Demonstration of YAML parsers in the Jupyter Notebook http://nbviewer.ipython.org/gist/tonyfast/e4bf0b6d77225faf1b04

yamlDemo.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Using YAML in IPython notebooks\n",
    "\n",
    "## 1. Using PyYAML\n",
    "\n",
    "[PyYaml]() is a python module to load yaml files and strings.\n",
    "\n",
    "``pip install pyyaml``\n",
    "\n",
    "## 2. Using YamlMagic\n",
    "\n",
    "[Yamlmagic]() is method of creating python variables using yaml syntax in Jupyter Notebook cells.  Yamlmagic uses [cell magic]().\n",
    "\n",
    "1. ``pip install yamlmagic``\n",
    "1. ``%load_ext yamlmagic``"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The Magics\n",
    "\n",
    "* __line magic__ starts with `%`\n",
    "* __cell magic__ starts with `%%`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "application/json": {
       "cell": {
        "!": "OSMagics",
        "HTML": "Other",
        "SVG": "Other",
        "bash": "Other",
        "capture": "ExecutionMagics",
        "debug": "ExecutionMagics",
        "file": "Other",
        "html": "DisplayMagics",
        "javascript": "DisplayMagics",
        "latex": "DisplayMagics",
        "perl": "Other",
        "prun": "ExecutionMagics",
        "pypy": "Other",
        "python": "Other",
        "python2": "Other",
        "python3": "Other",
        "ruby": "Other",
        "script": "ScriptMagics",
        "sh": "Other",
        "svg": "DisplayMagics",
        "sx": "OSMagics",
        "system": "OSMagics",
        "time": "ExecutionMagics",
        "timeit": "ExecutionMagics",
        "writefile": "OSMagics"
       },
       "line": {
        "alias": "OSMagics",
        "alias_magic": "BasicMagics",
        "autocall": "AutoMagics",
        "automagic": "AutoMagics",
        "autosave": "KernelMagics",
        "bookmark": "OSMagics",
        "cat": "Other",
        "cd": "OSMagics",
        "clear": "KernelMagics",
        "colors": "BasicMagics",
        "config": "ConfigMagics",
        "connect_info": "KernelMagics",
        "cp": "Other",
        "debug": "ExecutionMagics",
        "dhist": "OSMagics",
        "dirs": "OSMagics",
        "doctest_mode": "BasicMagics",
        "ed": "Other",
        "edit": "KernelMagics",
        "env": "OSMagics",
        "gui": "BasicMagics",
        "hist": "Other",
        "history": "HistoryMagics",
        "install_default_config": "DeprecatedMagics",
        "install_ext": "ExtensionMagics",
        "install_profiles": "DeprecatedMagics",
        "killbgscripts": "ScriptMagics",
        "ldir": "Other",
        "less": "KernelMagics",
        "lf": "Other",
        "lk": "Other",
        "ll": "Other",
        "load": "CodeMagics",
        "load_ext": "ExtensionMagics",
        "loadpy": "CodeMagics",
        "logoff": "LoggingMagics",
        "logon": "LoggingMagics",
        "logstart": "LoggingMagics",
        "logstate": "LoggingMagics",
        "logstop": "LoggingMagics",
        "ls": "Other",
        "lsmagic": "BasicMagics",
        "lx": "Other",
        "macro": "ExecutionMagics",
        "magic": "BasicMagics",
        "man": "KernelMagics",
        "matplotlib": "PylabMagics",
        "mkdir": "Other",
        "more": "KernelMagics",
        "mv": "Other",
        "notebook": "BasicMagics",
        "page": "BasicMagics",
        "pastebin": "CodeMagics",
        "pdb": "ExecutionMagics",
        "pdef": "NamespaceMagics",
        "pdoc": "NamespaceMagics",
        "pfile": "NamespaceMagics",
        "pinfo": "NamespaceMagics",
        "pinfo2": "NamespaceMagics",
        "popd": "OSMagics",
        "pprint": "BasicMagics",
        "precision": "BasicMagics",
        "profile": "BasicMagics",
        "prun": "ExecutionMagics",
        "psearch": "NamespaceMagics",
        "psource": "NamespaceMagics",
        "pushd": "OSMagics",
        "pwd": "OSMagics",
        "pycat": "OSMagics",
        "pylab": "PylabMagics",
        "qtconsole": "KernelMagics",
        "quickref": "BasicMagics",
        "recall": "HistoryMagics",
        "rehashx": "OSMagics",
        "reload_ext": "ExtensionMagics",
        "rep": "Other",
        "rerun": "HistoryMagics",
        "reset": "NamespaceMagics",
        "reset_selective": "NamespaceMagics",
        "rm": "Other",
        "rmdir": "Other",
        "run": "ExecutionMagics",
        "save": "CodeMagics",
        "sc": "OSMagics",
        "set_env": "OSMagics",
        "store": "StoreMagics",
        "sx": "OSMagics",
        "system": "OSMagics",
        "tb": "ExecutionMagics",
        "time": "ExecutionMagics",
        "timeit": "ExecutionMagics",
        "unalias": "OSMagics",
        "unload_ext": "ExtensionMagics",
        "who": "NamespaceMagics",
        "who_ls": "NamespaceMagics",
        "whos": "NamespaceMagics",
        "xdel": "NamespaceMagics",
        "xmode": "BasicMagics"
       }
      },
      "text/plain": [
       "Available line magics:\n",
       "%alias  %alias_magic  %autocall  %automagic  %autosave  %bookmark  %cat  %cd  %clear  %colors  %config  %connect_info  %cp  %debug  %dhist  %dirs  %doctest_mode  %ed  %edit  %env  %gui  %hist  %history  %install_default_config  %install_ext  %install_profiles  %killbgscripts  %ldir  %less  %lf  %lk  %ll  %load  %load_ext  %loadpy  %logoff  %logon  %logstart  %logstate  %logstop  %ls  %lsmagic  %lx  %macro  %magic  %man  %matplotlib  %mkdir  %more  %mv  %notebook  %page  %pastebin  %pdb  %pdef  %pdoc  %pfile  %pinfo  %pinfo2  %popd  %pprint  %precision  %profile  %prun  %psearch  %psource  %pushd  %pwd  %pycat  %pylab  %qtconsole  %quickref  %recall  %rehashx  %reload_ext  %rep  %rerun  %reset  %reset_selective  %rm  %rmdir  %run  %save  %sc  %set_env  %store  %sx  %system  %tb  %time  %timeit  %unalias  %unload_ext  %who  %who_ls  %whos  %xdel  %xmode\n",
       "\n",
       "Available cell magics:\n",
       "%%!  %%HTML  %%SVG  %%bash  %%capture  %%debug  %%file  %%html  %%javascript  %%latex  %%perl  %%prun  %%pypy  %%python  %%python2  %%python3  %%ruby  %%script  %%sh  %%svg  %%sx  %%system  %%time  %%timeit  %%writefile\n",
       "\n",
       "Automagic is ON, % prefix IS NOT needed for line magics."
