Quick demo of ipython & notebook

quick_tour.ipynb

{
 "metadata": {
  "name": "quick_tour"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "IPython notebook quick tour\n",
      "---------------------------\n",
      "\n",
      "### Installation\n",
      "\n",
      " - Python >= 2.7\n",
      " - [`pip`](https://pypi.python.org/pypi/pip) >= 1"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!apt-cache policy python\n",
      "!apt-cache policy python-pip"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "python:\r\n",
        "  Installed: 2.7.3-0ubuntu2\r\n",
        "  Candidate: 2.7.3-0ubuntu2\r\n",
        "  Version table:\r\n",
        " *** 2.7.3-0ubuntu2 0\r\n",
        "        500 http://gb.archive.ubuntu.com/ubuntu/ precise/main amd64 Packages\r\n",
        "        100 /var/lib/dpkg/status\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "python-pip:\r\n",
        "  Installed: 1.0-1build1\r\n",
        "  Candidate: 1.0-1build1\r\n",
        "  Version table:\r\n",
        " *** 1.0-1build1 0\r\n",
        "        500 http://gb.archive.ubuntu.com/ubuntu/ precise/universe amd64 Packages\r\n",
        "        100 /var/lib/dpkg/status\r\n"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      " - [IPython](http://ipython.org/install.html) : better to install at least the 0.13 from `pip` or the latest development version on [github](https://github.com/ipython/ipython)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!apt-cache policy ipython-notebook\n",
      "!pip search ipython | head -3"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "ipython-notebook:\r\n",
        "  Installed: (none)\r\n",
        "  Candidate: 0.12.1+dfsg-0ubuntu1\r\n",
        "  Version table:\r\n",
        "     0.12.1+dfsg-0ubuntu1 0\r\n",
        "        500 http://gb.archive.ubuntu.com/ubuntu/ precise/universe amd64 Packages\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "ipython                   - IPython: Productive Interactive Computing\r\n",
        "  INSTALLED: 1.0.dev\r\n",
        "  LATEST:    0.13.2\r\n"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "- Scientific libraries : [Numpy](http://www.numpy.org/), [Scipy](http://www.scipy.org/) and [Matplotlib](http://matplotlib.org/). Not really worth the trouble to install from source or `pip` (unless familiar with linear algebra `fortran/c++` libraries). Just install the current packages by `sudo apt-get python-matplotlib`."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!apt-cache policy python-numpy python-matplotlib python-scipy \n",
      "!pip search numpy | head -3\n",
      "!pip search scipy | head -3\n",
      "!pip search matplotlib | head -3"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "python-numpy:\r\n",
        "  Installed: 1:1.6.1-6ubuntu1\r\n",
        "  Candidate: 1:1.6.1-6ubuntu1\r\n",
        "  Version table:\r\n",
        " *** 1:1.6.1-6ubuntu1 0\r\n",
        "        500 http://gb.archive.ubuntu.com/ubuntu/ precise/main amd64 Packages\r\n",
        "        100 /var/lib/dpkg/status\r\n",
        "python-matplotlib:\r\n",
        "  Installed: 1.1.1~rc1+git20120423-0ubuntu1\r\n",
        "  Candidate: 1.1.1~rc1+git20120423-0ubuntu1\r\n",
        "  Version table:\r\n",
        " *** 1.1.1~rc1+git20120423-0ubuntu1 0\r\n",
        "        500 http://gb.archive.ubuntu.com/ubuntu/ precise/universe amd64 Packages\r\n",
        "        100 /var/lib/dpkg/status\r\n",
        "python-scipy:\r\n",
        "  Installed: 0.9.0+dfsg1-1ubuntu2\r\n",
        "  Candidate: 0.9.0+dfsg1-1ubuntu2\r\n",
        "  Version table:\r\n",
        " *** 0.9.0+dfsg1-1ubuntu2 0\r\n",
        "        500 http://gb.archive.ubuntu.com/ubuntu/ precise/universe amd64 Packages\r\n",
        "        100 /var/lib/dpkg/status\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "netCDF4                   - python/numpy interface to netCDF  library (versions 3 and 4)\r\n",
        "numpy                     - NumPy: array processing for numbers, strings, records, and objects.\r\n",
        "  INSTALLED: 1.7.1 (latest)\r\n",
        "close failed in file object destructor:\r\n",
        "sys.excepthook is missing\r\n",
        "lost sys.stderr\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "scipy                     - SciPy: Scientific Library for Python\r\n",
        "  INSTALLED: 0.9.0\r\n",
        "  LATEST:    0.12.0\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "matplotlib                - Python plotting package\r\n",
        "  INSTALLED: 1.1.1rc\r\n",
        "  LATEST:    1.2.1\r\n"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      " - It is worth getting the 0.13 version of the machine learning package [`sklearn`](scikit-learn.org) from that alternative debian [repository](http://neuro.debian.net/pkgs/python-sklearn.html) or from `pip`.\n",
      " - Same story for the recent and under heavy development `pandas` library for easy data manipulation and storage, using `pip` worked fine for me.   "
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!apt-cache policy python-sklearn\n",
      "!pip show pandas"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "python-sklearn:\r\n",
        "  Installed: 0.13-2~nd12.04+1\r\n",
        "  Candidate: 0.13-2~nd12.04+1\r\n",
        "  Version table:\r\n",
        " *** 0.13-2~nd12.04+1 0\r\n",
        "        500 http://neurodebian.g-node.org/ precise/main amd64 Packages\r\n",
        "        100 /var/lib/dpkg/status\r\n",
        "     0.10.0-1build1 0\r\n",
        "        500 http://gb.archive.ubuntu.com/ubuntu/ precise/universe amd64 Packages\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "---\r\n",
        "Name: pandas\r\n",
        "Version: 0.10.1\r\n",
        "Location: /usr/local/lib/python2.7/dist-packages\r\n",
        "Requires: python-dateutil, pytz, numpy\r\n"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Start-up\n",
      "\n",
      "Clone this notebook from this [GitHub Gist](https://gist.github.com/pilipolio/5626773) into a given directory and launch `ipython` from it:\n",
      "        \n",
      "    `git clone [email protected]:5626773.git quick_tour_notebook` or `git clone http://gist.github.com/5626773.git quick_tour_notebook` \n",
      "    `cd quick_tour_notebook`\n",
      "    `ipython notebook --pylab=inline`\n",
      "\n",
      "Then `Shift+Enter` to run the current cell and move to the next one. Double click one `markdown` cell to see the actual raw text. Press `tab` in code cells to prompt auto-completion.\n",
      "\n",
      "### The markdown syntax\n",
      "\n",
      "[`markdown`](http://daringfireball.net/projects/markdown) is a text-to-HTML conversion tool for web writers with a wiki-like syntax. [Stackoverflow](http://stackoverflow.com/editing-help) and [GitHub](https://help.github.com/articles/github-flavored-markdown) rely on it, with their own flavoured additions. [IPython notebooks](http://nbviewer.ipython.org/url/github.com/ipython/ipython/raw/master/examples/notebooks/Part%204%20-%20Markdown%20Cells.ipynb) enable to mix markdown and Latex syntaxes to produce (utlimately) publication quality [scientific articles or books](http://nbviewer.ipython.org/urls/raw.github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/master/Prologue/Prologue.ipynb). Latex is rendered through the javascript library [`mathjax`](http://www.mathjax.org). `markdown` and `mathjax` libraries may sometimes clash but that improves at each new release. Except those minor bugs, the full Latex language is implemented and a lot of packages are available and one can write fairly complex formulas like in a normal `.tex` document :\n",
      "\n",
      "$$P[a_i = k | x_i] = \\frac{P[a_i = k, x_i]}{P[x_i]} = \\frac{P[x_i | a_i = k ] P[a_i = k]}{\\sum \\limits_k^m P[x_i | a_i = k ]} = \\pi_k \\ \\frac{1}{|\\Sigma^k|} \\text{exp} \\Big( - \\frac{1}{2}(x_i - \\mu^k)^{T} \\Sigma_k^{-1} (x_i - \\mu^k) \\Big) \\frac{1}{\\sum \\limits_k^m \\ldots} $$\n",
      "\n",
      "\n",
      "### IPython special functions\n",
      "\n",
      "Magic functions `%%` and calling the shell using `!` :"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "! rm new_file.txt\n",
