In this assignment, solutions to problems 3, 4 and 9 in Chapter 8 from textbook “Automated Data Collection with R” by S.Munzert, C. Rubba, P. Meißner, and D. Nyhuis, are provided below.
library(stringr)raw.data <- "555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5543642Dr. Julius Hibbert"
names <- unlist(str_extract_all(raw.data, "[[:alpha:]., ]{2,}"))
names ## [1] "Moe Szyslak" "Burns, C. Montgomery" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders" "Simpson, Homer" "Dr. Julius Hibbert"The following could be done without using functions because the vector containg the names is very short. However, if the vector had a relatively large length with many changes to be done, doing the same task without functions would be very repetitive.
As practice of using functions in R, I will use the function grepall as described in section 8.2 from the textbook and create another function to change the displayed order of a full name.
grepall <- function(pattern, x,
ignore.case = FALSE, perl = FALSE,
fixed = FALSE, useBytes = FALSE,
value = FALSE, logic = FALSE){
# error and exception handling
if(length(pattern) == 0 | length(x) == 0){
warning("Length of pattern or data equals zero.")
return(NULL)
}
# apply grepl() and all()
indices <- sapply(pattern, grepl, x, ignore.case, perl, fixed, useBytes)
index <- apply(indices, 1, all)
# indexation and return of results
if(logic == T) return(index)
if(value == F) return((1:length(x))[index])
if(value == T) return(x[index])
}Identify the names listed as last name, first name and change the order.
pattern <-"[[:alpha:]]+, [[:graph:] ]+"
old <- grepall(pattern,names,value=T)
indices <- grepall(pattern,names,value=F)
old## [1] "Burns, C. Montgomery" "Simpson, Homer"indices## [1] 2 5# function that change the order of names to first and last names
new <- function(input){
n<-length(input)
flname <- vector('character')
for (i in 1:n){
split_name <- unlist(str_split(input[i],", "))
temp <- paste(split_name[2], split_name[1])
flname <- c(flname, temp)
}
return(flname)
}
names[indices] <- new(old)
names## [1] "Moe Szyslak" "C. Montgomery Burns" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders" "Homer Simpson" "Dr. Julius Hibbert"pattern <- "[ [:upper:]][[:lower:]]+\\."
title <-str_detect(names, pattern)
title## [1] FALSE FALSE TRUE FALSE FALSE TRUEpattern <- "[:upper:]\\. [[:alpha:]]+ "
middle_name <-str_detect(names, pattern)
middle_name## [1] FALSE TRUE FALSE FALSE FALSE FALSEDescription of the following regular expressions with examples:
The regular expression returns a substring consisting of at least one of digits from 0 to 9 followed by character $.
text<- " This is an example where digits appear: 111, 045$, 6.99, $401, 76$, 432$00."
unlist(str_extract_all(text, '[[0-9]]+\\$'))## [1] "045$" "76$" "432$"\b indicates word edge, and so the expression returns whole word(s) consisting of 1 to 4 letters from a to z.
text<- " This is another example t2o what such expression wil1 return."
unlist(str_extract_all(text, '\\b[a-z]{1,4}\\b'))## [1] "is" "what" "such"$ indicates end of a string, and the expression returns the shortest possible sequence of any character zero or more times followed by the sequence of characters “.txt” in the end of the a string.
text<- c("mydata.txt","main_data.txt.","xxx-data.txt", "data.txt contains all data.")
unlist(str_extract_all(text, ".*?\\.txt$"))## [1] "mydata.txt" "xxx-data.txt"$ indicates end of a string, and the expression returns the shortest possible sequence of any character zero or more times followed by sequence of characters “.txt” in the end of the a string.
text<- c("mydata.txt","main_data.txt.","xxx-data.txt", "data.txt contains all data.")
