few cmdcheck updates

nicholasjclark · Mar 19, 2024 · 1ebdff1 · 1ebdff1
1 parent d4d1c51
commit 1ebdff1
Show file tree

Hide file tree

Showing 33 changed files with 437 additions and 40 deletions.
diff --git a/NAMESPACE b/NAMESPACE
@@ -183,6 +183,7 @@ importFrom(scoringRules,es_sample)
 importFrom(stats,Gamma)
 importFrom(stats,acf)
 importFrom(stats,as.formula)
+importFrom(stats,binomial)
 importFrom(stats,coef)
 importFrom(stats,complete.cases)
 importFrom(stats,cor)

diff --git a/R/families.R b/R/families.R
@@ -1,7 +1,7 @@
 #' Supported mvgam families
 #' @importFrom stats make.link dgamma pgamma rgamma qnorm plnorm runif pbeta dlnorm dpois
 #' @importFrom stats pnorm ppois plogis gaussian poisson Gamma dnbinom rnbinom dnorm dbeta
-#' @importFrom stats rbinom pbinom dbinom qbinom qlogis
+#' @importFrom stats binomial rbinom pbinom dbinom qbinom qlogis
 #' @importFrom brms lognormal student bernoulli rstudent_t qstudent_t dstudent_t pstudent_t
 #' @param link a specification for the family link function. At present these cannot
 #' be changed

diff --git a/R/get_mvgam_priors.R b/R/get_mvgam_priors.R
@@ -178,11 +178,11 @@ get_mvgam_priors = function(formula,
 
   # Check for gp terms in the validated formula
   list2env(check_gp_terms(formula, data_train, family = family),
-           env = environment())
+           envir = environment())
 
   # Check for missing rhs in formula
   list2env(check_obs_intercept(formula, orig_formula),
-           env = environment())
+           envir = environment())
 
   # Validate observation formula
   formula <- interpret_mvgam(formula, N = max(data_train$time))
@@ -202,7 +202,7 @@ get_mvgam_priors = function(formula,
   list2env(check_nmix(family, family_char,
                       trend_formula, trend_model,
                       trend_map, data_train,
-                      priors = TRUE), env = environment())
+                      priors = TRUE), envir = environment())
 
   # Validate remaining trend arguments
   trend_val <- validate_trend_restrictions(trend_model = trend_model,
@@ -216,7 +216,7 @@ get_mvgam_priors = function(formula,
                                            data_train = data_train,
                                            use_stan = use_stan,
                                            priors = TRUE)
-  list2env(trend_val, env = environment())
+  list2env(trend_val, envir = environment())
   if(is.null(trend_map)) trend_map <- rlang::missing_arg()
   if(is.null(n_lv)) n_lv <- rlang::missing_arg()
 

diff --git a/R/globals.R b/R/globals.R
@@ -10,4 +10,9 @@ utils::globalVariables(c("y", "year", "smooth_vals", "smooth_num",
                          "term", "data_test", "object", "row_num", "trends_test",
                          "trend", "trend_series", "trend_y", ".", "gam",
                          "group", "mod", "row_id", "byvar", "direction",
-                         "index..time..index", "trend_test", "Var2"))
+                         "index..time..index", "trend_test", "Var2",
+                         "add_cor", "add_ma", "add_nmix", "binomial",
+                         "current", "drop_obs_intercept",
+                         "gp_details", "gp_terms", "k", "mus",
+                         "name", "needed", "nmix_trendmap", "orig_formula",
+                         "trial", "use_var1", "use_var1cor", "xcols_drop"))
diff --git a/R/hindcast.mvgam.R b/R/hindcast.mvgam.R
@@ -2,10 +2,6 @@
 #'@name hindcast.mvgam
 #'@importFrom stats predict
 #'@inheritParams predict.mvgam
-#'@param series Either a \code{integer} specifying which series in the set is to be forecast,
-#'or the character string \code{'all'}, specifying that all series should be forecast. This is preferable
-#'if the fitted model contained multivariate trends (either as a dynamic factor or \code{VAR} process),
-#'as it saves recomputing the full set of trends for each series individually
 #'@param ... Ignored
 #'@details Posterior retrodictions are drawn from the fitted \code{mvgam} and
 #'organized into a convenient format

