sinarueeger · July 17, 2019 14:09
diff --git a/1-user-2019.md b/1-user-2019.md
diff --git a/2-examples.R b/2-examples.R

 ## 1. tidy eval
 ## 2. usethis
 ## 3. pkg
 ## 4. tidyr
 ## 5. vroom
 ## 6. data.table
 ## 7. rray


 ## ===================================================================
 ## tidy eval
 ## ===================================================================

 ## by Lionel Henry


 ## example with dplyr ------------------------------------------------

 library(dplyr)
 iris %>% 
  group_by(Species) %>%
  summarise(avg = mean(Petal.Length, na.rm = TRUE))


 ## with tidyeval
 group_mean <- function(data, by, var) {
  
  data %>%
    group_by({{ by }}) %>%
    summarise(avg = mean({{ var }}, na.rm = TRUE))
 }

 group_mean(data = iris, by = Species, var = Petal.Length)
 group_mean(data = msleep, by = vore, var = sleep_total)



 ## an example with ggplot2 -------------------------------------------

 library(ggplot2)
 theme_set(theme_bw())
 ggplot(data = iris, aes(x = Sepal.Length, y = Petal.Length, group = Species, color = Species)) +
  geom_point() +
  geom_smooth(method = "lm")

 ## tidyeval
 plot_point_smooth <- function(data, x, y, gr = NULL, method = "lm") {
  
  ggplot(data = data, aes({{ x }}, {{ y }}, group = {{ gr }}, color = {{ gr }})) +
    geom_point() +
    geom_smooth(method = method)
  
 }
 plot_point_smooth(iris, x = Sepal.Length, y = Petal.Length, gr = Species)
 plot_point_smooth(msleep, x = sleep_total, y = sleep_rem, gr = NULL)


 ## ===================================================================
 ## usethis
 ## ===================================================================

 ## by Jenny Bryan



 library(usethis)

 ## 1.
 create_package("~/tmp/mypackage")

 ## 2. 
 use_git()

 ## 3. 
 use_mit_license()
 use_rprofile()
 use_mit_license()

 ## 4. 
 devtools::check()

 ## 5. commit

 ## 6. 
 use_github()

 ## updates DESCRIPTION file

 ## 7.
 devtools::install()

 ## 8.
 use_readme_rmd()
 ## knit + commit + push

 ## clean up
 fs::dir_delete("~/tmp/mypackage")


 ## ===================================================================
 ## pak 
 ## ===================================================================

 ## by Gábor Csárdi

 #install.packages("pak")

 ## basic pkg installation --------------------------------------------

 pak::pkg_install("usethis")
 pak::pkg_remove("usethis")
 pak::pkg_install("r-lib/usethis")
 pak::pkg_status("usethis")



 ## go to a project (needs a .Proj file) ------------------------------

 usethis::create_project("~/tmp/test")
 dir()
 pak:::proj_create()
 dir()
 readLines("DESCRIPTION")
 pak:::proj_install("usethis")
 ## this installs dependencies into a private project library
 readLines("DESCRIPTION")

 ## cleaning up -------------------------------------------------------
 fs::dir_delete("~/tmp/test")


 ## ===================================================================
 ## pivot_wide and long 
 ## ===================================================================

 ## by Hadley Wickham

 # pak::pkg_install("tidyverse/tidyr")

 library(tidyr)

 # pak::pkg_install("chrk623/dataAnim")
 # Master's Thesis project by Charco Hui

 library(dataAnim)
 datoy_wide
 ## this needs to be longer

 datoy_long
 ## this needs to be wider

 ## lets make it longer
 datoy_wide %>%
  pivot_longer(-Name, names_to = "Subject", values_to = "Grade")

 ## lets make it wider
 datoy_long %>%
  dplyr::mutate(Time = 1:nrow(datoy_long)) %>%
  pivot_wider(names_from = "Subject", values_from = c("Score", "Time"))



 ## ===================================================================
 ## vroom
 ## ===================================================================

