Python Lecture.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Iterators"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Sources:\n",
    "\n",
    "https://nvie.com/posts/iterators-vs-generators/"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![image.png](https://nvie.com/img/relationships.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Generator Function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fib():\n",
    "    prev, curr = 0, 1\n",
    "    while True:\n",
    "        yield curr\n",
    "        prev, curr = curr, prev + curr\n",
    "\n",
    "f = fib()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Called next(f) yields: 1\n",
      "Called next(f) yields: 2\n",
      "Called next(f) yields: 3\n",
      "Called next(f) yields: 5\n",
      "Called next(f) yields: 8\n"
     ]
    }
   ],
   "source": [
    "for _ in range(5):\n",
    "    print(f\"Called next(f) yields: {next(f)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Generator Expressions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "gen_exp = (x ** 2 for x in range(10) if x % 2 == 0) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "ename": "StopIteration",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mStopIteration\u001b[0m                             Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-10-d097888c6d32>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgen_exp\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mStopIteration\u001b[0m: "
     ]
    }
   ],
   "source": [
    "print(next(gen_exp))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Creating Iterables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import string\n",
    "alphabet_iterable = iter(string.ascii_lowercase)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "next(alphabet_iterable)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Itertools\n",
    "\n",
    "https://docs.python.org/3/library/itertools.html\n",
    "\n",
    "\n",
    "### Infinite Iterators\n",
    "* cycle\n",
    "* count\n",
    "* repeat\n",
    "\n",
    "### Terminating Iterators\n",
    "\n",
    "* accumulate\n",
    "* chain\n",
    "* compress\n",
    "* zip_longest\n",
    "* ... and more\n",
    "\n",
    "### Combinations\n",
    "\n",
    "* permutations\n",
    "* combinations\n",
    "* combinations_with_replacement"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Functools\n",
    "\n",
    "https://docs.python.org/3/library/functools.html\n",
    "\n",
    "* functools.reduce\n",
    "* functools.partial"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## More\n",
    "\n",
    "Itertools and Functools to recreate k-means\n",
    "\n",
    "https://www.youtube.com/watch?v=ThS4juptJjQ"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Where Does Range Fit In?\n",
    "\n",
    "Source:\n",
    "\n",
    "http://treyhunner.com/2018/02/python-range-is-not-an-iterator/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_range = range(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "'range' object is not an iterator",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-13-3e09a998729c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mnext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtest_range\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m: 'range' object is not an iterator"
     ]
    }
   ],
   "source": [
    "next(test_range)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_range[5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(test_range)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hasattr(test_range, '__iter__')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "range_iterator"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(test_range.__iter__())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Typing Module"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "# typing module syntax (new)\n",
    "from typing import NamedTuple\n",
    "\n",
    "class Employee(NamedTuple):\n",
    "    name: str\n",
    "    id: int\n",
    "        \n",
    "ogi = Employee(name=\"Ogi\", id=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Ogi'"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ogi.name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ogi.id"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Ogi'"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ogi[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "'Employee' object does not support item assignment",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-53-99142f099809>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mogi\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"Ogy\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m: 'Employee' object does not support item assignment"
     ]
    }
   ],
   "source": [
    "ogi[0] = \"Ogy\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Ogy'"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ogi = ogi._replace(name=\"Ogy\")\n",
    "ogi.name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "# old style syntax\n",
    "from collections import namedtuple \n",
    "\n",
    "Employee = namedtuple('Employee', ['name', 'id'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Collections"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Deque"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "from collections import deque\n",
    "import random\n",
    "\n",
    "queue = deque()\n",
    "queue_list = list()\n",
    "\n",
    "numbers = list(range(100_000))\n",
    "random.shuffle(numbers)\n",
    "\n",
    "def reset_objects(queue, queue_list):\n",
    "    queue.clear()\n",
    "    queue_list.clear()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "29.5 ms ± 3.18 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "reset_objects(queue, queue_list)\n",
    "for number in numbers:\n",
    "    queue.append(number)\n",
    "#     queue.appendleft(number)\n",
    "\n",
    "while queue:\n",
    "    queue.pop()\n",
    "#     queue.popleft()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "30.7 ms ± 3.66 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "reset_objects(queue, queue_list)\n",
    "for number in numbers:\n",
    "    queue_list.append(number)\n",
    "#     queue_list.insert(0, number)\n",
    "    \n",
    "while queue_list:\n",
    "    queue_list.pop()\n",
    "#     queue_list.pop(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3.13 s ± 26 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "reset_objects(queue, queue_list)\n",
    "for number in numbers:\n",
    "#     queue_list.append(number)\n",
    "    queue_list.insert(0, number)\n",
    "    \n",
    "while queue_list:\n",
    "#     queue_list.pop()\n",
    "    queue_list.pop(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "26.2 ms ± 2.84 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "reset_objects(queue, queue_list)\n",
    "for number in numbers:\n",
    "#     queue.append(number)\n",
    "    queue.appendleft(number)\n",
    "\n",
    "while queue:\n",
    "#     queue.pop()\n",
    "    queue.popleft()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Various Dictionaries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [],
   "source": [
    "# lowercase objects have a c-implementation under the hood\n",
    "from collections import defaultdict, OrderedDict\n",
    "\n",
    "\n",
    "test_defaultdict = defaultdict(int)\n",
    "test_ordereddict = OrderedDict()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_defaultdict['abc']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "key: first \t value: 1\n",
      "key: second \t value: 2\n",
      "key: third \t value: 3\n"
     ]
    }
   ],
   "source": [
    "test_ordereddict['first'] = 1\n",
    "test_ordereddict['second'] = 2\n",
    "test_ordereddict['third'] = 3\n",
    "\n",
    "for key, value in test_ordereddict.items():\n",
    "    print(f\"key: {key} \\t value: {value}\")"
   ]
  },
  {
   "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": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}