Re: [R] traceback performs differently in "interactive-mode" then in "script-mode"
Hi Malte,
I think I asked the same question on Stack Overflow ten years ago:
https://stackoverflow.com/q/13116099/559676 I hope you'll find the answer
helpful there.
Regards,
Yihui
--
https://yihui.org
On Wed, Dec 21, 2022 at 6:19 AM Flender, Malte
wrote:
> Hello,
>
> a few days ago I encountered a strange behavior of base R.
> I'm not really sure if it is a bug or not.
> Thus I am somewhat hesitant to write a bug report.
> Instead I write to R-Help to ask you if this behavior can be considered a
> bug or not.
> I started with a question at stackoverflow (
> https://stackoverflow.com/questions/74796994/r-traceback-performs-differently-in-interactive-mode-then-in-script-mode),
> but got no response there.
>
> The strange behavior of base R lies in how it acts differently in an
> interactive R-Session then the execution of an R-Script.
> As you see in the MWE below the traceback()-function returns NULL in
> script mode (first call) and an actual traceback in interactive mode
> (second call).
>
> Can you reproduce this behavior?
>
> Here is MWE, which contains a small test-script and the calls to it in an
> interactive and script mode:
>
> user@server:~/folder> cat test.r
>
> options(error = NULL)
>
> onexit <- function() {
> error.msg <- geterrmessage()
> traceback <- traceback()
>
> print(paste("error.msg: ", nchar(error.msg), sep = ""))
> print(paste("traceback: ", is.null(traceback), " : ", traceback, sep =
> ""))
>
> if (nchar(error.msg) != 0 && !is.null(traceback)) {
> print("Uncaught Error")
> } else if (nchar(error.msg) != 0 && is.null(traceback)) {
> print("Caught Error")
> } else if (nchar(error.msg) == 0 && is.null(traceback)) {
> print("No Error")
> } else {
> stop("ERROR in on.exit: bad traceback error.msg combination")
> }
> }
>
> fail <- function() {
> on.exit(
> onexit(),
> add = TRUE,
> after = TRUE)
>
> print("SOMETHING")
> stop("BAD")
> }
>
> fail()
>
> user@server:~/folder> docker run -it --rm -v /home/user/folder/:/data/R/
> r-base:4.2.2 R -e 'source("/data/R/test.r")'
>
> R version 4.2.2 (2022-10-31) -- "Innocent and Trusting"
> Copyright (C) 2022 The R Foundation for Statistical Computing
> Platform: x86_64-pc-linux-gnu (64-bit)
>
> R is free software and comes with ABSOLUTELY NO WARRANTY.
> You are welcome to redistribute it under certain conditions.
> Type 'license()' or 'licence()' for distribution details.
>
> Natural language support but running in an English locale
>
> R is a collaborative project with many contributors.
> Type 'contributors()' for more information and
> 'citation()' on how to cite R or R packages in publications.
>
> Type 'demo()' for some demos, 'help()' for on-line help, or
> 'help.start()' for an HTML browser interface to help.
> Type 'q()' to quit R.
>
> > source("/data/R/test.r")
> [1] "SOMETHING"
> Error in fail() : BAD
> Calls: source -> withVisible -> eval -> eval -> fail
> No traceback available
> [1] "error.msg: 75"
> [1] "traceback: TRUE : "
> [1] "Caught Error"
> Execution halted
> user@server:~/folder> docker run -it --rm -v /home/user/folder/:/data/R/
> r-base:4.2.2 R
>
> R version 4.2.2 (2022-10-31) -- "Innocent and Trusting"
> Copyright (C) 2022 The R Foundation for Statistical Computing
> Platform: x86_64-pc-linux-gnu (64-bit)
>
> R is free software and comes with ABSOLUTELY NO WARRANTY.
> You are welcome to redistribute it under certain conditions.
> Type 'license()' or 'licence()' for distribution details.
>
> Natural language support but running in an English locale
>
> R is a collaborative project with many contributors.
> Type 'contributors()' for more information and
> 'citation()' on how to cite R or R packages in publications.
>
> Type 'demo()' for some demos, 'help()' for on-line help, or
> 'help.start()' for an HTML browser interface to help.
