{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Bootcamp:  Demography\n",
    "\n",
    "**David Backus**\n",
    "\n",
    "We love demography, specifically the dynamics of population growth and decline.  You can drill down seemingly without end, as this [terrific graphic](http://www.bloomberg.com/graphics/dataview/how-americans-die/) about causes of death suggests.    \n",
    "\n",
    "We take a look here at the UN's [population data](http://esa.un.org/unpd/wpp/Download/Standard/Population/):  the age distribution of the population, life expectancy, fertility (the word we use for births), and mortality (deaths).  Explore the website, it's filled with interesting data.  There are other sources that cover longer time periods, and for some countries you can get detailed data on specific things (causes of death, for example).  \n",
    "\n",
    "We use a number of countries as examples, but Japan and China are the most striking.  The code is written so that the country is easily changed.  \n",
    "\n",
    "This IPython notebook was created by Dave Backus, Chase Coleman, and Spencer Lyon for the NYU Stern course [Data Bootcamp](http://databootcamp.nyuecon.com/).  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Preliminaries\n",
    "\n",
    "Import statements and a date check for future reference.   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Today is 2016-03-23\n",
      "What version of Python are we running? \n",
      "3.5.1 |Anaconda 2.5.0 (64-bit)| (default, Jan 29 2016, 15:01:46) [MSC v.1900 64 bit (AMD64)]\n"
     ]
    }
   ],
   "source": [
    "# import packages \n",
    "import pandas as pd                   # data management\n",
    "import matplotlib.pyplot as plt       # graphics \n",
    "import matplotlib as mpl              # graphics parameters\n",
    "import numpy as np                    # numerical calculations \n",
    "\n",
    "# IPython command, puts plots in notebook \n",
    "%matplotlib inline\n",
    "\n",
    "# check Python version \n",
    "import datetime as dt \n",
    "import sys\n",
    "print('Today is', dt.date.today())\n",
    "print('What version of Python are we running? \\n', sys.version, sep='') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## Population by age \n",
    "\n",
    "We have both \"estimates\" of the past (1950-2015) and \"projections\" of the future (out to 2100).  Here we focus on the latter, specifically what the UN refers to as the medium variant:  their middle of the road projection.  It gives us a sense of how Japan's population might change over the next century. \n",
    "\n",
    "It takes a few seconds to read the data.  \n",
    "\n",
    "What are the numbers?  Thousands of people in various 5-year age categories.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Major area, region, country or area *</th>\n",
       "      <th>Reference date (as of 1 July)</th>\n",
       "      <th>0-4</th>\n",
       "      <th>5-9</th>\n",
       "      <th>10-14</th>\n",
       "      <th>15-19</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>WORLD</td>\n",
       "      <td>2015</td>\n",
       "      <td>670928.185</td>\n",
       "      <td>637448.895</td>\n",
       "      <td>607431.299</td>\n",
       "      <td>590069.337</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>WORLD</td>\n",
       "      <td>2020</td>\n",
       "      <td>677599.590</td>\n",
       "      <td>664282.610</td>\n",
       "      <td>634568.409</td>\n",
       "      <td>604322.921</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>WORLD</td>\n",
       "      <td>2025</td>\n",
       "      <td>673174.914</td>\n",
       "      <td>671929.973</td>\n",
       "      <td>661684.410</td>\n",
       "      <td>631509.113</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Major area, region, country or area *  Reference date (as of 1 July)  \\\n",
       "0                                 WORLD                           2015   \n",
       "1                                 WORLD                           2020   \n",
       "2                                 WORLD                           2025   \n",
       "\n",
       "          0-4         5-9       10-14       15-19  \n",
       "0  670928.185  637448.895  607431.299  590069.337  \n",
       "1  677599.590  664282.610  634568.409  604322.921  \n",
       "2  673174.914  671929.973  661684.410  631509.113  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "url1 = 'http://esa.un.org/unpd/wpp/DVD/Files/'\n",
    "url2 = '1_Indicators%20(Standard)/EXCEL_FILES/1_Population/'\n",
    "url3 = 'WPP2015_POP_F07_1_POPULATION_BY_AGE_BOTH_SEXES.XLS'\n",
