Lecture14.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this notebook, we will cover:\n",
    "\n",
    "* [String basics and length](#String-basics-and-length)\n",
    "* [Combining strings](#Combining-strings)\n",
    "* [Subsetting strings](#Subsetting-strings)\n",
    "* [Locales](#Locales)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Loading tidyverse: ggplot2\n",
      "Loading tidyverse: tibble\n",
      "Loading tidyverse: tidyr\n",
      "Loading tidyverse: readr\n",
      "Loading tidyverse: purrr\n",
      "Loading tidyverse: dplyr\n",
      "Conflicts with tidy packages ---------------------------------------------------\n",
      "filter(): dplyr, stats\n",
      "lag():    dplyr, stats\n"
     ]
    }
   ],
   "source": [
    "library(tidyverse)\n",
    "library(stringr)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# String basics and length"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'STATS 306'"
      ],
      "text/latex": [
       "'STATS 306'"
      ],
      "text/markdown": [
       "'STATS 306'"
      ],
      "text/plain": [
       "[1] \"STATS 306\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "(mystring <- \"STATS 306\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'STATS 306'"
      ],
      "text/latex": [
       "'STATS 306'"
      ],
      "text/markdown": [
       "'STATS 306'"
      ],
      "text/plain": [
       "[1] \"STATS 306\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "(mystring2 <- 'STATS 306')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can create strings using double quotes or single quotes -- there's no difference. However, for consisteny, you might want to stick to double quotes except in cases when your strong itself has double quotes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'\"MLE\" stands for \"Maximum Likelihood Estimate\"'"
      ],
      "text/latex": [
       "'\"MLE\" stands for \"Maximum Likelihood Estimate\"'"
      ],
      "text/markdown": [
       "'\"MLE\" stands for \"Maximum Likelihood Estimate\"'"
      ],
      "text/plain": [
       "[1] \"\\\"MLE\\\" stands for \\\"Maximum Likelihood Estimate\\\"\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "(mystring3 <- '\"MLE\" stands for \"Maximum Likelihood Estimate\"')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can create a string with double quotes in it while using double quotes to create it but you will have to use a lot of *escape* all the double quotes!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'\"MLE\" stands for \"Maximum Likelihood Estimate\"'"
      ],
      "text/latex": [
       "'\"MLE\" stands for \"Maximum Likelihood Estimate\"'"
      ],
      "text/markdown": [
       "'\"MLE\" stands for \"Maximum Likelihood Estimate\"'"
      ],
      "text/plain": [
       "[1] \"\\\"MLE\\\" stands for \\\"Maximum Likelihood Estimate\\\"\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "(mystring3 <- \"\\\"MLE\\\" stands for \\\"Maximum Likelihood Estimate\\\"\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is also means that if you actually want a backslash in your string, you need to escape it as well."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'\\ is the backslash character'"
      ],
      "text/latex": [
       "'\\textbackslash{} is the backslash character'"
      ],
      "text/markdown": [
       "'\\ is the backslash character'"
      ],
      "text/plain": [
       "[1] \"\\\\ is the backslash character\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "(mystring4 <- \"\\\\ is the backslash character\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>'\"'</li>\n",
       "\t<li>'\"'</li>\n",
       "\t<li>'\\''</li>\n",
       "\t<li>'\\''</li>\n",
       "\t<li>'\\'</li>\n",