 ## by Jim Hester

 ## get a large data (> 10 MB) ----------------------------------------

 ## from here: https://portals.broadinstitute.org/collaboration/giant/index.php/GIANT_consortium_data_files

 ## Height
 download.file("https://portals.broadinstitute.org/collaboration/giant/images/8/80/Height_AA_add_SV.txt.gz", "Height_AA_add_SV.txt.gz")

 ## BMI
 download.file("https://portals.broadinstitute.org/collaboration/giant/images/3/33/BMI_African_American.fmt.gzip", "BMI_African_American.fmt.gzip")

 path_to_file_1 <- "Height_AA_add_SV.txt.gz"
 path_to_file_2 <- "BMI_African_American.fmt.gzip" #Height_HA_add_SV.txt.gz"

 ## file size
 ## pak::pkg_install("fs")
 ## library(fs)
 fs::file_size(path_to_file_1)
 fs::file_size(path_to_file_2)


 ## vroom -------------------------------------------------------------
 ## pak::pkg_install("vroom")
 library(vroom)
 library(dplyr)

 system.time(
  giant_vroom <- vroom::vroom(path_to_file_1)
 )
 giant_vroom
 ## 0.154 sec

 system.time(
 tmp <- giant_vroom %>% select(CHR, POS) %>% filter(CHR == 1)
  )
 ## 0.001 sec


 ## with DT
 system.time(
  giant_DT <- data.table::fread(path_to_file_1)
 )
 ## 0.107 sec

 system.time(
  giant_DT %>% select(CHR, POS) %>% filter(CHR == 1)
 )
 ## 0.002 sec


 ## col_select --------------------------------------------------------
 giant_vroom_select <- vroom::vroom(path_to_file_1, 
                                   col_select = list(SNPNAME, ends_with("_MAF")))
 head(giant_vroom_select)

 giant_vroom_remove <- vroom::vroom(path_to_file_1, 
                                   col_select = -ExAC_AFR_MAF)
 head(giant_vroom_remove)

 giant_vroom_rename <- vroom::vroom(path_to_file_1, 
                                   col_select = list(p = Pvalue, everything()))
 head(giant_vroom_rename)


 ## multiple dataset --------------------------------------------------
 data_combined <- vroom::vroom( 
                    c(path_to_file_1, path_to_file_2), 
                    id = "path")
 table(data_combined$path)

 ## compare to purrr + fread



 ## ===================================================================
 ## data.table
 ## ===================================================================

 ## by Arun Srinivasan

 # pak::pkg_install("data.table")
 library(data.table)

 p <- 2e8
 dat <- data.table(x = sample(1e5, p, TRUE), y = runif(p))

 system.time(
  tmp <- dat[x %in% 2000:3000, ]
 )

 system.time(
  tmp <- dat[x %in% 2000:3000, ]
 )



 ## ===================================================================
 ## rray
 ## ===================================================================

 ## by Davis Vaughan

 ## devtools::install_github("r-lib/rray")

 ## default -----------------------------------------------------------
 mat_1 <- matrix(c(15, 10, 8, 6, 12, 9), byrow = FALSE, nrow = 2) 
 mat_2 <- matrix(c(5, 2, 3), nrow = 1)

 ## lesson 1
 mat_1 + mat_2

 ## lesson 2
 dim(mat_1[,2:3])
 dim(mat_1[,1]) ## why not 2x1?

 length(mat_1[,1]) ## turned into a vector!
 dim(mat_1[,1, drop = FALSE]) ## but with drop = FALSE we can keep it a matrix

 ## rray ---------------------------------------------------------------
 library(rray)

 (mat_1_rray <- rray(c(15, 10, 8, 6, 12, 9), dim = c(2, 3)))
 (mat_2_rray <- rray(c(5, 2, 3), dim = c(1, 3)))

 ## lesson 1
 mat_1_rray + mat_2_rray

 ## lesson 2
 dim(mat_1_rray[,2:3])
 dim(mat_1_rray[,1])

 ## smart functions
 mat_1_rray / rray_sum(mat_1_rray, axes = 1)
 rray_bind(mat_1_rray, mat_2_rray, .axis = 1)
 rray_bind(mat_1_rray, mat_2_rray, .axis = 2)




