#1. Using the 173 majors listed in fivethirtyeight.com’s College Majors dataset [https://fivethirtyeight.com/features/the-economic-guide-to-picking-a-college-major/], provide code that identifies the majors that contain either “DATA” or “STATISTICS”
##Load data
majors <- read.csv(url('https://raw.githubusercontent.com/fivethirtyeight/data/master/college-majors/majors-list.csv'), stringsAsFactors = F)
str(majors)## 'data.frame': 174 obs. of 3 variables:
## $ FOD1P : chr "1100" "1101" "1102" "1103" ...
## $ Major : chr "GENERAL AGRICULTURE" "AGRICULTURE PRODUCTION AND MANAGEMENT" "AGRICULTURAL ECONOMICS" "ANIMAL SCIENCES" ...
## $ Major_Category: chr "Agriculture & Natural Resources" "Agriculture & Natural Resources" "Agriculture & Natural Resources" "Agriculture & Natural Resources" ...majors$Major[grepl("DATA", majors$Major)]## [1] "COMPUTER PROGRAMMING AND DATA PROCESSING"majors$Major[grepl("STATISTICS", majors$Major)]## [1] "MANAGEMENT INFORMATION SYSTEMS AND STATISTICS"
## [2] "STATISTICS AND DECISION SCIENCE"#2 Write code that transforms the data below:
[1] “bell pepper” “bilberry” “blackberry” “blood orange”
[5] “blueberry” “cantaloupe” “chili pepper” “cloudberry”
[9] “elderberry” “lime” “lychee” “mulberry”
[13] “olive” “salal berry”
Into a format like this:
c(“bell pepper”, “bilberry”, “blackberry”, “blood orange”, “blueberry”, “cantaloupe”, “chili pepper”, “cloudberry”, “elderberry”, “lime”, “lychee”, “mulberry”, “olive”, “salal berry”)
fruit_list <- '[1] "bell pepper" "bilberry" "blackberry" "blood orange"
[5] "blueberry" "cantaloupe" "chili pepper" "cloudberry"
[9] "elderberry" "lime" "lychee" "mulberry"
[13] "olive" "salal berry"'##Load library
library(stringr)foods <- str_extract_all(fruit_list, '[a-z]+\\s[a-z]+|[a-z]+')
unlist(foods)## [1] "bell pepper" "bilberry" "blackberry" "blood orange" "blueberry"
## [6] "cantaloupe" "chili pepper" "cloudberry" "elderberry" "lime"
## [11] "lychee" "mulberry" "olive" "salal berry"#3 Describe, in words, what these expressions will match: (.)\1\1
Any character repeated 3 times in a row
test_vec <- c("aaa", "aaba" , "abcdef" , "thbbbht")
nums <- unlist(str_extract_all(test_vec, "(.)\\1\\1"))
nums## [1] "aaa" "bbb"“(.)(.)\2\1”
Two characters followed by the first two in reverse order
test_vec2 <- c("aabbaa", "aaba" , "abcdef")
nums2 <- unlist(str_extract_all(test_vec2, "(.)(.)\\2\\1"))
nums2## [1] "abba"(..)\1
Two characters repeated twice.
test_vec3 <- c("dodo", "ketchup" , "banana" , "cookie")
nums3 <- unlist(str_extract_all(test_vec3, "(..)\\1"))
nums3## [1] "dodo" "anan"“(.).\1.\1”
A character repeated three times with characters in between each repitition, e.g. abaca
test_vec4 <- c("avocado", "cadaea" , "banana" , "cookie")
nums4 <- unlist(str_extract_all(test_vec4, "(.).\\1.\\1"))
nums4## [1] "adaea" "anana""(.)(.)(.).*\3\2\1"
The characters followed by any character repeate 0 or more times and then then the same three characters in reverse order.
test_vec5 <- c("abc312131cba", "pizza", "bananaracecar" , "cookie")
nums5 <- unlist(str_extract_all(test_vec5, "(.)(.)(.).*\\3\\2\\1"))
nums5## [1] "abc312131cba" "racecar"#4 Construct regular expressions to match words that:
Start and end with the same character.
^(.).*\1$
test_vec6 <- c("abc312131cba", "pizza", "icecream" , "cookie")
nums6 <- str_extract(test_vec6, '^(.).*\\1$')
unlist(nums6)## [1] "abc312131cba" NA NA NAContain a repeated pair of letters (e.g. “church” contains “ch” repeated twice.)
(..).*\1
test_vec7 <- c("church", "bus", "river" , "mississippi")
nums7 <- str_extract_all(test_vec7, '(..).*\\1')
unlist(nums7)## [1] "church" "issis"Contain one letter repeated in at least three places (e.g. “eleven” contains three “e”s.)
([a-z]).\1.\1
test_vec8 <- c("church", "eleven", "river" , "mississippi")
nums8 <- str_extract_all(test_vec8, '([a-z]).*\\1.*\\1')
unlist(nums8)## [1] "eleve" "ississippi"