leetcode/notebooks/collections/counter.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Counter\n",
    "\n",
    "Keeps track of number of times an item is added."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from collections import Counter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counter({'b': 3, 'a': 2, 'c': 1})\n",
      "Counter({'c': 3, 'b': 2, 'a': 1})\n",
      "Counter({'b': 3, 'a': 2, 'c': 1})\n"
     ]
    }
   ],
   "source": [
    "print(Counter(['a', 'a', 'b', 'b', 'b', 'c']))\n",
    "\n",
    "# Notice that in the following cases of dict and kwargs, a new Counter\n",
    "# is created with the given number and no \"counting\" happens\n",
    "print(Counter({ 'a': 1, 'b': 2, 'c': 3}))\n",
    "print(Counter(a=2, b=3, c=1))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Empty counter can be created and later items added."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counter({'a': 1})\n",
      "Counter({'a': 2})\n",
      "Counter({'b': 4, 'a': 2, 'c': 2})\n"
     ]
    }
   ],
   "source": [
    "empty = Counter()\n",
    "\n",
    "empty.update('a')\n",
    "print(empty)\n",
    "\n",
    "empty.update('a')\n",
    "print(empty)\n",
    "\n",
    "empty.update('bbbbcc')\n",
    "print(empty)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Counts of an item can be retrieved by simply indexing."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of 'b': 4\n"
     ]
    }
   ],
   "source": [
    "print(\"Number of 'b':\", empty['b'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "❗️ Counter returns count of `0` for non-existent keys."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of 'z': 0\n"
     ]
    }
   ],
   "source": [
    "print(\"Number of 'z':\", empty['z'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### ⭐️ `most_common(n)`\n",
    "\n",
    "Returns `n` most common items as a sequence of pairs. If `n` is not provided, returns all in decreasing order."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Top 3 letters in the dictionary:\n",
      "e : 235331\n",
      "i : 201032\n",
      "a : 199554\n"
     ]
    }
   ],
   "source": [
    "c = Counter()\n",
    "\n",
    "with open('/usr/share/dict/words', 'r') as f:\n",
    "    for line in f:\n",
    "        c.update(line.rstrip().lower())\n",
    "\n",
    "print(\"Top 3 letters in the dictionary:\")\n",
    "for item, count in c.most_common(3):\n",
    "    print(f\"{item} : {count}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Set and arithmetic operations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "c1 + c2 = Counter({'a': 5, 'b': 5, 'e': 5, 'c': 3, 'd': 1})\n",
      "c1 - c2 = Counter({'e': 5, 'a': 3})\n",
      "c1 | c2 = Counter({'e': 5, 'a': 4, 'b': 3, 'c': 2, 'd': 1})\n",
      "c1 & c2 = Counter({'b': 2, 'a': 1, 'c': 1})\n"
     ]
    }
   ],
   "source": [
    "c1 = Counter(a=4, b=2, c=1, d=0, e=5)\n",
    "c2 = Counter(a=1, b=3, c=2, d=1)\n",
    "\n",
    "print(\"c1 + c2 =\", c1 + c2)\n",
    "print(\"c1 - c2 =\", c1 - c2) # NOTE: 0 counts and -ve counts are removed\n",
    "\n",
    "print(\"c1 | c2 =\", c1 | c2) # NOTE: Largest counts are preserved\n",
    "print(\"c1 & c2 =\", c1 & c2) # NOTE: Smallest counts are preserved"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Some extra APIs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "a : 2\n",
      "a : 2\n",
      "b : 4\n",
      "b : 4\n",
      "b : 4\n",
      "b : 4\n",
      "c : 3\n",
      "c : 3\n",
      "c : 3\n",
      "d : 1\n"
     ]
    }
   ],
   "source": [
    "c = Counter('aabbbbcccd')\n",
    "\n",
    "# Get an iterator to loop through\n",
    "# NOTE: Does not return count == 0 items\n",
    "for el in c.elements():\n",
    "    print(f\"{el} : {c[el]}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total items = 5\n"
     ]
    }
   ],
   "source": [
    "print(\"Total items =\", Counter('aaabb').total())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "9e0fd7424d8281b91a098a189d6ae37333be9d5a00ec75c9d3dec88c73652714"
  },
  "kernelspec": {
   "display_name": "Python 3.10.1 ('leetcode-yPz04C5d')",
   "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": "3.10.1"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}