Merge pull request #72 from tdhock/N_unique

error for N not unique
tdhock · Dec 3, 2024 · 5f722cb · 5f722cb
2 parents 66b632c + a1ad8a0
commit 5f722cb
Show file tree

Hide file tree

Showing 6 changed files with 51 additions and 38 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: atime
 Type: Package
 Title: Asymptotic Timing
-Version: 2024.11.29
+Version: 2024.12.3
 Authors@R: c(
     person("Toby", "Hocking",
      email="[email protected]",

diff --git a/NEWS b/NEWS
@@ -1,3 +1,8 @@
+Changes in version 2024.12.3
+
+- atime errors if user provides duplicate N values.
+- predict(length=100) in sparse vignette, for CRAN.
+
 Changes in version 2024.11.29
 
 - use seconds.limit=Inf in test, for CRAN.

diff --git a/R/atime.R b/R/atime.R
@@ -114,6 +114,11 @@ atime <- function(N=default_N(), setup, expr.list=NULL, times=10, seconds.limit=
   if(length(N)<2){
     stop("length(N) should be at least 2")
   }
+  N.tab <- table(N)
+  N.bad <- N.tab[N.tab>1]
+  if(length(N.bad)){
+    stop("please remove duplicate values from N: ", paste(names(N.bad), collapse=", "))
+  }
   formal.names <- names(formals())
   mc.args <- as.list(match.call()[-1])
   dots.list <- mc.args[!names(mc.args) %in% formal.names]

diff --git a/man/atime.Rd b/man/atime.Rd
@@ -9,7 +9,7 @@ N, setup, expr.list=NULL, times=10, seconds.limit=0.01, verbose=FALSE,
 result=FALSE, N.env.parent=NULL, ...)}
 
 \arguments{
-  \item{N}{numeric vector of at least two data sizes, default is \code{2^seq(2,20)}.}
+  \item{N}{numeric vector of at least two unique data sizes, default is \code{2^seq(2,20)}.}
   \item{setup}{expression to evaluate for every data size, before timings.}
   \item{expr.list}{named list of expressions to time.}
   \item{times}{number of times to evaluate each timed expression.}

diff --git a/tests/testthat/test-CRAN.R b/tests/testthat/test-CRAN.R
@@ -1,7 +1,15 @@
 library(data.table)
 library(testthat)
 
-test_that("warning for only one N", {
+test_that("error when user provided duplicate N", {
+  expect_error({
+    atime::atime(N=c(1,2,2,3,9,9,9), num=numeric(N))
+  },
+  "please remove duplicate values from N: 2, 9",
+  fixed=TRUE)
+})
+
+test_that("warning when result contains only one N", {
   expect_warning({
     seconds.limit <- 0.001
     atime.list <- atime::atime(

diff --git a/vignettes/sparse.Rmd b/vignettes/sparse.Rmd
@@ -25,7 +25,7 @@ to time and memory).
 
 ```{r}
 library(Matrix)
-N_seq <- as.integer(10^seq(1,7,by=0.25))
+N_seq <- unique(as.integer(10^seq(0,7,by=0.25)))
 vec.mat.result <- atime::atime(
   N=N_seq,
   vector=numeric(N),
@@ -64,40 +64,35 @@ quantities (seconds, kilobytes, length).
 seconds.limit <- 0.01
 done.vec <- NULL
 measure.vars <- c("seconds","kilobytes","length")
-press_result <- bench::press(
-  N = N_seq,
-  {
-    exprs <- function(...){
-      as.list(match.call()[-1])
-    }
-    elist <- exprs(
-      vector=numeric(N),
-      matrix=matrix(0, N, N),
-      Matrix=Matrix(0, N, N))
-    elist[names(done.vec)] <- NA #Don't run exprs which already exceeded limit.
-    mark.args <- c(elist, list(iterations=10, check=FALSE))
-    mark.result <- do.call(bench::mark, mark.args)
-    ## Rename some columns for easier interpretation.
-    desc.vec <- attr(mark.result$expression, "description")
-    mark.result$description <- desc.vec
-    mark.result$seconds <- as.numeric(mark.result$median)
-    mark.result$kilobytes <- as.numeric(mark.result$mem_alloc/1024)
-    ## Compute length column to measure in addition to time/memory.
-    mark.result$length <- NA
-    for(desc.i in seq_along(desc.vec)){
-      description <- desc.vec[[desc.i]]
-      result <- eval(elist[[description]])
-      mark.result$length[desc.i] <- length(result)
-    }
-    ## Set NA time/memory/length for exprs which were not run.
-    mark.result[desc.vec %in% names(done.vec), measure.vars] <- NA
-    ## If expr went over time limit, indicate it is done.
-    over.limit <- mark.result$seconds > seconds.limit
-    over.desc <- desc.vec[is.finite(mark.result$seconds) & over.limit]
-    done.vec[over.desc] <<- TRUE
-    mark.result
+press_result <- bench::press(N = N_seq, {
+  exprs <- function(...)as.list(match.call()[-1])
+  elist <- exprs(
+    vector=numeric(N),
+    matrix=matrix(0, N, N),
+    Matrix=Matrix(0, N, N))
+  elist[names(done.vec)] <- NA #Don't run exprs which already exceeded limit.
+  mark.args <- c(elist, list(iterations=10, check=FALSE))
+  mark.result <- do.call(bench::mark, mark.args)
+  ## Rename some columns for easier interpretation.
+  desc.vec <- attr(mark.result$expression, "description")
+  mark.result$description <- desc.vec
+  mark.result$seconds <- as.numeric(mark.result$median)
+  mark.result$kilobytes <- as.numeric(mark.result$mem_alloc/1024)
+  ## Compute length column to measure in addition to time/memory.
+  mark.result$length <- NA
+  for(desc.i in seq_along(desc.vec)){
+    description <- desc.vec[[desc.i]]
+    result <- eval(elist[[description]])
+    mark.result$length[desc.i] <- length(result)
   }
-)
+  ## Set NA time/memory/length for exprs which were not run.
+  mark.result[desc.vec %in% names(done.vec), measure.vars] <- NA
+  ## If expr went over time limit, indicate it is done.
+  over.limit <- mark.result$seconds > seconds.limit
+  over.desc <- desc.vec[is.finite(mark.result$seconds) & over.limit]
+  done.vec[over.desc] <<- TRUE
+  mark.result
+})
 ```
 
 The `bench::press` code above is relatively complicated, because it re-implements two functions that are provided by atime:
@@ -156,7 +151,7 @@ vec.mat.pred <- predict(
   vec.mat.best,
   seconds=vec.mat.result$seconds.limit,
   ##kilobytes=1000,#not available on CRAN.
-  length=1e6)
+  length=100)
 plot(vec.mat.pred)
 ```