Question 3

library(stringr)
## Warning: package 'stringr' was built under R version 3.2.5
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,}"))

phone <- unlist(str_extract_all(raw.data, "\\(?(\\d{3})?\\)?(-|)?\\d{3}(-|)?\\d{4}"))

1 - convert to first_name and last_name

name_wo_comma <- unlist(name[!str_detect(name,",")])

name_wo_pref <- name
for (pref in c("Mr.","Ms.","Mrs.","Dr.","Rev.")){
        name_wo_pref <- unlist(str_trim(str_replace_all(name_wo_pref,pref,"")))
}
name_w_comma <- unlist(str_split(name_wo_pref[str_detect(name_wo_pref,",")],","))

name1 <- str_c(name_w_comma[2],name_w_comma[1],sep="_")
name2 <- str_c(name_w_comma[4],name_w_comma[3],sep="_")

name_wo_comma <- unlist(name_wo_pref[!str_detect(name_wo_pref,",")])
name_wo_comma <- unlist(str_replace_all(name_wo_comma," ","_"))

ex1_ans <- c(name_wo_comma,str_trim(name1),str_trim(name2))
print(ex1_ans)
## [1] "Moe_Szyslak"         "Timothy_Lovejoy"     "Ned_Flanders"       
## [4] "Julius_Hibbert"      "C. Montgomery_Burns" "Homer_Simpson"

2 - logical vector for titles

ex2_ans <- unlist(str_detect(name,"Dr.")) | unlist(str_detect(name,"Rev."))
print(ex2_ans)
## [1] FALSE FALSE  TRUE FALSE FALSE  TRUE

3 - logical vector for a second name.

Assumption - first name and last name will only be separated by one space. So, if there’s a middle name, then there will be more than one space.

ex3_ans <- as.logical(str_count(ex1_ans,"\\s"))
print(ex3_ans)
## [1] FALSE FALSE FALSE FALSE  TRUE FALSE

Question 4

  1. The pattern this describes is any number before the end of a sentence signaled by a “$”. For example “25$” will yield “25”.

  2. The pattern this describes is any word that’s four lower-case letters or less. For example, “Silo vase Case base1” will yield only “vase”

  3. This doesn’t describe any pattern. first “.*" will repeat the entire string inputted but “?” will turn everything into empty quotes.

  4. This describes a very specific pattern where there needs to be at least two digits followed by “/” then only two digits, followed by “/” then followed by at least four digits.

  5. Not really sure what this pattern is because I tried it on different strings and kept getting nothing.

Question 9

q9 <- paste0("clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0Tanw","Uwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigO",
"d6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5",
"fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr")
q9 <- str_conv(q9,"UTF-8")
q9_msg <- unlist(str_extract_all(q9,"[[:upper:][:punct:]]"))
print(q9_msg)
##  [1] "C" "O" "N" "G" "R" "A" "T" "U" "L" "A" "T" "I" "O" "N" "S" "." "Y"
## [18] "O" "U" "." "A" "R" "E" "." "A" "." "S" "U" "P" "E" "R" "N" "E" "R"
## [35] "D" "!"

Question 9 –> “CONGRATULATIONS. YOU ARE. A. SUPERNERD!”