Generalized Linear Models
=========================


.. _glm_notebook:

`Link to Notebook GitHub <https://github.com/statsmodels/statsmodels/blob/master/examples/notebooks/glm.ipynb>`_

.. raw:: html

   
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[1]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">print_function</span>
   <span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
   <span class="kn">import</span> <span class="nn">statsmodels.api</span> <span class="kn">as</span> <span class="nn">sm</span>
   <span class="kn">from</span> <span class="nn">scipy</span> <span class="kn">import</span> <span class="n">stats</span>
   <span class="kn">from</span> <span class="nn">matplotlib</span> <span class="kn">import</span> <span class="n">pyplot</span> <span class="k">as</span> <span class="n">plt</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <h2 id="glm-binomial-response-data">GLM: Binomial response data</h2>
   <h3 id="load-data">Load data</h3>
   <p> In this example, we use the Star98 dataset which was taken with permission
    from Jeff Gill (2000) Generalized linear models: A unified approach. Codebook
    information can be obtained by typing: </p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[2]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="k">print</span><span class="p">(</span><span class="n">sm</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">star98</span><span class="o">.</span><span class="n">NOTE</span><span class="p">)</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   <div class="output_subarea output_stream output_stdout output_text">
   <pre>
   ::
   
       Number of Observations - 303 (counties in California).
   
       Number of Variables - 13 and 8 interaction terms.
   
       Definition of variables names::
   
           NABOVE   - Total number of students above the national median for the
                      math section.
           NBELOW   - Total number of students below the national median for the
                      math section.
           LOWINC   - Percentage of low income students
           PERASIAN - Percentage of Asian student
           PERBLACK - Percentage of black students
           PERHISP  - Percentage of Hispanic students
           PERMINTE - Percentage of minority teachers
           AVYRSEXP - Sum of teachers&apos; years in educational service divided by the
                   number of teachers.
           AVSALK   - Total salary budget including benefits divided by the number
                      of full-time teachers (in thousands)
           PERSPENK - Per-pupil spending (in thousands)
           PTRATIO  - Pupil-teacher ratio.
           PCTAF    - Percentage of students taking UC/CSU prep courses
           PCTCHRT  - Percentage of charter schools
           PCTYRRND - Percentage of year-round schools
   
           The below variables are interaction terms of the variables defined
           above.
   
           PERMINTE_AVYRSEXP
           PEMINTE_AVSAL
           AVYRSEXP_AVSAL
           PERSPEN_PTRATIO
           PERSPEN_PCTAF
           PTRATIO_PCTAF
           PERMINTE_AVTRSEXP_AVSAL
           PERSPEN_PTRATIO_PCTAF
   
   
   </pre>
   </div>
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p>Load the data and add a constant to the exogenous (independent) variables:</p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[3]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">data</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">star98</span><span class="o">.</span><span class="n">load</span><span class="p">()</span>
   <span class="n">data</span><span class="o">.</span><span class="n">exog</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">add_constant</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">exog</span><span class="p">,</span> <span class="n">prepend</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p> The dependent variable is N by 2 (Success: NABOVE, Failure: NBELOW): </p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[4]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="k">print</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">endog</span><span class="p">[:</span><span class="mi">5</span><span class="p">,:])</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   <div class="output_subarea output_stream output_stdout output_text">
   <pre>
   [[ 452.  355.]
    [ 144.   40.]
    [ 337.  234.]
    [ 395.  178.]
    [   8.   57.]]
   
   </pre>
   </div>
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p> The independent variables include all the other variables described above, as
    well as the interaction terms:</p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[5]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="k">print</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">exog</span><span class="p">[:</span><span class="mi">2</span><span class="p">,:])</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   <div class="output_subarea output_stream output_stdout output_text">
   <pre>
   [[  3.43973000e+01   2.32993000e+01   1.42352800e+01   1.14111200e+01
       1.59183700e+01   1.47064600e+01   5.91573200e+01   4.44520700e+00
       2.17102500e+01   5.70327600e+01   0.00000000e+00   2.22222200e+01
       2.34102872e+02   9.41688110e+02   8.69994800e+02   9.65065600e+01
       2.53522420e+02   1.23819550e+03   1.38488985e+04   5.50403520e+03
       1.00000000e+00]
    [  1.73650700e+01   2.93283800e+01   8.23489700e+00   9.31488400e+00
       1.36363600e+01   1.60832400e+01   5.95039700e+01   5.26759800e+00
       2.04427800e+01   6.46226400e+01   0.00000000e+00   0.00000000e+00
       2.19316851e+02   8.11417560e+02   9.57016600e+02   1.07684350e+02
       3.40406090e+02   1.32106640e+03   1.30502233e+04   6.95884680e+03
       1.00000000e+00]]
   
   </pre>
   </div>
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <h3 id="fit-and-summary">Fit and summary</h3>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[6]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">glm_binom</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">GLM</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">endog</span><span class="p">,</span> <span class="n">data</span><span class="o">.</span><span class="n">exog</span><span class="p">,</span> <span class="n">family</span><span class="o">=</span><span class="n">sm</span><span class="o">.</span><span class="n">families</span><span class="o">.</span><span class="n">Binomial</span><span class="p">())</span>
   <span class="n">res</span> <span class="o">=</span> <span class="n">glm_binom</span><span class="o">.</span><span class="n">fit</span><span class="p">()</span>
   <span class="k">print</span><span class="p">(</span><span class="n">res</span><span class="o">.</span><span class="n">summary</span><span class="p">())</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   <div class="output_subarea output_stream output_stdout output_text">
   <pre>
                    Generalized Linear Model Regression Results                  
   ==============================================================================
   Dep. Variable:           [&apos;y1&apos;, &apos;y2&apos;]   No. Observations:                  303
   Model:                            GLM   Df Residuals:                      282
   Model Family:                Binomial   Df Model:                           20
   Link Function:                  logit   Scale:                             1.0
   Method:                          IRLS   Log-Likelihood:                -2998.6
   Date:                Thu, 21 May 2015   Deviance:                       4078.8
   Time:                        05:58:05   Pearson chi2:                 4.05e+03
   No. Iterations:                     7                                         
   ==============================================================================
                    coef    std err          z      P&gt;|z|      [95.0% Conf. Int.]
   ------------------------------------------------------------------------------
   x1            -0.0168      0.000    -38.749      0.000        -0.018    -0.016
   x2             0.0099      0.001     16.505      0.000         0.009     0.011
   x3            -0.0187      0.001    -25.182      0.000        -0.020    -0.017
   x4            -0.0142      0.000    -32.818      0.000        -0.015    -0.013
   x5             0.2545      0.030      8.498      0.000         0.196     0.313
   x6             0.2407      0.057      4.212      0.000         0.129     0.353
   x7             0.0804      0.014      5.775      0.000         0.053     0.108
   x8            -1.9522      0.317     -6.162      0.000        -2.573    -1.331
   x9            -0.3341      0.061     -5.453      0.000        -0.454    -0.214
   x10           -0.1690      0.033     -5.169      0.000        -0.233    -0.105
   x11            0.0049      0.001      3.921      0.000         0.002     0.007
   x12           -0.0036      0.000    -15.878      0.000        -0.004    -0.003
   x13           -0.0141      0.002     -7.391      0.000        -0.018    -0.010
   x14           -0.0040      0.000     -8.450      0.000        -0.005    -0.003
   x15           -0.0039      0.001     -4.059      0.000        -0.006    -0.002
   x16            0.0917      0.015      6.321      0.000         0.063     0.120
   x17            0.0490      0.007      6.574      0.000         0.034     0.064
   x18            0.0080      0.001      5.362      0.000         0.005     0.011
   x19            0.0002   2.99e-05      7.428      0.000         0.000     0.000
   x20           -0.0022      0.000     -6.445      0.000        -0.003    -0.002
   const          2.9589      1.547      1.913      0.056        -0.073     5.990
   ==============================================================================
   
   </pre>
   </div>
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <h3 id="quantities-of-interest">Quantities of interest</h3>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[7]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="k">print</span><span class="p">(</span><span class="s">&#39;Total number of trials:&#39;</span><span class="p">,</span>  <span class="n">data</span><span class="o">.</span><span class="n">endog</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">sum</span><span class="p">())</span>
   <span class="k">print</span><span class="p">(</span><span class="s">&#39;Parameters: &#39;</span><span class="p">,</span> <span class="n">res</span><span class="o">.</span><span class="n">params</span><span class="p">)</span>
   <span class="k">print</span><span class="p">(</span><span class="s">&#39;T-values: &#39;</span><span class="p">,</span> <span class="n">res</span><span class="o">.</span><span class="n">tvalues</span><span class="p">)</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   <div class="output_subarea output_stream output_stdout output_text">
   <pre>
   Total number of trials: 807.0
   Parameters:  [ -1.68150366e-02   9.92547661e-03  -1.87242148e-02  -1.42385609e-02
      2.54487173e-01   2.40693664e-01   8.04086739e-02  -1.95216050e+00
     -3.34086475e-01  -1.69022168e-01   4.91670212e-03  -3.57996435e-03
     -1.40765648e-02  -4.00499176e-03  -3.90639579e-03   9.17143006e-02
      4.89898381e-02   8.04073890e-03   2.22009503e-04  -2.24924861e-03
      2.95887793e+00]
   T-values:  [-38.74908321  16.50473627 -25.1821894  -32.81791308   8.49827113
      4.21247925   5.7749976   -6.16191078  -5.45321673  -5.16865445
      3.92119964 -15.87825999  -7.39093058  -8.44963886  -4.05916246
      6.3210987    6.57434662   5.36229044   7.42806363  -6.44513698
      1.91301155]
   
   </pre>
   </div>
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p>First differences: We hold all explanatory variables constant at their means and manipulate the percentage of low income households to assess its impact on the response variables: </p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[8]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">means</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">exog</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
   <span class="n">means25</span> <span class="o">=</span> <span class="n">means</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
   <span class="n">means25</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">=</span> <span class="n">stats</span><span class="o">.</span><span class="n">scoreatpercentile</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">exog</span><span class="p">[:,</span><span class="mi">0</span><span class="p">],</span> <span class="mi">25</span><span class="p">)</span>
   <span class="n">means75</span> <span class="o">=</span> <span class="n">means</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
   <span class="n">means75</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">=</span> <span class="n">lowinc_75per</span> <span class="o">=</span> <span class="n">stats</span><span class="o">.</span><span class="n">scoreatpercentile</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">exog</span><span class="p">[:,</span><span class="mi">0</span><span class="p">],</span> <span class="mi">75</span><span class="p">)</span>
   <span class="n">resp_25</span> <span class="o">=</span> <span class="n">res</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">means25</span><span class="p">)</span>
   <span class="n">resp_75</span> <span class="o">=</span> <span class="n">res</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">means75</span><span class="p">)</span>
   <span class="n">diff</span> <span class="o">=</span> <span class="n">resp_75</span> <span class="o">-</span> <span class="n">resp_25</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p>The interquartile first difference for the percentage of low income households in a school district is:</p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[9]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="k">print</span><span class="p">(</span><span class="s">&quot;</span><span class="si">%2.4f%%</span><span class="s">&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">diff</span><span class="o">*</span><span class="mi">100</span><span class="p">))</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   <div class="output_subarea output_stream output_stdout output_text">
   <pre>
   -11.8753%
   
   </pre>
   </div>
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <h3 id="plots">Plots</h3>
   <p> We extract information that will be used to draw some interesting plots: </p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[10]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">nobs</span> <span class="o">=</span> <span class="n">res</span><span class="o">.</span><span class="n">nobs</span>
   <span class="n">y</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">endog</span><span class="p">[:,</span><span class="mi">0</span><span class="p">]</span><span class="o">/</span><span class="n">data</span><span class="o">.</span><span class="n">endog</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
   <span class="n">yhat</span> <span class="o">=</span> <span class="n">res</span><span class="o">.</span><span class="n">mu</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p>Plot yhat vs y:</p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[11]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="kn">from</span> <span class="nn">statsmodels.graphics.api</span> <span class="kn">import</span> <span class="n">abline_plot</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[12]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">()</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">scatter</span><span class="p">(</span><span class="n">yhat</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span>
   <span class="n">line_fit</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">OLS</span><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">sm</span><span class="o">.</span><span class="n">add_constant</span><span class="p">(</span><span class="n">yhat</span><span class="p">,</span> <span class="n">prepend</span><span class="o">=</span><span class="bp">True</span><span class="p">))</span><span class="o">.</span><span class="n">fit</span><span class="p">()</span>
   <span class="n">abline_plot</span><span class="p">(</span><span class="n">model_results</span><span class="o">=</span><span class="n">line_fit</span><span class="p">,</span> <span class="n">ax</span><span class="o">=</span><span class="n">ax</span><span class="p">)</span>
   
   
   <span class="n">ax</span><span class="o">.</span><span class="n">set_title</span><span class="p">(</span><span class="s">&#39;Model Fit Plot&#39;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">set_ylabel</span><span class="p">(</span><span class="s">&#39;Observed values&#39;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">set_xlabel</span><span class="p">(</span><span class="s">&#39;Fitted values&#39;</span><span class="p">);</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   
   