unlist(str_extract_all(text, ".*?\\.txt$"))## [1] "mydata.txt" "xxx-data.txt"The expression returns a sequence of characters in the date format xx/xx/xxxx (e.g., 09/15/2018).
text<- c("Dec 14, 2001","This assignment is due on 09/16/2018.","Jane's birthday is 10/10/2010.", "When is yor birthday?")
unlist(str_extract_all(text, "\\d{2}/\\d{2}/\\d{4}"))## [1] "09/16/2018" "10/10/2010"The regular expression returns a sequence of characters that describes a html tag. For example, “<email>some_email_address_here</email>”. In the regular expression “\1” is backreferencing to the substring from the expression “(.+?)”.
text<- ("<html>
<body>
<h1>This is heading 1</h1>
<h2>This is heading 2</h2>
<h3>This is heading 3</h3>
<h4>This is heading 4</h4>
<h5>This is heading 5</h5>
<h6>This is heading 6</h6>
</body>
</html>")
unlist(str_extract_all(text, "<(.+?)>.+?</\\1>"))## [1] "<h1>This is heading 1</h1>" "<h2>This is heading 2</h2>"
## [3] "<h3>This is heading 3</h3>" "<h4>This is heading 4</h4>"
## [5] "<h5>This is heading 5</h5>" "<h6>This is heading 6</h6>"The secret message below is sequence of characters from th alpha (upper and lower), digit and punct classes. Let’s first extract the elements of upper and lower alpha classes, separetely.
msg <- "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"lower <- str_extract_all(msg,"[[a-z]+]")
lower## [[1]]
## [1] "c" "l" "c" "o" "p" "o" "w" "z" "m" "s" "t" "c" "d" "w" "n" "k" "i"
## [18] "g" "v" "d" "i" "c" "p" "u" "g" "g" "v" "h" "r" "y" "n" "j" "u" "w"
## [35] "c" "z" "i" "h" "q" "r" "f" "p" "x" "s" "j" "d" "w" "p" "n" "a" "n"
## [52] "w" "o" "w" "i" "s" "d" "i" "j" "j" "k" "p" "f" "d" "r" "c" "o" "c"
## [69] "b" "t" "y" "c" "z" "j" "a" "t" "a" "o" "o" "t" "j" "t" "j" "n" "e"
## [86] "c" "f" "e" "k" "r" "w" "w" "w" "o" "j" "i" "g" "d" "v" "r" "f" "r"
## [103] "b" "z" "b" "k" "n" "b" "h" "z" "g" "v" "i" "z" "c" "r" "o" "p" "w"
## [120] "g" "n" "b" "q" "o" "f" "a" "o" "t" "f" "b" "w" "m" "k" "t" "s" "z"
## [137] "q" "e" "f" "y" "n" "d" "t" "k" "c" "f" "g" "m" "c" "g" "x" "o" "n"
## [154] "h" "k" "g" "r"upper <- str_extract_all(msg,"[[A-Z]]+")
upper## [[1]]
## [1] "C" "O" "N" "G" "R" "A" "T" "U" "L" "AT" "I" "O" "N" "S"
## [15] "Y" "O" "U" "A" "R" "E" "A" "S" "U" "P" "E" "R" "N" "E"
## [29] "R" "D"Bingo!! Now it is just to make it presentable. Note that in the original string each word is separated by a punctuation mark.
meaning <- unlist(str_extract_all(msg,"[[A-Z]]+|[[:punct:]]"))
meaning## [1] "C" "O" "N" "G" "R" "A" "T" "U" "L" "AT" "I" "O" "N" "S"
## [15] "." "Y" "O" "U" "." "A" "R" "E" "." "A" "." "S" "U" "P"
## [29] "E" "R" "N" "E" "R" "D" "!"meaning <- str_c(meaning, collapse ="")
meaning <- str_replace_all(meaning, pattern = "\\.+", replacement =" ")
meaning## [1] "CONGRATULATIONS YOU ARE A SUPERNERD!"