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

{
 "metadata": {
  "name": "",
  "signature": "sha256:a37a234cd37895919493dabe7ab645bb2b5e24d9b304ab564e18b59eac4f7a0a"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Functions"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "* Functions as Objects\n",
      "* Lambda Functions\n",
      "* Closures\n",
      "* \\*args, \\*\\*kwargs\n",
      "* Currying\n",
      "* Generators\n",
      "* Generator Expressions"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Functions as Objects"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Python treats functions as objects which can simplify data cleaning"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%file transform_util.py\n",
      "import re\n",
      "\n",
      "\n",
      "class TransformUtil:\n",
      "\n",
      "    @classmethod\n",
      "    def remove_punctuation(cls, value):\n",
      "        \"\"\"Removes !, #, and ?.\n",
      "        \"\"\"        \n",
      "        return re.sub('[!#?]', '', value) \n",
      "\n",
      "    @classmethod\n",
      "    def clean_strings(cls, strings, ops): \n",
      "        \"\"\"General purpose method to clean strings.\n",
      "\n",
      "        Pass in a sequence of strings and the operations to perform.\n",
      "        \"\"\"        \n",
      "        result = [] \n",
      "        for value in strings: \n",
      "            for function in ops: \n",
      "                value = function(value) \n",
      "            result.append(value) \n",
      "        return result"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Overwriting transform_util.py\n"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%file tests/test_transform_util.py\n",
      "from nose.tools import assert_equal\n",
      "from ..transform_util import TransformUtil\n",
      "\n",
      "\n",
      "class TestTransformUtil():\n",
      "\n",
      "    states = [' Alabama ', 'Georgia!', 'Georgia', 'georgia', \\\n",
      "          'FlOrIda', 'south carolina##', 'West virginia?']\n",
      "    \n",
      "    expected_output = ['Alabama',\n",
      "                       'Georgia',\n",
      "                       'Georgia',\n",
      "                       'Georgia',\n",
      "                       'Florida',\n",
      "                       'South Carolina',\n",
      "                       'West Virginia']\n",
      "    \n",
      "    def test_remove_punctuation(self):\n",
      "        assert_equal(TransformUtil.remove_punctuation('!#?'), '')\n",
      "        \n",
      "    def test_map_remove_punctuation(self):\n",
      "        # Map applies a function to a collection\n",
      "        output = map(TransformUtil.remove_punctuation, self.states)\n",
      "        assert_equal('!#?' not in output, True)\n",
      "\n",
      "    def test_clean_strings(self):\n",
      "        clean_ops = [str.strip, TransformUtil.remove_punctuation, str.title] \n",
      "        output = TransformUtil.clean_strings(self.states, clean_ops)\n",
      "        assert_equal(output, self.expected_output)\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Overwriting tests/test_transform_util.py\n"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!nosetests tests/test_transform_util.py -v"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "core.tests.test_transform_util.TestTransformUtil.test_clean_strings ... ok\r\n",
        "core.tests.test_transform_util.TestTransformUtil.test_map_remove_punctuation ... ok\r\n",
        "core.tests.test_transform_util.TestTransformUtil.test_remove_punctuation ... ok\r\n",
        "\r\n",
        "----------------------------------------------------------------------\r\n",
        "Ran 3 tests in 0.002s\r\n",
        "\r\n",
        "OK\r\n"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Lambda Functions"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Lambda functions are anonymous function and are convenient for data analysis, as data transformation functions take functions as arguments."
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Sort a sequence of strings by the number of letters"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "strings = ['foo', 'bar,', 'baz', 'f', 'fo', 'b', 'ba']\n",
      "strings.sort(key=lambda x: len(list(x)))\n",
      "strings"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "['f', 'b', 'fo', 'ba', 'foo', 'baz', 'bar,']"
       ]
      }
     ],
     "prompt_number": 7
    }
   ],
   "metadata": {}
  }
 ]
}