Updates for vignette for v0.2.0 and documentation fixes

Updated vignette with new package changes
* 'spatstat.geom' and 'sf' packages
*  New color for Navy Yard plot
* Updated documentation of various hypothesis testing
* Changed `lower_tail` argument in `spatial_power()` to `alpha` argument
* Fixed colors and typos
* Use `cut()` function instead of `reclassify()` function from 'raster' package

Renamed internal `wind` argument in `spatial_power()` as `win` to match `jitter_power()`

Updated documentation with correct order of `cols` in `spatial_plots()` function

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: sparrpowR
 Title: Power Analysis to Detect Spatial Relative Risk Clusters
 Version: 0.2.0
-Date: 2021-02-05
+Date: 2021-02-06
 Authors@R:
     c(person(given = "Ian D.",
              family = "Buller",

NEWS.md

@@ -4,7 +4,7 @@
 * Updates to dependencies
   * Updated 'spatstat' package to new subsetted packages based on feedback from the Spatstat Team (Adrian Baddeley and Ege Rubak). 'spatstat.geom' and 'spatstat.core' packages replace 'spatstat' package in Depends
   * Imports 'lifecycle' package to document deprecated argument `cascon` in `spatial_power()` and `jitter_power()` functions
-  * Replaced 'parallel' and 'doParallel' packages in Imports with 'doFuture', 'doRNG', and 'future' packages to allow for parallel processing in `spatial_power()` and `jitter_power()` functions to work across environments
+  * Replaced 'parallel' and 'doParallel' packages in Imports with 'doFuture', 'doRNG', and 'future' packages to allow for parallel processing in `spatial_power()` and `jitter_power()` functions to work across all CRAN environments
   * Removed 'utils' package from Imports because the progress bar in `spatial_power()` and `jitter_power()` functions is now produced with a helper function in utils.R that imports the 'iterators' package
   * Removed 'tidyverse' package from Suggests
 * Changes to DESCRIPTION
@@ -29,9 +29,10 @@
   * Added `plot_axes` argument to toggle the display of axes in plots
   * Added `plot_square` argument to toggle the margins of plots
   * Changed the value of `cex.axis` and `cex` in plots
+  * Updated documentation with correct order of `cols`
 * Changes to `jitter_power()`
   * Added `p_correct` argument to apply a multiple testing correction
-  * Specify all packages for functions
+  * Specified all packages for functions
   * Deprecated `cascon` argument (moved to `spatial_plots()` function)
   * Estimates case-only power (lower tail) and case/control (lower and upper tail) and captures both outputs. Case-only is now a one-tailed hypothesis test by default. The arguments `lower_tail` and `upper_tail` have been replaced with argument `alpha`
   * Used `as.solist()` to specify appropriate class to lists
@@ -42,9 +43,10 @@
   * Increased the `sim_total` value for a more realistic example
   * Specify all packages for functions
   * Updated code to reflect updates to functions in 'sparrpowR'
-* Changes to README.md
-  * Added CRAN badges
-  * Added plotting for case and control clustering
+  * Updated code to use 'sf' package
+  * Updated explanation of the `cascon` argument to plot various hypothesis tests
+  * Changed `cols` values to be more visible 
+  * Used `cut` instead of `reclassify` in 'raster' package for categorical plot
 * Added utils.R file
   * Removed the helper `comb()` function functions from `jitter_power()`, `spatial_power()`, and `spatial_plots()` and added to the utils.R file
   * Removed 'utils' package from Imports because the progress bar in `spatial_power()` and `jitter_power()` functions is now produced with a helper `progBar()` function

