Skip to content

Instantly share code, notes, and snippets.

@natashawatkins

natashawatkins/pandas-panel.ipynb

Last active April 7, 2017 02:07
Show Gist options
  • Save natashawatkins/b177082057c6143a53587c175e90ccc3 to your computer and use it in GitHub Desktop.
Save natashawatkins/b177082057c6143a53587c175e90ccc3 to your computer and use it in GitHub Desktop.
Download ZIP
Pandas panel lecture
Display the source blob
Display the rendered blob
Raw
pandas-panel.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Pandas for Panel Data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Econometricians often need to work with panel data and large datasets more generally. Common tasks include\n",
"* Importing data, cleaning it and reshaping it across several axes\n",
"* Selecting a time series or cross-section from a panel\n",
"* Grouping and summarising data\n",
"\n",
"``pandas`` (derived from 'panel' and 'data') contains powerful and easy-to-use tools for solving exactly these kinds of problems\n",
"\n",
"To illustrate this, in what follows, we will use a panel dataset of real minimum wages from the OECD to create:\n",
"* summary statistics over multiple dimensions of our data\n",
"* a time series of the average minimum wage of countries in the dataset\n",
"* kernel density estimates of wages by continent\n",
"\n",
"We will begin by reading in our data using ``pandas-datareader`` and reshaping the resulting ``DataFrame`` with a ``MultiIndex``\n",
"\n",
"Additional detail will be added to our ``DataFrame`` using pandas' ``merge`` function, and data will be summarised with the ``groupby`` function"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Slicing and reshaping data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"As discussed in the previous lecture, we can access online data sources such as the OECD with the [pandas-datareader package](https://pandas-datareader.readthedocs.io/)\n",
"\n",
"We will read in a dataset from the OECD of real minimum wages in 32 countries (series code is ``RMW``) and assign it to ``realwage``\n",
"\n",
"Note that ``.head()`` will be used to display only the first few rows of a dataframe (by default, the first 5 rows are displayed)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>Country</th>\n",
" <th colspan=\"3\" halign=\"left\">Ireland</th>\n",
" <th>...</th>\n",
" <th colspan=\"3\" halign=\"left\">Costa Rica</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Series</th>\n",
" <th colspan=\"2\" halign=\"left\">In 2015 constant prices at 2015 USD PPPs</th>\n",
" <th>In 2015 constant prices at 2015 USD exchange rates</th>\n",
" <th>...</th>\n",
" <th>In 2015 constant prices at 2015 USD PPPs</th>\n",
" <th colspan=\"2\" halign=\"left\">In 2015 constant prices at 2015 USD exchange rates</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Pay period</th>\n",
" <th>Annual</th>\n",
" <th>Hourly</th>\n",
" <th>Annual</th>\n",
" <th>...</th>\n",
" <th>Hourly</th>\n",
" <th>Annual</th>\n",
" <th>Hourly</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Time</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>2006-01-01</th>\n",
" <td>17,132.44</td>\n",
" <td>8.24</td>\n",
" <td>19,090.54</td>\n",
" <td>...</td>\n",
" <td>nan</td>\n",
" <td>nan</td>\n",
" <td>nan</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-01-01</th>\n",
" <td>18,100.92</td>\n",
" <td>8.70</td>\n",
" <td>20,169.70</td>\n",
" <td>...</td>\n",
" <td>nan</td>\n",
" <td>nan</td>\n",
" <td>nan</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-01</th>\n",
" <td>17,747.41</td>\n",
" <td>8.53</td>\n",
" <td>19,775.78</td>\n",
" <td>...</td>\n",
" <td>nan</td>\n",
" <td>nan</td>\n",
" <td>nan</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-01-01</th>\n",
" <td>18,580.14</td>\n",
" <td>8.93</td>\n",
" <td>20,703.69</td>\n",
" <td>...</td>\n",
" <td>nan</td>\n",
" <td>nan</td>\n",
" <td>nan</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2010-01-01</th>\n",
" <td>18,755.83</td>\n",
" <td>9.02</td>\n",
" <td>20,899.47</td>\n",
" <td>...</td>\n",
" <td>nan</td>\n",
" <td>nan</td>\n",
" <td>nan</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 128 columns</p>\n",
"</div>"
],
"text/plain": [
"Country Ireland \\\n",
"Series In 2015 constant prices at 2015 USD PPPs \n",
"Pay period Annual Hourly \n",
"Time \n",
"2006-01-01 17,132.44 8.24 \n",
"2007-01-01 18,100.92 8.70 \n",
"2008-01-01 17,747.41 8.53 \n",
"2009-01-01 18,580.14 8.93 \n",
"2010-01-01 18,755.83 9.02 \n",
"\n",
"Country ... \\\n",
"Series In 2015 constant prices at 2015 USD exchange rates ... \n",
"Pay period Annual ... \n",
"Time ... \n",
"2006-01-01 19,090.54 ... \n",
"2007-01-01 20,169.70 ... \n",
"2008-01-01 19,775.78 ... \n",
"2009-01-01 20,703.69 ... \n",
"2010-01-01 20,899.47 ... \n",
"\n",
"Country Costa Rica \\\n",
"Series In 2015 constant prices at 2015 USD PPPs \n",
"Pay period Hourly \n",
"Time \n",
"2006-01-01 nan \n",
"2007-01-01 nan \n",
"2008-01-01 nan \n",
"2009-01-01 nan \n",
"2010-01-01 nan \n",
"\n",
"Country \n",
"Series In 2015 constant prices at 2015 USD exchange rates \n",
"Pay period Annual Hourly \n",
"Time \n",
"2006-01-01 nan nan \n",
"2007-01-01 nan nan \n",
"2008-01-01 nan nan \n",
"2009-01-01 nan nan \n",
"2010-01-01 nan nan \n",
"\n",
"[5 rows x 128 columns]"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"import pandas_datareader.data as web\n",
"import datetime as dt\n",
"\n",
"pd.set_option('display.max_columns', 6) # display 6 columns for viewing purposes\n",
"pd.options.display.float_format = '{:,.2f}'.format # reduce decimal points to 2\n",
"\n",
"start, end = dt.datetime(2006, 1, 1), dt.datetime(2016, 1, 1)\n",
"realwage = web.DataReader('RMW', 'oecd', start, end)\n",
"realwage.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The ``DataFrame`` has a ``DatetimeIndex``"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"pandas.tseries.index.DatetimeIndex"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(realwage.index)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The columns contain multiple levels of indexing, known as a ``MultiIndex``, with levels being ordered hierarchially (Country > Series > Pay period)\n",
"\n",
"A ``MultiIndex`` is the simplest and most flexible way to manage panel data in pandas (the other option is to use the ``panel`` data structure)\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"pandas.indexes.multi.MultiIndex"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(realwage.columns)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"FrozenList(['Country', 'Series', 'Pay period'])"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"realwage.columns.names"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Like before, we can select the country (the top level of our ``MultiIndex``)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>Series</th>\n",
" <th colspan=\"2\" halign=\"left\">In 2015 constant prices at 2015 USD PPPs</th>\n",
" <th colspan=\"2\" halign=\"left\">In 2015 constant prices at 2015 USD exchange rates</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Pay period</th>\n",
" <th>Annual</th>\n",
" <th>Hourly</th>\n",
" <th>Annual</th>\n",
" <th>Hourly</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Time</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2006-01-01</th>\n",
" <td>12,594.40</td>\n",
" <td>6.05</td>\n",
" <td>12,594.40</td>\n",
" <td>6.05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-01-01</th>\n",
" <td>12,974.40</td>\n",
" <td>6.24</td>\n",
" <td>12,974.40</td>\n",
" <td>6.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-01</th>\n",
" <td>14,097.56</td>\n",
" <td>6.78</td>\n",
" <td>14,097.56</td>\n",
" <td>6.78</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-01-01</th>\n",
" <td>15,756.42</td>\n",
" <td>7.58</td>\n",
" <td>15,756.42</td>\n",
" <td>7.58</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2010-01-01</th>\n",
" <td>16,391.31</td>\n",
" <td>7.88</td>\n",
" <td>16,391.31</td>\n",
" <td>7.88</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Series In 2015 constant prices at 2015 USD PPPs \\\n",
"Pay period Annual Hourly \n",
"Time \n",
"2006-01-01 12,594.40 6.05 \n",
"2007-01-01 12,974.40 6.24 \n",
"2008-01-01 14,097.56 6.78 \n",
"2009-01-01 15,756.42 7.58 \n",
"2010-01-01 16,391.31 7.88 \n",
"\n",
"Series In 2015 constant prices at 2015 USD exchange rates \n",
"Pay period Annual Hourly \n",
"Time \n",
"2006-01-01 12,594.40 6.05 \n",
"2007-01-01 12,974.40 6.24 \n",
"2008-01-01 14,097.56 6.78 \n",
"2009-01-01 15,756.42 7.58 \n",
"2010-01-01 16,391.31 7.88 "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"realwage['United States'].head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We will want to sort the ``MultiIndex`` by calling ``.sortlevel()`` on the dataframe, so we can filter our data efficiently later\n",
"\n",
"By default, levels will be sorted top-down\n",
"\n",
"Note the difference between viewing and overwriting a dataframe: the above selection of 'United States' merely viewed a filtered version of ``realwage`` while keeping the underlying structure in tact\n",
"\n",
"In the following case, ``.sortlevel()`` is called and ``realwage`` is reassigned to the resulting dataframe, overwriting our original dataframe"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>Country</th>\n",
" <th colspan=\"3\" halign=\"left\">Australia</th>\n",
" <th>...</th>\n",
" <th colspan=\"3\" halign=\"left\">United States</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Series</th>\n",
" <th colspan=\"2\" halign=\"left\">In 2015 constant prices at 2015 USD PPPs</th>\n",
" <th>In 2015 constant prices at 2015 USD exchange rates</th>\n",
" <th>...</th>\n",
" <th>In 2015 constant prices at 2015 USD PPPs</th>\n",
" <th colspan=\"2\" halign=\"left\">In 2015 constant prices at 2015 USD exchange rates</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Pay period</th>\n",
" <th>Annual</th>\n",
" <th>Hourly</th>\n",
" <th>Annual</th>\n",
" <th>...</th>\n",
" <th>Hourly</th>\n",
" <th>Annual</th>\n",
" <th>Hourly</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Time</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>2006-01-01</th>\n",
" <td>20,410.65</td>\n",
" <td>10.33</td>\n",
" <td>23,826.64</td>\n",
" <td>...</td>\n",
" <td>6.05</td>\n",
" <td>12,594.40</td>\n",
" <td>6.05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-01-01</th>\n",
" <td>21,087.57</td>\n",
" <td>10.67</td>\n",
" <td>24,616.84</td>\n",
" <td>...</td>\n",
" <td>6.24</td>\n",
" <td>12,974.40</td>\n",
" <td>6.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-01</th>\n",
" <td>20,718.24</td>\n",
" <td>10.48</td>\n",
" <td>24,185.70</td>\n",
" <td>...</td>\n",
" <td>6.78</td>\n",
" <td>14,097.56</td>\n",
" <td>6.78</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-01-01</th>\n",
" <td>20,984.77</td>\n",
" <td>10.62</td>\n",
" <td>24,496.84</td>\n",
" <td>...</td>\n",
" <td>7.58</td>\n",
" <td>15,756.42</td>\n",
" <td>7.58</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2010-01-01</th>\n",
" <td>20,879.33</td>\n",
" <td>10.57</td>\n",
" <td>24,373.76</td>\n",
" <td>...</td>\n",
" <td>7.88</td>\n",
" <td>16,391.31</td>\n",
" <td>7.88</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 128 columns</p>\n",
"</div>"
],
"text/plain": [
"Country Australia \\\n",
"Series In 2015 constant prices at 2015 USD PPPs \n",
"Pay period Annual Hourly \n",
"Time \n",
"2006-01-01 20,410.65 10.33 \n",
"2007-01-01 21,087.57 10.67 \n",
"2008-01-01 20,718.24 10.48 \n",
"2009-01-01 20,984.77 10.62 \n",
"2010-01-01 20,879.33 10.57 \n",
"\n",
"Country ... \\\n",
"Series In 2015 constant prices at 2015 USD exchange rates ... \n",
"Pay period Annual ... \n",
"Time ... \n",
"2006-01-01 23,826.64 ... \n",
"2007-01-01 24,616.84 ... \n",
"2008-01-01 24,185.70 ... \n",
"2009-01-01 24,496.84 ... \n",
"2010-01-01 24,373.76 ... \n",
"\n",
"Country United States \\\n",
"Series In 2015 constant prices at 2015 USD PPPs \n",
"Pay period Hourly \n",
"Time \n",
"2006-01-01 6.05 \n",
"2007-01-01 6.24 \n",
"2008-01-01 6.78 \n",
"2009-01-01 7.58 \n",
"2010-01-01 7.88 \n",
"\n",
"Country \n",
"Series In 2015 constant prices at 2015 USD exchange rates \n",
"Pay period Annual Hourly \n",
"Time \n",
"2006-01-01 12,594.40 6.05 \n",
"2007-01-01 12,974.40 6.24 \n",
"2008-01-01 14,097.56 6.78 \n",
"2009-01-01 15,756.42 7.58 \n",
"2010-01-01 16,391.31 7.88 \n",
"\n",
"[5 rows x 128 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"realwage = realwage.sortlevel(axis=1)\n",
"realwage.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Stacking and unstacking levels of the ``MultiIndex`` will be used throughout this lecture to reshape our dataframe into a format we need\n",
"\n",
"``.stack()`` rotates the lowest level of the column ``MultiIndex`` to the row index (``.unstack()`` works in the opposite direction - try it out)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>Country</th>\n",
" <th colspan=\"2\" halign=\"left\">Australia</th>\n",
" <th>Belgium</th>\n",
" <th>...</th>\n",
" <th>United Kingdom</th>\n",
" <th colspan=\"2\" halign=\"left\">United States</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>Series</th>\n",
" <th>In 2015 constant prices at 2015 USD PPPs</th>\n",
" <th>In 2015 constant prices at 2015 USD exchange rates</th>\n",
" <th>In 2015 constant prices at 2015 USD PPPs</th>\n",
" <th>...</th>\n",
" <th>In 2015 constant prices at 2015 USD exchange rates</th>\n",
" <th>In 2015 constant prices at 2015 USD PPPs</th>\n",
" <th>In 2015 constant prices at 2015 USD exchange rates</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Time</th>\n",
" <th>Pay period</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 rowspan=\"2\" valign=\"top\">2006-01-01</th>\n",
" <th>Annual</th>\n",
" <td>20,410.65</td>\n",
" <td>23,826.64</td>\n",
" <td>21,042.28</td>\n",
" <td>...</td>\n",
" <td>20,376.32</td>\n",
" <td>12,594.40</td>\n",
" <td>12,594.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Hourly</th>\n",
" <td>10.33</td>\n",
" <td>12.06</td>\n",
" <td>10.09</td>\n",
" <td>...</td>\n",
" <td>9.81</td>\n",
" <td>6.05</td>\n",
" <td>6.05</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">2007-01-01</th>\n",
" <th>Annual</th>\n",
" <td>21,087.57</td>\n",
" <td>24,616.84</td>\n",
" <td>21,310.05</td>\n",
" <td>...</td>\n",
" <td>20,954.13</td>\n",
" <td>12,974.40</td>\n",
" <td>12,974.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Hourly</th>\n",
" <td>10.67</td>\n",
" <td>12.46</td>\n",
" <td>10.22</td>\n",
" <td>...</td>\n",
" <td>10.07</td>\n",
" <td>6.24</td>\n",
" <td>6.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-01</th>\n",
" <th>Annual</th>\n",
" <td>20,718.24</td>\n",
" <td>24,185.70</td>\n",
" <td>21,416.96</td>\n",
" <td>...</td>\n",
" <td>20,902.87</td>\n",
" <td>14,097.56</td>\n",
" <td>14,097.56</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 64 columns</p>\n",
"</div>"
],
"text/plain": [
"Country Australia \\\n",
"Series In 2015 constant prices at 2015 USD PPPs \n",
"Time Pay period \n",
"2006-01-01 Annual 20,410.65 \n",
" Hourly 10.33 \n",
"2007-01-01 Annual 21,087.57 \n",
" Hourly 10.67 \n",
"2008-01-01 Annual 20,718.24 \n",
"\n",
"Country \\\n",
"Series In 2015 constant prices at 2015 USD exchange rates \n",
"Time Pay period \n",
"2006-01-01 Annual 23,826.64 \n",
" Hourly 12.06 \n",
"2007-01-01 Annual 24,616.84 \n",
" Hourly 12.46 \n",
"2008-01-01 Annual 24,185.70 \n",
"\n",
"Country Belgium \\\n",
"Series In 2015 constant prices at 2015 USD PPPs \n",
"Time Pay period \n",
"2006-01-01 Annual 21,042.28 \n",
" Hourly 10.09 \n",
"2007-01-01 Annual 21,310.05 \n",
" Hourly 10.22 \n",
"2008-01-01 Annual 21,416.96 \n",
"\n",
"Country ... \\\n",
"Series ... \n",
"Time Pay period ... \n",
"2006-01-01 Annual ... \n",
" Hourly ... \n",
"2007-01-01 Annual ... \n",
" Hourly ... \n",
"2008-01-01 Annual ... \n",
"\n",
"Country United Kingdom \\\n",
"Series In 2015 constant prices at 2015 USD exchange rates \n",
"Time Pay period \n",
"2006-01-01 Annual 20,376.32 \n",
" Hourly 9.81 \n",
"2007-01-01 Annual 20,954.13 \n",
" Hourly 10.07 \n",
"2008-01-01 Annual 20,902.87 \n",
"\n",
"Country United States \\\n",
"Series In 2015 constant prices at 2015 USD PPPs \n",
"Time Pay period \n",
"2006-01-01 Annual 12,594.40 \n",
" Hourly 6.05 \n",
"2007-01-01 Annual 12,974.40 \n",
" Hourly 6.24 \n",
"2008-01-01 Annual 14,097.56 \n",
"\n",
"Country \n",
"Series In 2015 constant prices at 2015 USD exchange rates \n",
"Time Pay period \n",
"2006-01-01 Annual 12,594.40 \n",
" Hourly 6.05 \n",
"2007-01-01 Annual 12,974.40 \n",
" Hourly 6.24 \n",
"2008-01-01 Annual 14,097.56 \n",
"\n",
"[5 rows x 64 columns]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"realwage.stack().head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can also pass in an argument to select the level we would like to stack"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>Series</th>\n",
" <th colspan=\"2\" halign=\"left\">In 2015 constant prices at 2015 USD PPPs</th>\n",
" <th colspan=\"2\" halign=\"left\">In 2015 constant prices at 2015 USD exchange rates</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>Pay period</th>\n",
" <th>Annual</th>\n",
" <th>Hourly</th>\n",
" <th>Annual</th>\n",
" <th>Hourly</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Time</th>\n",
" <th>Country</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"5\" valign=\"top\">2006-01-01</th>\n",
" <th>Australia</th>\n",
" <td>20,410.65</td>\n",
" <td>10.33</td>\n",
" <td>23,826.64</td>\n",
" <td>12.06</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Belgium</th>\n",
" <td>21,042.28</td>\n",
" <td>10.09</td>\n",
" <td>20,228.74</td>\n",
" <td>9.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Brazil</th>\n",
" <td>3,310.51</td>\n",
" <td>6.13</td>\n",
" <td>2,032.87</td>\n",
" <td>3.77</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Canada</th>\n",
" <td>13,649.69</td>\n",
" <td>6.56</td>\n",
" <td>14,335.12</td>\n",
" <td>6.89</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Chile</th>\n",
" <td>5,201.65</td>\n",
" <td>9.63</td>\n",
" <td>3,333.76</td>\n",
" <td>6.17</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Series In 2015 constant prices at 2015 USD PPPs \\\n",
"Pay period Annual Hourly \n",
"Time Country \n",
"2006-01-01 Australia 20,410.65 10.33 \n",
" Belgium 21,042.28 10.09 \n",
" Brazil 3,310.51 6.13 \n",
" Canada 13,649.69 6.56 \n",
" Chile 5,201.65 9.63 \n",
"\n",
"Series In 2015 constant prices at 2015 USD exchange rates \n",
"Pay period Annual Hourly \n",
"Time Country \n",
"2006-01-01 Australia 23,826.64 12.06 \n",
" Belgium 20,228.74 9.70 \n",
" Brazil 2,032.87 3.77 \n",
" Canada 14,335.12 6.89 \n",
" Chile 3,333.76 6.17 "
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"realwage.stack(level='Country').head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Using a ``DatetimeIndex`` makes it easy to select a particular time period\n",
"\n",
"Selecting one year and stacking the two lower levels of the ``MultiIndex`` creates a cross-section of our panel data"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>Time</th>\n",
" <th colspan=\"4\" halign=\"left\">2015-01-01</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Series</th>\n",
" <th colspan=\"2\" halign=\"left\">In 2015 constant prices at 2015 USD PPPs</th>\n",
" <th colspan=\"2\" halign=\"left\">In 2015 constant prices at 2015 USD exchange rates</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Pay period</th>\n",
" <th>Annual</th>\n",
" <th>Hourly</th>\n",
" <th>Annual</th>\n",
" <th>Hourly</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Country</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Australia</th>\n",
" <td>21,715.53</td>\n",
" <td>10.99</td>\n",
" <td>25,349.90</td>\n",
" <td>12.83</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Belgium</th>\n",
" <td>21,588.12</td>\n",
" <td>10.35</td>\n",
" <td>20,753.48</td>\n",
" <td>9.95</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Brazil</th>\n",
" <td>4,628.63</td>\n",
" <td>8.57</td>\n",
" <td>2,842.28</td>\n",
" <td>5.26</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Canada</th>\n",
" <td>16,536.83</td>\n",
" <td>7.95</td>\n",
" <td>17,367.24</td>\n",
" <td>8.35</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Chile</th>\n",
" <td>6,633.56</td>\n",
" <td>12.28</td>\n",
" <td>4,251.49</td>\n",
" <td>7.87</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Time 2015-01-01 \\\n",
"Series In 2015 constant prices at 2015 USD PPPs \n",
"Pay period Annual Hourly \n",
"Country \n",
"Australia 21,715.53 10.99 \n",
"Belgium 21,588.12 10.35 \n",
"Brazil 4,628.63 8.57 \n",
"Canada 16,536.83 7.95 \n",
"Chile 6,633.56 12.28 \n",
"\n",
"Time \n",
"Series In 2015 constant prices at 2015 USD exchange rates \n",
"Pay period Annual Hourly \n",
"Country \n",
"Australia 25,349.90 12.83 \n",
"Belgium 20,753.48 9.95 \n",
"Brazil 2,842.28 5.26 \n",
"Canada 17,367.24 8.35 \n",
"Chile 4,251.49 7.87 "
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"realwage['2015'].stack(level=(1,2)).transpose().head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For the rest of lecture, we will work with a dataframe of the hourly real minimum wages across countries and time, measured in 2015 US dollars\n",
"\n",
"To create our filtered dataframe (``realwage_f``), we can use the ``xs`` method to select values at lower levels in the multiindex, while keeping the higher levels (countries in this case)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"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>Australia</th>\n",
" <th>Belgium</th>\n",
" <th>Brazil</th>\n",
" <th>...</th>\n",
" <th>Turkey</th>\n",
" <th>United Kingdom</th>\n",
" <th>United States</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Time</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>2006-01-01</th>\n",
" <td>12.06</td>\n",
" <td>9.70</td>\n",
" <td>3.77</td>\n",
" <td>...</td>\n",
" <td>2.27</td>\n",
" <td>9.81</td>\n",
" <td>6.05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-01-01</th>\n",
" <td>12.46</td>\n",
" <td>9.82</td>\n",
" <td>4.01</td>\n",
" <td>...</td>\n",
" <td>2.26</td>\n",
" <td>10.07</td>\n",
" <td>6.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-01</th>\n",
" <td>12.24</td>\n",
" <td>9.87</td>\n",
" <td>4.17</td>\n",
" <td>...</td>\n",
" <td>2.22</td>\n",
" <td>10.04</td>\n",
" <td>6.78</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-01-01</th>\n",
" <td>12.40</td>\n",
" <td>10.21</td>\n",
" <td>4.47</td>\n",
" <td>...</td>\n",
" <td>2.28</td>\n",
" <td>10.15</td>\n",
" <td>7.58</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2010-01-01</th>\n",
" <td>12.34</td>\n",
" <td>10.05</td>\n",
" <td>4.71</td>\n",
" <td>...</td>\n",
" <td>2.30</td>\n",
" <td>9.96</td>\n",
" <td>7.88</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 32 columns</p>\n",
"</div>"
],
"text/plain": [
"Country Australia Belgium Brazil ... Turkey United Kingdom \\\n",
"Time ... \n",
"2006-01-01 12.06 9.70 3.77 ... 2.27 9.81 \n",
"2007-01-01 12.46 9.82 4.01 ... 2.26 10.07 \n",
"2008-01-01 12.24 9.87 4.17 ... 2.22 10.04 \n",
"2009-01-01 12.40 10.21 4.47 ... 2.28 10.15 \n",
"2010-01-01 12.34 10.05 4.71 ... 2.30 9.96 \n",
"\n",
"Country United States \n",
"Time \n",
"2006-01-01 6.05 \n",
"2007-01-01 6.24 \n",
"2008-01-01 6.78 \n",
"2009-01-01 7.58 \n",
"2010-01-01 7.88 \n",
"\n",
"[5 rows x 32 columns]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"realwage_f = realwage.xs(('Hourly', 'In 2015 constant prices at 2015 USD exchange rates'),\n",
" level=('Pay period', 'Series'), axis=1)\n",
"realwage_f.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Merging dataframes and filling NaNs"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Similar to relational databases like SQL, pandas has built in methods to merge datasets together\n",
"\n",
"Using country information from [WorldData.info](https://www.worlddata.info/downloads/), we'll add the continent of each country to ``realwage_f`` with the ``merge`` function"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"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 (en)</th>\n",
" <th>Country (de)</th>\n",
" <th>Country (local)</th>\n",
" <th>...</th>\n",
" <th>Deathrate</th>\n",
" <th>Life expectancy</th>\n",
" <th>Url</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Afghanistan</td>\n",
" <td>Afghanistan</td>\n",
" <td>Afganistan/Afqanestan</td>\n",
" <td>...</td>\n",
" <td>13.70</td>\n",
" <td>51.30</td>\n",
" <td>https://www.laenderdaten.info/Asien/Afghanista...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Egypt</td>\n",
" <td>Ägypten</td>\n",
" <td>Misr</td>\n",
" <td>...</td>\n",
" <td>4.70</td>\n",
" <td>72.70</td>\n",
" <td>https://www.laenderdaten.info/Afrika/Aegypten/...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Åland Islands</td>\n",
" <td>Ålandinseln</td>\n",
" <td>Åland</td>\n",
" <td>...</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>https://www.laenderdaten.info/Europa/Aland/ind...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Albania</td>\n",
" <td>Albanien</td>\n",
" <td>Shqipëria</td>\n",
" <td>...</td>\n",
" <td>6.70</td>\n",
" <td>78.30</td>\n",
" <td>https://www.laenderdaten.info/Europa/Albanien/...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Algeria</td>\n",
" <td>Algerien</td>\n",
" <td>Al-Jaza’ir/Algérie</td>\n",
" <td>...</td>\n",
" <td>4.30</td>\n",
" <td>76.80</td>\n",
" <td>https://www.laenderdaten.info/Afrika/Algerien/...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 17 columns</p>\n",
"</div>"
],
"text/plain": [
" Country (en) Country (de) Country (local) \\\n",
"0 Afghanistan Afghanistan Afganistan/Afqanestan \n",
"1 Egypt Ägypten Misr \n",
"2 Åland Islands Ålandinseln Åland \n",
"3 Albania Albanien Shqipëria \n",
"4 Algeria Algerien Al-Jaza’ir/Algérie \n",
"\n",
" ... Deathrate \\\n",
"0 ... 13.70 \n",
"1 ... 4.70 \n",
"2 ... 0.00 \n",
"3 ... 6.70 \n",
"4 ... 4.30 \n",
"\n",
" Life expectancy Url \n",
"0 51.30 https://www.laenderdaten.info/Asien/Afghanista... \n",
"1 72.70 https://www.laenderdaten.info/Afrika/Aegypten/... \n",
"2 0.00 https://www.laenderdaten.info/Europa/Aland/ind... \n",
"3 78.30 https://www.laenderdaten.info/Europa/Albanien/... \n",
"4 76.80 https://www.laenderdaten.info/Afrika/Algerien/... \n",
"\n",
"[5 rows x 17 columns]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import urllib.request\n",
"\n",
"url = 'http://www.worlddata.info/download/countries.csv'\n",
"source = urllib.request.urlopen(url)\n",
"worlddata = pd.read_csv(source, sep=';')\n",
"worlddata.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First we'll select just the country and continent variables from ``worlddata`` and rename the column to 'Country'"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"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>Continent</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Afghanistan</td>\n",
" <td>Asia</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Egypt</td>\n",
" <td>Africa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Åland Islands</td>\n",
" <td>Europe</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Albania</td>\n",
" <td>Europe</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Algeria</td>\n",
" <td>Africa</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Country Continent\n",
"0 Afghanistan Asia\n",
"1 Egypt Africa\n",
"2 Åland Islands Europe\n",
"3 Albania Europe\n",
"4 Algeria Africa"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"worlddata = worlddata[['Country (en)', 'Continent']]\n",
"worlddata = worlddata.rename(columns={'Country (en)':'Country'})\n",
"worlddata.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We want to merge our new dataframe, ``worlddata``, with ``realwage_f``\n",
"\n",
"The pandas ``merge`` function allows dataframes to be joined together by rows\n",
"\n",
"Our dataframes will be merged using country names, requiring us to use the transpose of ``realwage_f`` so that rows correspond to country names in both dataframes"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>Time</th>\n",
" <th>2006-01-01 00:00:00</th>\n",
" <th>2007-01-01 00:00:00</th>\n",
" <th>2008-01-01 00:00:00</th>\n",
" <th>...</th>\n",
" <th>2014-01-01 00:00:00</th>\n",
" <th>2015-01-01 00:00:00</th>\n",
" <th>2016-01-01 00:00:00</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Country</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>Australia</th>\n",
" <td>12.06</td>\n",
" <td>12.46</td>\n",
" <td>12.24</td>\n",
" <td>...</td>\n",
" <td>12.67</td>\n",
" <td>12.83</td>\n",
" <td>12.98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Belgium</th>\n",
" <td>9.70</td>\n",
" <td>9.82</td>\n",
" <td>9.87</td>\n",
" <td>...</td>\n",
" <td>10.01</td>\n",
" <td>9.95</td>\n",
" <td>9.76</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Brazil</th>\n",
" <td>3.77</td>\n",
" <td>4.01</td>\n",
" <td>4.17</td>\n",
" <td>...</td>\n",
" <td>5.27</td>\n",
" <td>5.26</td>\n",
" <td>5.41</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Canada</th>\n",
" <td>6.89</td>\n",
" <td>6.96</td>\n",
" <td>7.24</td>\n",
" <td>...</td>\n",
" <td>8.22</td>\n",
" <td>8.35</td>\n",
" <td>8.48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Chile</th>\n",
" <td>6.17</td>\n",
" <td>6.28</td>\n",
" <td>6.28</td>\n",
" <td>...</td>\n",
" <td>7.67</td>\n",
" <td>7.87</td>\n",
" <td>8.31</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
"Time 2006-01-01 2007-01-01 2008-01-01 ... 2014-01-01 \\\n",
"Country ... \n",
"Australia 12.06 12.46 12.24 ... 12.67 \n",
"Belgium 9.70 9.82 9.87 ... 10.01 \n",
"Brazil 3.77 4.01 4.17 ... 5.27 \n",
"Canada 6.89 6.96 7.24 ... 8.22 \n",
"Chile 6.17 6.28 6.28 ... 7.67 \n",
"\n",
"Time 2015-01-01 2016-01-01 \n",
"Country \n",
"Australia 12.83 12.98 \n",
"Belgium 9.95 9.76 \n",
"Brazil 5.26 5.41 \n",
"Canada 8.35 8.48 \n",
"Chile 7.87 8.31 \n",
"\n",
"[5 rows x 11 columns]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"realwage_f.transpose().head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can use either left, right, inner, or outer join to merge our datasets:\n",
"* left join includes only countries from the left dataset\n",
"* right join includes only countries from the right dataset\n",
"* outer join includes countries that are in either the left and right datasets\n",
"* inner join includes only countries common to both the left and right datasets\n",
"\n",
"By default, ``merge`` will use an inner join\n",
"\n",
"Here we will pass ``how='left'`` to keep all countries in ``realwage_f``, but discard countries in ``worlddata`` that do not have a corresponding data entry ``realwage_f``\n",
"\n",
"This is illustrated by the red shading in the following diagram\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<img src=\"https://cloud.githubusercontent.com/assets/21038129/24655284/f8a6a7e0-1980-11e7-8160-3a0392f1c723.png\" width=\"30%\" align=\"left\">"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We will also need to specify where the country name is located in each dataframe, which will be the ``key`` that is used to merge the dataframes 'on'\n",
"\n",
"Our 'left' dataframe (``realwage_f.transpose()``) contains countries in the index, so we set ``left_index=True``\n",
"\n",
"Our 'right' dataframe (``worlddata``) contains countries in the 'Country' column, so we set ``right_on='Country'``"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>2006-01-01 00:00:00</th>\n",
" <th>2007-01-01 00:00:00</th>\n",
" <th>2008-01-01 00:00:00</th>\n",
" <th>...</th>\n",
" <th>2016-01-01 00:00:00</th>\n",
" <th>Country</th>\n",
" <th>Continent</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>12.06</td>\n",
" <td>12.46</td>\n",
" <td>12.24</td>\n",
" <td>...</td>\n",
" <td>12.98</td>\n",
" <td>Australia</td>\n",
" <td>Australia</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>9.70</td>\n",
" <td>9.82</td>\n",
" <td>9.87</td>\n",
" <td>...</td>\n",
" <td>9.76</td>\n",
" <td>Belgium</td>\n",
" <td>Europe</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>3.77</td>\n",
" <td>4.01</td>\n",
" <td>4.17</td>\n",
" <td>...</td>\n",
" <td>5.41</td>\n",
" <td>Brazil</td>\n",
" <td>South America</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100</th>\n",
" <td>6.89</td>\n",
" <td>6.96</td>\n",
" <td>7.24</td>\n",
" <td>...</td>\n",
" <td>8.48</td>\n",
" <td>Canada</td>\n",
" <td>North America</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38</th>\n",
" <td>6.17</td>\n",
" <td>6.28</td>\n",
" <td>6.28</td>\n",
" <td>...</td>\n",
" <td>8.31</td>\n",
" <td>Chile</td>\n",
" <td>South America</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 13 columns</p>\n",
"</div>"
],
"text/plain": [
" 2006-01-01 00:00:00 2007-01-01 00:00:00 2008-01-01 00:00:00 \\\n",
"17 12.06 12.46 12.24 \n",
"23 9.70 9.82 9.87 \n",
"32 3.77 4.01 4.17 \n",
"100 6.89 6.96 7.24 \n",
"38 6.17 6.28 6.28 \n",
"\n",
" ... 2016-01-01 00:00:00 Country Continent \n",
"17 ... 12.98 Australia Australia \n",
"23 ... 9.76 Belgium Europe \n",
"32 ... 5.41 Brazil South America \n",
"100 ... 8.48 Canada North America \n",
"38 ... 8.31 Chile South America \n",
"\n",
"[5 rows x 13 columns]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged = pd.merge(realwage_f.transpose(), worlddata, how='left', left_index=True, right_on='Country')\n",
"merged.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Countries that appeared in ``realwage_f`` but not in ``worlddata`` will have ``NaN`` in the Continent column\n",
"\n",
"To check whether this has occured, we can use ``.isnull()`` on the continent column and filter the merged dataframe"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>2006-01-01 00:00:00</th>\n",
" <th>2007-01-01 00:00:00</th>\n",
" <th>2008-01-01 00:00:00</th>\n",
" <th>...</th>\n",
" <th>2016-01-01 00:00:00</th>\n",
" <th>Country</th>\n",
" <th>Continent</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>247</th>\n",
" <td>3.42</td>\n",
" <td>3.74</td>\n",
" <td>3.87</td>\n",
" <td>...</td>\n",
" <td>5.28</td>\n",
" <td>Korea</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>247</th>\n",
" <td>0.23</td>\n",
" <td>0.45</td>\n",
" <td>0.39</td>\n",
" <td>...</td>\n",
" <td>0.55</td>\n",
" <td>Russian Federation</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>247</th>\n",
" <td>1.50</td>\n",
" <td>1.64</td>\n",
" <td>1.71</td>\n",
" <td>...</td>\n",
" <td>2.08</td>\n",
" <td>Slovak Republic</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3 rows × 13 columns</p>\n",
"</div>"
],
"text/plain": [
" 2006-01-01 00:00:00 2007-01-01 00:00:00 2008-01-01 00:00:00 ... \\\n",
"247 3.42 3.74 3.87 ... \n",
"247 0.23 0.45 0.39 ... \n",
"247 1.50 1.64 1.71 ... \n",
"\n",
" 2016-01-01 00:00:00 Country Continent \n",
"247 5.28 Korea NaN \n",
"247 0.55 Russian Federation NaN \n",
"247 2.08 Slovak Republic NaN \n",
"\n",
"[3 rows x 13 columns]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged[merged['Continent'].isnull()]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We have three missing values!\n",
"\n",
"One option to deal with NaN values is to create a dictionary containing these countries and their respective continents\n",
"\n",
"``.map()`` will match countries in ``merged['Country']`` with their continent from the dictionary\n",
"\n",
"Notice how countries not in our dictionary are mapped with ``NaN``"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"17 NaN\n",
"23 NaN\n",
"32 NaN\n",
"100 NaN\n",
"38 NaN\n",
"108 NaN\n",
"41 NaN\n",
"225 NaN\n",
"53 NaN\n",
"58 NaN\n",
"45 NaN\n",
"68 NaN\n",
"233 NaN\n",
"86 NaN\n",
"88 NaN\n",
"91 NaN\n",
"247 Asia\n",
"117 NaN\n",
"122 NaN\n",
"123 NaN\n",
"138 NaN\n",
"153 NaN\n",
"151 NaN\n",
"174 NaN\n",
"175 NaN\n",
"247 Europe\n",
"247 Europe\n",
"198 NaN\n",
"200 NaN\n",
"227 NaN\n",
"241 NaN\n",
"240 NaN\n",
"Name: Country, dtype: object"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"missing_continents = {'Korea' : 'Asia',\n",
" 'Russian Federation' : 'Europe',\n",
" 'Slovak Republic' : 'Europe'}\n",
"\n",
"merged['Country'].map(missing_continents)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We don't want to overwrite the entire series with this mapping\n",
"\n",
"``.fillna()`` only fills in ``NaN`` values in ``merged['Continent']`` with the mapping, while leaving other values in the column unchanged"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>2006-01-01 00:00:00</th>\n",
" <th>2007-01-01 00:00:00</th>\n",
" <th>2008-01-01 00:00:00</th>\n",
" <th>...</th>\n",
" <th>2016-01-01 00:00:00</th>\n",
" <th>Country</th>\n",
" <th>Continent</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>247</th>\n",
" <td>3.42</td>\n",
" <td>3.74</td>\n",
" <td>3.87</td>\n",
" <td>...</td>\n",
" <td>5.28</td>\n",
" <td>Korea</td>\n",
" <td>Asia</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 13 columns</p>\n",
"</div>"
],
"text/plain": [
" 2006-01-01 00:00:00 2007-01-01 00:00:00 2008-01-01 00:00:00 ... \\\n",
"247 3.42 3.74 3.87 ... \n",
"\n",
" 2016-01-01 00:00:00 Country Continent \n",
"247 5.28 Korea Asia \n",
"\n",
"[1 rows x 13 columns]"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged['Continent'] = merged['Continent'].fillna(merged['Country'].map(missing_continents))\n",
"\n",
"# Check for whether continents were correctly mapped\n",
"\n",
"merged[merged['Country'] == 'Korea']"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now that we have all the data we want in a single ``DataFrame``, we will reshape it back into panel form with a ``MultiIndex``"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>2006-01-01 00:00:00</th>\n",
" <th>2007-01-01 00:00:00</th>\n",
" <th>2008-01-01 00:00:00</th>\n",
" <th>...</th>\n",
" <th>2014-01-01 00:00:00</th>\n",
" <th>2015-01-01 00:00:00</th>\n",
" <th>2016-01-01 00:00:00</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Continent</th>\n",
" <th>Country</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 rowspan=\"4\" valign=\"top\">Asia</th>\n",
" <th>Israel</th>\n",
" <td>5.77</td>\n",
" <td>6.03</td>\n",
" <td>5.92</td>\n",
" <td>...</td>\n",
" <td>5.91</td>\n",
" <td>6.31</td>\n",
" <td>6.59</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Japan</th>\n",
" <td>5.69</td>\n",
" <td>5.75</td>\n",
" <td>5.79</td>\n",
" <td>...</td>\n",
" <td>6.39</td>\n",
" <td>6.48</td>\n",
" <td>6.65</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Korea</th>\n",
" <td>3.42</td>\n",
" <td>3.74</td>\n",
" <td>3.87</td>\n",
" <td>...</td>\n",
" <td>4.64</td>\n",
" <td>4.93</td>\n",
" <td>5.28</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Turkey</th>\n",
" <td>2.27</td>\n",
" <td>2.26</td>\n",
" <td>2.22</td>\n",
" <td>...</td>\n",
" <td>2.51</td>\n",
" <td>2.69</td>\n",
" <td>3.23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Australia</th>\n",
" <th>Australia</th>\n",
" <td>12.06</td>\n",
" <td>12.46</td>\n",
" <td>12.24</td>\n",
" <td>...</td>\n",
" <td>12.67</td>\n",
" <td>12.83</td>\n",
" <td>12.98</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
" 2006-01-01 2007-01-01 2008-01-01 ... \\\n",
"Continent Country ... \n",
"Asia Israel 5.77 6.03 5.92 ... \n",
" Japan 5.69 5.75 5.79 ... \n",
" Korea 3.42 3.74 3.87 ... \n",
" Turkey 2.27 2.26 2.22 ... \n",
"Australia Australia 12.06 12.46 12.24 ... \n",
"\n",
" 2014-01-01 2015-01-01 2016-01-01 \n",
"Continent Country \n",
"Asia Israel 5.91 6.31 6.59 \n",
" Japan 6.39 6.48 6.65 \n",
" Korea 4.64 4.93 5.28 \n",
" Turkey 2.51 2.69 3.23 \n",
"Australia Australia 12.67 12.83 12.98 \n",
"\n",
"[5 rows x 11 columns]"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged = merged.set_index(['Continent', 'Country']).sort_index()\n",
"merged.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"While merging, we lost our ``DatetimeIndex``, as we merged columns that were not in datetime format"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index([2006-01-01 00:00:00, 2007-01-01 00:00:00, 2008-01-01 00:00:00,\n",
" 2009-01-01 00:00:00, 2010-01-01 00:00:00, 2011-01-01 00:00:00,\n",
" 2012-01-01 00:00:00, 2013-01-01 00:00:00, 2014-01-01 00:00:00,\n",
" 2015-01-01 00:00:00, 2016-01-01 00:00:00],\n",
" dtype='object')"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged.columns"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now that we have set the merged columns as the index, we can recreate a ``DatetimeIndex`` using ``to_datetime()``"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"DatetimeIndex(['2006-01-01', '2007-01-01', '2008-01-01', '2009-01-01',\n",
" '2010-01-01', '2011-01-01', '2012-01-01', '2013-01-01',\n",
" '2014-01-01', '2015-01-01', '2016-01-01'],\n",
" dtype='datetime64[ns]', name='Time', freq=None)"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged.columns = pd.to_datetime(merged.columns)\n",
"merged.columns = merged.columns.rename('Time')\n",
"merged.columns"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The ``DatetimeIndex`` tends to work more smoothly in the row axis, so we will go ahead and transpose ``merged``"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>Continent</th>\n",
" <th colspan=\"3\" halign=\"left\">Asia</th>\n",
" <th>...</th>\n",
" <th colspan=\"3\" halign=\"left\">South America</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Country</th>\n",
" <th>Israel</th>\n",
" <th>Japan</th>\n",
" <th>Korea</th>\n",
" <th>...</th>\n",
" <th>Brazil</th>\n",
" <th>Chile</th>\n",
" <th>Colombia</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Time</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>2006-01-01</th>\n",
" <td>5.77</td>\n",
" <td>5.69</td>\n",
" <td>3.42</td>\n",
" <td>...</td>\n",
" <td>3.77</td>\n",
" <td>6.17</td>\n",
" <td>4.39</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-01-01</th>\n",
" <td>6.03</td>\n",
" <td>5.75</td>\n",
" <td>3.74</td>\n",
" <td>...</td>\n",
" <td>4.01</td>\n",
" <td>6.28</td>\n",
" <td>4.42</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-01</th>\n",
" <td>5.92</td>\n",
" <td>5.79</td>\n",
" <td>3.87</td>\n",
" <td>...</td>\n",
" <td>4.17</td>\n",
" <td>6.28</td>\n",
" <td>4.39</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-01-01</th>\n",
" <td>5.84</td>\n",
" <td>5.99</td>\n",
" <td>4.00</td>\n",
" <td>...</td>\n",
" <td>4.47</td>\n",
" <td>6.61</td>\n",
" <td>4.54</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2010-01-01</th>\n",
" <td>5.68</td>\n",
" <td>6.14</td>\n",
" <td>3.99</td>\n",
" <td>...</td>\n",
" <td>4.71</td>\n",
" <td>6.78</td>\n",
" <td>4.60</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 32 columns</p>\n",
"</div>"
],
"text/plain": [
"Continent Asia ... South America \n",
"Country Israel Japan Korea ... Brazil Chile Colombia\n",
"Time ... \n",
"2006-01-01 5.77 5.69 3.42 ... 3.77 6.17 4.39\n",
"2007-01-01 6.03 5.75 3.74 ... 4.01 6.28 4.42\n",
"2008-01-01 5.92 5.79 3.87 ... 4.17 6.28 4.39\n",
"2009-01-01 5.84 5.99 4.00 ... 4.47 6.61 4.54\n",
"2010-01-01 5.68 6.14 3.99 ... 4.71 6.78 4.60\n",
"\n",
"[5 rows x 32 columns]"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged = merged.transpose()\n",
"merged.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Grouping and summarising data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Grouping and summarising data can be particularly useful for understanding large panel datasets\n",
"\n",
"A simple way to summarise data is to call an [aggregation method](http://pandas.pydata.org/pandas-docs/stable/basics.html#descriptive-statistics) on the dataframe, such as ``.mean()`` or ``.max()``\n",
"\n",
"For example, we can calculate the average real minimum wage for each country over the period 2006 to 2016 (the default is to aggregate over rows)\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Continent Country \n",
"Asia Israel 5.95\n",
" Japan 6.18\n",
" Korea 4.22\n",
" Turkey 2.46\n",
"Australia Australia 12.51\n",
" New Zealand 9.54\n",
"Central America Costa Rica 11.01\n",
"Europe Belgium 9.94\n",
" Czech Republic 2.15\n",
" Estonia 2.08\n",
"dtype: float64"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged.mean().head(10)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Using this series, we can plot the average real minimum wage over the past decade for each country in our data set"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAW8AAAFiCAYAAAA5olnKAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f3e8a65ef98>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"import matplotlib\n",
"matplotlib.style.use('seaborn')\n",
"%matplotlib inline\n",
"\n",
"merged.mean().sort_values(ascending=False).plot(kind='bar', title=\"Average real minimum wage 2006 - 2016\")\n",
"\n",
"#Set country labels\n",
"country_labels = merged.mean().sort_values(ascending=False).index.get_level_values('Country').tolist()\n",
"plt.xticks(range(0, len(country_labels)), country_labels)\n",
"plt.xlabel('Country')\n",
"\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Passing in ``axis=1`` to ``.mean()`` will aggregate over columns (giving the average minimum wage for all countries over time)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Time\n",
"2006-01-01 5.06\n",
"2007-01-01 5.22\n",
"2008-01-01 5.28\n",
"2009-01-01 5.48\n",
"2010-01-01 5.52\n",
"dtype: float64"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged.mean(axis=1).head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can plot this time series as a line graph"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEVCAYAAAARjMm4AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIiIdUrIQEZEO/X8KLtRAl8aHmQAAAABJRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f3e86fd6710>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"merged.mean(axis=1).plot()\n",
"plt.title('Average real minimum wage 2006 - 2016')\n",
"plt.ylabel('2015 USD')\n",
"plt.xlabel('Year')\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can also specify a level of the ``MultiIndex`` (in the column axis) to aggregate over"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>Continent</th>\n",
" <th>Asia</th>\n",
" <th>Australia</th>\n",
" <th>Central America</th>\n",
" <th>Europe</th>\n",
" <th>North America</th>\n",
" <th>South America</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Time</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>2006-01-01</th>\n",
" <td>4.29</td>\n",
" <td>10.25</td>\n",
" <td>nan</td>\n",
" <td>4.80</td>\n",
" <td>4.49</td>\n",
" <td>4.78</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-01-01</th>\n",
" <td>4.44</td>\n",
" <td>10.73</td>\n",
" <td>nan</td>\n",
" <td>4.94</td>\n",
" <td>4.58</td>\n",
" <td>4.90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-01</th>\n",
" <td>4.45</td>\n",
" <td>10.76</td>\n",
" <td>nan</td>\n",
" <td>4.99</td>\n",
" <td>4.85</td>\n",
" <td>4.95</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-01-01</th>\n",
" <td>4.53</td>\n",
" <td>10.97</td>\n",
" <td>nan</td>\n",
" <td>5.16</td>\n",
" <td>5.26</td>\n",
" <td>5.21</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2010-01-01</th>\n",
" <td>4.53</td>\n",
" <td>10.95</td>\n",
" <td>nan</td>\n",
" <td>5.17</td>\n",
" <td>5.45</td>\n",
" <td>5.36</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Continent Asia Australia Central America Europe North America \\\n",
"Time \n",
"2006-01-01 4.29 10.25 nan 4.80 4.49 \n",
"2007-01-01 4.44 10.73 nan 4.94 4.58 \n",
"2008-01-01 4.45 10.76 nan 4.99 4.85 \n",
"2009-01-01 4.53 10.97 nan 5.16 5.26 \n",
"2010-01-01 4.53 10.95 nan 5.17 5.45 \n",
"\n",
"Continent South America \n",
"Time \n",
"2006-01-01 4.78 \n",
"2007-01-01 4.90 \n",
"2008-01-01 4.95 \n",
"2009-01-01 5.21 \n",
"2010-01-01 5.36 "
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged.mean(level='Continent', axis=1).head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can see that there are several missing values in 'Central America'\n",
"\n",
"Instead of filling these in, we'll go ahead and drop 'Australia' and 'Central America' for plotting purposes"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"merged = merged.drop('Central America', level='Continent', axis=1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can plot the average minimum wages in each continent as a time series"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEVCAYAAAD6u3K7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f3e86ea5828>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"merged.mean(level='Continent', axis=1).plot()\n",
"plt.title('Average real minimum wage')\n",
"plt.ylabel('2015 USD')\n",
"plt.xlabel('Year')\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We will also drop Australia as a continent for plotting purposes"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAZEAAAEVCAYAAAAhANiZAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIcZMkogQQogxkyQihBBizP4/7B5T99gZbBUAAAAASUVORK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f3e86d25f60>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"merged = merged.drop('Australia', level='Continent', axis=1)\n",
"merged.mean(level='Continent', axis=1).plot()\n",
"plt.title('Average real minimum wage')\n",
"plt.ylabel('2015 USD')\n",
"plt.xlabel('Year')\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"``.describe()`` is useful for quickly retrieving a number of common summary statistics"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>Continent</th>\n",
" <th>Asia</th>\n",
" <th>Europe</th>\n",
" <th>North America</th>\n",
" <th>South America</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>44.00</td>\n",
" <td>200.00</td>\n",
" <td>33.00</td>\n",
" <td>33.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>4.70</td>\n",
" <td>5.15</td>\n",
" <td>5.17</td>\n",
" <td>5.48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>1.56</td>\n",
" <td>3.82</td>\n",
" <td>3.37</td>\n",
" <td>1.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>2.22</td>\n",
" <td>0.23</td>\n",
" <td>0.52</td>\n",
" <td>3.77</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>3.37</td>\n",
" <td>2.02</td>\n",
" <td>0.53</td>\n",
" <td>4.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>5.48</td>\n",
" <td>3.54</td>\n",
" <td>7.16</td>\n",
" <td>4.91</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>5.95</td>\n",
" <td>9.70</td>\n",
" <td>7.67</td>\n",
" <td>6.28</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>6.65</td>\n",
" <td>12.39</td>\n",
" <td>8.48</td>\n",
" <td>8.31</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Continent Asia Europe North America South America\n",
"count 44.00 200.00 33.00 33.00\n",
"mean 4.70 5.15 5.17 5.48\n",
"std 1.56 3.82 3.37 1.24\n",
"min 2.22 0.23 0.52 3.77\n",
"25% 3.37 2.02 0.53 4.60\n",
"50% 5.48 3.54 7.16 4.91\n",
"75% 5.95 9.70 7.67 6.28\n",
"max 6.65 12.39 8.48 8.31"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged.stack().describe()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This is a simplified way to use ``groupby``\n",
"\n",
"Using ``groupby`` generally follows a 'split-apply-combine' process:\n",
"* split: data is grouped based on one or more keys\n",
"* apply: a function is called on each group independently\n",
"* combine: the results of the function calls are combined into a new data structure\n",
"\n",
"The ``groupby`` method achieves the first step of this process, creating a new ``DataFrameGroupBy`` object with data split into groups\n",
"\n",
"Let's split ``merged`` by continent again, this time using the ``groupby`` function, and name the resulting object ``grouped``"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<pandas.core.groupby.DataFrameGroupBy object at 0x7f3e86c0f5c0>"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"grouped = merged.groupby(level='Continent', axis=1)\n",
"grouped"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Calling an aggregation method on the object applies the function to each group, the results of which are combined in a new data structure\n",
"\n",
"For example, we can return the number of countries in our dataset for each continent using ``.size()``\n",
"\n",
"In this case, our new data structure is a ``Series``"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Continent\n",
"Asia 4\n",
"Europe 19\n",
"North America 3\n",
"South America 3\n",
"dtype: int64"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"grouped.size()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Calling ``.get_group()`` to return just the countries in a single group, we can create a kernel density estimate of the distribution of real minimum wages in 2016 for each continent\n",
"\n",
"``grouped.groups.keys()`` will return the keys from the ``groupby`` object"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAecAAAFnCAYAAACcvYGMAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f3e86c38eb8>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import seaborn as sns\n",
"\n",
"continents = grouped.groups.keys()\n",
"\n",
"for continent in continents:\n",
" sns.kdeplot(grouped.get_group(continent)['2015'].unstack(), label=continent, shade=True)\n",
"\n",
"plt.title('Real minimum wages in 2015')\n",
"plt.xlabel('US dollars')\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This lecture has provided an introduction to some of pandas' more advanced features, including multiindices, merging, grouping and plotting\n",
"\n",
"Other features that may be useful in panel data analysis include the ``panel`` structure and pivot tables in pandas \n",
"\n",
"Alternatively, you may want to consider [xarray](http://xarray.pydata.org/en/stable/), a python package that extends pandas to N-dimensional data structures"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"# Exercises"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exercise 1 ##"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Load in a dataset of employment rates by age and sex from Eurostat using the ``pandas-datareader`` package (the relevant series code is ``lfsi_emp_a`` - it may take a few moments to load)\n",
"\n",
"Start off by exploring the dataset and the variables available in the ``MultiIndex`` levels\n",
"\n",
"Write a program that quickly returns all values in the ``MultiIndex``"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"## Exercise 2 ##"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Filter the above dataframe to only include employment as a percentage of 'active population'\n",
"\n",
"Create a grouped boxplot using ``seaborn`` of employment rates in 2015 by age group and sex\n",
"\n",
"**Hint:** ``GEO`` includes both areas and countries"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<img src=\"https://cloud.githubusercontent.com/assets/21038129/24689477/2d428ff8-1a0a-11e7-887e-2cd070a49f18.png\" align=\"left\">"
]
},
{
"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": "3.6.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
@natashawatkins
Copy link
Author

natashawatkins commented Apr 4, 2017 •
edited
Loading

box

venn2

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment