dplyr Use Cases: Non-Interactive Mode

The current release of dplyr (v 0.4.1) offers lot more flexibility regarding usage of important verbs in non-interactive mode. In this post, I'm exploring different possible use-cases.

• group_by_, select_, rename_:

For group_by_, select_ and rename_, we can pass a character vector of variable names as an argument to .dots parameter.

• filter_:

To use filter_ function, we need to pass filter criteria as a parameter to .dots. The criteria can be created using lazyeval::interp function.

• mutate_, transmute_, summarise_:

We need to provide 2 things to these functions - a list of functions to be applied on the input variables (with corresponding input variables) and a character vector of output variables names. These 2 things can be passed to the .dots argument using combination of lazyeval::interp  and setNames function.

• joins:

For 2 table verbs, there's no *_join_ function and we don't need one for general purposes. We can just pass a named vector to by argument. setNames function comes in handy while doing this.

The R Code for the above mentioned use cases is shown below and can also be found on this GitHub Gist.

	# using dplyr finctions in non-interactive mode
	# examples
	library(plyr)
	library(dplyr)
	d1 = data_frame(x = seq(1,20),y = rep(1:10,2),z = rep(1:5,4))
	head(d1)
	#### single table verbs ####
	# group_by
	group_by_fn <- function(d_in,gp_vec){
	d_out = d_in %>%
	group_by_(.dots = gp_vec)
	}
	gp_vec = c("y","z")
	d1_gp_by_out = group_by_fn(d1,gp_vec)
	head(d1_gp_by_out)
	# select/rename (haven't included drop variables case)
	select_fn <- function(d_in,sel_vec){
	d_out = d_in %>%
	select_(.dots = sel_vec)
	}
	sel_vec = c("x","y")
	d1_select_out = select_fn(d1,sel_vec)
	head(d1_select_out)
	# filter
	filter_fn <- function(d_in,filter_crit){
	d_out = d_in %>%
	filter_(filter_crit)
	}
	y_vec = 6:8
	filter_crit = interp(~ filter_var %in% y_vec,filter_var = as.name("y"))
	d1_filter_out = filter_fn(d1,filter_crit)
	head(d1_filter_out)
	z_vec = 1:2
	filter_crit2 = interp(~ filter_var1 %in% y_vec & filter_var2 %in% z_vec,.values = list(filter_var1 = as.name("y"),
	filter_var2 = as.name("z")))
	d1_filter2_out = filter_fn(d1,filter_crit2)
	head(d1_filter2_out)
	# mutate, transmute, summarise
	mutate_fn <- function(d_in,op_ls,var_vec){
	d_out = d_in %>%
	mutate_(.dots = setNames(op_ls,var_vec))
	}
	var1_rng = 3:5
	op_ls = list(interp(~f(var1,var2), .values = list(f = as.name("*"),
	var1 = as.name("x"),
	var2 = as.name("y"))),
	interp(~f(var1 %in% var1_rng,var2,var3),.values= list(f = as.name("ifelse"),
	var1 = as.name("x"),
	var2 = as.name("y"),
	var3 = as.name("z"))))
	var_vec = c("yy","zz")
	d1_mutate_out = mutate_fn(d1, op_ls, var_vec)
	head(d1_mutate_out)
	var_ls = list("yy","zz")
	d1_mutate_out1 = mutate_fn(d1, op_ls, var_ls)
	head(d1_mutate_out1)
	#### two table verbs ####
	# joins
	d2 = data_frame(xx = seq(1,20),yy = rep(1:10,2),zz = rep(1:2,10))
	join_fn <-function(d_in1,d_in2,var_vec1,var_vec2){
	d_out = d_in1 %>%
	left_join(d_in2,setNames(var_vec2,var_vec1))
	}
	var_vec1 = c("x","y")
	var_vec2 = c("xx","yy")
	d_join_out = join_fn(d1,d2,var_vec1,var_vec2)
	head(d_join_out)
	# everything combined (essentially, power of %>%)
	d_combined_out = d1 %>%
	filter_fn(filter_crit) %>%
	group_by_fn(gp_vec) %>%
	mutate_fn(op_ls,var_vec) %>%
	select_fn(c("x","y","z")) %>%
	join_fn(.,d2,var_vec1,var_vec2)
	head(d_combined_out)
	# sources:
	# http://cran.r-project.org/web/packages/dplyr/vignettes/nse.html
	# http://stackoverflow.com/questions/28125816/r-standard-evalation-for-join-dplyr

view raw dplyr_functions_programmatic_use.R hosted with ❤ by GitHub