Demonstration of grouping by repeating letters in Python

repeating_letters.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# `itertools` to the Rescue\n",
    "\n",
    "https://docs.python.org/3/library/itertools.html#itertools.groupby\n",
    "\n",
    "Given a list of strings comprising capital letters, find (for each string) the longest consecutive substring containing a single repeated letter, and print out the letter along with the number of times it repeats itself in that substring. If there is a tie, choose the letter that comes earliest in the alphabet."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from itertools import groupby"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "strings = \"\"\"\n",
    "HELLOTHEREWORLD\n",
    "NOWISTHETIMEFORALLGOOD\n",
    "MEETBEETBOOBOO\n",
    "ZZOEUCUTAAEUCUTTTCUU\n",
    "\"\"\".split()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['HELLOTHEREWORLD',\n",
       " 'NOWISTHETIMEFORALLGOOD',\n",
       " 'MEETBEETBOOBOO',\n",
       " 'ZZOEUCUTAAEUCUTTTCUU']"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "strings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "H 1\n",
      "E 1\n",
      "L 2\n",
      "O 1\n",
      "T 1\n",
      "H 1\n",
      "E 1\n",
      "R 1\n",
      "E 1\n",
      "W 1\n",
      "O 1\n",
      "R 1\n",
      "L 1\n",
      "D 1\n",
      "\n",
      "N 1\n",
      "O 1\n",
      "W 1\n",
      "I 1\n",
      "S 1\n",
      "T 1\n",
      "H 1\n",
      "E 1\n",
      "T 1\n",
      "I 1\n",
      "M 1\n",
      "E 1\n",
      "F 1\n",
      "O 1\n",
      "R 1\n",
      "A 1\n",
      "L 2\n",
      "G 1\n",
      "O 2\n",
      "D 1\n",
      "\n",
      "M 1\n",
      "E 2\n",
      "T 1\n",
      "B 1\n",
      "E 2\n",
      "T 1\n",
      "B 1\n",
      "O 2\n",
      "B 1\n",
      "O 2\n",
      "\n",
      "Z 2\n",
      "O 1\n",
      "E 1\n",
      "U 1\n",
      "C 1\n",
      "U 1\n",
      "T 1\n",
      "A 2\n",
      "E 1\n",
      "U 1\n",
      "C 1\n",
      "U 1\n",
      "T 3\n",
      "C 1\n",
      "U 2\n"
     ]
    }
   ],
   "source": [
    "for s in strings:\n",
    "    print()\n",
    "    for letter, iterator in groupby(s):\n",
    "        print(letter, sum(1 for _ in iterator))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "[(1, 'D'), (1, 'E'), (1, 'E'), (1, 'E'), (1, 'H'), (1, 'H'), (1, 'L'), (1, 'O'), (1, 'O'), (1, 'R'), (1, 'R'), (1, 'T'), (1, 'W'), (2, 'L')]\n",
      "\n",
      "[(1, 'A'), (1, 'D'), (1, 'E'), (1, 'E'), (1, 'F'), (1, 'G'), (1, 'H'), (1, 'I'), (1, 'I'), (1, 'M'), (1, 'N'), (1, 'O'), (1, 'O'), (1, 'R'), (1, 'S'), (1, 'T'), (1, 'T'), (1, 'W'), (2, 'L'), (2, 'O')]\n",
      "\n",
      "[(1, 'B'), (1, 'B'), (1, 'B'), (1, 'M'), (1, 'T'), (1, 'T'), (2, 'E'), (2, 'E'), (2, 'O'), (2, 'O')]\n",
      "\n",
      "[(1, 'C'), (1, 'C'), (1, 'C'), (1, 'E'), (1, 'E'), (1, 'O'), (1, 'T'), (1, 'U'), (1, 'U'), (1, 'U'), (1, 'U'), (2, 'A'), (2, 'U'), (2, 'Z'), (3, 'T')]\n"
     ]
    }
   ],
   "source": [
    "for s in strings:\n",
    "    print()\n",
    "    print(\n",
    "        sorted(\n",
    "            [\n",
    "                (sum(1 for _ in iterator), letter)\n",
    "                for letter, iterator in groupby(s)\n",
    "            ]\n",
    "        )\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def sort_key(t):\n",
    "    count, letter = t\n",
    "    return -count, letter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "[(2, 'L'), (1, 'D'), (1, 'E'), (1, 'E'), (1, 'E'), (1, 'H'), (1, 'H'), (1, 'L'), (1, 'O'), (1, 'O'), (1, 'R'), (1, 'R'), (1, 'T'), (1, 'W')]\n",
      "\n",
      "[(2, 'L'), (2, 'O'), (1, 'A'), (1, 'D'), (1, 'E'), (1, 'E'), (1, 'F'), (1, 'G'), (1, 'H'), (1, 'I'), (1, 'I'), (1, 'M'), (1, 'N'), (1, 'O'), (1, 'O'), (1, 'R'), (1, 'S'), (1, 'T'), (1, 'T'), (1, 'W')]\n",
      "\n",
      "[(2, 'E'), (2, 'E'), (2, 'O'), (2, 'O'), (1, 'B'), (1, 'B'), (1, 'B'), (1, 'M'), (1, 'T'), (1, 'T')]\n",
      "\n",
      "[(3, 'T'), (2, 'A'), (2, 'U'), (2, 'Z'), (1, 'C'), (1, 'C'), (1, 'C'), (1, 'E'), (1, 'E'), (1, 'O'), (1, 'T'), (1, 'U'), (1, 'U'), (1, 'U'), (1, 'U')]\n"
     ]
    }
   ],
   "source": [
    "for s in strings:\n",
    "    print()\n",
    "    print(\n",
    "        sorted(\n",
    "            [\n",
    "                (sum(1 for _ in iterator), letter)\n",
    "                for letter, iterator in groupby(s)\n",
    "            ],\n",
    "            key=sort_key,\n",
    "        )\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2 L\n",
      "2 L\n",
      "2 E\n",
      "3 T\n"
     ]
    }
   ],
   "source": [
    "for s in strings:\n",
    "    print(\n",
    "        *sorted(\n",
    "            [\n",
    "                (sum(1 for _ in iterator), letter)\n",
    "                for letter, iterator in groupby(s)\n",
    "            ],\n",
    "            key=sort_key,\n",
    "        )[0]\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2 L HELLOTHEREWORLD\n",
      "2 L NOWISTHETIMEFORALLGOOD\n",
      "2 E MEETBEETBOOBOO\n",
      "3 T ZZOEUCUTAAEUCUTTTCUU\n"
     ]
    }
   ],
   "source": [
    "for s in strings:\n",
    "    print(\n",
    "        *sorted(\n",
    "            [\n",
    "                (sum(1 for _ in iterator), letter)\n",
    "                for letter, iterator in groupby(s)\n",
    "            ],\n",
    "            key=sort_key,\n",
    "        )[0],\n",
    "        s\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}