{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Словари"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "неупорядоченная коллекция\n",
    "\n",
    "ассоциативный массив или хеш\n",
    "\n",
    "неупорядоченное множество пар ключ: значение с требованием уникальности ключей\n",
    "\n",
    "{} - создание пустого словаря\n",
    "\n",
    "\n",
    "Основные особенности словарей:\n",
    "\n",
    "1.\tДоступ осуществляется по ключу, а не по индексу. \n",
    "2.\tЗначения хранятся в неотсортированном порядке.\n",
    "3.\tСловарь может хранить вложенные словари, в качестве значений объекты любого типа. Ключ в словаре может быть строкой, целым или вещественным числом либо кортежем, состоящим из указанных типов. Ключ не допускает изменений.\n",
    "4.\tСловари реализованы как хеш-таблицы с быстрым доступом.\n",
    "5.\tСловари как и списки хранят ссылки на объекты, а не сами объекты.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'Ivan': 23, 'Vasya': 19, 'Olya': 18}\n",
      "23\n",
      "{'Vasya': 19, 'Olya': 18}\n",
      "dict_keys(['Vasya', 'Olya'])\n",
      "True\n",
      "False\n"
     ]
    }
   ],
   "source": [
    "dic = {'Ivan' : 23, 'Vasya' : 18}\n",
    "dic['Vasya'] = 19\n",
    "dic['Olya'] = 18\n",
    "print(dic)\n",
    "print(dic['Ivan'])\n",
    "del dic['Ivan']\n",
    "print(dic)\n",
    "print(dic.keys())\n",
    "print('Olya' in dic)\n",
    "print(18 in dic)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Создание словаря"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'name': 'Ivan', 'age': 25}"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "D = {'name': 'Ivan', 'age': 25}\n",
    "D"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'name': 'Egor', 'age': 15}"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "D = {}\n",
    "D['name'] = 'Egor'\n",
    "D['age'] = 15\n",
    "D"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'id': 1999, 'name': 'Egor', 'size': 3}\n",
      "{'id': 1999, 'name': 'Egor', 'size': 3}\n",
      "{'id': 1999, 'name': 'Egor', 'size': 3}\n",
      "{'id': 1999, 'name': 'Egor', 'size': 3}\n"
     ]
    }
   ],
   "source": [
    "d1 = dict(id = 1999, name = \"Egor\", size = 3)\n",
    "d2 = dict({\"id\": 1999, \"name\": \"Egor\", \"size\": 3})\n",
    "d3 = dict([(\"id\", 1999), (\"name\", \"Egor\"), (\"size\", 3)])\n",
    "d4 = dict(zip((\"id\", \"name\", \"size\"), (1999, \"Egor\", 3)))\n",
    "print(d1)\n",
    "print(d2)\n",
    "print(d3)\n",
    "print(d4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'name': None, 'age': None}\n",
      "{'name': 123, 'age': 123}\n"
     ]
    }
   ],
   "source": [
    "d1 = {}.fromkeys(['name', 'age'])\n",
    "d2 = {}.fromkeys(['name', 'age'], 123)\n",
    "print(d1)\n",
    "print(d2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{0: 0, 1: 1, 2: 4, 3: 9, 4: 16}"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d = dict((x, x**2) for x in range(5))\n",
    "d"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Методы работы со словарем"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5\n",
      "{0: 0, 1: 1, 2: 4, 3: 9, 4: 16}\n",
      "{}\n"
     ]
    }
   ],
   "source": [
    "print(len(d))\n",
    "print(d)\n",
    "d.clear()\n",
    "print(d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Alice phone is 2341\n"
     ]
    }
   ],
   "source": [
    "people = {'Alice': {'phone': '2341', 'addr': 'Lenin st, 23'},\n",
    "          'Alik': {'phone': '1311', 'addr': 'Lenin st, 13'},\n",
    "          'Mike':  {'phone': '9102', 'addr': 'Maklin st, 42'}}\n",
    "name = 'Alice'          \n",
    "key = 'phone'\n",
    "if name in people: \n",
    "    print(\"%s phone is %s\" % (name, people[name][key]))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'user': 'admin', 'attr': [1, 2, 3]}\n",
      "{'user': 'admin', 'attr': [2, 3]}\n",
      "{'user': 'admin', 'attr': [2, 3]}\n",
      "True\n",
      "{'user': 'admin', 'attr': [2, 3], 'new': 34}\n",
      "{'user': 'admin', 'attr': [2, 3]}\n",
      "False\n"
     ]
    }
   ],
   "source": [
    "x = {\"user\": 'admin','attr': [1, 2, 3]}\n",
    "y = x.copy()\n",
    "print(y)\n",
    "x['attr'].remove(1)\n",
    "print(x)\n",
    "print(y)\n",
    "print(x==y)\n",
    "x['new']=34\n",
    "print(x)\n",
    "print(y)\n",
    "print(x==y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'user': 'admin', 'attr': [1, 2, 3]}\n",
      "{'user': 'admin', 'attr': [1, 2, 3]}\n",
      "{'user': 'admin', 'attr': [1, 2, 3]}\n",
