datascience_plus_article.R

current_test <- function(df) {
  
  for (i in 1:nrow(df)) { # for every row
    if ((df[i, 'col1'] + df[i, 'col2'] + df[i, 'col3'] + df[i, 'col4']) > 4) { # check if > 4
      df[i, 5] <- "greater_than_4" # assign 5th column
    } else {
      df[i, 5] <- "lesser_than_4" # assign 5th column
    }
  }
  return(df[,5])
}

vectorized_test <- function(df) {
  output <- character (nrow(df)) 
  
  for (i in 1:nrow(df)) {
    if ((df[i, 'col1'] + df[i, 'col2'] + df[i, 'col3'] + df[i, 'col4']) > 4) {
      output[i] <- "greater_than_4"
    } else {
      output[i] <- "lesser_than_4"
    }
  }
  return(df$output)
}

trueonly_test <- function(df) {
  output <- character(nrow(df))
  condition <- (df$col1 + df$col2 + df$col3 + df$col4) > 4
  
  for (i in (1:nrow(df))[condition]) {  # run loop only for true conditions
    if (condition[i]) {
      output[i] <- "greater_than_4"
    } else {
      output[i] <- "lesser_than_4"
    }
  }
  return(df$output)
}

ifelse_test <- function(df) {
  output <- ifelse ((df$col1 + df$col2 + df$col3 + df$col4) > 4, "greater_than_4", "lesser_than_4")
  return(output)
}

standard_test <- function(df) {
  output <- 1
  output[df$col1 + df$col2 + df$col3 + df$col4 > 4] <- "greater_than_4"
  output[output != "greater_than_4"] <- "lesser_than_4"
  return(output)
}

rowsums_test <- function(df) {
  output <- 1
  output[rowSums(df) > 4] <- "greater_than_4"
  output[output != "greater_than_4"] <- "lesser_than_4"
  return(output)
}

library(microbenchmark)

test_me <- function(e) {
  col1 <- runif (12^e, 0, 2)
  col2 <- rnorm (12^e, 0, 2)
  col3 <- rpois (12^e, 3)
  col4 <- rchisq (12^e, 2)
  df <- data.frame (col1, col2, col3, col4)
  
  bm <- microbenchmark(
    #current_test(df),
    #vectorized_test(df),
    #trueonly_test(df),
    ifelse_test(df),
    standard_test(df),
    rowsums_test(df),
    times = 10)
  
  return(bm)  
}