Merge pull request #45 from r-spatial/LargeN

address #44

Author: rsbivand

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: classInt
-Version: 0.4-9
-Date: 2023-02-21
+Version: 0.4-10
+Date: 2023-08-24
 Title: Choose Univariate Class Intervals
 Authors@R: c(
   person("Roger", "Bivand", role=c("aut", "cre"), email="[email protected]", comment=c(ORCID="0000-0003-2392-6140")),

R/classInt.R

@@ -132,11 +132,13 @@ classIntervals <- function(var, n, style="quantile", rtimes=3, ..., intervalClos
 # introduced related to https://github.com/r-spatial/classInt/issues/7
     sampling <- FALSE
     if (warnLargeN &&
-      (style %in% c("kmeans", "hclust", "bclust", "fisher", "jenks"))) {
+      (style %in% c("fisher", "jenks"))) {
       if (nobs > largeN) {
         warning("N is large, and some styles will run very slowly; sampling imposed")
         sampling <- TRUE
-        nsamp <- ifelse(samp_prop*nobs > 3000, as.integer(ceiling(samp_prop*nobs)), 3000L)
+# issue 44
+        nsamp <- as.integer(ceiling(samp_prop*nobs))
+        if (nsamp > largeN) nsamp <- as.integer(largeN)
       }
     }
     if (style =="fixed") {

inst/tinytest/test_largeN.R

@@ -0,0 +1,8 @@
+library(classInt)
+# issue 44
+set.seed(101)
+large_n <- 1000
+x <- 1:(large_n + 1)
+expect_warning(classInt::classIntervals(x, n = 10, style = "fisher", 
+  largeN = large_n, samp_prop = 0.05))
+

man/classIntervals.Rd

@@ -30,7 +30,7 @@ classIntervals2shingle(x)
   \item{dataPrecision}{default NULL, permits rounding of the interval endpoints (added by Richard Dunlap). The data precision used for printing interval values in the legend returned by \code{findColours}, and in the \code{print} method for classIntervals objects. If intervalClosure is \dQuote{left}, the value returned is \code{ceiling} of the data value multiplied by 10 to the dataPrecision power, divided by 10 to the dataPrecision power. The argument does not round \code{var}, the input variable.}
   \item{warnSmallN}{default TRUE, if FALSE, quietens warning for n >= nobs}
   \item{warnLargeN}{default TRUE, if FALSE large data handling not used}
-  \item{largeN}{default 3000L, the QGIS sampling threshold; over 3000, the observations presented to "fisher" and "jenks" are either a \code{samp_prop=} sample or a sample of 3000, whichever is larger}
+  \item{largeN}{default 3000L, the QGIS sampling threshold; over \code{largeN}, the observations presented to "fisher" and "jenks" are either a \code{samp_prop=} sample or a sample of \code{largeN}, whichever is smaller}
   \item{samp_prop}{default 0.1, QGIS 10\% sampling proportion}
   \item{gr}{default \code{c("[", "]")}, if the \pkg{units} package is available, \code{units::units_options("group")} may be used directly to give the enclosing bracket style}
   \item{\dots}{arguments to be passed to the functions called in each style}