Data Collection Assignment 3

library(openintro)
library(stringr)
library(RCurl)
library(tidyverse)
library(dplyr)

Exercise 1:

Provide Code that Identifies Majors with “Data” or “Statistics” in the name

#Read data into R using RCurl
x <- getURL("https://raw.githubusercontent.com/fivethirtyeight/data/master/college-majors/all-ages.csv")
college_data <- read.csv(text = x)


str_subset(college_data$Major,("DATA|STATISTICS"))

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

Exercise 2:

write code that transforms data:

#raw text
dat <- '[1] "bell pepper"  "bilberry"     "blackberry"   "blood orange"

[5] "blueberry"    "cantaloupe"   "chili pepper" "cloudberry"  

[9] "elderberry"   "lime"         "lychee"       "mulberry"    

[13] "olive"        "salal berry"'

#extracting the phrases
fruit_dat<-str_extract_all(dat,"[a-z]+ ?[a-z]+")%>%unlist()

#collapsing with ', '
fruit_dat<-str_c(fruit_dat, collapse=', ')


#adding in quotes
fruit_dat<-cat(gsub("\\b", '"', fruit_dat, perl=T))

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

Exercise 3

describe the following pattern

part 1

“(.)\1\1”

This will ONLY match “(any character or”.“)\1\1”. It looks like a backreference, but you need to escape the "" if you want to use it as a backreference.

Example:

x<-c("(.)\1\1","check\1\1","aaa","b)\1\1")

pattern<-"(.)\1\1"

str_view_all(x,pattern)

part 2

“(.)(.)\2\1”

This will match a first group, a second group, followed by the second group again and then the first group again.

Example:

pattern<-"(.)(.)\\2\\1"

str_view(words,pattern, match=TRUE)

part 3

“(..)\1”

this will only match “(any two characters or ..)\1” because it is not a backreference

Example:

x<-c("(.)\1\1","check\1\1","aaa","b)\1\1")

pattern<-"(..)\1"

str_view_all(x,pattern)

part 4

“(.).\1.\1”

this will match a group, followed by any character, followed by the group, followed by any character, followed by the group.

Example:

pattern<-"(.).\\1.\\1"

str_view(words,pattern, match=TRUE)

part 5

"(.)(.)(.).*\3\2\1"

this will match three groups, followed by any number of characters until the group is repeated in reverse.

Example:

pattern<-"(.)(.)(.).*\\3\\2\\1"

str_view(words,pattern, match=TRUE)

Excersise 4:

Construct regular expressions that meet requirements

part 1

Start and end with the same character.

pattern<-"^(.).*\\1$"


#Example

result<-str_subset(words[1:300],pattern)%>%unlist()

result

##  [1] "america"    "area"       "dad"        "dead"       "depend"    
##  [6] "educate"    "else"       "encourage"  "engine"     "europe"    
## [11] "evidence"   "example"    "excuse"     "exercise"   "expense"   
## [16] "experience" "eye"

part 2

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

pattern<-"(..).*\\1"

result<-str_subset(words[1:300],pattern)%>%unlist()

result

## [1] "appropriate" "church"      "condition"   "decide"      "environment"

part 3

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

pattern<-"(.).*\\1.*\\1"

result<-str_subset(words[1:300],pattern)%>%unlist()

result

##  [1] "appropriate" "available"   "believe"     "between"     "business"   
##  [6] "degree"      "difference"  "discuss"     "eleven"      "environment"
## [11] "evidence"    "exercise"    "expense"     "experience"