.. _implotninerst:

========
plotnine
========


.. only:: html

    **Links:** :download:`notebook <im_plotnine.ipynb>`, :downloadlink:`html <im_plotnine2html.html>`, :download:`PDF <im_plotnine.pdf>`, :download:`python <im_plotnine.py>`, :downloadlink:`slides <im_plotnine.slides.html>`, :githublink:`GitHub|_doc/notebooks/2016/pydata/im_plotnine.ipynb|*`


`plotnine <http://plotnine.readthedocs.io/en/stable/>`__ is an extension
of `ggplot <http://ggplot.yhathq.com/>`__. The language makes it to
compose the data with the layout. I replicate the example from the
gallery `Two Variable Bar
Plot <http://plotnine.readthedocs.io/en/stable/generated/plotnine.geoms.geom_col.html#two-variable-bar-plot>`__.

.. code:: ipython3

    %matplotlib inline

.. code:: ipython3

    from jyquickhelper import add_notebook_menu
    add_notebook_menu()






.. contents::
    :local:





example
-------

.. code:: ipython3

    import pandas as pd
    
    df = pd.DataFrame({
        'variable': ['gender', 'gender', 'age', 'age', 'age', 'income', 'income', 'income', 'income'],
        'category': ['Female', 'Male', '1-24', '25-54', '55+', 'Lo', 'Lo-Med', 'Med', 'High'],
        'value': [60, 40, 50, 30, 20, 10, 25, 25, 40],
    })
    df['variable'] = pd.Categorical(df['variable'], categories=['gender', 'age', 'income'])
    
    df






.. raw:: html

    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>category</th>
          <th>value</th>
          <th>variable</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>Female</td>
          <td>60</td>
          <td>gender</td>
        </tr>
        <tr>
          <th>1</th>
          <td>Male</td>
          <td>40</td>
          <td>gender</td>
        </tr>
        <tr>
          <th>2</th>
          <td>1-24</td>
          <td>50</td>
          <td>age</td>
        </tr>
        <tr>
          <th>3</th>
          <td>25-54</td>
          <td>30</td>
          <td>age</td>
        </tr>
        <tr>
          <th>4</th>
          <td>55+</td>
          <td>20</td>
          <td>age</td>
        </tr>
        <tr>
          <th>5</th>
          <td>Lo</td>
          <td>10</td>
          <td>income</td>
        </tr>
        <tr>
          <th>6</th>
          <td>Lo-Med</td>
          <td>25</td>
          <td>income</td>
        </tr>
        <tr>
          <th>7</th>
          <td>Med</td>
          <td>25</td>
          <td>income</td>
        </tr>
        <tr>
          <th>8</th>
          <td>High</td>
          <td>40</td>
          <td>income</td>
        </tr>
      </tbody>
    </table>
    </div>



.. code:: ipython3

    from plotnine import ggplot, aes, geom_col
    
    (ggplot(df, aes(x='variable', y='value', fill='category')) + geom_col())


.. parsed-literal::
    c:\Python364_x64\lib\site-packages\statsmodels\compat\pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.
      from pandas.core import datetools



.. image:: im_plotnine_5_1.png




.. parsed-literal::
    <ggplot: (117046438299)>



.. code:: ipython3

    from plotnine import geom_bar
    
    (ggplot(df, aes(x='variable', y='value', fill='category'))
     + geom_bar(stat='identity', position='dodge'))  



.. image:: im_plotnine_6_0.png




.. parsed-literal::
    <ggplot: (-9223371919808042629)>



.. code:: ipython3

    from plotnine import position_dodge, geom_text, lims
    
    dodge_text = position_dodge(width=0.9)                              # new
    
    (ggplot(df, aes(x='variable', y='value', fill='category'))
     + geom_bar(stat='identity', position='dodge', show_legend=False)   # modified
     + geom_text(aes(y=-.5, label='category'),                          # new
                 position=dodge_text,
                 color='gray', size=8, angle=45, va='top')
     + lims(y=(-5, 60))                                                 # new
    )



.. image:: im_plotnine_7_0.png




.. parsed-literal::
    <ggplot: (-9223371919808021020)>



.. code:: ipython3

    
    dodge_text = position_dodge(width=0.9)
    
    (ggplot(df, aes(x='variable', y='value', fill='category'))
     + geom_bar(stat='identity', position='dodge', show_legend=False)
     + geom_text(aes(y=-.5, label='category'),
                 position=dodge_text,
                 color='gray', size=8, angle=45, va='top')
     + geom_text(aes(label='value'),                                    # new
                 position=dodge_text,
                 size=8, va='bottom', format_string='{}%')
     + lims(y=(-5, 60))
    )



.. image:: im_plotnine_8_0.png




.. parsed-literal::
    <ggplot: (-9223371919807976034)>



.. code:: ipython3

    from plotnine import theme, element_rect, element_blank, element_line, element_text
    
    dodge_text = position_dodge(width=0.9)
    ccolor = '#555555'
    
    (ggplot(df, aes(x='variable', y='value', fill='category'))
     + geom_bar(stat='identity', position='dodge', show_legend=False)
     + geom_text(aes(y=-.5, label='category'),
                 position=dodge_text,
                 color=ccolor, size=8, angle=45, va='top')              # modified
     + geom_text(aes(label='value'),
                 position=dodge_text,
                 size=8, va='bottom', format_string='{}%')
     + lims(y=(-5, 60))
     + theme(panel_background=element_rect(fill='white'),               # new
             axis_title_y=element_blank(),
             axis_line_x=element_line(color='black'),
             axis_line_y=element_blank(),
             axis_text_y=element_blank(),
             axis_text_x=element_text(color=ccolor),
             axis_ticks_major_y=element_blank(),
             panel_grid=element_blank(),
             panel_border=element_blank())
    )



.. image:: im_plotnine_9_0.png




.. parsed-literal::
    <ggplot: (-9223371919807821799)>