Merge branch 'master' into froll-prod2

Author: jangorecki

.github/workflows/pkgup.yaml

@@ -39,7 +39,6 @@ jobs:
           Rscript -e 'stopifnot(file.copy("DESCRIPTION", file.path(tdir<-tempdir(), "PACKAGES"))); db<-available.packages(paste0("file://", tdir)); deps<-setdiff(tools::package_dependencies(read.dcf("DESCRIPTION", fields="Package")[[1L]], db, which="most")[[1L]], installed.packages(priority="high")[,"Package"]); if (length(deps)) { ap<-available.packages()[,"Version"]; ap<-ap[names(ap) %in% deps]; if (!all(deps%in%names(ap))) stop("dependencies are not avaiable in repository: ",paste(setdiff(deps, names(ap)), collapse=", ")); ip<-installed.packages()[,"Version"]; ip<-ip[names(ip) %in% deps]; pkgs<-ap[deps]>ip[deps]; install.packages(names(pkgs[pkgs|is.na(pkgs)]), INSTALL_opts="--html") }'
       - name: build
         run: |
-          sed -i "0,/^Version: [0-9.]\+$/s//&-$(TZ=UTC git log -1 --format=%ct)/" ./DESCRIPTION
           echo "Revision:" $GITHUB_SHA >> ./DESCRIPTION
           R CMD build .
       - name: check

.gitlab-ci.yml

@@ -77,8 +77,6 @@ build:
     - rm -r bus
   script:
     - sed -i '/^[[:space:]]*$/d' ./DESCRIPTION ## make last line end abruptly; i.e. without a final \n
-    - |
-      sed -i "0,/^Version: [0-9.]\+$/s//&-$(date -d "$CI_COMMIT_TIMESTAMP" +%s)/" ./DESCRIPTION
     - echo "Revision:" $CI_COMMIT_SHA >> ./DESCRIPTION
     - R CMD build .
     - mkdir -p bus/$CI_JOB_NAME/
@@ -184,7 +182,7 @@ test-lin-dev-gcc-strict-cran:
     - R CMD check --as-cran $(ls -1t data.table_*.tar.gz | head -n 1)
     - (! grep "warning:" data.table.Rcheck/00install.out)
     - >-
-        Rscript -e 'l=tail(readLines("data.table.Rcheck/00check.log"), 1L); notes<-"Status: 3 NOTEs"; if (!identical(l, notes)) stop("Last line of ", shQuote("00check.log"), " is not ", shQuote(notes), " (size of tarball, non-API calls, V8 package) but ", shQuote(l)) else q("no")'
+        Rscript -e 'l=tail(readLines("data.table.Rcheck/00check.log"), 1L); notes<-"Status: 2 NOTEs"; if (!identical(l, notes)) stop("Last line of ", shQuote("00check.log"), " is not ", shQuote(notes), " (non-API calls, V8 package) but ", shQuote(l)) else q("no")'
 
 ## R-devel on Linux clang
 # R compiled with clang, flags removed: -flto=auto -fopenmp
@@ -207,7 +205,7 @@ test-lin-dev-clang-cran:
     - R CMD check --as-cran $(ls -1t data.table_*.tar.gz | head -n 1)
     - (! grep "warning:" data.table.Rcheck/00install.out)
     - >-
-        Rscript -e 'l=tail(readLines("data.table.Rcheck/00check.log"), 1L); notes<-"Status: 3 NOTEs"; if (!identical(l, notes)) stop("Last line of ", shQuote("00check.log"), " is not ", shQuote(notes), " (size of tarball, non-API calls, V8 package) but ", shQuote(l)) else q("no")'
+        Rscript -e 'l=tail(readLines("data.table.Rcheck/00check.log"), 1L); notes<-"Status: 2 NOTEs"; if (!identical(l, notes)) stop("Last line of ", shQuote("00check.log"), " is not ", shQuote(notes), " (non-API calls, V8 package) but ", shQuote(l)) else q("no")'
 
 # stated dependency on R
 test-lin-ancient-cran:

NAMESPACE

@@ -57,6 +57,7 @@ export(frollsum)
 export(frollmax)
 export(frollmin)
 export(frollprod)
+export(frollmedian)
 export(frollapply)
 export(frolladapt)
 export(nafill)

