Data-607 Week-3 Assignment

—————————————————————————

Student Name : Sachid Deshmukh

Date : 09/16/2018

• GitHub Location for rmd file

• GitHub Location for pdf file

• RPubs location of published file

—————————————————————————

library(stringr)

## Warning: package 'stringr' was built under R version 3.4.3

Question 3: Copy the introductory example. The vector name stores the extracted names.

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"

* (a)

name.clean = str_replace_all(name,",", "")
name.fl = unlist(str_replace_all(name.clean, "[:alpha:]*[:punct:] ", ""))
name.fl

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

* (b)

str_detect(name.clean, unlist(str_extract_all(name.clean, "[:alpha:]{2,}[:punct:]")))

## [1] FALSE FALSE  TRUE FALSE FALSE  TRUE

* (c)

str_detect(name.clean, unlist(str_extract_all(name.clean, "[A-Z][:punct:]{1}")))

## [1] FALSE  TRUE FALSE FALSE FALSE FALSE

Question 4: Describe the type of strings that conform to the following regular expression

* (a) [0-9]+\$ : This regex match one or more digit follwed by $ sign

Example

str = "The value of this product is 100$"
amount = unlist(str_extract_all(str, "[0-9]+\\$"))
amount

## [1] "100$"

* (b) \b[a-z]{1,4}\b : This regex match any word in lower case whihc is 1 to 4 chars long

Example

str = "This is my batbinton bat"
bat = unlist(str_extract_all(str, "\\b[a-z]{1,4}\\b"))
bat

## [1] "is"  "my"  "bat"

* (c) .*?\.txt$ : This regex match any word endting wiht .txt # Example

files = c("Program.R", "Program.cpp", "Program.txt")
txt = unlist(str_extract_all(files, ".*?\\.txt$"))
txt

## [1] "Program.txt"

* (d) \d{2}/\d{2}/\d{4} : This regex match date pattern mm/dd/yyyy

Example

str = "Today's date is 09/16/2018"
date = unlist(str_extract_all(str,"\\d{2}/\\d{2}/\\d{4}" ))
date

## [1] "09/16/2018"

* (e) <(.+?)>.+?</\1> : This regex matches any word wrapped inside <> and </> HTML tags

Example

str = "To print in bold write <b>Bold</b> in Html"
html = unlist(str_extract_all(str, "<(.+?)>.+?</\\1>"))
html

## [1] "<b>Bold</b>"

Question 9 : Secret Message

sm =  "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"
decoded <- unlist(str_extract_all(sm, "[[:upper:].]{1,}"))
decoded <- str_replace_all(paste(decoded, collapse = ''), "[.]", " "); decoded

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