A3

Load required libraries.

tidyverse

library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.6     v dplyr   1.0.7
## v tidyr   1.1.4     v stringr 1.4.0
## v readr   2.1.1     v forcats 0.5.1

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

1.

Read CSV file from Fivethirtyeight’s Github repo. Take a subset including the names of the majors.

filename <- "https://raw.githubusercontent.com/fivethirtyeight/data/master/college-majors/majors-list.csv"

majors <- read.csv(filename, header=TRUE, sep=",")

majors <- subset(majors, select=2)

Use gsub() with regex to clean the data.

y <-gsub(pattern = "\"", replacement = "", majors)
y <- gsub(pattern = "\\n", replacement="", y)

z <- str_split(y, ", ")

Loop through the majors, looking for the ones containing the keywords DATA or STATISTICS.

a <- data.frame(as.list(z))


for (i in 1:nrow(a)) {
  m <- a[i,1]
  if (length(grep("DATA", m)) != 0) {
    print(m)
  }
  if (length(grep("STATISTICS", m)) != 0) {
    print(m)
  }
}

## [1] "MANAGEMENT INFORMATION SYSTEMS AND STATISTICS"
## [1] "COMPUTER PROGRAMMING AND DATA PROCESSING"
## [1] "STATISTICS AND DECISION SCIENCE"

2.

Input string to be transformed:

a <- '[1] "bell pepper"  "bilberry"     "blackberry"   "blood orange"
[5] "blueberry"    "cantaloupe"   "chili pepper" "cloudberry"  
[9] "elderberry"   "lime"         "lychee"       "mulberry"    
[13] "olive"        "salal berry"'

Regex for cleaning the string

x <-a 

b <- gsub('(\n)|(\\[|\\])|[0-9]', '', x)

b <- gsub('(\\s+)', ' ', b)


b <- gsub('\" ', '\", ', b)

c <-paste('c(', b ,')',sep="")
c <- gsub("c\\( ", "c\\(", c)

Finally, use writeLines() to see the raw transformed string.

writeLines(c)

## c("bell pepper", "bilberry", "blackberry", "blood orange", "blueberry", "cantaloupe", "chili pepper", "cloudberry", "elderberry", "lime", "lychee", "mulberry", "olive", "salal berry")

3.

Describe what the expressions will match.

(.)\1\1

#1 
z <- c("aabbc", "aba","a\1\1" ,"bcc", "xcccx", "church", "bcb", "ffffffxyzhhhhhhhf", "k", "banana", "eleven")
str_view(z, "(.)\1\1", match=TRUE)

This matches any character followed by 2 Start of Header (SOH) characters.

"(.)(.)\\2\\1"

#2 
z <- c("aabbc", "aba","a\1\1" ,"bcc", "xcccx", 
       "church", "bcb", "fxyzhhhhhhhf", 
       "k", "banana", "eleven", "naabbm",
       "abba", "\"woow\"")
str_view(z, '"(.)(.)\\2\\1"', match=TRUE)

This matches any string that contains a 4-character palindrome enclosed by double quotes. In other words, it will match strings that go forward the same as backwards with " on both ends.

(..)\1

#3
z <- c("aabbc", "aba","a\1\1" ,"bcc", "xcccx", 
       "church", "bcb", "aabjjjj", "hijklmnmn","ffffffxyzhhhhhhhf", 
       "k", "banana", "eleven", "ab\1", "bb\1", "cc", "gfrt\1",
       "abba")
str_view(z, "(..)\1", match=TRUE)

This will match any string that contains two characters followed by a SOH character.

"(.).\\1.\\1"

#4
z <- c("aabbc", "aba","a\1\1" ,"bcc", "xcccx", 
       "church", "bcb", "aabjjjj", "hijklmnmn","ffffffxyzhhhhhhhf", 
       "k", "banana", "eleven", "ab\1", "bb\1", "cc", "gfrt\1",
       "abba", "abaca", "\"abaca\"")

str_view(z, '"(.).\\1.\\1"', match=TRUE)

This will match a string enclosed in double quotes with a character that repeats twice with 1 character between each repetition.

"(.)(.)(.).*\\3\\2\\1" This will match a string that contains a substring enclosed within double quotes, that starts with 3 characters, then has any number of random other characters, then has the same first 3 characters mirrored. In other words, the substring is like a palindrome, except the reflection happens after some random characters in between.

4.

Construct regular expressions to match words that:

Start and end with the same character.

x <- c("abc", "aba", "bcc", "bcb", "ffffffxyzhhhhhhhf", "k")
str_view(x, "^(.).*\\1$", match=TRUE)

Contain a repeated pair of letters (e.g. “church” contains “ch” repeated twice.)

y <- c("aabbc", "aba", "bcc", "church", "bcb", "ffffffxyzhhhhhhhf", "k")
str_view(y, ".*(..).*(..).*", match=TRUE)

Contain one letter repeated in at least three places (e.g. “eleven” contains three “e”s.)

z <- c("aabbc", "aba", "bcc", "church", "bcb", "ffffffxyzhhhhhhhf", "k", "banana", "eleven")
str_view(z, ".*(.).*\\1.*\\1.*", match=TRUE)