   <div class="output_png output_subarea ">
   <img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAmUAAAG8CAYAAACfVtJdAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzs3XuclHX5//HXZ4HVTSFYFlE0D1+0yFJc1MSwFtPd1UwK
   MDso4CFRMw8wGpkn0kU8hGZpEWq6aoomP5Qyd9hUyE1NRQRTM8+KprliYLrIYa/fH/cszM7OzM7c
   c7pn5v18PO4HOzP34ZqZfbiXn891Xx9nZoiIiIhIYVUUOgARERERUVImIiIiEghKykREREQCQEmZ
   iIiISAAoKRMREREJACVlIiIiIgGgpExEio5zblfnXKdzrtf/hjnnjnPOPZzm+b/inPun/wi7nSvl
   WEWkvOk/EiKSU86515xznzjnBsc8vzySrOxcwNi6EqYPo7blZvawmY2I2u8159zXkpxnbNR51jrn
   /umcO85HPDOdc7f6fDsiUuT6FjoAESl5BrwCfA+4FsA5txdQFXktCD5tZp1JXjfA9XKOt8zsMwDO
   uW8CdzvnHgPWZSlGESlxGikTkXy4DZgc9XgKcAtRiY5z7tPOuVucc/+JjEyd55xzkdcqnHM/d869
   55x7GTgi+uSRY290zr3tnFvlnLskk+nCyMjXm5GfbwV2Bv4YGQk7u7fjzexe4ANgzzjnHuacW+Sc
   e98596Jz7geR5w8DzgW+0zVi5zd+ESlOSspEJB8eAwY450Y45/oA38FL1KL9CugP7AbU4SVxx0de
   m4qXiO0D7AccRfdRtpuB9cBwoBZoAH6QRnwJR8HMbBLwBvANM+tvZj9PeiIvgRwPDASeibPL/Mj5
   dsB7H5c65w42sxbgUmB+5Dq1acQvIiVASZmI5MuteIlWPfAc8FbXC1GJ2rlm9pGZvQ7MASZFdjka
   uNrM3jKzD/CSl65RtKHA4cA0M+sws/eAXwDfTSO2dufcB5Ftus/3N8w59wHwHnABcKyZvRi9g3Pu
   M8CXgRlmtt7MVgA3sGUU0dH7NKmIlCjVlIlIPhheUvYw3khYt6lLoAboB7we9dwbwI6Rn3cA3ox5
   rcsukWP/HZntBO9/OKP36c3g6Joy59zYNI7t8nZXTVkSw4DVZvZR1HNv4I3+iUiZU1ImInlhZm84
   517BG9U6IebldmADsCvwfOS5nYFVkZ//HXlM1Gtd3gQ+ISaxyrJs3ZDwNlDtnNvWzP4XeS76fQbl
   xgcRKQBNX4pIPp0IfM3MOqKfNLNNwF3ALOfcts65XYBpbKk7uws4wzm3o3NuEPCTqGP/DSwGrnLO
   9Y/UdA13zn01i3G/i1evlhEzexN4BJjtnNvKObc3XoLa9T7fAXZ1UUN+IlI+lJSJSN6Y2Stm9lT0
   U1E/nw58hNc+42Hg98BNkdeuB8LACuBJYEHMsZOBSrxatdXAH4Dto66RbAQq0WvRz88Gzu+l5izV
   a3wPb0TwbeD/ARea2YOR1/4Q+fd959yTSc4nIiXImeVutNw59zu8O6b+Y2Z7Jdjnl3jTGR8Dx5mZ
   bgMXERGRspPrkbKbgMMSveic+zqwu5ntgXfL+29yHI+IiIhIIOU0KTOzh/EaKCYyDmiO7Pt3YGDk
   9nYRERGRslLomrId6X6b+ypgpwLFIiIiIlIwhU7KoGejRN0SLiIiImWn0H3K3gKimy3uRFSX7y7O
   OSVqIiIiUjTMLO3WNoVOyhYBPwLmO+dGA/81s3fj7ZjLu0Qlt2bOnMnMmTMLHYb4oO+uuOn7K176
   7oqb31aDOU3KnHN34C0sXOOcexO4CG85FMzst2b2Z+fc151zL+H1Jzo+8dlERERESldOkzIz+14K
   +/wolzGIiIiIFIMgFPpLiRs7dmyhQxCf9N0VN31/xUvfXXnKaUf/bHHOWTHEKSIiIuXro49gxgy4
   7jrnq9BfI2UiIiIiGXrkEdhnH1i71v85lJSJiIiI+PTJJ3DuuTBhAlx+Odxyi/9zFbolhoiIiEhR
   WrECJk+G3Xbzfh6a4UKRGikTERERScPGjTB7Nhx6KEyfDgsXZp6QgUbKRERERFL24ove6Ng228Cy
   ZbDzztk7t0bKRERERHrR2QnXXgsHHgjf/z4sXpzdhAw0UiYiIiKS1JtvwgknwIcfendZfvazubmO
   RspERERE4jCDW2+FffeFgw+GtrbcJWSgkTIRERGRHt57D04+2ashW7zY60GWaxopExEREYlyzz2w
   997eqNiTT+YnIQONlImIiIgAsGYNnHmmN015990wZkx+r6+RMhERESl7DzzgjY596lPw9NP5T8hA
   I2UiIiJSxj7+2FtE/J574IYboLGxcLFopExERETK0mOPQW0tfPABrFxZ2IQMNFImIiIiZWb9evjZ
   z+DGG72GsEcdVeiIPErKREREpGysXOktk7Tzzl7t2PbbFzqiLTR9KSIiIiVv0ya4/HI45BDvDst7
   7w1WQgYaKRMREZES99JLMGUKVFZ6fcd22aXQEcWnkTIREREpSWbw61/D6NFw9NFe24ugJmSgkTIR
   ERGJEg6HmTNnHgCh0FQaC31Lok+rVsGJJ3p3Vra1wYgRhY6odxopExEREcBLyMaPn0Jr6zhaW8cx
   fvwUwuFwocNKixncdhuMGgVf+Qo88khxJGSgkTIRERGJmDNnHh0dlwNTAOjo8J4rltGy996DU06B
   F16AlhYvMSsmGikTERGRordoEYwcCcOHe8X8xZaQgUbKREREJCIUmkpb2xQ6OrzHVVUzCIWaCxtU
   L9asgbPOgr/+Fe6805uyLFYaKRMREREAGhsbWbiwmfr6RdTXL2LhwuZAT10++KC3iPhWW8GKFcWd
   kAE4Myt0DL1yzlkxxCkiIiK59/HHcO65sGCBt4j4YYcVOqLunHOYmUv3OI2UiYiISNH4+9+9RcTf
   e89bMiloCVkmVFMmIiIigbd+PVx8MVx/vbeI+Le/XeiIsk9JmYiIiATaP/4BkybBTjt5tWNBW7My
   WzR9KSIiIoG0aRNceSUcfDCcfrrX9qJUEzLQSJmIiIgE0Msvw3HHQZ8+8MQTsOuuhY4o9zRSJiIi
   IoFhBnPneouIT5zotb0oh4QMNFImIiIiAfHWW/CDH0B7u9cM9vOfL3RE+aWRMhERESkoM7j9dq/V
   xejR3iLi5ZaQgZIyERERSSAcDjNq1FgGD96dUaMOIhwOZ/0a7e1w9NEwaxbcfz9cdBH065f1yxQF
   JWUiIiLSQzgcZty4SSxffjyrV1/A8uUvMG7cd7OamP3pT94i4rvsAsuWwb77Zu3URUnLLImIiEgP
   DQ0TaW0dB0yJPNMMzKW+fhiLFy/I6Nxr18K0afDQQ3DzzfDVr2YYbMBomSUREZEMhcNhGhom0tAw
   MSdTddmKJUhxpmvJEm8R8T59vEawpZaQZcTMAr95YYqIiOROS0uLVVUNNbjZ4GarqhpqLS0tgYsl
   X3G2tLRYZeWQzdeBGqusHOj7Wh9/bHbWWWbDhpndd1+Wgw2YSN6Sdr6j6UsRERHiT9fV1y/KeKou
   27HkM85wOMy5587m9ddXscsu2zN79gU0NjamfZ4nnoDJk736seuug8GDsx5qoPidvlSfMhEREYmr
   sbHRVxLWZcMGuOQS+O1v4Ze/hO98J4vBlSAlZSIiIkAoNJW2til0dHiPq6pmEAo1By6WIMWZzLPP
   eqNj228PTz8NO+xQ6IiCT9OXIiIiEeFwmDlz5gFe8pPJKFEuYwlSnLE2bYKrr4bLL4dLL/U69Lu0
   J/KKm9/pSyVlIiIikhWvvOItIu6c1+pit90KHVFhqCWGiIiIFIQZzJsHBxwA3/qW13+sXBOyTKim
   TERERHx7+21vivLdd2HpUthzz0JHVLw0UiYiIiK+zJ/vLSL+pS/BY48pIcuURspEREQkLe+/Dz/8
   ITzzDNx3H+y3X6EjKg0aKRMREZGU3Xeft0zSjjt6i4grIcsejZSJiIhIr9auhenT4YEH4Pbboa6u
   0BGVHo2UiYiISFJLl3pLJDkHK1cqIcsVjZSJiIhIXOvWwXnneQX98+bBEUcUOqLSppEyERER6eHJ
   J2HUKFi1yhsdU0KWexopExERkc02bIBZs+A3v4FrroHvfrfQEZUPJWUiIiICwHPPeYuIDxkCy5fD
   sGGFjqi8aPpSRESkzHV2wlVXeQX8J50Ef/6zErJC0EiZiIhIHoTDYebMmQdAKDSVxsbGAkfkefVV
   bxHxzk6vK//w4YWOqHxppExERCTHwuEw48dPobV1HK2t4xg/fgrhcDjn12xomEhDw8S41zKDG27w
   lkg68khYskQJWaE5Myt0DL1yzlkxxCkiIhJPQ8NEWlvHAVMizzRTX7+IxYsX5OR6XUlgR8flAFRV
   zWDhwubNo3P//rc3Tfn223DLLfDFL+YkjLLlnMPMXLrHaaRMRESkxMyZMy+SkE0BvOSsa+r0rrtg
   n328dhePPaaELEhUUyYiIpJjodBU2tqm0NHhPa6qmkEo1JzXGDZs2Jbvfc+7q/KPf/SmLSVYNH0p
   IiKSB/ks9I+dvqysDDNgwO845pitmT0bqqpydmnB//SlkjIREZESFA6HufzyW/jXv45jw4aDmD+/
   ioMPLnRU5cFvUqbpSxERkRL0qU818tprjTQ2wtVXw4ABhY5IeqNCfxERKRu9tYlId78gWrcOzj4b
   vvMdb5mkG29UQlYsNH0pIiJlobc2EenuF0TLlnnLJO25p7d2ZU1NoSMqT4FsieGcO8w590/n3IvO
   uRlxXq9xzrU45552zv3DOXdcLuMREZHylaxNhJ/9gmTDBrj4Yjj8cDjvPK/thRKy4pOzmjLnXB/g
   WuBQ4C3gCefcIjN7Pmq3HwHLzexc51wN8IJz7jYz25iruERERErJ8897o2ODB3vtLnbcsdARiV+5
   HCn7EvCSmb1mZhuA+cA3Y/b5N9A10z0AeF8JmYiI5EIoNJWqqhlAM9Ac6RU21fd+hdbZCb/4BXz1
   q3DiiXD//UrIil3Oasqcc0cBjWZ2UuTxscABZnZ61D4VwIPAZ4H+wNFmdn+cc6mmTEREMpZqr7Cg
   Lh7e5bXX4PjjvWnL5matWRk0getT5pybCBzWS1J2PlBjZmc554YDrcBIM/sw5lxKykREpOyZwe9+
   Bz/5CZxzDoRC0KdPoaOSWEHsU/YW8Jmox58BVsXs82VgFoCZveycexX4HPBk7Mlmzpy5+eexY8cy
   duzY7EYrIiISYO+84y0ivmoVPPgg7LVXoSOSLkuWLGHJkiUZnyeXI2V9gReAQ4C3gceB70UX+jvn
   rgLWmNnPnHNDgWXA3ma2OuZcGikTESkjQZ8+zLe774Yf/chLyi64ACorCx2RJBO4kTIz2+ic+xEQ
   BvoAN5rZ8865kyOv/xa4FLjJObcC76aDH8cmZCIiUl5i+4S1tU0pmj5h2fbBB14y9uSTcO+9cMAB
   hY5IcknNY0VEJFAaGibS2joOr08YQDP19YtYvHhBIcPKu3AYfvADmDABZs+GT32q0BFJqgLZPFZE
   RKTY5XvJpf/9D049FaZO9e6svOYaJWTlQkmZiIgESi76hPlNrLqmUltbx9HaOo7x46fkNDFra4N9
   9vHWr1y5Er72tZxdSgJI05ciIhI42Sz0z2Qty3xNpa5bBxdeCLfeCnPnwjdjW61LUQlcob+IiIhf
   jY2NWSvs776WJXR0eM8F5caB5cth0iT43Oe80bEhQwodkRSKkjIRESk50SNt7e3v+j5PKDSVtrYp
   dHR4j72p1OZshMjGjXDZZfDLX8JVV8Exx4BLe2xFSomSMhERSVkx9A+Lna6srDyHysqzWL/eez2d
   xKqxsZGFC5uj3nN2WnO88IK3iPinPw3LlsFnPtP7MVL6VFMmIiIpyaQ2K5/i1YHV1t5ETc1goLDJ
   ZGcnXHstXHyxt516qkbHSpFqykREJKeCXpuVTE3N4IL3OXv9dW8R8XXr4NFHYY89ChqOBJBaYoiI
   SN7ko+dXLlpqZMIMbroJ9tsPGhrg4YeVkEl8mr4UEZGUZDp92dvxsfVqgO/6taDUvr37rtcE9rXX
   vHYXe+9dkDAkz/xOXyopExGRlGWS7CTr+dWzOP8soB/r118JBLd+LZkFC+C00+DEE+Gii7SIeDlR
   TZmIiORcNvuHRYutV1u/fi5wCsVYv/bBB3D66fD447BwIRx4YKEjkmKhmjIRkQLI93qKQRC0Wq9Y
   qX4nyfZbvNibohw0yGsKq4RM0mJmgd+8MEVESkNLS4tVVQ01uNngZquqGmotLS2FDitrWlparL5+
   gtXXT+jxvhK9FvuZVFYOtMrKIXn7jFL9ThLt97//mZ16qtlnPmPW2pqzMKVIRPKWtPMd1ZSJiORZ
   vtZTLIRMbgbIZqF/ulL9TuLtt//+L7B69aWMGQPXXAMDB+YsTCkSqikTEZGCy6SXWbx6teDXkI1i
   xYpx3HknfOtbhY5Fip1qykRE8qzQtVVBq2cLQjypfieh0FQqK88BFgGrce4NbrnlaSVkkhUaKRMR
   ybNcraeYitjpxba2KVltNZHuAt65jidVqX4nmzY5Nm06AzgIuJa+fa9m4MD5eY1VSpdqykREykg+
   6tnS6WVWTPV1//oXfOlL/2LNmm2BYZFngxuvFI5qykREJBBy1cusUDo74de/hpkzYYcdlrJmTSVb
   kkiR7FFSJiJSRtKdXkxFJl3+cxFPNr35preI+EcfwSOPwKuv7hyZbvVeD1q8Utw0fSkiUmayuS5k
   puthZjuebDGDW26Bs8+G6dPhnHOgb2QYI4jxSrBo7UsREcm7YqoJS9V//gMnnwwvv+wtIj5yZKEj
   kmLjNylTSwwREZGIhQu9JGzECHjiCSVkkl+qKRMREd+CXhOWqv/+F844Ax59FBYsgC9/udARSTnS
   SJmIiPjW1d+rvn4R9fWLCtJjLFOtrd4i4v37w9NPKyGTwlFNmYiIlKWPPoIZM+Dee+HGG6GhodAR
   SalQTZmIiEiKHn0UamthzRpYuVIJmQSDkjIRESkbn3wCP/0pjB8Pl13m3V05aFD8fYOwJqeUFxX6
   i4hIWVi5EiZNgt12gxUrYOjQxPsGZU1OKS8aKRMRkZK2cSPMng2HHALTpnltL5IlZABz5syLJGRT
   AC8562oYK5IrGikTEZGS9eKLMGUKVFXBsmWw886FjkgkMY2UiYiUqHKuiershOuugwMPhO99z2t7
   kU5CFgpNpapqBtAMNEf6r03NVbgigFpiiIiUpGysSVms3nwTTjgB1q711q/83Of8nUdrXIpfWvtS
   REQ2K8U1KXtjBrfdBqEQnHmm14Osr4p0pAD8JmX6dRURkaL33nveIuIvvgjhsNeDTKTYqKZMRKQE
   FWtNlJ86uHvu8ZZJ2mMPePJJJWRSvDR9KSJSooqtJirdOrg1a7xpyrY2aG6GMWPyGa1IYqopExGR
   opZOHdwDD3jF/EccAVdcAdtum9dQRZJSTZmISJEothGs/HoGmBj5ebfNz3Z9Zps2VbLttpfx1FO7
   cMMNoI9OSomSMhGRPCqH5Xv8Jp11daNobb0C+GXkmTOoq/tx1Gd2I3AQffq0Mn/+SzQ2HpKT+EUK
   RUmZiEgedV++Bzo6vOdKJSnLJOlcuvQpvIRsStRzi3jooZV0dCwG9gZg06aPmDfvDo46SkmZlBYl
   ZSIikjXZTjo//HBnnn32dKBf9oIUCSi1xBARyaNUW1Xke4mk6OvNmjUrrWtHH9ve/q7vGLp/NrfQ
   t++bPP/85Zx00kdsvfX+dH1mlZVn0d7+flkuHyUlzswCv3lhioiUhpaWFquvn2D19ROspaUl7utV
   VUMNbja42aqqhsbdL5vxRF8PBhiEUrp27LGVlUOssnKg79hbWlpszJgf2sCBz9nee79vr7665fn6
   +glWWzvGKiuH5O2zEfEjkrekne+oJYaISMDke4mkeNeDRcCCXq8d79ja2puoqRkMpFfobwZz58IF
   F3jb6adDRcx8TjkuHyXFRy0xRETyRC0tkqupGZx2krRqFZx4InzwgdcMdsSIHAUnEmBKykRE0pCr
   lhbRiV5d3Sja2mbQ0eG95tWdNad1rnPPnc3rr69i0KCtGDBgCDU1gxMmkKHQVNrapmy+HpwBnMSW
   mrfE1449Nt1YzeD222HaNG9k7Nxzky8inun1RIJM05ciImnIxfRZvOWFzjvv9EiLiPRG48LhMOPG
   TWL9+isjz3QlWHslXbYoNilM59p+Rw7few9OPRWefx5uvRVGjUrpMI1USuBpmSURkTzIRVKWzXNm
   Uh+WT4sWwSmnwDHHwCWXwNZbFzoikexRTZmISB5o+iwza9fCWWfB0qVw553wla8UOiKR4FCfMhGR
   NDQ2NrJwoTfiVF+/KCv1ZLG9yzLpwxUKTaWy8pzN5/KmL3cjWU+0fHnoIdh7b+jXD55+WgmZSCxN
   X4qIBEBXnVR7+7s8++y/NteEJasDS3audAr9c+3jj70C/gUL4Prr4fDD8x6CSF6ppkxEpASUWh+u
   xx+HyZO9Iv5rr4Xq6kJHJJJ7qikTEZHAWL/eK+CfNw9+9Ss4+uhCRyQSfKopE5GCy/c6j0GW6tqY
   QfaPf8Do0bB8uVc75ich0++ElCNNX4pIQcXr0ZWN4vliVqx9uDZtgquugiuugMsugxNOAJf2BI5+
   J6T4qaZMRIpSqdVQlauXX4bjjoM+feCmm2C33fyfS78TUuz8JmWavhQREd+6FhEfPRomTIAHH8ws
   IRMpZyr0F5GCUjPW/MnWtGjXedatq6aj41JgCH/9K3z+89mJU78TUq40fSkiBVesNVTFJFt1WuFw
   mG99awrr1t0F7E/fvtdyzz0jOeKIhqzHq98JKVaqKRMRkYSyVac1duxxLF06E9g1o/OIlDLVlImI
   BESptnP405/gscfmAB8VOhSRkqSkTEQki7qmCVtbx9HaOo7x46cEIjHLpP/Z2rXwgx/AGWdAU9PL
   VFUdkvA8pZqQiuSDpi9FRLIoyO0c/NRpLVkCxx8P9fUwZw7075/4POovJuLRMksiIpJUY2NjyglS
   Rwf89Kdw113eIuJf/3rv55kzZ14kIZuy+Rxz5sxTUiaSIiVlIiJZVArtHJ58EiZNgpEjYeVKGDy4
   0BGJlAfVlImIZFFjYyMLF3pTlvX1iwI3fZes5mvDBrjoIjjiCO/f+fPTS8hKYd1OkUJSTZmISJlI
   VvP17LMweTIMHQo33ADDhvm/hvqLSbkLZJ8y59xhwC+APsANZnZ5nH3GAlcD/YB2MxsbZx8lZSIi
   GYp3E8Khh/6Jww77A5ddBpde6t1l6WcRcRHZInB9ypxzfYBrgcOAPYHvOec+H7PPQOA64Egz+yJw
   VK7iEREJuvy3k9iWJ5/8GffeC3//O5x0UjASMrXVKCx9/oWTVqF/JNHaxszWprD7l4CXzOy1yLHz
   gW8Cz0ft831ggZmtAjCz9nTiEREpFbFTi21tU7Jej9b9JoQ9gLF8+9vv8ZvfQJ8+WbtMRvLxOUhi
   +vwLq9eRMufcHc65Ac65bYBngOedcz9O4dw7Am9GPV4VeS7aHkC1c+4h59yTzrlJqQYuIlJKureT
   8P4odtVmZUtjYyM33DCfwYP3on//ocyd+zzz5o0ITEIG+fkcJDF9/oWVykjZnma21jl3DHA/8BPg
   KeCKXo5LpQisHzAKOAT4FPCoc+4xM3sxdseZM2du/nns2LGMHTs2hdOLiEiX+fNh2rSxnHYanH8+
   9Os3vNAhiZSEJUuWsGTJksxPZGZJN+BZvOTpD8DYyHMrUzhuNNAS9fhcYEbMPjOAmVGPbwCOinMu
   ExHJlpaWFquvn2D19ROspaWl0OGYmRdTVdVQg5sNbraqqqFZi6293ezoo81GjDB7/PH0Ysr355Ts
   cwji91Zqcvl7WE4ieUuvOVbslkpSdgbwFt4oWQWwK/BwCsf1BV6O7F8JPA18PmafEcBf8O7O/BTe
   9Oiecc6V0w9PRMpHkP/o5CLpuO8+s2HDzKZNM/v44/RiKdTnFO9zCPL3VmqU/GbOb1KWdksM55wD
   +pjZxhT2PZwtLTFuNLPZzrmTI1nWbyP7nA0cD3QC15vZL+Ocx9KNU0QkniCvTZlNH34I06fDX/4C
   N90E6VZ8jBp1EMuXbwKGAVOBdwr6OZXL9yalIWdrXzrntgdmATua2WHA54EDgRt7O9bM7scbYYt+
   7rcxj38O/DyNmEVEJImlS+G44+CQQ2DFChgwIL3jw+EwK1Y8h9dCErxE6NjsBikiPaTSp+xmYDHe
   /y4BvAhMy1VAIlIagtDrKF4MiZYCCofDjBo1lsGDd2fUqIOKsj/TunUQCsH3vw+/+pXXmT/dhAy8
   O/A6O6+m6w48uJyKipsTLpmUj+9aSzhJWehtfhN4MvLv8qjnnvYzV+p3QzVlIkWlUPU/0bUwTU1N
   KReMt7S0WGXlkM37Qo1VVg4sqnqaJ54w+/znzb79bbP33svsXPX1EyKfg0W2m622ti7uvvn8rlXr
   JMWCHBb6LwEGdyVleHdVLvVzMb+bkjKR4hLvj3p9/YScXjM2OaioGJxyDPHihdE5jzkb1q83u+gi
   s+22M7v9drPOzszPmU6iVYjvWiTo/CZlqfQpCwF/BP7POfcIMAQthyQiAdO96SV0ds4tbEB58Nxz
   3iLiQ4bA8uX+FxGP1djYyMKFzVELi6uju0g+9JqUmdky51wd8LnIUy+Y2YbchiUixaz7cj5E6n+a
   0zpHOByOSgqm+kgKxlBRMY3Ozt5jCIWmsnTpJNav73rmbJxbR3t7H8LhcMrXziTmdI7t7IRvfKOV
   lpZ9qaq6im99q4phw85L+VqpaGxsTCn+bHzXIhLR21Aa3v92TmZLxedkYLKfYTm/G5q+FCk6mdT/
   +KlTindMU1NTyjG0tLRYbW2d9e+/sznX3yCUVo1UU1OTVVQM8lVblc77feUVs113fc3gbwYLIscM
   sKamppSulQuq9RLpjhzWlF0L/CqyXQ+8Atzt52J+NyVlIuXFb51SNpIDP9duaWlJq4bNzzU7O82u
   v96spsasqupSg+Zu+1dXD/f1fkUk+/wmZalMX/4o+rFzbiBwZ1aG6UREsijVKbds81pI7JGz8//7
   33DSSfCCwBLwAAAgAElEQVT22/DQQ1BXdyMdHRfk7HoiUhipFPrH+hjYLduBiIh0KWSdkv9rj8Fb
   ztdTUTGNuroQDQ0TN583UcKY7Jp33QVnnAFTp8Ippyxm+vTfMmjQVqxefUbUGc5g+vQfp/U+M6/Z
   E5Fs63WZJefcH6MeVgB7AneZ2YwEh2SdllkSKT+FTBrSvXY4HGb8+Cl0dBwL/I2KiheZNOkb3HVX
   S+SOUC/RWrgw8V2Msdfcf/9GTjvNu6vyllvggw+6ruGdr2/f06iqGky/fv048siDePvtD33Em1ps
   IpIev8sspZKUjY16uBF43czeTPdCmVBSJiJBF5tUzZkzz/dajfff701XHnUUXHopfOpTidd+DIWm
   pp1gaR1Jkdzym5T1usySmS2J2trynZCJSO+CsKRRMZo1axaDB+/O4MG7M2vWrG6vpfuZNjY2snjx
   AhYvXpD2iFNXHNXVe7P//k9x6qne6NgvfuElZMl078/mJWddyaGIFJlEdwAA/wM+TLCt9XNXgd8N
   3X0pklChljQqdk1NTQYDopZW2tJWItFnms7dnal+L1OmTInE8WeDtQa32PnnX9njXLW1dZE7PLu3
   6vB7t6gXW8hgtFVUDC5oSw2RUkOuWmIEYVNSJpKYlrnxp7p6eI/PrautRPy1H8f46p2WLIlraWkx
   2N7gmYTtLXouHzXIamvHdFvH009SnklfNRFJzm9SlvLdl8657YCto0bY3sjOWJ2ISPC9/vo73ZZx
   6ujwpg6TTVX21qLjootagTagT8J9ei4fBTU1izaf1++SSEuXPkVn59VpvR8Rya1ekzLn3DhgDjAM
   +A+wC/A88IXchiYiqdAyN/5Mn348558fv61E7GdaUTGNDRu2zdq1N26E2bPhqacuAP6Et8Tw5Zvj
   OPLI8ZtbabS3vxtz9DMsW7aChoaJm++0LFR/NhHJst6G0oCVQA2wPPL4YOB3fobl/G5o+lIkKS1z
   409TU5NVVw+36urhPWqqetZxhbrVoKW7jFLX93P99Q/b/vubNTSY3XrrQ91qu2CQHXrood2mIysr
   h1hl5cDIY/8xxIsp37WI+j2VckEOl1laFvl3BdAn8vNKPxfzuykpE5FC6FlbFrLq6uFpJRVbkp+z
   Da42aLcjj/yzdXZueT06UYlfz1Zn9fUT4tbBZVI/mM8kSTekSDnxm5SlUlP2gXOuP/Aw8Hvn3H/w
   7swUESkze7Hvvq+m1c/Lqwk7HRgL7AEs5b77fsDixXfEnXqM186ipmYwixcviPQXy/hNbJbPac/Y
   2jjVsIn01GufMuCbeEsrTQNagJeAI3MZlIgUvyD3TuuKbdSosYwadVDCGEOhqVRVzQCageZIvd7U
   lM7d0DCRlpYwb731NeCHwFbAdsAEOjuv3px8xX5Oya7pJx4RKSK9DaXhVaDu6GcYLlsbmr4UKSpB
   nqqKjQ1qDEIJY/Tfm2y+VVSEbfvt3zHnDoo77einH1qx1mUF+XdCJNvwOX2ZyjJLM4FvAx8A84E/
   mFns7UA5pWWWRIpLkJfxiRcbLALGZRxjz3Ov5JBDZnHwwXtz4YVzIi0otiyFlMlSTMVIi6BLufC7
   zFKvNWVmNhOY6ZwbCRwN/NU5t8rMDkk/TBGR0rVhwzbAV6KeWU5FxUbOO+889ttvvx69xMptOSS1
   7hDpRapDasAOwOnAI+juSxFJIt9TVYmm9JqammzbbXewvn23s+HD99k8NZjO9GXqMZjV1Hxsffpc
   b3BrSu87k8+pWKcxRcoBOZy+/CHeCNl2wB+AO83suRzmifFisN7iFJFgyddU1axZs+JODT755JOc
   f/6lwKeAnwPQt2+ImTOnsWDB/bz++jsMGtSfAQO2oaZmqO8Y//c/OOcc+POf4Xe/g40b03vffj6n
   cDjM+PFTInczbnnPGoUSCQa/05epJGWz8RKxp/0GlyklZSISTzgc5utfP4bOzjnE1mUtW7aC1auH
   AKd0e62iIhTZ318yE51ENTb+mN/85gC+8hX4xS/g05/O1jtLLsg1eyKS25qyc/2FJCKSW3PmzKOz
   c4+0jvH299cra8sI1ZVALa2tQ7jooqeYOXNUmpGLiPSU8oLkIiLpiB5RqqsbxdKlTwG5mMocA8zY
   /KiiYhqh0B1R05dnb37NuTMx+4HvK3kNUK9nS6vG+TzyyB+A7iNUuZ661XqnIiXKTyFavjdU6C9S
   VHoW0w+IrNuY3aL/Ldfx1o6sqBjcbQ3L2EL/pqYm34X1GzaYDR/+e4OPky5zlK+bHFToLxJc5KrQ
   PwhUUyZSXBL3AltAtuuf0h2V8jOK9cILMHkybNzYzrPPNvDJJ2cC8WvSVO8lIlmvKXPO/Q9IlAmZ
   mQ1I92IiItmWbu+rdPbv7IRrr4WLL/a2U0+tYfHi2T36jYmIZEPCpMzMtgVwzjUBbwO3RV46BhiW
   +9BEpFjF1jzBGcBJbFmvsXv9U6E6vSe77htvwPHHezcDPPoo7BG5n6C3pE71XiLiVyotMVaa2d69
   PZdLmr4UKT6pFvoXqudWous2NDTS3Oz1HguFvH/79En/3H6TTC1FJFL8ctmn7FHgOuCOyFPfBU4z
   sy+nHaVPSspESleharDiXferX13KwIG/47XX4JZbYOTInIbQg5rCipQGv0lZRQr7fB+vo/+7ke3o
   yHMiIjkTDodpaJhIQ8NEwuFwHq64M489NocvfAEefzz/CRl0tdy4HC9R9JKzclsfU6Sc9ZqUmdmr
   ZjbOzGoi2zfN7LU8xCYiAZDr5CgUmkpV1Qy8OzS9mrO6ulGMHz+F1tbdaG19jsMO+z677167+frp
   xBRv33A4THv7u1RUTANuB17GuV247LIXuPRS2Gqr7L2/VGLt2mfZshXZu7CIFJ/eemYAnwMeAJ6N
   PN4bON9P/w2/G+pTJlIQheq5VV8/IdJ7bGBkwXDv+pWVQ9LqNRYv/u7H/9ZgldXU/D+7557WnLyv
   3mLtvk8o0tMtPwu5i0hu4LNPWSoJ0V+BA4DlkceuK0HL16akTKQwvOTo5qTNUnN33dGRrfv1q6uH
   pxxTvPi942+Lei6cs/eUyufXc5+QVVcPz2pTWDWaFckvv0lZKjVlnzKzv0eNrBmwITvjdCIiPYVC
   U6moeDEn596woZYtyyQB/Dsn1/FvL/bddySh0FTmzJmX8bRx180Dra3jaG0dx/jxU/JUoyciaest
   awPuB3Zny0jZUcD9fjJAvxsaKRMpiHxNX8bT1NRkzm2bxenLW6xv31/attt+aJWVx+XlPaU/fRlv
   ijWzGPM52qkROREPOZy+HI5XU9aB10T2b8Cufi7md1NSJlI4hfxD29LSYrW1Y6y6erjV1tZtvn46
   MbW0tNjo0dNs221fsy9/+R179938vqdUrhW/pi47iVS+krJCJvAiQeM3KUulT1kfM9vknNsWqDCz
   tdkfr0tOfcpExI+NG+GKK+Dqq2HOHJg0CVzanYPyL5u92/LV+0xrfopskcs+Za865+bhFft/mHZk
   IpJX+e/vlV+pvr9//Qv22uu/zJmzkhEjTmbo0HBRJGQQv01IKDTV17kaGxtZuNBLkOrrF6kZrUiQ
   9TaUBmwDfAdYCLwOXAt8xc+wnN8NTV+KpCRoU0jZniZM5f1t2mT2q1+ZDRjwifXrd25gPot0ZeOz
   y/c0bZB+90QKiVzVlFn35GgQcCuwyc/F/G5KykRSU6gWFvHk4o90b+/vjTfMDjnEbPRosy9/+bTA
   fBaFUIgkSYX+Ih6/SVmv05fOM9Y59xvgKWArvKWWRKSEZHvaM59LBplBczOMGgVf+xo8/DBss03Q
   Wl3kVyGWbGpsbGTx4gUsXrxAU6QiPvRNYZ9XgaeBO4FzzOx/uQ1JRMLh8OY/oKHQ1JT/wIVCU2lr
   m0JHh/fYq0VqTul60cXgbW1TutUepRNP177ekkG7pXTtOXPm0d7+LtCXmprBCa8R7/2deOIdTJgA
   L78Mf/nLljUr/X4WIiIFk2wYDegDXOhnCC6bG5q+lDKS6bSTnymkRJ3vW1pa0oondl9vyaBQCj26
   Qt36kfV2ja73d8EFT9n225v95Cdm69al9lkEaYotl7GoxkukcMhhn7In/Jw4m5uSMiknhagLi3dN
   GG1VVUOttnZMyvEkSu4SJR1b9k/vPX/wgdmkSWa77272t7+l/j6DlKjkI5YgJaAi5cRvUpbK9GWb
   c+5avOnLj6JG2J7K7pidiBRK7FQfeO0YOjre4fXXL8no3PvuOzKrvapaW+HEE+HII+Hpp2Gbbbzn
   U5li7V5nBR0d3nOFqH/KRyyNjY2q7RIpIqn0KasFvgBcDMyJ2kQkB7LZoypVXb2sqqsvAeZGru39
   Md9ll51SjqeubhQVFdM271tZeRbt7e8nvHlgy3vdDTg76TU++gh+9CM44QS44Qa47rruCVk+1nfM
   5s0Q7e3vF/T6IhJAfobX8r2h6UspM4Wadko0pZbqUkFb6sNGm3P9rW/fwb1Oz3Wdu7Z2jNXW1sW9
   xiOPmO2xh9mxx5qtXt3z2qlO+WYyZZjN6caWlharrBxoset6JjtfkKZeRSQ5clhTtj1wI9ASebwn
   cKKfi/ndlJSJ5I/fhLBnYjQ649q4Tz4xO/dcs6FDze6+O51rJ75W9t5fNtajbInU04222toxebu+
   iOSW36QslZqym4GbgPMij18E7ookaiJSYoJSh7RyJUyeDLvsAitWwNChifdNp/1FUN6fpzGyNVNT
   s6jQwYhIgaVSU1ZjZncCmwDMbAOwMadRiZSYcqgFiq2Fq6z8J5WV50Q9Pof29nd7/Qz+/Ocwe+xx
   G/vtt4ZDDnmGe+6Jn5BFf6bA5vUdhw+/gr59t+L73z+NWbNmpRR7Kt9PNmv9/JwrnWPK4fdNpCT1
   NpQGLAEGA8sjj0cDS/0My/nd0PSlFLFyqgWKnRrcUi9WF6mhSv4Z3HjjX62i4nGDtw3+YFVVQ62p
   qSlur7F4n2lTU1OkN9qWPmlNTU29xpxOH7Zs1fr5OVd6tX2l//smElTksKZsX+ARYE3k3xeBkX4u
   5ndTUibFTLVAvX8GnZ1m111n1q/fGoPHovYLWUXFoB4JRqLzVVcPj9snLZPYik2pvR+RYuQ3Keu1
   pszMljnn6oDPRZ56wbwpTBEpM36Xf0pm1SqvzcWaNbD//ufzyCP7AgdEXv0bnZ1XE9vLS0SkFKWy
   IPnRQJWZ/QMYD9zpnBuV88hESkQh+o7lQia9wOJ9BtOnT+XWW71FxHfY4UX69/82HR1PdatDq6h4
   MeXz1dWNYtCgrYAzNj8PZzB9+vFJa6xS+X6KqUarVH7fRMpSb0NpwDORfw/Cqy/7BvC4n2E5vxua
   vpQiVwrL3WQ6LRb9Gcyf/4BNmGD2xS+aXXvt37rVQFVWDtzcr6ypqSlhfVT0+brvN9Gg2vr339ma
   mppSqrFK9v0UY41WKfy+iRQzclhT9nTk38uAYyI/L/dzMb+bkjKRwstWrdI995htv73Zj3/sLSLe
   23lTSTCSnSPTuFWjJSLp8puUpdKn7C3n3DygHrjMObc1qbXSEJESkk4vsHjWrIEzz4SHH4Y//AEO
   Oii144LVV0xEJId6y9qAbYCJwB6RxzsADX4yQL8bGikTSSifbRpSbckQu88DD5jtvLPZKaeYffhh
   z/0zbUmR7ByZTj8W4/SliBQWuZq+9M7NvsCZwOnAKD8XymRTUiYSX7bXY8z0XLHn2HrrXW3cuNds
   xx3N7r8/+XGZ9t/qrS4sk8RVNVoikg6/SZnzjk3MOXch8G3g/wEO+CZwt5ldku1RuyQxWG9xipSj
   hoaJtLaOo6tlBHhd7RcvXlCQc/U8xxq2334Fzz33VQYNSjukrMcnIpIPzjnMzKV7XCq1YccC+5vZ
   RWZ2IV5H/0npXkhEikUYr2JhLu3t7/o4Pvo/K8vZa69rMk7IgqyY2mWISLClkpS9BVRFPd4aWJWb
   cEQkVeFwmPb2d6momEa21mOsrDwL7//DxgGn8Oyz/0or0ZgwYTrO7QO8CdxJVdV3s9YjK9f9t/wk
   V5n0bhMR6SHRvCbwq8h2D/A2cHNkewtY6Geu1O+GaspEuuleXxWyiorBVltbl3G9U21tna/2Dxs3
   ml12mVlNjdm0ac/YoYfmpv4qV7VdfuvV1C5DROIhBy0xlgEW+feeyM8Or4FsSgVezrnDgF8AfYAb
   zOzyBPvtDzwKHG1m/y+Vc4vkUy6WF8rEnDnz6Oi4nK76qs7OvaipWZRxXDU1g9M+5qWX4LjjoF8/
   eOIJ2HXXLwK5qfPKVXuM2M+zazmnxsbGzaNh3uvQ1jaFhQubC/47ICKlJ2FSZmY3AzjnqoDd8RKx
   l8xsXSonds71Aa4FDsUbXXvCObfIzJ6Ps9/lQAte0icSKNn4o5ztpM6r9ZoLLAIym8KLjq2ubhRt
   bTMS9iKL3nf69Km8+mojF1wAF1wAp58OFSl2MAxakptMsoQt095tIiLdJBpCA/oBVwDtwFORrR24
   EujX2xAccCDQEvX4J8BP4ux3FvBD4CZgYoJz5WZ8USQF2VheKJt9rlpaWqyycsjm80GNVVYO9N3q
   ITa2pqamFHqB3WUVFQ/aZz/7X3v++cyv2VvsuW5JkSymbKw4ICLlhWz3KcObdrwB6B/13ADgeuCa
   Xk8MRwHXRz0+FvhVzD47Ag/hjZDdBExIcK7cfXIivQjaMj3xzldbW5e1cyWKree+T9khhxyV02ua
   5a95q5/GtCIi8fhNypLVlH0D+KyZdUaNqq11zp0CvIDXTDbpIFwvr3clfj8xM3POOZJMX86cOXPz
   z2PHjmXs2LEpnF4kc8UwReWnFiyR9vb3aWiYCHSfWly/fgBQF7XnSioqOnueIMuSTR9mU6J6tcbG
   RhYubI6abvW++3ifkYiUpyVLlrBkyZLMT5QoWwP+5ee1qH1G03368lxgRsw+rwCvRrYPgXeBcXHO
   lYM8ViR1saMo6UxZ5WL6Mldd/J0baM71Nwh1O/e995pVV3dY377XGdyS0XW96deBBqMNRvc69ZqN
   kcbo7yt6erbr59raOqutHVOQ71NESg85mL68F5gS5/lJwKJeT+zdRPAysCtQCTwNfD7J/pq+lKIQ
   hJqobK93WVtbZxUVgzcnYzDUoMXg9zZs2F9st93M/vrX7Fw3tiausnJI0nNle+1KGBB5n6HIz1tq
   8yDU6/nVBkNEepOLpGwn4HFgKXBVZFsKPAHslNLJ4XC8qc6XgHMjz50MnBxnXyVlUhRK8Y9yvPcE
   Fxp8aDvuGLa1a3N7rd4+v0ySwfjvbUJki/d88nhK8fsXkezym5Qla4mxyjl3APA14At4NWL3mdkD
   aUyN3g/cH/PcbxPse3yq5xUplHA4zLJlK/A63pey/YHDqaw8mRtvnEz//oWNJlf9yfwohhpDESlO
   yQr9iWR7D0Q2kbK2pV/ZscDZm58vhT/KWxKNGuAg4Hn22usGrrzyLCC7Re35TmpirwdnACdF/dzl
   bGBKr/HEK/wPSsIoIsXNeXlXsDnnrBjilNLW0DCR1tZxeHcBhoGZVFe/x+23X1f0f5TXr4fjj3+Z
   u+8ezOc+dyNXXvnFuN3sq6pmZKWbfb6bx8Y2yF269KluP7e3v8/atav54IOP2WWX7Zk9+4Ki/05F
   pHCcc5hZ2g3xlZSJpKh7UgbQTH39IhYvzs2SQvnyj3/A5Mmwww5www3ev11K9T3HylXyKSLlyW9S
   luKiKCISCk2lqmoG0Aw0R6a5MlviqJA2bYIrr4SDD4Yf/hD+9KfuCVk56d4LzUvOukbWRETyRUmZ
   SIq6aonq6xdRX7+oqEdSXnkFxo6FW29dzYgRp3LXXRNZvDjcY79cJ6LhcJiGhok0NEwkHO55fRGR
   suLnls18b6glRkkKcu+uIMnm++rsNJs716ymxuykk563rbfevtf+X7n6XIPUhDVIsYhI8SPbfcqC
   tCkpKz1B7nIfJNl8X6tWmR12mNm++5o9+2zh+20V+vqxSjWpF5H885uUJW2JIZIr2V7PMF/rI+Zb
   Nt6XGcyfD2ed5dWO/fSn0K9fjgIuYkHqhSYi5UlJmUhEvto05LMdRHu7l4j94x9w332w335bYmhv
   f5+KihCdnc8Ae+W935qasIqIxPAzvJbvDU1flpygTV/ma/oz3etkEtcf/2g2bJjZ9OlmH3+c+JwV
   FYOstnZMQabsNGUoIqUIn9OX6lMmBZPtEaNMzpevflx+rpPu+1q7FqZPhwcfhJtugrq6zGMQEZHU
   +e1TpunLEpXvjul+ZLuGp1RrgtJ5X0uWwPHHw6GHwooVFHzNymwpht9nEZFMKSkrQbHdydvaphR1
   T618yFd9U7zr1NWdnvHakh0dXgH/XXfBvHlwxBHdX49dZqitbUbc9xrE5Ee/zyJSNvzMeeZ7QzVl
   aQlaq4Fika/6pujrNDU1ZVzL9sQTZiNGmH3nO2bt7fGvF3uNpqamHu81qG1F9PssIsUGtcSQoAvi
   KEy0fE1/Rl+noWGi75YXGzZAUxPMnQvXXAPf/W78/eK11Vi6tGcNWam2FRERKRZKykpQEFsNaAoq
   u5591ltEfOhQWL4chg3L/Jzt7e+n9Fy+BfH3WUQkJ/wMr+V7Q9OXaQtaq4FymILy85mnO2W4caPZ
   z3/uLZM0b563bFJ61whZRcVgq62t63Gd2toxBjWbY4Eaq60dk9L7yLWg/T6LiCSDpi8lWqneiRhU
   fkcCuxY53zKtm/iYV16B447zfv773+H//i+12Lquce65l7BixXN0dl7N8uUwfnz3GGtqhgKjgUWR
   I6dQU/NqahfJMf0+i0hZ8JPJ5XtDI2VFL6hF5NmSy5HAzk5vVKymxhsl27gxNzGW+nckIpIv+Bwp
   qyhwTihlomu0pr5+EfX1i8quniwcDtPQMJGGhomEw+GEz8X697/hG9/wivmXLIFQCPr0Se3YdMX7
   joCMrpOLOEVESpafTC7fGxopk4BLNsqUqCVFb6NS8+ebbbed2YUXmq1fn9q1/MaYzv6p1ncV08ib
   atZEJJvwOVJW8IQrpSCVlEkRSPSHPd60YXX18IRTie3tXs+xESPMHn+853UymSpNJ/mId53a2rqU
   E61iubmjmJJHESkOfpMyFfqLZEk2itH//Gc46SQ4+mhv3cqqqiwFF5FpjK+/vqrkepmpP5uIBIWS
   Mil6QVrYPJ54fbamTz+dWbO2LHW09dYX07fvEk47DX7/exg7Nr3z5WtJqF122Z3Vq/0fr/5iIiJJ
   +Bley/eGpi8lgWxPPeVqKivetGHXc/vtd75tv/1HdsIJZmvWpDbFWIglobrqydKtSwt6rZamL0Uk
   2/A5fem8Y4PNOWfFEKfkX0PDRFpbx9E19QTe3YOxSwgV6nzJrFsH550Hd9wBv/0tHHlkz35nVVUz
   AnenatCXy/KjFN+TiBSOcw4zc+kep+lLkQJYtsxbJmnPPWHlSqip8Z4vhvqmUmzkWorvSUSKj/qU
   SVELhaZSVTUDaAaaI3VLU3s9LlH/LL/nS9WGDfCzn8Hhh8ORR67kv/+dyPe/n14Pr3A4zKhRY+nf
   fxgDBuzM7rvXMmrUQTnpBZaLPmPqXSYikoCfOc98b6imTJJIt26ptxqiXNVBPfec2X77mTU2mt12
   20MJe4D1Fltl5RCDUI91KiGU1XqoXNRaqX5LRMoB6lMmkpp898/atMnsqqu8ZZLmzvWWTUoWQ7Kk
   cMtxPY/vei5b7yUXn1Ox9C4TEcmE36RMNWUiGeitQPy117xFxDduhMceg+HDez+n6ptERMqUn0wu
   3xsaKSs7fqYkU90/W1Noyc7T2Wl2ww3e6NgVV/RcRDz22IqKQVZbOyal2It9+tKL3ztnZeWQHuds
   aWmx2to6q64entJnIiISNGj6UkpFttZo7O0amdaNJZqKe/ttsyOOMKutNXvmmeQx1NbWWUXF4EiS
   lXrstbV1tu22O1j//p+x4cP3sdraMTnpBZbt+jovKRtoMNpgtFVWDkxQM7cl2YzdR0Qk6JSUSclI
   t+6oUHVK8a67114/t+22Mzv/fLNPPvF3jlKusert/cZ7HUaX9GciIqXHb1KmmjIRn+rqRvHAAyE6
   O+cCh9Knzyg++GAif/wjfOlLhY5ORESKjp9MLt8bGikLtFxMcWV7+jK3MbYavGUHHvh3++ij5MfE
   W2op37EXUuotPzR9KSLFC01fSiHkc61Iv/vnIsba2jEGBxuEDT42aEk6xZYshnzHXmi9fbcq9BeR
   Yuc3KdPal5KRfK4V6Ve2YwyHwxx++DWY3Qm8A3wd+Cb19a8mPKffGIrh8xURke78rn2pZZakV1oW
   Z4t16+Dkk9dhdjfQH9gDOJ+KipvTWI4pDMxl2bIVRfd56ndBRCSH/Ayv5XtD05cFk0oNUNCn17IV
   47JlZl/4gtl22z1icEe3OwRra+sSXru+foLV1tZZ377bGIwwGJhyDVlTU1NgPt9i+K5FRIIA1ZRJ
   LqTSsqEYCtEziXHDBrOLLzYbMsTsttvM7r8/teQkNomBAQZfTPp5xkt8mpqaAvH5llv7DhERv/wm
   ZWqJIRkrhmWB/Mb4z3/C5MkwcCA89RTstBNAIwsXNkctr9Qc99xz5syjo+NyttSDAVyS9Hqxx3R0
   wNKlqiETESkHSsokqVBoKm1tU+jo8B5XVEyjvX1PwuFw4BOxTNx/f5hp097ilVeO4uSTV/HLX+6J
   iyrZ9J+Ibg/M2PyoqmoGoVBzxvHmQ+zvQjHFLiJSFPwMr+V7Q9OXBeV3OaBMrxlvyi7XU6UtLS32
   hS8cbbDE4CmDo3z3yYo/fTnCYKJVVAy22tq6Hm0xamvHdOvTFbS6rWKYqs6mcnu/IpIdqKZMcimf
   9USJCspzXWh+//0t1q/fmQYfGvzMoHlzA9Pa2jG+30tsQltRMciampq67RP9viorB1ptbZ0SgQLT
   jQ0i4pffpEzTlxI48eqquuq34j2fjWnUd96BSZOq2bDhQuACYB9g8ubXX389eS1YIo2NjcyZM4/O
   zm2MticAABi6SURBVDmb4+7s9OrEzjvP2yf2/a5fDzU1qiMrtES/h6U8bS8ihaU+ZZKSUGgqVVUz
   gGagOVJPlGpfLr/CwERgLu3t78bdo739/e5HJOijlay/1t13wz77QP/+bwD3AW/0uM4uu+yU4XsR
   ERHphZ/htXxvaPoyEPJVX+OtfzjQoCZqSm+INTU1JV0XMd1pz9WrzY45xmyPPcwefTT6+FCPaydq
   eZHK55FJrzfVNBWOpi9FxC9UUyalpLa2Lm4Nm7fm5GiDCQYt3WrbEtW9xXu+tvZi22kns9NPt26L
   iEcX3Cer6/KzaHpv6z36WaxccktJsYj44Tcp09qXEkiJ1nwEYp4/m+rqe9h335G0t7/P8uXHp3DM
   C2y9dTV/+tMQDjkku/Flsw5M616KiBQnv2tfqtBf8i4cDkc1Xp0at3A6WU+sLc8/A1zP6tW/pLUV
   KivPorLyHNavT3TMEOAg+vR5mt//voZD0sjIYmPOlejrJKqjExGREuVneC3fG5q+LBnpTMn11qus
   unp4nGnJMT2OWbfO7NvffsUqK1fbyJGXpT0NlWjpo2xPLfZsjTEkUlun6UsRkWKCpi+lGGRzSi6V
   cz39NEyaBHvsAXPnwnbbZS/mUGhqryN+mV6ntvYmamoGZ+0aIiKSe5q+lJSkMnVYLJJNcW7cCJdf
   DtdcA3PmwLHH0m2ZpGzIx5qfNTWD4yaspfQ9iohIhJ/htXxvaPoyK4JwN9+WdhejDUb7WsIoelqz
   qampx3TlP/9pdsABZoceavbGG9mJOR8tK1L9fnL5Pfp5P7pDUUSkO9QSQ3qTz6WSEvGSsiHd6qbS
   +UOeLCHZtMnsmmvMBg82u/Za73E65w1Cy4pUEpxcfY9+3k8QEn0RkaBRUia9CkJSlmkMiY5//XWz
   r33N7MADzf71r/Ri8ptYFOrzzNV1/Zw3CL9TIiJB4zcpU01ZGUlWg1XM3n77YPbdF0IhOOcc6NMn
   veOLbY3DUv0eRUTKnZKyMtLY2MjChc1RBeLNeU88Mk0oQqGpLF06KdKLbGuc246PP57AX/4CI0fm
   JOSksRQiOcrV9+jn/ShBFBHJHrXEkLxL5c7BRPuEw2HGjfsu69efApxNRUUz99zzRY48siGjeMaP
   nxIZLfMSi4ULU0t0Su0uSD/vp9Q+AxGRTPltiaGkTAInWZJ08MGTWLJkJjA8snd2lh5SYiEiItmi
   PmVSMhLVeDnXyKOPXg20p3SedBKtfPQcExERSUZJmRSBvjz//A849tgOdtqpiVdfvYXOzquBxDVM
   saNtbW1TUp6SFBERKQQlZRI43YvHh+DcgdTU/I9//nMk7713HtCXiooQI0d+kdmz4ydaxXZHpYiI
   SEWhAxCJ1djYyJ133sKuu/ansvJAzjtvDUOG/Ix1687DS7J+TmfnHGpqBivJEhGRkqGkTAJnxQo4
   //wGRo6cwBtvDOKSS2rTPkcoNJWqqhlAM9AcmeacmvVY8yEcDtPQMJGGhomEw+FChyMBpd8TkRLg
   p+NsvjfU0T/QsrX24YYNZpdealZTY3bzzWadnd2v4WcJoGJfkzHfyxiVwmdWjrTclUiw4LOjv1pi
   SEYy6fEV7cUXYfJk2GYb+N3vYOed41+r3NpWNDRMpLV1HF21cdlqARJPtr5Lyb98/p6ISO8C2xLD
   OXcY8AugD3CDmV0e8/oxwI8BB3wInGpmK3Mdl2RHpgX1nZ3w61/DzJlw0UVw2mlQkWBSXW0rcks3
   R4iIFFZOkzLnXB/gWuBQ4C3gCefcIjN7Pmq3V4CvmtmaSAI3Dxidy7gkGN58E044AT78EB55BD77
   2UJHFDxaxkhSod8TkdKQ60L/LwEvmdlrZrYBmA98M3oHM3vUzNZEHv4d2CnHMZWkQhX5+imoN4Nb
   boF994WDD4a2NiVkiXStc1lfv4j6+kU5nU4spZsjyk0+f09EJHdyWlPmnDsKaDSzkyKPjwUOMLPT
   E+x/NvBZM5sa87xqypIodC1QOrVe//kPnHwyvPQS3Hor7LNPXkKUFJVj3Z6ISLYFcu1L59xE4LBU
   kjLn3MHAdcAYM/sg5jUlZUkUS5HvwoXwwx/ClCnws5/BVlsVOiIREZHsC2qh/1vAZ6IefwZYFbuT
   c25v4Hq8BO6D2NcBZs6cufnnsWPHMnbs2GzGKVkUO9pywAGNnHkm/O1vcPfdMGZMgQMUERHJoiVL
   lrBkyZKMz5PrkbK+wAvAIcDbwOPA96IL/Z1zOwMPAsea2WMJzqORsiQKPX2ZLJbKyj/x6U/fwlFH
   VXHFFbDttomP07SZiIiUgkBOXwI45w5nS0uMG81stnPuZAAz+61z7gZgPPBG5JANZvalmHMoKetF
   UJKanlOpHzFq1ByWLbswYYxBSioleILyuy0ikqrAJmXZoKSseHhJ2QnAEZFn7qC+/m5CoakJE6+e
   idzZVFffw777jtQf4TKnhF1EipHfpExrX0o3sa010mm1sX49VFdfCewPPITXVmEaodDUmMak3h/Z
   rtGPmAiAZlavvoDW1nGMHz9l83UzbfuR7HitGxhMqf/eiIgUv5x39JfiETsqsXTpJGAD69f/AoC2
   tikJRylWrvSWSdpll//jjjse4ne/uxaAUMjbP9kf0u6NL+cCPye2qzzQLbZksaTy3qKPT/aaiIhI
   3vhZMDPfG1qQPC/q6ydEFjS2yHazwehuj+vrJ3Q7ZuNGs9mzvUXEb7qp+yLi0XpbMLlrIezq6uE9
   YuhaIDve85m8t67jMz235I4W2haRYoTPBck1fSm+vfgifOUrsHgxPPkkHHccuAQz6F0dx2trr6e6
   +hJGjBjR4/XFixdw++3Xqau8bKZO9SJSVvxkcvneKLGRsq5Rofr6CYH6v/7YUYnKyiH/v707D5ar
   rhI4/j1h4kxUGEaScgEFRCtDmBADCAyjBJUyCUosRKB0BoEgDCrEJYzgUgyDAuq44FYsAREKJGhi
   KUogCYQkA0rYQkiIsUREBSQlAVkkJCHvzB+3H3l03tLvpbtv9+vvp6orfbtv3z79ftWdU+f+7vnl
   y16241ZViq6uzO99L3OHHTbk2LGX5qGHHlnT56i16tHb32dbKyb9vd5qjCSpnhhipcyrL5us1a8m
   q24/ALxke6+9JjN9Ovzxj3/loYfey4YNJwG1fY7eVh6YOPFyRo/e6cXj9/f6bW2N0N/rbbsgSaoX
   W2K0iXZZEqlaJlx1FcycCTNmwOLFR3Hzze9lMJ+jt88+YsRMurq+DrRegipJ0lC06jJLGgb+8hc4
   5RT4zW9g/nyYOBGWLu0a9HFeepUljBjxKbq6plN9paVJmSSpEznRv8lmzjy5rSayX3cdTJgAe+xR
   TOafOLF4vK/P0V+/r+pJ2xMmjAPGN/sj1ZX9zSRJ9eLpyxK0w/ylp56CT34Sli6FH/yguMqyWm/z
   zwYzX67V59cNpN3jlyQ1hnPKVDeLFsEJJ8DUqfC1r/W9iHi1ocyXa4cEtS/tOj9QktRYzinTNnvu
   OfjsZ2HuXLj0UpgypfHvOXny5LZKxCRJahSTMgGwbFmxTNK++xZLJr3qVYM/RvVE/mKe2RX1DbSF
   dNrnlSQ1lqcvO9zGjXDOOTBrFnz3u3DUUdt2vHY+HTkUnfZ5JUkDc06ZBm3VKjj2WNhllyIpe81r
   yo5IkqT2N9SkzJYYHWjzZvjqV+Ed74DTTivaXpiQSZJULpOyDvO738GkSTBvHtx5J0yfXiwibr8t
   SZLKZVLWITLhoovgwAPhAx8o2l7stlvxXHe/rYULp7Fw4TSOOOI4EzNJkprMqy87wCOPwIknwrp1
   RTPYPfd86fNf//ollQaoLnckSVJZrJQNY5lw9dXF0kgHHQS//OXWCZkkSWoNVsqGqccfh49+FFav
   hhtuKPqP9cV+W5Iklc9K2TD085/D3nvDrrvC3Xf3n5DB1guFu36jJEnNZ5+yYeTpp4tFxBcvLhYR
   P/jgsiNSTzaalaTOYJ+yDnfLLUV1bORIWLGiPgmZbTLqxytcJUkDsVLW5tavLxYRnzMHLrkEDjus
   PsftTiKKqzKLeWae1hy6d7/7SBYunEb3Fa5QnC5esGBumWFJkhrASlkHuuOO4srKtWuLRcTrlZBB
   dZuMIjnrPvU2HFkVlCSVzasv29DGjfClL8HFF8N3vgNHH112RO2tuip4663H1b0q6BWukqSBePqy
   zaxaBR/+MLz2tXDppcW/QzHQpPNOOn3ZrFOLTvSXpM4w1NOXVsraxObN8I1vFAuJn39+0aE/Bj3c
   hVoqQ91tMrYkEcXzJhZDN3nyZP9ekqQ+WSlrAw8+CMcdByNGFK0udt9924431MrQcK2eDdfPJUkq
   hxP9h6HM4orKAw6AI44o2l5sa0L2UvOBI4GLePzxtQPuPVwn/9s8V5LUCjx92aIefRQ+8pHiysol
   S2DcuPode9Kkfbjppk9RJPEnANO4//7/Yv78+R2bjHhqUZJUNitlLWj27KLVxf77w+231zchmz9/
   Puee+x0yvwl8A7gKeA0bN/7vgFWvmTNPZtSoM4ArgCsqVxCeXL/gJEnqYFbKWsi6dfCxj8HKlXD9
   9bDffvV/j5eegux2CTBtwNf2NflfkiRtOytlLeL664tlknbeuVhEvGdC1vjGpo/WXPWaPHkyCxbM
   ZcGCuSZkkiTVkZWykj39NHz603DzzfDDH8KkSS99vt6NTaubmI4Y8SkmTBjH+edvfUzbX0iS1Dy2
   xCjRkiVw/PFw6KFFD7Ltt996n3o1Nu2ZYE2atA9LltwD9J1s2SZCkqShsXlsG1m/Hj7/ebj22qLl
   xXve09j327raNnCCVT33bP364jGTMkmSGsOkrMnuuqtYJmn8+GIR8Z126n//eqyZaIIlSVLrc6J/
   k2zaBGefXVTFzjqrqJINlJBBeY1Nh3v7i8ZfPCFJ0uA4p6wJVq8uqmNjxsBll8HrXtfc9x/q/LDh
   OtHf+XKSpEYa6pwyk7IG2rwZLrgAvvxlOPdcOOmkoS8ivq3qmWC1e7JWr4snJEnqjRP9W8zvf19c
   WZkJy5bBG99Ybjz1Wkao3i06JElSwTlldZYJs2YVSyQdfnixiHjZCVk9DYdFyYf7fDlJUnuyUlZH
   f/5zsYj4Y4/B4sWw115lR6TeuFyUJKkVOaesTq69FmbMgFNOgS98AUaOLDuixnCSvCRJ/XOif0nW
   rYOPfxxWrIArr4S3vrXsiBqv3Sf6S5LUSCZlJZg3r7ii8uij4bzzYNSosiOSJEll8+rLJnrmGZg5
   ExYuhKuvhkMOKTsiSZLU7rz6cpCWLoUJE4oeZCtWmJBJkqT6sFJWo+efLxYRv+YauPjiot2FJElS
   vZiU1eDuu4tlksaNKxYRHz267IgkSdJw4+nLfmzaBOecA1OnFlWyH/3IhEySJDWGlbI+/PrXRXVs
   p51g+XLYeeeyI5IkScOZlbIqXV3FIuIHHwwnngg33GBCJkmSGs9KWQ8PPQQnnFCctrz9dthjj7Ij
   kiRJncJKGcUi4pddVnTjnzoVliwxIZMkSc3V8ZWyxx4ruvI//DAsWgTjx5cdkSRJ6kQdXSn78Y/h
   LW8pbsuWmZBJkqTydGSl7Ikn4NRTi/5jP/sZHHBA2RFJkqRO13GVshtvhL33hjFjilYXJmSSJKkV
   dEyl7Nln4fTTi6Tsyivhne8sOyJJkqQtOqJSduutxSLiGzYUi4ibkEmSpFYzrCtlzz8PZ50FV10F
   F10E06aVHZEkSVLvhm1Stnw5HHssjB1bVMfGjCk7IkmSpL4Nu9OXL7wAX/wiTJ4MZ54Jc+aYkEmS
   pNY3rCpla9YUi4jvuCPccw/sskvZEUmSJNVmWFTKurrgW9+Ct72tWLty/nwTMkmS1F4aWimLiCnA
   BcB2wKWZ+ZVe9vk2MBV4Djg+M5cP5j3+8IciEduwoVhE/E1vqkfkkiRJzdWwSllEbAd8F5gCjAM+
   GBF7Vu1zGPCmzHwzcDJwYa3Hz4TLL4f99ivmjy1dakLWqhYvXlx2CBoix669OX7ty7HrTI08fbk/
   8EBmPpSZm4DZwPuq9pkGXAGQmcuAHSPi1QMd+LHH4H3vK05ZLloEZ5wB221X7/BVL/64tC/Hrr05
   fu3LsetMjUzKdgb+1GP74cpjA+3T72ywOXOKBcTHj4c77nARcUmSNDw0ck5Z1rhf1PK6J5+E004r
   ErGf/hQOPHDbgpMkSWolkVlr7jTIA0ccCJydmVMq258FunpO9o+Ii4DFmTm7sr0GmJSZa6uO1Zgg
   JUmSGiAzq4tOA2pkpewu4M0RsRvwKHAM8MGqfa4DTgVmV5K4v1YnZDC0DyZJktROGpaUZeYLEXEq
   MJ+iJcZlmfnriPjPyvMXZ+a8iDgsIh4A/gac0Kh4JEmSWlnDTl9KkiSpdi3V0T8ipkTEmoj4bUSc
   0cc+3648vyIiJjY7RvVuoLGLiH+vjNl9EXFbROxdRpzqXS3fvcp+b42IFyLi/c2MT32r8XfzkIhY
   HhGrImJxk0NUP2r47RwdETdGxL2V8Tu+hDDVi4j4fkSsjYiV/ewzuJwlM1viRnGK8wFgN2AkcC+w
   Z9U+hwHzKvcPAG4vO25vNY/dvwL/WLk/xbFrnVst49djv0XAL4Ajy47bW83fvR2B+4FdKtujy47b
   26DG72zg/O6xA9YBf1d27N4S4O3ARGBlH88POmdppUpZw5rNquEGHLvM/FVmPlXZXMYA/ejUVLV8
   9wBOA+YAf2lmcOpXLWP3IWBuZj4MkJmPNzlG9a2W8fszsEPl/g7Ausx8oYkxqg+Z+X/Ak/3sMuic
   pZWSsoY0m1VT1DJ2PZ0IzGtoRBqMAccvInam+M+ieyk0J6O2hlq+e28GXhURt0TEXRFxbNOi00Bq
   Gb9ZwF4R8SiwAvhEk2LTtht0ztLQBckHqa7NZtVUNY9BRLwDmA78W+PC0SDVMn4XAGdmZkZEsPX3
   UOWoZexGAvsA7wJeDvwqIm7PzN82NDLVopbx+xxwb2YeEhF7AAsjYkJmPtPg2FQfg8pZWikpewR4
   fY/t11Nklf3ts0vlMZWrlrGjMrl/FjAlM/sr+aq5ahm/fSn6CUIxr2VqRGzKzOuaE6L6UMvY/Ql4
   PDPXA+sjYikwATApK18t43cQcC5AZv4uIn4PjKXoBarWNuicpZVOX77YbDYiXkbRbLb6B/864MPw
   4ooBvTabVdMNOHYR8QbgJ8B/ZOYDJcSovg04fpn5xszcPTN3p5hX9lETspZQy+/mz4C3RcR2EfFy
   ignHq5scp3pXy/itAQ4FqMxHGgs82NQoNVSDzllaplKWNpttW7WMHXAW8E/AhZVqy6bM3L+smLVF
   jeOnFlTj7+aaiLgRuA/oAmZlpklZC6jxu3cecHlErKAopHwmM58oLWi9KCKuASYBoyPiT8B/U0wX
   GHLOYvNYSZKkFtBKpy8lSZI6lkmZJElSCzApkyRJagEmZZIkSS3ApEySJKkFmJRJkiS1AJMySaWK
   iM0Rsbxyuycido2I2yrP7RoRH+yx74SImDqE91gcEfvWIda6HEeSetMyzWMldaznMnNi1WPda6Pu
   DnwIuKayPZFiyacbBvkeSX3Wya3XcSRpK1bKJLWciHi2cvfLwNsrVbTPAP8DHFPZPioiXhER34+I
   ZZUq27TK60dFxOyIWB0RPwFGUbUwcERMiYgf9dg+JCJ+Xrl/YUTcGRGrIuLsAWIkIj4QEZdX7o+J
   iDkRcUfldlDl8UlVFcFX1unPJWmYsFImqWyjImJ55f6DmXkkW6pRZwCnZ+bhABGxFtg3M2dUts8D
   bs7M6RGxI7AsIm4CTgGezcxxETEeuIetK1w3ARdHxKjKYt3HsKUi97nMfDIitgNuiojxmbmy6vXZ
   x/1vAd/MzNsqa77eCIwDZgIfy8xfVdag3DDYP5Sk4c2kTFLZ1vdy+rJb9LLd87F3A4dHxOmV7b8H
   3gC8nSI5IjNXRsR91QeurDt4IzAtIuYChwHdxzkmIk6i+I18LbAnUJ2U9eVQYM/KGq8A20fEK4Db
   gG9GxNXATzLzkRqPJ6lDmJRJaie9zed6f2b+tucDlYSoOqHrzWzgVOAJ4K7M/FtE7E5R1dovM5+q
   nJb8hwFiGdXz7YEDMnNj1f5fiYhfAO8BbouIyZn5mxpilNQhnFMmqZU9A2zfz/Z8YEb3RkR0V9yW
   UlwgQET8C7B3H8dfAuwDnMSWU5c7AH8Dno6IVwN9Xe25NiL+OSJGAEewJUlbUBXTWyr/7pGZ92fm
   V4E7gbF9HFdShzIpk1S23qpf3Y+tADZHxL0R8QngFmBc90R/4IvAyIi4LyJWUVwIAHAh8MqIWF15
   7K5e3zizC/gFMKXyL5m5AlgOrAGuBm7tI+4zK6+5DXi0x+MzgP0iYkVE3A+cXHn8ExGxMiJWABsZ
   /BWkkoa5yPTqbkmSpLJZKZMkSWoBJmWSJEktwKRMkiSpBZiUSZIktQCTMkmSpBZgUiZJktQCTMok
   SZJagEmZJElSC/h/Tsfl2hav/qoAAAAASUVORK5CYII=
   "
   >
   </div>
   