      "{'user': 'admin', 'attr': [2, 3]}\n",
      "False\n"
     ]
    }
   ],
   "source": [
    "from copy import deepcopy\n",
    "x = {\"user\": 'admin', 'attr': [1, 2, 3]}\n",
    "print(x)\n",
    "z = deepcopy(x)\n",
    "print(z)\n",
    "z['attr'].remove(1)\n",
    "print(x)\n",
    "print(z)\n",
    "print(x==z)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "admin\n",
      "None\n"
     ]
    },
    {
     "ename": "KeyError",
     "evalue": "'name'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-15-33440943961a>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[0md\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m{\u001b[0m\u001b[1;33m}\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0md\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'name'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 4\u001b[1;33m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0md\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'name'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;31mKeyError\u001b[0m: 'name'"
     ]
    }
   ],
   "source": [
    "print(x.get('user'))\n",
    "d = {}\n",
    "print(d.get('name'))\n",
    "print(d['name']) #error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Alice {'phone': '2341', 'addr': 'Lenin st, 23'}\n",
      "Alik {'phone': '1311', 'addr': 'Lenin st, 13'}\n",
      "Mike {'phone': '9102', 'addr': 'Maklin st, 42'}\n",
      "{'Alice': {'phone': '2341', 'addr': 'Lenin st, 23'}, 'Alik': {'phone': '1311', 'addr': 'Lenin st, 13'}, 'Mike': {'phone': '9102', 'addr': 'Maklin st, 42'}}\n"
     ]
    }
   ],
   "source": [
    "for key, value in people.items():\n",
    "    print(key, value)\n",
    "print((people))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dict_keys(['Alice', 'Alik', 'Mike'])\n",
      "dict_values([{'phone': '2341', 'addr': 'Lenin st, 23'}, {'phone': '1311', 'addr': 'Lenin st, 13'}, {'phone': '9102', 'addr': 'Maklin st, 42'}])\n"
     ]
    }
   ],
   "source": [
    "print(people.keys())\n",
    "print(people.values())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'Alice': {'phone': '2341', 'addr': 'Lenin st, 23'}, 'Alik': {'phone': '1311', 'addr': 'Lenin st, 13'}, 'Mike': {'phone': '9102', 'addr': 'Maklin st, 42'}}\n",
      "{'Alice': {'phone': '2341', 'addr': 'Lenin st, 23'}, 'Alik': {'phone': '1311', 'addr': 'Lenin st, 13'}}\n"
     ]
    }
   ],
   "source": [
    "print(people)\n",
    "people.pop('Mike')\n",
    "print(people)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('Alik', {'phone': '1311', 'addr': 'Lenin st, 13'})\n",
      "{'Alice': {'phone': '2341', 'addr': 'Lenin st, 23'}}\n"
     ]
    }
   ],
   "source": [
    "print(people.popitem())\n",
    "print(people)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'title': 'Python Web Site', 'url': 'http://www.python.org', 'www': 'python'}\n",
      "{'title': 'Python Web Site', 'url': 'http://www.python.org', 'www': 'python.org'}\n"
     ]
    }
   ],
   "source": [
    "d = {'title': 'Python Web Site', 'url': 'http://www.python.org', 'www': 'python'}\n",
    "print(d)\n",
    "d2 = {'www':'python.org'}\n",
    "d.update(d2)\n",
    "print(d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{1: 11, 2: 22, 3: 33}\n",
      "dict_values([11, 22, 33])\n",
      "{1: 11, 3: 33}\n"
     ]
    },
    {
     "ename": "KeyError",
     "evalue": "22",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-19-3c657fb33de8>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      7\u001b[0m \u001b[1;32mdel\u001b[0m \u001b[0md\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m2\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      8\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0md\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 9\u001b[1;33m \u001b[1;32mdel\u001b[0m \u001b[0md\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m22\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     10\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0md\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mKeyError\u001b[0m: 22"
     ]
    }
   ],
   "source": [
    "d={}\n",
    "d[1]=11\n",
    "d[2]=22\n",
    "d[3]=33\n",
    "print(d)\n",
    "print(d.values())\n",
    "del d[2]\n",
    "print(d)\n",
    "del d[22] # error\n",
    "print(d)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Операции"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Python - Guido van Rossum\n",
      "Perl - Larry Wall\n",
      "Tcl - John Ousterhout\n"
     ]
    }