diff --git a/R/mvgam.R b/R/mvgam.R
@@ -68,7 +68,9 @@
 #'   \item`bernoulli()` for binary data
 #'   \item`nb()` for count data
 #'   \item`poisson()` for count data
-#'   \item`binomial()` for count data with imperfect detection when the number of trials is known
+#'   \item`binomial()` for count data with imperfect detection when the number of trials is known;
+#'   note that the `cbind()` function must be used to bind the discrete observations and the number
+#'   of trials
 #'   \item`nmix()` for count data with imperfect detection when the number of trials
 #'   is unknown and should be modeled via a State-Space N-Mixture model.
 #'   The latent states are Poisson, capturing the 'true' latent
@@ -571,6 +573,33 @@
 #' scale_y_discrete(labels = mod$trend_model$changepoints) +
 #' labs(y = 'Potential changepoint',
 #'      x = 'Rate change')
+#'
+#' # Example showcasing how cbind() is needed for Binomial observations
+#' # Simulate two time series of Binomial trials
+#' trials <- sample(c(20:25), 50, replace = TRUE)
+#' x <- rnorm(50)
+#' detprob1 <- plogis(-0.5 + 0.9*x)
+#' detprob2 <- plogis(-0.1 -0.7*x)
+#' dat <- rbind(data.frame(y = rbinom(n = 50, size = trials, prob = detprob1),
+#'                         time = 1:50,
+#'                         series = 'series1',
+#'                         x = x,
+#'                         ntrials = trials),
+#'              data.frame(y = rbinom(n = 50, size = trials, prob = detprob2),
+#'                         time = 1:50,
+#'                         series = 'series2',
+#'                         x = x,
+#'                         ntrials = trials)) %>%
+#'  dplyr::mutate(series = as.factor(series)) %>%
+#'  dplyr::arrange(time, series)
+#'
+#' # Fit a model using the binomial() family; must specify observations
+#' # and number of trials in the cbind() wrapper
+#' mod <- mvgam(cbind(y, ntrials) ~ series + s(x, by = series)
+#'              family = binomial(),
+#'              data = dat)
+#' summary(mod)
+#'
 #' }
 #'@export
 
@@ -639,11 +668,11 @@ mvgam = function(formula,
 
   # Check for gp terms in the validated formula
   list2env(check_gp_terms(formula, data_train, family = family),
-           env = environment())
+           envir = environment())
 
   # Check for missing rhs in formula
   list2env(check_obs_intercept(formula, orig_formula),
-           env = environment())
+           envir = environment())
 
   # Check for brmspriors
   if(!missing(priors)){
@@ -704,7 +733,7 @@ mvgam = function(formula,
   # Nmixture additions?
   list2env(check_nmix(family, family_char,
                       trend_formula, trend_model,
-                      trend_map, data_train), env = environment())
+                      trend_map, data_train), envir = environment())
 
   # Validate remaining trend arguments
   trend_val <- validate_trend_restrictions(trend_model = trend_model,
@@ -717,7 +746,7 @@ mvgam = function(formula,
                                            n_lv = n_lv,
                                            data_train = data_train,
                                            use_stan = use_stan)
-  list2env(trend_val, env = environment())
+  list2env(trend_val, envir = environment())
   if(is.null(trend_map)) trend_map <- rlang::missing_arg()
   if(is.null(n_lv)) n_lv <- rlang::missing_arg()
 
@@ -786,7 +815,7 @@ mvgam = function(formula,
                        data_train = data_train,
                        family = family,
                        family_char = family_char,
-                       knots = knots), env = environment())
+                       knots = knots), envir = environment())
 
   # Update initial values of lambdas using the full estimates from the
   # fitted gam model to speed convergence; remove initial betas so that the