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p>Plot yhat vs. Pearson residuals:</p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[13]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">()</span>
   
   <span class="n">ax</span><span class="o">.</span><span class="n">scatter</span><span class="p">(</span><span class="n">yhat</span><span class="p">,</span> <span class="n">res</span><span class="o">.</span><span class="n">resid_pearson</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">hlines</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">set_xlim</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">set_title</span><span class="p">(</span><span class="s">&#39;Residual Dependence Plot&#39;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">set_ylabel</span><span class="p">(</span><span class="s">&#39;Pearson Residuals&#39;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">set_xlabel</span><span class="p">(</span><span class="s">&#39;Fitted values&#39;</span><span class="p">)</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt output_prompt">
       Out[13]:</div>
   
   
   <div class="output_text output_subarea output_pyout">
   <pre>
   &lt;matplotlib.text.Text at 0x7fb596e897d0&gt;
   </pre>
   </div>
   
   </div>
   
   <div class="output_area"><div class="prompt"></div>
   
   
   <div class="output_png output_subarea ">
   <img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAmkAAAG8CAYAAACFajLTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzt3XmcHGd95/Hvb7AHxsRGHsvYYAx2xE2MaU5lRdCQMDNO
   ALGyQghXxLGIkAQneABxBNCCHDCJOAJZghxja80Vb4zATsi0BWEAOQmX5QMbh/sGg7DNObs+9Ns/
   qlrTavVRVV3HU92f9+tVr5np6e56uqqm6jvPVebuAgAAQFgmqi4AAAAADkdIAwAACBAhDQAAIECE
   NAAAgAAR0gAAAAJESAMAAAgQIQ1AYmb2TDNr9vn9kpk9P4f1zJjZd4Z9nxCY2TYzu6jqciQxStsd
   GAWENGBEmdk3zexXZvZzM/uhmV1kZscM857u/j53n+/3lHgplJkdMLNfxJ9tv5l9zMz+oOj1ZhTU
   ZJRm9hwzuyPedj81s31m9sQM73Ohmb2hiDICiBDSgNHlkp7k7kdLOl3SaZL+stoi5eqh8We7v6QL
   Jb3TzF5bbZFq44p4262SdL6ki81sVcVlAtCBkAaMAXe/UdLlkh7SeszM1prZv5vZzWZ2lZmtb/vd
   c8zsa2b2MzP7upk9o+3xT7c9b9bMbjCzW8zsHZKs7XeHNPOZ2SlxDdhE/PNzzez6eB1fM7MtGT/b
   Te7+XkkvkvRKM5uO3/9uZna+mX3fzL5rZm9oW/dzzOwKM3tHXPYvmdlvt5V10Gv3mtlfm9lN8fY5
   o+21p5rZJ+PPdbmk1e3lHbDdl8zs9fH7/8zMmmZ2XNvvH9v22m+b2eb48Tub2d+Y2bfiWtN3mdld
   +mw2i7edS7pA0pSkXz/sSWYPist0s5l90cyeHD++RdIzJL08rpH7SKKdBSAVQhow2kySzOxeks6Q
   9Jn455Mk/bOk17v7sZJeKukSMzvOzO4q6e2SznD3YyT9pqSrDntjs9WSLpH0KknHSfqapHVtTxnU
   zHejpCfG63iupLeaWSPrB5V0qaQjJD0q/vlCSbdKWiOpIWlO0v9oe/6jJX01LvvrJH2orTYpyWtv
   iF/7ZkW1US3vl/S5+HdvkLRZ8bbot93bXv90Sc+RdHdJk/FzZGb3kfRRRftmtaSHaWW/vEnSfRXV
   mN5X0kmSBtYqmtkR8ef6uaSvdPzuSEmXSVqUdLykF0t6n5nd3913SnqfpHPd/Wh3f8qgdQFIj5AG
   jC6T9GEz+5mkbysKUdvj3z1L0kfdfVGS3P1jkj4v6YmKAsUBSaeZ2ZS73+ju13d5/9+T9EV3/5C7
   3+Hub5P0w4719+TuH3X3b8Tff0pRTd9vZfyscvfbJO2XNG1mJ0j6XUkvcfdld/+xpLdJ+sO2l/zI
   3d8el/1iSf8l6UkJX/stdz8/ron635LuYWZ3N7N7S3qkpNe4+23u/mlFQael33aXom1/gbt/1d3/
   r6SLFYUxKaq52uPu/xiX+SZ3v9rMTNILJJ3t7re4+y8kvbGjvJ3WmtnNkn4g6WmSNrr7zzufI+mu
   7v4md7/d3T+hKGA+Pf69acA+BjCcI6ouAIDCuKSnuPu/mdnjFIWFR0r6rKT7SHpqq/kqdoSkf3P3
   X5nZ0xTV4JxvZldIWnD3/+p4/3tK+m7HY4lHBprZ7yqqwbqfon8Yj5J0TeJPd/j7HamoxucmRZ/v
   SEk/iDKMFK/j220v+V7HW3xL0We6d4LXHgyj8faSpF9TVPt1s7svd7zvyfH3Pbd7t/eWtBy/r+L3
   +LoOd7yibfeFtvKa+v8T/p/uPigQ31OH78/WNpICGxABjCJCGjAG3P1TcZ+xcyU9XlHguMjdu/YD
   c/fLJV1uZneWdI6k8yQ9ruNp35d0sJkrrtE5ue33v1AUHlpObHvunRU1lT5L0kfc/Q4z263hamae
   Iul2RSH0LpL+n6Tj3P1Aj+ef1PHzfSR9RFEwGfTaXn4g6VgzO8rdf9X2vnfE3/fd7gN8W1Eza6f9
   isLcg939Bxnet5fvSzrZzCyuMZSiz3JD/D0hDSgYzZ3A+HibpEeb2WMkvVfSk81szszuZGZ3sWiO
   rJPiZrunxH3TbpP0S62EjHYflfQQM9sY9206S21BTFF/qceZ2clmdjdJr2z73WS87Jd0IK5Vm0v5
   eVr97abN7JmS3inpTe5+cxxWLpf0FjM72swmzGxNXKPYcnczO8vMjjSzp0p6oKKmyB8meG1X7v4t
   Rc2X/zN+38dKelLbU3pu987P1cX7JT3BzJ5qZkfE/QdPj4PkeZLeZmbHx9vkJDNLuz07fUbSrxQN
   DjjSzGbiz/LB+Pc3qstgAwD5IaQBY8Ld90vaJWmru39XUc3TqyT9SFEtzYJWmsleoqg58CeK+om9
   qPU28dJ6v6cq6rS+X1GH9b1t6/uYpH9U1IT5OUXNra3X/lxRqLtYUfPk0xXVYh1S5AEf6Woza3V4
   f56kv3D3bW2//yNFQfD6eB3/R4eGyM8oamr9saIO/pvc/eYEr+02F1z7z8+Q9Jj4da9VtM0Vf+5+
   273be7Vv728r6ge4oGi/7JP00Ph5WxUNgvhPM/uppD2KpibpZtBcdq313SrpyYr65/1YUQh+trt/
   OX7e+ZIeHI/8/FCf9wOQka3UYpe8YrOTFXW4vbuik8JOd/9bi4bP/6OiavVvSvoDd7+lkkICGElm
   9hxJz0/QLwsAKlNlTdptikZPPUTRKKI/NbMHSXqFohFM95f08fhnAACAsVJZSHP3H7r7VfH3v5D0
   JUUdeTdopXlgl6T/Xk0JAYywUm5fBQDDqKy585BCmJ0i6ZOSfkPSt+NJHlujxW5q/QwAADAuKh84
   YGa/pmgo/p93TqYYD/uuPkUCAACUrNJ50uLJJy9RNG/Qh+OHbzSzE939h2Z2D0UjoDpfR3ADAAC1
   4e6p54GsrCYtbso8X9L18e1kWi5VdK87xV8/3PlaSXJ3lpour3vd6yovAwv7bxwX9l29F/ZffZes
   qqxJW6dotvFrzGxf/NgrFc25dLGZPV/xFBzVFA8AAKA6lYU0d9+r3jV5TyizLAAAAKGpfOAAxs/M
   zEzVRcAQ2H/1xb6rN/bf+AliCo60Dr3fLwAAQLjMTF6ngQMAAADojZAGAAAQIEIaAABAgAhpAAAA
   ASKkAQAABIiQBgAAECBCGgAAQIAIaQAAAAEipAEAAASIkAYAABAgQhoAAECACGkAAAABIqQBAAAE
   iJAGAAAQIEIaAABAgAhpAAAAASKkAQAABIiQBgAAECBCGgAAQIAIaQAAAAEipAEAAASIkAYAABAg
   QhoAAECACGkAAAABIqQBAAAEiJAGAAAQIEIaAABAgAhpAAAAASKkAQAABIiQBgAAECBCGgAAQIAI
   aQAAAAEipAEAAASIkAYAABAgQhoAAECACGkAAAABIqQBAAAEiJAGAAAQIEIaUIFms6m5uU2am9uk
   ZrNZdXEAAAEyd6+6DKmZmdex3IAUBbSNGzdreflcSdLU1Fbt3r1L8/PzFZcMAFAEM5O7W+rX1THs
   ENJQZ3Nzm7RnzwZJm+NHdml29lJdfvklVRYLAFCQrCGN5k4AAIAAHVF1AYBxs7CwRXv3btbycvTz
   1NRWLSzsqrZQAIDg0NwJVKDZbGrHjp2SotBGfzQAGF217JNmZu+R9ERJP3L30+LHtkn6H5J+HD/t
   le6+2PE6QhoAAKiFuvZJu0DSGR2PuaS3uHsjXha7vA4AAGCkVRrS3P3Tkm7u8qvUaRMAAGCUVF2T
   1suLzexqMzvfzFZVXRgAAICyhRjS3iXpVEkPk/QDSTuqLQ4AAED5gpuCw91/1PrezP5B0mXdnrdt
   27aD38/MzGhmZqboogEAAAy0tLSkpaWlod+n8ik4zOwUSZe1je68h7v/IP7+JZIe5e7P6HgNozsB
   AEAtZB3dWWlNmpl9QNJ6SavN7DuSXidpxswepmiU5zckvbDCIgIAAFSi8pq0LKhJAwAAdVHXedIA
   AADQBSENAAAgQIQ0AACAABHSAAAAAkRIAwAACBAhDQAAIECENAAAgAAR0gAAAAJESAMAAAgQIQ0A
   ACBAhDQAAIAAEdIAAAACREgDAAAIECENAAAgQIQ0AACAABHSAAAAAkRIAwAACBAhDQAAIECENAAA
   gAAR0gAAAAJESAMAAAgQIQ0AACBAhDQAAIAAEdIAAAACREgDAAAIECENAAAgQIQ0AACAABHSAAAA
   AkRIAwCgj2azqbm5TZqb26Rms1l1cTBGzN2rLkNqZuZ1LDcAoF6azaY2btys5eVzJUlTU1u1e/cu
   zc/PV1wy1ImZyd0t9evqGHYIaQCAMszNbdKePRskbY4f2aXZ2Ut1+eWXVFks1EzWkEZzJwAAQICO
   qLoAAACEamFhi/bu3azl5ejnqamtWljYVW2hMDZo7gQAoI9ms6kdO3ZKikIb/dGQFn3SEBROagAA
   RAhpCAajoQAAWEFIQzAYDQUAwApGdwIAAIwQRncid4yGAgBgeDR3ohAMHAAAIEKfNAAAgADRJw0A
   AGCEENIAAAACREgDAAAIECENAAAgQIQ0AACAAFUa0szsPWZ2o5ld2/bYtJntMbMvm9nlZraqyjIC
   qEaz2dTc3CbNzW1Ss9msujgAULqqa9IukHRGx2OvkLTH3e8v6ePxzwDGSOv+r3v2bNCePRu0ceNm
   ghqAsVP5PGlmdoqky9z9tPjnGyStd/cbzexESUvu/sCO1zBPGjDCuP8rgFEySvOkneDuN8bf3yjp
   hCoLAwAAUIWg793p7m5mVJkBY4b7vwJAmCHtRjM70d1/aGb3kPSjbk/atm3bwe9nZmY0MzNTTulq
   intpok7m5+e1e/eutmN2F8csgNpYWlrS0tLS0O8TYp+0N0v6ibufa2avkLTK3V/R8Rr6pKXQ6oS9
   vHyupKhWYvduLnoAAJShljdYN7MPSFovabWi/mevlfQRSRdLurekb0r6A3e/peN1hLQU6IQNAEB1
   soa0Sps73f3pPX71hFILAgAAEJgQ+6QhZ3TCBgCgfirvk5YFzZ3pMXAAQN1xHkNd1bJPWlaENAAY
   LwyAQp0R0gAAI4sBUKizUbrjAAAAwNhj4AAAIHgMgMI4orkTAFALDBxAXdEnDQAAIED0SQMAABgh
   hDQAAIAAEdKAEddsNjU3t0lzc5vUbDarLg4AICH6pAEjjAlAAaB6DBwAcBgmAAWA6jFwAAAAYIQw
   mS0wwpgAFADqi+ZOYMQxASgAVIs+aQAAAAGiTxoAAMAIIaQBAAAEiJAGAAAQIEIaAABAgAhpAAAA
   ASKkAQBqgfvQYtwQ0gAAlUkavFr3od2zZ4P27NmgjRs3E9Qw8pgnDQBQiVbwWl4+V1J0R4zdu3d1
   nXCZ+9CizrLOk8ZtoQAAldixY2cc0KLgtbwcPcZdMYAIIQ0AEDzuQ4txRJ80oCJ0gsa4W1jYoqmp
   rZJ2SdoVB68tXZ87Pz+v3bujJs7Z2Ut7NosCo4Q+aUAF0vTFAUZZs9nUjh07JUWhjb8BjCJusA7U
   CJ2gAWB8cIN1AACAEcLAAaACdIIGAAxCTdqIolN62OgEjVHC+QYoBn3SRhCd0gGUhfMNMBh90nDQ
   oRNERifP1ugpYJxR45M/zjdAcQaGNDP7CzO7m0XON7N9Zsa/SABqhXs/AqibJAMHnufub4uD2bSk
   Z0u6SBJnt0DRKR04HLcgKgbnG6A4SUJaqw31iZIucvcvmqVuVkWJWp3SVyaIpH8IgGJwvgGKM3Dg
   gJldKOmekn5d0umS7iTpE+7+iMJL17tMDBwAkAod3AFUpbA7DpjZhKSGpK+5+y1mdpykk9z9mmxF
   HR4hDUAW3IIIQBVyD2lm9ghJ3X5pktzdr0y7srwQ0tAPF2IAQEiKCGlL6h7SJEnu/vi0K8sLIQ29
   0KQFdMc/L0B1uME6IG5cDnTDPy9AtbKGtET37jSz0yQ9SNJdWo+5+/9OuzIAQPmYfgSopyST2W6T
   9LeS3inp8ZLeLGlDscUCsllY2KKpqa2SdknaFc/ZtKXqYkH1nu2/zmUHUF9JRnd+UdHUG1e6++lm
   doKk97n7E8ooYI8y0dyJnuh7E546N7fVuewto/AZgDorcgqOz7n7o8zsC5J+W9LPJN3g7g/IVtTh
   EdJQB4TFFXXuK1jnsrc755xz9Ja3XCBJOvvs5+rVr351xSUCxkeRN1j/nJkdK+k8SZ+XtE/Sv6dd
   UVpm9k0zuya+V+hni14fkqPpZzDuE4m0ivy7ajabOuecd+imm16jm256jc455x0cj0AduHviRdKp
   kh6a5jVZF0nfkDTd43eOaiwuLvrU1AkuXejShT41dYIvLi5WXazgzM6eGW8jj5cLfXb2zKqLVZk6
   HzdllL3odXA8jobFxUWfnT3TZ2fPrM3fDyJxbkmdhQaO7jSz9eqYL83MHufun8o7MHZbfQnrQAqM
   EkMWdb6/Yxll5+8Kg3T2K9y7dzP9CsdAkik4XqaVkHYXSY+W1OqfViSX9DEzu0PSu939vILXB+Rm
   YWGL9u7drOXl6OdolOmuagtVsfn5+dpeUOpcdonjcRQQ5MfTwJDm7k9q/9nMTpb09sJKtGKdu//A
   zI6XtMfMbnD3T7d+uW3btoNPnJmZ0czMTAlFQufJfnLyZdq///6am9uUS+f4UelsX+eaI5Rv/fqH
   a8+es9oeOUvr1788t/fneATKtbS0pKWlpaHfJ/UdB8zMJF3v7g8aeu3J1/k6Sb9w9x3xz5623MhP
   K0jt3/8TXXfd1br11rdJGn5YP9ME1EfWMD0qITxv0QjSUxV1xZWkUzU7+43ajSBFcTg/1lvW0Z1J
   OvC/o235O0lXSHpvlg5wSRdJR0k6Ov7+rvE659p+n1NXPgwj787IdG6uh6yd3Os8eKBoHPtIgoED
   9aWiBg4o6n/WcrukD7j73tRpMJ0TJO2OKu10hKLJcy8veJ0AEsjaN4Y+Nb3RZwxJ1L1vJNJL0ift
   whLK0bnOb0h6WNnrRTp5X1i4UGFc1aHPGE3VQAV6VbFJurbPck2Waru8FtHcGYy8q9+pzg/fqDZ3
   9jr2RumYzPpZQt93ZRil4wDlU8bmzn5B6JR4eXO8nCbpoZLOlXRulpXltRDSgGoNc7EP8ULXK4SM
   UjgZ5rOMe5+5UToOUI2sIS3JvTuvcveHdTy2z90bOVTkZcLoTgB56nV/Tkkjcd9Oabh7kI7K/Uuz
   GvfPj+EVee9OM7PHtv2wTtwJAADGxsLCFk1NbZW0S9KuuL/olsSv536/QDZJRnc+T9IFZna3+Odb
   JD23uCIBGBadvNPpN2hlVAazDDMwJ8vAhpX5FG/Uddd9Wbfe+teS6nk7IwY1oTJJ20Ul3U3S3bK0
   qea9iD5pIyfUvkp1s7i46I3GOp+YOJb+MykxcCDf9az04Vo7Ev3ZRuk4QPmUd580M3u2u19kZgs6
   9AbrFq/sLcXGx97okzZamEk7Hyvb8VRJfyz6z6Aqh/bh2iSJ/lwYb1n7pPVr7jwq/nq0uoS0tCsC
   emGS03ysbMdLqy4K0GaLpGcd/ImmQiC5niHN3d8df91WWmmAgNS3X9cWrdRajO9Fsb77r/46+3BN
   Tt6uhzzkAq1efVyQE/UCwRrUHqpojrRjJB0p6eOS9kt6dpa21bwW0SdtpIQ4B1GIZRrk0DIv+MTE
   cd5orA++3N0M2/+njvtvkLr1iapbeYEiKe/JbH0lEF0df90o6XxFAwi44wByFdoJva6Td4a2HbPI
   I2DVdf/1UnToHIXjBghZ1pCWZAqO1nOeJOmf3P2nZkafNOSKGwfnYxS2Y78+inVtwhy23EX22+wc
   uFPHKTJQrLr+3Y2CJCHtMjO7QdL/lfQiM7t7/D0wspgXKTxpwkRI+y/0EDTuA3cIIP2FfvyOvCTV
   bZKmJd0p/v6ukk7MUm2X1yKaO1GAziafkJqAQipL0Xo17UVNmAsunRkvC32bMEPZZnk0vRbZ3Dlq
   TcNphNB3MZTjtJdxPj7ypAL7pN1V0msknRf/fD9JT8qysrwWQlq+Qj9JlCGPk3VR2zGEC0nZum3L
   RmOdS6sPbgdptTca6you6WB5XeQ4vvJXdQCpw7avehuNiiJD2sWStkq6zldC29VZVpbXMoohraqg
   VIeTRBmGPRFR01G8RmP9Yduh0VhfdbHcvf/fbx3+xsb1H7Wq/7byXn8R+7EOx28dFBnSvhB/3df2
   GCEtR1X+EVR9kkqq6IvIsNuhyO1Yl31UtLK3Q9JjLsnf77iGoNBVHUDyPKaL/Cwcv8MrMqT9u6Sp
   VkiTtEbSZ7OsLK9l1EJalRfhKted10UwjxPIsCe4IrfjqISAOs19lmZdhOh6q/JvJ89jmuMwbEWG
   tDlJn5T0Y0nvl/QtSY/PsrK8FkJafqr6TzLNxKv9ts/i4qJPTh5/sPyTk8dnDnDDnKyrnMeq6tqA
   JPIqY1kX1DR/k1wcMYy8jmmOw7AVFtKi99ZqRfOkPSn+/l5ZVpbXMmohreqLbBX/Sa6cUBZd6v/Z
   +518+vVTKnu7VvUfeR1OznUoY7s05a367xdw5zgMXSEhTdIjJD1V0kPin0+WtFPSt7OsLK9l1EKa
   ez2aq/K0chEcfDHsd/KZnl5z2Ounp9d0rKMewSCrOnzOOpSxXdoLXtF/v1WcH8btnDQK2Gfhyj2k
   Sdou6UuSPiDpa5J2SPqGpL+QdJcsK8trGcWQNm5WLoJrE128e518+k3LULdgkFWvQBHKCXtxcdEb
   jfU+MXGcR/OcXegTE8d6o7Eu6AtJSNuv7BqSUGplQtkHwLCKCGnXt8JYPJntLyWdkmUleS+EtNEQ
   XbzX+cTEsZlrLKI+aavisLfWJydXHXx9GReaUC4i3bZLKBfZ9nKYrXKzow+GtVFtgs5TEf9sDNou
   IfyDE8oxDOShiJC2r+Pnq7KsoIiFkFaeLBe5tK8ZdpTnoE71RV2kQ76IhHCR7VWOKFAXX66Q908a
   ee/LJNslhOMnhDIAeSkipP1U0mVtyy1t31+aZWV5LYS0cmS5yBV5YUzbmbvoGpSQLyKhlK3KkJZl
   G4RW85altnmQJNslhIBbxjEc2v7G6CoipM30WdZnWVleCyGtHFlOkkWeWJO+d1kXmFCCUDchXGS7
   lWNy8vi4ebr4cqXdP0Vss/ymdek/TU0aaf6OqgwwZUxrE8LfCMZDoVNwhLYQ0soRWkhLelItKzyF
   fpKv+iLbqxxllSvt/qmiWbGfoo7j0I/bdkUeKyH/k4XRQ0hD7kJr7my9/6CTdpkn3zwuIqGEqVGU
   ZtvmfdwM+35F/8Mz7sccIS0bjp1sCGkoRBkDB/JWt5qCupQ1JEUcY3nvi2FDAMdGsdi+6bHNsiOk
   YaQVNWK0zDJ1U+f/5qsK43lcKHqVPc/PVGQ5kU1VTe+jos7nq6oVee/OB0g6T9IeSZ+Il3/LsrK8
   FkLaeAnxv7e8ylTXk16VAaRONVQ0h4cjxPNI3dT1fBWCIkPaNZJeJOkxkh4ZL4/IsrK8FkLaeAnx
   xJBXmep64agyKBXZ1yu0QFTX4yNEIZ5H6objMbusIe0IDXabu78rwfMApDQ/P6/du3dpx46dkqSF
   hV2an5+vuFTF27Fjp5aXz5W0WZK0vBw9NuizN5tN7d9/oyYmXqIDB6LHpqa2amFh19Blajab2rhx
   c1wuae/ezdq9u9r9kXU7AUUY1/NVpQalOEnbJP2ppHsouj3UtKTpLIkwr0XUpI2Vqv9761a7UmSZ
   QqvNcc//tlNZajX6zRuWZpv1KnuINS0hlqmuqj6PYLypwObObyq6sXr78vUsK8trIaSNnxA7qddh
   hGGRZRrm82f5nL0CS9apYjrL3mis8+huCGe6tBhEIArxeKizEP8BwngoLKSFuBDSUJayazJCrDkp
   YpLX2dkzvdFY743GusQXzF7lyKN8i4uLfsQRxx0MQ9Jql47y7du3J/48RV34CRZA/WUNaQP7pJnZ
   pKKBA4+T5JI+Kenv3f22fBpcAYyLzn5fU1NbtXv3axL1a1lY2KK9ezdreVkHX7uwsNI/Jk0ZVvrU
   bNH8/Lx27Nip22/foVbfr8jf6JOfvFKvfnXyz1NEP7b5+Xn6/SA43f6OUIBBKU7S+ZJ2SfptSb8j
   6UJJ/5AlEea1iJo0lKTs5qaQmrfaa7zyut9mklqvfjVHw/YPTNMfTVo7sEYuxJrPURF6DWLo5StS
   SOepulCRU3AkeazMhZCGMpV9Mg7h5N95Ep6cPD5V02Qvg0JN1pN/+zbbvn17z+3Xq9/Z4uKiT04e
   f0hz5+Tkqq7rbl9Xo7G+5+cJYT9WZdjPHnoICL18ReOfk/SKDGlXSrpv289rJF2ZZWV5LYS0ao3z
   xWdc9Asfwxh0cSty/rXFxUWfmDi2LYid4NLCIaGq0Vjv09NrvNFY1/XY3r59u09MHBcHvQWfnFx1
   SLhrH1QxrhfxPD57KCGg17kulPJVZdw/fxZFhrTfkfRtRX3RPinpW5J+O8vK8loIadUZpYsPYbO7
   KMwcV9hJuN92L3Ki2m6/m5g4LvG+7xXyWjWM7Z+nThPm5i2PC3gIIaDfuS6E8lVplK4DZSkspEXv
   rbtIOl3SQyXdOcuK8lwIadUZlZMTJ5neon28EIeQViC5W8/apTwVOf9at981GuuHeu9e/dbynC6k
   bvIabVv1dhoUtKsuX9VG/Z+NvBVZk/YHko6Jv3+NpA9JeniWleW1ENKqMyohre6fo8gT5Mq2WfSo
   79Zalx5Y2sWoqPnXigiAvWri0gxQqPK4C3muv6pDQJL+k4QUJFVkSLs2/vpYSUuSniTps1lWltdC
   SKvOqPwHWfXFsuyJYId5f2napXVxYFtIdaGq4kKWdnRomvdt3y4TE8f2nUet27qqPu46yzdOd81I
   a1TOdQhDkSHtqvjrmyQ9M/5+X5aV5bUQ0qpVpxNwr7JWeQIuskkvzzLOzp7pRx99skvHtAW21d5o
   rEv0OYb9nGUeZ0nXNUqjFssMjHU6Z7Sra7kRniJD2r9I2qnodlCr4v5pV2dZWV4LIQ29dE7FMChE
   VHECLrJzfN66jfJs9eMaVI5hyllmmCk7OIVy4S/rOMpj+4ayzYCsigxpR0naJOl+8c/3kDSXZWWJ
   CyWdIenxKcjoAAAevElEQVQGSV+RtLXL7/PefhgBhzdHFTdCcRhFTjNRZlnzCGkhTHEQUhNku6KD
   SVnHUZ2Od6AohYQ0SUdIuiHLG2ddJN1J0lclnSLpSElXSXpQx3Ny3nyog35Nl7OzZ/r09BqPRiW2
   LgZrg734DnvD8rJqFobpiD/M79Nc2IfdFiGGtLKCSRnHUZ1qjoGiFFmT9hFJ98ny5pkKJP2mpMW2
   n18h6RUdz8lz26EG+gWbQzu5r/ZoVKK7tHDIvFYhjUzsfF7ItQXbt2/36ek1Pj295rCO8sMMHMhj
   ioMs260O236Ugkkd+mACRSsypH1a0i8k/Zuky+Ll0iwrS1Qg6fclndf287MkvaPjOblvQISt14m6
   2+OtGrSpqRP63iIoT4uL0Wz1Zsd6NF3F2p63FUrz+apWZIDJY4qDtNstSS1mGcfMoM82ap368xxV
   G0KIBtLKGtIsem1vZjbT7XF3X+r7wozMbJOkM9z9BfHPz5L0GHd/cdtz+hcaAAAgIO5uaV8zkeBN
   l7otmUqYzPckndz288mSvtulXCxjtCwuLmpq6gRJF0q6UFNTJ2hxcbHn41neK2vZZmfPjN/L4+VC
   SdFj09Nrhvp8VW/3bp9tdvbMXPZd63ezs2dqdvbMTJ837XYb9HnSft4s+21lHYuSem+XRmO9pqfX
   qNFYV9ixkMf+rWoZ9tgZ1bIMKmeI55lxWDJL8Ma/Kelzipo8b5N0QNLPCvwgR0j6mqKBA5Ni4ABi
   gwYOJG1KybspqXuTa/RYmtsOhTjNQB5NTUU33aUdcNGvuTMafJK8rFk+28pret86qv2m7ZOTxwfb
   qb8qITWBhlSWQeq6v0eBMjZ3HpEgx71T0h9KuljSIyX9kaQHZI+F/bn77Wb2Z5KaikZ6nu/uXypq
   fShHs9nUjh07JUkLC1s0Pz/f9bF+5ufnBz6nCgsLW7R372YtL7ceeamkzZqcfJne+MaLEr9PaJ+v
   tX8e+MAHSjpPq1efoIWFXUGUsfPYufzySxK9bn5+Xrt372p77S5J0saNm7W8fK6kUyWddfD5U1Nb
   Dz4nLyvHy6ldf//KV75Rt97615I2S5JuvTV6rIjt3nnsFvF589C5v3fs2Bnvr2gbLS9LO3bsrOTY
   DKksGEGDUpykL8Rfr2l77KosiTCvRWNekxZijUs/3f7THDTR7DDvnbU2pddz04zWbDTWe6Oxrjb7
   ppc8awfyrmnI+/0Or11Y8OnpNUPVzCX5DI3Guq6jj7vV5k1Pr8n8+ZKUJY/zSVHnpW7buNFYF0yN
   ULfaqTQ16GWqU63fqFGBozs/JenOki6S9GZJZ4s7DlSmjn9k3U5iaZuV0rx3kvdJckHp3NaTk8eP
   RABLIo+Rl+3yvICX0Vyd5v2GHbnY+doogKw+eNy134qrav26HJQ5CrjRWB/MebCzeVpanWpkd9nq
   9k/+qCgypJ0iaUrS3SRtk/QWSffNsrK8lnEOaXXsUxBiSMv63u3Te4zyCS6POcyqKFu7NLWgoVzw
   W+WZnFwVH2vppnJpf4+8L8T9tlPZf4etzxVK2IiC9VqP+hku1uK8jHIVFtKi99ZRkh6QZQVFLIS0
   eoW00Jo7k+o9IKAe230Yndt1YuJYbzTWHbwwVnkMJtnnaY+LfhP2ViHEecX67fcij4nQQnQ3Vf9N
   IHxF1qRtkPRfkr4Z/9xQgZPZJir0GIe0Opywuul20cnjP+FW357p6TXeaKwvtC/MoXczGP2TcLRt
   18f3QF04eLx1u+n69PSaUo/DQcdOmotmqH9TWZuUD789Wj7HapW1qyHVmnUT6jGEcBQZ0q6UtErS
   vrbHvphlZXkt4xzS3MM/YZWljBNj+4CAqAlq8G2K8uyflPR9izomuvcHWtclvC4EdWFKE9JCrAVJ
   e2yX8Q/FoDKN+3lp3D8/+isypH0m/toe0q7JsrK8lnEPaaMm68mt7ItrkqCUNTT2e22Si2PZt25a
   GYW4NsjaxTTbJMSQ1isc9zr+yuo/SRABsikypL1H0jMlXSvpfpLeIenvs6wsr4WQNjqGCRhlXlyT
   XJyGKc8w/X2q6g8UYrhpV9eBA+7dpwXpNl1H7+dfmHgaEQDFKzKkHSXpryR9Pl7OkXSXLCvLayGk
   jY5hLvRlXVyTrqeqkFb0yLIqpl0oW5E1RFne+/CBG8f1PAZa/TL7hbgqPwuAAkJaPO3GSyT9naQX
   SjoyywqKWAhp4eo8iefRwXuYvlqDypdE0vBVRXPn4mK1czQVddHOa1BJ1YFi2GOiVf5ugzVan2vl
   /Rd8YuK43AfQ5PFZgHFXREi7WNJ7Jf2xpA9LenuWFRSxENLC1HkSn5xcdUiAyDJVQp4Xhqzv1b1/
   0PqetUtlDhxYKdtiXJO21tesOS3VekOTxz4PJVDk1STc6/OU2eQcevM2ELIiQtq1bd8f0T5woOqF
   kBamw0/iaxPXQKXpEJ31wpD1vQ4Pn8cnGulZhugzLbh06Jxmda59ymOfhxIo8ixHt31DSAPqIWtI
   63eD9dtb33h00/M+T0Xdpb3ZeZ5Cu7F4p86bcu/ff3/t2/cChXBD5YWFLfr4x5+pAwd2HCzPgQPZ
   ytNsNttuNC7t3btZu3eHcUP1/ftv1NzcJknDHZ9lH+d53sC8299JmTdID/lm7FWev4BC9Upvku6Q
   9PO25fa273+WJRHmtYiatFzl1TSUpblz0Pvl2SE6r8+Zd43CsLVXvforpRVKTUnS42hQ83BRd7nI
   8nmKrJ1sf//t27eXtq5Q+qOF0rQN9KOiRneGuBDS8nXoxXnRpbWZZ5BPO3Cg1+sPnTw2vw7ReXVI
   r7qfXB7v0bktQglpnWXrFkKT3GA75M/XT9ZjdFzDSl32K8YbIQ2ZHdr5vLqTfOdFJuTbMOVVo5Bn
   x/K0YTiUmqZBum2jaCLddNutDhfzYYJWHT5fEcb1c6NeCGnIbOXCkKyjf1G6nWyrvKF5GdNL5NVU
   mVavC9swtThFNYN1Cy7R3HDptlvaAJT3Z0ryfsMEjnENK+Nag4h6IaRhKIuLi5lqJ/LUPaTlf2ub
   JIo68efdby+rvEcdlnUP1fZm9G7rHBSEkgavvD9T0vfrPt1L79tBFVnmOgmxrxzQjpCGVLqd1LKe
   5Ldv3+7T02t8enqNb9++fagydU510bpAlX3iLapWYpiLcJ7yvKBXVYOTNLh1e+4geX+mpO83bIgn
   rABhyhrS+k3BgRHVb6qF9qkmFhYGT79wzjnn6C//8s2S/laS9Jd/eZYk6dWvfnXqch2+/ovGYij9
   6tUn6PLLLyl1nUn3dVlTG2RZT+eUFHNzm+JjerOklalRJAU7tUinw6d7OV379j1X3T5Tt+0V6nQ2
   TJEBZJQl2VW9iJq0oeRZS9CtiXR6ek3OJS5fWc2dITdJJS3rsJ+p6KlRshzvVTV3JvlMSUa2Ji1T
   GbVudTrmgaKI5k4kRUhLpoyBAyFfrNIcJ8N8pmGPx+7Ttgx/66QqBg50e00egyaSvG9Rx+K4DmgA
   2mUNaTR3jqE8Zw4/++znHmzijJyls89++fCFDEBRTUd1aZJKo6rP1Nl0Pzn5MjUa52n16hMOacLN
   crzn/ZmyvF+3ZunW98PYsWNn16bhEI9LYKxlSXZVL6ImbWh51hLkNXBg3IRUo1blvGllzA3Wa6BM
   1TVlWdcz7H4ps3aL5k4ge01a5YErU6EJaaUIKUSMmqIvXHmNZiwzeGRZzzBNmXnc6aFV5rInAh52
   v5QdnDiXYNwR0pAr/vstVpE1GVn2XdX9hrJexPPskJ+2H1z7eqP7yy4Mvf3KDDMEJ6A8hDTkquqL
   9qgbZvsOal4OYTRjGnmMDk0bNoY9vntPvJz974V/jIDRRUhDrnoN/Q/tP++8agPKrlUYZuJg6ZiD
   r5OOOSyohTKaMalu5Z2eXlNoOYYNRN3KPDFxXG36iXVDzVoybCdkQUhDrrrN/t9teoOQyjjMfFFV
   1GD0Otn3uwgkmfIkzecJ4YLTu1aq2H0xzGfvNdBimG3ZK6yG/E/DuGE7IStCGnLXfhHLY26mvOVV
   81B1DUa7QReBpPPSJQkgoVxwOsshrXZpsfJ9MUj7/Gx53L6s+3ZYKGW/hPQ3EDK2E7LKGtKYJw09
   tc/rNDe3qeLSjIdB81cNmpcuze13Qpkrq30usC984WrddNNmScWWIY/bFLVek9ctp1rb4RnP+FPd
   dNPxkt4raV7Ly6cxhxkwrrIku6oXUZNWulBqXYooU0jNnUn+U+81cCDt50iyrrr01atqHUXUrPR7
   z377I+/m26r/vkPEdkJWorkTRQuh/1KnURs4MMxFIG1gGLSukMJrnvIMVnmHtMXFRW801seDEBYS
   Hxt5z/s27HYP8VyRl1H+bCgOIQ2okay1Jf00GutTB4Z+6xrV/jd5fq48g2y3udcajXWJallD2lfU
   NgGHyxrS6JMGBCbLPR6bzaauu+5qSS89+Njk5Mu0sHBR7uvKW5b+YcP0Kcvz3rXd7q2ZdXt29hE8
   cEBavfrSyvdPWqH0dQRGQpZkV/UiatJQc3nXNqzUpCy6dKZLa73RWBdUGfNaR2hNe2n1Wveg2rCi
   mzvzElKtHhAK0dwJ1EueQaGoC2OI/cPqHAKGDVpFDRzIU0iBEQhF1pBGcydQkTybGvNswmvXKt+O
   HTsPNumNS7NVHtN0dOrXFJik6bTfMRNC03WrHHk1AQNjL0uyq3oRNWmouSJqPYp6zyJrRapq7iyi
   XEnUuRYQQHaiuROohzo1B5URKrKEy7SvSfP8xcXF+M4Oaz3vOx/Uad8DyE/WkEZzJ1IpogkoVEV9
   Vka/HSpLM12a1zSbzcR3Beh8brSPhm82bqEpEEAqWZJd1YuoSavEONUCFPlZ69TkNQr7PM327nWz
   9zp+7jpIW8PZ+dxQBksAg4jmTmSV9ERXp3AxrCI/a92CTygXwqzlGDakHX30vYPeP3WV5u+g23O3
   b99eq78jjDdCGjJJc6IkpOX3WUMJPnUxTLBNGwYmJ48/+FxptU9OrqrVPGx1MWx4jvoNjsf5CPVH
   SEMmaU6UdasBGkZ0sV4Vdx5fm+lCjfwMG5rThKZGY12838+MBw6kX9e4/J0Mg5CGcZI1pDFwAImN
   X6fnIyX9cfz9y6osCIaUZqDB6tUnSNqg1sCObgMH+g0qYWBIMmnm9uv23LPPfrHOOWdr7nMDortx
   GjQWlCzJrupF1KTlhv/6uxunpt06KPM4HbSuQb/n2EmOgQP1wHVieBqV5k5J2yR9V9K+eDmjy3Py
   3HZjjxPd4UKdH2yclbm9FhcXvdFY59PTa7zRWJ/bPTaBOuIfj+FlDWkhNne6pLe4+1uqLsi4COV2
   MiEp6jZLLWnm7qqjIppGijxOO8srSTfc8FUtL5+rm26SNm5Mvn/Gr1sAgMJkSXZFLpJeJ2lhwHPy
   CrdAT0XW3Izyf6Z1q0nqVt5GY33P/RPa56NGFkUL7ZivI41QTZokvdjM/kjS5xUFtluqLhDGDzWM
   2dSt43y38n7rW2/o+fyQasqKqJGlgzg6hXTMj5tKQpqZ7ZF0YpdfvVrSuyS9Pv75DZJ2SHp+SUUD
   SjGoOZULZbXuc58Ttbzce+RgKAE+70A86s3wyC6UY37cVBLS3H02yfPM7B8kXdbtd9u2bTv4/czM
   jGZmZvIoGlCKfv+Z1v1CWXR/vrx1K+8b3xiVd9xqDupWCwqEamlpSUtLS0O/j0VNpeEws3u4+w/i
   718i6VHu/oyO53ho5QbyMje3SXv2HDpP1+zspbr88kuqLFYqZdQE5rmOutZcdgb6qamtQwX6UTj2
   gBCZmdzd0r4uxD5p55rZwxSN8vyGpBdWXB4AKRXdNJJ3bWNdm3Ly7itUt1pQYNQFV5OWBDVpCFUe
   NTJ5146MImp8ilPXWkUgZKNUkwbUUl61O4ykQpXqWqsIjCJq0oCcULtTHmob06F2DKhW1pq0iSIK
   AwB5aTabmpvbpLm5TWo2m5JWahtnZy/V7OylhQS0busN0aBytgLtnj0btGfPBm3cuDnozwOgTZYZ
   cKtexB0HEKAyZuUet9nlq5rpvC4zrCcp5yjf3QKoC2W84wA1aUBOiq7dCaVGpMwapkPn7YqaN1vN
   dqO43rTqUk4A2TBwAMhRkZ2uQ5ho9JxzztFrX/tWHThwP0nrajfR7jjqnFZjcvIvtH//6Zqb20T/
   NCBwhDSgBprNpr7whaslfV/RHdXKv7A2m0299rU7dODAW+NHtmp5+VmFBsWq5u2qy3xhScrZPlp4
   //4bdd11R2rfvudKqt/dLIBxw+hOIHCdIxmll0rarKmp95Z6ge02elX6e83O3rPQEaxVjUysy4jI
   NOVkBDJQDeZJA0ZUZzOnJE1Pv0Hvf3/1NSATE1/RwsK2QtdR1bxddZkvrC7lBJAeIQ0I3P79Pzns
   sUc84vTSL8ydTWsTEy/R61+/QECokbo04wKI0NwJ5CzvG39v2PCHuvXWIyT9jSRpcvJluvTSiyoJ
   R3VpAkRvZe9Djhkge3MnIQ3IUd4z4a/0ITpR0k5J31ejcSddeeXe3MqM5Agc6XBnCCBCnzQgAMVN
   kzEfL7u0evWlQ74Xssjr3qzjJIRpY4A6I6QBAaMPUTgIHADKRkgDcpR3qGqf4yp6f2puUB/8kwEM
   hz5pQM7Gqd/SuH1W+lelN07HCNALAwcAlGocQwuBA0AWhDQApWL2egBIJmtImyiiMAAAABgOAwcA
   ZEKncAAoFs2dADLLq48Wfb0AjDL6pAGopXEcgABgvBDSANQSAxAAjDoGDgAAAIwQBg4AqBQDEACg
   O5o7AVSOgQMARhl90gAAAAJEnzQAAIARQkgDgBHVbDY1N7dJc3Ob1Gw2qy4OgJRo7gSAEcT8c0A4
   6JMGADiI+eeAcNAnDQAAYIQwTxoAjCDmnwPqj+ZOABhRzD8HhIE+aQAAAAGiTxoAYGQxnQjGESEN
   QGm40CKL1nQie/Zs0J49G7Rx42aOH4wFmjsBlIJ5u5AV04mg7mjuBFKiVqdcO3bsjAPaZklRWGt1
   agcAHI4pODCWOmt19u7dTK0OECimE8G4orkTY4nmk/LR3IlhMJ0I6ixrcyc1aQBKMT8/r927d7Vd
   aAloSG5+fp7jBWOHmjSMJWp1AABlYTJbICWaTwAAZSCkAQAABIgpOAAAAEZIJSHNzJ5qZteZ2R1m
   9vCO373SzL5iZjeY2VwV5QMAAKhaVaM7r5W0UdK72x80swdLepqkB0s6SdLHzOz+7n6g/CICAABU
   p5KaNHe/wd2/3OVXT5H0AXe/zd2/Kemrkh5dauEAAAACEFqftHtK+m7bz99VVKMGAAAwVgpr7jSz
   PZJO7PKrV7n7ZSneimGcAABg7BQW0tx9NsPLvifp5Laf7xU/dpht27Yd/H5mZkYzMzMZVgcAAJCv
   paUlLS0tDf0+lc6TZmafkPRSd/9C/PODJb1fUT+0kyR9TNJ9OydFY540AABQF7WaJ83MNprZdySt
   lfQvZvavkuTu10u6WNL1kv5V0p+QxgAAwDjijgMAAAAFqlVNGgAAAPojpAEAAASIkAYAABAgQhoA
   AECACGkAAAABIqQBAAAEiJAGAAAQIEIaAABAgAhpAAAAASKkAQAABIiQBgAAECBCGgAAQIAIaQAA
   AAEipAEAAASIkAYAABAgQhoAAECACGkAAAABIqQBAAAEiJAGAAAQIEIaAABAgAhpAAAAASKkAQAA
   BIiQBgAAECBCGgAAQIAIaQAAAAEipAEAAASIkAYAABAgQhoAAECACGkAAAABIqQBAAAEiJAGAAAQ
   IEIaAABAgAhpAAAAASKkAQAABIiQBgAAECBCGgAAQIAIaQAAAAEipAEAAASIkAYAABAgQhoAAECA
   CGkAAAABIqQBAAAEiJAGAAAQIEIaAABAgAhpAAAAASKkAQAABKiSkGZmTzWz68zsDjN7eNvjp5jZ
   spnti5f/VUX5AAAAqlZVTdq1kjZK+lSX333V3Rvx8icllwslWFpaqroIGAL7r77Yd/XG/hs/lYQ0
   d7/B3b9cxbpRPU409cb+qy/2Xb2x/8ZPiH3STo2bOpfM7LFVFwYAAKAKRxT1xma2R9KJXX71Kne/
   rMfLvi/pZHe/Oe6r9mEze4i7/7yocgIAAITI3L26lZt9QtKCu1+Z5vdmVl2hAQAAUnJ3S/uawmrS
   UjhYaDNbLelmd7/DzH5d0v0kfb3zBVk+KAAAQJ1UNQXHRjP7jqS1kv7FzP41/tV6SVeb2T5J/0fS
   C939lirKCAAAUKVKmzsBAADQXYijOw8yszPM7AYz+4qZbe3xnL+Nf3+1mTXKLiN6G7T/zOyZ8X67
   xsyuMLOHVlFOHC7J3178vEeZ2e1mdmaZ5UN/Cc+dM/FI+i+a2VLJRUQfCc6dq81s0cyuivffcyoo
   JjqY2XvM7EYzu7bPc1JllmBDmpndSdI7JZ0h6cGSnm5mD+p4zu9Juq+730/SFknvKr2g6CrJ/lPU
   3/Bx7v5QSW+QtLPcUqKbhPuu9bxzJS2qrW8pqpXw3LlK0t9JerK7/4ak3y+9oOgq4d/fn0na5+4P
   kzQjaYeZhdDHfNxdoGi/dZUlswQb0iQ9WtHdB77p7rdJ+qCkp3Q8Z4OkXZLk7p+RtMrMTii3mOhh
   4P5z9/9w95/GP35G0r1KLiO6S/K3J0kvlvRPkn5cZuEwUJL99wxJl7j7dyXJ3feXXEb0lmT//UDS
   MfH3x0j6ibvfXmIZ0YW7f1rSzX2ekjqzhBzSTpL0nbafvxs/Nug5XOjDkGT/tXu+pI8WWiIkNXDf
   mdlJii4crf8E6dwajiR/e/eTNG1mnzCzz5vZs0srHQZJsv/Ok/QQM/u+pKsl/XlJZcNwUmeWkKtH
   k570O5tZuFiEIfF+MLPHS3qepHXFFQcpJNl3b5P0Cnd3MzPR3BmSJPvvSEkPl/Q7ko6S9B9m9p/u
   /pVCS4Ykkuy/V0m6yt1nzGyNpD1mdjoTv9dCqswSckj7nqST234+WVHq7Pece8WPoXpJ9p/iwQLn
   STrD3ftVE6M8SfbdIyR9MMpnWi3pd83sNne/tJwioo8k++87kva7+7KkZTP7lKTTJRHSqpdk//03
   SedIkrt/zcy+IekBkj5fSgmRVerMEnJz5+cl3c/MTjGzSUlPk9R5AbhU0h9JkpmtlXSLu99YbjHR
   w8D9Z2b3lvQhSc9y969WUEZ0N3Dfufuvu/up7n6qon5pLyKgBSPJufMjkh5rZncys6MkPUbS9SWX
   E90l2X83SHqCJMV9mh6gLhO/IzipM0uwNWnufruZ/ZmkpqQ7STrf3b9kZi+Mf/9ud/+omf2emX1V
   0i8lPbfCIqNNkv0n6bWSjpX0rrhG5jZ3f3RVZUYk4b5DoBKeO28ws0VJ10g6IOk8dyekBSDh399f
   SbrAzK5WVNnycne/qbJCQ5JkZh9QNCn/6njC/tcp6lqQObMwmS0AAECAQm7uBAAAGFuENAAAgAAR
   0gAAAAJESAMAAAgQIQ0AACBAhDQAAIAAEdIABMfM7jCzffFypZndx8yuiH93HzN7ettzTzez382w
   jiUze0QOZc3lfQCgU7CT2QIYa79y90bHY617u54q6RmSPhD/3FB0m6p/TbkOVz73+s3rfQDgENSk
   AagFM/tF/O2bJP1WXMv2ckn/U9LT4p+famZ3NbP3mNln4lq4DfHrp8zsg2Z2vZl9SNKUOm52bGZn
   mNnFbT/PmNll8ffvMrPPmdkXzWzbgDLKzH7fzC6Ivz/ezP7JzD4bL/8tfnx9R43hr+W0uQCMAGrS
   AIRoysz2xd9/3d03aaW2aqukl7r7kyXJzG6U9Ah3Pyv++a8kfdzdn2dmqyR9xsw+JumPJf3C3R9s
   ZqdJulKH14B9TNK7zWwqvvn407RSY/cqd7/ZzO4k6WNmdpq7X9vxeu/x/dslvdXdr4jvWbso6cGS
   FiT9ibv/R3wPzf+XdkMBGF2ENAAhWu7S3NliXX5uf2xO0pPN7KXxz3eWdG9Jv6UoLMndrzWzazrf
   OL5v4qKkDWZ2iaTfk9R6n6eZ2QsUnTfvIelBkjpDWi9PkPSg+B61knS0md1V0hWS3mpm75P0IXf/
   XsL3AzAGCGkA6q5bf7Az3f0r7Q/EAakz4HXzQUl/JukmSZ9391+a2amKar0e6e4/jZsx7zKgLFPt
   q5f0GHe/teP555rZP0t6oqQrzGze3f8rQRkBjAH6pAGom59LOrrPz01JZ7V+MLNWjdynFA04kJn9
   hqSH9nj/T0p6uKQXaKWp8xhJv5T0MzM7QVKv0aQ3mtkDzWxC0kathLbLO8r0sPjrGne/zt3fLOlz
   kh7Q430BjCFCGoAQdasdaz12taQ7zOwqM/tzSZ+Q9ODWwAFJb5B0pJldY2ZfVDSwQJLeJenXzOz6
   +LHPd12x+wFJ/yzpjPir3P1qSfsk3SDpfZL29ij3K+LXXCHp+22PnyXpkWZ2tZldJ2lL/Pifm9m1
   Zna1pFuVfoQqgBFm7owcBwAACA01aQAAAAEipAEAAASIkAYAABAgQhoAAECACGkAAAABIqQBAAAE
   iJAGAAAQIEIaAABAgP4/+Zc6KUM7/CgAAAAASUVORK5CYII=
   "
   >
   </div>
   
