], numeric(n))
   q <- length(theta)
   pie <- c(numeric(q), 1, numeric(n))
   for (j in seq(n)) {

R/gratis-package.R

@@ -23,12 +23,11 @@
 #' @importFrom GA startParallel garun
 #' @importFrom tsfeatures tsfeatures
 #' @importFrom doRNG "%dorng%"
+#' @import fGarch
 #' @import shiny
+#' @import feasts
 #' @keywords internal
 
 "_PACKAGE"
 
 NULL
-
-# utils::globalVariables(c(".", "x", "Season2"))
-# magrittr::`%>%`

R/mar_model.R

@@ -41,7 +41,7 @@
 #' \code{phi}, \code{Phi}, \code{sigmas} and \code{weights}.
 #' @author Rob J Hyndman
 #' @seealso \code{\link{simulate.mar}}
-#' @examples
+#' @examplesIf require("fGarch", quietly=TRUE)
 #' n <- 100
 #' # Quarterly MAR model with randomly selected parameters
 #' model1 <- mar_model(seasonal_periods = 4)

R/rmixmorm.R

@@ -39,8 +39,8 @@ rmixnorm <- function(n, means, sigmas, weights) {
   for (i in seq(k)) {
     if (nsamp[i] > 0) {
       data[idx == i, ] <- mvtnorm::rmvnorm(
-        n = nsamp[i], mean = means[, i], 
-        sigma = as.matrix(sigmas[, , i]), 
+        n = nsamp[i], mean = means[, i],
+        sigma = as.matrix(sigmas[, , i]),
         checkSymmetry = FALSE
       )
     }
@@ -113,7 +113,7 @@ dmixnorm <- function(x, means, sigmas, weights, log = FALSE) {
 #'     Conditional Distributions using Smooth Mixtures of Asymmetric Student T Densities,
 #'     Journal of Statistical Planning and Inference, 140(12), pp. 3638-3654.
 #' @author Feng Li, Central University of Finance and Economics.
-#' @examples
+#' @examplesIf require("fGarch", quietly=TRUE)
 #' n <- 1000
 #' means.ar.par.list <- list(c(0, 0.8), c(0, 0.6, 0.3))
 #' require("fGarch")

inst/CITATION

@@ -9,7 +9,7 @@ vers <- paste("R package version", vers)
 
 citHeader("To cite the gratis package in publications, please use:")
 bibentry(bibtype = "Manual",
-         title    = "{gratis}: {GeneRAting TIme Series} with diverse and controllable characteristics",
+         title    = "{gratis}: An R package for {GeneRAting TIme Series} with diverse and controllable characteristics",
          author   = c(as.person("Yanfei Kang"),
                       as.person("Feng Li"),
                       as.person("Rob J Hyndman"),

vignettes/QuickStart.Rmd

@@ -5,6 +5,7 @@ output: rmarkdown::html_vignette
 vignette: >
   %\VignetteIndexEntry{Introduction to gratis}
   %\VignetteEngine{knitr::rmarkdown}
+  %\VignetteDepends{feasts}
   %\VignetteEncoding{UTF-8}
 ---
 
@@ -62,11 +63,11 @@ qmar %>%
   autoplot(value)
 ```
 
-Each of these series comes from the same MAR model, but with different stochastic inputs. Although the two ARIMA models are seasonal, the seasonality is too weak to been in the plots.
+Each of these series comes from the same MAR model but with different stochastic inputs. Although the two ARIMA models are seasonal, the seasonality is too weak to been in the plots.
 
-# Generate mutiple seasonal time series
+# Generate multiple seasonal time series
 
-Time series can exhibit multiple seasonal pattern of different length, especially when series observed at a high frequency such as daily or hourly data. Here is an example in which we generate 1 hourly time series of length 2 weeks.
+Time series can exhibit multiple seasonal patterns of different lengths, especially when series are observed at a high frequency such as daily or hourly data. Here is an example in which we generate 1 hourly time series of length 2 weeks.
 
 ```{r hmarmodel}
 hmar <- mar_model(seasonal_periods = c(24, 7*24))