NEWS.md

@@ -246,7 +246,51 @@
     #9: 2025-09-22     9         8           9.0
     ```
 
-19. New rolling functions, `frollmin` and `frollprod`, have been implemented, towards [#2778](https://github.com/Rdatatable/data.table/issues/2778). Thanks to @jangorecki for implementation.
+19. New rolling functions: `frollmin`, `frollprod` and `frollmedian`, have been implemented, towards [#2778](https://github.com/Rdatatable/data.table/issues/2778). Thanks to @jangorecki for implementation. Implementation of rolling median is based on a novel algorithm "sort-median" described by [@suomela](https://github.com/suomela) in his 2014 paper [Median Filtering is Equivalent to Sorting](https://arxiv.org/abs/1406.1717). "sort-median" scales very well, not only for size of input vector but also for size of rolling window.
+    ```r
+    rollmedian = function(x, n) {
+      ans = rep(NA_real_, nx<-length(x))
+      if (n<=nx) for (i in n:nx) ans[i] = median(x[(i-n+1L):(i)])
+      ans
+    }
+    library(data.table)
+    setDTthreads(8)
+    set.seed(108)
+    x = rnorm(1e5)
+
+    n = 100
+    system.time(rollmedian(x, n))
+    #   user  system elapsed
+    #  2.049   0.001   2.051
+    system.time(frollapply(x, n, median, simplify=unlist))
+    #   user  system elapsed
+    #  3.071   0.223   0.436
+    system.time(frollmedian(x, n))
+    #   user  system elapsed
+    #  0.013   0.000   0.004
+
+    n = 1000
+    system.time(rollmedian(x, n))
+    #   user  system elapsed
+    #  3.496   0.009   3.507
+    system.time(frollapply(x, n, median, simplify=unlist))
+    #   user  system elapsed
+    #  4.552   0.307   0.632
+    system.time(frollmedian(x, n))
+    #   user  system elapsed
+    #  0.015   0.000   0.004
+
+    n = 10000
+    system.time(rollmedian(x, n))
+    #   user  system elapsed
+    # 16.350   0.025  16.382
+    system.time(frollapply(x, n, median, simplify=unlist))
+    #   user  system elapsed
+    # 14.865   0.722   2.267
+    system.time(frollmedian(x, n))
+    #   user  system elapsed
+    #  0.028   0.000   0.005
+    ```
 
 ### BUG FIXES
 

R/froll.R

@@ -213,3 +213,6 @@ frollmin = function(x, n, fill=NA, algo=c("fast","exact"), align=c("right","left
 frollprod = function(x, n, fill=NA, algo=c("fast","exact"), align=c("right","left","center"), na.rm=FALSE, has.nf=NA, adaptive=FALSE, partial=FALSE, give.names=FALSE, hasNA) {
   froll(fun="prod", x=x, n=n, fill=fill, algo=algo, align=align, na.rm=na.rm, has.nf=has.nf, adaptive=adaptive, partial=partial, hasNA=hasNA, give.names=give.names)
 }
+frollmedian = function(x, n, fill=NA, algo=c("fast","exact"), align=c("right","left","center"), na.rm=FALSE, has.nf=NA, adaptive=FALSE, partial=FALSE, give.names=FALSE, hasNA) {
+  froll(fun="median", x=x, n=n, fill=fill, algo=algo, align=align, na.rm=na.rm, has.nf=has.nf, adaptive=adaptive, partial=partial, hasNA=hasNA, give.names=give.names)
+}

R/onLoad.R

@@ -14,10 +14,6 @@
     # check when installed package is loaded but skip when developing the package with cc()
     dllV = if (is.loaded("CdllVersion",PACKAGE="data_table")) .Call(CdllVersion) else "before 1.12.0"
     RV = as.character(packageVersion("data.table"))
-    if (sum(.dots <- charToRaw(RV) == charToRaw(".")) > 2L) {
-      ## trim dev version suffix 1.17.99-1234567890, note that base:::package_version turns `-` into `.` #7339
-      RV = substring(RV, 1L, which(.dots)[3L]-1L)
-    }
     if (dllV != RV) {
       dll = if (.Platform$OS.type=="windows") "dll" else "so"
       # https://bugs.r-project.org/bugzilla/show_bug.cgi?id=17478