R/jitter_power.R

@@ -20,17 +20,17 @@
 #' 
 #' The function uses the \code{\link[sparr]{risk}} function to estimate the spatial relative risk function and forces the \code{tolerate} argument to be TRUE in order to calculate asymptotic p-values.
 #' 
-#' If \code{samp_control = "uniform"} the control locations are randomly generated uniformly within the window of \code{obs_data}. By default, the resolution is an integer value of 128 and can be specified using the \code{resolution} argument in the internally called \code{\link[sparr]{risk}} function.
+#' If \code{samp_control = "uniform"} the control locations are randomly generated uniformly within the dow of \code{obs_data}. By default, the resolution is an integer value of 128 and can be specified using the \code{resolution} argument in the internally called \code{\link[sparr]{risk}} function.
 #' 
-#' If \code{samp_control = "CSR"} the control locations are randomly generated assuming complete spatial randomness (homogeneous Poisson process) within the window of \code{obs_data} with a \code{lambda = number of controls / [resolution x resolution]}. By default, the resolution is an integer value of 128 and can be specified using the \code{resolution} argument in the internally called \code{\link[sparr]{risk}} function.
+#' If \code{samp_control = "CSR"} the control locations are randomly generated assuming complete spatial randomness (homogeneous Poisson process) within the dow of \code{obs_data} with a \code{lambda = number of controls / [resolution x resolution]}. By default, the resolution is an integer value of 128 and can be specified using the \code{resolution} argument in the internally called \code{\link[sparr]{risk}} function.
 #' 
 #' If \code{samp_control = "MVN"} the control locations are randomly generated assuming a multivariate normal distribution \emph{centered at each observed location}. The optional argument \code{s_control} specifies the standard deviation of the multivariate normal distribution (1 by default) in the units of the \code{obs_data}. 
 #' 
 #' The function computes a one-sided hypothesis test for case clustering (\code{alpha = 0.05} by default). The function also computes a two-sided hypothesis test for case clustering and control clustering (lower tail = 0.025 and upper tail = 0.975).
 #' 
 #' The function has functionality for a correction for multiple testing. If \code{p_correct = "FDR"}, calculates a False Discovery Rate by Benjamini and Hochberg. If \code{p_correct = "Sidak"}, calculates a Sidak correction. If \code{p_correct = "Bonferroni"}, calculates a Bonferroni correction. If \code{p_correct = "none"} (the default), then the function does not account for multiple testing and uses the uncorrected \code{alpha} level. See the internal \code{pval_correct} function documentation for more details.
 #'
-#' @return An object of class "list". This is a named list with the following components:
+#' @return An object of class "list". This is a named list with the follog components:
 #' 
 #' \describe{
 #' \item{\code{sim}}{An object of class 'rrs' for the first iteration of simulated data.}

R/spatial_plots.R

@@ -4,9 +4,9 @@
 #' 
 #' @param input An object of class "ppplist" from the \code{\link{spatial_data}} function or an object of class "list" from the \code{\link{spatial_power}} or \code{\link{jitter_power}} functions.
 #' @param p_thresh A numeric value between 0 and 1 (default = 0.8) for the power threshold.
-#' @param cascon Logical. If TRUE, displays the statistical power to detect case clusters and control clusters. If FALSE (the default), displays the statistical power to detect case clusters only. 
+#' @param cascon Logical. If TRUE, displays the statistical power to detect case clusters and control clusters (two-tailed hypothesis). If FALSE (the default), displays the statistical power to detect case clusters only (one-tailed, lower-tail hypothesis). 
 #' @param n_sim Integer. The number of simulated iterations to plot. The default is one (1).
-#' @param cols Character string of length four (4) specifying the colors for plotting: 1) sufficiently powered, 2) insufficiently powered, 3) case locations, 4) control locations. The default colors in hex are \code{c("#000000", "#CCCCCC", "#FF0000", "#0000FF")} or \code{c("grey0", "grey80", "red", "blue")}.
+#' @param cols Character string of length four (4) specifying the colors for plotting: 1) insufficiently powered, 2) sufficiently powered, 3) case locations, 4) control locations. The default colors in hex are \code{c("#000000", "#CCCCCC", "#FF0000", "#0000FF")} or \code{c("grey0", "grey80", "red", "blue")}.
 #' @param chars Vector of integers or character string of length two (2) for symbols of case and control locations. Default is \code{c(1,1)}. 
 #' @param sizes Vector of integers of length two (2) for the size of the symbols for case and control locations. Default is \code{c(1,1)}. 
 #' @param scale Integer. A graphical expansion factor (default is 1) for text (and point) size within plots. Intended for scaling plot features with plot resolution.

