Rename R to R-arrow (#68)

Tmonster · amoeba · web-flow · commit c84afb2ea6d5 · 2023-12-06T09:38:20.000+01:00
* should change arrow to show R-arrow * new arrow benchmarks report solution as R-arrow * update arrow to R-arrow in a few more places * Fix remaining issues in Tmonster#10 (#13) * Fix remaining issues in arrow -> R-arrow rename * Fix bug in rename code in report.R The previous code was causing something wild to happen. The changed code is idiomatic code for replacing values in a data.frame based on a condition. --------- Co-authored-by: Bryce Mecum <petridish@gmail.com>
diff --git a/.github/workflows/regression.yml b/.github/workflows/regression.yml
@@ -17,7 +17,7 @@ jobs:
   strategy:
     fail-fast: false
     matrix:
-      solution: [data.table, collapse, dplyr, pandas, pydatatable, spark, juliadf, juliads, polars, arrow, duckdb, duckdb-latest, datafusion]
+      solution: [data.table, collapse, dplyr, pandas, pydatatable, spark, juliadf, juliads, polars, R-arrow, duckdb, duckdb-latest, datafusion]
   name: Regression Tests solo solutions
   runs-on: ubuntu-20.04
   env:
diff --git a/R-arrow/groupby-R-arrow.R b/R-arrow/groupby-R-arrow.R
@@ -7,13 +7,13 @@ source("./_helpers/helpers.R")
 stopifnot(requireNamespace("bit64", quietly=TRUE)) # used in chk to sum numeric columns
 .libPaths("./arrow/r-arrow") # tidyverse/dplyr#4641 ## leave it like here in case if this affects arrow pkg as well
 suppressPackageStartupMessages({
-  library("arrow", lib.loc="./arrow/r-arrow", warn.conflicts=FALSE)
-  library("dplyr", lib.loc="./arrow/r-arrow", warn.conflicts=FALSE)
+  library("arrow", lib.loc="./R-arrow/r-arrow", warn.conflicts=FALSE)
+  library("dplyr", lib.loc="./R-arrow/r-arrow", warn.conflicts=FALSE)
 })
 ver = packageVersion("arrow")
 git = ""
 task = "groupby"
-solution = "arrow"
+solution = "R-arrow"
 fun = "group_by"
 cache = TRUE
 on_disk = FALSE
diff --git a/R-arrow/join-R-arrow.R b/R-arrow/join-R-arrow.R
@@ -6,13 +6,13 @@ source("./_helpers/helpers.R")
 
 .libPaths("./arrow/r-arrow") # tidyverse/dplyr#4641 ## leave it like here in case if this affects arrow pkg as well
 suppressPackageStartupMessages({
-  library("arrow", lib.loc="./arrow/r-arrow", warn.conflicts=FALSE)
-  library("dplyr", lib.loc="./arrow/r-arrow", warn.conflicts=FALSE)
+  library("arrow", lib.loc="./R-arrow/r-arrow", warn.conflicts=FALSE)
+  library("dplyr", lib.loc="./R-arrow/r-arrow", warn.conflicts=FALSE)
 })
 ver = packageVersion("arrow")
 git = ""
 task = "join"
-solution = "arrow"
+solution = "R-arrow"
 cache = TRUE
 on_disk = FALSE
 
diff --git a/R-arrow/setup-R-arrow.sh b/R-arrow/setup-R-arrow.sh
@@ -0,0 +1,6 @@
+#!/bin/bash
+set -e
+
+# install stable arrow
+mkdir -p ./R-arrow/r-arrow
+Rscript -e 'install.packages(c("arrow","dplyr"), lib="./R-arrow/r-arrow")'
diff --git a/R-arrow/upg-R-arrow.sh b/R-arrow/upg-R-arrow.sh
@@ -3,4 +3,4 @@ set -e
 
 # upgrade all packages in arrow library only if new arrow is out
 echo 'upgrading arrow...'
-Rscript -e 'ap=available.packages(); if (ap["arrow","Version"]!=packageVersion("arrow", lib.loc="./arrow/r-arrow")) update.packages(lib.loc="./arrow/r-arrow", ask=FALSE, checkBuilt=TRUE, quiet=TRUE)'
+Rscript -e 'ap=available.packages(); if (ap["arrow","Version"]!=packageVersion("arrow", lib.loc="./R-arrow/r-arrow")) update.packages(lib.loc="./R-arrow/r-arrow", ask=FALSE, checkBuilt=TRUE, quiet=TRUE)'
diff --git a/R-arrow/ver-R-arrow.sh b/R-arrow/ver-R-arrow.sh
@@ -0,0 +1,4 @@
+#!/bin/bash
+set -e
+
+Rscript -e 'v=read.dcf(system.file(package="arrow", lib.loc="./R-arrow/r-arrow", "DESCRIPTION"), fields=c("Version","RemoteSha")); colnames(v)[colnames(v)=="RemoteSha"]="Revision"; cnafill=function(x) {x=c(x); x[is.na(x)]=""; x}; fw=function(f, v) writeLines(v, file.path("R-arrow", f)); invisible(mapply(fw, toupper(colnames(v)), cnafill(v)))'
diff --git a/_benchplot/benchplot-dict.R b/_benchplot/benchplot-dict.R
@@ -42,7 +42,7 @@ solution.dict = {list(
   "juliads" = list(name=c(short="IMD.jl", long="InMemoryDatasets.jl"), color=c(strong="#b80000", light="#ff1f1f")),
   "clickhouse" = list(name=c(short="clickhouse", long="ClickHouse"), color=c(strong="hotpink4", light="hotpink1")),
   "polars" = list(name=c(short="polars", long="Polars"), color=c(strong="deepskyblue4", light="deepskyblue3")),
-  "arrow" = list(name=c(short="arrow", long="Arrow"), color=c(strong="aquamarine3", light="aquamarine1")),
+  "R-arrow" = list(name=c(short="R-arrow", long="R-arrow"), color=c(strong="aquamarine3", light="aquamarine1")),
   "duckdb" = list(name=c(short="duckdb", long="DuckDB"), color=c(strong="#ddcd07", light="#fff100")),
   "duckdb-latest" = list(name=c(short="duckdb-latest", long="duckdb-latest"), color=c(strong="#ddcd07", light="#fff100")),
   "datafusion" = list(name=c(short="datafusion", long="Datafusion"), color=c(strong="deepskyblue4", light="deepskyblue3"))
@@ -199,7 +199,7 @@ groupby.syntax.dict = {list(
     "regression v1 v2 by id2 id4" = "DF.groupby(['id2','id4']).agg((pl.pearson_corr('v1','v2')**2).alias('r2')).collect()",
     "sum v3 count by id1:id6" = "DF.groupby(['id1','id2','id3','id4','id5','id6']).agg([pl.sum('v3').alias('v3'), pl.count('v1').alias('count')]).collect()"
   )},
-  "arrow" = {c(
+  "R-arrow" = {c(
     "sum v1 by id1" = "AT %>% group_by(id1) %>% summarise(v1=sum(v1, na.rm=TRUE))",
     "sum v1 by id1:id2" = "AT %>% group_by(id1, id2) %>% summarise(v1=sum(v1, na.rm=TRUE))",
     "sum v1 mean v3 by id3" = "AT %>% group_by(id3) %>% summarise(v1=sum(v1, na.rm=TRUE), v3=mean(v3, na.rm=TRUE))",
@@ -260,7 +260,7 @@ groupby.syntax.dict = {list(
   "juliads" =     list(),
   "clickhouse" =  list(),
   "polars"     =  list(),
-  "arrow"      =  list("Expression row_number() <= 2L not supported in Arrow; pulling data into R" = "max v1 - min v2 by id3", "Expression cor(v1, v2, ... is not supported in arrow; pulling data into R" = "regression v1 v2 by id2 id4"),
+  "R-arrow"      =  list("Expression row_number() <= 2L not supported in R-arrow; pulling data into R" = "max v1 - min v2 by id3", "Expression cor(v1, v2, ... is not supported in R-arrow; pulling data into R" = "regression v1 v2 by id2 id4"),
   "duckdb"     =  list(),
   "duckdb-latest"     =  list(),
   "datafusion" =  list()
@@ -309,7 +309,7 @@ groupby.data.exceptions = {list(
   "polars" = {list(
     # "out of memory" = c("G1_1e9_1e2_0_0","G1_1e9_1e1_0_0","G1_1e9_2e0_0_0","G1_1e9_1e2_0_1","G1_1e9_1e2_5_0") # q10
   )},
-  "arrow" = {list(
+  "R-arrow" = {list(
     # "timeout" = c(), # q10
     "internal error" = c("G1_1e8_2e0_0_0", "G1_1e8_1e2_0_1", "G1_1e8_1e2_5_0", "G1_1e9_1e2_0_0","G1_1e9_1e2_0_1","G1_1e9_1e2_5_0","G1_1e9_1e1_0_0", # inherits from dplyr
                          "G1_1e9_2e0_0_0"), # #190
@@ -413,7 +413,7 @@ join.syntax.dict = {list(
     "medium inner on factor" = "DF.merge(medium, on='id5')",
     "big inner on int" = "DF.merge(big, on='id3')"
   )},
-  "arrow" = {c(
+  "R-arrow" = {c(
     "small inner on int" = "inner_join(DF, small, by='id1')",
     "medium inner on int" = "inner_join(DF, medium, by='id2')",
     "medium outer on int" = "left_join(DF, medium, by='id2')",
@@ -454,7 +454,7 @@ join.query.exceptions = {list(
   "juliads" =     list(),
   "clickhouse" =  list(),
   "polars"     =  list(),
-  "arrow"      =  list(),
+  "R-arrow"      =  list(),
   "duckdb"     =  list(),
   "duckdb-latest"     =  list(),
   "datafusion" =  list()
@@ -496,7 +496,7 @@ join.data.exceptions = {list(
   "polars" = {list(
     "out of memory" = c("J1_1e9_NA_0_0","J1_1e9_NA_5_0","J1_1e9_NA_0_1")
   )},
-  "arrow" = {list(
+  "R-arrow" = {list(
     "out of memory" = c("J1_1e9_NA_0_0","J1_1e9_NA_5_0","J1_1e9_NA_0_1", "J1_1e8_NA_0_0", "J1_1e8_NA_5_0", "J1_1e8_NA_0_1" )#,
     # "not yet implemented: #189" = c("J1_1e7_NA_0_0","J1_1e7_NA_5_0","J1_1e7_NA_0_1","J1_1e8_NA_0_0","J1_1e8_NA_5_0","J1_1e8_NA_0_1","J1_1e9_NA_0_0","J1_1e9_NA_5_0","J1_1e9_NA_0_1")
   )},
diff --git a/_control/solutions.csv b/_control/solutions.csv
@@ -25,8 +25,8 @@ clickhouse,groupby
 clickhouse,join
 polars,groupby
 polars,join
-arrow,groupby
-arrow,join
+R-arrow,groupby
+R-arrow,join
 duckdb,groupby
 duckdb,join
 duckdb-latest,groupby
diff --git a/_launcher/launcher.R b/_launcher/launcher.R
@@ -14,7 +14,7 @@ readret = function(x) {
 file.ext = function(x) {
   ans = switch(
     x,
-    "collapse"=, "data.table"=, "dplyr"=, "h2o"=, "arrow"=, "duckdb"="R", "duckdb-latest"="R",
+    "collapse"=, "data.table"=, "dplyr"=, "h2o"=, "R-arrow"=, "duckdb"="R", "duckdb-latest"="R",
     "pandas"=, "spark"=, "pydatatable"=, "modin"=, "dask"=, "datafusion"=, "polars"="py",
     "clickhouse"="sql",
     "juliadf"="jl", "juliads"="jl",
diff --git a/_launcher/solution.R b/_launcher/solution.R
@@ -110,7 +110,7 @@ if ("quiet" %in% names(args)) {
 file.ext = function(x) {
   ans = switch(
     x,
-    "collapse"=, "data.table"=, "dplyr"=, "h2o"=, "arrow"=, "duckdb"="R", "duckdb-latest"="R",
+    "collapse"=, "data.table"=, "dplyr"=, "h2o"=, "R-arrow"=, "duckdb"="R", "duckdb-latest"="R",
     "pandas"="py", "spark"=, "pydatatable"=, "modin"=, "dask"=, "datafusion"=, "polars"="py",
     "clickhouse"="sql",
     "juliadf"="jl", "juliads"="jl"
diff --git a/_report/report.R b/_report/report.R
@@ -6,7 +6,7 @@ get_report_status_file = function(path=getwd()) {
   file.path(path, "report-done")
 }
 get_report_solutions = function() {
-  c("collapse", "data.table", "dplyr", "pandas", "pydatatable", "spark", "dask", "juliadf", "juliads", "clickhouse", "cudf", "polars","arrow","duckdb", "duckdb-latest", "datafusion")
+  c("collapse", "data.table", "dplyr", "pandas", "pydatatable", "spark", "dask", "juliadf", "juliads", "clickhouse", "cudf", "polars", "duckdb", "duckdb-latest", "datafusion", "arrow", "R-arrow")
 }
 get_data_levels = function() {
   ## groupby
@@ -69,6 +69,9 @@ clean_time = function(d) {
   if (nrow(d[!nzchar(version) | is.na(version)]))
     stop("timings data contains NA or '' as version field, that should not happen")
   old_advanced_groupby_questions = c("median v3 sd v3 by id2 id4","max v1 - min v2 by id2 id4","largest two v3 by id2 id4","regression v1 v2 by id2 id4","sum v3 count by id1:id6")
+
+  # replace arrow with R-arrow (see https://github.com/duckdblabs/db-benchmark/pull/66)
+  d[which(solution == "arrow"),c("solution")] == "R-arrow"
   d[!nzchar(git), git := NA_character_
     ][,"on_disk" := as.logical(on_disk)
       ][task=="groupby" & solution%in%c("pandas","dask","spark") & batch<1558106628, "out_cols" := NA_integer_
@@ -243,9 +246,13 @@ transform = function(ld) {
 # all ----
 
 time_logs = function(path=getwd()) {
-  ct = clean_time(load_time(path=getwd()))
+  lt <- load_time(path=getwd())
+
+  ct = clean_time(lt)
   d = model_time(ct)
-  l = model_logs(clean_logs(load_logs(path=path)))
+  ll <- load_logs(path=path)
+  ll$solution[ll$solution == "arrow"] <- "R-arrow"
+  l = model_logs(clean_logs(ll))
   q = model_questions(clean_questions(load_questions(path=path)))
   
   lq = merge_logs_questions(l, q)
diff --git a/arrow/setup-arrow.sh b/arrow/setup-arrow.sh
diff --git a/arrow/ver-arrow.sh b/arrow/ver-arrow.sh
diff --git a/run.conf b/run.conf
@@ -1,7 +1,7 @@
 # task, used in init-setup-iteration.R
 export RUN_TASKS="groupby join"
 # solution, used in init-setup-iteration.R
-export RUN_SOLUTIONS="collapse data.table juliads juliadf dplyr pandas pydatatable spark dask clickhouse polars arrow duckdb duckdb-latest datafusion"
+export RUN_SOLUTIONS="collapse data.table juliads juliadf dplyr pandas pydatatable spark dask clickhouse polars R-arrow duckdb duckdb-latest datafusion"
 
 # flag to upgrade tools, used in run.sh on init
 export DO_UPGRADE=false
diff --git a/run.sh b/run.sh
@@ -71,8 +71,8 @@ if [[ "$DO_UPGRADE" == true && "$RUN_SOLUTIONS" =~ "h2o" ]]; then ./h2o/upg-h2o.
 if [[ "$RUN_SOLUTIONS" =~ "h2o" ]]; then ./h2o/ver-h2o.sh; fi;
 if [[ "$DO_UPGRADE" == true && "$RUN_SOLUTIONS" =~ "polars" ]]; then ./polars/upg-polars.sh; fi;
 if [[ "$RUN_SOLUTIONS" =~ "polars" ]]; then ./polars/ver-polars.sh; fi;
-if [[ "$DO_UPGRADE" == true && "$RUN_SOLUTIONS" =~ "arrow" ]]; then ./arrow/upg-arrow.sh; fi;
-if [[ "$RUN_SOLUTIONS" =~ "arrow" ]]; then ./arrow/ver-arrow.sh; fi;
+if [[ "$DO_UPGRADE" == true && "$RUN_SOLUTIONS" =~ "R-arrow" ]]; then ./R-arrow/R-upg-arrow.sh; fi;
+if [[ "$RUN_SOLUTIONS" =~ "R-arrow" ]]; then ./R-arrow/ver-R-arrow.sh; fi;
 if [[ "$DO_UPGRADE" == true && "$RUN_SOLUTIONS" == "duckdb" ]]; then ./duckdb/upg-duckdb.sh; fi;
 if [[ "$RUN_SOLUTIONS" == "duckdb" ]]; then ./duckdb/ver-duckdb.sh; fi;
 if [[ "$DO_UPGRADE" == true && "$RUN_SOLUTIONS" == "duckdb-latest" ]]; then ./duckdb-latest/setup-duckdb-latest.sh; fi;

-Original file line number
+Diff line change
@@ @@ -0,0 +1,4 @@ @@
 +#!/bin/bash
 +set -e
++
 +Rscript -e 'v=read.dcf(system.file(package="arrow", lib.loc="./R-arrow/r-arrow", "DESCRIPTION"), fields=c("Version","RemoteSha")); colnames(v)[colnames(v)=="RemoteSha"]="Revision"; cnafill=function(x) {x=c(x); x[is.na(x)]=""; x}; fw=function(f, v) writeLines(v, file.path("R-arrow", f)); invisible(mapply(fw, toupper(colnames(v)), cnafill(v)))'