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

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook was prepared by [Donne Martin](http://donnemartin.com). Source and license info is on [GitHub](https://github.com/donnemartin/data-science-ipython-notebooks)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Files\n",
    "\n",
    "* Read a File\n",
    "* Write a File\n",
    "* Read and Write UTF-8"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read a File\n",
    "\n",
    "Open a file in read-only mode.<br\\>\n",
    "Iterate over the file lines.  rstrip removes the EOL markers.<br\\>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "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"
     ]
    }
   ],
   "source": [
    "old_file_path = 'type_util.py'\n",
    "with open(old_file_path, 'r') as old_file:\n",
    "    for line in old_file:\n",
    "        print(line.rstrip())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Write to a file\n",
    "\n",
    "Create a new file overwriting any previous file with the same name, write text, then close the file:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "new_file_path = 'hello_world.txt'\n",
    "with open(new_file_path, 'w') as new_file:\n",
    "    new_file.write('hello world!')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read and Write UTF-8"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "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')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}