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p>Histogram of standardized deviance residuals:</p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[14]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="kn">from</span> <span class="nn">scipy</span> <span class="kn">import</span> <span class="n">stats</span>
   
   <span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">()</span>
   
   <span class="n">resid</span> <span class="o">=</span> <span class="n">res</span><span class="o">.</span><span class="n">resid_deviance</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
   <span class="n">resid_std</span> <span class="o">=</span> <span class="n">stats</span><span class="o">.</span><span class="n">zscore</span><span class="p">(</span><span class="n">resid</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">hist</span><span class="p">(</span><span class="n">resid_std</span><span class="p">,</span> <span class="n">bins</span><span class="o">=</span><span class="mi">25</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">set_title</span><span class="p">(</span><span class="s">&#39;Histogram of standardized deviance residuals&#39;</span><span class="p">);</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   
   
   <div class="output_png output_subarea ">
   <img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAk4AAAGtCAYAAADgYftEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzt3XuUbGV95vHvA0cCetSDAQERhChMYrzAjBITSSxiVJZR
   1MxolEkQ4xgnySjjqBE0Ca1OohJvM8a4koh6IKLxEk3QoBCkFHPBkAAiSNAoAgoHuYqDxgu/+WPv
   5hRNX97urqaq+3w/a9U6u6r2fvevdt2e8+633k5VIUmSpKXtNOkCJEmS1guDkyRJUiODkyRJUiOD
   kyRJUiODkyRJUiODkyRJUiODk9alJF9I8nOTrmOSkjwjyVVJbk3yyEnXMyvJTJJTx9jee5K8tl/+
   2SSXjavtkX3cnuTHGtcdy+NL8o4kv7PadqbRYu/PJIMkV41pP8Mkzx9HW1Irg5OmTpIrkjx+zm3H
   Jjl39npVPayqPrNEOwf0X4gb9XX+RuA3q+reVXVR60ajQWSNjHtyuJpts6rOraofH3P7K6ln9Y1U
   /UZV/e9xtDVtWt6f49oV43+9SYvaqF8oWt/G/WGYMba1vdFk57Vot3HfAfYHLp1UDWthkZC7Js+h
   FjbJ17c0zQxOWi/uFKT6Xqmf75cPS3J+kluSXJvkjf1qs//jvbk/nfVT6fxOv/22JFuT3Gek3WOS
   fC3J9SPrze5nJsmHkpya5BbguUkeneQfktyU5BtJ3pbkHiPt3Z7kN5J8Kcm3krwmyYP7bW5O8v7R
   9ec8xnlrTfIjwK3AzsBFSb60wPZv6be7Jcnnk/xkkl8HjgZ+uz8mf9Wve3ySL/c1XpLk6SPtHJvk
   s0n+MMmNSb6S5MiR+w9M8ul+2zOBPebU8cEk1/SP99NJHjpy33v6U1Z/k+TbwCDJoUn+pW/v/cCu
   I+vfcZonyS/3j2H28u9Jzunv+5Ekb+yfy2v7fYy28/L++bo6ya/Nd/yW8fgek+Tv+9fAhUkeN1Lf
   P81Z9yUjx3z0FOTuST6W5Lr+GJ+eZN+R7Yb9a+ezfR2fTPKjI/cfPlLDlUme23Ic5tR2bJK/S/Lm
   JNcDJybZZaHtk+zR13xTkhuSfGakrTt6jZPs1j/WG5NcAjx6zn7vdJp0OcdlTjsP6Z+nm5N8s3/t
   SGNncNK0mtvDMPf6aJD6P8Bbquq+wI8BH+xv/9n+3/v2p7POA54HPBcY9OtuBv4IoP9CfzvwHGAf
   4L7AA+bs9yjgg/2+TgN+CBwH/Cjw08Djgd+cs80TgUOBxwCvAP6s38f+wMP75fnMW2tV/XtVbe7X
   eURVHTR3wyRP6h//QX2tzwRuqKo/Bd4LvKE/Jk/rN/kycHhV3Qd4NfDnSfYaafIw4LL+cZ4EnDxy
   32nAP/X3vbavefT5+TjwEGBP4F/6/Y96DvDa/jGdD3wU2ArsTvdc/mfm6YGsqr/oH8O96Z6nf+tr
   AXh9v89H9v/uC/xef2yOBF4K/AJwcP/vYhZ8fP2X+MeA11TV7sDLgA/3oeZ04D8kechIW0ePPP7R
   ntXQHdP9+8t36F+Xc47TscD9gV36fZHkQcDf0L0P9gAOAS5c6jgs4DC643h/4A+ANyyy/UuBq/p9
   3h84YaSd0cd2InAg3Wv4Sdz19THXco/LrNcCn6iqLX2d/3eRfUgrV1VevEzVBbiCrkflppHL/wM+
   M7LOV4Gf75c/DcwAe8xp5wDgdmCnkdvOBv77yPWDge/R9d78HvDekft2A/59ZD8zwHCJ2v8n8Jcj
   128Hfnrk+vnAy0euv5Eu9M3X1kK17jTS9o8tsO0RwL8CPzX6+Pv73k0XVBZ7HBcAR/XLxwJfGrnv
   nv2+70/3ZfZ9YLeR+98LnLpAu1v6be/dX38P8J6R+38O+Pqcbf6OLphAFyKvmnP/TnTh5e399QDf
   Hj02dKH2K/3yu4A/GLnvoIWO5SKP75R++RWzyyP3fwI4pl8+Ffjdkf18C9h1qeeBLvzcOHL9HOCV
   I9d/AzijXz4B+PA8bSx6HOZZ/1jga63b0wXsjwIPnqet0ffnvwFPHLnvBaPP4dxjv4Lj8mv98lbg
   T4B9F3tte/Gy2os9TppGBTytqnafvdD14iw0zuX5dKHii0k+l+QXF2l7H+BrI9evBDYBe/X3XX1H
   EVXfAW6Ys/3Vo1eSHNyfSrgm3em736frmRi1bWT5O/Nc38z8Fqt1UVV1Dt3/zN8ObEvyJ0nuvdD6
   6U5RXtCfdrkJeNicx3HtSNu39Yub6Xp6buqP1aw7ak6yc5LXpzsNeAvdFypsP91V3PmYPgD4+pzy
   vsbifh+4F/Di/vqedOHun0cezxkj+9yHrqdk1pWLtL3Q45t9LT4IeObsfvp9PRbYu7//NLb3KB4N
   fKSqvjt3J0nu2T9HV/TH6dPAfZOMvuavHVkefd3sB3xlntqXOg7zGT0uS23/h3Q9lWcm+bckr1ig
   zQfQfrzvpPG4zPptuuflc+l+1fe81v1Iy2Fw0nqx4ODgqvpyVR1dVXvSnVr4UJLdmP90wDfoeqJm
   7Q/8gO5L6RrggXfssGtjbgia2+Y76AZoP6S6U2KvYnzvq4Vq3Tbv2nNU1duq6lHAQ+mC5ctn7xpd
   rz/V86fAbwH364PqF2gbkH0NsHuSe47c9qCRfRxNd3rz8f3xOXB2t6Olzmlv7hiWBy208yTPBn4Z
   +C9V9cP+5uvpgsVDR8L3lupOQ87uY/+RZkaXl/v4rqTrXdt95HLvqjqpv/9vgT3TTRfxbLafSpw1
   285L6Z6jw/rj9Di6Y9TyHFwJPHie25c6DvMZfS4W3b6qvl1VL6uqB9M9x/8ryRHztLnU8b6NLqDN
   2ocVHJeq2lZVv15V+wIvBP44jVNMSMthcNK6l+RXkuzZX72F7kP3duCb/b+jXyrvA16SbqqCzXTj
   ON5fVbcDHwaemuSnk+xCd2puqS+uzXSnFW9L8uN0p1CWLHmB5bkWq3XxHSSPSjcY/h50X0zfpRuP
   BV3wGv1CuRfdMbse2Kn/n/rDGh4HVfU1utOPr05yjySHA08ZWWUz3enOG5Pcq38Mdyp1zvW/B36Q
   5MV9e7/EnMHEI4/xUOBtwDOq6o6ewf74/Bnw1tnXRZJ9kzyxX+UDwLFJfqIPRCeu4vH9Od1r5ol9
   79qu6Qaw79tv/326cVpvpBuzddacxz77+DfThZRbktxvgZoWeq2cBvxCkmcm2ZTkR5M8suE4LGqp
   7ZP8Yj8gO3SnIH9I936b6wPACUm2JHkg8KI5918I/Nf++B1Jd7p2Vstxoa/nmX37ADez/XNAGiuD
   k9aLxaYoeBLwhSS3Am8Bnl3dAOrb6E7j/F1/quEwuvEtp9L94u4rdKHiRQBVdUm//H663p5bgevo
   vvgXquFldL0q36LrtXn/nHXmq3nu/Qs9rgVrXaTtWffp67mRbszY9XSnVqAbbPvQ/pj8ZVVdCrwJ
   +Ae6nreHAZ9dosbR60fTjaW6kW6c2NaR+06hO7X1dbperH9gkcffB41fohtvcwPwLLpAO9++n0Y3
   Zuqz2f7Luo/3972C7jTSP/aneM6i67mgqj4BvBX4FHA53ViyxY7lgo+vqq7u63gl3WvlSrpektHP
   1tPofjTwwTmhd/Sxv5VuTN31dOHxjHlqmve4VdWVwJP7/d5ANz7tEUsdh3nM9zwvtv1B/fVb+5rf
   XlWfnqfdV9O9Br5KN/7rlDn7OQ54Kt1YxqOBj4zc13JcZj2qr/NW4K+AF1fVFQusK61Yqhb7vOhX
   6ubzOB+4uqqemmQG+G90/6MHOKH/MJI2jL6X5ya603BLjbORJO0ANjWudxzdOI7ZwaUFvLmq3rwm
   VUkTkuSpdD0QoTu98nlDkyRp1pKn6vpzxk8G3sn2c+ytgxal9eYoutNKX6cbG/XsyZYjSZomLWOc
   3kL3a5y55+ZflOSiJCcn2bIm1Ul3s6p6wcivh55QVfPOyi1J2jEtGpySPAW4rqou4M49TO+g+1nx
   IXQ/NX3TmlUoSZI0JRYdHJ7kD4BfpZs7Zle6X+p8uKqOGVnnAOD0qnr4PNsvPfJckiRpSlTVokOR
   Fu1xqqpXVtV+VXUg3ViPT1XVMUn2GVntGcDFi7ThZc7lxBNPnHgN03bxmHhcPC4eF4+Jx2XSlxat
   v6qD7lTdbKsn9TPhFt3cHC9cRjuSJEnrUnNwqqohMOyXf3WN6pEkSZpazhw+AYPBYNIlTB2Pyfw8
   LvPzuMzP43JXHpP5eVxWrmnm8BU3ntRati9JkjQuSajVDA6XJEnSdgYnSZKkRgYnSZKkRgYnSZKk
   RgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYn
   SZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKk
   RgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRpsmXYAkSDLW9qpqrO1JkjoGJ2lqjCvsjDeE
   SZK281SdJElSI4OTJElSo6bglGTnJBckOb2/fr8kZyW5PMmZSbasbZmSJEmT19rjdBxwKdsHYRwP
   nFVVBwNn99clSZI2tCWDU5IHAk8G3sn2UadHAVv75a3A09ekOkmSpCnS0uP0FuDlwO0jt+1VVdv6
   5W3AXuMuTJIkadosGpySPAW4rqouYIHfOFc3YYyTxkiSpA1vqXmcfgY4KsmTgV2B+yQ5FdiWZO+q
   ujbJPsB1CzUwMzNzx/JgMGAwGKy6aEmSpNUaDocMh8NlbZPWGYaTPA54WVU9NclJwA1V9YYkxwNb
   quouA8STlDMYS0vrZg4f3wSYvu8kafmSUFWLziK83HmcZj+NXw88IcnlwM/31yVJkja05h6nFTVu
   j5PUxB4nSZq8tehxkiRJ2mEZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJ
   khoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZ
   nCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJ
   khoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhoZnCRJkhotGZyS7JrkvCQXJrk0
   yev622eSXJ3kgv5y5NqXK0mSNDmpqqVXSu5ZVbcl2QR8FngZ8Hjg1qp68yLbVUv70o4uCTCu90rw
   fSdJy5eEqspi6zSdqquq2/rFXYCdgZtm97Hy8iRJktaXpuCUZKckFwLbgHOq6pL+rhcluSjJyUm2
   rFmVkiRJU6C1x+n2qjoEeCDwc0kGwDuAA4FDgGuAN61VkZIkSdNg03JWrqpbknwceFRVDWdvT/JO
   4PT5tpmZmbljeTAYMBgMVlKnJEnSWA2HQ4bD4bK2WXJweJI9gB9U1c1JdgM+CbwauKSqru3XeQnw
   6Ko6es62Dg6XGjg4XJImr2VweEuP0z7A1iQ70Z3aO7Wqzk5ySpJD6D7tvwq8cNUVS5IkTbGm6QhW
   3Lg9TlITe5wkafLGNh2BJEmSDE6SJEnNDE6SJEmNDE6SJEmNDE6SJEmNDE6SJEmNDE6SJEmNDE6S
   JEmNDE6SJEmNDE6SJEmNDE6SJEmNDE6SJEmNDE6SJEmNNk26AGm9Shb9A9qSpA3I4CStSo2pHUOY
   JK0HnqqTJElqZHCSJElqZHCSJElqZHCSJElqZHCSJElqZHCSJElqZHCSJElqZHCSJElqZHCSJElq
   ZHCSJElqZHCSJElqZHCSJElqZHCSJElqZHCSJElqZHCSJElqtGnSBUh3pySTLkGStI4ZnLQDqjG1
   YwiTpB2Np+okSZIaGZwkSZIaLRqckuya5LwkFya5NMnr+tvvl+SsJJcnOTPJlrunXEmSpMlZNDhV
   1XeBI6rqEOARwBFJDgeOB86qqoOBs/vrkiRJG9qSp+qq6rZ+cRdgZ+Am4Chga3/7VuDpa1KdJEnS
   FFkyOCXZKcmFwDbgnKq6BNirqrb1q2wD9lrDGiVJkqbCktMRVNXtwCFJ7gt8MskRc+6vJOP6fbck
   SdLUap7HqapuSfJx4D8B25LsXVXXJtkHuG6h7WZmZu5YHgwGDAaDlVcrSZI0JsPhkOFwuKxtUrVw
   Z1GSPYAfVNXNSXYDPgm8GngScENVvSHJ8cCWqrrLAPEktVj70t2tmzl8nBNgTmdbvu8kafmSUFWL
   zm68VI/TPsDWJDvRjYc6tarOTnIB8IEkzweuAJ41joIlSZKm2aI9Tqtu3B4nTRl7nCRJC2npcXLm
   cEmSpEYGJ0mSpEYGJ0mSpEYGJ0mSpEYGJ0mSpEYGJ0mSpEYGJ0mSpEYGJ0mSpEYGJ0mSpEYGJ0mS
   pEYGJ0mSpEYGJ0mSpEYGJ0mSpEabJl2ApPFLFv3j3stSVWNrS5LWO4OTtCGNK+yML4BJ0kbgqTpJ
   kqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGTkegqTfOOYkkSVoNg5PWCeclkiRNnqfq
   JEmSGhmcJEmSGhmcJEmSGhmcJEmSGhmcJEmSGhmcJEmSGhmcJEmSGjmPk6RFjXMC0qpxzcclSZNh
   cJK0BCcflaRZnqqTJElqZHCSJElqtGRwSrJfknOSXJLkC0le3N8+k+TqJBf0lyPXvlxJkqTJyVKD
   NZPsDexdVRcm2Qz8M/B04FnArVX15kW2LQeDarW6wcnjHGdjW5Nqy88DSdMsCVW16IDMJQeHV9W1
   wLX98reTfBHYd3Yfq65SkiRpnVjWGKckBwCHAv/Y3/SiJBclOTnJljHXJkmSNFWapyPoT9N9CDiu
   73l6B/Ca/u7XAm8Cnj93u5mZmTuWB4MBg8FgFeVKkiSNx3A4ZDgcLmubJcc4ASS5B/Ax4Iyqeus8
   9x8AnF5VD59zu2OctGqOcdo4bfl5IGmatYxxavlVXYCTgUtHQ1OSfUZWewZw8UoLlSRJWg9aflV3
   OPAZ4PNs/6/nK4HnAIf0t30VeGFVbZuzrT1OWjV7nDZOW34eSJpmLT1OTafqVlGAwUmrZnDaOG35
   eSBpmo3lVJ0kSZI6BidJkqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGBidJ
   kqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGmyZdgKQdR7LoHx1flqoaW1uS1MrgJOluNK6wM74A
   JknL4ak6SZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKk
   RgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYnSZKkRgYn
   SZKkRksGpyT7JTknySVJvpDkxf3t90tyVpLLk5yZZMvalytJkjQ5qarFV0j2BvauqguTbAb+GXg6
   8Dzg+qo6KckrgN2r6vg529ZS7UtLSQKM63VkWxulLT9bJI1bEqoqi62zZI9TVV1bVRf2y98Gvgjs
   CxwFbO1X20oXpiRJkjasZY1xSnIAcChwHrBXVW3r79oG7DXWyiRJkqbMptYV+9N0HwaOq6pbu9Mn
   naqqJPP2m8/MzNyxPBgMGAwGK61V68jo60OSpGk0HA4ZDofL2mbJMU4ASe4BfAw4o6re2t92GTCo
   qmuT7AOcU1U/Pmc7xzjtoByXZFtr3ZafLZLGbSxjnNJ9A54MXDobmnp/DTy3X34u8NGVFipJkrQe
   tPyq7nDgM8Dn2f7fxROAzwEfAPYHrgCeVVU3z9nWHqcdlD1OtrXWbfnZImncWnqcmk7VraIAg9MO
   yuBkW2vdlp8tksZtLKfqJEmS1DE4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4
   SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIk
   NTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNdo06QIkaSWSjK2tqhpbW5I2NoOTpHVqXGFnfAFM0sbn
   qTpJkqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGBidJkqRGBidJ
   kqRGSwanJO9Ksi3JxSO3zSS5OskF/eXItS1TkiRp8lp6nN4NzA1GBby5qg7tL58Yf2mSJEnTZcng
   VFXnAjfNc5d/GVOSJO1QVjPG6UVJLkpycpItY6tIkiRpSq00OL0DOBA4BLgGeNPYKpIkSZpSm1ay
   UVVdN7uc5J3A6QutOzMzc8fyYDBgMBisZJeSJEljNRwOGQ6Hy9omVbX0SskBwOlV9fD++j5VdU2/
   /BLg0VV19DzbVUv72niS0P2GYCyt2ZZtrWlbfk5Jgu67q6oWHcO9ZI9TkvcBjwP2SHIVcCIwSHII
   3SfXV4EXjqFeSZKkqdbU47Tixu1x2mHZ42Rb66ktP6ckQVuPkzOHS5IkNTI4SZIkNTI4SZIkNTI4
   SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIk
   NTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4
   SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNTI4SZIkNdo06QK0OkkmXYK0
   7o3zfVRVY2tL0vQxOG0I4/qgzpjbktYLX/eS2niqTpIkqZHBSZIkqdGSwSnJu5JsS3LxyG33S3JW
   ksuTnJlky9qWKUmSNHktPU7vBo6cc9vxwFlVdTBwdn9dkiRpQ1syOFXVucBNc24+CtjaL28Fnj7m
   uiRJkqbOSsc47VVV2/rlbcBeY6pHkiRpaq16cHh1k5Y4cYkkSdrwVjqP07Yke1fVtUn2Aa5baMWZ
   mZk7lgeDAYPBYIW7lCRJGp/hcMhwOFzWNmmZ5TbJAcDpVfXw/vpJwA1V9YYkxwNbquouA8STlLPo
   rq1uxuNpnQDTtmxrx2vLzzxp/UpCVS06k+2SwSnJ+4DHAXvQjWf6PeCvgA8A+wNXAM+qqpvn2dbg
   tMYMTrZlW9PVlp950vo1luC0ygIMTmvM4GRbtjVdbfmZJ61fLcHJmcMlSZIaGZwkSZIaGZwkSZIa
   GZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwk
   SZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIa
   GZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwkSZIaGZwk
   SZIaGZwkSZIaGZwkSZIabVrNxkmuAL4F/BD4flUdNo6iJEmSptGqghNQwKCqbhxHMZIkSdNsHKfq
   MoY2JEmSpt5qg1MBf5vk/CQvGEdBkiRJ02q1p+oeW1XXJNkTOCvJZVV17jgKkyRJmjarCk5VdU3/
   7zeTfAQ4DLhTcJqZmbljeTAYMBgMVrNLSZKksRgOhwyHw2Vtk6pa0c6S3BPYuapuTXIv4Ezg1VV1
   5sg6tdL21SYJ3RnTsbRmW7ZlW6tsy888af1KQlUtOnZ7NT1OewEf6b642QS8dzQ0SZIkbTQr7nFq
   atwepzVnj5Nt2dZ0teVnnrR+tfQ4OXO4JElSI4OTJElSI4OTJElSI4OTJElSo9VOgKkV6H+JKGkD
   Guf724Hm0vQxOE3MOH8RJGl6+N6WNjJP1UmSJDUyOEmSJDUyOEmSJDUyOEmSJDUyOEmSJDUyOEmS
   JDXasNMRnHLKKdx8881ja++YY45hy5YtY2tPkiStP1nLCdaS1KQmcHvAAw7mhht+imT3Vbd1++1b
   ueSS8znooIPGUNnsBHnT+Zfdbcu2bGt62hrX5+e4J911Yk5tVEmoqkXfMBu2x6kKvve93wUOXnVb
   mzefsfqCJGminJhTGgfHOEmSJDUyOEmSJDUyOEmSJDUyOEmSJDUyOEmSJDUyOEmSJDUyOEmSJDXa
   sPM4jdvBB69+PihJWo5xT1w5bZyYU+uRwWlZnEBO0t1pR/jM2REeozYST9VJkiQ1MjhJkiQ1MjhJ
   kiQ1MjhJkiQ1MjhJkiQ1MjhJkiQ1cjoCSdKyTOv8UuOsa1xzQk3rXFXTWtd6YHCSJC3TtM69ZF3L
   M611TTdP1UmSJDUyOEmSJDVaVXBKcmSSy5J8KckrxlWUJEnSNFpxcEqyM/BHwJHAQ4HnJPmJcRWm
   Hc1w0gVMqeGkC9C6Mpx0AVNoOOkCtMGspsfpMODLVXVFVX0feD/wtPGUpR3PcNIFTKnhpAvQujKc
   dAFTaDjpArTBrCY47QtcNXL96v42SZKkDWk10xFM9aQNO+8Mmze/kJ122rzqtr7znW+MoSJJkrTe
   ZaWTViV5DDBTVUf2108Abq+qN4ysM9XhSpIkaVRVLTox1WqC0ybgX4HHA98APgc8p6q+uKIGJUmS
   ptyKT9VV1Q+S/A/gk8DOwMmGJkmStJGtuMdJkiRpR7OmM4cneW2Si5JcmOTsJPut5f7WiyR/mOSL
   /bH5yyT3nXRN0yDJM5NckuSHSf7jpOuZNCeYvask70qyLcnFk65lWiTZL8k5/XvnC0lePOmapkGS
   XZOc13//XJrkdZOuaVok2TnJBUlOn3Qt0yLJFUk+3x+Xzy227lr/yZWTquqRVXUI8FHgxDXe33px
   JvCTVfVI4HLghAnXMy0uBp4BfGbShUyaE8wu6N10x0TbfR94SVX9JPAY4Ld8rUBVfRc4ov/+eQRw
   RJLDJ1zWtDgOuJQp/3X83ayAQVUdWlWHLbbimganqrp15Opm4Pq13N96UVVnVdXt/dXzgAdOsp5p
   UVWXVdXlk65jSjjB7Dyq6lzgpknXMU2q6tqqurBf/jbwReABk61qOlTVbf3iLnRjcW+cYDlTIckD
   gScD7wQAsb9XAAACT0lEQVQW/fXYDqjpeKz5H/lN8vtJrgSeC7x+rfe3Dv0a8DeTLkJTxwlmtWxJ
   DgAOpfsP2Q4vyU5JLgS2AedU1aWTrmkKvAV4OXD7UivuYAr42yTnJ3nBYiuuZgJMAJKcBew9z12v
   rKrTq+pVwKuSHE/3hD1vtftcD5Y6Lv06rwK+V1Wn3a3FTVDLcRFgF7qWKclm4EPAcX3P0w6v79k/
   pB9H+skkg6oaTrisiUnyFOC6qrogyWDS9UyZx1bVNUn2BM5Kclnfw30Xqw5OVfWExlVPYwfqWVnq
   uCQ5lq679PF3S0FTYhmvlx3d14HRH1PsR9frJN1FknsAHwb+vKo+Oul6pk1V3ZLk48Cj2LH/eN3P
   AEcleTKwK3CfJKdU1TETrmviquqa/t9vJvkI3XCJeYPTWv+q7qCRq08DLljL/a0XSY6k6yp9Wj+A
   UXe1o597Px84KMkBSXYBfhn46wnXpCmUJMDJwKVV9dZJ1zMtkuyRZEu/vBvwBHbw76CqemVV7VdV
   BwLPBj5laIIk90xy7375XsAT6X6sNK+1HuP0uiQX9+eYB8BL13h/68Xb6AbLn9X/9PGPJ13QNEjy
   jCRX0f0y6ONJzph0TZNSVT8AZieYvRT4CyeYhSTvA/4eODjJVUl2iFP/S3gs8Ct0vxq7oL/4y0PY
   B/hU//1zHnB6VZ094ZqmjUMCOnsB5468Vj5WVWcutLITYEqSJDVa81/VSZIkbRQGJ0mSpEYGJ0mS
   pEYGJ0mSpEYGJ0mSpEYGJ0mSpEYGJ0mSpEYGJ0mSpEb/H5VBeXsYh+MpAAAAAElFTkSuQmCC
   "
   >
   </div>
   
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p>QQ Plot of Deviance Residuals:</p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[15]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="kn">from</span> <span class="nn">statsmodels</span> <span class="kn">import</span> <span class="n">graphics</span>
   <span class="n">graphics</span><span class="o">.</span><span class="n">gofplots</span><span class="o">.</span><span class="n">qqplot</span><span class="p">(</span><span class="n">resid</span><span class="p">,</span> <span class="n">line</span><span class="o">=</span><span class="s">&#39;r&#39;</span><span class="p">)</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt output_prompt">
       Out[15]:</div>
   
