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

{
 "metadata": {
  "name": "",
  "signature": "sha256:c535c4eb558966d14a178dfbd21918ecadc105f12b3c5f939ebf807d5afd1e6f"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Files\n",
      "\n",
      "* Open a File for Reading\n",
      "* Read a File\n",
      "* Write to a New File\n",
      "* Read and write UTF-8"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Open a File for Reading\n",
      "\n",
      "Open a file in read-only mode:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "path = 'type_util.py'\n",
      "f = open(path)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Read a File\n",
      "\n",
      "Read the entire file with readlines.  Iterate over the file lines as you would with a list.  rstrip removes the EOL markers."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "for line in f:\n",
      "    print(line.rstrip())"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "class TypeUtil:\n",
        "\n",
        "    @classmethod\n",
        "    def is_iterable(cls, obj):\n",
        "        \"\"\"Determines if obj is iterable.\n",
        "\n",
        "        Useful when writing functions that can accept multiple types of\n",
        "        input (list, tuple, ndarray, iterator).  Pairs well with\n",
        "        convert_to_list.\n",
        "        \"\"\"\n",
        "        try:\n",
        "            iter(obj)\n",
        "            return True\n",
        "        except TypeError:\n",
        "            return False\n",
        "\n",
        "    @classmethod\n",
        "    def convert_to_list(cls, obj):\n",
        "        \"\"\"Converts obj to a list if it is not a list and it is iterable,\n",
        "        else returns the original obj.\n",
        "        \"\"\"\n",
        "        if not isinstance(obj, list) and cls.is_iterable(obj):\n",
        "            obj = list(obj)\n",
        "        return obj\n"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Write to a New File\n",
      "\n",
      "Create a new file (overwriting any previous file with the same name), write text then close the file:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "path = 'hello_world.txt'\n",
      "f = open(path, 'w')\n",
      "f.write('hello world!')\n",
      "f.close()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Read and Write UTF-8"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import codecs\n",
      "with codecs.open(\"hello_world_new.txt\", \"a\", \"utf-8\") as new_file:\n",
      "    with codecs.open(\"hello_world.txt\", \"r\", \"utf-8\") as old_file:                   \n",
      "        for line in old_file:\n",
      "            new_file.write(line + '\\n')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    }
   ],
   "metadata": {}
  }
 ]
}