Assignment 3 - Data 607

Question 3

library(stringr)
library(knitr)

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,}"))
phone<-unlist(str_extract_all(raw.data, "\\(?(\\d{3})?\\)?(-| )?\\d{3}(-| )?\\d{4}"))

name

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

3.1)

kable(data.frame(name,phone))

name	phone
Moe Szyslak	555-1239
Burns, C. Montgomery	(636) 555-0113
Rev. Timothy Lovejoy	555-6542
Ned Flanders	555 8904
Simpson, Homer	636-555-3226
Dr. Julius Hibbert	5553642

• first_name last_name format:

for(i in 1:length(name)) {
  if(str_detect(name[i],",")==TRUE) {
    temp<-unlist(str_split(name[i],","))
    name[i]<-paste(temp[2], temp[1], sep=" ")
  }
}
kable(data.frame(name))

name
Moe Szyslak
C. Montgomery Burns
Rev. Timothy Lovejoy
Ned Flanders
Homer Simpson
Dr. Julius Hibbert

3.2)

with_title<-str_detect(name, "Rev.|Dr.")
title<-c()
for(j in 1:length(with_title)) {
  if(with_title[j]==FALSE){
    title[j]<-'NA'
  } else if(str_detect(name[j], "Rev.")=='TRUE') {
    title[j]<-"Rev."
  } else {
    title[j]<-"Dr."
  }
}
kable(data.frame(name, with_title, title))

name	with_title	title
Moe Szyslak	FALSE	NA
C. Montgomery Burns	FALSE	NA
Rev. Timothy Lovejoy	TRUE	Rev.
Ned Flanders	FALSE	NA
Homer Simpson	FALSE	NA
Dr. Julius Hibbert	TRUE	Dr.

3.3)

middle_name<-str_count(unlist(str_extract_all(name, "[^Dr\\. |Rev\\. ].+")), " ")
middle_name<-ifelse(middle_name==2, "yes", "no")
kable(data.frame(name, middle_name))

name	middle_name
Moe Szyslak	no
C. Montgomery Burns	yes
Rev. Timothy Lovejoy	no
Ned Flanders	no
Homer Simpson	no
Dr. Julius Hibbert	no

Question 4

v<-c("abc$123", "$123", "123$", "1$23", "data*", "tournamentinfo.txt", "science", "MSDS", "CUNY", "Texas", "Austin.", "<title> Data Science </title>", "txt.tournamentinfo", "04/24/1915", "12/12/12", "<table> List of dates <table>")

4.1)

[0-9]+\\$, string of digit(s) followed by a dollar sign

unlist(str_extract_all(v, "[0-9]+\\$"))

## [1] "123$" "1$"

4.2)

\\b[a-z]{1,4}\\b, string of lower case letters that ranges between 1 to 4 letters

unlist(str_extract_all(v, "\\b[a-z]{1,4}\\b"))

## [1] "abc"  "data" "txt"  "txt"  "of"

4.3)

.*?\\.txt$, string with any character(s) or number(s) that ends with .txt

unlist(str_extract_all(v, ".*?\\.txt$"))

## [1] "tournamentinfo.txt"

4.4)

\\d{2}/\\d{2}/\\d{4}, string that contains 2 digits with a slash then 2 digits and a slash and followed by 4 digits (e.g. numeric birthdate)

unlist(str_extract_all(v, "\\d{2}/\\d{2}/\\d{4}"))

## [1] "04/24/1915"

4.5)

<(.+?)>.+?</\\1>, string that has an opening and closing brackets at the beginning, then can take any string in the middle, then opening and closing brackets with a forward slash (e.g. html coding): <values> anything </values>

unlist(str_extract_all(v, "<(.+?)>.+?</\\1>"))

## [1] "<title> Data Science </title>"

Question 9

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

uppercase<-paste(unlist(str_extract_all(hidden, "[[A-Z].?]")), collapse="")
lowercase<-paste(unlist(str_extract_all(hidden, "[[a-z].?]")), collapse="")
numbers<-paste(unlist(str_extract_all(hidden, "[[0-9].?]")), collapse="")

uppercase

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

lowercase

## [1] "clcopowzmstcdwnkigvdicpuggvhrynjuwczihqrfpxsjdwpnanwowisdijjkpfdrcocbtyczjataootjtjnecfek.rwwwojigdvrfrbz.bknbhzgvizcrop.wgnb.qofaotfbwmktszqefyndtkcfgmcgxonhkgr"

numbers

## [1] "1087792855078035307553364.1162.24905..651724639589659490545"

• The meaningful sentence is the following:

uppercase<-str_replace_all(uppercase, "[.]", " ")
kable(data.frame(uppercase))

uppercase
CONGRATULATIONS YOU ARE A SUPERNERD