   
   <div class="output_png output_subarea output_pyout">
   <img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAmUAAAGyCAYAAAClXLMtAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzs3Xl4ldW59/HvClPCoKBWGUTBOKI4HrW2Dqktg9Jja1vr
   UKsetVq1gWjPa6vUmuPQantqSXCsQ0WtYwennCJYTdE6zyAoCIKKgEpBBUkgYb1/PAnZCQECJNlP
   ku/nunKx8+y9yZ2o8HOt+7lXiDEiSZKk7MrJdgGSJEkylEmSJKWCoUySJCkFDGWSJEkpYCiTJElK
   AUOZJElSCmQtlIUQBoYQngwhvBlCmBZCGF1zfasQwuQQwswQwqQQQu9s1ShJktRaQrbmlIUQ+gJ9
   Y4yvhRB6Ai8D3wb+C/gkxvibEMLPgD4xxp9npUhJkqRWkrWVshjjwhjjazWPlwEzgAHAMcCEmpdN
   IAlqkiRJ7VoqespCCIOA/YDnge1ijItqnloEbJelsiRJklpN1kNZzdblX4AxMcbPM5+Lyd6q50BJ
   kqR2r3M2v3gIoQtJILszxvhgzeVFIYS+McaFIYR+wEeNvM+gJkmS2owYY9jQa7J592UAbgWmxxjH
   ZTz1MHBqzeNTgQcbvhcgxuhHK35ceumlWa+ho334M/dn3hE+/Jn7M+8IH02VzZWyrwInA2+EEF6t
   uXYRcBVwfwjhDGAu8P3slCdJktR6shbKYoxPs+6Vum+0Zi2SJEnZlvVGf7UNBQUF2S6hw/Fn3vr8
   mbc+f+atz595emVteOzmCCHEtli3JEnqeEIIxDQ3+kuSJKmOoUySJCkFDGWSJEkpYCiTJElKAUOZ
   JElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiTJElKAUOZJElSChjK
   JEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiTJElKAUOZJElSChjKJEmSUsBQ
   JkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiTJElKAUOZJElSChjKJEmSUsBQJkmSlAKG
   MkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiTJElKAUOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQw
   lEmSJKVA52wXIEmS1JrKyqZQWjqJysrOdOtWxejRwxk16vBsl2UokyRJHUdZ2RTGjHmM2bOvXHNt
   9uyxAFkPZm5fSpKkDqO0dFK9QAYwe/aVjB8/OUsV1clqKAsh3BZCWBRCmJpxrTiE8EEI4dWaj5HZ
   rFGSJLUflZWNbxJWVHRq5UrWlu2Vsj8CDUNXBK6JMe5X8zExC3VJkqR2qFu3qkav5+ZWt3Ila8tq
   KIsxPgUsaeSp0Nq1SJKk9m/06OHk54+tdy0//2IKC4dlqaI6aW30LwwhnAK8BPw0xrg02wVJkqS2
   r7aZf/z4S6io6ERubjWFhSOz3uQPEGKM2S0ghEHAIzHGoTWfbwt8XPP05UC/GOMZDd4Ts123JElS
   U4QQiDFucBcwdStlMcaPah+HEG4BHmnsdcXFxWseFxQUUFBQ0NKlSZIkbVB5eTnl5eUb/b40rpT1
   izEuqHl8PnBgjPGkBu9xpUySJLUJbWKlLIRwD3AEsE0I4X3gUqAghLAvyV2Y7wJnZ7FESZKkVpH1
   lbJN4UqZJElqK5q6UpbtOWWSJEnCUCZJkpQKhjJJkqQUMJRJkiSlgKFMkiQpBQxlkiRJKWAokyRJ
   SgFDmSRJUgoYyiRJklLAUCZJkpQChjJJkqQUMJRJkiSlgKFMkiQpBQxlkiRJKWAokyRJSgFDmSRJ
   UgoYyiRJklKgc7YLkCRJakxZ2RRKSydRWdmZbt2qGD16OKNGHZ7tslqMoUySJKVOWdkUxox5jNmz
   r1xzbfbssQDtNpi5fSlJklKntHRSvUAGMHv2lYwfPzlLFbU8Q5kkSUqdysrGN/MqKjq1ciWtx1Am
   SZJSp1u3qkav5+ZWt3IlrcdQJkmSUmf06OHk54+tdy0//2IKC4dlqaKWF2KM2a5ho4UQYlusW5Ik
   NV1Z2RTGj59MRUUncnOrKSwc1iab/EMIxBjDBl/XFsONoUySJLUVTQ1lbl9KkiSlgKFMkiQpBQxl
   kiRJKWAokyRJSgFDmSRJUgoYyiRJklLAUCZJkpQChjJJkqQUMJRJkiSlgKFMkiQpBQxlkiRJKWAo
   kyRJSgFDmSRJUgoYyiRJklLAUCZJkpQCnbNdgCRJat/KyqZQWjqJysrOdOtWxejRwxk16vBsl5U6
   hjJJktRiysqmMGbMY8yefeWaa7NnjwUwmDXg9qUkSWoxpaWT6gUygNmzr2T8+MlZqii9DGWSJKnF
   VFY2vilXUdGplStJP0OZJElqMd26VTV6PTe3upUrST9DmSRJajGjRw8nP39svWv5+RdTWDgsSxWl
   V4gxZu+Lh3AbMAr4KMY4tObaVsB9wI7AXOD7McalDd4Xs1m3JElq+l2VZWVTGD9+MhUVncjNraaw
   cFiHavIPIRBjDBt8XZZD2WHAMuCOjFD2G+CTGONvQgg/A/rEGH/e4H2GMkmSsqixuyrz88dSUjKi
   QwWupmhqKMvq9mWM8SlgSYPLxwATah5PAL7dqkVJkqQN8q7K5pfGnrLtYoyLah4vArbLZjGSJGlt
   3lXZ/NIYytao2aN0n1KSpJTxrsrml8aJ/otCCH1jjAtDCP2Ajxp7UXFx8ZrHBQUFFBQUtE51kiSJ
   0aOHM3v22AY9ZRdTWDgyi1WlQ3l5OeXl5Rv9vqw2+gOEEAYBjzRo9F8cY7w6hPBzoLeN/pIktb4N
   3V3Zpu+q/OQTePddOPDAFv9SbeXuy3uAI4BtSPrHfgk8BNwP7IAjMSRJyop2e3fltGlQUgJ//jOM
   Hg3/8z8t/iXbRCjbVIYySZJa1ogRv2DSpCsauX4JEydenoWKNsPq1fD3v8O4cUkoO/dcOPts2Hbb
   VvnyTQ1laewpkyRJWdYu7q5ctgxuvx1KS6FnTzj/fPj+96Fbt2xX1ihDmSRJWkubvrty7ly49lr4
   4x+hoABuvRUOPRTCBhersirVIzEkSVJ2tLkzK2OEp5+G730PDjggufbyy/CXv8Bhh6U+kIE9ZZIk
   aR3axN2VK1fC/fcn/WKffgpjxsCpp0KvXtmubA0b/SVJUvv18cdw001w/fUwZAgUFcHRR0NO+jYB
   28TZl5IkSRvljTfgjDNg112T3rHHHoPHH4dvfjOVgWxj2OgvSZLSbfVqKCtLtihnzEhGWsycCV/6
   UrYra1aGMkmSlE6ff1430mLLLZORFscdB127ZruyFmEokyRJ6fLuu8lIi9tvhyOPTH79ylfaxB2U
   m6Ntb75KkqT2IUZ46in47nfhP/4j6Q975RV44AH46lfbfSADV8okSerQNnToeIurrIT77kvOo/z8
   82SkxYQJyQT+DsZQJklSB9XYoeOzZycDY1s8mH30Edx4I9xwA+y1F1x2GRx1VJu/g3JzOKdMkqQO
   oLEVsdLSSa1/6PjrryerYn/7W9K0P3p0EsraMQ8klyRJwLpXxPLyljf6+mY/dLy6um6kxdtvw3nn
   waxZsM02zft12jhDmSRJ7Vxp6aR6gQxg9uwr2Xrr4xt9fbMdOv7558mh4KWl0KdPMtLie99rtyMt
   NlfH3biVJKmDqKxsfA2mb9/eLXPo+LvvwgUXwKBBySHhd9wBL7wAJ51kIFsPV8okSWrnunWravT6
   9ttvS2HhMMaPvyTj0PGRm9bkHyNMmZL0i02ZAqefnoy02HHHzay+47DRX5Kkdq6xnrL8/IspKdnE
   AJapshLuvTfpF/vii+Rg8FNOgR49NrPq9qOpjf6GMkmSOoCysimMHz85Y0Vs2OYFskWL6kZa7LNP
   EsZGjOjQIy3WxVAmSZKa32uvJVuUDz4I3/9+MtJizz2zXVWqORJDkqQOqtmn9FdXw6OPJluUs2Y5
   0qKFGMokSWrDGgawQw7pz113zW+eKf2ffQa33QbjxycBrKgoGWnRpUtzfguq4falJEltVGMN/Hl5
   x7NixX1rvXajpvTPnp0EsTvugOHDkzD25S83V9kdTlO3L+3GkySpjWpsKOyKFXs0+toNTumPEcrL
   4dvfhoMPhtzc5Eike+81kLUSty8lSWqjGh8K2/hMsnVO6a+oqBtpUVGRrIr96U+OtMgCQ5kkSW1U
   40Nhh5OX92NWrLhxzZVkSv/I+i9buDAZaXHjjbDvvnDVVclWpSMtssZQJklSGzV69HBmzx7bYCjs
   RE4+eW+ee24dU/pffTUZafHQQ3D88fDEEzBkSJa+A2Wy0V+SpDasSUNhq6vh4YeTLco5c+AnP4Ef
   /Qi22io7RXcwDo+VJKmj+/TTZKRFaSn07Zv0i33nO460aGUOj5UkqR1obA7Zs89+uP7BsO+8k4y0
   uPPO5Oije+7xDso2wFAmSVJKrT2HbApPPHE3VVV1TfxrBsMefVgy0mLcOHjmGTjzzGSkxcCBrV+4
   Nonbl5IkpdSIEb9g0qQrMq78Arii3mu6UcGv9jyOCzq9BytXJluUP/whdO/eqrVq3dy+lCSpjVt7
   Dlnd531ZwDncwNncxNwPt4B7roVhwxxp0Yb5T06SpJRaew5ZFfvxChM4hekMYRs+4Qj+yaUHnZD0
   jhnI2jT/6UmSlCJlZVMYMeIXFBQU8/HHC+nb9wJyqOZY/so/eYSHOJxp7EU+szmP66nKv4PCwmHZ
   LlvNwJ4ySZJSomFj/xZ8yvm9hvOjyhksyd2ShwYfRPV/FvDMix+tfy6ZUqXZ5pSFEHYGPogxVoQQ
   vgYMBe6IMS5tnlI3nqFMktReZI68mDZtBosX38fOzKKQ8ZzMXUxkJM8fnEvJc7dlu1RtoqaGsqZs
   X/4FqKoJZzcBA4G7N7M+SZI6vNqVsUmTruCf/7yUfRZ342H+k2f4Csvoyd68wQ+4m9dzd8h2qWoF
   Tbn7cnWMsSqE8B1gfIxxfAjh1ZYuTJKk9q60dBLzZ/+C07mVIsaRw0LG8SuO5z5WUDfSIje3OotV
   qrU0JZStDCGcBJwC/GfNNc9nkCRpc3z4IT94awp38gde5EAu4BoepyswCTICWX7+xRQWjsxamWo9
   TQllpwNnA1fGGN8NIQwG7mzZsiRJaqdefjmZuv/oo/Tulc9hPMVMdst4QWDrrU9gr712r2nkH2kj
   fwfRpLsvQwjdgR1ijG+1fEkbZqO/JKlNqaqCBx+EkhKYN48Z3xjFL+Z25+2PljFnTmDFirpjk/Lz
   L6akxCDWnjTn3ZfHAL8FusUYB4UQ9gP+J8Z4TPOUuvEMZZKkNmHpUrjlFhg/nn/32ILru+zKA1Vb
   MevdThlBbAp5edeRn9+PAQN6OeKiHWrOUPYKcCTwZIxxv5pr02KMezVLpZvAUCZJSrWZM6G0FP70
   Jxg1iqcPOIzTrnuvZv7Y2udXAowYcQkTJ17e6qWq5TXn2ZerYoxLQ6j3e63e5MokSWqPYoR//INF
   F/+Sbq+9ziP9DuDO7UfyyfQtmPt/T7Jkyb01L2z8r96Kik6tV6tSqSmh7M0Qwg+AziGEXYDRwDMt
   W5YkSelXVjaFG39fxuHvz+DY955idfVqfh/34/aqT6h470XgMeBKoDjjXQ3Ps0w49kJNGR5bCOwJ
   VAL3AJ8BRS1ZlCRJaVZWNoURe53ItG8Vces//sgeMz/hxxVHsduqn3BjVTkV5JGMtriy5h2ZQWw4
   MLbe75eMvfD8yo5ugytlMcblwMU1H60mhDCXJABWk2yhHtSaX1+SpEy1xyH1eedNvj1vGvdWf8Cf
   OINDGc0s7iDpEyvOeEfmX7G1QexKIGniz8s7PqO537sttZ5QFkJ4ZD3vi61w92UECmKM/27hryNJ
   0nr938NPMPGsa/nlokUM4E3Gcwk/5mM+5aqaV9T+dZq5Ipb5uDZwXUKfPu9x0EE7UFh4nkFM9axv
   pex3rVbFum3wTgVJklrMkiXM+OnFDJ1wB71W7881XMBDvE41PyW5i7JWbQDLXBHLfAxwOPn5Eykp
   OcMwpkY1aXhsNoQQ5gCfkmxf3hRjvDnjOUdiSJJazttvQ2kpqybcQVkYxBXLDuFl/lDzZO1IiynU
   NfI3fDyZ3Nx59O+/kt69t6ZXry/VTOd3BllHtNkjMUIID8QYjwshTCPZSswUY4x7b26RG/DVGOOC
   EMKXgMkhhLdijE/VPllcXLzmhQUFBRQUFLRwOZKkdi1GmDw5mbr/4ovMOvIoju36Nd5c8jD1V8Ua
   roBdkhHAzqsJYFBYeKYBrIMqLy+nvLx8o9+3zpWyEEL/GOOHIYQdWXsbMcYY5230V9tEIYRLgWUx
   xt/VfO5KmSSpeXzxBdx1VxLGcnJ448ijOfufi3jt7TwqKrYjad7PXAkDp/BrYzTnRP+rY4w/29C1
   5lRz1manGOPnIYQeJPcV/0+McVLN84YySdLmmT8frrsObr4ZDjmE5758JOc+MJUZb3WlomJrki3K
   zOn7ybYkdGLrrd9iwoRzDWJqkqaGsqbMKRveyLWjN76kjbId8FQI4TXgeeDR2kAmSdJmeeEFOOkk
   Vu6+Bw/+aTJH9/46vZ6s4vDi6bz6Wj8qKm6grrsnc6bY4cDl5OevNJCpRayvp+wc4FwgP4QwNeOp
   XsC/WrKoGOO7wL4t+TUkSR1DWdkUrh03kSFvvcDxC1+jf6zguk4DuWX1sXzy3hkk25KB+nPGau+m
   rBtlUbtCVlJiIFPLWN9IjLuBvwNXAT+jrq/s8xjj4pYuTJKkTVU76HXBm1M5+sMPuSm+x1y6cRVF
   PMxyqqs7Ubc9mXkMUmOjLQ4nGWdxsYFMLWqd25cxxk9jjHNjjCcAHwArSQ4i7xFC2KG1CpQkaWOU
   lU2h5Jw/8e1JU/nn/L8zJO7BsXyTI3iPv1FBNb+mbk2i4dDX2jB2ODCC5M7KU9h///MoKXHqvlrW
   Bo9ZCiEUApcCH5HMDKs1tKWKkiRpo8XI85f/jm5X/I47V63mRnZlCIUs5HfUrYQ1DGGNrYxB7ZiL
   IUN6cdlljrZQ69hgKCM5fHw3tywlSan0xRdw5518/Iti8hav5MZ4KPdwH5Vcxdrhq2EIG4FhTGnR
   lFD2HsnB4JIkpccHH8B111F5/Q08G7bksk935kmmkDTl55IEsIbhq2EIm0yXLlPJzf0uO+44sGbm
   mGFM2dGUOWW3AbsCZSR9ZZAMj72mhWtbX03OKZOkjuq556CkhJWPlvHnvIFc+ek+TF+5E8k6QzF1
   g15HZPw6GfiInJwP2Xrrbqxe3Zl+/fo6+FWtYrOPWcrwXs1H15qPwNrHLkmS1HJWrYK//AXGjYNF
   i5i46wGcVvVdFn08gLpRFg3HWEwGPqFz59+y++75DBiwLYWFPzCAKbVSeyD5+rhSJkkdxOLFycT9
   666D/HwoKqIsZ0uOO+FGVqy4jySMFZOMthhO/aOQIC/vbB54wCCm7Gq2lbIQwrbAhcAQIK/mcowx
   Hrl5JUqStA4zZiRnUd53H3zrW/Dww5R9+DmXXHIHU6cuoqrqgJoXZjbu125VJoNe8/JmcOGFRxjI
   1GY0padsMnAf8N/A2cBpwMcxxgtbvLp11+RKmSS1N6tXw6RJfDT2UjpPe5N7t9yN3y3vzUc5fVi5
   cikrV24B7AF0IQljV1D/oPDkbMq6uyePN5ApFZrzQPJXYoz7hxDeiDHuXXPtpRjjfzRTrRvNUCZJ
   7cjy5XDHHVBayqeVVVy5bHdKPx5NJfcCfUlWv64DdqFuCn/mVmUSxkJ4h/3228owptRpzkb/2jsu
   F4YQvgl8CPTZnOIkSeL99+Haa1l540281G07bu6xK3fMW8Xq+AhJ8OpHXQjbI+ONjW1VzuTCC4+g
   uPjc1v4upGbTlFB2ZQihN/BTYDywBXB+i1YlSWqfYkxGWowbB5Mn8+yu+3Jm5VFM/+wc+HgCsKrm
   hZl/PXWmrncM6t9dmRwSPmHCea6Oqc1b59mXtWKMj8QYl8YYp8YYC2KM+8cYH26N4iRJ7cSqVXDP
   PSzZfU/eLxjBRY/MYptle/OV57dgeuU9wCSSlbHao5WrqD+FfziwgGTwKyTB7HL69v2UCRM8JFzt
   Q1N6yv7Y4FIEiDGe3lJFbYg9ZZLURixeDH/4Ayt+93teXx75dUU+j/I1VnMUSZ/YHtSNtQA4krqt
   yQnU9ZTVXrsDWE4IVey0U3dKSs4wkCn1mrOnrIy6YbF5wLEkfWWSJDVu+vRkpMX99/PqoN0569N9
   eamqD/Wb9fdg7TMpM7cmOwOvkZPzBnl5OeTkvFVzFFI/p/CrXdro4bEhhBzgXzHGQ1qmpCbV4EqZ
   JKXN6tUwcSKUlFDxwkvcnrsjv/lsK979oiewF3XrAMXUTeDPbNqvXRmrG/7at+/53HLLsQYwtWnN
   uVLW0K7AlzbhfZKk9mjZsmSkRUkJdO/O3wbtzSnLC1i2dHeSk/lq/6rJbNZvGMhqV8aeJTf3WPLy
   tmDw4J6Ot1CH0pSesmXUbV9GYBHw8xjjX1q4tvXV5EqZJGXbe+8lIy1u+gNPh95cXdmPSRU5wDbA
   UNY+k3I4jfeJJXdR1k7gd6yF2ptmGx6bRoYyScqOskf/yQMX/C/HzHmJI6oXc2fYjtI4hHfZvuYV
   y6ibKVZM3aDXzDCWNOvDEvLyupGfP5gBA3rZJ6Z2q1lCWQihG3ASsCfJuvJU4P4Y4+fNVeimMJRJ
   Uuv6vwf/waSzL+Kkj95hK6oo5cvczvl8zu0kzfu1MmeKZR6D5J2T6rg2O5SFEIYADwPPAC+RNAYc
   AHwF+CZwVIzx981W8UYwlElSyyorm8Ill9zB4rfn8YMvZnIeH/E2WzCOIyhjZ1bzK5JVsIatybW9
   YplN+8kxSF26vMvQoVvaJ6YOpzka/a8FzokxTm7wG38DeIJk1SwroUyS1Pxqg9j06XPYuTKHMbzP
   95jLXxnAUZzMVAY0eEfDSftQ17x/KsnK2InAKvLze1BScpZhTFqP9YWyAQ0DGUCM8fEQQiXwnZYr
   S5LUWsrKpjB6dAnvzlnNUSznaqazF8u4ngPYjaP5mC1rXtkwgGWuitXKbN7fnq5dp3HRRUfavC81
   wfq2L2cCe8cYKxpczwXeiDHu2gr1NcrtS0nadLUrYjNnLmD58k/pQR9OZT5jmMcyuvB7DuF+9mTl
   WqMsMgNYY5P2FwArCKEH3bv3Yrfd+rhVKdE8PWW/AL4M/CTGOLfm2mCgFHghxnh585W7cQxlkrTx
   alfE5syJQB92YBk/4XVO5z3KGcQ4DuZpdgCqG7yzsbsnFwA5dOlSTW5uXs2kfe+glBrTXHdf/gS4
   EOhRc2k58NsY4/hmqXITGcokaeOUlU3hzDMnsHDh53yVPMbwAkcyj9vZh2s5iLn0ynh1wy3JhqMs
   qsjP9+5JqamadU5ZCGELgBjjZ81Q22YzlEnSxhk17CL6PD6dIl5kSyop4WAmsA/L6FTzisa2Jt2S
   lJqDw2MlSfDxx7x9wUX0uutPTKcf4ziQ/2NnIrV/P6x7azI3tztDhmxjCJM2k6FMkjqg2ib+Lm+9
   zVkr5vAdFvEXtqeEHZnGYbg1KbU+Q5kkdSBlZVMYUziO3d9dQBHzGMJSrmcPbmJ7PmEo8DHJXZRu
   TUqtrdlCWQihB3ABsEOM8UchhF2A3WKMjzZPqRvPUCZJdSY+MJEnTv0lP1oxg0/pyTgO4n6GsIpO
   UG+sxXDqVsS6Aj3Zb79KXnnllixVLnUMzTHRv9YfgZdJjlcC+BD4M5C1UCZJAubOhfHjOXjctXy+
   eidO4zieYSCQ+Wd/5oyxx4C6AJaXdzaXX35Kq5Uraf2aEsryY4zfDyGcABBjXB7CBsOeJKklxAhP
   P82Cn/+CvOef5za2pXT1kczjYJIAtq4ZY7VDXi8BOtG16zQuvPBItyqlFGlKKKsMIeTVfhJCyAcq
   W64kSdJaKit57eLL6HbDTXSu+IJxcVcm8H2WU0myMtbYkUdQ/xzKG6hr5B9tIJNSpik9ZcOBscAQ
   ksPMvgqcFmN8suXLW2dN9pRJ6hg++ghuuonPf/O/PL8sl9+zD3+nN5Hak+46Ax8Akcaa+AFycnqS
   l9fTRn4pS5p7eOw2JEcuATwXY/xkM+vbLIYySe3eG2/w/n9fxJZPPM6f49Zcs3pn3qQ2TGVucmSu
   kAVqm/hD+De//OVRHgQupUBznH15AMn/eq25VPNrBIgxvrK5RW4qQ5mkdqm6GsrK+OSSYlZNm874
   1TvxB/ZjMVVALjC45oVVGW+qbeAfQbKZ0YmcnNe55JJhBjIpJZojlJVTP5TVE2P82iZXt5kMZZLa
   k4kPTOSFc37GSYtnsYQcfs9g/sxOrGJozSs6A28BO9d83tiRSEkg69p1GhdddKSBTEoRh8dKUkrV
   Tt2vfGs2Z6yYyal8zD/YjnHsw7N0J9mY2CPjHVXAQur+P9kjkaS2pDmHx+YB5wKHkvyJ8BRwQ4yx
   ojkK3RSGMkltVfGl1/HPK+6ncPU8DmchtzGI69iZ99i35hWdgbnA9hnvylwZCyRBrDPQmfz8nh6J
   JKVcc4ayB4DPgLtI/jQ4CdgyxnhccxS6KQxlktqcykr+dvyP2PGhh+hBZ0o4kDvYm+V0Jwlhg2pe
   WAXMAs5j7S1Kz6eU2qLmnOi/Z4xxSMbnT4QQpm96aZLUgSxaBDfeyJKrfkv3iu6M5UAe46vENfdO
   VZGMrsicvD8duJu6+WKvAa/TpUseQ4du6xal1E41JZS9EkI4JMb4LEAI4cskxy5JktbhqfG3sqT4
   ag7797vcTx9KOYjpHE7SsJ85db82hM0EepHcSVkElAC/BXLJy+vMhReOsHlfaueasn35FrAr8D5J
   T9kOwNsk/1sXY4x7t3SRjdTk9qWk1Cl7+EkeL/oV3577EvmxguvYk5vZjcV8BhzA2g37ULc1WQIs
   qbnWndzcHjbuS+1Ec/aUDVrf8zHGuRtTWHMwlElKlc8+446vHctXX3mexeTxe3bkzwyjik41L/iA
   pHG/sYb9SiDXECa1Y83WUxZjnBtC6AMMzHx9Sw6PDSGMBMYBnYBbYoxXt9TXkqRNNmcOcy74Ob0f
   fpBucVv4iuDZAAAgAElEQVRO5ns8xwCSENYt44UrqBvyWtsnthzIIz9/Gxv2JQFNWym7HDgNmAOs
   rr3eUsNjQwidSLZHvwHMB14ETowxzsh4jStlkrIjRp69qpSKq69h6KcfcguDuY4d+IBDM16UOegV
   oD/wBsnN68mQV3iNE0/cjbvv9v85pfauOe++PB7IjzGu3PyymuQg4J3abdEQwr3At4AZ63uTJLWo
   igoePOFHDH74b/SJgXHszDfZmy/Yh2RlLPPoo54kW5O1IrA3cD2QSwifcMIJexrIJNXTlFD2JtAH
   WNTCtdQaQHJTQa0PgINb6WtL0hplZVO47NyrOfq96ZzNB+SyFT9jfyZxGJF3qJu6X7s9OaHB71Db
   NzaPur6xHlx22eluV0paS1NC2a+AV0MI00g6UiG56/KYFqqpSfuSxcXFax4XFBRQUFDQQuVI6ihq
   jz+aPn0Oe1QuZgwfM5FPuI+dOJKvMoNDqftjM4+61bEjqD9XbAFJUOtBjx5bsttufWzglzqQ8vJy
   ysvLN/p9TekpmwHcAEyjrqcsxhj/udFfrSkFJXPQimOMI2s+vwhYndnsb0+ZpOZUXHw9V1/9ACsr
