CUNY MSDS Data 607 HW3

Libraries:

library(stringr)
library(tidyverse)
library(kableExtra)
library(knitr)
library(plyr)

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

1. Use the tools of this chapter to rearrange the vector so that all elements conform to the standard first_name last_name.
2. Construct a logical vector indicating whether a character has a title (i.e., Rev. and Dr.).
3. Construct a logical vector indicating whether a character has a second name.

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

#pull out words
original_names <- unlist(str_extract_all(raw.data, "[[:alpha:]., ]{2,}"))
#remove middle names - detect a space, letter, and a '.', then replace with blank
names1 <- str_replace(original_names, "\\s[A-z]\\. ", " ")
#rearrange to first name last name - find word groups then swap them
names2 <- str_replace(names1, "(\\w+),\\s(\\w+)", "\\2 \\1")
#remove title: search for a-z{2-3letters} followed by a '.', then replace with blank
new_names <- str_replace(names2, "[A-z]{2,3}\\. ", " ")

originaln <- data.frame(original_names)
newn <- data.frame(new_names)

kable(list(originaln, newn), "html", escape = F) %>%
  kable_styling("striped", full_width = T) %>%
  column_spec(1, bold = T) %>%
  row_spec(1, bold = T)

title <- str_detect(names2,"[A-z]{2,3}\\. ")
df1 <- data.frame(names2, title)
kable(df1, "html", escape = F) %>%
  kable_styling("striped", full_width = T) 

second_name <- str_detect(original_names, "[A-Z]{1}\\.")
df2 <- data.frame(original_names, second_name)
kable(df2, "html", escape = F) %>%
  kable_styling("striped", full_width = T) 

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

1. [0-9]+\$
2. \b[a-z]{1,4}\b
3. .*?\.txt$
4. \d{2}/\d{2}/\d{4}
5. <(.+?)>.+?</\1>  

(a) [0-9]+\$ [0-9]select digits 0-9, + - one or more times, $

reg_a <- "534435457$saf!@#3123$"
str_extract_all(reg_a, "[0-9]+\\$" )

## [[1]]
## [1] "534435457$" "3123$"

(b) \b[a-z]{1,4}\ //b Word Edge, [a-z] letters a-z lowercase, {1,4} min,max chars

reg_b <- "nick hale y amanda nic khaleyamanda HI"
str_extract_all(reg_b, "\\b[a-z]{1,4}\\b")

## [[1]]
## [1] "nick" "hale" "y"    "nic"

(c) .*?\.txt$ Pulls out files: . any character except line break, /* zero or more times, //. literal ., $ end of line

reg_c <- "c:/local/nic/test.txt"
str_extract_all(reg_c, ".*?\\.txt$")

## [[1]]
## [1] "c:/local/nic/test.txt"

(d) \d{2}/\d{2}/\d{4} Pulls out dates: //d any digit, {2} 2 characters, / a ‘/’

rec_d <- " 02/10/2018"
str_extract_all(rec_d, "\\d{2}/\\d{2}/\\d{4}")

## [[1]]
## [1] "02/10/2018"

(e) <(.+?)>.+?</\1> Pulls out html code:

reg_e <- "<p>this is a paragraph</p>"
str_extract_all(reg_e, "<(.+?)>.+?</\\1>")

## [[1]]
## [1] "<p>this is a paragraph</p>"

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!

mystery <- "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"
#pull out all capital letters and periods
mystery1 <- unlist(str_extract_all(mystery, "[[A-Z].]"))
#Join the letters together, remove the spaces
mystery1 <- paste(mystery1, collapse = "")
#replaces the '.'s with a space
str_replace_all(mystery1, "[.]", " ")

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