   ],
   "source": [
    "table = {'Python': 'Guido van Rossum',\n",
    "        'Perl':     'Larry Wall',\n",
    "        'Tcl':      'John Ousterhout' }\n",
    "for lang in table:\n",
    "    print(lang, '-', table[lang])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{(2, 3, 4): 88, (7, 8, 9): 99}\n",
      "88\n"
     ]
    }
   ],
   "source": [
    "Matrix = {}\n",
    "Matrix[(2, 3, 4)] = 88\n",
    "Matrix[(7, 8, 9)] = 99\n",
    "X = 2; Y = 3; Z = 4\n",
    "print(Matrix)\n",
    "print(Matrix[(X, Y, Z)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Serg\n",
      "writer\n"
     ]
    }
   ],
   "source": [
    "man = {'name': 'Serg',\n",
    "        'jobs': ['programmer', 'writer'],\n",
    "        'web': 'www.iakovlev.org',\n",
    "        'home': {'city': 'Moscow', 'zip': 129000}}\n",
    "print(man['name'])\n",
    "print(man['jobs'][1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'h': 3, 'o': 1, 'w': 1, ' ': 3, 'm': 2, 'a': 1, 'n': 1, 'y': 1, 't': 1, 'i': 1, 'e': 1, 's': 1}\n"
     ]
    }
   ],
   "source": [
    "def histogram(s):\n",
    "    d = dict()\n",
    "    for c in s:\n",
    "        if c not in d:d[c] = 1\n",
    "        else:d[c] += 1\n",
    "    return d\n",
    "hist = histogram('how many times hh')\n",
    "print(hist)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{3: ['h', ' '], 1: ['o', 'w', 'a', 'n', 'y', 't', 'i', 'e', 's'], 2: ['m']}\n"
     ]
    }
   ],
   "source": [
    "def invert_dict(d):\n",
    "    inv = dict()\n",
    "    for key in d:\n",
    "        val = d[key]\n",
    "        if val not in inv:inv[val] = [key]\n",
    "        else:inv[val].append(key)\n",
    "    return inv\n",
    "print(invert_dict(hist))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'hello': 4, 'world': 3, 'the': 1, 'beautiful': 1}\n",
      "'hello' occurs 4 times\n",
      "'world' occurs 3 times\n"
     ]
    }
   ],
   "source": [
    "import string\n",
    "import sys\n",
    "\n",
    "words = {}\n",
    "strip = string.whitespace + string.punctuation + string.digits + \"\\\"'\"\n",
    "filename = 'my_file.txt'\n",
    "for line in open(filename):\n",
    "    for word in line.lower().split():\n",
    "        word = word.strip(strip)\n",
    "        if len(word) > 2:\n",
    "            words[word] = words.get(word, 0) + 1\n",
    "print(words)\n",
    "for word in sorted(words):\n",
    "    if (words[word]>1): print(\"'{0}' occurs {1} times\".format(word, words[word]))   \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "awk  -  Brian Kernighan\n",
      "java  -  James Gosling\n",
      "parrot  -  Simon Cozens\n",
      "perl  -  Larry Wall\n",
      "php  -  Rasmus Lerdorf\n",
      "python  -  Guido van Rossum\n",
      "tcl  -  John Ousterhout\n",
      "\n",
      "Brian Kernighan\n",
      "Guido van Rossum\n",
      "James Gosling\n",
      "John Ousterhout\n",
      "Larry Wall\n",
      "Rasmus Lerdorf\n",
      "Simon Cozens\n"
     ]
    }
   ],
   "source": [
    "author = {\"php\":\"Rasmus Lerdorf\",\\\n",
    "    \"perl\":\"Larry Wall\",\\\n",
    "    \"tcl\":\"John Ousterhout\",\\\n",
    "    \"awk\":\"Brian Kernighan\",\\\n",
    "    \"java\":\"James Gosling\",\\\n",
    "    \"parrot\":\"Simon Cozens\",\\\n",
    "    \"python\":\"Guido van Rossum\"}\n",
    "\n",
    "for language in sorted(author.keys()):\n",
    "    print(language,\" - \", author[language])\n",
    "\n",
    "print()\n",
    "\n",
    "for aut in sorted(author.values()):\n",
    "    print(aut)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'parent1': ['child1', 'child2'], 'parent2': ['child3', 'child4']}\n"
     ]
    }
   ],
   "source": [
    "def invert_dict_nonunique(d):\n",
    "    newdict = {}\n",
    "    for k, v in d.items():\n",
    "        newdict.setdefault(v, []).append(k)\n",
    "    return newdict\n",
    "d = {'child1': 'parent1','child2': 'parent1','child3': 'parent2','child4': 'parent2'}\n",
    "print(invert_dict_nonunique(d))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4  -  ['hello']\n",
      "3  -  ['world']\n",
      "1  -  ['the', 'beautiful']\n"
     ]
    }
   ],
   "source": [
    "newdict = {}\n",
    "for k, v in words.items():\n",
    "    newdict.setdefault(v, []).append(k)    \n",
    "    \n",
    "for no in sorted(newdict.keys(), reverse = True):\n",
    "    print(no, \" - \", newdict[no])  \n"
   ]
  }
 ],
 "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": "3.7.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}