> Type 'q()' to quit R.
>
> > source("/data/R/test.r")
> [1] "SOMETHING"
> Error in fail() : BAD
> 6: stop("BAD") at test.r#30
> 5: fail() at test.r#33
> 4: eval(ei, envir)
> 3: eval(ei, envir)
> 2: withVisible(eval(ei, envir))
> 1: source("/data/R/test.r")
> [1] "error.msg: 22"
> [1] "traceback: FALSE : stop(\"BAD\")"
> [2] "traceback: FALSE : fail()"
> [3] "traceback: FALSE : eval(ei, envir)"
> [4] "traceback: FALSE : eval(ei, envir)"
> [5] "traceback: FALSE : withVisible(eval(ei, envir))"
> [6] "traceback: FALSE : source(\"/data/R/test.r\")"
> [1] "Uncaught Error"
> >
>
>
> Mit freundlichem Gruß / Best regards
> WAGO GmbH & Co. KG
>
> Malte Flender
> Komplexitätsmanagement / Data Science
> phone: +49 571 887-49779
> fax: +49 571 887-849779
> mailto: malte.flen...@wago.com
>
> WAGO GmbH & Co.KG
> Hansastraße 27
> 32423 Minden
> Deutschland
> http://www.wago.com
Re: [R] [External] Amazing AI
On 12/21/22 7:50 AM, Barry Rowlingson wrote:
Next year one of my R programming assigments will read like this:
"Here is some R code written by a multi-million dollar AI system to
compute [something]. It doesn't work. Fix the bugs, then ask the AI to
write a letter to its creators apologising for how rubbish it is at
coding. Collect one million dollars."
You might want to be careful about such a promise. Kahneman, Sibony,
and Sunstein (2021) Noise: A flaw in human judgment (Little, Brown and
Company) claim that genuine expertise is acquired by learning from
frequent, rapid, high-quality feedback on the quality of their
decisions. Few people have access to such feedback. They call leaders
in fields without such feedback "respect-experts", and note that
respect-experts have only the illusion of competence.
1. They further say that most respect-experts can be beaten by
simple heuristics developed by intelligent lay people.
2. Moreover, with a modest amount of data, ordinary least squares
can beat most such heuristics.
3. And if lots of data are available, AI can beat the simple
heuristics.
They provide substantial quantities of research to support those
claims.
Regarding your million dollars, it should not be hard to write an R
interface to existing AI code cited by Kahneman et al.
Do you really want one of your students initiating a legal procedure
to try to collect your million dollars?
A quarter century ago, my friend Soren Bisgaard told me about a
colleague who had raved about AI. Soren thought, "You prefer artificial
intelligence to real intelligence?"
I perceive a role for AI in identifying subtle phenomena missed by
more understandable modeling techniques. Let's use the best
understandable model, and apply AI to the residuals from that. Then
identify the variables that make the largest contributions to a useful
AI model, and see if they can be added to the other model.
Spencer Graves
On Sun, Dec 18, 2022 at 7:01 PM Boris Steipe wrote:
This email originated outside the University. Check before clicking links or
attachments.
Technically not a help question. But crucial to be aware of, especially for
those of us in academia, or otherwise teaching R. I am not aware of a suitable
alternate forum. If this does not interest you, please simply ignore - I
already know that this may be somewhat OT.
Thanks.
--
You very likely have heard of ChatGPT, the conversation interface on top of the
GPT-3 large language model and that it can generate code. I thought it doesn't
do R - I was wrong. Here is a little experiment:
MY PROMPT:
==
Please write me some R code that will read a tsv file, remove all rows that have duplicates in the
column "names", and store the median values of the remaining rows in a variable called
"Medians". Of course, that calculation should only be done with columns that are numeric.
Print the last variable in order from largest to smallest.
AI RESPONSE:
Here is some R code that should accomplish what you've described:
(Note: the code is formatted in a little terminal window, complete with a button to
"copy code" at the top.)
# Read the tsv file
data <- read.table("file.tsv", header = TRUE, sep = "\t")
# Remove rows with duplicates in the "names" column
data <- data[!duplicated(data$names), ]
# Select only the numeric columns
num_columns <- sapply(data, is.numeric)
numeric_data <- data[, num_columns]
# Calculate the medians for each column
Medians <- apply(numeric_data, 1, median)
# Sort Medians in descending order
Medians <- sort(Medians, decreasing = TRUE)
# Print Medians
print(Medians)
This code assumes that the tsv file is called "file.tsv" and is stored in the
current working directory. It also assumes that the first row of the file contains the
column names.
MY PROMPT:
==
Can you provide me with a bit of sample data that I can use to test this code?
AI RESPONSE:
Certainly! Here is some sample data that you can use to test the code I
provided:
nameage height weight
Alice 23 5.6 120
Bob 32 6.2 180
Charlie 29 5.9 160
Alice 23 5.6 120
David 25 5.8 140
Eve 27 5.5 110
You can save this data as a tsv file and use it to test the code.
--
Notes:
1) The code, as written does not work with the test data. The reason is that the test data
specifies a column "name", but the code assumes "names" (which I specified in
the instructions). Once this is fixed in the test data, the code executes.
2) The instructions are not accurately translated: I had asked for row means.
But changing the margin in the apply() statement from 2 to 1 does the correct
thing.
3) Note that the test data contains both numeric and non-numeric columns.
Re: [R] [External] Amazing AI
Next year one of my R programming assigments will read like this:
"Here is some R code written by a multi-million dollar AI system to
compute [something]. It doesn't work. Fix the bugs, then ask the AI to
write a letter to its creators apologising for how rubbish it is at
coding. Collect one million dollars."
On Sun, Dec 18, 2022 at 7:01 PM Boris Steipe wrote:
>
> This email originated outside the University. Check before clicking links or
> attachments.
>
> Technically not a help question. But crucial to be aware of, especially for
> those of us in academia, or otherwise teaching R. I am not aware of a
> suitable alternate forum. If this does not interest you, please simply ignore
> - I already know that this may be somewhat OT.
>
> Thanks.
> --
>
> You very likely have heard of ChatGPT, the conversation interface on top of
> the GPT-3 large language model and that it can generate code. I thought it
> doesn't do R - I was wrong. Here is a little experiment:
>
> MY PROMPT:
> ==
> Please write me some R code that will read a tsv file, remove all rows that
> have duplicates in the column "names", and store the median values of the
> remaining rows in a variable called "Medians". Of course, that calculation
> should only be done with columns that are numeric. Print the last variable in
> order from largest to smallest.
>
>
> AI RESPONSE:
>
>
> Here is some R code that should accomplish what you've described:
>
> (Note: the code is formatted in a little terminal window, complete with a
> button to "copy code" at the top.)
>
>
> # Read the tsv file
> data <- read.table("file.tsv", header = TRUE, sep = "\t")
>
> # Remove rows with duplicates in the "names" column
> data <- data[!duplicated(data$names), ]
>
> # Select only the numeric columns
> num_columns <- sapply(data, is.numeric)
> numeric_data <- data[, num_columns]
>
> # Calculate the medians for each column
> Medians <- apply(numeric_data, 1, median)
>
> # Sort Medians in descending order
> Medians <- sort(Medians, decreasing = TRUE)
>
> # Print Medians
> print(Medians)
>
>
> This code assumes that the tsv file is called "file.tsv" and is stored in the
> current working directory. It also assumes that the first row of the file
> contains the column names.
>
>
>
> MY PROMPT:
> ==
> Can you provide me with a bit of sample data that I can use to test this code?
>
> AI RESPONSE:
>
> Certainly! Here is some sample data that you can use to test the code I
> provided:
>
>
> nameage height weight
> Alice 23 5.6 120
> Bob 32 6.2 180
> Charlie 29 5.9 160
> Alice 23 5.6 120
> David 25 5.8 140
> Eve 27 5.5 110
>
>
> You can save this data as a tsv file and use it to test the code.
>
>
> --
>
> Notes:
> 1) The code, as written does not work with the test data. The reason is that
> the test data specifies a column "name", but the code assumes "names" (which
> I specified in the instructions). Once this is fixed in the test data, the
> code executes.
>
> 2) The instructions are not accurately translated: I had asked for row means.
> But changing the margin in the apply() statement from 2 to 1 does the correct
> thing.
>
> 3) Note that the test data contains both numeric and non-numeric columns.
> Also, the name "Alice" is duplicated in the test data, which is subtle, and
> the right thing to do.
>
>
> --
>
> A similar experiment, run on the beta-site of OpenAI's Codex code-completion
> tool gives the following code (complete with the comments.):
>
>
> # Read in the data
> data <- read.table("mydata.tsv", sep = "\t", header = TRUE)
>
> # Remove all rows that have duplicates in the column "names"
> unique_names <- unique(data$names)
> data_unique <- data[data$names %in% unique_names,]
>
> # Calculate medians
> Medians <- sapply(data_unique[, sapply(data_unique, is.numeric)], median,
> na.rm = TRUE)
>
> # Print last variable in order form largest to smallest
> rev(sort(Medians[length(Medians)]))
>
>
> Note that the strategy is quite different (e.g using %in%, not duplicated()
> ), the interpretation of "last variable" is technically correct but not what
> I had in mind (ChatGPT got that right though).
>
>
> Changing my prompts slightly resulted it going for a dplyr solution instead,
> complete with %>% idioms etc ... again, syntactically correct but not giving
> me the fully correct results.
>
> --
>
> Bottom line: The AI's ability to translate natural language instructions into
> code is astounding. Errors the AI makes are subtle and probably not easy to
> fix if you don't already know what you are doing. But the way that this can
> be "confidently incorrect" and plausible makes it nearly
[R] traceback performs differently in "interactive-mode" then in "script-mode"
Hello,
a few days ago I encountered a strange behavior of base R.
I'm not really sure if it is a bug or not.
Thus I am somewhat hesitant to write a bug report.
Instead I write to R-Help to ask you if this behavior can be considered a bug
or not.
I started with a question at stackoverflow
(https://stackoverflow.com/questions/74796994/r-traceback-performs-differently-in-interactive-mode-then-in-script-mode),
but got no response there.
The strange behavior of base R lies in how it acts differently in an
interactive R-Session then the execution of an R-Script.
As you see in the MWE below the traceback()-function returns NULL in script
mode (first call) and an actual traceback in interactive mode (second call).
Can you reproduce this behavior?
Here is MWE, which contains a small test-script and the calls to it in an
interactive and script mode:
user@server:~/folder> cat test.r
options(error = NULL)
onexit <- function() {
error.msg <- geterrmessage()
traceback <- traceback()
print(paste("error.msg: ", nchar(error.msg), sep = ""))
print(paste("traceback: ", is.null(traceback), " : ", traceback, sep = ""))
if (nchar(error.msg) != 0 && !is.null(traceback)) {
print("Uncaught Error")
} else if (nchar(error.msg) != 0 && is.null(traceback)) {
print("Caught Error")
} else if (nchar(error.msg) == 0 && is.null(traceback)) {
print("No Error")
} else {
stop("ERROR in on.exit: bad traceback error.msg combination")
}
}
fail <- function() {
on.exit(
onexit(),
add = TRUE,
after = TRUE)
print("SOMETHING")
stop("BAD")
}
fail()
user@server:~/folder> docker run -it --rm -v /home/user/folder/:/data/R/
r-base:4.2.2 R -e 'source("/data/R/test.r")'
R version 4.2.2 (2022-10-31) -- "Innocent and Trusting"
Copyright (C) 2022 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
Natural language support but running in an English locale
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> source("/data/R/test.r")
[1] "SOMETHING"
Error in fail() : BAD
Calls: source -> withVisible -> eval -> eval -> fail
No traceback available
[1] "error.msg: 75"
[1] "traceback: TRUE : "
[1] "Caught Error"
Execution halted
user@server:~/folder> docker run -it --rm -v /home/user/folder/:/data/R/
r-base:4.2.2 R
R version 4.2.2 (2022-10-31) -- "Innocent and Trusting"
Copyright (C) 2022 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
Natural language support but running in an English locale
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> source("/data/R/test.r")
[1] "SOMETHING"
Error in fail() : BAD
6: stop("BAD") at test.r#30
5: fail() at test.r#33
4: eval(ei, envir)
3: eval(ei, envir)
2: withVisible(eval(ei, envir))
1: source("/data/R/test.r")
[1] "error.msg: 22"
[1] "traceback: FALSE : stop(\"BAD\")"
[2] "traceback: FALSE : fail()"
[3] "traceback: FALSE : eval(ei, envir)"
[4] "traceback: FALSE : eval(ei, envir)"
[5] "traceback: FALSE : withVisible(eval(ei, envir))"
[6] "traceback: FALSE : source(\"/data/R/test.r\")"
[1] "Uncaught Error"
>
Mit freundlichem Gruß / Best regards
WAGO GmbH & Co. KG
Malte Flender
Komplexitätsmanagement / Data Science
phone: +49 571 887-49779
fax: +49 571 887-849779
mailto: malte.flen...@wago.com
WAGO GmbH & Co.KG
Hansastraße 27
32423 Minden
Deutschland
http://www.wago.com
Re: [R] Integer division
> Richard O'Keefe > on Wed, 21 Dec 2022 16:44:51 +1300 writes: > Lack of consensus: I should mention Python's // operator, > which does flooring division. I should mention Common > Lisp, where (floor - -), (ceiling - -), (round - -), and > (truncate - -) all return a quotient and appropriate > remainder. I should mention Smalltalk, where // and \\ > are flooring quotient and remainder and quo: and rem: are > truncating quotient and remainder. I should give > dishonourable mention to certain programming languages > where the quotient and remainder operators do not actually > fit together. > Why the lack of consensus: It starts with the fact that > there wasn't an agreed *mathematical* definition. Number > theorists, as a rule, don't care about negative numbers > all that much. To the extent that they do care, x mod y > has to go around in neat cycles, which flooring division > does satisfy and truncating division does not. > It then goes on to early computers which used sign-and- > magnitude or ones-complement representation. In those > computers, truncating division was the *obvious* thing to > do. It also had the nice property that n / (2**k) was the > same thing as an arithmetic right shift by k bits. And > then twos-complement became popular. And not only is the > twos-complement range asymmetric (so that x might be > representable but -x not) but arithmetic right shifts > aren't the same as truncating division any more. Whoops! > And then, although flooring division still made sense > for twos-complement but truncating division didn't really, > new programming languages kept on specifying truncating > division because the programming languages of the 1960s > for the hardware of the 1960s did so. So new hardware > designers supported the new programming languages without > supporting the *reasons* why truncating division had been > used. >> (-8:7)%%4 > [1] 0 1 2 3 0 1 2 3 0 1 2 3 0 1 2 3 > Think about for example histogramming a collection of > integers by their remainders and what would happen with > truncating remainder. > On Tue, 20 Dec 2022 at 19:53, Göran Broström > wrote: >> Thanks Richard, >> >> the "rounding claim" was my mistake (as I replied to >> Martin), I should said "truncates toward zero" as you >> explain. >> >> However, my point was that these two mathematical >> functions should be defined in the documentation, as you >> also say. And I was surprised that there is no consensus >> regarding the definition of such elementary functions. >> >> Göran [...] Thank you all for your contributions, notably Richard's last one providing really interesting historical context (of "why this mess?"). Note that the Wikipedia page https://en.m.wikipedia.org/wiki/Modulo_operation also does mention "Euclidean division" which does have possibly even nicer mathematical properties than the floored division R (and quite a few other good softwares) use. Still, be assured that we won't change R here. Mathematical (Algebra) related R packages can easily introduce corresponding versions of div() and mod() functions, I'd say, and I'd guess these would already exist somewhere. Yesterday, I've updated the ?Arithmetic help page which now does mention (more clearly if it was really already derivable from the previous doc) what happens, also mentioning Knuth and the Wikipedia page. --> https://stat.ethz.ch/R-manual/R-devel/library/base/html/Arithmetic.html (search for "R-devel R-manual ETH" in your browser, then -> 'Packages' -> 'base' ..) Martin -- Martin Maechler ETH Zurich and R Core team __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
