Rpub link:
http://rpubs.com/ssufian/527284
GitHub link:
https://github.com/ssufian/Data_607
library(tidyverse)## -- Attaching packages ----- tidyverse 1.2.1 --## v ggplot2 3.2.1 v purrr 0.3.2
## v tibble 2.1.3 v dplyr 0.8.3
## v tidyr 0.8.3 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.4.0## -- Conflicts -------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(stringr)
#copy the raw data
raw.data <-"555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5553642Dr. Julius Hibbert"
raw.data## [1] "555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5553642Dr. Julius Hibbert"The names extracted from the original is shown below:
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"library(stringr)
#extract last names
last1 <- str_extract(name, '[[:alpha:]]{1,}\\,|\\b [[:alpha:]]{1,}')
name## [1] "Moe Szyslak" "Burns, C. Montgomery" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders" "Simpson, Homer" "Dr. Julius Hibbert"last <- str_extract(last1, "[[:alpha:]]{1,}")
last## [1] "Szyslak" "Burns" "Lovejoy" "Flanders" "Simpson" "Hibbert"#extract first names
first1 <- str_extract(name, '[[:alpha:]]{1,} |\\. [[:alpha:]]{1,}|\\, [[:alpha:]]{2,}')
first <- str_extract(first1, "[[:alpha:]]{1,}")
first1## [1] "Moe " ". Montgomery" ". Timothy" "Ned "
## [5] ", Homer" ". Julius"first## [1] "Moe" "Montgomery" "Timothy" "Ned" "Homer"
## [6] "Julius"# prob 3 cont'd: putting firstname lastname convention in dataframe
df <- data.frame(first,last)
df## first last
## 1 Moe Szyslak
## 2 Montgomery Burns
## 3 Timothy Lovejoy
## 4 Ned Flanders
## 5 Homer Simpson
## 6 Julius Hibbert# logical check for titles or not in dataframe
df$title <- str_detect(name, 'Rev.|Dr.')
df## first last title
## 1 Moe Szyslak FALSE
## 2 Montgomery Burns FALSE
## 3 Timothy Lovejoy TRUE
## 4 Ned Flanders FALSE
## 5 Homer Simpson FALSE
## 6 Julius Hibbert TRUE# logical check if there's middle name in dataframe
df$middlename <- str_detect(name, ' [[:alpha:]]{1,}\\.')
df## first last title middlename
## 1 Moe Szyslak FALSE FALSE
## 2 Montgomery Burns FALSE TRUE
## 3 Timothy Lovejoy TRUE FALSE
## 4 Ned Flanders FALSE FALSE
## 5 Homer Simpson FALSE FALSE
## 6 Julius Hibbert TRUE FALSE# create a new column with first and last names in FINAL dataframe
df$first_last <- paste(df$first,df$last, sep=" ",collapse=NULL)
df## first last title middlename first_last
## 1 Moe Szyslak FALSE FALSE Moe Szyslak
## 2 Montgomery Burns FALSE TRUE Montgomery Burns
## 3 Timothy Lovejoy TRUE FALSE Timothy Lovejoy
## 4 Ned Flanders FALSE FALSE Ned Flanders
## 5 Homer Simpson FALSE FALSE Homer Simpson
## 6 Julius Hibbert TRUE FALSE Julius Hibbertans:
This regex returns a string of numericals followed by $ sign
test <- "999$a###6-77$.2.2$a11$"
unlist(str_extract_all(test, '[0-9]+\\$'))## [1] "999$" "77$" "2$" "11$"ans:
This regex returns 1-4 lower alpha characters bounded at both ends with a leading non-word and an ending non-word
test2 <- "z-one3 55.tree !CRAZY%$-czdz"
unlist(str_extract_all(test2, '\\b[a-z]{1,4}\\b'))## [1] "z" "tree" "czdz"ans:
This regex returns anything with as many repititions, 0 or more times that ends with a litteral of .txt
test3 <- "911!889]]2.txt else.pdf----%&@.txt"
unlist(str_extract_all(test3, '.*?\\.txt$'))## [1] "911!889]]2.txt else.pdf----%&@.txt"ans: This regex returns a date format type such 2 digit month, 2 digit days followed by 4 digit year: two digits(usually months) followed by another two digits(days) and then four digits(years)
test4 <- "09/11/2019 02/02/2002 1986/01/02"
unlist(str_extract_all(test4, '\\d{2}/\\d{2}/\\d{4}'))## [1] "09/11/2019" "02/02/2002"<(.+?)>.+?</\1>
ans:
This regex matches any
test5 <- "<oor><pi>jacki007<//ollaah>12ee22<li>once upon a time in 1999 </oor>"
unlist(str_extract_all(test5, '<(.+?)>.+?</\\1>'))## [1] "<oor><pi>jacki007<//ollaah>12ee22<li>once upon a time in 1999 </oor>"The following code hides a secret message. Crack it with R and regular expressions. Hint: Some of the characters are more revealing than others! The code snippet is also available in the materials at www.r-datacollection.com.
encrypted <- "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"
## remove all numbers and lowercase letters
cracked <- unlist(str_extract_all(encrypted, '[^[a-z]|[0-9]]'))
cracked## [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" "!"cracked1 <- paste0(cracked, collapse="")
cracked1## [1] "CONGRATULATIONS.YOU.ARE.A.SUPERNERD!"gsub(".", " ", cracked1,fixed=TRUE) ## [1] "CONGRATULATIONS YOU ARE A SUPERNERD!"