Data Structure - Set, Hash.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Set, no duplication"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Used for Integer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{1, 2, 3}\n",
      "{1, 3, 4, 5}\n"
     ]
    }
   ],
   "source": [
    "ls = [1,1,2,2,2,3]\n",
    "a = set(ls)\n",
    "print(a)\n",
    "\n",
    "b = {1, 3, 4, 5, 5, 1}\n",
    "print(b)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "True\n"
     ]
    }
   ],
   "source": [
    "print(1 in a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{2, 3}\n"
     ]
    }
   ],
   "source": [
    "a.remove(1)\n",
    "print(a)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Used for Character "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'d', 'e', 'f', 's'}"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a = {x for x in \"aabbcdsef\" if x not in 'abc'}\n",
    "a"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Used for tuple"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{(1, 2), (1, 3)}"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ls = [(1,2), (1,2), (1,3)]\n",
    "a = set(ls)\n",
    "a\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{(1, 2)}"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ls = (1,2)\n",
    "a = set([ls]) ## only as a list \n",
    "a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "Dictionary, just like hashmap, key : value  \n",
    "tuple can be used as key"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Check the value "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'A'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grade_book = {\"Peter\" : 'A', \"Lu\" : \"B\", \"James\": \"C\"}\n",
    "grade_book[\"Peter\"]\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Add a record "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Peter': 'A', 'Lu': 'B', 'James': 'C', 'Jay': 'B'}"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grade_book[\"Jay\"] = 'B'\n",
    "grade_book"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Delete "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Lu': 'A'}"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grade_book = {\"peter\" : \"A\", \"Lu\" : \"A\" }\n",
    "del grade_book[\"peter\"]\n",
    "grade_book"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Check the key "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"Peter\" in grade_book"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"Ana\" in grade_book"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Iterate "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Peter', 'A'), ('Lu', 'B'), ('James', 'C'), ('Jay', 'B')]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[(k,v) for k, v in grade_book.items()]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Get or default, the key might not in dictionary "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'a': 1, 'd': 2, 'f': 1, 'i': 2, 's': 2, 'u': 2}"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s = \"auiufisdsd\"\n",
    "d = {}\n",
    "for i in s:\n",
    "    d[i] = d.get(i,0) + 1 # if d[i] doesn't exist, then return 0\n",
    "    #d[i] = d[i] +1\n",
    "d"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'list'> u ['a', 'u', 'i', 'f', 's', 'd']\n"
     ]
    }
   ],
   "source": [
    "keys = [i for i in d.keys()]\n",
    "#print (keys)\n",
    "print (type(keys),keys[1],keys)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1, 2, 2, 1, 2, 2]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "values = [i for i in d.values()]\n",
    "values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'str'> i dict_keys(['a', 'u', 'i', 'f', 's', 'd'])\n"
     ]
    }
   ],
   "source": [
    "str_key = str(d.keys())\n",
    "\n",
    "print (type(str_key),str_key[1], str_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "i 2\n"
     ]
    }
   ],
   "source": [
    "print (str(d.keys())[1], d[str(d.keys())[1]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "a 1\n",
      "u 2\n",
      "i 2\n",
      "f 1\n",
      "s 2\n",
      "d 2\n"
     ]
    }
   ],
   "source": [
    "for (a, b) in zip(d.keys(), d.values()):\n",
    "    print (a,b)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "a 1\n",
      "u 2\n",
      "i 2\n",
      "f 1\n",
      "s 2\n",
      "d 2\n"
     ]
    }
   ],
   "source": [
    "for (a, b) in d.items():\n",
    "    print (a,b)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "use Counter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['p', 'e', 't', 'r']\n",
      "Counter({'e': 3, 'p': 2, 't': 1, 'r': 1})\n",
      "<class 'collections.Counter'>\n"
     ]
    }
   ],
   "source": [
    "import collections\n",
    "s = \"pepeter\"\n",
    "c = collections.Counter(s)\n",
    "ls = [i for i in c.keys()]\n",
    "print (ls)\n",
    "print (c)\n",
    "print (type(c))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "defaultdict, good for construct graph "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_items([('yellow', [1, 3]), ('blue', [2, 4]), ('red', [1])])"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import collections\n",
    "s = [('yellow', 1), ('blue', 2), ('yellow', 3), ('blue', 4), ('red', 1)]\n",
    "d = collections.defaultdict(list)\n",
    "for k, v in s:\n",
    "    d[k].append(v)\n",
    "d.items()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_items([('red', {1, 3}), ('blue', {2, 4})])"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import collections\n",
    "s = [('red', 1), ('blue', 2), ('red', 3), ('blue', 4), ('red', 1), ('blue', 4)]\n",
    "d = collections.defaultdict(set)\n",
    "for k, v in s:\n",
    "    d[k].add(v)\n",
    "d.items()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counter({'d': 3, 'u': 2, 'i': 2, 's': 2, 'a': 1, 'f': 1})\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'d'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import collections\n",
    "s = \"auiufisdsdd\"\n",
    "d = collections.Counter(s)\n",
    "print(d)\n",
    "max(d, key = d.get)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "ListNode, heap => get a tuple(node.val, index, node) To make sure this runs in Python3, simply add a tie-breaker in your heap elements (tuples)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1\n",
      "2\n",
      "3\n"
     ]
    }
   ],
   "source": [
    "class ListNode:\n",
    "    def __init__(self, x):\n",
    "        self.val = x\n",
    "        self.next = None\n",
    "\n",
    "a = ListNode(1)\n",
    "b = ListNode(2)\n",
    "c = ListNode(3)\n",
    "ls = [a, b, c]\n",
    "\n",
    "import heapq\n",
    "heap = [(n.val, index, n) for index, n in enumerate(ls)]\n",
    "heapq.heapify(heap)\n",
    "while heap:\n",
    "    print(heapq.heappop(heap)[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "odict_keys(['0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z'])"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import string\n",
    "from collections import OrderedDict\n",
    "base = OrderedDict((k, i) for i, k in enumerate(string.digits + string.ascii_letters))\n",
    "base.keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}