R/spatial_power.R

@@ -195,18 +195,18 @@ spatial_power <- function(win = spatstat.geom::unit.square(),
   match.arg(p_correct, choices = c("none", "FDR", "Sidak", "Bonferroni"))
 
   # marked uniform disc ppp with user-specified radius for cases
-  rcluster_case <- function(x0, y0, rad, n, scalar, lamb, wind, types = "case", ...) {
+  rcluster_case <- function(x0, y0, rad, n, scalar, lamb, win, types = "case", ...) {
 
     if (samp_case == "uniform") {
-      x <- spatstat.core::runifdisc(n = n, radius = rad, centre = c(x0, y0), win = wind, ...)
+      x <- spatstat.core::runifdisc(n = n, radius = rad, centre = c(x0, y0), win = win, ...)
     }  
 
     if (samp_case == "MVN") {
       x1 <- rep(x0, n)
       y1 <- rep(y0, n)
       x2 <- x1 + stats::rnorm(n, 0, scalar) 
       y2 <- y1 + stats::rnorm(n, 0, scalar) 
-      x <- spatstat.geom::ppp(x2, y2, window = wind)
+      x <- spatstat.geom::ppp(x2, y2, window = win)
      }  
 
     if (samp_case == "CSR") {
@@ -230,33 +230,33 @@ spatial_power <- function(win = spatstat.geom::unit.square(),
    }
 
   # marked uniform ppp for controls
-  rcluster_control <- function(x0, y0, scalar, n, lamb, ex, nclust, rad, types = "control", wind, ...) {
+  rcluster_control <- function(x0, y0, scalar, n, lamb, ex, nclust, rad, types = "control", win, ...) {
     if (samp_control == "uniform") { 
-      x <- spatstat.core::runifpoint(n, win = wind, ...) 
+      x <- spatstat.core::runifpoint(n, win = win, ...) 
      }
 
     if (samp_control == "systematic") {
-      x <- spatstat.geom::rsyst(nx = sqrt(n), win = wind, ...)
+      x <- spatstat.geom::rsyst(nx = sqrt(n), win = win, ...)
      }
 
     if (samp_control == "MVN") {
       x1 <- rep(x0, n)
       y1 <- rep(y0, n)
       x2 <- x1 + stats::rnorm(n, 0, scalar) 
       y2 <- y1 + stats::rnorm(n, 0, scalar) 
-      x <- spatstat.geom::ppp(x2, y2, window = wind)
+      x <- spatstat.geom::ppp(x2, y2, window = win)
      }  
 
     if (samp_control == "CSR") {
-      l <- n / (diff(wind$xrange) * diff(wind$yrange))
-      x <- spatstat.core::rpoispp(lambda = l, win = wind, ...)
+      l <- n / (diff(win$xrange) * diff(win$yrange))
+      x <- spatstat.core::rpoispp(lambda = l, win = win, ...)
      }
 
     if (samp_control == "IPP") {
       if (class(lamb) != "function") {
         stop("The argument 'l_control' should be an intensity function")
       }
-      x <- spatstat.core::rpoispp(lambda = lamb, win = wind, ...)
+      x <- spatstat.core::rpoispp(lambda = lamb, win = win, ...)
     }
 
     if (samp_control == "clustered") {
@@ -269,7 +269,7 @@ spatial_power <- function(win = spatstat.geom::unit.square(),
                                        rcluster = control_clustering, 
                                        n = nclust,
                                        radius = rad,
-                                       win = wind,
+                                       win = win,
                                        ...)
      }
     spatstat.geom::marks(x) <- types
@@ -285,7 +285,7 @@ spatial_power <- function(win = spatstat.geom::unit.square(),
       x1 <- rcluster_case(x0 = x_case[i], y0 = y_case[i],
                           rad = r_case[i], n = n_case[i],
                           scalar = s_case[i], lamb = l_case[[i]],
-                          wind = win, ...))
+                          win = win, ...))
     pppCase[[i]] <- x1
   }
   pppCase <- spatstat.geom::as.solist(pppCase)
@@ -325,7 +325,7 @@ spatial_power <- function(win = spatstat.geom::unit.square(),
                                  n = n_control[i],
                                  scalar = s_control[i],
                                  lamb =NULL,
-                                 wind = win, ...))
+                                 win = win, ...))
         pppControl[[i]] <- y1
        }
       pppControl <- spatstat.geom::as.solist(pppControl)
@@ -339,7 +339,7 @@ spatial_power <- function(win = spatstat.geom::unit.square(),
                                 ex = e_control,
                                 lamb = l_control,
                                 scalar = NULL,
-                                wind = win,
+                                win = win,
                                 ...))
       }
 

cran-comments.md

@@ -4,7 +4,7 @@
 * Updates to dependencies
   * Updated 'spatstat' package to new subsetted packages based on feedback from the Spatstat Team (Adrian Baddeley and Ege Rubak). 'spatstat.geom' and 'spatstat.core' packages replace 'spatstat' package in Depends
   * Imports 'lifecycle' package to document deprecated argument `cascon` in `spatial_power()` and `jitter_power()` functions
-  * Replaced 'parallel' and 'doParallel' packages in Imports with 'doFuture', 'doRNG', and 'future' packages to allow for parallel processing in `spatial_power()` and `jitter_power()` functions to work across environments
+  * Replaced 'parallel' and 'doParallel' packages in Imports with 'doFuture', 'doRNG', and 'future' packages to allow for parallel processing in `spatial_power()` and `jitter_power()` functions to work across all CRAN environments
   * Removed 'tidyverse' package from Suggests
 * Changes to DESCRIPTION
   * Added ORCID for all authors and contributors
@@ -28,9 +28,10 @@
   * Added `plot_axes` argument to toggle the display of axes in plots
   * Added `plot_square` argument to toggle the margins of plots
   * Changed the value of `cex.axis` and `cex` in plots
+  * Updated documentation with correct order of `cols`
 * Changes to `jitter_power()`
   * Added `p_correct` argument to apply a multiple testing correction
-  * Specify all packages for functions
+  * Specified all packages for functions
   * Deprecated `cascon` argument (moved to `spatial_plots()` function)
   * Estimates case-only power (lower tail) and case/control (lower and upper tail) and captures both outputs. Case-only is now a one-tailed hypothesis test by default. The arguments `lower_tail` and `upper_tail` have been replaced with argument `alpha`
   * Used `as.solist()` to specify appropriate class to lists
@@ -41,9 +42,10 @@
   * Increased the `sim_total` value for a more realistic example
   * Specify all packages for functions
   * Updated code to reflect updates to functions in 'sparrpowR'
-* Changes to README.md
-  * Added CRAN badges
-  * Added plotting for case and control clustering
+  * Updated code to use 'sf' package
+  * Updated explanation of the `cascon` argument to plot various hypothesis tests
+  * Changed `cols` values to be more visible 
+  * Used `cut` instead of `reclassify` in 'raster' package for categorical plot
 * Added utils.R file
   * Removed the helper `comb()` function functions from `jitter_power()`, `spatial_power()`, and `spatial_plots()` and added to the utils.R file
   * Removed 'utils' package from Imports because the progress bar in `spatial_power()` and `jitter_power()` functions is now produced with a helper `progBar()` function