Last active
February 4, 2019 09:56
-
-
Save toyeiei/4f244d23e7767a6fea8a31ba7ac5602e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# intro to stringr | |
install.packages("stringr") | |
library(stringr) | |
# check state.name | |
print(state.name) | |
# most used function in stringr | |
str_view(state.name, pattern = "New", match = T) | |
# create an example string | |
text <- "DataRockie is the coolest DS school on the internet, founded in Y2015. | |
It offers free online courses on datarockie.com, go check it!" | |
# basic regular expressions | |
str_view(text, "DataRockie") | |
str_view(text, "2015") | |
str_view(text, "datarockie") | |
# this character | means OR | |
# look for words 'DataRockie' OR 'datarockie' | |
str_view_all(text, "(D|d)ata(R|r)ockie") | |
# look for digits | |
str_view(text, "[0-9]") | |
str_view(text, "[0-9]+") | |
str_view(text, "\\d") | |
str_view(text, "\\d+") | |
# look for English alphabet | |
str_view_all(text, "[a-z]+") | |
str_view_all(text, "[A-Z]+") | |
# look for space | |
str_view_all(text, "\\s") | |
# split text by " " | |
text_split <- str_split(text, pattern = " ")[[1]] | |
text_split | |
# look for words start with 'i' | |
str_view_all(text_split, "^i.+") | |
# look for words end with 's' | |
str_view_all(text_split, ".+s$") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment