Data 607 Week2

Our final answer is presented first, followed by the code to accomplish it.

##      First_Name Last_Name Second_Name_Boolean Title_Boolean Title
## 1           Moe   Szyslak                  No            No      
## 2 C. Montgomery     Burns                 Yes            No      
## 3   Rev Timothy   Lovejoy                  No           Yes   Rev
## 4           Ned  Flanders                  No            No      
## 5         Homer   Simpson                  No            No      
## 6     Dr Julius   Hibbert                  No           Yes    Dr

library(stringr)
raw.data <-"555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5553642Dr. Julius Hibbert"
new.data<-data.frame("First_Name" = integer(15),"Last_Name" = integer(15),"Second_Name_Boolean" = integer(15),"Title_Boolean" = integer(15),"Title" = integer(15))
#Strip Names and initials in order.
split.string<-raw.data
next.split<-split.string
for (i in 1:15) {
extracter<-as.character(unlist(str_extract(next.split, "[A-Z][.]|[A-Z]{1}[[:alpha:]]{1,9}\\,?")))
new.data[[i,1]]<-extracter
split.string<-unlist(str_split_fixed(next.split, "[A-Z][.]|[A-Z]{1}[[:alpha:]]{1,9}\\,?",2))
next.split<-split.string[[2]]
               }
#Append all initial initials to full middles names.
for(i in 1:15){
  if (!is.na(unlist(str_extract(new.data[[i,1]], "[.]")))) {
 new.data[[i,1]]<-paste(new.data[[i,1]],new.data[[i+1,1]], sep=" ")
 new.data[[i,3]]<-"Yes"
      for(j in i:13)                                                 {
 new.data[[j+1,1]]<-new.data[[j+2,1]]       
                                                                     }
 new.data[[15,1]]<-NA
                                                          } else{ new.data[[i,3]]<-"No"} 
             }
#Move titles to title place
for(i in 1:12){
  if (unlist(str_detect(new.data[[i,1]],"Dr|Rev"))=="TRUE") {
            new.data[[i,5]]<-new.data[[i,1]]
 new.data[[i,1]]<-paste(new.data[[i,1]],new.data[[i+1,1]], sep=" ")
      for(j in i:13)                                                 {
 new.data[[j+1,1]]<-new.data[[j+2,1]]       
                                                                     }
 new.data[[15,1]]<-NA
  new.data[[i,4]]<-"Yes"
                                                          } else{ new.data[[i,4]]<-"No"} 
}
#Switch any name that is last name first and put names in first and last column
for (i in seq(1,11, by=2)){
if (unlist(str_detect(new.data[[i,1]],","))=="TRUE") {
new.data[[i,1]]<-unlist(str_extract(new.data[[i,1]], "[:alpha:]{1,15}"))
    new.data[[i,2]]<-new.data[[i,1]]
    new.data[[i,1]]<-new.data[[i+1,1]]
    new.data[[i,3]]<-new.data[[i+1,3]]
    new.data[[i,4]]<-new.data[[i+1,4]]
    new.data[[i,5]]<-new.data[[i+1,5]]
                                                        
                                                     } else           {
   new.data[[i,2]]<-new.data[[i+1,1]]
                                                                      }
               }
final.answer<-data.frame("First_Name" = integer(6),"Last_Name" = integer(6),"Second_Name_Boolean" = integer(6),"Title_Boolean" = integer(6),"Title" = integer(6))
for (i in seq(1,11, by=2)){
  for(j in 1:5)                {
       new.row<-ceiling(i/2)
       final.answer[[new.row,j]]<-new.data[[i,j]]
                               }
                          }
final.answer

The first code is to find numbers followed by dollar signs.

example1<-"990$ gog akd kkd2$5$  %%%5$"
extraction1<-unlist(str_extract_all(example1, "[0-9]+\\$"))
extraction1

## [1] "990$" "2$"   "5$"   "5$"

The second code finds words that are all lower case and between 1 and 4 letters.

example2<-"I am for.. each panda Now."
extraction2<-unlist(str_extract_all(example2, "\\b[a-z]{1,4}\\b"))
extraction2

## [1] "am"   "for"  "each"

The third code is to find text files and will find anything ending in .txt.

example3<-"I am.txt$ for.. each panda Now.txt"
extraction3<-unlist(str_extract_all(example3, ".*?\\.txt$"))
extraction3

## [1] "I am.txt$ for.. each panda Now.txt"

example4<-".txt"
extraction4<-unlist(str_extract_all(example4, ".*?\\.txt$"))
extraction4

## [1] ".txt"

The fourth code is to find dates in mm/dd/yyyy.

example5<-"05/26/2004 3/17/1980 07/16/2000"
extraction5<-unlist(str_extract_all(example5, "\\d{2}/\\d{2}/\\d{4}"))
extraction5

## [1] "05/26/2004" "07/16/2000"

The last code finds html codes, like the color code around this statement.

example6<-"<fred>aa aa</fred> ate </fred"
extraction6<-unlist(str_extract_all(example6, "<(.+?)>.+?</\\1>"))
extraction6

## [1] "<fred>aa aa</fred>"