DATA 607 HW3

CHAPTER 8 QS 3

Extract the names

library(stringr)
raw.data <-"555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5553642Dr. Julius Hibbert"
name <- unlist(str_extract_all(raw.data, "[[:alpha:]., ]{2,}"))
name

## [1] "Moe Szyslak"          "Burns, C. Montgomery" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders"         "Simpson, Homer"       "Dr. Julius Hibbert"

Reorder the first and second names

first_second <- str_split(name, ", ")
first_second <- sapply(first_second, function(x) str_replace(paste(x[2], x[1]),"^NA ",""))
title_regex <- "^(Mr|Mrs|Dr|Rev)\\."
name_wo_title<-str_replace(first_second, title_regex, "")
name_wo_title

## [1] "Moe Szyslak"         "C. Montgomery Burns" " Timothy Lovejoy"   
## [4] "Ned Flanders"        "Homer Simpson"       " Julius Hibbert"

Detect which have the titles - the vector

str_detect(first_second, title_regex)

## [1] FALSE FALSE  TRUE FALSE FALSE  TRUE

Detect which have the second names

name_wo_title[str_detect(name_wo_title, "\\b[a-zA-Z]\\b")]

## [1] "C. Montgomery Burns"

CHAPTER 8 QS 4

Describe the types of strings that conform to the following regular expressions and construct an example that is matched by the regular expression.

(a) [0-9]+\$ is for Money (digits followed by $)

samples <- c('123$', '456$', 8900)
str_match(samples, "[0-9]+\\$")

##      [,1]  
## [1,] "123$"
## [2,] "456$"
## [3,] NA

(b) \b[a-z]{1,4}\b is first instance of a word of size 1 to 4 that sit inside a sentence.

samples <- c('Here we go', 'Oye', 8900, 'I will not forgive you Mr. 500.')
str_match(samples, "\\b[a-z]{1,4}\\b")

##      [,1]  
## [1,] "we"  
## [2,] NA    
## [3,] NA    
## [4,] "will"

(c) .*?\.txt$ is for filenames with extension txt

samples <- c('abc.csv', 'Tex.txt', '8900.txt', 7200, 'Wer$234.txt')
str_match(samples, ".*?\\.txt$")

##      [,1]         
## [1,] NA           
## [2,] "Tex.txt"    
## [3,] "8900.txt"   
## [4,] NA           
## [5,] "Wer$234.txt"

(d) \d{2}/\d{2}/\d{4} is for dd/dd/dddd - a rather non-strict representation of date

samples <- c('22/12/2008', 'Tex.txt', '8900/12/12', '12/1/7200', '90/90/9000')
str_match(samples, "\\d{2}/\\d{2}/\\d{4}")

##      [,1]        
## [1,] "22/12/2008"
## [2,] NA          
## [3,] NA          
## [4,] NA          
## [5,] "90/90/9000"

(e) <(.+?)>.+?</\1> is for xml opening and closing tags, though strictly speaking xml tags do not allow many special characters as shown below.

samples <- c('<abcd>.xx</abcd>.', '<xxx>Tex.txt</xxx>', '<root>8900.txt', 7200, '<456->Wer$234.txt</456->')
str_match(samples, "<(.+?)>.+?</\\1>")

##      [,1]                       [,2]  
## [1,] "<abcd>.xx</abcd>"         "abcd"
## [2,] "<xxx>Tex.txt</xxx>"       "xxx" 
## [3,] NA                         NA    
## [4,] NA                         NA    
## [5,] "<456->Wer$234.txt</456->" "456-"

CHAPTER 8 QS 9

The following code hides a secret message. Crack it with R and regular expressions. Hint: Some of the characters are more revealing than others! The code snippet is also available in the materials at www.r-datacollection.com. clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0Tanwo Uwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigO d6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5 fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr

raw.data1 <- "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"

Lets assume this is a message in english and is a transformation which is done by mapping the alphabets to an another set

SEARCH FOR SPACE - would be one of most commonly occuring character

sort(table(str_extract_all(raw.data1, ".")), decreasing=TRUE)[1:10]

