data-science-ipython-notebooks/core/structs.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:cafae0e55ae01630aff5ca46caf56896315bc7fec5174ea75bcaa1502717d3fa"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Data Structures"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Tuples"
     ]
    },
    {
     "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": 48,
       "text": [
        "(1, 2, 3)"
       ]
      }
     ],
     "prompt_number": 48
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "a_list = [1, 2, 3]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 49
    },
    {
     "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": 50,
       "text": [
        "tuple"
       ]
      }
     ],
     "prompt_number": 50
    },
    {
     "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": 51,
       "text": [
        "([1, 2, 3], (4, 5))"
       ]
      }
     ],
     "prompt_number": 51
    },
    {
     "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": 52,
       "text": [
        "[1, 2, 3]"
       ]
      }
     ],
     "prompt_number": 52
    },
    {
     "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": 53,
       "text": [
        "[1, 2, 3, 4]"
       ]
      }
     ],
     "prompt_number": 53
    },
    {
     "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": 54,
       "text": [
        "(1, 3, 2, 4, 5, 6)"
       ]
      }
     ],
     "prompt_number": 54
    },
    {
     "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": 55,
       "text": [
        "('foo', 'bar', 'foo', 'bar')"
       ]
      }
     ],
     "prompt_number": 55
    },
    {
     "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": 56,
       "text": [
        "([1, 2, 3, 4], (4, 5))"
       ]
      }
     ],
     "prompt_number": 56
    },
    {
     "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": 57,
       "text": [
        "(1, 2, 3, 4, 4, 5)"
       ]
      }
     ],
     "prompt_number": 57
    },
    {
     "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": 58
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Lists"
     ]
    },
    {
     "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": 59,
       "text": [
        "[1, 2, 3]"
       ]
      }
     ],
     "prompt_number": 59
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Convert to a list\n",
      "type(list(tup))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 60,
       "text": [
        "list"
       ]
      }
     ],
     "prompt_number": 60
    },
    {
     "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": 61,
       "text": [
        "[(1, 2, 3), [4, 5]]"
       ]
      }
     ],
     "prompt_number": 61
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Access by index\n",
      "nested_list[1]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 62,
       "text": [
        "[4, 5]"
       ]
      }
     ],
     "prompt_number": 62
    },
    {
     "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": 63,
       "text": [
        "[(1, 2, 3), [4, 5], 6]"
       ]
      }
     ],
     "prompt_number": 63
    },
    {
     "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": 64,
       "text": [
        "['start', (1, 2, 3), [4, 5], 6]"
       ]
      }
     ],
     "prompt_number": 64
    },
    {
     "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": 65,
       "text": [
        "[(1, 2, 3), [4, 5], 6]"
       ]
      }
     ],
     "prompt_number": 65
    },
    {
     "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": 66,
       "text": [
        "[[4, 5], 6]"
       ]
      }
     ],
     "prompt_number": 66
    },
    {
     "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": 67,
       "text": [
        "True"
       ]
      }
     ],
     "prompt_number": 67
    },
    {
     "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": 68,
       "text": [
        "[1, 3, 2, 4, 5, 6]"
       ]
      }
     ],
     "prompt_number": 68
    },
    {
     "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": 71,
       "text": [
        "[[4, 5], 6, 7, 8, 9, 7, 8, 9]"
       ]
      }
     ],
     "prompt_number": 71
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}