# Import RCurl to pull the csv file from the Github repo
library(RCurl)## Loading required package: bitops# Load the csv file from the Github repo's URL
college_majors_url <- getURL("https://raw.githubusercontent.com/fivethirtyeight/data/master/college-majors/recent-grads.csv")
college_majors <-data.frame(read.csv(text=college_majors_url, header=T))
# Perform regex using grep function and then output the result
data_or_stats <- grep(pattern = 'DATA|STATISTICS', college_majors$Major, value = TRUE, ignore.case = TRUE)
data_or_stats## [1] "MANAGEMENT INFORMATION SYSTEMS AND STATISTICS"
## [2] "STATISTICS AND DECISION SCIENCE"
## [3] "COMPUTER PROGRAMMING AND DATA PROCESSING"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”)
library(stringr)
original_data <- '[1] "bell pepper" "bilberry" "blackberry" "blood orange"
[5] "blueberry" "cantaloupe" "chili pepper" "cloudberry"
[9] "elderberry" "lime" "lychee" "mulberry"
[13] "olive" "salal berry"'
# str_extract_all returns a list
result <- str_extract_all(original_data, pattern = '[a-z]+\\s?[a-z]+')
result_string <- str_c(result, collapse = ", ")## Warning in stri_c(..., sep = sep, collapse = collapse, ignore_null = TRUE):
## argument is not an atomic vector; coercingwriteLines(result_string)## c("bell pepper", "bilberry", "blackberry", "blood orange", "blueberry", "cantaloupe", "chili pepper", "cloudberry", "elderberry", "lime", "lychee", "mulberry", "olive", "salal berry")# vector <- as.vector(unlist(result))
# vectorMatches strings containing any single character except new line followed by ‘\1\1’.
Matches strings containing any two characters that are immediately followed by the same two characters in the opposite order. In essence, it matches a 4-character palindrome.
Matches strings containing any two characters (except new line) followed by ‘\1’.
Matches strings containing any single character (except new line) followed by any character then the matched character followed by any character, then the matched character again.
Matches strings containing any three characters in a row in which the three characters are repreated but in the opposite order later in the string.
See samples below for validating the above descriptions.
sample_01 <- c('a\1\1', 'b\1\1', 'ccc\1\1c', 'd\1d')
str_view(sample_01, "(.)\1\1")sample_02 <- c('abcccba', 'badmomdad', 'maddam')
str_view(sample_02, "(.)(.)\\2\\1")sample_03 <- c('abc\1d', 'abc\2dd', '\1d')
str_view(sample_03, "(..)\1")sample_04 <- c('philzlyl')
str_view(sample_04, "(.).\\1.\\1")sample_05 <- c('philzzzzzlih', 'phillih','philzzzzzhil','philzzliphzzzlihp')
str_view(sample_05, "(.)(.)(.).*\\3\\2\\1")Construct regular expressions to match words that:
Start and end with the same character.
Answer: "^(.).*\\1$"
# Start and end with the same character.
sample_04_01 <- c('helloh', 'hello', 'helloho')
str_view(sample_04_01, "^(.).*\\1$")Contain a repeated pair of letters (e.g. “church” contains “ch” repeated twice.)
Answer: "(..).*\\1"
# Contain a repeated pair of letters (e.g. "church" contains "ch" repeated twice.)
sample_04_02 <- c('church', 'badmomdad', 'helo')
str_view(sample_04_02, "(..).*\\1")Contain one letter repeated in at least three places (e.g. “eleven” contains three “e”s.)
Answer: “(.).\\1.\\1”
# Contain one letter repeated in at least three places (e.g. "eleven" contains three "e"s.)
sample_04_03 <- c('eleven', 'elevn', 'daddy', 'dady')
str_view(sample_04_03, "(.).*\\1.*\\1")See the samples to confirm answers above.