    "url = url1 + url2 + url3 \n",
    "\n",
    "cols = [2, 5] + list(range(6,28))\n",
    "#est = pd.read_excel(url, sheetname=0, skiprows=16, parse_cols=cols, na_values=['…'])\n",
    "prj = pd.read_excel(url, sheetname=1, skiprows=16, parse_cols=cols, na_values=['…'])\n",
    "\n",
    "prj.head(3)[list(range(6))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0-4</th>\n",
       "      <th>5-9</th>\n",
       "      <th>10-14</th>\n",
       "      <th>15-19</th>\n",
       "      <th>20-24</th>\n",
       "      <th>25-29</th>\n",
       "      <th>30-34</th>\n",
       "      <th>35-39</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",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>5.269038</td>\n",
       "      <td>5.398973</td>\n",
       "      <td>5.603638</td>\n",
       "      <td>5.960784</td>\n",
       "      <td>6.111768</td>\n",
       "      <td>6.843421</td>\n",
       "      <td>7.455687</td>\n",
       "      <td>8.345753</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2055</th>\n",
       "      <td>4.271907</td>\n",
       "      <td>4.371016</td>\n",
       "      <td>4.458145</td>\n",
       "      <td>4.557117</td>\n",
       "      <td>4.685414</td>\n",
       "      <td>4.829637</td>\n",
       "      <td>5.013420</td>\n",
       "      <td>5.236482</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2095</th>\n",
       "      <td>3.720541</td>\n",
       "      <td>3.789596</td>\n",
       "      <td>3.860493</td>\n",
       "      <td>3.938189</td>\n",
       "      <td>4.025477</td>\n",
       "      <td>4.106967</td>\n",
       "      <td>4.194272</td>\n",
       "      <td>4.290983</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           0-4       5-9     10-14     15-19     20-24     25-29     30-34  \\\n",
       "Year                                                                         \n",
       "2015  5.269038  5.398973  5.603638  5.960784  6.111768  6.843421  7.455687   \n",
       "2055  4.271907  4.371016  4.458145  4.557117  4.685414  4.829637  5.013420   \n",
       "2095  3.720541  3.789596  3.860493  3.938189  4.025477  4.106967  4.194272   \n",
       "\n",
       "         35-39  \n",
       "Year            \n",
       "2015  8.345753  \n",
       "2055  5.236482  \n",
       "2095  4.290983  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# rename some variables \n",
    "pop = prj \n",
    "names = list(pop) \n",
    "pop = pop.rename(columns={names[0]: 'Country', \n",
    "                          names[1]: 'Year'}) \n",
    "# select country and years \n",
    "country = ['Japan']\n",
    "years     = [2015, 2055, 2095]\n",
    "pop = pop[pop['Country'].isin(country) & pop['Year'].isin(years)]\n",
    "pop = pop.drop(['Country'], axis=1)\n",
    "\n",
    "# set index = Year \n",
    "# divide by 1000 to convert numbers from thousands to millions\n",
    "pop = pop.set_index('Year')/1000\n",
    "\n",
    "pop.head()[list(range(8))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Year</th>\n",
       "      <th>2015</th>\n",
       "      <th>2055</th>\n",
       "      <th>2095</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0-4</th>\n",
       "      <td>5.269038</td>\n",
       "      <td>4.271907</td>\n",
       "      <td>3.720541</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5-9</th>\n",
       "      <td>5.398973</td>\n",
       "      <td>4.371016</td>\n",
       "      <td>3.789596</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10-14</th>\n",
       "      <td>5.603638</td>\n",
       "      <td>4.458145</td>\n",
       "      <td>3.860493</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Year       2015      2055      2095\n",
       "0-4    5.269038  4.271907  3.720541\n",
       "5-9    5.398973  4.371016  3.789596\n",
       "10-14  5.603638  4.458145  3.860493"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# transpose (T) so that index = age \n",
    "pop = pop.T\n",
    "pop.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0xa259e10>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAewAAAGOCAYAAABVFjAxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nwRYREUkBFWwREZEUUMEWERFJgf8fl98VgYezMt0AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xcab75c0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = pop.plot(kind='bar',  \n",
    "              color='blue', \n",
    "              alpha=0.5, subplots=True, sharey=True, figsize=(8,6))\n",
    "\n",
    "for axnum in range(len(ax)):  \n",
    "    ax[axnum].set_title('')\n",
    "    ax[axnum].set_ylabel('Millions')\n",
    "        \n",
