Python Training Notes - June 2012

0-python-training.ipynb

1-getting-started.ipynb

2-working-with-data.ipynb

3-classes.ipynb

4-modules.ipynb

{
 "metadata": {
  "name": "4-modules"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Modules"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import time\n",
      "time.asctime()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 1,
       "text": [
        "'Sun Jun 23 14:29:36 2013'"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "time"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 2,
       "text": [
        "<module 'time' from '/Users/anand/pyenvs/sandbox27/lib/python2.7/lib-dynload/time.so'>"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "x = time"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "x.asctime()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 4,
       "text": [
        "'Sun Jun 23 14:30:08 2013'"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "**Example: num module**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%file num.py\n",
      "\n",
      "def square(x):\n",
      "    return x*x\n",
      "\n",
      "def cube(x):\n",
      "    return x*x"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Writing num.py\n"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import num"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "num"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "<module 'num' from 'num.py'>"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "num.square(3)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 9,
       "text": [
        "9"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "dir(num)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 10,
       "text": [
        "['__builtins__',\n",
        " '__doc__',\n",
        " '__file__',\n",
        " '__name__',\n",
        " '__package__',\n",
        " 'cube',\n",
        " 'square']"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%file num2.py\n",
      "\"\"\"Module to demonstates user-defined modules and docstrings.\n",
      "\"\"\"\n",
      "def square(x):\n",
      "    \"\"\"Computes square of a number.\n",
      "    \"\"\"\n",
      "    return x*x\n",
      "\n",
      "def cube(x):\n",
      "    \"\"\"Computes cube of a number.\n",
      "    \n",
      "    Examples:\n",
      "\n",
      "        >>> cube(2)\n",
      "        8\n",
      "        >>> cube(3)\n",
      "        27\n",
      "    \"\"\"\n",
      "    return x*x\n",
      "\n",
      "if __name__ == \"__main__\":\n",
      "    print square(2)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Overwriting num2.py\n"
       ]
      }
     ],
     "prompt_number": 22
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "help(\"num2\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Help on module num2:\n",
        "\n",
        "NAME\n",
        "    num2 - Module to demonstates user-defined modules and docstrings.\n",
        "\n",
        "FILE\n",
        "    /Users/anand/Dropbox/Trainings/2013/python-june2013/notebook/num2.py\n",
        "\n",
        "FUNCTIONS\n",
        "    cube(x)\n",
        "        Computes cube of a number.\n",
        "        \n",
        "        Examples:\n",
        "        \n",
        "            >>> cube(2)\n",
        "            8\n",
        "            >>> cube(3)\n",
        "            27\n",
        "    \n",
        "    square(x)\n",
        "        Computes square of a number.\n",
        "\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 17,
       "text": [
        "<module 'num2' from 'num2.py'>"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Standard Library Modules"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "**os module**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import os\n",
      "print os.getcwd()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/Users/anand/Dropbox/Trainings/2013/python-june2013/notebook\n"
       ]
      }
     ],
     "prompt_number": 24
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "**Problem** Write a program `pwd.py` that prints the current working directory."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "os.listdir(\"..\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 26,
       "text": [
        "['5835376', 'notebook', 'notebook.tgz']"
       ]
      }
     ],
     "prompt_number": 26
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "**Problem:** Write a program `lspy.py` that prints all `.py` files in the current directory. If directory is specified as argument, it should print .py files in that directory instead of current directory."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "os.stat(\"a.txt\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 27,
       "text": [
        "posix.stat_result(st_mode=33188, st_ino=53498985, st_dev=234881026L, st_nlink=1, st_uid=501, st_gid=20, st_size=23, st_atime=1371979045, st_mtime=1371892575, st_ctime=1371892575)"
       ]
      }
     ],
     "prompt_number": 27
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# length of a file\n",
      "os.stat(\"a.txt\").st_size"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 28,
       "text": [
        "23"
       ]
      }
     ],
     "prompt_number": 28
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "**Problem** Write a program `ls_by_size.py` to print all the files in the given directory ordered by file size."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "f = os.popen(\"pwd\")\n",
      "print f.read()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/Users/anand/work/trainings/2013/python-june2013/notebook\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 32
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "f = os.popen(\"pwd\")\n",
      "print f.read().strip().split(\"/\")[-1]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "notebook\n"
       ]
      }
     ],
     "prompt_number": 33
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# using the unix sort to sort a.txt and reading \n",
      "# the first line from its output\n",
      "f = os.popen(\"sort a.txt\")\n",