 ## ===================================================================
 ## rstatsmeme
 ## ===================================================================

 ## discovered via Frie

 # pak::pkg_install("favstats/rstatsmemes")
 library(rstatsmemes)
 show_me_an_R_meme()

	## 1. tidy eval
	## 2. usethis
	## 3. pkg
	## 4. tidyr
	## 5. vroom
	## 6. data.table
	## 7. rray


	## ===================================================================
	## tidy eval
	## ===================================================================

	## by Lionel Henry


	## example with dplyr ------------------------------------------------

	library(dplyr)
	iris %>%
	group_by(Species) %>%
	summarise(avg = mean(Petal.Length, na.rm = TRUE))


	## with tidyeval
	group_mean <- function(data, by, var) {

	data %>%
	group_by({{ by }}) %>%
	summarise(avg = mean({{ var }}, na.rm = TRUE))
	}

	group_mean(data = iris, by = Species, var = Petal.Length)
	group_mean(data = msleep, by = vore, var = sleep_total)



	## an example with ggplot2 -------------------------------------------

	library(ggplot2)
	theme_set(theme_bw())
	ggplot(data = iris, aes(x = Sepal.Length, y = Petal.Length, group = Species, color = Species)) +
	geom_point() +
	geom_smooth(method = "lm")

	## tidyeval
	plot_point_smooth <- function(data, x, y, gr = NULL, method = "lm") {

	ggplot(data = data, aes({{ x }}, {{ y }}, group = {{ gr }}, color = {{ gr }})) +
	geom_point() +
	geom_smooth(method = method)

	}
	plot_point_smooth(iris, x = Sepal.Length, y = Petal.Length, gr = Species)
	plot_point_smooth(msleep, x = sleep_total, y = sleep_rem, gr = NULL)


	## ===================================================================
	## usethis
	## ===================================================================

	## by Jenny Bryan



	library(usethis)

	## 1.
	create_package("~/tmp/mypackage")

	## 2.
	use_git()

	## 3.
	use_mit_license()
	use_rprofile()
	use_mit_license()

	## 4.
	devtools::check()

	## 5. commit

	## 6.
	use_github()

	## updates DESCRIPTION file

	## 7.
	devtools::install()

	## 8.
	use_readme_rmd()
	## knit + commit + push

	## clean up
	fs::dir_delete("~/tmp/mypackage")


	## ===================================================================
	## pak
	## ===================================================================

	## by Gábor Csárdi

	#install.packages("pak")

	## basic pkg installation --------------------------------------------

	pak::pkg_install("usethis")
	pak::pkg_remove("usethis")
	pak::pkg_install("r-lib/usethis")
	pak::pkg_status("usethis")



	## go to a project (needs a .Proj file) ------------------------------

	usethis::create_project("~/tmp/test")
	dir()
	pak:::proj_create()
	dir()
	readLines("DESCRIPTION")
	pak:::proj_install("usethis")
	## this installs dependencies into a private project library
	readLines("DESCRIPTION")

	## cleaning up -------------------------------------------------------
	fs::dir_delete("~/tmp/test")


	## ===================================================================
	## pivot_wide and long
	## ===================================================================

	## by Hadley Wickham

	# pak::pkg_install("tidyverse/tidyr")

	library(tidyr)

	# pak::pkg_install("chrk623/dataAnim")
	# Master's Thesis project by Charco Hui

	library(dataAnim)
	datoy_wide
	## this needs to be longer

	datoy_long
	## this needs to be wider

	## lets make it longer
	datoy_wide %>%
	pivot_longer(-Name, names_to = "Subject", values_to = "Grade")

	## lets make it wider
	datoy_long %>%
	dplyr::mutate(Time = 1:nrow(datoy_long)) %>%
	pivot_wider(names_from = "Subject", values_from = c("Score", "Time"))



	## ===================================================================
	## vroom
	## ===================================================================

	## by Jim Hester

	## get a large data (> 10 MB) ----------------------------------------

	## from here: https://portals.broadinstitute.org/collaboration/giant/index.php/GIANT_consortium_data_files

	## Height
	download.file("https://portals.broadinstitute.org/collaboration/giant/images/8/80/Height_AA_add_SV.txt.gz", "Height_AA_add_SV.txt.gz")

	## BMI
	download.file("https://portals.broadinstitute.org/collaboration/giant/images/3/33/BMI_African_American.fmt.gzip", "BMI_African_American.fmt.gzip")

	path_to_file_1 <- "Height_AA_add_SV.txt.gz"
	path_to_file_2 <- "BMI_African_American.fmt.gzip" #Height_HA_add_SV.txt.gz"

	## file size
	## pak::pkg_install("fs")
	## library(fs)
	fs::file_size(path_to_file_1)
	fs::file_size(path_to_file_2)


	## vroom -------------------------------------------------------------
	## pak::pkg_install("vroom")
	library(vroom)
	library(dplyr)

	system.time(
	giant_vroom <- vroom::vroom(path_to_file_1)
	)
	giant_vroom
	## 0.154 sec

	system.time(
	tmp <- giant_vroom %>% select(CHR, POS) %>% filter(CHR == 1)
	)
	## 0.001 sec


	## with DT
	system.time(
	giant_DT <- data.table::fread(path_to_file_1)
	)
	## 0.107 sec

	system.time(
	giant_DT %>% select(CHR, POS) %>% filter(CHR == 1)
	)
	## 0.002 sec


	## col_select --------------------------------------------------------
	giant_vroom_select <- vroom::vroom(path_to_file_1,
	col_select = list(SNPNAME, ends_with("_MAF")))
	head(giant_vroom_select)

	giant_vroom_remove <- vroom::vroom(path_to_file_1,
	col_select = -ExAC_AFR_MAF)
	head(giant_vroom_remove)

	giant_vroom_rename <- vroom::vroom(path_to_file_1,
	col_select = list(p = Pvalue, everything()))
	head(giant_vroom_rename)


	## multiple dataset --------------------------------------------------
	data_combined <- vroom::vroom(
	c(path_to_file_1, path_to_file_2),
	id = "path")
	table(data_combined$path)

	## compare to purrr + fread



	## ===================================================================
	## data.table
	## ===================================================================

	## by Arun Srinivasan

	# pak::pkg_install("data.table")
	library(data.table)

	p <- 2e8
	dat <- data.table(x = sample(1e5, p, TRUE), y = runif(p))

	system.time(
	tmp <- dat[x %in% 2000:3000, ]
	)

	system.time(
	tmp <- dat[x %in% 2000:3000, ]
	)



	## ===================================================================
	## rray
	## ===================================================================

	## by Davis Vaughan

	## devtools::install_github("r-lib/rray")

	## default -----------------------------------------------------------
	mat_1 <- matrix(c(15, 10, 8, 6, 12, 9), byrow = FALSE, nrow = 2)
	mat_2 <- matrix(c(5, 2, 3), nrow = 1)

	## lesson 1
	mat_1 + mat_2

	## lesson 2
	dim(mat_1[,2:3])
	dim(mat_1[,1]) ## why not 2x1?

	length(mat_1[,1]) ## turned into a vector!
	dim(mat_1[,1, drop = FALSE]) ## but with drop = FALSE we can keep it a matrix

	## rray ---------------------------------------------------------------
	library(rray)

	(mat_1_rray <- rray(c(15, 10, 8, 6, 12, 9), dim = c(2, 3)))
	(mat_2_rray <- rray(c(5, 2, 3), dim = c(1, 3)))

	## lesson 1
	mat_1_rray + mat_2_rray

	## lesson 2
	dim(mat_1_rray[,2:3])
	dim(mat_1_rray[,1])

	## smart functions
	mat_1_rray / rray_sum(mat_1_rray, axes = 1)
	rray_bind(mat_1_rray, mat_2_rray, .axis = 1)
	rray_bind(mat_1_rray, mat_2_rray, .axis = 2)




	## ===================================================================
	## rstatsmeme
	## ===================================================================

	## discovered via Frie

	# pak::pkg_install("favstats/rstatsmemes")
	library(rstatsmemes)
	show_me_an_R_meme()