   enMMCxjDHHZmGdeyMzfzDf5Nd5JF+0HUBbHMqft9SRb5p+D2pKSGmnMkxosxxgObrbINCCF0Jmn0
   /zrwIfACNvpLagFlZVM444wrWbEol9OZRyHz+Igcfs8R/JU9qeJ96o4/mgHsQt025RJgW5Lm/dq7
   KVfRt28Ot9zyE1fFJK3RnKHsGpJty4ep275s6ZEYR1E3EuPWGOOvGzxvKJO00YqLr+d3v3uU5ctX
   EuNn5LMlhbzDD1nIY+xMCQfzPFXUrYjNIglikNxBWV7zee05lHNIVsZ60LPnai644OtO3Ze0luYM
   ZeU00ufVUiMxmsJQJqkpanvEZs5cwPLln5AMcN2SAmZRxDt8hc+4hZ24nm/wAT1q3lUbxIaT/L9h
   Z5Ljj2q3KMtqrnWmb99OropJ2qBmC2VpZCiTtD5lZVMYPbqEOXNWA1sB0I0FnEgniniBrqxgHIdz
   F3vzBbNZe1uyM3UrYh5/JGnzNGsoCyF8ExgC5NZeizFetlkVbgZDmaR1Oemkn3HPPbNI7kvai+1Y
   xjm8zI95iVfYnnEczGQ6ERlY8451bUtGoCc5Od0YPLiHU/clbbJmGx4bQriJ5N7vI4GbgeOA5ze7
   QklqRrVN+4sWdQf2ZD9eo4hH+E9mcg97cQQFvM0BNa+eRd3KWAQKSLYlp5FsS27jtqSkVteUnrKp
   McahIYQ3Yox7hxB6AhNjjIeu940tyJUySVDXMzZ16gyqqrYlh1V8ix4U8RyD+ZjxHMIt7MsS8qhb
   EeuFd05Kak3NeczSippfvwghDAAWk3S8SlKrq+sXW0gSrAJb0IczWEYhz7GALRnHQfyN3lQRgKU1
   H5krYpUkh5RcRU5OT3r0qPbOSUlZ15RQ9kgIoQ/wW+AVkj/Zbm7RqiSpgbow9jnQG9iendmaQiZz
   Mh8wkZ05gYN5gV9S/7ijhkcd9WTIkEE26ktKnY26+zKE0A3IjTF+2nIlNakOty+lDqS4+Hp+/ety
   Vq4MQORIujCGlziED7iZfK6ngPlsQbJF+QZ125ILgECXLnkMHbqtQUxSVmz23ZchhIOA92OMC2o+
   PxX4LjCX5BikfzdfuRvHUCa1f5nnUFZW9iKX3TmJGRTxFDl0YRwH8if2YgVz8bgjSWnWHKHsVeDr
   McZ/hxAOB+4DfgLsB+weY/xecxa8MQxlUvuz9qDX/sBW9GU+5/IFZ/EKL9GXcQzgcQ4lGV/hcUeS
   0q85QtnrMcZ9ah5fB3wcYyxu+Fw2GMqk9qVutlgfkpAV2Z+tKOIFvslM7mYopRzITE6kbsq+xx1J
   ahua4+7LTiGELjHGVcA3gLOa+D5JapKGs8U6sZpv8RZFfMCOLGU8BzGaXVhKEcmq2GNAEcmU/WeB
   NwihKzvtNNDhrpLavPWFq3uAf4YQPgG+AJ4CCCHsQnJ/uSRttPq9Yr2BrmzJbpzBCxTyAvPpyjgO
   42/sRjU5wEKSMHYqyarYDUAOeXndeeCB/2cQk9RurPfuyxDCISSds5NijMtrru0K9IwxvtI6JTZa
   l9uXUhtSP4htAWwNLGMXtmI0T/ID5lHGzpRwIC+xnLrG/Uz9gU5ANb17v8tdd51lIJPUJngguaSs
   Ky6+nquvfoCKij4k/WKLgT35OnMp4kUOYj5/YEdu4HI+5P9q3tWwcX8ByQzrHvTo0YvdduvjaAtJ
   bYqhTFLW1PWK9SJZ3dqFXFbxA56iiHcA1oy0qGBH1p4tthTY0mn7ktoFQ5mkVrV2r9gqYB/6sYJz
   eZGzeJkX2JJxfI1/MIi6kRbOFpPUvhnKJLW4hgeCw1bAMmAXDuA1iniPUcziT+xJKQcyi1UkJ7VB
   EsZqR1osB6rIz+/uXZSS2h1DmaQWVXf0URVJ0EpGWnybdyjiOQaymFIO4VbO51P+2uDdtedRdgY6
   k5/f0zAmqd0ylElqNpnT9lesqGT16hXANsBQYBa9GcSZvMJPeJH32IJxHMRDHEE1T1F/yGvStB9C
   D7p3t2lfUsdgKJO02crKpjB6dAlz5kSSuydrLQP2YFc+YTSPcxLzeLRmpMXLnEb9XrEyalfE+vbt
   5NFHkjocQ5mkzVJcfD1XXPEE1dXJ3ZN1It/gPYp4lgNZwE3syA1cwQLKap63V0ySMhnKJG2y4uLr
   ueyy/yPGfak9+COXVZzMGxTxPKuBcfwXd7OQCj5n7bligS5d8hg6dFu3JyV1eIYySRutbruyGtgS
   GEx//s25vMyPeI3n6c84DuIJzgIm4YHgkrRhhjJJG5TZwL98+afAl4CuwB4cyL8oYgEjeY+7GMh4
   9uAdtqx5Z+0W5WSgE127TuOii440iElSIwxlktap8Qb+ZXQin+8wiyKepT+fUsoQbuNQPuVb1D/y
   CHJyepKX19M7KCVpAwxlktZSP4x1obaBvw8rOJM3+AkvMJctGcdZPMxsqskhmSm2HOhK585LGDt2
   pCtikrQRDGWSgMaOP6oNY53ZjU8YzfOcyDQeYRdKOJBXOBV4jPp3UK4iP7+Hd1BK0iYwlEkdUG0A
   mzt3GZWVK6iqWsLKlduQbFEmxx9BJ4YxhyKe5QAWchP7cQP7s5DvUjdfzH4xSWouhjKpg6k79qh2
   gv4E6oIY5BH5Ia8zhudZRQ7j+C/uYQGVNSMvnC8mSS3DUCa1c2vfObk1ybFHVwC/qHlVZwbwGefx
   AmfyKs8wgHGcSzlvAP3w+CNJanlNDWWdN/QCSelRVjaF0tJJvPXW27z3XjXJtmRfoCewR8YrO3MQ
   H1DEs4xgDncylEO4mdn8A/gYOI0kjN1AsiK2jStikpRlrpRJbUDtXZPvvtubGE8FrqP+0UedgSo6
   U8132JcifkpfllHKydzGp3xGV9yelKTscPtSaifqesUCcB/J1mT9Re4+fM6PWM5PuIs5bLVmpMVq
   +lN/izKH3NzuDBmyjduTktRK3L6U2rD625SrgL2o+881WRUD2J1PGM2LnMBMHmIwxzCO13gOeBNY
   Qteu79O169t06dKDwYMHGcQkKcUMZVJK1J8nNoik72sWsG/NK5IgFljFcHpTRAn78m9uZDf24HQW
   8V2SMRbb14yxOMYxFpLUhrh9KaVAWdkUzjxzAgsXQjLGInObMglj3TmMHzKOMUynkgrGcTr3soBK
   PsY7JyUpvdy+lNqIsrIpnHrqdSxeXNu4X3+bcnv25Twu40yu4WkO4BwO55/kEcJUdtihH7vvvj+F
   hcMMYZLUxhnKpCwqLr6e3/zmDVasyBxnkayMHcw8iniP4fyOO/gmB7M7c+gErCA/P4eSkgsNYpLU
   jhjKpBbW8OijGFfQqdMWrFy5lJUrewIPUjvstTPVfJeuFDGALwGlDOEs/srnPAN0Ii9vBhde6JFH
   ktQeGcqkFlB/2n4usDtwCvXPlryO2oGvW3EwZ/E/nMcMZrENv+Y8HmU5q/mEEK5jxx36sfvufSks
   PM/VMUlqp2z0l5pZXdN+X6C2rzPz6KPax53ZgwWMAb7P/TzIlykhl9dZCeTQo4dN+5LUHtjoL7WC
   xrYmKyu7snr1viThqzjj1cl/boHVjOBdiniOfVjKDezJ7rzFR2wHQF7e2TzwwA8MYpLUwRjKpE1Q
   G8amTfucVat2pv7WZJeMV1atedSdLziFqYxhCCtYyjhO5xiqWcko4FqgEzk5r3Phhd5JKUkdUU62
   C5DamrKyKYwZ8xivvtqXVat2Aa4EJgH9ah5XURfGhjOQWVzFIczjDwxjBmdxIPtzH3cQagLZZGqb
   +C+5ZJhN/JLUQblSJjVR7erY1KmLqKp6hMa2JhPDgds5hFMpYgVf5zEmMJCDOIAPu+WRk/MRPTuN
   J8ZV5OS8xY47DmTAgF428UtSB2cok5qgfvP+9jVXqzJekTzuwkq+xwcU8SxbMZ9SduHHnY5k8D79
   GW/DviRpPVK3fRlCKA4hfBBCeLXmY2S2a5JKSyexcGHm9iQkK2ILgLFszUFcxETeZWvO5Bau4Gp2
   YwkP9D2cOx86n5dfvs5AJklar9SNxAghXAp8HmO8Zj2vcSSGml1Z2RRKSycxf/7HLFy4lJ49O7Ns
   WRU9e3Zm/vyVVFXtSbJlOQV4DLiSIUxgDL/mOObwcM52XN9lINO79KdLlx4MHtzTcRaSpDY/EmOD
   hUvNpbZXbMaMLlRUnEgSuH7A4sWPASNqfg3UrpAFDmUkz1HETgzlY27PG8RLNz/AqT/4Fqdm79uQ
   JLVxaV0p+y/gU+Al4KcxxqUNXuNKmTZZ5orYvHnvU1m5PatWbUvdUNfGfp1CD27hVBYxmrkspwe/
   53ymbPcC1996nKthkqR1aupKWVZ6ykIIk0MIUxv5OAa4ARgM7EvSsPO7bNSo9ql2nMWkScN5881t
   WLZsf1at+gN1i8Zr/7oD8/gNjzCXhzmSmZzJ9hyUk8/0/Z8zkEmSmk1Wti9jjMOa8roQwi3AI409
   V1xcvOZxQUEBBQUFzVGa2rGysimceup1LF58H8kK2JXUjbWoavDrKr7CvyjiPo5kPLdzGgfyKnMZ
   DMCIYZcwceLlrVm+JKmNKC8vp7y8fKPfl8bty34xxgU1j88HDowxntTgNW5fqsnq94xtRxLEaj/q
   tifhMbpwJMdRShFv04ePKOGH3E4XlvG/a36//PyLKSkZ6QqZJKlJ2nKj/9UhhH2BCLwLnJ3letSG
   1W5Xzp7dl/qHgmeOtRjLNhRxFndyLsfydujGb3N34cUv7c/nyxexdc9OdFt2Av369a0Z8mogkyQ1
   v9SFshjjKdmuQe1HaekkZs/O3KZMQhiMAMayFycwhtf5LjvwYKftuWCXozjlf8/jfkOXJKmVpS6U
   Sc2psrL2X/HalbHDCazmaK6niKcZwu/4y7b78+M9z+GUn36b+wxjkqQsSV1PWVPYU6Z1aTgAtrKy
   mmXL/kwy0uIRTmNHRlPK5/Ti7m0H8PWbxnD0t7+e7bIlSe1YW+4pkzZKZhCbMyewYsVJJANgbwKm
   sCPn8RPy+C9u5kn6c07XnVi6505cdvkJHO3KmCQpJVwpU5tV/67KG6g/8PVyvsq/KGIcX2Myf2QI
   d27Rn36HDKGwcJiN+pKkVuNKmdq02tWvysrOfPbZB0BXtthi2zWPV66srlkVq72rEqAzXVjJ8bxJ
   Ef9BLz6nhDGcxu0spydH7FfMxInFWfueJElaH0OZUmPtbcgbyTz8u/7j2lWxYgC+xEeczZOcwx94
   k1x+yXj+zlHEjEMrcnOrW/cbkiRpIxjKlDUNV8MWLNiChQuvoS5wAUwiCWENHyf/6g5lPmM4g+/w
   V/7MVxnOKN7khyThbdSar5WffzGFhSNb4buSJGnTGMrUatYdwqB+EMv813Ltx4HVjGI6RXyd3XmD
   69mTXZnJJ3wJmEJe3nVsu21nljnwVZLUhhjK1GKaHsKg/r+KVY0+7slyTmM8YyhhCZ0Zx248wHxW
   8RxQSm7uPIYM6cVll51nAJMktTmGMrWIuuONarcb1xfCoH4Qq526fyUwnEGcRyHdOJVb+Qf9OZUJ
   PMNXgKfIy/shu+X3q1kNO9MwJklqswxlahF1xxvVWl8Ig/pB7HAg8o2uR/Kz3Pc4YPkHPLz1Hpw7
   +L+YtXIZIdzNEb0mk5tbTWGhq2KSpPbBOWVqNpnbla+//i5Ll07IeLbhSlnmnZSJvn1PZ8e+XTlm
   xSK+/+Fz9N2iCz0v/jmccgr07Nk634QkSc2sqXPKDGXaJJkBrFu3Kg45pD933TV/PduVjYew/v3z
   6NXrS2wXPuOyAUvZ7R9/h6FDoagIRo6EnBwkSWrLDGVqNhsOYJCXdzwrVtyX8a71h7Bk63EYo7bf
   EkpK4G9/g+OOgzFjYM89W+17kySppTnRX81i7YZ9eOqphgEMVqzYo8E7kz6vPn1OZO+9d6sJYacl
   /V/V1fDoo/C/l8KsWXDeecmv22zT0t+OJEmpZSjTeq3dsN9YAIO1G/cBDueggybXHW302WfJqlhp
   KWy9NZx/Pnzve9ClS3OXLUlSm2PDjtarsrKx3N5YABtOXt6P611JpugPgzlzkgA2aBA88wzcdRc8
   /zyceKKBTJKkGq6UaY2GvWOjRw+nW7d1B7DkbMpEfv5ETj55b5577hIqKjqR262KS7/Wl0Nu+T08
   9RSccQa89hrssEPrfUOSJLUhNvoLaLx3LD9/LCefPGCtpv78/Is5+eTtee65BUkAq23aH3U4VFbC
   vffCuHGwYkXSuH/KKdCjRza+LUmSss67L7VRRoz4BZMmXdHI9UsoLBzG+PGT1w5gmRYtghtugBtv
   hH33TcLYiBGOtJAkdXjefamN0njvGFRUdGLUqMPXPTX/tdeSVbGHHoLjj4cnnoAhQ1qwUkmS2ieX
   MQSwjt4xyM2tXvtidTU8+CAUFMA3vwm77w7vvJOskhnIJEnaJK6UdTCNNfOPGnU4o0cPZ/bssWv1
   jhUWjqx782efwW23JSMttt02mbr/3e96B6UkSc3AUNaBNNbMP3v2WIA125Pjx1+S0Ts2Mrk+ezaM
   Hw933AHDh8Pdd8OXv5yV70GSpPbKRv8OZH3N/BMnXl7/YoxQXp70iz3zDJx5Jpx7Lgwc2DrFSpLU
   Ttjor7Wsr5k/4xO4554kjK1cmWxR3n23Iy0kSWphhrIOZL3N/AsXJiMtbroJ9tsPfvMbGDbMkRaS
   JLUS/8btQEaPHk5+/th6147Z/nRuWfUi7LEHfPQRPPkk/P3vzhiTJKmVuVLWzqzr7kqoa+a/rnQs
   +89/h+9/+By7VKwgb/hP4YG7Yautslm6JEkdmqGsHdng3ZWffsqot19i1My7oV8/uOQ38J3vONJC
   kqQU8O7LdmRdd1eeduh5/HG/TnDXXTByZHIE0sEHZ6FCSZI6Hu++7IDq310Z+RpPUsQ4Dn/+H3DY
   GHjjDdh++6zVJ0mS1s1Q1o5061ZFNyo4ibspYhydqWIcRdx6xBAe+tWvsl2eJElaD0NZG7G+Bn4A
   Fizg2q3ep0+nrXmh+gj+m/9lMsPIzx9LSdHR2StckiQ1iT1lbUBjDfz5+WMpKRnBqL49kkGvjz4K
   J51E+dAvc9WDMzOOShpWP7xJkqRW1dSeMkNZG9Cwgb8TVXyLh/if3uezVy+gsDA5BqlPn+wVKUmS
   GmWjfztS28C/JUs5g1spZDzzGcAD/Q9mr9fvgc7+Y5Qkqa1zZHsbMLjqI0opZA47sT+v8H3u51D+
   xfMDdzeQSZLUTvg3eivbYMN+rRjhiSdg3DhunPY0t/YewtClU/mQAQDk519MYeHIVq5ekiS1FENZ
   K9rgxH2AFSvg7ruT5v0YoaiIbvffz45PvMjQ8Teyy5oG/pE28EuS1I7Y6N+K1jVxf8SIS5h42zlw
   /fVw881w4IFQVARf/zqEDfYFSpKkFGtqo789Za2o/sT9xAG8xE9ffQj23BOWLoUpU5LxFt/4hoFM
   kqQOxO3LdWhy79dG6NatCkhGWnybByliHAN5n0m9d4Hn/ulIC0mSOjBDWSOa1Pu1CS44/RAKXv46
   Jy1+h/cZyDiKmLrTS1xzzdEGMkmSOjh7yhqx3t6viZdv/G84cyaUlsLdd/PBvv/B1SsGMrXbQCfu
   S5LUATg8djM01vsFUFHRqem/SYzw+OPJXZQvvghnnw3TprF9//6Mb6Y6JUlS+5GVRv8QwnEhhDdD
   CNUhhP0bPHdRCGFWCOGtEMLwbNRX2/vVUG5u9YbfvGJFcgfl0KFwwQXwne/AvHlw+eXQv38zVypJ
   ktqLbN19ORU4FpiSeTGEMAQ4HhgCjASuDyG0eo2jRw8nP39svWvJsNZh637T/PkwdizsuCM8/DCU
   lMAbb8AZZ0BeXgtXLEmS2rqsbF/GGN+CZI+1gW8B98QYVwFzQwjvAAcBz7VmfbU9XuPHX0LFhoa1
   vvBCEsD+/nf4wQ/gX/+CXXZpzXIlSVI7kLaesv7UD2AfQM25Qq1s1KjD192AX1UFf/tb0i82fz6M
   Hg3XXQe9e7dukZIkqd1osVAWQpgM9G3kqYtjjI9sxG+VnttDlyxJ+sWuvRYGDYKf/hSOOcZDwSVJ
   0mZrsTQRY1xPA9Y6zQcGZny+fc21tRQXF695XFBQQEFBwSZ8uSZ6661kpMU998B//meySnbAAS33
   9SRJUptVXl5OeXn5Rr8vq3PKQghPAv8dY3y55vMhwN0kfWQDgMeBnRsOJWu1sy8ffxyuuQZefjkZ
   aXHOOdCvX8t/XUmS1G6kek5ZCOFYoBTYBigLIbwaYzwqxjg9hHA/MB2oAs7N6snjTz4J3/se/PWv
   kJubtTIkSVL750R/SZKkFtTUlbJszSmTJElSBkOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmS
   JKWAoUySJCkFDGWSJEkpYCiTJElKAUOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUyS
   JCkFDGWSJEkpYCiTJElKAUOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWS
   JEkpYCiTJElKAUOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiT
   JElKAUOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiTJElKAUOZ
   JElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKVAVkJZCOG4EMKbIYTqEML+GdcHhRBWhBBerfm4
   Phv1SZIktbZsrZRNBY4FpjTy3Dsxxv1qPs5t5bq0DuXl5dkuocPxZ976/Jm3Pn/mrc+feXplJZTF
   GN+KMc7MxtfWpvE/4tbnz7z1+TNvff7MW58/8/RKY0/Z4Jqty/IQwqHZLkaSJKk1dG6p3ziEMBno
   28hTF8cYH1nH2z4EBsYYl9T0mj0YQtgzxvh5S9UpSZKUBiHGmL0vHsKTwE9jjK9szPMhhOwVLUmS
   tJFijGFDr2mxlbKNsKbIEMI2wJIYY3UIYSdgF2BOwzc05RuTJElqS7I1EuPYEML7wJeBshDC32ue
   OgJ4PYTwKvAAcHaMcWk2apQkSWpNWd2+lCRJUiKNd182SQjh8hDC6yGE10II/wghDMx2Te1dCOG3
   IYQZNT/3v4YQtsx2Te3dugYtq/mFEEaGEN4KIcwKIfws2/W0dyGE20IIi0IIU7NdS0cRQhgYQniy
   5s+UaSGE0dmuqb0LIeSGEJ6vySrTQwi/Xu/r2+pKWQihV+1dmSGEQmCfGOOZWS6rXQshDAP+EWNc
   HUK4CiDG+PMsl9WuhRB2B1YDN7Gem2K0eUIInYC3gW8A84EXgRNjjDOyWlg7FkI4DFgG3BFjHJrt
   ejqCEEJfoG+M8bUQQk/gZeDb/nveskII3WOMX4QQOgNPA/8dY3y6sde22ZWyBmMyegKfZKuWjiLG
   ODnGuLrm0+eB7bNZT0fgoOVWcxDJaSJzY4yrgHv/f3t3HyNXVYdx/Pu0UEBog9CYiKmpJbUIal8o
   pq3EEJsa0ehCJMFAlBfDH75AI0LUrEGNbyhRUIghJA0aEIhAfOG1EaEpukXD2oKlikQxiqHgS0Ga
   soLw+Mc9g7PLzOy27O6dmX0+yWTPnHvu3t+5aTa/nnPuPcBAzTH1Ndv3ArvqjmMmsb3T9rZS3g38
   Djii3qj6n+09pTgHmA38q13bnk3KACR9RdJfgDOAi+uOZ4Y5G7i97iAiJsnrgL82fX+s1EX0JUkL
   geVU/8GOKSRplqRtwBPAPbZ3tGvbDa/EaGu8F9DaHgQGJX0GuBQ4a1oD7EMTeemvpEHgOdvXTWtw
   fWofX7Qck6s313FE7IMydXkTsL6MmMUUKjNMy8o67I2STrC9qVXbrk7KbK+bYNPryKjNpBjvnks6
   E3gPsHZaApoB9uLfeUydvwHNDwstoBoti+grkvYHbgautf3juuOZSWw/Lek2YCWwqVWbnp2+lLS4
   6esAsLWuWGYKSe8GLgQGbI/UHc8MlJcmT537gcWSFkqaA5wK/LTmmCImlSQBG4Adti+rO56ZQNJ8
   SYeW8kHAOjrkK7389OVNwBLgBeCPwEdtP1lvVP1N0iNUCxUbixS32P5YjSH1PUknA98B5gNPA1tt
   n1hvVP1J0onAZVQLcTfY7vjoerwykq6nemH44cCTwEW2r643qv4m6XhgM/Ag/5+y/6ztO+uLqr9J
   egvwfapBsFnANbYvadu+V5OyiIiIiH7Ss9OXEREREf0kSVlEREREF0hSFhEREdEFkpRFREREdIEk
   ZRERERFdIElZRERERBdIUhYR+0TS4ZK2ls/jkh4r5V2SHprmWAYkvanp+xcl7fWuE+Xlsb9tc+wY
   SXdL+r2kP0j63CuJuUMMrfryzlLeJOnYqbhuRNQvSVlE7BPb/7S93PZy4ErgW6W8DHhxsq8naXaH
   w5YUMwAAAAPFSURBVCcDRzfF9nnbP5/Eax8E/AT4qu2jgKXAGklT8fLkVn25u/GV7NMZ0beSlEXE
   ZFHTz9mSrpK0XdJGSQcCSDpS0h2S7pe0WdKSUr+wjEI9IOkuSQtK/fckXSnpPuDrrc6XtAZ4H3CJ
   pN9IWlTO+0D5HcdJ+qWkbZJ+JemQcr3NkobLZ/U4fTsN+IXtuwBsPwt8Avh0ucYXJH3qpRtR9fv1
   pfyjEu92Sec0tdkt6cslri2SXjNeX0bdbOldkoZK/D+UdHCpv1jSQ+Vetn1zeER0nyRlETEVFgNX
   2H4z8BTQSCquAs61vZJqH9XvlvrLgattLwV+QLW1VMMRwGrbF7Q63/YQ1T6VF9heYftPlBGlso/l
   DcB5tpcBa4FngSeAdbaPBT445nqtHA0MN1eU68yVdAgvH71q/n52ifc44DxJry71r6LaqmwZ1dY3
   53TqS/MvlzQfGATWlj4MA+dLOgw4yfYx5V5+aZx+RUQX2a/uACKiLz1q+8FSHgYWlpGcNcCN1b7I
   QLWXKsAq4KRSvhb4RikbuNG2S/Kzus358PIN20W1P+7jtocBbO8GKMnaFZKWUu2f+8YJ9KndhvD7
   j3PeekmNvi2gSlh/DTxn+7ZSP0y1UfF412ocW0WVKA6VezEHGKLaH3VE0gbg1vKJiB6RpCwipsJ/
   msovAAdSjczvKuvOWmmXiOwpP2cBT3U4v9Vaq3brrz5Jlax9qKxVG2nTrmEH8I5RwUqLgD22d0n6
   L6NnHhrTtSdQjc6tsj0i6Z7GMeD5pvYvMvrv8UTWjf3M9mljKyW9rVzzFKop1r1+4CEi6pHpy4iY
   DrL9DPCopFMAVHlrOT5ENY0IcDrVdN4otv/d4fxngHljTwEeBl4raWU5Z25JwuYBO0u7DwOdHiKA
   akr1+MYTnWXh/7eBb5bjfwZWlGMrgDeU+nlUieiIpKOoRrjG06ovY/t1H/B2SUeWax4saXEZjTzU
   9h3A+VQPJEREj0hSFhGTxW3Kzd9PBz4iaRuwHXh/qT8XOEvSA6XN+ja/q935NwAXlkXvi1460X4e
   OBW4vJyzETiAai3bGaVuCbC7Q+zYHinXGpT0MPB34BHbl5YmNwOHSdoOfJwqGQS4E9hP0g7ga8CW
   NtdpXjfWsi9j4vkHcCZwfblnQ6Ufc4FbSt29VCOCEdEjZOfp6oiIvSFpALgIeK/tneO1j4iYiCRl
   EREREV0g05cRERERXSBJWUREREQXSFIWERER0QWSlEVERER0gSRlEREREV0gSVlEREREF0hSFhER
   EdEF/gdnB2p+pQ+LLgAAAABJRU5ErkJggg==
   "
   >
   </div>
   
