DATA 606 Week 3

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

library(stringr)
raw.data <- paste("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,}"))
name

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

1. Use the tools of this chapter to rearrange the vector so that all the elements conform to the standard first_name last_name format. Some names have abbreviations such as C for Charles. I want to remove them. I also notice that there is a comma for the names that do need to be switched. I want to use this to my advantage in order to flip names over the comma. I also want to remove titles from names.

#Some names contain Abbs such as C for Charles. 
#Lets remove them 
name2 <- sub(" [A-z]{1}\\. ","",name)
name2

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

#Lets now remove titles from the names
name3 <- sub("[A-z]{2,3}\\. ","",name2)
name3

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

#We can use the fact that the names that need to be switched have a comma,
#we can flip names over the entries with the comma
name4 <- sub("(\\w+),\\s(\\w+)","\\2 \\1", name3)
name4

## [1] "Moe Szyslak"      "Montgomery Burns" "Timothy Lovejoy" 
## [4] "Ned  Flanders"    "Homer Simpson"    "Julius Hibbert"

#Now as a data frame 
df.names <- data.frame(name4)
df.names

##              name4
## 1      Moe Szyslak
## 2 Montgomery Burns
## 3  Timothy Lovejoy
## 4    Ned  Flanders
## 5    Homer Simpson
## 6   Julius Hibbert

2. Construct a logical vector indicating whether a character has a title

#Recall the original sample 'name2' from part a
title_vector <- str_detect(name2, "[[:alpha:]]{2,}\\.")
title_vector

## [1] FALSE FALSE  TRUE FALSE FALSE  TRUE

#It can be seen easier as a data frame
df.titlevector <- data.frame(name2,title_vector)
df.titlevector

##                  name2 title_vector
## 1          Moe Szyslak        FALSE
## 2    Burns, Montgomery        FALSE
## 3 Rev. Timothy Lovejoy         TRUE
## 4        Ned  Flanders        FALSE
## 5       Simpson, Homer        FALSE
## 6   Dr. Julius Hibbert         TRUE

We have correctly identifed who has a title or not using TRUE/FALSE statements

3. Contruct a logical vector that indicates if a character has a second name

secondname <- str_detect(name," [A-z]{1}\\. ")
df.secondname <- data.frame(name,secondname)
df.secondname

##                    name secondname
## 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

We have correctly identifed who has a second name

3. Describe the Types of Strings that conform to the following regular expressions and contruct an example that is matched by the regular expression

# [0-9]+\\$
#\\b[a-z]{1,4}\\b
# .*?\\.txt$
#\\d{2}/\\d{2}/\\d{4}
#<(.+?)>.+?</\\1>

#A digit or more followed by the dollar $ 
pattern1<-"[0-9]+\\$"
sample1=c("1837648", "hy45$", "55$")
str_detect(sample1, pattern1)

## [1] FALSE  TRUE  TRUE

#Any word that has anywhere between 1 to 4 letters end with word boundary
pattern2<-"\\b[a-z]{1,4}\\b"
sample2<-c("cat","dogs","birds", "the", "abc is 123 is cool")
str_detect(sample2,pattern2)

## [1]  TRUE  TRUE FALSE  TRUE  TRUE

#A string that ends with a .txt and then new line or end line 
pattern3<-".*?\\.txt$"
sample3<-c("hello.txt", "txt", "pets.txt","hd73tdh.txt")
str_detect(sample3,pattern3)

## [1]  TRUE FALSE  TRUE  TRUE

#Numbers that are written in format nn/nn/nnn
pattern4='\\d{2}/\\d{2}/\\d{4}'
sample4<-c("109/8473/9848", "33/33/3333", "5/4/3")
str_detect(sample4, pattern4)

## [1] FALSE  TRUE FALSE

#Select one or more character inside brakcets <>
#Followed by one or more character 
#Followed by the same character inside the previous <> with a / in front (html format)
pattern5<-"<(.+?)>.+?</\\1>"
sample5<-c("<bob>hello</bob>", "<bob>hello<bob>")
str_detect(sample5,pattern5)

## [1]  TRUE FALSE

9. Extra Credit-The following code hides a secret message. Crack it with R and regular expressions.

secret_code <-"clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"

#lets extract upper case letters
secret_code2 <- unlist(str_extract_all(secret_code, "[[:upper:].]{1,}"))
secret_code2

##  [1] "C"  "O"  "N"  "G"  "R"  "A"  "T"  "U"  "L"  "AT" "I"  "O"  "N"  "S" 
## [15] "."  "Y"  "O"  "U"  "."  "A"  "R"  "E"  "."  "A"  ".S" "U"  "P"  "E" 
## [29] "R"  "N"  "E"  "R"  "D"

#I can see the message but it can be massaged to look like standard text that anyone could read
secret_code3 <- str_replace_all(paste(secret_code2, collapse = ''), "[.]", " ")
secret_code3

## [1] "CONGRATULATIONS YOU ARE A SUPERNERD"