{
 "metadata": {
  "name": "",
  "signature": "sha256:f24f6112f8e8e28d262a4f84be84d1ae459154a9a445687d55392ff177e6a03c"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Data Structures"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## tuple"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# One dimensional, fixed-length, immutable sequence\n",
      "tup = (1, 2, 3)\n",
      "tup"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 1,
       "text": [
        "(1, 2, 3)"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "a_list = [1, 2, 3]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Convert to a tuple\n",
      "type(tuple(a_list))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 3,
       "text": [
        "tuple"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Nested tuples\n",
      "nested_tup = ([1, 2, 3], (4, 5))\n",
      "nested_tup"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 4,
       "text": [
        "([1, 2, 3], (4, 5))"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Access by index O(1)\n",
      "nested_tup[0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "[1, 2, 3]"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Although tuples are immutable, their contents can contain mutable objects\n",
      "nested_tup[0].append(4)\n",
      "nested_tup[0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 6,
       "text": [
        "[1, 2, 3, 4]"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Concatenate tuples\n",
      "# Creates a new tuple and copies objects\n",
      "(1, 3, 2) + (4, 5, 6)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "(1, 3, 2, 4, 5, 6)"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Multiply copies references to objects (objects themselves are not copied)\n",
      "('foo', 'bar') * 2"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "('foo', 'bar', 'foo', 'bar')"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Unpack tuples\n",
      "a, b = nested_tup\n",
      "a, b"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 9,
       "text": [
        "([1, 2, 3, 4], (4, 5))"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Unpack nested tuples\n",
      "(a, b, c, d), (e, f) = nested_tup\n",
      "a, b, c, d, e, f"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 10,
       "text": [
        "(1, 2, 3, 4, 4, 5)"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# A common use of variable unpacking is when iterating over sequences\n",
      "# of tuples or lists\n",
      "seq = [( 1, 2, 3), (4, 5, 6), (7, 8, 9)] \n",
      "for a, b, c in seq: \n",
      "    print(a, b, c)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "(1, 2, 3)\n",
        "(4, 5, 6)\n",
        "(7, 8, 9)\n"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## list"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# One dimensional, variable-length, mutable sequence\n",
      "a_list = [1, 2, 3]\n",
      "a_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "[1, 2, 3]"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Convert to a list\n",
      "type(list(tup))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "list"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Nested list\n",
      "nested_list = [(1, 2, 3), [4, 5]]\n",
      "nested_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "[(1, 2, 3), [4, 5]]"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Access by index\n",
      "nested_list[1]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 15,
       "text": [
        "[4, 5]"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Append an element O(1)\n",
      "nested_list.append(6)\n",
      "nested_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 16,
       "text": [
        "[(1, 2, 3), [4, 5], 6]"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Insert an element at a specific index\n",
      "# Insert is expensive as it has to shift subsequent elements O(n)\n",
      "nested_list.insert(0, 'start')\n",
      "nested_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 17,
       "text": [
        "['start', (1, 2, 3), [4, 5], 6]"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Pop removes and returns an element from a specified index\n",
      "# Pop is expensive as it has to shift subsequent elements O(n)\n",
      "# O(1) if pop is used for the last element\n",
      "nested_list.pop(0)\n",
      "nested_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 18,
       "text": [
        "[(1, 2, 3), [4, 5], 6]"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Remove locates the first such value and removes it O(n)\n",
      "nested_list.remove((1, 2, 3))\n",
      "nested_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "[[4, 5], 6]"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Check if a list contains a value O(n)\n",
      "6 in nested_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 20,
       "text": [
        "True"
       ]
      }
     ],
     "prompt_number": 20
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Concatenate lists\n",
      "# Creates a new list and copies objects\n",
