#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”
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" ...grep(pattern = 'STATISTICS|DATA', majors$Major, value = TRUE, ignore.case = TRUE)## [1] "MANAGEMENT INFORMATION SYSTEMS AND STATISTICS"
## [2] "COMPUTER PROGRAMMING AND DATA PROCESSING"
## [3] "STATISTICS AND DECISION SCIENCE"majors$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”)
Source_data = '[1] "bell pepper" "bilberry" "blackberry" "blood orange"
[5] "blueberry" "cantaloupe" "chili pepper" "cloudberry"
[9] "elderberry" "lime" "lychee" "mulberry"
[13] "olive" "salal berry"'
library(stringr)
healthy <- str_extract_all(Source_data, '[:alpha:]+\\s[:alpha:]+|[:alpha:]+')
unlist(healthy)## [1] "bell pepper" "bilberry" "blackberry" "blood orange" "blueberry"
## [6] "cantaloupe" "chili pepper" "cloudberry" "elderberry" "lime"
## [11] "lychee" "mulberry" "olive" "salal berry"cat(paste0("c(",paste0(sep = '"',healthy, collapse = ', ', sep='"'),paste(")")))## c("c("bell pepper", "bilberry", "blackberry", "blood orange", "blueberry", "cantaloupe", "chili pepper", "cloudberry", "elderberry", "lime", "lychee", "mulberry", "olive", "salal berry")")#The two exercises below are taken from R for Data Science, 14.3.5.1 in the on-line version: #3 Describe, in words, what these expressions will match: (.)\1\1 = ‘(.)’ matches any one character and the ‘/1’ means the same character repeated a second time and the next ‘/1’ means the same character appearing three times in a row such as ‘bbb’ (Are two slashes not needed?)
“(.)(.)\2\1” = ‘(.)(.)’ represents a pair of characters, and //2//1 means the next pair of characters match it exactly with case sensitivity such as hiih
(..)\1 = ‘(..)’shows two characters, and’/1’ represents that those two characters are repeated such as hihi (Are two slashes not needed?)
“(.).\1.\1” = the 1st, 3rd, and 5th ch match. Character A, followed by any character, Character A, followed by any character, Character A, such as 23242.
“(.)(.)(.).*\3\2\1” = First 3 characters match the last 3 characters in rever order, with any characters in between such as 12398321
#4 Construct regular expressions to match words that: Start and end with the same character.
str_subset(words, "^(.)((.*\\1$)|\\1?$)")## [1] "a" "america" "area" "dad" "dead"
## [6] "depend" "educate" "else" "encourage" "engine"
## [11] "europe" "evidence" "example" "excuse" "exercise"
## [16] "expense" "experience" "eye" "health" "high"
## [21] "knock" "level" "local" "nation" "non"
## [26] "rather" "refer" "remember" "serious" "stairs"
## [31] "test" "tonight" "transport" "treat" "trust"
## [36] "window" "yesterday"Contain a repeated pair of letters (e.g. “church” contains “ch” repeated twice.)
str_subset(words, "([A-Za-z][A-Za-z]).*\\1")## [1] "appropriate" "church" "condition" "decide" "environment"
## [6] "london" "paragraph" "particular" "photograph" "prepare"
## [11] "pressure" "remember" "represent" "require" "sense"
## [16] "therefore" "understand" "whether"Contain one letter repeated in at least three places (e.g. “eleven” contains three “e”s.)
str_subset(words, "([a-z]).*\\1.*\\1")## [1] "appropriate" "available" "believe" "between" "business"
## [6] "degree" "difference" "discuss" "eleven" "environment"
## [11] "evidence" "exercise" "expense" "experience" "individual"
## [16] "paragraph" "receive" "remember" "represent" "telephone"
## [21] "therefore" "tomorrow"#Latex error-> tinytex
```