    "ax[0].set_title('Population by age', fontsize=14, loc='left')   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Exercise.** What do you see here?  What else would you like to know?  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Exercise.** Adapt the preceeding code to do the same thing for China.  Or some other country that sparks your interest.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fertility:  aka birth rates\n",
    "\n",
    "We might wonder, why is the population falling in Japan?  Other countries?  Well, one reason is that birth rates are falling.  Demographers call this fertility.  Here we look at the fertility using the same [UN source](http://esa.un.org/unpd/wpp/Download/Standard/Fertility/) as the previous example.  We look at two variables:  total fertility and fertility by age of mother.  In both cases we explore the numbers to date, but the same files contain projections of future fertility.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Major area, region, country or area *</th>\n",
       "      <th>1950-1955</th>\n",
       "      <th>1955-1960</th>\n",
       "      <th>1960-1965</th>\n",
       "      <th>1965-1970</th>\n",
       "      <th>1970-1975</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>WORLD</td>\n",
       "      <td>4.961571</td>\n",
       "      <td>4.898665</td>\n",
       "      <td>5.024379</td>\n",
       "      <td>4.922202</td>\n",
       "      <td>4.475478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>More developed regions</td>\n",
       "      <td>2.823786</td>\n",
       "      <td>2.807368</td>\n",
       "      <td>2.685900</td>\n",
       "      <td>2.387534</td>\n",
       "      <td>2.150816</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Less developed regions</td>\n",
       "      <td>6.075417</td>\n",
       "      <td>5.941033</td>\n",
       "      <td>6.129418</td>\n",
       "      <td>6.034843</td>\n",
       "      <td>5.416602</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Major area, region, country or area *  1950-1955  1955-1960  1960-1965  \\\n",
       "0                                 WORLD   4.961571   4.898665   5.024379   \n",
       "1                More developed regions   2.823786   2.807368   2.685900   \n",
       "2                Less developed regions   6.075417   5.941033   6.129418   \n",
       "\n",
       "   1965-1970  1970-1975  \n",
       "0   4.922202   4.475478  \n",
       "1   2.387534   2.150816  \n",
       "2   6.034843   5.416602  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# fertility overall \n",
    "uft  = 'http://esa.un.org/unpd/wpp/DVD/Files/'\n",
    "uft += '1_Indicators%20(Standard)/EXCEL_FILES/'\n",
    "uft += '2_Fertility/WPP2015_FERT_F04_TOTAL_FERTILITY.XLS'\n",
    "\n",
    "cols = [2] + list(range(5,18))\n",
    "ftot = pd.read_excel(uft, sheetname=0, skiprows=16, parse_cols=cols, na_values=['…'])\n",
    "\n",
    "ftot.head(3)[list(range(6))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Country</th>\n",
       "      <th>China</th>\n",
       "      <th>Japan</th>\n",
       "      <th>Germany</th>\n",
       "      <th>United States</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2000-2005</th>\n",
       "      <td>1.50</td>\n",
       "      <td>1.2980</td>\n",
       "      <td>1.3513</td>\n",
       "      <td>2.0420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2005-2010</th>\n",
       "      <td>1.53</td>\n",
       "      <td>1.3388</td>\n",
       "      <td>1.3623</td>\n",
       "      <td>2.0590</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-2015</th>\n",
       "      <td>1.55</td>\n",
       "      <td>1.3960</td>\n",
       "      <td>1.3909</td>\n",
       "      <td>1.8902</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Country    China   Japan  Germany  United States\n",
       "2000-2005   1.50  1.2980   1.3513         2.0420\n",
       "2005-2010   1.53  1.3388   1.3623         2.0590\n",
       "2010-2015   1.55  1.3960   1.3909         1.8902"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# rename some variables \n",
    "names = list(ftot)\n",
    "f = ftot.rename(columns={names[0]: 'Country'}) \n",
    "\n",
    "# select countries \n",
    "countries = ['China', 'Japan', 'Germany', 'United States of America']\n",
    "f = f[f['Country'].isin(countries)]\n",
    "\n",
    "# shape\n",
    "f = f.set_index('Country').T \n",
    "f = f.rename(columns={'United States of America': 'United States'})\n",