      "[1, 3, 2] + [4, 5, 6]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 21,
       "text": [
        "[1, 3, 2, 4, 5, 6]"
       ]
      }
     ],
     "prompt_number": 21
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Extend a list by appending elements\n",
      "# Faster than concatenating lists\n",
      "nested_list.extend([7, 8, 9])\n",
      "nested_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 22,
       "text": [
        "[[4, 5], 6, 7, 8, 9]"
       ]
      }
     ],
     "prompt_number": 22
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## sort"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Sort in-place O(n log n)\n",
      "a_list = [1, 5, 3, 9, 7, 6]\n",
      "a_list.sort()\n",
      "a_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 23,
       "text": [
        "[1, 3, 5, 6, 7, 9]"
       ]
      }
     ],
     "prompt_number": 23
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Sort by secondary key: str length\n",
      "b_list = ['the', 'quick', 'brown', 'fox', 'jumps', 'over']\n",
      "b_list.sort(key=len)\n",
      "b_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 24,
       "text": [
        "['the', 'fox', 'over', 'quick', 'brown', 'jumps']"
       ]
      }
     ],
     "prompt_number": 24
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## bisect"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# The bisect module does not check whether the list is sorted, as this check\n",
      "# would be expensive O(n).  Using bisect on an unsorted list will not result\n",
      "# in an error but could lead to incorrect results.\n",
      "import bisect\n",
      "\n",
      "# Find the location where an element should be inserted to keep the\n",
      "# list sorted\n",
      "c_list = [1, 2, 2, 3, 5, 13]\n",
      "bisect.bisect(c_list, 8)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 25,
       "text": [
        "5"
       ]
      }
     ],
     "prompt_number": 25
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Inserts an element into a location to keep the list sorted\n",
      "bisect.insort(c_list, 8)\n",
      "c_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 26,
       "text": [
        "[1, 2, 2, 3, 5, 8, 13]"
       ]
      }
     ],
     "prompt_number": 26
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## slice"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "![alt text](http://www.nltk.org/images/string-slicing.png)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Select a section of list types (arrays, tuples, NumPy arrays)\n",
      "# start:stop\n",
      "# start is included, stop is not\n",
      "# number of elements in the result is stop - start\n",
      "d_list = 'Monty Python'\n",
      "d_list[6:10]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 27,
       "text": [
        "'Pyth'"
       ]
      }
     ],
     "prompt_number": 27
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Omit start to default to start of the sequence\n",
      "d_list[:5]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 28,
       "text": [
        "'Monty'"
       ]
      }
     ],
     "prompt_number": 28
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Omit end to default to end of the sequence\n",
      "d_list[6:]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 29,
       "text": [
        "'Python'"
       ]
      }
     ],
     "prompt_number": 29
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Negative indices slice relative to the end\n",
      "d_list[-12:-7]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 30,
       "text": [
        "'Monty'"
       ]
      }
     ],
     "prompt_number": 30
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Slice can also take a step such as the one below, which takes\n",
      "# every other element\n",
      "e_list[::2]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 33,
       "text": [
        "[1, 2, 5, 13]"
       ]
      }
     ],
     "prompt_number": 33
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Passing -1 for the step reverses the list or tuple:\n",
      "e_list[::-1]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 34,
       "text": [
        "[13, ['H', 'a', 'l', 'l'], 5, 3, 2, 1, 1]"
       ]
      }
     ],
     "prompt_number": 34
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Assign elements to a slice\n",
      "# Slice range does not have to equal number of elements to assign\n",
      "e_list = [1, 1, 2, 3, 5, 8, 13]\n",
      "e_list[5:] = ['H', 'a', 'l', 'l']\n",
      "e_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 31,
       "text": [
        "[1, 1, 2, 3, 5, 'H', 'a', 'l', 'l']"
       ]
      }
     ],
     "prompt_number": 31
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Compare assigning into a slice (above) versus assigning into\n",
      "# an inde\n",
      "e_list"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 32,
       "text": [
        "[1, 1, 2, 3, 5, ['H', 'a', 'l', 'l'], 13]"
       ]
      }
     ],
     "prompt_number": 32
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}