      "%%file new_file.txt\n",
      "Creating a new file\n",
      "within IPython"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Writing new_file.txt\n"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "directory_path = '.'\n",
      "! ls $directory_path"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "hello.py  MONTHLY  new_file.txt  quick_tour.ipynb\r\n"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# http://matplotlib.org/examples/pylab_examples/contour_demo.html\n",
      "%load http://matplotlib.org/mpl_examples/pylab_examples/major_minor_demo1.py"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#!/usr/bin/env python\n",
      "\"\"\"\n",
      "Demonstrate how to use major and minor tickers.\n",
      "\n",
      "The two relevant userland classes are Locators and Formatters.\n",
      "Locators determine where the ticks are and formatters control the\n",
      "formatting of ticks.\n",
      "\n",
      "Minor ticks are off by default (NullLocator and NullFormatter).  You\n",
      "can turn minor ticks on w/o labels by setting the minor locator.  You\n",
      "can also turn labeling on for the minor ticker by setting the minor\n",
      "formatter\n",
      "\n",
      "Make a plot with major ticks that are multiples of 20 and minor ticks\n",
      "that are multiples of 5.  Label major ticks with %d formatting but\n",
      "don't label minor ticks\n",
      "\n",
      "The MultipleLocator ticker class is used to place ticks on multiples of\n",
      "some base.  The FormatStrFormatter uses a string format string (eg\n",
      "'%d' or '%1.2f' or '%1.1f cm' ) to format the tick\n",
      "\n",
      "The pylab interface grid command changes the grid settings of the\n",
      "major ticks of the y and y axis together.  If you want to control the\n",
      "grid of the minor ticks for a given axis, use for example\n",
      "\n",
      "  ax.xaxis.grid(True, which='minor')\n",
      "\n",
      "Note, you should not use the same locator between different Axis\n",
      "because the locator stores references to the Axis data and view limits\n",
      "\n",
      "\"\"\"\n",
      "\n",
      "from pylab import *\n",
      "from matplotlib.ticker import MultipleLocator, FormatStrFormatter\n",
      "\n",
      "majorLocator   = MultipleLocator(20)\n",
      "majorFormatter = FormatStrFormatter('%d')\n",
      "minorLocator   = MultipleLocator(5)\n",
      "\n",
      "\n",
      "t = arange(0.0, 100.0, 0.1)\n",
      "s = sin(0.1*pi*t)*exp(-t*0.01)\n",
      "\n",
      "ax = subplot(111)\n",
      "plot(t,s)\n",
      "\n",
      "ax.xaxis.set_major_locator(majorLocator)\n",
      "ax.xaxis.set_major_formatter(majorFormatter)\n",
      "\n",
      "#for the minor ticks, use no labels; default NullFormatter\n",
      "ax.xaxis.set_minor_locator(minorLocator)\n",
      "\n",
      "show()\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAAD9CAYAAAC1DKAUAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x2ec08d0>"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%file hello.py\n",
      "hello_string = 'Hello world'\n",
      "print hello_string"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Overwriting hello.py\n"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%run hello.py\n",
      "hello_string"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Hello world\n"
       ]
      },
      {
       "output_type": "pyout",
       "prompt_number": 11,
       "text": [
        "'Hello world'"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%history 1-5"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "!apt-cache policy python\n",
        "!apt-cache policy python-pip\n",
        "!apt-cache policy ipython-notebook\n",
        "!pip search ipython | head -3\n",
        "!apt-cache policy python-numpy python-matplotlib python-scipy \n",
        "!pip search numpy | head -3\n",
        "!pip search scipy | head -3\n",
        "!pip search matplotlib | head -3\n",
        "!apt-cache policy python-sklearn\n",
        "!pip show pandas\n",
        "! rm new_file.txt\n",
        "%%file new_file.txt\n",
        "Creating a new file\n",
        "within IPython\n"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Numpy arrays and quick plotting\n",
      "\n",
      "Also `numpy` and `matplotlib.pyplot` contents are imported when using the `--pylab` option, it is a good habit to use the following import conventions : "
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from matplotlib import pyplot as plt\n",
      "import numpy as np\n",
      "a = np.array([[1, 2], [3, 4]])\n",
      "fig = plt.plot(a[0,:], a[1,:])\n",
      "a"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "array([[1, 2],\n",
        "       [3, 4]])"
       ]
      },
      {
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD9CAYAAABHnDf0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0x31237d0>"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### A demonstration of Pandas, the data-frame and time-series objects\n",
      "\n",
      "Hybrid between a `SQL` table and a 'numpy.array'\n",
      "\n",
      " - named columns and rows indexes;\n",
      " - `groupby` and `join` functions\n",
      " - good handling of missing values\n",
      " - originally developed for financial time-series analysis\n",
      " - active developement and well integrated within IPython "
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd\n",
      "df = pd.DataFrame(data=a, columns=['a', 'b'])\n",
      "df.ix[df['a']>1,:]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>a</th>\n",
        "      <th>b</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 3</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "   a  b\n",
        "1  3  4"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "! wget ftp://ftp.ngdc.noaa.gov/STP/SOLAR_DATA/SUNSPOT_NUMBERS/INTERNATIONAL/monthly/MONTHLY"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "--2013-05-31 09:58:13--  ftp://ftp.ngdc.noaa.gov/STP/SOLAR_DATA/SUNSPOT_NUMBERS/INTERNATIONAL/monthly/MONTHLY\r\n",
        "           => `MONTHLY.1'\r\n",
        "Resolving ftp.ngdc.noaa.gov (ftp.ngdc.noaa.gov)... 140.172.184.81\r\n",
        "Connecting to ftp.ngdc.noaa.gov (ftp.ngdc.noaa.gov)|140.172.184.81|:21... "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "connected.\r\n",
        "Logging in as anonymous ... "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Logged in!\r\n",
        "==> SYST ... "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "done.    ==> PWD ... "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "done.\r\n",
        "==> TYPE I ... "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "done.  ==> CWD (1) /STP/SOLAR_DATA/SUNSPOT_NUMBERS/INTERNATIONAL/monthly ... "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "done.\r\n",
        "==> SIZE MONTHLY ... "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "21503\r\n",
        "==> PASV ... "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "done.    ==> RETR MONTHLY ... "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "done.\r\n",
        "Length: 21503 (21K) (unauthoritative)\r\n",
        "\r\n",
        "\r",
        " 0% [                                       ] 0           --.-K/s              "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\r",
        "100%[======================================>] 21,503      --.-K/s   in 0.1s    \r\n",
        "\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "2013-05-31 09:58:14 (154 KB/s) - `MONTHLY.1' saved [21503]\r\n",
        "\r\n"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!head -6 MONTHLY"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "                          MONTHLY MEAN SUNSPOT NUMBERS                         \r\n",
        "===============================================================================\r\n",
        "Year    Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  \r\n",
        "-------------------------------------------------------------------------------\r\n",
        "1749    58.0  62.6  70.0  55.7  85.0  83.5  94.8  66.3  75.9  75.5 158.6  85.2\r\n",
        "1750    73.3  75.9  89.2  88.3  90.0 100.0  85.4 103.0  91.2  65.7  63.3  75.4\r\n"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!tail -10 MONTHLY"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "2010    13.2  18.8  15.4   8.0   8.7  13.6  16.1  19.6  25.2  23.5  21.5  14.4\r\n",
        "2011    18.8  29.6  55.8  54.4  41.6  37.0  43.8  50.6  78.0  88.0  96.7  73.0\r\n",
        "2012    58.3  32.9  64.3  55.2  69.0  64.5  66.5  63.0  61.4  53.3  61.8  40.8\r\n",
        "2013    62.9  38.0  57.9  72.4        \r\n",
        "-------------------------------------------------------------------------------\r\n",
        "No observations were available during February 1824.  The value shown was      \r\n",
        "interpolated from the January and March monthly means of that year.            \r\n",
        " \r\n",
        " \r\n",
        "Note:  Data are preliminary after Jun 2010.\r\n"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = pd.read_csv('MONTHLY', skiprows=[0,1,3], header=0, sep=' ', skipinitialspace=True, index_col='Year', nrows=265)\n",
      "df.ix[:,'Jan':'May'].head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>Jan</th>\n",
        "      <th>Feb</th>\n",
        "      <th>Mar</th>\n",
        "      <th>Apr</th>\n",
        "      <th>May</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Year</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>1749</th>\n",
        "      <td> 58.0</td>\n",
        "      <td> 62.6</td>\n",
        "      <td> 70.0</td>\n",
        "      <td> 55.7</td>\n",
        "      <td> 85.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1750</th>\n",
        "      <td> 73.3</td>\n",
        "      <td> 75.9</td>\n",
        "      <td> 89.2</td>\n",
        "      <td> 88.3</td>\n",
        "      <td> 90.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1751</th>\n",
        "      <td> 70.0</td>\n",
        "      <td> 43.5</td>\n",
        "      <td> 45.3</td>\n",
        "      <td> 56.4</td>\n",
        "      <td> 60.7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1752</th>\n",
        "      <td> 35.0</td>\n",
        "      <td> 50.0</td>\n",
        "      <td> 71.0</td>\n",
        "      <td> 59.3</td>\n",
        "      <td> 59.7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1753</th>\n",
        "      <td> 44.0</td>\n",
        "      <td> 32.0</td>\n",
        "      <td> 45.7</td>\n",
        "      <td> 38.0</td>\n",
        "      <td> 36.0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "output_type": "pyout",
       "prompt_number": 18,
       "text": [
        "       Jan   Feb   Mar   Apr   May\n",
        "Year                              \n",
        "1749  58.0  62.6  70.0  55.7  85.0\n",
        "1750  73.3  75.9  89.2  88.3  90.0\n",
        "1751  70.0  43.5  45.3  56.4  60.7\n",
        "1752  35.0  50.0  71.0  59.3  59.7\n",
        "1753  44.0  32.0  45.7  38.0  36.0"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "stacked_df = df.stack()\n",
      "stacked_df.head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "Year     \n",
        "1749  Jan    58.0\n",
        "      Feb    62.6\n",
        "      Mar    70.0\n",
        "      Apr    55.7\n",
        "      May    85.0"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "plt.figure(figsize=(18, 5))\n",
      "stacked_df.plot(color='grey', alpha=.8, lw=.25)\n",
      "pd.rolling_mean(stacked_df, 300).plot(style='-b',lw=2)\n",
      "yearly_mean = stacked_df.groupby(level=0).mean()\n",
      "reindex_yearly_mean = yearly_mean.reindex(stacked_df.index, level=0)\n",
      "reindex_yearly_mean.plot(color='green', alpha=.75);"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAABBUAAAFFCAYAAACzN9VXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAABJRU5ErkJggg==\n",
       "text": [
        "<matplotlib.figure.Figure at 0x3118550>"
       ]
      }
     ],
     "prompt_number": 20
    }
   ],
   "metadata": {}
  }
 ]
}