    "f.tail(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x92c4278>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAa8AAAELCAYAAABu5gn5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nhBg4ZF5CCCEGDpmXEEKIgeP/AeIUsOVSRjMsAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x928d860>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots()\n",
    "f.plot(ax=ax, kind='line', alpha=0.5, lw=3, figsize=(6.5, 4))\n",
    "ax.set_title('Fertility (births per woman, lifetime)', fontsize=14, loc='left')\n",
    "ax.legend(loc='best', fontsize=10, handlelength=2, labelspacing=0.15)\n",
    "ax.set_ylim(ymin=0)\n",
    "ax.hlines(2.1, -1, 13, linestyles='dashed')\n",
    "ax.text(8.5, 2.4, 'Replacement = 2.1')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Exercise.** What do you see here?  What else would you like to know?  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Exercise.** Add Canada to the figure.  How does it compare to the others?  What other countries would you be interested in?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Life expectancy \n",
    "\n",
    "One of the bottom line summary numbers for mortality is life expectancy:  if mortaility rates fall, people live longer, on average.  Here we look at life expectancy at birth.  There are also numbers for life expectancy given than you live to some specific age; for example, life expectancy given that you survive to age 60. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Major area, region, country or area *</th>\n",
       "      <th>1950-1955</th>\n",
       "      <th>1955-1960</th>\n",
       "      <th>1960-1965</th>\n",
       "      <th>1965-1970</th>\n",
       "      <th>1970-1975</th>\n",
       "      <th>1975-1980</th>\n",
       "      <th>1980-1985</th>\n",
       "      <th>1985-1990</th>\n",
       "      <th>1990-1995</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>WORLD</td>\n",
       "      <td>46.807955</td>\n",
       "      <td>49.211594</td>\n",
       "      <td>51.069722</td>\n",
       "      <td>55.378481</td>\n",
       "      <td>58.049389</td>\n",
       "      <td>60.212254</td>\n",
       "      <td>61.989053</td>\n",
       "      <td>63.610776</td>\n",
       "      <td>64.536781</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>More developed regions</td>\n",
       "      <td>64.669835</td>\n",
       "      <td>67.679537</td>\n",
       "      <td>69.440381</td>\n",
       "      <td>70.281907</td>\n",
       "      <td>71.063794</td>\n",
       "      <td>71.960446</td>\n",
       "      <td>72.806852</td>\n",
       "      <td>73.901457</td>\n",
       "      <td>74.107521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Less developed regions</td>\n",
       "      <td>41.508118</td>\n",
       "      <td>43.882493</td>\n",
       "      <td>46.017378</td>\n",
       "      <td>51.441078</td>\n",
       "      <td>54.770858</td>\n",
       "      <td>57.342650</td>\n",
       "      <td>59.418113</td>\n",
       "      <td>61.229860</td>\n",
       "      <td>62.453399</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Major area, region, country or area *  1950-1955  1955-1960  1960-1965  \\\n",
       "0                                 WORLD  46.807955  49.211594  51.069722   \n",
       "1                More developed regions  64.669835  67.679537  69.440381   \n",
       "2                Less developed regions  41.508118  43.882493  46.017378   \n",
       "\n",
       "   1965-1970  1970-1975  1975-1980  1980-1985  1985-1990  1990-1995  \n",
       "0  55.378481  58.049389  60.212254  61.989053  63.610776  64.536781  \n",
       "1  70.281907  71.063794  71.960446  72.806852  73.901457  74.107521  \n",
       "2  51.441078  54.770858  57.342650  59.418113  61.229860  62.453399  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# life expectancy at birth, both sexes  \n",
    "ule  = 'http://esa.un.org/unpd/wpp/DVD/Files/1_Indicators%20(Standard)/EXCEL_FILES/3_Mortality/'\n",
    "ule += 'WPP2015_MORT_F07_1_LIFE_EXPECTANCY_0_BOTH_SEXES.XLS'\n",
    "\n",
    "cols = [2] + list(range(5,34))\n",
    "le  = pd.read_excel(ule, sheetname=0, skiprows=16, parse_cols=cols, na_values=['…'])\n",
    "\n",
    "le.head(3)[list(range(10))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Country</th>\n",
       "      <th>1950-1955</th>\n",
       "      <th>1955-1960</th>\n",
       "      <th>1960-1965</th>\n",
       "      <th>1965-1970</th>\n",
       "      <th>1970-1975</th>\n",
       "      <th>1975-1980</th>\n",
       "      <th>1980-1985</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>WORLD</td>\n",
       "      <td>46.807955</td>\n",
       "      <td>49.211594</td>\n",
       "      <td>51.069722</td>\n",
       "      <td>55.378481</td>\n",
       "      <td>58.049389</td>\n",
       "      <td>60.212254</td>\n",
       "      <td>61.989053</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>More developed regions</td>\n",
       "      <td>64.669835</td>\n",
       "      <td>67.679537</td>\n",
       "      <td>69.440381</td>\n",
       "      <td>70.281907</td>\n",
       "      <td>71.063794</td>\n",
       "      <td>71.960446</td>\n",
       "      <td>72.806852</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Less developed regions</td>\n",
       "      <td>41.508118</td>\n",
       "      <td>43.882493</td>\n",
       "      <td>46.017378</td>\n",
       "      <td>51.441078</td>\n",
       "      <td>54.770858</td>\n",
       "      <td>57.342650</td>\n",
       "      <td>59.418113</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  Country  1950-1955  1955-1960  1960-1965  1965-1970  \\\n",
       "0                   WORLD  46.807955  49.211594  51.069722  55.378481   \n",
       "1  More developed regions  64.669835  67.679537  69.440381  70.281907   \n",
       "2  Less developed regions  41.508118  43.882493  46.017378  51.441078   \n",
       "\n",
       "   1970-1975  1975-1980  1980-1985  \n",
       "0  58.049389  60.212254  61.989053  \n",
       "1  71.063794  71.960446  72.806852  \n",
       "2  54.770858  57.342650  59.418113  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# rename some variables \n",
    "oldname = list(le)[0]\n",
    "l = le.rename(columns={oldname: 'Country'}) \n",
    "l.head(3)[list(range(8))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Country</th>\n",
       "      <th>China</th>\n",
       "      <th>Japan</th>\n",
       "      <th>Germany</th>\n",
       "      <th>United States</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1990-1995</th>\n",
       "      <td>69.386</td>\n",
       "      <td>79.447</td>\n",
       "      <td>75.878</td>\n",
       "      <td>75.617</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1995-2000</th>\n",
       "      <td>70.587</td>\n",
       "      <td>80.475</td>\n",
       "      <td>77.212</td>\n",
       "      <td>76.404</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-2005</th>\n",
       "      <td>72.852</td>\n",
       "      <td>81.829</td>\n",
       "      <td>78.573</td>\n",
       "      <td>77.133</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2005-2010</th>\n",
       "      <td>74.438</td>\n",
       "      <td>82.621</td>\n",
       "      <td>79.757</td>\n",
       "      <td>78.113</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-2015</th>\n",
       "      <td>75.432</td>\n",
       "      <td>83.298</td>\n",
       "      <td>80.647</td>\n",
       "      <td>78.873</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Country     China   Japan  Germany  United States\n",
       "1990-1995  69.386  79.447   75.878         75.617\n",
       "1995-2000  70.587  80.475   77.212         76.404\n",
       "2000-2005  72.852  81.829   78.573         77.133\n",
       "2005-2010  74.438  82.621   79.757         78.113\n",
       "2010-2015  75.432  83.298   80.647         78.873"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# select countries \n",
    "countries = ['China', 'Japan', 'Germany', 'United States of America']\n",
    "l = l[l['Country'].isin(countries)]\n",
    "\n",
    "# shape\n",
    "l = l.set_index('Country').T \n",
    "l = l.rename(columns={'United States of America': 'United States'})\n",
    "l.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(0, 85.0)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZgAAAHqCAYAAAA50VifAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x92fbb00>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots()\n",
    "l.plot(ax=ax, kind='line', alpha=0.5, lw=3, figsize=(6, 8), grid=True)\n",
    "ax.set_title('Life expectancy at birth', fontsize=14, loc='left')\n",
    "ax.set_ylabel('Life expectancy in years')\n",
    "ax.legend(loc='best', fontsize=10, handlelength=2, labelspacing=0.15)\n",
    "ax.set_ylim(ymin=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Exercise.** What other countries would you like to see?  Can you add them?  The code below generates a list.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "countries = le.rename(columns={oldname: 'Country'})['Country']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Exercise.**  Why do you think the US is falling behind?  What would you look at to verify your conjecture?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "## Mortality:  aka death rates \n",
