लगभग data.table

## arrays ---------

arrmatr <- array(1:20, c(4,5))

class(arrmatr)

typeof(arrmatr)

is.array(arrmatr)

is.matrix(arrmatr)

## lists ------------------

mylist <- as.list(arrmatr)

is.vector(mylist)

is.list(mylist)

## data.frames ------------

df <- as.data.frame(arrmatr)
df2 <- as.data.frame(mylist)

is.list(df)

df$V6 <- df$V1 + df$V2

## data.tables -----------------------
library(data.table)

data.table::setDT(df)

is.list(df)

is.data.frame(df)

is.data.table(df)

df2 <- df

df[V1 == 1, V2 := 999]

data.table::fsetdiff(df, df2)

df2 <- data.table::copy(df)

df[V1 == 2, V2 := 999]

data.table::fsetdiff(df, df2)

## operations on data.tables ------------

#using list properties

df$'V1'[1]

df[['V1']]

df[[1]][1]

sapply(df, class)

sapply(df, function(x) sum(is.na(x)))

library(magrittr)
library(microbenchmark)

## Bigger example ----

rown <- 100000

dt <- 
	data.table(
		w = sapply(seq_len(rown), function(x) paste(sample(letters, 3, replace = T), collapse = ' '))
		, a = sample(letters, rown, replace = T)
		, b = runif(rown, -3, 3)
		, c = runif(rown, -3, 3)
		, e = rnorm(rown)
	) %>%
	.[, d := 1 + b + c + rnorm(nrow(.))]

# vectorization

microbenchmark({
	dt[
		, first_l := unlist(strsplit(w, split = ' ', fixed = T))[1]
		, by = 1:nrow(dt)
	   ]
})

# second

first_l_f <- function(sd)
{
	strsplit(sd, split = ' ', fixed = T) %>%
		do.call(rbind, .) %>%
		`[`(,1)
}

dt[, first_l := NULL]

microbenchmark({
	dt[
		, first_l := .(first_l_f(w))
		]
})

# third

first_l_f2 <- function(sd)
{
	strsplit(sd, split = ' ', fixed = T) %>%
		unlist %>%
		matrix(nrow = 3) %>%
		`[`(1,)
}

dt[, first_l := NULL]

microbenchmark({
	dt[
		, first_l := .(first_l_f2(w))
		]
})

# fourth

rown <- 100000

words <-
	sapply(
		seq_len(rown)
		, function(x){
			nwords <- rbinom(1, 10, 0.5)
			paste(
				sapply(
					seq_len(nwords)
					, function(x){
						paste(sample(letters, rbinom(1, 10, 0.5), replace = T), collapse = '')
					}
				)
				, collapse = ' '
			)
		}
	)

dt <- 
	data.table(
		w = words
		, a = sample(letters, rown, replace = T)
		, b = runif(rown, -3, 3)
		, c = runif(rown, -3, 3)
		, e = rnorm(rown)
	) %>%
	.[, d := 1 + b + c + rnorm(nrow(.))]

first_l_f3 <- function(sd, n)
{
	l <- strsplit(sd, split = ' ', fixed = T)
	
	maxl <- max(lengths(l))
	
	sapply(l, "length<-", maxl) %>%
		`[`(n,) %>%
		as.character
}

microbenchmark({
	dt[
		, (paste0('w_', 1:3)) := lapply(1:3, function(x) first_l_f3(w, x))
		]
})

dt[
	, (paste0('w_', 1:3)) := lapply(1:3, function(x) first_l_f3(w, x))
	]

# fifth

rown <- 100000

words <-
	sapply(
		seq_len(rown)
		, function(x){
			nwords <- rbinom(1, 10, 0.5)
			paste(
				sapply(
					seq_len(nwords)
					, function(x){
						paste(sample(letters, rbinom(1, 10, 0.5), replace = T), collapse = '')
					}
				)
				, collapse = ' '
			)
		}
	)

dt <- 
	data.table(
		w = words
		, a = sample(letters, rown, replace = T)
		, b = runif(rown, -3, 3)
		, c = runif(rown, -3, 3)
		, e = rnorm(rown)
	) %>%
	.[, d := 1 + b + c + rnorm(nrow(.))]

microbenchmark({
	
	w_split <- dt[
		, data.table::tstrsplit(w, split = ' ', fixed = T, keep = 1L:3L)
		]
	
	dt[
		, `:=` (
			w_1 = as.character(w_split[[1]])
			, w_2 = as.character(w_split[[2]])
			, w_3 = as.character(w_split[[3]])
		)
		]

})

# chaining

res1 <- dt[a == 'a'][sample(.N, 100)]

res2 <- dt[, .N, a][, N]

res3 <- dt[, coefficients(lm(e ~ d))[1], a][, .(letter = a, coef = V1)]

# piping

samplpe_b <- dt[a %in% head(letters), sample(b, 1)]

res4 <- 
	dt %>%
	.[a %in% head(letters)] %>%
	.[, 
	  {
	  	dt0 <- .SD[1:100]
	  	
	  	quants <- 
	  		dt0[, c] %>%
	  		quantile(seq(0.1, 1, 0.1), na.rm = T)
	  	
	  	.(q = quants)
	  }
	  , .(cond = b > samplpe_b)
	  ] %>%
	glm(
		cond ~ q -1
		, family = binomial(link = "logit")
		, data = .
	) %>%
	summary %>%
	.[[12]]

# function

rm(lm_preds)

lm_preds <- function(
	sd, by, n
)
{
	
	if(
		n < 100 | 
		!by[['a']] %in% head(letters, 4)
	   )
	{
		
		res <-
			list(
				low = NA
				, mean = NA
				, high = NA
				, coefs = NA
			)
		
	} else {

		lmm <- 
			lm(
				d ~ c + b
				, data = sd
			)
		
		preds <- 
			stats::predict.lm(
				lmm
				, sd
				, interval = "prediction"
				)
		
		res <-
			list(
				low = preds[, 2]
				, mean = preds[, 1]
				, high = preds[, 3]
				, coefs = coefficients(lmm)
			)
	}

	res
	
}

res5 <- 
	dt %>%
	.[e < 0] %>%
	.[.[, .I[b > 0]]] %>%
	.[, `:=` (
		low = as.numeric(lm_preds(.SD, .BY, .N)[[1]])
		, mean = as.numeric(lm_preds(.SD, .BY, .N)[[2]])
		, high = as.numeric(lm_preds(.SD, .BY, .N)[[3]])
		, coef_c = as.numeric(lm_preds(.SD, .BY, .N)[[4]][1])
		, coef_b = as.numeric(lm_preds(.SD, .BY, .N)[[4]][2])
		, coef_int = as.numeric(lm_preds(.SD, .BY, .N)[[4]][3])
	)
	, a
	] %>%
	.[!is.na(mean), -'e', with = F]


# plot

plo <- 
	res5 %>%
	ggplot +
	facet_wrap(~ a) +
	geom_ribbon(
		aes(
			x = c * coef_c + b * coef_b + coef_int
			, ymin = low
			, ymax = high
			, fill = a
		)
		, size = 0.1
		, alpha = 0.1
	) +
	geom_point(
		aes(
			x = c * coef_c + b * coef_b + coef_int
			, y = mean
			, color = a
		)
		, size = 1
	) +
	geom_point(
		aes(
			x = c * coef_c + b * coef_b + coef_int
			, y = d
		)
		, size = 1
		, color = 'black'
	) +
	theme_minimal()

print(plo)

## load libs ----------------

library(data.table)
library(ggplot2)
library(magrittr)
library(microbenchmark)


## arrays ---------

arrmatr <- array(1:20, c(4,5))

class(arrmatr)

typeof(arrmatr)

is.array(arrmatr)

is.matrix(arrmatr)


## lists ------------------

mylist <- as.list(arrmatr)

is.vector(mylist)

is.list(mylist)


## data.frames ------------

df <- as.data.frame(arrmatr)

is.list(df)

df$V6 <- df$V1 + df$V2


## data.tables -----------------------

data.table::setDT(df)

is.list(df)

is.data.frame(df)

is.data.table(df)

df2 <- df

df[V1 == 1, V2 := 999]

data.table::fsetdiff(df, df2)

df2 <- data.table::copy(df)

df[V1 == 2, V2 := 999]

data.table::fsetdiff(df, df2)


## operations on data.tables ------------

#using list properties

df$'V1'[1]

df[['V1']]

df[[1]][1]

sapply(df, class)

sapply(df, function(x) sum(is.na(x)))


## Bigger example ----

rown <- 100000

dt <- 
	data.table(
		w = sapply(seq_len(rown), function(x) paste(sample(letters, 3, replace = T), collapse = ' '))
		, a = sample(letters, rown, replace = T)
		, b = runif(rown, -3, 3)
		, c = runif(rown, -3, 3)
		, e = rnorm(rown)
	) %>%
	.[, d := 1 + b + c + rnorm(nrow(.))]

# vectorization

# zero - for loop

microbenchmark({
	for(i in 1:nrow(dt))
		{
		dt[
			i
			, first_l := unlist(strsplit(w, split = ' ', fixed = T))[1]
		]
	}
})

# first

microbenchmark({
	dt[
		, first_l := unlist(strsplit(w, split = ' ', fixed = T))[1]
		, by = 1:nrow(dt)
	   ]
})

# second

first_l_f <- function(sd)
{
	strsplit(sd, split = ' ', fixed = T) %>%
		do.call(rbind, .) %>%
		`[`(,1)
}

dt[, first_l := NULL]

microbenchmark({
	dt[
		, first_l := .(first_l_f(w))
		]
})

# third

first_l_f2 <- function(sd)
{
	strsplit(sd, split = ' ', fixed = T) %>%
		unlist %>%
		matrix(nrow = 3) %>%
		`[`(1,)
}

dt[, first_l := NULL]

microbenchmark({
	dt[
		, first_l := .(first_l_f2(w))
		]
})

# fourth

rown <- 100000

words <-
	sapply(
		seq_len(rown)
		, function(x){
			nwords <- rbinom(1, 10, 0.5)
			paste(
				sapply(
					seq_len(nwords)
					, function(x){
						paste(sample(letters, rbinom(1, 10, 0.5), replace = T), collapse = '')
					}
				)
				, collapse = ' '
			)
		}
	)

dt <- 
	data.table(
		w = words
		, a = sample(letters, rown, replace = T)
		, b = runif(rown, -3, 3)
		, c = runif(rown, -3, 3)
		, e = rnorm(rown)
	) %>%
	.[, d := 1 + b + c + rnorm(nrow(.))]

first_l_f3 <- function(sd, n)
{
	l <- strsplit(sd, split = ' ', fixed = T)
	
	maxl <- max(lengths(l))
	
	sapply(l, "length<-", maxl) %>%
		`[`(n,) %>%
		as.character
}

microbenchmark({
	dt[
		, (paste0('w_', 1:3)) := lapply(1:3, function(x) first_l_f3(w, x))
		]
})

dt[
	, (paste0('w_', 1:3)) := lapply(1:3, function(x) first_l_f3(w, x))
	]


# chaining

res1 <- dt[a == 'a'][sample(.N, 100)]

res2 <- dt[, .N, a][, N]

res3 <- dt[, coefficients(lm(e ~ d))[1], a][, .(letter = a, coef = V1)]

# piping

samplpe_b <- dt[a %in% head(letters), sample(b, 1)]

res4 <- 
	dt %>%
	.[a %in% head(letters)] %>%
	.[, 
	  {
	  	dt0 <- .SD[1:100]
	  	
	  	quants <- 
	  		dt0[, c] %>%
	  		quantile(seq(0.1, 1, 0.1), na.rm = T)
	  	
	  	.(q = quants)
	  }
	  , .(cond = b > samplpe_b)
	  ] %>%
	glm(
		cond ~ q -1
		, family = binomial(link = "logit")
		, data = .
	) %>%
	summary %>%
	.[[12]]


# function

rm(lm_preds)

lm_preds <- function(
	sd, by, n
)
{
	
	if(
		n < 100 | 
		!by[['a']] %in% head(letters, 4)
	   )
	{
		
		res <-
			list(
				low = NA
				, mean = NA
				, high = NA
				, coefs = NA
			)
		
	} else {

		lmm <- 
			lm(
				d ~ c + b
				, data = sd
			)
		
		preds <- 
			stats::predict.lm(
				lmm
				, sd
				, interval = "prediction"
				)
		
		res <-
			list(
				low = preds[, 2]
				, mean = preds[, 1]
				, high = preds[, 3]
				, coefs = coefficients(lmm)
			)
	}

	res
	
}

res5 <- 
	dt %>%
	.[e < 0] %>%
	.[.[, .I[b > 0]]] %>%
	.[, `:=` (
		low = as.numeric(lm_preds(.SD, .BY, .N)[[1]])
		, mean = as.numeric(lm_preds(.SD, .BY, .N)[[2]])
		, high = as.numeric(lm_preds(.SD, .BY, .N)[[3]])
		, coef_c = as.numeric(lm_preds(.SD, .BY, .N)[[4]][1])
		, coef_b = as.numeric(lm_preds(.SD, .BY, .N)[[4]][2])
		, coef_int = as.numeric(lm_preds(.SD, .BY, .N)[[4]][3])
	)
	, a
	] %>%
	.[!is.na(mean), -'e', with = F]


# plot

plo <- 
	res5 %>%
	ggplot +
	facet_wrap(~ a) +
	geom_ribbon(
		aes(
			x = c * coef_c + b * coef_b + coef_int
			, ymin = low
			, ymax = high
			, fill = a
		)
		, size = 0.1
		, alpha = 0.1
	) +
	geom_point(
		aes(
			x = c * coef_c + b * coef_b + coef_int
			, y = mean
			, color = a
		)
		, size = 1
	) +
	geom_point(
		aes(
			x = c * coef_c + b * coef_b + coef_int
			, y = d
		)
		, size = 1
		, color = 'black'
	) +
	theme_minimal()

print(plo)