## 
##  c  5  o  w  g  n  f  j  r  t 
## 12 11 11 11  9  9  8  8  8  8

So let’s search for most commonly used three letter words - ‘and’ and ‘the’. For this let’s what three letter groups are most repeating in the given messae.

str_extract_all(raw.data1, "c...c")

## [[1]]
## character(0)

str_extract_all(raw.data1, "5...5")

## [[1]]
## character(0)

str_extract_all(raw.data1, "o...o")

## [[1]]
## character(0)

str_extract_all(raw.data1, "w...w")

## [[1]]
## [1] "w1Yww"

str_extract_all(raw.data1, "g...g")

## [[1]]
## character(0)

str_extract_all(raw.data1, "n...n")

## [[1]]
## [1] "n0Tan"

str_extract_all(raw.data1, "f...f")

## [[1]]
## character(0)

str_extract_all(raw.data1, "j...j")

## [[1]]
## character(0)

str_extract_all(raw.data1, "r...r")

## [[1]]
## character(0)

str_extract_all(raw.data1, "t...t")

## [[1]]
## [1] "tj55t"

#space_vowels_period <- c("c","5","o","w","g","n","f","j","r","t")
#str_replace_all(raw.data1, space_vowels_period, "\ ")

Based on above let’s assume ‘n’ is space but our results are not encouraging (fragments too long), so we will try with ‘t’ also, which is also disappointing for same reason

str_replace_all(raw.data1,"n", "\ ")

## [1] "clcopCow1zmstc0d87w kig7OvdicpNuggvhry 92Gjuwczi8hqrfpRxs5Aj5dwp 0Ta woUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3 e6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkA bhzgv4R9i05zEcrop.wAg b.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89 6Nd5t9kc4fE905gmc4Rgxo5 hDk!gr"

str_replace_all(raw.data1,"t", "\ ")

## [1] "clcopCow1zms c0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0b 7yczja Oaoo j55 3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1o fb7wEm24k6 3sR9zqe5fy89n6Nd5 9kc4fE905gmc4Rgxo5nhDk!gr"

Let’s just try with various other elements we identified as ‘space’ candidates. But our results are similar.

str_replace_all(raw.data1,"j", "\ ")

## [1] "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92G uwczi8hqrfpRxs5A 5dwpn0TanwoUwisdi 7L 8kpf03AT5Idr3coc0bt7ycz atOaoot 55t3N 3ne6c4Sfek.r1w1Ywwo igOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"

raw.data1

## [1] "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"

str_replace_all(raw.data1,"5", "\ ")

## [1] "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs Aj dwpn0TanwoUwisdij7Lj8kpf03AT Idr3coc0bt7yczjatOaootj  t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i0 zEcrop.wAgnb.SqoU6 fPa1otfb7wEm24k6t3sR9zqe fy89n6Nd t9kc4fE90 gmc4Rgxo nhDk!gr"

str_replace_all(raw.data1,"o", "\ ")

## [1] "clc pC w1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0Tanw Uwisdij7Lj8kpf03AT5Idr3c c0bt7yczjatOa  tj55t3Nj3ne6c4Sfek.r1w1Yww jigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcr p.wAgnb.Sq U65fPa1 tfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgx 5nhDk!gr"

str_replace_all(raw.data1,"w", "\ ")

## [1] "clcopCo 1zmstc0d87 nkig7OvdicpNuggvhryn92Gju czi8hqrfpRxs5Aj5d pn0Tan oU isdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1 1Y  ojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop. Agnb.SqoU65fPa1otfb7 Em24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"

str_replace_all(raw.data1,"g", "\ ")

## [1] "clcopCow1zmstc0d87wnki 7OvdicpNu  vhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1Ywwoji Od6vrfUrbz2.2bkAnbhz v4R9i05zEcrop.wA nb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905 mc4R xo5nhDk! r"

str_replace_all(raw.data1,"f", "\ ")

