# stringr and forcats exercises

library(tidyverse)
library(stringr)
library(forcats)

#1 Create a string with an embedded double quote

#2 Find the length of that string using str_length()

#3 Create the string "this is the time" and the string "to do good things"

#4 Combine them using a space as a separator

#5 investigate the letters data, create a new string vector that prefixes each letter element with "Letter :"

#6 Create a list that states the letter that follows it - for example "b follows a", "c follows b" etc.

#7 collapse letters to string "abcdefghijklmnopqrstuvwxyz"

#8 use string_replace_na on a character vector containing NAs

#9 use str_sub to extract the third through sixth characters from a character vector having at least 7 strings

#10 use str_to_upper, str_to_lower and str_to_title on any string

#11 Investigate str_wrap() and str_trim(). Describe what they do and apply them to a string where these functions have an effect on the string

courses <- c("CS2500", "DS2000", "DS4100")
#12 match the string DS4100 in the courses vector

#13 match all DS courses

#14 match the course numbers


complex <- c("\\.TO NOT BE", "TO BE\\.", "2 B", NA)
writeLines(complex)
#15 match all letters in complex

#16 match all numbers in complex

#17 use anchoring to match the styring "2 B"

#18 write 1 regex that matches "TO NOT BE" and "TO BE"

abc <- c("abc", "a.c", "a*c", "a c", "a*c")

#19 use str_detect to find "a*c" in abc. Use sum to determine how many copies of "a*c" is in the vector, use mean to determine the proportion of strings are "a*c" in abc

#20 use the stringr::words vector to find all words that contain no consonants.

words_df <- tibble(
  word = words,
  i = seq_along(word)
)

#21 use filter and str_detect to find all words in words_df ending in x

all_a <- c("a", "aa", "aaa", "aaaa")

#22 use str_count to count the number of a's in all_a

#23 use str_extract and str_extract_all to extract the letters from abc vector

#24 replace all of the a's in abc with b's

#25 investigate the boundary function and use it with str_split() on your choice of data


#forcats
#26 create a factor for the likert scale values: strongly agree, aggree, neither agree or disagree, disagree, strongly disagree