    "\n",
    "Another thing that affects the age distribution of the population is the mortality rate:  if mortality rates fall people live longer, on average.  Here we look at how mortality rates have changed over the past 60+ years.  Roughly speaking, people live an extra five years every generation.  Which is a lot.  Some of you will live to be a hundred.  (Look at the 100+ agen category over time for Japan.)  \n",
    "\n",
    "The experts look at mortality rates by age.  The UN has a [whole page](http://esa.un.org/unpd/wpp/Download/Standard/Mortality/) devoted to mortality numbers.  We take 5-year mortality rates from the Abridged Life Table.  \n",
    "\n",
    "The numbers are percentages of people in a given age group who die over a 5-year period.  0.1 means that 90 percent of an age group is still alive in five years.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Major area, region, country or area *</th>\n",
       "      <th>Period</th>\n",
       "      <th>Age (x)</th>\n",
       "      <th>Age interval (n)</th>\n",
       "      <th>Probability of dying q(x,n)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>59524</th>\n",
       "      <td>Tonga</td>\n",
       "      <td>2010-2015</td>\n",
       "      <td>75</td>\n",
       "      <td>5</td>\n",
       "      <td>0.279867</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>59525</th>\n",
       "      <td>Tonga</td>\n",
       "      <td>2010-2015</td>\n",
       "      <td>80</td>\n",
       "      <td>5</td>\n",
       "      <td>0.397735</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>59526</th>\n",
       "      <td>Tonga</td>\n",
       "      <td>2010-2015</td>\n",
       "      <td>85</td>\n",
       "      <td>15</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Major area, region, country or area *     Period  Age (x)  \\\n",
       "59524                                 Tonga  2010-2015       75   \n",
       "59525                                 Tonga  2010-2015       80   \n",
       "59526                                 Tonga  2010-2015       85   \n",
       "\n",
       "       Age interval (n)  Probability of dying q(x,n)  \n",
       "59524                 5                     0.279867  \n",
       "59525                 5                     0.397735  \n",
       "59526                15                          NaN  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# mortality overall \n",
    "url  = 'http://esa.un.org/unpd/wpp/DVD/Files/'\n",
    "url += '1_Indicators%20(Standard)/EXCEL_FILES/3_Mortality/'\n",
    "url += 'WPP2015_MORT_F17_1_ABRIDGED_LIFE_TABLE_BOTH_SEXES.XLS'\n",
    "\n",
    "cols = [2, 5, 6, 7, 9]\n",
    "mort = pd.read_excel(url, sheetname=0, skiprows=16, parse_cols=cols, na_values=['…'])\n",
    "mort.tail(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Country</th>\n",
       "      <th>Period</th>\n",
       "      <th>Age</th>\n",
       "      <th>Interval</th>\n",
       "      <th>Mortality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>WORLD</td>\n",
       "      <td>1950-1955</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.141804</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>WORLD</td>\n",
       "      <td>1950-1955</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>0.085487</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>WORLD</td>\n",
       "      <td>1950-1955</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>0.031513</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Country     Period  Age  Interval  Mortality\n",
       "0   WORLD  1950-1955    0         1   0.141804\n",
       "1   WORLD  1950-1955    1         4   0.085487\n",
       "2   WORLD  1950-1955    5         5   0.031513"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# change names \n",
    "names = list(mort)\n",
    "m = mort.rename(columns={names[0]: 'Country', names[2]: 'Age', names[3]: 'Interval', names[4]: 'Mortality'})\n",
    "m.head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Comment.** At this point, we need to pivot the data.  That's not something we've done before, so take it as simply something we can do easily if we have to.  We're going to do this twice to produce different graphs:    \n",
    "\n",
    "* Compare countries for the same period.  \n",
    "* Compare different periods for the same country.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dimensions: (64, 5)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Country</th>\n",
       "      <th>China</th>\n",
       "      <th>Germany</th>\n",
       "      <th>Japan</th>\n",
       "      <th>United States of America</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.001756</td>\n",
       "      <td>0.000397</td>\n",
       "      <td>0.000462</td>\n",
       "      <td>0.000597</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.001286</td>\n",
       "      <td>0.000456</td>\n",
       "      <td>0.000437</td>\n",
       "      <td>0.000714</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>0.001844</td>\n",
       "      <td>0.001300</td>\n",
       "      <td>0.001141</td>\n",
       "      <td>0.002264</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Country     China   Germany     Japan  United States of America\n",
       "Age                                                            \n",
       "5        0.001756  0.000397  0.000462                  0.000597\n",
       "10       0.001286  0.000456  0.000437                  0.000714\n",
       "15       0.001844  0.001300  0.001141                  0.002264"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# compare countries for most recent period\n",
    "countries = ['China', 'Japan', 'Germany', 'United States of America']\n",
    "mt = m[m['Country'].isin(countries) & m['Interval'].isin([5]) & m['Period'].isin(['2010-2015'])] \n",
    "print('Dimensions:', mt.shape) \n",
    "\n",
    "mp = mt.pivot(index='Age', columns='Country', values='Mortality')  \n",
    "mp.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x9191390>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYwAAAEaCAYAAAACBmAUAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nZhiGYRjGkvh/MxOUUkZgBgIAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x9191cc0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots()\n",
    "mp.plot(ax=ax, kind='line', alpha=0.5, linewidth=3, \n",
    "#        logy=True, \n",
    "        figsize=(6, 4))\n",
    "ax.set_title('Mortality by age', fontsize=14, loc='left')\n",
    "ax.set_ylabel('Mortality Rate (log scale)')\n",
    "ax.legend(loc='best', fontsize=10, handlelength=2, labelspacing=0.15)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Exercises.**\n",
    "\n",
    "* What country's old people have the lowest mortality?\n",
    "* What do you see here for the US?  Why is our life expectancy shorter?\n",
    "* What other countries would you like to see?  Can you adapt the code to show them?  \n",
    "* Anything else cross your mind?  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dimensions: (208, 5)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Period</th>\n",
       "      <th>1950-1955</th>\n",
       "      <th>1980-1985</th>\n",
       "      <th>2010-2015</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.043088</td>\n",
       "      <td>0.006487</td>\n",
       "      <td>0.001756</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.025641</td>\n",
       "      <td>0.003300</td>\n",
       "      <td>0.001286</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>0.026845</td>\n",
       "      <td>0.004172</td>\n",
       "      <td>0.001844</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Period  1950-1955  1980-1985  2010-2015\n",
       "Age                                    \n",
       "5        0.043088   0.006487   0.001756\n",
       "10       0.025641   0.003300   0.001286\n",
       "15       0.026845   0.004172   0.001844"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# compare periods for the one country -- countries[0] is China \n",
    "mt = m[m['Country'].isin([countries[0]]) & m['Interval'].isin([5])] \n",
    "print('Dimensions:', mt.shape) \n",
    "\n",
    "mp = mt.pivot(index='Age', columns='Period', values='Mortality')  \n",
    "mp = mp[[0, 6, 12]]\n",
    "mp.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0xd7d7dd8>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAEaCAYAAAAVJPDdAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xdae0a58>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots()\n",
    "mp.plot(ax=ax, kind='line', alpha=0.5, linewidth=3, \n",
    "#        logy=True, \n",
    "        figsize=(6, 4))\n",
    "ax.set_title('Mortality over time', fontsize=14, loc='left')\n",
    "ax.set_ylabel('Mortality Rate (log scale)')\n",
    "ax.legend(loc='best', fontsize=10, handlelength=2, labelspacing=0.15)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "**Exercise.**  What do you see?  What else would you like to know?  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "**Exercise.** Repeat this graph for the United States?  How does it compare?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.5.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}