Performance Drop3395.Rmd

---
title: "Performance"
author: "Doris Amoakohene"
date: "`r Sys.Date()`"
output: html_document
---



Performance drop with 1.12.0 (Selection + assignment)
#3395
https://github.com/Rdatatable/data.table/issues/3395

```{r}

library(atime)
library(data.table)
library(ggplot2)
library(git2r)
```

```{r}
  tdir <- tempfile()
  dir.create(tdir)
  git2r::clone("https://github.com/Rdatatable/data.table", tdir)
  
```

```{r}

atime.list <- atime::atime_versions(
pkg.path=tdir,
pkg.edit.fun=function(old.Package, new.Package, sha, new.pkg.path){
      pkg_find_replace <- function(glob, FIND, REPLACE){
        atime::glob_find_replace(file.path(new.pkg.path, glob), FIND, REPLACE)
      }
      Package_regex <- gsub(".", "_?", old.Package, fixed=TRUE)
      Package_ <- gsub(".", "_", old.Package, fixed=TRUE)
      new.Package_ <- paste0(Package_, "_", sha)
      pkg_find_replace(
        "DESCRIPTION", 
        paste0("Package:\\s+", old.Package),
        paste("Package:", new.Package))
      pkg_find_replace(
        file.path("src","Makevars.*in"),
        Package_regex,
        new.Package_)
      pkg_find_replace(
        file.path("R", "onLoad.R"),
        Package_regex,
        new.Package_)
      pkg_find_replace(
        file.path("R", "onLoad.R"),
        sprintf('packageVersion\\("%s"\\)', old.Package),
        sprintf('packageVersion\\("%s"\\)', new.Package))
      pkg_find_replace(
        file.path("src", "init.c"),
        paste0("R_init_", Package_regex),
        paste0("R_init_", gsub("[.]", "_", new.Package_)))
      pkg_find_replace(
        "NAMESPACE",
        sprintf('useDynLib\\("?%s"?', Package_regex),
        paste0('useDynLib(', new.Package_))
    },
  N=10^seq(3,8),
  setup={ 
    n_day <- 60
    n_clientid <- 1e5
    n_Platform <- 7
    X <- data.table(
  day = sample(1:n_day, N, TRUE),
  clientid = as.character(sample(1:n_clientid, N, TRUE)),
  Platform = as.character(sample(1:n_Platform, N, TRUE))
)
  },
  expr=data.table:::`[.data.table`( X(, .(x = uniqueN(day) - 1L,
                                          first_active_day = min(day),
                                          last_active_day = max(day)),
                                      by = .(Platform, clientid)),
  "Before"="5b6ded1fbd4d480a5f854470b9696d09b9fb6dd9",#https://github.com/Rdatatable/data.table/tree/5b6ded1fbd4d480a5f854470b9696d09b9fb6dd9
  "Regression"="662d165246bba60877af84550689416ffb06584d", #https://github.com/Rdatatable/data.table/tree/662d165246bba60877af84550689416ffb06584d
  "Fixed"="324b4b2a7b080cc98c9982ef4a77260392d5f32b") #fixed:https://github.com/Rdatatable/data.table/tree/324b4b2a7b080cc98c9982ef4a77260392d5f32b