Data 607 HW 3 - Regular Expressions

3. Copy the introductory example. The vector name stores the extracted name.

library(stringr)
#input the raw data
raw.data <- "555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5553642Dr. Julius Hibbert"
name <- unlist(str_extract_all(raw.data, "[[:alpha:]., ]{2,}"))

#list the vector names from the raw data
name

## [1] "Moe Szyslak"          "Burns, C. Montgomery" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders"         "Simpson, Homer"       "Dr. Julius Hibbert"

(a) Use the tools of this chapter to rearrange the vector so that all elements conform to the standard first_name last_name.

#split the name list by the "," delimiter
#only names with last name, first name format will be split
#names with first name - last name format will be untouched 
sp_name<-str_split(name,",")
sp_name

## [[1]]
## [1] "Moe Szyslak"
## 
## [[2]]
## [1] "Burns"          " C. Montgomery"
## 
## [[3]]
## [1] "Rev. Timothy Lovejoy"
## 
## [[4]]
## [1] "Ned Flanders"
## 
## [[5]]
## [1] "Simpson" " Homer" 
## 
## [[6]]
## [1] "Dr. Julius Hibbert"

reverse the list entries with last name, first name format so first name comes first

for (i in 1:length(sp_name)){
  if (length(sp_name[[i]]) > 1) {
    temp <- sp_name[[i]][1]
    sp_name[[i]][1] <- sp_name[[i]][2]
    sp_name[[i]][2] <- temp
  }
}
sp_name

## [[1]]
## [1] "Moe Szyslak"
## 
## [[2]]
## [1] " C. Montgomery" "Burns"         
## 
## [[3]]
## [1] "Rev. Timothy Lovejoy"
## 
## [[4]]
## [1] "Ned Flanders"
## 
## [[5]]
## [1] " Homer"  "Simpson"
## 
## [[6]]
## [1] "Dr. Julius Hibbert"

(b) Construct a logical vector indicating whether a character has a title (i.e., Rev. and Dr.).

title_name <- str_detect(name,"Rev.|Dr.|Mr.|Ms.|Mrs.")
comb_list <- data.frame (name, title_name)
comb_list

##                   name title_name
## 1          Moe Szyslak      FALSE
## 2 Burns, C. Montgomery      FALSE
## 3 Rev. Timothy Lovejoy       TRUE
## 4         Ned Flanders      FALSE
## 5       Simpson, Homer      FALSE
## 6   Dr. Julius Hibbert       TRUE

(c) Construct a logical vector indicating whether a character has a second name

mid_name <- str_detect(name," [A-Z]\\.")
comb_list2 <- data.frame (name, mid_name)
comb_list2

##                   name mid_name
## 1          Moe Szyslak    FALSE
## 2 Burns, C. Montgomery     TRUE
## 3 Rev. Timothy Lovejoy    FALSE
## 4         Ned Flanders    FALSE
## 5       Simpson, Homer    FALSE
## 6   Dr. Julius Hibbert    FALSE

**7. Consider the string

. We would like to extract the first HTML tag. To do so we write the regular expression <.+>. Explain why this fails and correct the expression.**

tag1 <- "<title>+++BREAKING NEWS+++</title>"

#using the wrong regex <.+>
# this regex will pick up the entire string since it will pick-up
# the second ">" (Greedy quantification)
wrong_tag <- str_extract(tag1,"<.+>")
wrong_tag

## [1] "<title>+++BREAKING NEWS+++</title>"

#to prevent this from happening, we use the
#the regex below

right_tag <- str_extract(tag1,"<[[:alpha:]]+>")
right_tag

## [1] "<title>"

8. Consider the string (5-3)²⁼⁵2-253+3^2 conforms to the binomial theorem. We would like to extract the formula in the string. To do so we write the regular expression [^0-9=+*()]+. Explain why this fails and correct the expression.

#assign formula to string variable
bi_for <- "(5-3)^2=5^2-2*5*3+3^2"

#wrong formula used
#the ^ sign and the - sign are special signs in regex 
#they must be preceeded by escape characters \\
wrong_formula <- str_extract(bi_for, "[^0-9=+*()]+")
wrong_formula

## [1] "-"

#the righ formula with escpae characters
#digits where also converted to \\d instead of using 0-9
right_formula <- str_extract(bi_for, "[\\-\\^\\d=+*()]+")
right_formula

## [1] "(5-3)^2=5^2-2*5*3+3^2"