diff --git a/man/get_mvgam_priors.Rd b/man/get_mvgam_priors.Rd
diff --git a/man/hindcast.mvgam.Rd b/man/hindcast.mvgam.Rd
diff --git a/man/mvgam.Rd b/man/mvgam.Rd
diff --git a/man/update.mvgam.Rd b/man/update.mvgam.Rd
diff --git a/misc/BeamOptions.tex b/misc/BeamOptions.tex
@@ -41,8 +41,8 @@
     \put(\LenToUnit{0.88\paperwidth},\LenToUnit{0.88\paperheight}){#1}}}
 \AddToShipoutPictureFG{
   \AtPagemyUpperLeft{{
-      \href{http://mc-stan.org/}{\includegraphics[scale=0.25,keepaspectratio]{../logos/Stan.png}}
+      \href{https://nicholasjclark.github.io/mvgam/}{\includegraphics[scale=0.5,keepaspectratio]{mvgam_logo.png}}
       \hspace{0.025in}
-      \href{http://ggplot2.tidyverse.org}{\includegraphics[scale=0.5,keepaspectratio]{../logos/ggplot2.png}}
+      \href{https://mc-stan.org/}{\includegraphics[scale=0.75,keepaspectratio]{stan_logo.png}}
 }}
 }%
diff --git a/misc/Rplots.pdf b/misc/Rplots.pdf
diff --git a/misc/cache/__packages b/misc/cache/__packages
@@ -0,0 +1,9 @@
+knitr
+ggplot2
+nlme
+mgcv
+Rcpp
+brms
+marginaleffects
+insight
+mvgam
diff --git a/misc/cache/unnamed-chunk-1_d1ca7f1d2764d3ad7f68b1deac173f02.RData b/misc/cache/unnamed-chunk-1_d1ca7f1d2764d3ad7f68b1deac173f02.RData
diff --git a/misc/cache/unnamed-chunk-1_d1ca7f1d2764d3ad7f68b1deac173f02.rdb b/misc/cache/unnamed-chunk-1_d1ca7f1d2764d3ad7f68b1deac173f02.rdb
diff --git a/misc/cache/unnamed-chunk-1_d1ca7f1d2764d3ad7f68b1deac173f02.rdx b/misc/cache/unnamed-chunk-1_d1ca7f1d2764d3ad7f68b1deac173f02.rdx
diff --git a/misc/cache/unnamed-chunk-2_ad6e810bc91f96416ef0c5c84cba99cc.RData b/misc/cache/unnamed-chunk-2_ad6e810bc91f96416ef0c5c84cba99cc.RData
diff --git a/misc/cache/unnamed-chunk-2_ad6e810bc91f96416ef0c5c84cba99cc.rdb b/misc/cache/unnamed-chunk-2_ad6e810bc91f96416ef0c5c84cba99cc.rdb
diff --git a/misc/cache/unnamed-chunk-2_ad6e810bc91f96416ef0c5c84cba99cc.rdx b/misc/cache/unnamed-chunk-2_ad6e810bc91f96416ef0c5c84cba99cc.rdx
diff --git a/misc/figure/unnamed-chunk-3-1.pdf b/misc/figure/unnamed-chunk-3-1.pdf
diff --git a/misc/figure/unnamed-chunk-4-1.pdf b/misc/figure/unnamed-chunk-4-1.pdf
diff --git a/misc/figure/unnamed-chunk-5-1.pdf b/misc/figure/unnamed-chunk-5-1.pdf
diff --git a/misc/figure/unnamed-chunk-6-1.pdf b/misc/figure/unnamed-chunk-6-1.pdf
diff --git a/misc/figure/unnamed-chunk-7-1.pdf b/misc/figure/unnamed-chunk-7-1.pdf
diff --git a/misc/mvgam_cheatsheet-concordance.tex b/misc/mvgam_cheatsheet-concordance.tex
@@ -0,0 +1,4 @@
+\Sconcordance{concordance:mvgam_cheatsheet.tex:mvgam_cheatsheet.Rnw:%
+1 7 1 50 0 1 6 3 1 1 7 1 1 1 8 95 1 4 0 34 1 %
+6 0 14 1 6 0 10 1 1 3 34 1 1 6 8 1 4 0 5 1 9 %
+0 22 1}
diff --git a/misc/mvgam_cheatsheet.Rnw b/misc/mvgam_cheatsheet.Rnw
@@ -1,10 +1,18 @@
 \documentclass[final,9pt,fleqn]{beamer}
 \input{BeamOptions.tex}
 
-\setbeamertemplate{footline}{\hfill {\footnotesize \href{https://creativecommons.org/licenses/by-sa/4.0/}{CC BY-SA 4.0} $\circ$ Nicholas J. Clark $\circ$ Learn more at \href{https://nicholasjclark.github.io/mvgam/index.html}{https://nicholasjclark.github.io/mvgam/index.html} $\circ$ package version $1.0.8$ $\circ$ updated: \today} \hspace {0.1in} \vspace{0.1in}}
+\setbeamertemplate{footline}{\hfill {\footnotesize \href{https://creativecommons.org/licenses/by-sa/4.0/}{CC BY-SA 4.0} $\circ$ Nicholas J. Clark $\circ$ Learn more at \href{https://nicholasjclark.github.io/mvgam/index.html}{https://nicholasjclark.github.io/mvgam/index.html} $\circ$ package version $1.0.9$ $\circ$ updated: \today} \hspace {0.1in} \vspace{0.1in}}
 
 \begin{document}
 
+<<include=FALSE>>=
+library(knitr)
+opts_chunk$set(
+concordance=TRUE
+)
+@
+
+
 
 <<setup, include=FALSE>>=
 library(knitr)
@@ -52,7 +60,7 @@ Usage: \texttt{\color{Orchid} mvgam(formula, trend\_formula, data, trend\_model,
 \texttt{\color{Orchid} data}: a \texttt{data.frame} or \texttt{list} containing the response variable(s) and optional predictor variables. See \href{https://nicholasjclark.github.io/mvgam/articles/data_in_mvgam.html}{the data formatting vignette} for guidance on data preparation
 
 \medskip
-\texttt{\color{Orchid} trend\_model}: optional latent dynamic process. Options include: 
+\texttt{\color{Orchid} trend\_model}: optional latent dynamic process. Options include:
 \begin{itemize}
 
