Please deliver links to an R Markdown file (in GitHub and rpubs.com) with solutions to problems 3 and 4 from chapter 8 of Automated Data Collection in R. Problem 9 is extra credit.
Problems
library(stringr)
raw.data <- "555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5553642Dr. Julius Hibbert"
main_names <- unlist(str_extract_all(raw.data, "[[:alpha:]., ]{2,}")) # extract names only.
main_names
## [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.
names1 <- str_replace(main_names, "\\s[A-z]\\. ", " ")#remove initials and then replace with blank
names2 <- str_replace(names1, "(\\w+),\\s(\\w+)", "\\2 \\1")#find words and then swap.switch from last name first name to first name last name
final_names <- sub("[A-z]{2,3}\\. ","",names2)#Remove titles
final_names
## [1] "Moe Szyslak" "Montgomery Burns" "Timothy Lovejoy"
## [4] "Ned Flanders" "Homer Simpson" "Julius Hibbert"
(b)Construct a logical vector indicating whether a character has a title.
title <- str_detect(names2,"[A-z]{2,3}\\. ")
df_title <- data.frame(names2,title)
df_title
## names2 title
## 1 Moe Szyslak FALSE
## 2 Montgomery Burns FALSE
## 3 Rev. Timothy Lovejoy TRUE
## 4 Ned Flanders FALSE
## 5 Homer Simpson FALSE
## 6 Dr. Julius Hibbert TRUE
(c).Construct a logical vector indicating whether a character has a second name
second_name <- str_detect(main_names," [A-Z]{1}\\. ")
df_name <- data.frame(main_names,second_name)
df_name
## main_names second_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
construct an example that is matched by the regular expression.
It matches vector containing a range of number from 0 to 9 (one or more digits) and ending with a dollar sign.
reg_exp <- "The average salary amount for data scientist can be over 100000$"
str_extract_all(reg_exp, "[0-9]+\\$" )
## [[1]]
## [1] "100000$"
It matches vector containing a word Edge with 1 to 4 lowercase letters
lower <- "automated data collection with r"
unlist(str_extract_all(lower, "\\b[a-z]{1,4}\\b"))
## [1] "data" "with" "r"
It matches vector that ends in .txt
text <- c("You should write a text with 500 words", "You can save the file.txt")
unlist(str_extract_all(text, ".*?\\.txt$"))
## [1] "You can save the file.txt"
It matches vector with two digits and forward slash, two digits and foward slash, four digits.
digit <- c("Today is 09/11/2019", "Can you guess 9/11/9")
unlist(str_extract_all(digit, "\\d{2}/\\d{2}/\\d{4}"))
## [1] "09/11/2019"
It matches vector that starts with a zero or more letter inside inequality symbol and ends with forward slash and the same word or letter inside inequality symbol-Pulls a html code
compare <- c("<p> Assignment number three </p>")
unlist(str_extract_all(compare, "<(.+?)>.+?</\\1>"))
## [1] "<p> Assignment number three </p>"
clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0Tanwo Uwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigO d6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5 fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr
secret_message <- "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0Tanwo
Uwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigO
d6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5
fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"
Get all capital letters and periods
secret_message1 <- unlist(str_extract_all(secret_message, "[[A-Z].]"))
secret_message1
## [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"
Put the letters together and remove the spaces
secret_message1 <- paste(secret_message1, collapse = "")
secret_message1
## [1] "CONGRATULATIONS.YOU.ARE.A.SUPERNERD"
Replace ‘.’ with a space
str_replace_all(secret_message1, "[.]", " ")
## [1] "CONGRATULATIONS YOU ARE A SUPERNERD"
secret_message1
## [1] "CONGRATULATIONS.YOU.ARE.A.SUPERNERD"