       "\t<li>'\\/'</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item '\"'\n",
       "\\item '\"'\n",
       "\\item '\\textbackslash{}''\n",
       "\\item '\\textbackslash{}''\n",
       "\\item '\\textbackslash{}'\n",
       "\\item '\\textbackslash{}/'\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. '\"'\n",
       "2. '\"'\n",
       "3. '\\''\n",
       "4. '\\''\n",
       "5. '\\'\n",
       "6. '\\/'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       "[1] \"\\\"\"  \"\\\"\"  \"'\"   \"'\"   \"\\\\\"  \"\\\\/\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "(mystrings <- c(\"\\\"\", '\"', '\\'', \"'\", \"\\\\\", \"\\\\/\")) # note the use of c() to create a character vector"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The printed representation of strings shows the escapes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1] \"\\\"\"  \"\\\"\"  \"'\"   \"'\"   \"\\\\\"  \"\\\\/\"\n"
     ]
    }
   ],
   "source": [
    "print(mystrings)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Use `writeLines()` to see the raw contents of the string. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\"\n",
      "\"\n",
      "'\n",
      "'\n",
      "\\\n",
      "\\/\n"
     ]
    }
   ],
   "source": [
    "writeLines(mystrings)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It is good to know of a few about a few more escape sequences."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "First line\n",
      "Second line\n"
     ]
    }
   ],
   "source": [
    "writeLines(\"First line\\nSecond line\") # newline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Text\n",
      "\tIndented Text\n",
      "Text\n"
     ]
    }
   ],
   "source": [
    "writeLines(\"Text\\n\\tIndented Text\\nText\") # newlines and tab"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can also print characters if you know their unicode using `\\u`. For example, the copyright character has unicode `00A9`. Wikipedia has [a complete list](https://en.wikipedia.org/wiki/List_of_Unicode_characters)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "©\n"
     ]
    }
   ],
   "source": [
    "writeLines(\"\\u00A9\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Base R has strong functions but we will avoid them use the ones in the `stringr` package. They all start with `str_`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>1</li>\n",
       "\t<li>9</li>\n",
       "\t<li>6</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item 1\n",
       "\\item 9\n",
       "\\item 6\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. 1\n",
       "2. 9\n",
       "3. 6\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       "[1] 1 9 6"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_length(c(\"a\", \"character\", \"vector\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Combining strings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'Let us concatenate strings!'"
      ],
      "text/latex": [
       "'Let us concatenate strings!'"
      ],
      "text/markdown": [
       "'Let us concatenate strings!'"
      ],
      "text/plain": [
       "[1] \"Let us concatenate strings!\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_c(\"Let us con\", \"catenate strings!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "mystrings <- c(\"one\", \"two\", \"ten\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>'*** one ***'</li>\n",
       "\t<li>'*** two ***'</li>\n",
       "\t<li>'*** ten ***'</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item '*** one ***'\n",
       "\\item '*** two ***'\n",
       "\\item '*** ten ***'\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. '*** one ***'\n",
       "2. '*** two ***'\n",