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%lsmagic\n",
    "# line magic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1\n",
      "CPU times: user 32 µs, sys: 1 µs, total: 33 µs\n",
      "Wall time: 58.9 µs\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "# cell magic\n",
    "a = 1\n",
    "print(a)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Using PyYaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'b': {'c': 'some string'}, 'a': 1}\n",
      "{'c': 'some string'}\n"
     ]
    }
   ],
   "source": [
    "import yaml\n",
    "yamlFromModule = yaml.safe_load(\"\"\"\n",
    "a : 1\n",
    "b: \n",
    "  c: some string\n",
    "\"\"\")\n",
    "print(yamlFromModule)\n",
    "print(yamlFromModule['b'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'b': {'c': 'some string'}, 'a': 1}\n",
      "{'c': 'some string'}\n"
     ]
    }
   ],
   "source": [
    "import yaml\n",
    "yamlFromModuleLine = yaml.safe_load(\"a : 1\\nb:\\n  c: some string\\n\")\n",
    "print(yamlFromModuleLine)\n",
    "print(yamlFromModuleLine['b'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Using yamlmagic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# load the magic \n",
    "%load_ext yamlmagic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            require(\n",
       "                [\n",
       "                    \"notebook/js/codecell\",\n",
       "                    \"codemirror/mode/yaml/yaml\"\n",
       "                ],\n",
       "                function(cc){\n",
       "                    cc.CodeCell.options_default.highlight_modes.magic_yaml = {\n",
       "                        reg: [\"^%%yaml\"]\n",
       "                    }\n",
       "                }\n",
       "            );\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%%yaml yamlFromMagic\n",
    "a : 1\n",
    "b: \n",
    "  c: some string"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'b': {'c': 'some string'}, 'a': 1}\n"
     ]
    }
   ],
   "source": [
    "print(yamlFromMagic)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Loading YAML from a remote location"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "remoteYamlResponse = requests.get(\n",
    "    url = \"https://raw.githubusercontent.com/ICBacon/icbacon.github.io/master/_config.yml\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "yamlFromRemote = yaml.safe_load(remoteYamlResponse.text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The keys in this yaml file are: \n",
      "github\n",
      "markdown\n",
      "title\n",
      "email\n",
      "description\n",
      "url\n",
      "disqus_username\n",
      "baseurl\n",
      "twitter_username\n"
     ]
    }
   ],
   "source": [
    "print('The keys in this yaml file are: ')\n",
    "for key in yamlFromRemote:\n",
    "    print(key)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Hacking yaml front matter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "urlStream = 'https://raw.githubusercontent.com/ICBacon/icbacon.github.io/master/_posts/2015-07-10-my-first-day-at-continuum.md'\n",
    "stream = requests.get(\n",
    "    url = urlStream,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'title': 'Installing Miniconda3 for a Mac OS X', 'layout': 'post'}\n"
     ]
    }
   ],
   "source": [
    "# Split the string using the stream tokens ---\n",
    "frontMatter = yaml.safe_load(stream.text.split('---')[1])\n",
    "print(frontMatter)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def myStreamParser( url ):\n",
    "    \"\"\"\n",
    "    Convert a remote file with yaml front matter\n",
    "    into Python variables.\n",
    "    \"\"\"\n",
    "    stream = requests.get(\n",
    "        url = url,\n",
    "    )\n",
    "    return yaml.safe_load(stream.text.split('---')[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "layout\n",
      "content1\n",
      "im\n",
      "flickr1\n",
      "link1\n"
     ]
    }
   ],
   "source": [
    "yamlStreamFunc = myStreamParser(\n",
    "    'https://raw.githubusercontent.com/tonyfast/nsf-goali/gh-pages/_posts/2014-08-06-Markdown-Example.html'\n",
    ")\n",
    "for key in yamlStreamFunc:\n",
    "    print(key)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Yaml can load JSON!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "True\n"
     ]
    }
   ],
   "source": [
    "remoteJSON = requests.get(\n",
    "    url='https://api.github.com/users/icbacon/events'\n",
    ")\n",
    "print(yaml.safe_load(remoteJSON.text) == remoteJSON.json())"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.4.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}