607Assignment3.Rmd

---
title: "607Assignment3"
author: "Lwin Shwe"
date: "2023-09-17"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

###  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".


```{r loading-data}
library(RCurl)
library(dplyr)
library(stringr)
library(tidyverse)

#Import CSV from Raw File of 173 majors listed in fivethirtyeight.com’s College Majors dataset
College_majors = read.csv('https://raw.githubusercontent.com/fivethirtyeight/data/master/college-majors/majors-list.csv')


# Identify the majors that contain either "DATA" or "STATISTICS"
Idenfied_majors <- College_majors %>%
  filter(str_detect(Major, "DATA|STATISTICS"))

```


###  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")


```{r string-data, echo=FALSE}
# Data String
String_data <- c(
  "bell pepper", "bilberry", "blackberry", "blood orange",
  "blueberry", "cantaloupe", "chili pepper", "cloudberry",
  "elderberry", "lime", "lychee", "mulberry",
  "olive", "salal berry"
)

# Transform the data into the desired format
transformed_data <- paste0('"', String_data, '"')

# Print the formatted data
cat(transformed_data, sep = ", ")

summary(transformed_data)

```

###  3. Describe, in words, what these expressions will match:

•	(.)\1\1 : This expression matches any character repeated three times in a row

```{r aaa}

# Check for matches of the pattern (.)\1\1 in each string
matches <- str_detect(String_data, "(.)\\1\\1")

# Display the matches
String_data[matches]

```


•	"(.)(.)\\2\\1": This expression matches two characters followed by the same two characters in reverse order

```{r aabb}

# Check for matches of the pattern (.)(.)\\2\\1 in each string
matches <- str_detect(String_data, "(.)(.)\\2\\1")

# Display the matches
String_data[matches]

```

•	(..)\1 : This expression matches two characters repeated twice. E.g "abab", "abba"

```{r abab}
# Check for matches of the pattern (..)\1 in each string
matches <- str_detect(String_data, "(..)\1")

# Display the matches
String_data[matches]
```


•	"(.).\\1.\\1" : This expression matches a character repeated three times with characters in between each repetition, e.g. abaca

```{r abaca}
# Check for matches of the pattern "(.).\\1.\\1" in each string
matches <- str_detect(String_data, "(.).\\1.\\1")

# Display the matches
String_data[matches]
```


•	"(.)(.)(.).*\\3\\2\\1" : This expression matches characters followed by any character repeate 0 or more times and then the same three characters in reverse order.Eg. "abc312131cba", "aaabbbccc"

```{r aaabbbccc}
# Check for matches of the pattern "(.)(.)(.).*\\3\\2\\1" in each string
matches <- str_detect(String_data, "(.)(.)(.).*\\3\\2\\1")

# Display the matches
String_data[matches]
```



### 4.Construct regular expressions to match words that:

•	Start and end with the same character.

```{r same-start-and-end}
# Consider words in the category of jewelries
Jewelries <- c(
  "studs", "necklaces", "bracelets", "rings",
  "pendant", "earrings", "anklets", "watches",
  "brooches", "cufflinks", "chains", "headpieces",
  "bangles", "hoops"
)

similarities_a <- str_subset(Jewelries, "^(.)((.*\\1$)|\\1?$)")
similarities_a
```


•	Contain a repeated pair of letters (e.g. "church" contains "ch" repeated twice.)

```{r repeated-pairs}
similarities_b <- str_subset(Jewelries, "(..).*\\1")
similarities_b
```


•	Contain one letter repeated in at least three places (e.g. "eleven" contains three "e"s

```{r repeated-three}
similarities_c <- str_subset(Jewelries, "(.).*\\1.*\\1")
similarities_c
```