      "print f.readline()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "five\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 36
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "**urllib module**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import urllib\n",
      "response = urllib.urlopen(\"http://python.org/\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 44
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "html = response.read()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 42
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "html[:200]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 43,
       "text": [
        "'<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\\n\\n\\n<html xmlns=\"http://www.w3.org/1999/xhtml\" xml:lang=\"en\" lang=\"en\">\\n\\n<head>\\n'"
       ]
      }
     ],
     "prompt_number": 43
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print response.headers"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Date: Sun, 23 Jun 2013 09:48:44 GMT\r\n",
        "Server: Apache/2.2.16 (Debian)\r\n",
        "Last-Modified: Sun, 23 Jun 2013 07:06:54 GMT\r\n",
        "ETag: \"105800d-5245-4dfccf0da3f80\"\r\n",
        "Accept-Ranges: bytes\r\n",
        "Content-Length: 21061\r\n",
        "Vary: Accept-Encoding\r\n",
        "Connection: close\r\n",
        "Content-Type: text/html\r\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 45
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "**Problem:** Write a program `wget.py` that takes a URL as command-line argument, downloads it and saves to a file. The filename should be base name of the URL. If the URL ends with a `/` then it should be saved to `index.html`.\n",
      "\n",
      "    $ python wget.py http://en.wikipedia.org/wiki/Python\n",
      "    saved to file Python\n",
      "    $ python wget.py http://python.org/\n",
      "    saved to file index.html\n",
      "    $ python wget.py http://python.org/images/python-logo.gif\n",
      "    saved to file python-logo.gif"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "**re module**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import re"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 47
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "How to validate phone numbers?\n",
      "\n",
      "examples:\n",
      "\n",
      "* 1234567890\n",
      "* 123-456-7890\n",
      "* 123 456 7890\n",
      "\n",
      "bad examples:\n",
      "\n",
      "* 1234acd"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def is_valid_phone(number):\n",
      "    m = re.match(\"^[0-9 -]*$\", number)\n",
      "    return m is not None\n",
      "\n",
      "print is_valid_phone(\"1234567890\")\n",
      "print is_valid_phone(\"123-456-7890\")\n",
      "print is_valid_phone(\"123 456 7890\")\n",
      "print is_valid_phone(\"12345dfkafgkd\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "True\n",
        "True\n",
        "True\n",
        "False\n"
       ]
      }
     ],
     "prompt_number": 59
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def is_valid_email(email):\n",
      "    m = re.match(\"[a-zA-Z0-9]+@[a-zA-Z0-9]+\\.[a-zA-Z0-9]$\", email)\n",
      "    return m is not None\n",
      "\n",
      "print is_valid_email(\"[email protected]\")\n",
      "print is_valid_email(\"[email protected]\")\n",
      "print is_valid_email(\"[email protected]@some$foo\")\n",
      "print is_valid_email(\"[email protected]\")\n",
      "print is_valid_email(\"name-example.com\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "True\n",
        "False\n",
        "False\n",
        "False\n",
        "False\n"
       ]
      }
     ],
     "prompt_number": 68
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%file antihtml.py\n",
      "import re\n",
      "def antihtml(html):\n",
      "    return re.sub(\"<[^<>]+>\", \"\", html)\n",
      "\n",
      "print antihtml('begin <b>hello <i>world</i></b> end')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Overwriting antihtml.py\n"
       ]
      }
     ],
     "prompt_number": 81
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!python antihtml.py"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "begin hello world end\r\n"
       ]
      }
     ],
     "prompt_number": 82
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Third-party Modules"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "**tablib module**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import tablib\n",
      "data = tablib.Dataset()\n",
      "data.append([\"a\", 1])\n",
      "data.append([\"b\", 2])\n",
      "\n",
      "f = open(\"a.xls\", \"wb\")\n",
      "f.write(data.xls)\n",
      "f.close()\n",
      "print \"wrote a.xls\""
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "wrote a.xls\n"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "**beautifulsoup**"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "pip install beautifulsoup4"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from bs4 import BeautifulSoup\n",
      "import urllib\n",
      "\n",
      "html = urllib.urlopen(\"http://news.ycombinator.com/\").read()\n",
      "soup = BeautifulSoup(html)\n",
      "\n",
      "links = soup.select(\"td.title a\")\n",
      "for a in links[:5]:\n",
      "    print a.get_text()\n",
      "    print a['href']\n",
      "    print "
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Snowden Leaves Hong Kong on Commercial Flight to Moscow\n",
        "http://www.scmp.com/news/hong-kong/article/1267261/snowden-leaves-hong-kong-commercial-flight-moscow\n",
        "\n",
        "HKSAR Government issues statement on Edward Snowden\n",
        "http://www.info.gov.hk/gia/general/201306/23/P201306230476.htm\n",
        "\n",
        "Snowden's destination is Venezuela through Havana\n",
        "http://www.interfax.com/news.asp\n",
        "\n",
        "Fmr NSA worker Edward Snowden leaves Hong Kong for Cuba\n",
        "http://www.rte.ie/news/2013/0623/458289-edward-snowden/\n",
        "\n",
        "This is a regular text file. People will read it. Maybe.\n",
        "http://slopjong.de/words.txt\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 17
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}