       "3. '*** ten ***'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       "[1] \"*** one ***\" \"*** two ***\" \"*** ten ***\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_c(\"*** \", mystrings , \" ***\") # each argument is expanded to the length of the longest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "mystrings_na <- c(\"one\", \"two\", NA)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>'*** one ***'</li>\n",
       "\t<li>'*** two ***'</li>\n",
       "\t<li>'NA'</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item '*** one ***'\n",
       "\\item '*** two ***'\n",
       "\\item 'NA'\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. '*** one ***'\n",
       "2. '*** two ***'\n",
       "3. 'NA'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       "[1] \"*** one ***\" \"*** two ***\" NA           "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_c(\"*** \", mystrings_na, \" ***\") # missingness is contagious!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>'*** one ***'</li>\n",
       "\t<li>'*** two ***'</li>\n",
       "\t<li>'*** NA ***'</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item '*** one ***'\n",
       "\\item '*** two ***'\n",
       "\\item '*** NA ***'\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. '*** one ***'\n",
       "2. '*** two ***'\n",
       "3. '*** NA ***'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       "[1] \"*** one ***\" \"*** two ***\" \"*** NA ***\" "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_c(\"*** \", str_replace_na(mystrings_na), \" ***\") # converts missing values to the string \"NA\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'one, two, ten'"
      ],
      "text/latex": [
       "'one, two, ten'"
      ],
      "text/markdown": [
       "'one, two, ten'"
      ],
      "text/plain": [
       "[1] \"one, two, ten\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_c(\"one\", \"two\", \"ten\", sep = \", \") # can provide a separator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>'one'</li>\n",
       "\t<li>'two'</li>\n",
       "\t<li>'ten'</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item 'one'\n",
       "\\item 'two'\n",
       "\\item 'ten'\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. 'one'\n",
       "2. 'two'\n",
       "3. 'ten'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       "[1] \"one\" \"two\" \"ten\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_c(mystrings, sep = \", \") # why does this not combine the strings?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'one, two, ten'"
      ],
      "text/latex": [
       "'one, two, ten'"
      ],
      "text/markdown": [
       "'one, two, ten'"
      ],
      "text/plain": [
       "[1] \"one, two, ten\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_c(mystrings, collapse = \", \") # use collapse if the strings you want to combine are in a vector"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Subsetting strings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>'a'</li>\n",
       "\t<li>'b'</li>\n",
       "\t<li>'c'</li>\n",
       "\t<li>'d'</li>\n",
       "\t<li>'e'</li>\n",
       "\t<li>'f'</li>\n",
       "\t<li>'g'</li>\n",
       "\t<li>'h'</li>\n",
       "\t<li>'i'</li>\n",
       "\t<li>'j'</li>\n",
       "\t<li>'k'</li>\n",
       "\t<li>'l'</li>\n",
       "\t<li>'m'</li>\n",
       "\t<li>'n'</li>\n",
       "\t<li>'o'</li>\n",
       "\t<li>'p'</li>\n",
       "\t<li>'q'</li>\n",
       "\t<li>'r'</li>\n",
       "\t<li>'s'</li>\n",
       "\t<li>'t'</li>\n",
       "\t<li>'u'</li>\n",
       "\t<li>'v'</li>\n",
       "\t<li>'w'</li>\n",
       "\t<li>'x'</li>\n",
       "\t<li>'y'</li>\n",