## [1] "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqr pRxs5Aj5dwpn0TanwoUwisdij7Lj8kp 03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4S ek.r1w1YwwojigOd6vr Urbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65 Pa1ot b7wEm24k6t3sR9zqe5 y89n6Nd5t9kc4 E905gmc4Rgxo5nhDk!gr"

str_replace_all(raw.data1,"r", "\ ")

## [1] "clcopCow1zmstc0d87wnkig7OvdicpNuggvh yn92Gjuwczi8hq fpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Id 3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek. 1w1YwwojigOd6v fU bz2.2bkAnbhzgv4R9i05zEc op.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!g "

str_replace_all(raw.data1,"c", "\ ")

## [1] " l opCow1zmst 0d87wnkig7Ovdi pNuggvhryn92Gjuw zi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3 o 0bt7y zjatOaootj55t3Nj3ne6 4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zE rop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9k 4fE905gm 4Rgxo5nhDk!gr"

Let’s try another approach - try to find repeating 2 or 3 character sequences. (substitutes for of, in, the, and)

sort(table(str_extract_all(raw.data1, ".{2}")), decreasing=TRUE)

## 
## co ot oU .2 05 0d 1z 24 2G 3A 3N 4f 4S 5d 5f 5n 5t 5z 65 6c 6N 7L 7w 7y 87 
##  2  2  2  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1 
## 8h 9n 9z a1 Aj An ao b. bh bk bt c0 c4 cl cp cz d5 d6 di E9 Ec Em f0 fb fe 
##  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1 
## fp fP fU g7 gg gm gn gO gr hD i0 Id ij j3 j5 j8 ja ji ju k! k. k6 kc ki kp 
##  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1 
## ms n0 n9 ne Nu nw Ov ow p. pC qe qr r1 r3 R9 rb Rg ro Rx ry s5 sd Sq sR t3 
##  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1 
## T5 t9 Ta tc tO v4 vh vr w1 wA wc wi wn wo wp xo y8 Yw z2 zg zi 
##  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1

sort(table(str_extract_all(raw.data1, ".{3}")), decreasing=TRUE)

## 
## .r1 2bk 3co 4k6 5Aj 5dw 5gm 5nh 5t3 5zE 65f 7Lj 8hq 8kp 92G 9i0 9n6 Agn 
##   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1 
## Anb aoo AT5 atO b.S b7w c0b c4f c4R c4S clc cro czi czj d87 dij Dk! E90 
##   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1 
## Em2 f03 fek fy8 gvh gxo hzg icp Idr ig7 jig juw Nd5 ne6 Nj3 Nug Od6 opC 
##   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1 
## otf Ovd ow1 p.w Pa1 pn0 qe5 qoU R9z rfp Rxs ryn t3s t7y t9k Tan tc0 tj5 
##   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1 
## Urb v4R vrf w1Y wis wnk woU wwo z2. zms 
##   1   1   1   1   1   1   1   1   1   1

So let’s search for most commonly used three letter words - ‘and’ and ‘the’. For this let’s what three letter groups are most repeating in the given messae.

str_extract_all(raw.data1, "c..c")

## [[1]]
## character(0)

str_extract_all(raw.data1, "5..5")

## [[1]]
## [1] "5Aj5"

str_extract_all(raw.data1, "o..o")

## [[1]]
## [1] "opCo"

str_extract_all(raw.data1, "w..w")

## [[1]]
## [1] "woUw" "w1Yw"

str_extract_all(raw.data1, "g..g")

## [[1]]
## character(0)

str_extract_all(raw.data1, "n..n")

## [[1]]
## character(0)

str_extract_all(raw.data1, "f..f")

## [[1]]
## character(0)

str_extract_all(raw.data1, "j..j")

## [[1]]
## [1] "j7Lj"

str_extract_all(raw.data1, "r..r")

## [[1]]
## [1] "rfUr"

str_extract_all(raw.data1, "t..t")

## [[1]]
## character(0)

Status : Unresolved. I would think ‘space’ is represented by a combination of characters. and following from that it is possible other characters are also represented by multiple characters.