 \item\texttt{\color{Orchid} None}: default, no dynamic trend
@@ -72,7 +80,7 @@ Usage: \texttt{\color{Orchid} mvgam(formula, trend\_formula, data, trend\_model,
 For autoregressive processes (\texttt{\color{Orchid} RW(), AR() or VAR()}), moving average and correlated process errors can also be specified by changing the \texttt{\color{Orchid} ma} and \texttt{\color{Orchid} cor} arguments
 
 \medskip
-\texttt{\color{Orchid} family}: observation distribution. Options include: 
+\texttt{\color{Orchid} family}: observation distribution. Options include (among others):
 \begin{itemize}
 
 \item\texttt{\color{Orchid} gaussian()}: Gaussian with identity link
@@ -94,15 +102,15 @@ For autoregressive processes (\texttt{\color{Orchid} RW(), AR() or VAR()}), movi
 See \href{https://nicholasjclark.github.io/mvgam/articles/mvgam_overview.html}{the introductory vignette} for more guidance on supported families and dynamic processes
 
 \medskip
-\texttt{\color{Orchid} ...}: other arguments such as user-specified \texttt{\color{Orchid} priors}, \texttt{\color{Orchid} newdata} for generating probabilistic forecasts and options to control \texttt{\color{Orchid} Stan} MCMC parameters 
+\texttt{\color{Orchid} ...}: other arguments such as user-specified \texttt{\color{Orchid} priors}, \texttt{\color{Orchid} newdata} for generating probabilistic forecasts and options to control \texttt{\color{Orchid} Stan} MCMC parameters
 
 \medskip
-\textbf{\color{BrickRed} Prior to modelling}, it is useful to: 
+\textbf{\color{BrickRed} Prior to modelling}, it is useful to:
 \begin{itemize}
 
 \item Inspect features of the data with \texttt{\color{Orchid} plot\_mvgam\_series()}
 
-\item Ensure there are no \texttt{\color{Orchid} NA}'s in predictors (though \texttt{\color{Orchid} NA}'s are allowed in response variables). See \href{https://nicholasjclark.github.io/mvgam/articles/data_in_mvgam.html}{the data formatting vignette} for guidance on data preparation 
+\item Ensure there are no \texttt{\color{Orchid} NA}'s in predictors (though \texttt{\color{Orchid} NA}'s are allowed in response variables). See \href{https://nicholasjclark.github.io/mvgam/articles/data_in_mvgam.html}{the data formatting vignette} for guidance on data preparation
 
 \item Inspect default priors with \texttt{\color{Orchid} get\_mvgam\_priors()}
 
@@ -168,9 +176,9 @@ conditional_effects(model)[[1]] + xlim(c(1, 12.1))
 
 For most \texttt{mvgam} models, functions from the \texttt{marginaleffects} package can be used for more targeted prediction-based inference. See \href{https://marginaleffects.com/}{The Marginal Effects Zoo} for guidance on computing and plotting predictions, slopes and comparisons
 <<fig.width=4, fig.height=1.75, fig.align='center', warning=FALSE, echo=FALSE>>=
-post_contrasts <- avg_comparisons(model, 
+post_contrasts <- avg_comparisons(model,
                                   variables = list(season = c(5, 11))) %>%
-  posteriordraws() 
+  posteriordraws()
 
 post_contrasts %>%
   ggplot(aes(x = draw)) +
@@ -205,13 +213,13 @@ Use \texttt{\color{Orchid} ppc(model)} to plot various kinds of posterior predic
 Extract in-sample posterior predictions with \texttt{\color{Orchid} hindcast(model)}. If validation data exist, generate forecast predictions with \texttt{\color{Orchid} forecast(model, newdata = newdata)}. As above, change the \texttt{\color{Orchid} type} argument for predictions on different scales. Both functions generate an object of class \texttt{mvgam\_forecast}, that can be plotted with an \texttt{S3} \texttt{\color{Orchid} plot()} function. See \href{https://nicholasjclark.github.io/mvgam/articles/forecast_evaluation.html}{the forecasting vignette} for more details about how to produce forecasts.
 
 <<fig.width=5.4, fig.height=2.5, fig.align='center', warning=FALSE, results='hide',echo=FALSE>>=
-  par(family = "serif", 
-      las = 1, 
+  par(family = "serif",
+      las = 1,
       mar=c(3,3,2,2),
       mgp = c(2,0.5,0),
-      bty = "l", 
-      cex.axis = 0.9, 
-      cex.lab = 0.9, 
+      bty = "l",
+      cex.axis = 0.9,
+      cex.lab = 0.9,
       cex.main = 0.9,
       xaxs = 'r',
       yaxs = 'r',

diff --git a/misc/mvgam_cheatsheet.pdf b/misc/mvgam_cheatsheet.pdf
diff --git a/misc/mvgam_cheatsheet.png b/misc/mvgam_cheatsheet.png