       "\t<li>'z'</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item 'a'\n",
       "\\item 'b'\n",
       "\\item 'c'\n",
       "\\item 'd'\n",
       "\\item 'e'\n",
       "\\item 'f'\n",
       "\\item 'g'\n",
       "\\item 'h'\n",
       "\\item 'i'\n",
       "\\item 'j'\n",
       "\\item 'k'\n",
       "\\item 'l'\n",
       "\\item 'm'\n",
       "\\item 'n'\n",
       "\\item 'o'\n",
       "\\item 'p'\n",
       "\\item 'q'\n",
       "\\item 'r'\n",
       "\\item 's'\n",
       "\\item 't'\n",
       "\\item 'u'\n",
       "\\item 'v'\n",
       "\\item 'w'\n",
       "\\item 'x'\n",
       "\\item 'y'\n",
       "\\item 'z'\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. 'a'\n",
       "2. 'b'\n",
       "3. 'c'\n",
       "4. 'd'\n",
       "5. 'e'\n",
       "6. 'f'\n",
       "7. 'g'\n",
       "8. 'h'\n",
       "9. 'i'\n",
       "10. 'j'\n",
       "11. 'k'\n",
       "12. 'l'\n",
       "13. 'm'\n",
       "14. 'n'\n",
       "15. 'o'\n",
       "16. 'p'\n",
       "17. 'q'\n",
       "18. 'r'\n",
       "19. 's'\n",
       "20. 't'\n",
       "21. 'u'\n",
       "22. 'v'\n",
       "23. 'w'\n",
       "24. 'x'\n",
       "25. 'y'\n",
       "26. 'z'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       " [1] \"a\" \"b\" \"c\" \"d\" \"e\" \"f\" \"g\" \"h\" \"i\" \"j\" \"k\" \"l\" \"m\" \"n\" \"o\" \"p\" \"q\" \"r\" \"s\"\n",
       "[20] \"t\" \"u\" \"v\" \"w\" \"x\" \"y\" \"z\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "letters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "letters_str = str_c(letters, collapse = \"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'abcdefghij'"
      ],
      "text/latex": [
       "'abcdefghij'"
      ],
      "text/markdown": [
       "'abcdefghij'"
      ],
      "text/plain": [
       "[1] \"abcdefghij\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_sub(letters_str, 1, 10) # the substring from position 1 through 10 (both inclusive)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'qrstuvwxyz'"
      ],
      "text/latex": [
       "'qrstuvwxyz'"
      ],
      "text/markdown": [
       "'qrstuvwxyz'"
      ],
      "text/plain": [
       "[1] \"qrstuvwxyz\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_sub(letters_str, -10, -1) # negative numbers count from the end"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "''"
      ],
      "text/latex": [
       "''"
      ],
      "text/markdown": [
       "''"
      ],
      "text/plain": [
       "[1] \"\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_sub(letters_str, 31, 40) # ranges outside the string will result in an emtpy stroing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'uvwxyz'"
      ],
      "text/latex": [
       "'uvwxyz'"
      ],
      "text/markdown": [
       "'uvwxyz'"
      ],
      "text/plain": [
       "[1] \"uvwxyz\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_sub(letters_str, 21, 30) # works but results in a shorter resulting string"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can change part of a string using the assignment form of `str_sub()`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'ABCDEFGHIJklmnopqrstuvwxyz'"
      ],
      "text/latex": [
       "'ABCDEFGHIJklmnopqrstuvwxyz'"
      ],
      "text/markdown": [
       "'ABCDEFGHIJklmnopqrstuvwxyz'"
      ],
      "text/plain": [
       "[1] \"ABCDEFGHIJklmnopqrstuvwxyz\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_sub(letters_str, 1, 10) <- str_to_upper(str_sub(letters_str, 1, 10))\n",
    "letters_str"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "What do you think `str_to_upper()` does?\n",
    "\n",
    "Have a look at the [stringr documentation](http://stringr.tidyverse.org/reference/index.html) to learn about other useful functions."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Locales"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'This Could Be The Title Of A Book'"
      ],
      "text/latex": [
       "'This Could Be The Title Of A Book'"
      ],
      "text/markdown": [
       "'This Could Be The Title Of A Book'"
      ],
      "text/plain": [
       "[1] \"This Could Be The Title Of A Book\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_to_title(\"this could be the title of a book\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>'A'</li>\n",
       "\t<li>'B'</li>\n",
       "\t<li>'C'</li>\n",
       "\t<li>'D'</li>\n",
       "\t<li>'E'</li>\n",
       "\t<li>'F'</li>\n",
       "\t<li>'G'</li>\n",
       "\t<li>'H'</li>\n",
       "\t<li>'I'</li>\n",
       "\t<li>'J'</li>\n",
       "\t<li>'K'</li>\n",
       "\t<li>'L'</li>\n",
       "\t<li>'M'</li>\n",
       "\t<li>'N'</li>\n",
       "\t<li>'O'</li>\n",
       "\t<li>'P'</li>\n",
       "\t<li>'Q'</li>\n",
       "\t<li>'R'</li>\n",
       "\t<li>'S'</li>\n",
       "\t<li>'T'</li>\n",
       "\t<li>'U'</li>\n",
       "\t<li>'V'</li>\n",
       "\t<li>'W'</li>\n",
       "\t<li>'X'</li>\n",
       "\t<li>'Y'</li>\n",
       "\t<li>'Z'</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item 'A'\n",
       "\\item 'B'\n",
       "\\item 'C'\n",
       "\\item 'D'\n",
       "\\item 'E'\n",
       "\\item 'F'\n",
       "\\item 'G'\n",
       "\\item 'H'\n",
       "\\item 'I'\n",
       "\\item 'J'\n",
       "\\item 'K'\n",
       "\\item 'L'\n",
       "\\item 'M'\n",
       "\\item 'N'\n",
       "\\item 'O'\n",
       "\\item 'P'\n",
       "\\item 'Q'\n",
       "\\item 'R'\n",
       "\\item 'S'\n",
       "\\item 'T'\n",
       "\\item 'U'\n",
       "\\item 'V'\n",
       "\\item 'W'\n",
       "\\item 'X'\n",
       "\\item 'Y'\n",
       "\\item 'Z'\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. 'A'\n",
       "2. 'B'\n",
       "3. 'C'\n",
       "4. 'D'\n",
       "5. 'E'\n",
       "6. 'F'\n",
       "7. 'G'\n",
       "8. 'H'\n",
       "9. 'I'\n",
       "10. 'J'\n",
       "11. 'K'\n",
       "12. 'L'\n",
       "13. 'M'\n",
       "14. 'N'\n",
       "15. 'O'\n",
       "16. 'P'\n",
       "17. 'Q'\n",
       "18. 'R'\n",
       "19. 'S'\n",
       "20. 'T'\n",
       "21. 'U'\n",
       "22. 'V'\n",
       "23. 'W'\n",
       "24. 'X'\n",
       "25. 'Y'\n",
       "26. 'Z'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       " [1] \"A\" \"B\" \"C\" \"D\" \"E\" \"F\" \"G\" \"H\" \"I\" \"J\" \"K\" \"L\" \"M\" \"N\" \"O\" \"P\" \"Q\" \"R\" \"S\"\n",
       "[20] \"T\" \"U\" \"V\" \"W\" \"X\" \"Y\" \"Z\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>'a'</li>\n",
       "\t<li>'b'</li>\n",
       "\t<li>'c'</li>\n",
       "\t<li>'d'</li>\n",
       "\t<li>'e'</li>\n",
       "\t<li>'f'</li>\n",
       "\t<li>'g'</li>\n",
       "\t<li>'h'</li>\n",
       "\t<li>'i'</li>\n",
       "\t<li>'j'</li>\n",
       "\t<li>'k'</li>\n",
       "\t<li>'l'</li>\n",
       "\t<li>'m'</li>\n",
       "\t<li>'n'</li>\n",
       "\t<li>'o'</li>\n",
       "\t<li>'p'</li>\n",
       "\t<li>'q'</li>\n",
       "\t<li>'r'</li>\n",
       "\t<li>'s'</li>\n",
       "\t<li>'t'</li>\n",
       "\t<li>'u'</li>\n",
       "\t<li>'v'</li>\n",
       "\t<li>'w'</li>\n",
       "\t<li>'x'</li>\n",
       "\t<li>'y'</li>\n",
       "\t<li>'z'</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item 'a'\n",
       "\\item 'b'\n",
       "\\item 'c'\n",
       "\\item 'd'\n",
       "\\item 'e'\n",
       "\\item 'f'\n",
       "\\item 'g'\n",
       "\\item 'h'\n",
       "\\item 'i'\n",
       "\\item 'j'\n",
       "\\item 'k'\n",
       "\\item 'l'\n",
       "\\item 'm'\n",
       "\\item 'n'\n",
       "\\item 'o'\n",
       "\\item 'p'\n",
       "\\item 'q'\n",
       "\\item 'r'\n",
       "\\item 's'\n",
       "\\item 't'\n",
       "\\item 'u'\n",
       "\\item 'v'\n",
       "\\item 'w'\n",
       "\\item 'x'\n",
       "\\item 'y'\n",
       "\\item 'z'\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. 'a'\n",
       "2. 'b'\n",
       "3. 'c'\n",
       "4. 'd'\n",
       "5. 'e'\n",
       "6. 'f'\n",
       "7. 'g'\n",
       "8. 'h'\n",
       "9. 'i'\n",
       "10. 'j'\n",
       "11. 'k'\n",
       "12. 'l'\n",
       "13. 'm'\n",
       "14. 'n'\n",
       "15. 'o'\n",
       "16. 'p'\n",
       "17. 'q'\n",
       "18. 'r'\n",
       "19. 's'\n",
       "20. 't'\n",
       "21. 'u'\n",
       "22. 'v'\n",
       "23. 'w'\n",
       "24. 'x'\n",
       "25. 'y'\n",
       "26. 'z'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       " [1] \"a\" \"b\" \"c\" \"d\" \"e\" \"f\" \"g\" \"h\" \"i\" \"j\" \"k\" \"l\" \"m\" \"n\" \"o\" \"p\" \"q\" \"r\" \"s\"\n",
       "[20] \"t\" \"u\" \"v\" \"w\" \"x\" \"y\" \"z\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "LETTERS\n",
    "str_to_lower(LETTERS)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "'ABCDEFGHIJKLMNOPQRSTUVWXYZ'"
      ],
      "text/latex": [
       "'ABCDEFGHIJKLMNOPQRSTUVWXYZ'"
      ],
      "text/markdown": [
       "'ABCDEFGHIJKLMNOPQRSTUVWXYZ'"
      ],
      "text/plain": [
       "[1] \"ABCDEFGHIJKLMNOPQRSTUVWXYZ\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "'abcdefghijklmnopqrstuvwxyz'"
      ],
      "text/latex": [
       "'abcdefghijklmnopqrstuvwxyz'"
      ],
      "text/markdown": [
       "'abcdefghijklmnopqrstuvwxyz'"
      ],
      "text/plain": [
       "[1] \"abcdefghijklmnopqrstuvwxyz\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "(LETTERS_str <- str_c(LETTERS, collapse = \"\"))\n",
    "str_to_lower(LETTERS_str)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "These three functions:\n",
    "\n",
    "* `str_to_lower()`\n",
    "* `str_to_upper()`\n",
    "* `str_to_title()`\n",
    "\n",
    "are <a href=\"https://en.wikipedia.org/wiki/Locale_(computer_software)\">**locale**</a> sensitive. That is, their behavior is sensitive to which language the user's computer system is using. A two letter code (e.g., `en` for English, `fr` for French, `es` for Spanish) can be passed to these functions as the `locale` argument to specify the locale (by default, the locale of the operating system is used).\n",
    "\n",
    "Another function affected by locale is `str_sort()`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>'a'</li>\n",
       "\t<li>'b'</li>\n",
       "\t<li>'c'</li>\n",
       "\t<li>'d'</li>\n",
       "\t<li>'e'</li>\n",
       "\t<li>'f'</li>\n",
       "\t<li>'g'</li>\n",
       "\t<li>'h'</li>\n",
       "\t<li>'i'</li>\n",
       "\t<li>'j'</li>\n",
       "\t<li>'k'</li>\n",
       "\t<li>'l'</li>\n",
       "\t<li>'m'</li>\n",
       "\t<li>'n'</li>\n",
       "\t<li>'o'</li>\n",
       "\t<li>'p'</li>\n",
       "\t<li>'q'</li>\n",
       "\t<li>'r'</li>\n",
       "\t<li>'s'</li>\n",
       "\t<li>'t'</li>\n",
       "\t<li>'u'</li>\n",
       "\t<li>'v'</li>\n",
       "\t<li>'w'</li>\n",
       "\t<li>'x'</li>\n",
       "\t<li>'y'</li>\n",
       "\t<li>'z'</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item 'a'\n",
       "\\item 'b'\n",
       "\\item 'c'\n",
       "\\item 'd'\n",
       "\\item 'e'\n",
       "\\item 'f'\n",
       "\\item 'g'\n",
       "\\item 'h'\n",
       "\\item 'i'\n",
       "\\item 'j'\n",
       "\\item 'k'\n",
       "\\item 'l'\n",
       "\\item 'm'\n",
       "\\item 'n'\n",
       "\\item 'o'\n",
       "\\item 'p'\n",
       "\\item 'q'\n",
       "\\item 'r'\n",
       "\\item 's'\n",
       "\\item 't'\n",
       "\\item 'u'\n",
       "\\item 'v'\n",
       "\\item 'w'\n",
       "\\item 'x'\n",
       "\\item 'y'\n",
       "\\item 'z'\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. 'a'\n",
       "2. 'b'\n",
       "3. 'c'\n",
       "4. 'd'\n",
       "5. 'e'\n",
       "6. 'f'\n",
       "7. 'g'\n",
       "8. 'h'\n",
       "9. 'i'\n",
       "10. 'j'\n",
       "11. 'k'\n",
       "12. 'l'\n",
       "13. 'm'\n",
       "14. 'n'\n",
       "15. 'o'\n",
       "16. 'p'\n",
       "17. 'q'\n",
       "18. 'r'\n",
       "19. 's'\n",
       "20. 't'\n",
       "21. 'u'\n",
       "22. 'v'\n",
       "23. 'w'\n",
       "24. 'x'\n",
       "25. 'y'\n",
       "26. 'z'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       " [1] \"a\" \"b\" \"c\" \"d\" \"e\" \"f\" \"g\" \"h\" \"i\" \"j\" \"k\" \"l\" \"m\" \"n\" \"o\" \"p\" \"q\" \"r\" \"s\"\n",
       "[20] \"t\" \"u\" \"v\" \"w\" \"x\" \"y\" \"z\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_sort(letters, locale = \"en\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<ol class=list-inline>\n",
       "\t<li>'a'</li>\n",
       "\t<li>'e'</li>\n",
       "\t<li>'i'</li>\n",
       "\t<li>'o'</li>\n",
       "\t<li>'u'</li>\n",
       "\t<li>'b'</li>\n",
       "\t<li>'c'</li>\n",
       "\t<li>'d'</li>\n",
       "\t<li>'f'</li>\n",
       "\t<li>'g'</li>\n",
       "\t<li>'h'</li>\n",
       "\t<li>'j'</li>\n",
       "\t<li>'k'</li>\n",
       "\t<li>'l'</li>\n",
       "\t<li>'m'</li>\n",
       "\t<li>'n'</li>\n",
       "\t<li>'p'</li>\n",
       "\t<li>'q'</li>\n",
       "\t<li>'r'</li>\n",
       "\t<li>'s'</li>\n",
       "\t<li>'t'</li>\n",
       "\t<li>'v'</li>\n",
       "\t<li>'w'</li>\n",
       "\t<li>'x'</li>\n",
       "\t<li>'y'</li>\n",
       "\t<li>'z'</li>\n",
       "</ol>\n"
      ],
      "text/latex": [
       "\\begin{enumerate*}\n",
       "\\item 'a'\n",
       "\\item 'e'\n",
       "\\item 'i'\n",
       "\\item 'o'\n",
       "\\item 'u'\n",
       "\\item 'b'\n",
       "\\item 'c'\n",
       "\\item 'd'\n",
       "\\item 'f'\n",
       "\\item 'g'\n",
       "\\item 'h'\n",
       "\\item 'j'\n",
       "\\item 'k'\n",
       "\\item 'l'\n",
       "\\item 'm'\n",
       "\\item 'n'\n",
       "\\item 'p'\n",
       "\\item 'q'\n",
       "\\item 'r'\n",
       "\\item 's'\n",
       "\\item 't'\n",
       "\\item 'v'\n",
       "\\item 'w'\n",
       "\\item 'x'\n",
       "\\item 'y'\n",
       "\\item 'z'\n",
       "\\end{enumerate*}\n"
      ],
      "text/markdown": [
       "1. 'a'\n",
       "2. 'e'\n",
       "3. 'i'\n",
       "4. 'o'\n",
       "5. 'u'\n",
       "6. 'b'\n",
       "7. 'c'\n",
       "8. 'd'\n",
       "9. 'f'\n",
       "10. 'g'\n",
       "11. 'h'\n",
       "12. 'j'\n",
       "13. 'k'\n",
       "14. 'l'\n",
       "15. 'm'\n",
       "16. 'n'\n",
       "17. 'p'\n",
       "18. 'q'\n",
       "19. 'r'\n",
       "20. 's'\n",
       "21. 't'\n",
       "22. 'v'\n",
       "23. 'w'\n",
       "24. 'x'\n",
       "25. 'y'\n",
       "26. 'z'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       " [1] \"a\" \"e\" \"i\" \"o\" \"u\" \"b\" \"c\" \"d\" \"f\" \"g\" \"h\" \"j\" \"k\" \"l\" \"m\" \"n\" \"p\" \"q\" \"r\"\n",
       "[20] \"s\" \"t\" \"v\" \"w\" \"x\" \"y\" \"z\""
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "str_sort(letters, locale = \"haw\") # vowels come before consonants in the Hawaiian alphabet"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "R",
   "language": "R",
   "name": "ir"
  },
  "language_info": {
   "codemirror_mode": "r",
   "file_extension": ".r",
   "mimetype": "text/x-r-source",
   "name": "R",
   "pygments_lexer": "r",
   "version": "3.3.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}