Data607HW03

Please deliver links to an R Markdown file (in GitHub and rpubs.com) with solutions to problems 3 and 4 from chapter 8 of Automated Data Collection in R. Problem 9 is extra credit. You may work in a small group, but please submit separately with names of all group participants in your submission.

Here is the referenced code for the introductory example in #3:

library(stringr)

## Warning: package 'stringr' was built under R version 3.4.4

library(XML)

## Warning: package 'XML' was built under R version 3.4.4

#Load data
raw.data <-"555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5553642Dr. Julius Hibbert" 
raw.data

## [1] "555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5553642Dr. Julius Hibbert"

(a) Use the tools of this chapter to rearrange the vector so that all elements conform to the standard first_name last_name.

Option 1

names = unlist(str_extract_all(raw.data, "[[A-z]., ]{2,}"))
names

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

#name <- unlist(str_extract_all(raw.data, "[[:alpha:]., ]{2,}"))
#name

Option 2

#First Name
firstName = unlist(str_extract_all(names, "[.,] [[A-z]]{2,}$|[[A-z]]{2,} "))
firstName = unlist(str_extract_all(firstName, "[[A-z]]{2,}"))
firstName

## [1] "Moe"        "Montgomery" "Timothy"    "Ned"        "Homer"     
## [6] "Julius"

#Last Name
lastName = unlist(str_extract_all(names, "[^[.,]] [[A-z]]{2,}$|[[A-z]]{2,}, "))
lastName = unlist(str_extract_all(lastName, "[[A-z]]{2,}"))
lastName

## [1] "Szyslak"  "Burns"    "Lovejoy"  "Flanders" "Simpson"  "Hibbert"

#Combine
data.frame("Fist Name" = firstName, "Last Name" = lastName)

##    Fist.Name Last.Name
## 1        Moe   Szyslak
## 2 Montgomery     Burns
## 3    Timothy   Lovejoy
## 4        Ned  Flanders
## 5      Homer   Simpson
## 6     Julius   Hibbert

(b) Construct a logical vector indicating whether a character has a title (i.e., Rev. and Dr.).

titles = unlist(str_extract_all(names, "[[A-z]]{2,}\\."))
titles

## [1] "Rev." "Dr."

data.frame("Name" = names, "HasTitle" = str_detect(names, titles))

##                   Name HasTitle
## 1          Moe Szyslak    FALSE
## 2 Burns, C. Montgomery    FALSE
## 3 Rev. Timothy Lovejoy     TRUE
## 4         Ned Flanders    FALSE
## 5       Simpson, Homer    FALSE
## 6   Dr. Julius Hibbert     TRUE

(c) Construct a logical vector indicating whether a character has a second name.

secondName = unlist(str_extract_all(names, " [[A-z]]{1}\\.? [[A-z]]{1,}\\.?"))
secondName = unlist(str_extract_all(secondName,"[[A-z]]{1}\\.? [[A-z]]{1,}\\.?"))
secondName

## [1] "C. Montgomery"

data.frame("Name" = names, "HasSecondName" = str_detect(names, secondName))

##                   Name HasSecondName
## 1          Moe Szyslak         FALSE
## 2 Burns, C. Montgomery          TRUE
## 3 Rev. Timothy Lovejoy         FALSE
## 4         Ned Flanders         FALSE
## 5       Simpson, Homer         FALSE
## 6   Dr. Julius Hibbert         FALSE

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]+\$

#Should contain numbers from 0 to 9 and $
data1 = c("100$", "2019$$", "9$$$ ", "-1$", "12$738372", ".367$", "2334$ is the total amount.")
str_detect(data1, "[0-9]+\\$")

## [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE

(b) \b[a-z]{1,4}\b

data2 = c("a", "cuny", "and", "a e", "data", "da t", " s ")
str_detect(data2, "\\b[a-z]{1,4}\\b")

## [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE

(c) .*?\.txt$

data3 = c("*.txt", "filename.txt", "all files with extension .txt", "files like .txt", "note.txt", "klmn.txt", "*.txt", "pqr874238743 .txt", ".txt")
str_detect(data3, ".*?\\.txt$")

## [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE

(d) \d{2}/\d{2}/\d{4}

#Contains atleast on date with format dd/mm/yyyy or mm/dd/yyyy
data4 = c("15/12/2019", "12/15/1029", "02/02/2016", "20/20/0000", "00/00/0000", "date like 01/13/2050", "from 01/01/2018 to 1/1/1000", "03/03/1999")
str_detect(data4, "\\d{2}/\\d{2}/\\d{4}")

## [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE

(e) <(.+?)>.+?</\1>

data5 = c("<html><title>CUNY Data Science</div><body>Data Sets</body></html>", "<div>NumPy</div>", "<div><div>NumPy<div></div>", "<img>NumPy</img>")
str_detect(data5, "<(.+?)>.+?</\\1>")

## [1] TRUE TRUE TRUE TRUE

Secret Message

secretCode = "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"
secretCode

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

#Looks like if we remove lower case then we get a hidden text
upperletters = unlist(str_extract_all(secretCode, "[[:upper:].! ]"))
upperletters

##  [1] "C" "O" "N" "G" "R" "A" "T" "U" "L" "A" "T" "I" "O" "N" "S" "." "Y"
## [18] "O" "U" "." "A" "R" "E" "." "A" "." "S" "U" "P" "E" "R" "N" "E" "R"
## [35] "D" "!"

upperletters1 = paste(upperletters, collapse="")
upperletters1

## [1] "CONGRATULATIONS.YOU.ARE.A.SUPERNERD!"

upperlettersfinal = str_replace_all(upperletters1, "[\\.]", " ")
upperlettersfinal

## [1] "CONGRATULATIONS YOU ARE A SUPERNERD!"