Intermediate R

String comparison

String comparison is based on alphabetical order

"Hello" > "GoodBye"

## [1] TRUE

Logical operators

• AND operator &
• OR operator |
• NOT operator !

# Every element compared with the their
c(TRUE, TRUE, FALSE) & c(TRUE, FALSE, FALSE)

## [1]  TRUE FALSE FALSE

# (AND operator) Only examinates the first element of each vector 
c(TRUE, TRUE, FALSE) && c(TRUE, FALSE, FALSE)

## [1] TRUE

# (OR  operator) Only examinates the first element of each vector 
c(TRUE, TRUE, FALSE) || c(TRUE, FALSE, FALSE)

## [1] TRUE

Loops

# While loop  
ctr <- 2
while(ctr <= 7){
  if(ctr == 100){
    break
  }
  print(paste("ctr is equal to", ctr))
  ctr <- ctr + 1
}

## [1] "ctr is equal to 2"
## [1] "ctr is equal to 3"
## [1] "ctr is equal to 4"
## [1] "ctr is equal to 5"
## [1] "ctr is equal to 6"
## [1] "ctr is equal to 7"

#Another While Example
# Initialize the speed variable
speed <- 88

while (speed > 30) {
  print(paste("Your speed is", speed))
  
  # Break the while loop when speed exceeds 80
  if (speed > 80 ) {
    break
  }
  
  if (speed > 48) {
    print("Slow down big time!")
    speed <- speed - 11
  } else {
    print("Slow down!")
    speed <- speed - 6
  }
}

## [1] "Your speed is 88"

For loops

num_vector <- c(1:15)

for(i in num_vector){
  if(i %% 2 == 0){
    next
  }else{
    print(paste(i, "is odd"))
  }
}

## [1] "1 is odd"
## [1] "3 is odd"
## [1] "5 is odd"
## [1] "7 is odd"
## [1] "9 is odd"
## [1] "11 is odd"
## [1] "13 is odd"
## [1] "15 is odd"

# The nyc list is already specified
nyc <- list(pop = 8405837, 
            boroughs = c("Manhattan", "Bronx", "Brooklyn", "Queens", "Staten Island"), 
            capital = FALSE)

# Loop version 1

for(i in nyc){
  print(i)
}

## [1] 8405837
## [1] "Manhattan"     "Bronx"         "Brooklyn"      "Queens"       
## [5] "Staten Island"
## [1] FALSE

# Loop version 2

for(i in 1:length(nyc)){
  print(nyc[[i]])
}

## [1] 8405837
## [1] "Manhattan"     "Bronx"         "Brooklyn"      "Queens"       
## [5] "Staten Island"
## [1] FALSE

ttt <- matrix(c("O", NA, "X", NA, "O", "O", "X", NA, "X"), 
              ncol = 3, nrow = 3)

for (i in 1:nrow(ttt)) {
  for (j in 1:ncol(ttt)) {
    print(paste("On row", i, "and column",j, "the board contains",ttt[i, j]))
  }
}

## [1] "On row 1 and column 1 the board contains O"
## [1] "On row 1 and column 2 the board contains NA"
## [1] "On row 1 and column 3 the board contains X"
## [1] "On row 2 and column 1 the board contains NA"
## [1] "On row 2 and column 2 the board contains O"
## [1] "On row 2 and column 3 the board contains NA"
## [1] "On row 3 and column 1 the board contains X"
## [1] "On row 3 and column 2 the board contains O"
## [1] "On row 3 and column 3 the board contains X"

# Pre-defined variables
rquote <- "r's internals are irrefutably intriguing"
chars <- strsplit(rquote, split = "")[[1]]

# Initialize rcount
rcount <- 0

# Finish the for loop
for (char in chars) {
  if (char == 'r'){
    rcount <- rcount + 1
  }
  if (char == 'u'){
    break
  }
}

# Print out rcount
print(rcount)

## [1] 5

Functions

• args(function): Shows the arguments of a function
• require(): the difference with library() function is when you’re trying to load the package that is not yet installed

Apply functions

lapply

• apply function over list or vector
• output = list

# The vector pioneers has already been created for you
pioneers <- c("GAUSS:1777", "BAYES:1702", "PASCAL:1623", "PEARSON:1857")

# Split names from birth year
split_math <- strsplit(pioneers, split = ":")

# Convert to lowercase strings: split_low

split_low<-lapply(split_math, tolower)

# Take a look at the structure of split_low
str(split_low)

## List of 4
##  $ : chr [1:2] "gauss" "1777"
##  $ : chr [1:2] "bayes" "1702"
##  $ : chr [1:2] "pascal" "1623"
##  $ : chr [1:2] "pearson" "1857"

# Transform: use anonymous function inside lapply

names <- lapply(split_low, function(x) x[1])

# Transform: use anonymous function inside lapply

years <- lapply(split_low, function(x) x[2])

# Generic select function
select_el <- function(x, index) {
  x[index]
}

# Use lapply() twice on split_low: names and years

names <- lapply(split_low, select_el, index = 1)
years <- lapply(split_low, select_el, index = 2)

lapply(split_low, function(x) {
  if (nchar(x[1]) > 5) {
    return(NULL)
  } else {
    return(x[2])
  }
})

## [[1]]
## [1] "1777"
## 
## [[2]]
## [1] "1702"
## 
## [[3]]
## NULL
## 
## [[4]]
## NULL

Sapply (Simplify apply)

• apply function over list or vector
• try to simplify list to array

Instead of return a list, sapply returns a named vector

# temp is already defined in the workspace

temp <- rnorm(5)

# Finish function definition of extremes_avg
extremes_avg <- function(x) {
  ( min(x) + max(x) ) / 2
}

# Apply extremes_avg() over temp using sapply()

sapply(temp, extremes_avg, USE.NAMES = FALSE)

## [1] -1.3945295  1.1253849 -2.6295448  1.1234166 -0.6408276

# Apply extremes_avg() over temp using lapply()

lapply(temp, extremes_avg)

## [[1]]
## [1] -1.394529
## 
## [[2]]
## [1] 1.125385
## 
## [[3]]
## [1] -2.629545
## 
## [[4]]
## [1] 1.123417
## 
## [[5]]
## [1] -0.6408276

# temp is already available in the workspace

# Definition of print_info()
print_info <- function(x) {
  cat("The average temperature is", mean(x), "\n")
}

# Apply print_info() over temp using sapply()

sapply(temp, print_info)

## The average temperature is -1.394529 
## The average temperature is 1.125385 
## The average temperature is -2.629545 
## The average temperature is 1.123417 
## The average temperature is -0.6408276

## [[1]]
## NULL
## 
## [[2]]
## NULL
## 
## [[3]]
## NULL
## 
## [[4]]
## NULL
## 
## [[5]]
## NULL

# Apply print_info() over temp using lapply()

lapply(temp, print_info)

## The average temperature is -1.394529 
## The average temperature is 1.125385 
## The average temperature is -2.629545 
## The average temperature is 1.123417 
## The average temperature is -0.6408276

## [[1]]
## NULL
## 
## [[2]]
## NULL
## 
## [[3]]
## NULL
## 
## [[4]]
## NULL
## 
## [[5]]
## NULL

Vapply

• Apply function over list or vector
• explicitly specify output format

# temp is already available in the workspace

# Definition of basics()
basics <- function(x) {
  c(min = min(x), mean = mean(x), max = max(x))
}

# Apply basics() over temp using vapply()

vapply(temp, basics, numeric(3))

##           [,1]     [,2]      [,3]     [,4]       [,5]
## min  -1.394529 1.125385 -2.629545 1.123417 -0.6408276
## mean -1.394529 1.125385 -2.629545 1.123417 -0.6408276
## max  -1.394529 1.125385 -2.629545 1.123417 -0.6408276

Useful functions

# seq() 
seq(1, 10, by = 3)

## [1]  1  4  7 10

seq(8, 2, by = -2)

## [1] 8 6 4 2

# rep()

rep(c(8, 6, 4, 2), times = 2)

## [1] 8 6 4 2 8 6 4 2

rep(c(8, 6, 4, 2), each = 2)

## [1] 8 8 6 6 4 4 2 2

# sort()

sort(c(8, 6, 4, 2, 8, 6, 4, 2), decreasing = TRUE)

## [1] 8 8 6 6 4 4 2 2

# is.*() as.*()

is.list(c(8, 6, 4, 2))

## [1] FALSE

is.list(as.list(c(8, 6, 4, 2)))

## [1] TRUE

li <- as.list(c(8, 6, 4, 2))

unlist(li)

## [1] 8 6 4 2

# append() and rev()

append(li, rev(li))

## [[1]]
## [1] 8
## 
## [[2]]
## [1] 6
## 
## [[3]]
## [1] 4
## 
## [[4]]
## [1] 2
## 
## [[5]]
## [1] 2
## 
## [[6]]
## [1] 4
## 
## [[7]]
## [1] 6
## 
## [[8]]
## [1] 8

Regular expressions

# The emails vector has already been defined for you
emails <- c("john.doe@ivyleague.edu", "education@world.gov", "dalai.lama@peace.org",
            "invalid.edu", "quant@bigdatacollege.edu", "cookie.monster@sesame.tv")

# Use grepl() to match for "edu"

grepl("edu", emails)

## [1]  TRUE  TRUE FALSE  TRUE  TRUE FALSE

# Use grep() to match for "edu", save result to hits

hits <- grep("edu", emails)

# Subset emails using hits

emails[hits]

## [1] "john.doe@ivyleague.edu"   "education@world.gov"     
## [3] "invalid.edu"              "quant@bigdatacollege.edu"

# more advanced regex
# Use grepl() to match for .edu addresses more robustly

grepl("@.*\\.edu$", emails)

## [1]  TRUE FALSE FALSE FALSE  TRUE FALSE

# Use grep() to match for .edu addresses more robustly, save result to hits

hits <- grep("@.*\\.edu$", emails)

# Subset emails using hits
emails[hits]

## [1] "john.doe@ivyleague.edu"   "quant@bigdatacollege.edu"

# The emails vector has already been defined for you
emails <- c("john.doe@ivyleague.edu", "education@world.gov", "global@peace.org",
            "invalid.edu", "quant@bigdatacollege.edu", "cookie.monster@sesame.tv")

# Use sub() to convert the email domains to datacamp.edu

sub("@.*\\.edu$", "@datacamp.edu", emails )

## [1] "john.doe@datacamp.edu"    "education@world.gov"     
## [3] "global@peace.org"         "invalid.edu"             
## [5] "quant@datacamp.edu"       "cookie.monster@sesame.tv"

Times and Dates

# Definition of character strings representing dates
str1 <- "May 23, '96"
str2 <- "2012-03-15"
str3 <- "30/January/2006"

# Convert the strings to dates: date1, date2, date3
date1 <- as.Date(str1, format = "%b %d, '%y")
date2 <- as.Date(str2, format = "%Y-%m-%d")
date3 <- as.Date(str3, format = "%d/%B/%Y")


# Convert dates to formatted strings
format(date1, "%A")

## [1] NA

format(date2, "%d")

## [1] "15"

format(date3, "%b %Y") 

## [1] NA

# Definition of character strings representing times
str1 <- "May 23, '96 hours:23 minutes:01 seconds:45"
str2 <- "2012-3-12 14:23:08"

# Convert the strings to POSIXct objects: time1, time2
time1 <- as.POSIXct(str1, format = "%B %d, '%y hours:%H minutes:%M seconds:%S")
time2 <- as.POSIXct(str2, format = "%Y-%m-%d %H:%M:%S")

# Convert times to formatted strings

format(time1, "%M")

## [1] NA

format(time2, "%I:%M %p")

## [1] "02:23 p. m."