   </div>
   
   <div class="output_area"><div class="prompt"></div>
   
   
   <div class="output_png output_subarea ">
   <img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAmUAAAGyCAYAAAClXLMtAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzs3Xl4ldW59/HvClPCoKBWGUTBOKI4HrW2Dqktg9Jja1vr
   UKsetVq1gWjPa6vUmuPQantqSXCsQ0WtYwennCJYTdE6zyAoCIKKgEpBBUkgYb1/PAnZCQECJNlP
   ku/nunKx8+y9yZ2o8HOt+7lXiDEiSZKk7MrJdgGSJEkylEmSJKWCoUySJCkFDGWSJEkpYCiTJElK
   AUOZJElSCmQtlIUQBoYQngwhvBlCmBZCGF1zfasQwuQQwswQwqQQQu9s1ShJktRaQrbmlIUQ+gJ9
   Y4yvhRB6Ai8D3wb+C/gkxvibEMLPgD4xxp9npUhJkqRWkrWVshjjwhjjazWPlwEzgAHAMcCEmpdN
   IAlqkiRJ7VoqespCCIOA/YDnge1ijItqnloEbJelsiRJklpN1kNZzdblX4AxMcbPM5+Lyd6q50BJ
   kqR2r3M2v3gIoQtJILszxvhgzeVFIYS+McaFIYR+wEeNvM+gJkmS2owYY9jQa7J592UAbgWmxxjH
   ZTz1MHBqzeNTgQcbvhcgxuhHK35ceumlWa+ho334M/dn3hE+/Jn7M+8IH02VzZWyrwInA2+EEF6t
   uXYRcBVwfwjhDGAu8P3slCdJktR6shbKYoxPs+6Vum+0Zi2SJEnZlvVGf7UNBQUF2S6hw/Fn3vr8
   mbc+f+atz595emVteOzmCCHEtli3JEnqeEIIxDQ3+kuSJKmOoUySJCkFDGWSJEkpYCiTJElKAUOZ
   JElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiTJElKAUOZJElSChjK
   JEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiTJElKAUOZJElSChjKJEmSUsBQ
   JkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiTJElKAUOZJElSChjKJEmSUsBQJkmSlAKG
   MkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiTJElKAUOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQw
   lEmSJKVA52wXIEmS1JrKyqZQWjqJysrOdOtWxejRwxk16vBsl2UokyRJHUdZ2RTGjHmM2bOvXHNt
   9uyxAFkPZm5fSpKkDqO0dFK9QAYwe/aVjB8/OUsV1clqKAsh3BZCWBRCmJpxrTiE8EEI4dWaj5HZ
   rFGSJLUflZWNbxJWVHRq5UrWlu2Vsj8CDUNXBK6JMe5X8zExC3VJkqR2qFu3qkav5+ZWt3Ila8tq
   KIsxPgUsaeSp0Nq1SJKk9m/06OHk54+tdy0//2IKC4dlqaI6aW30LwwhnAK8BPw0xrg02wVJkqS2
   r7aZf/z4S6io6ERubjWFhSOz3uQPEGKM2S0ghEHAIzHGoTWfbwt8XPP05UC/GOMZDd4Ts123JElS
   U4QQiDFucBcwdStlMcaPah+HEG4BHmnsdcXFxWseFxQUUFBQ0NKlSZIkbVB5eTnl5eUb/b40rpT1
   izEuqHl8PnBgjPGkBu9xpUySJLUJbWKlLIRwD3AEsE0I4X3gUqAghLAvyV2Y7wJnZ7FESZKkVpH1
   lbJN4UqZJElqK5q6UpbtOWWSJEnCUCZJkpQKhjJJkqQUMJRJkiSlgKFMkiQpBQxlkiRJKWAokyRJ
   SgFDmSRJUgoYyiRJklLAUCZJkpQChjJJkqQUMJRJkiSlgKFMkiQpBQxlkiRJKWAokyRJSgFDmSRJ
   UgoYyiRJklKgc7YLkCRJakxZ2RRKSydRWdmZbt2qGD16OKNGHZ7tslqMoUySJKVOWdkUxox5jNmz
   r1xzbfbssQDtNpi5fSlJklKntHRSvUAGMHv2lYwfPzlLFbU8Q5kkSUqdysrGN/MqKjq1ciWtx1Am
   SZJSp1u3qkav5+ZWt3IlrcdQJkmSUmf06OHk54+tdy0//2IKC4dlqaKWF2KM2a5ho4UQYlusW5Ik
   NV1Z2RTGj59MRUUncnOrKSwc1iab/EMIxBjDBl/XFsONoUySJLUVTQ1lbl9KkiSlgKFMkiQpBQxl
   kiRJKWAokyRJSgFDmSRJUgoYyiRJklLAUCZJkpQChjJJkqQUMJRJkiSlgKFMkiQpBQxlkiRJKWAo
   kyRJSgFDmSRJUgoYyiRJklLAUCZJkpQCnbNdgCRJat/KyqZQWjqJysrOdOtWxejRwxk16vBsl5U6
   hjJJktRiysqmMGbMY8yefeWaa7NnjwUwmDXg9qUkSWoxpaWT6gUygNmzr2T8+MlZqii9DGWSJKnF
   VFY2vilXUdGplStJP0OZJElqMd26VTV6PTe3upUrST9DmSRJajGjRw8nP39svWv5+RdTWDgsSxWl
   V4gxZu+Lh3AbMAr4KMY4tObaVsB9wI7AXOD7McalDd4Xs1m3JElq+l2VZWVTGD9+MhUVncjNraaw
   cFiHavIPIRBjDBt8XZZD2WHAMuCOjFD2G+CTGONvQgg/A/rEGH/e4H2GMkmSsqixuyrz88dSUjKi
   QwWupmhqKMvq9mWM8SlgSYPLxwATah5PAL7dqkVJkqQN8q7K5pfGnrLtYoyLah4vArbLZjGSJGlt
   3lXZ/NIYytao2aN0n1KSpJTxrsrml8aJ/otCCH1jjAtDCP2Ajxp7UXFx8ZrHBQUFFBQUtE51kiSJ
   0aOHM3v22AY9ZRdTWDgyi1WlQ3l5OeXl5Rv9vqw2+gOEEAYBjzRo9F8cY7w6hPBzoLeN/pIktb4N
   3V3Zpu+q/OQTePddOPDAFv9SbeXuy3uAI4BtSPrHfgk8BNwP7IAjMSRJyop2e3fltGlQUgJ//jOM
   Hg3/8z8t/iXbRCjbVIYySZJa1ogRv2DSpCsauX4JEydenoWKNsPq1fD3v8O4cUkoO/dcOPts2Hbb
   VvnyTQ1laewpkyRJWdYu7q5ctgxuvx1KS6FnTzj/fPj+96Fbt2xX1ihDmSRJWkubvrty7ly49lr4
   4x+hoABuvRUOPRTCBhersirVIzEkSVJ2tLkzK2OEp5+G730PDjggufbyy/CXv8Bhh6U+kIE9ZZIk
   aR3axN2VK1fC/fcn/WKffgpjxsCpp0KvXtmubA0b/SVJUvv18cdw001w/fUwZAgUFcHRR0NO+jYB
   28TZl5IkSRvljTfgjDNg112T3rHHHoPHH4dvfjOVgWxj2OgvSZLSbfVqKCtLtihnzEhGWsycCV/6
   UrYra1aGMkmSlE6ff1430mLLLZORFscdB127ZruyFmEokyRJ6fLuu8lIi9tvhyOPTH79ylfaxB2U
   m6Ntb75KkqT2IUZ46in47nfhP/4j6Q975RV44AH46lfbfSADV8okSerQNnToeIurrIT77kvOo/z8
   82SkxYQJyQT+DsZQJklSB9XYoeOzZycDY1s8mH30Edx4I9xwA+y1F1x2GRx1VJu/g3JzOKdMkqQO
   oLEVsdLSSa1/6PjrryerYn/7W9K0P3p0EsraMQ8klyRJwLpXxPLyljf6+mY/dLy6um6kxdtvw3nn
   waxZsM02zft12jhDmSRJ7Vxp6aR6gQxg9uwr2Xrr4xt9fbMdOv7558mh4KWl0KdPMtLie99rtyMt
   NlfH3biVJKmDqKxsfA2mb9/eLXPo+LvvwgUXwKBBySHhd9wBL7wAJ51kIFsPV8okSWrnunWravT6
   9ttvS2HhMMaPvyTj0PGRm9bkHyNMmZL0i02ZAqefnoy02HHHzay+47DRX5Kkdq6xnrL8/IspKdnE
   AJapshLuvTfpF/vii+Rg8FNOgR49NrPq9qOpjf6GMkmSOoCysimMHz85Y0Vs2OYFskWL6kZa7LNP
   EsZGjOjQIy3WxVAmSZKa32uvJVuUDz4I3/9+MtJizz2zXVWqORJDkqQOqtmn9FdXw6OPJluUs2Y5
   0qKFGMokSWrDGgawQw7pz113zW+eKf2ffQa33QbjxycBrKgoGWnRpUtzfguq4falJEltVGMN/Hl5
   x7NixX1rvXajpvTPnp0EsTvugOHDkzD25S83V9kdTlO3L+3GkySpjWpsKOyKFXs0+toNTumPEcrL
   4dvfhoMPhtzc5Eike+81kLUSty8lSWqjGh8K2/hMsnVO6a+oqBtpUVGRrIr96U+OtMgCQ5kkSW1U
   40Nhh5OX92NWrLhxzZVkSv/I+i9buDAZaXHjjbDvvnDVVclWpSMtssZQJklSGzV69HBmzx7bYCjs
   RE4+eW+ee24dU/pffTUZafHQQ3D88fDEEzBkSJa+A2Wy0V+SpDasSUNhq6vh4YeTLco5c+AnP4Ef
   /Qi22io7RXcwDo+VJKmj+/TTZKRFaSn07Zv0i33nO460aGUOj5UkqR1obA7Zs89+uP7BsO+8k4y0
   uPPO5Oije+7xDso2wFAmSVJKrT2HbApPPHE3VVV1TfxrBsMefVgy0mLcOHjmGTjzzGSkxcCBrV+4
   Nonbl5IkpdSIEb9g0qQrMq78Arii3mu6UcGv9jyOCzq9BytXJluUP/whdO/eqrVq3dy+lCSpjVt7
   Dlnd531ZwDncwNncxNwPt4B7roVhwxxp0Yb5T06SpJRaew5ZFfvxChM4hekMYRs+4Qj+yaUHnZD0
   jhnI2jT/6UmSlCJlZVMYMeIXFBQU8/HHC+nb9wJyqOZY/so/eYSHOJxp7EU+szmP66nKv4PCwmHZ
   LlvNwJ4ySZJSomFj/xZ8yvm9hvOjyhksyd2ShwYfRPV/FvDMix+tfy6ZUqXZ5pSFEHYGPogxVoQQ
   vgYMBe6IMS5tnlI3nqFMktReZI68mDZtBosX38fOzKKQ8ZzMXUxkJM8fnEvJc7dlu1RtoqaGsqZs
   X/4FqKoJZzcBA4G7N7M+SZI6vNqVsUmTruCf/7yUfRZ342H+k2f4Csvoyd68wQ+4m9dzd8h2qWoF
   Tbn7cnWMsSqE8B1gfIxxfAjh1ZYuTJKk9q60dBLzZ/+C07mVIsaRw0LG8SuO5z5WUDfSIje3OotV
   qrU0JZStDCGcBJwC/GfNNc9nkCRpc3z4IT94awp38gde5EAu4BoepyswCTICWX7+xRQWjsxamWo9
   TQllpwNnA1fGGN8NIQwG7mzZsiRJaqdefjmZuv/oo/Tulc9hPMVMdst4QWDrrU9gr712r2nkH2kj
   fwfRpLsvQwjdgR1ijG+1fEkbZqO/JKlNqaqCBx+EkhKYN48Z3xjFL+Z25+2PljFnTmDFirpjk/Lz
   L6akxCDWnjTn3ZfHAL8FusUYB4UQ9gP+J8Z4TPOUuvEMZZKkNmHpUrjlFhg/nn/32ILru+zKA1Vb
   MevdThlBbAp5edeRn9+PAQN6OeKiHWrOUPYKcCTwZIxxv5pr02KMezVLpZvAUCZJSrWZM6G0FP70
   Jxg1iqcPOIzTrnuvZv7Y2udXAowYcQkTJ17e6qWq5TXn2ZerYoxLQ6j3e63e5MokSWqPYoR//INF
   F/+Sbq+9ziP9DuDO7UfyyfQtmPt/T7Jkyb01L2z8r96Kik6tV6tSqSmh7M0Qwg+AziGEXYDRwDMt
   W5YkSelXVjaFG39fxuHvz+DY955idfVqfh/34/aqT6h470XgMeBKoDjjXQ3Ps0w49kJNGR5bCOwJ
   VAL3AJ8BRS1ZlCRJaVZWNoURe53ItG8Vces//sgeMz/hxxVHsduqn3BjVTkV5JGMtriy5h2ZQWw4
   MLbe75eMvfD8yo5ugytlMcblwMU1H60mhDCXJABWk2yhHtSaX1+SpEy1xyH1eedNvj1vGvdWf8Cf
   OINDGc0s7iDpEyvOeEfmX7G1QexKIGniz8s7PqO537sttZ5QFkJ4ZD3vi61w92UECmKM/27hryNJ
   0nr938NPMPGsa/nlokUM4E3Gcwk/5mM+5aqaV9T+dZq5Ipb5uDZwXUKfPu9x0EE7UFh4nkFM9axv
   pex3rVbFum3wTgVJklrMkiXM+OnFDJ1wB71W7881XMBDvE41PyW5i7JWbQDLXBHLfAxwOPn5Eykp
   OcMwpkY1aXhsNoQQ5gCfkmxf3hRjvDnjOUdiSJJazttvQ2kpqybcQVkYxBXLDuFl/lDzZO1IiynU
   NfI3fDyZ3Nx59O+/kt69t6ZXry/VTOd3BllHtNkjMUIID8QYjwshTCPZSswUY4x7b26RG/DVGOOC
   EMKXgMkhhLdijE/VPllcXLzmhQUFBRQUFLRwOZKkdi1GmDw5mbr/4ovMOvIoju36Nd5c8jD1V8Ua
   roBdkhHAzqsJYFBYeKYBrIMqLy+nvLx8o9+3zpWyEEL/GOOHIYQdWXsbMcYY5230V9tEIYRLgWUx
   xt/VfO5KmSSpeXzxBdx1VxLGcnJ448ijOfufi3jt7TwqKrYjad7PXAkDp/BrYzTnRP+rY4w/29C1
   5lRz1manGOPnIYQeJPcV/0+McVLN84YySdLmmT8frrsObr4ZDjmE5758JOc+MJUZb3WlomJrki3K
   zOn7ybYkdGLrrd9iwoRzDWJqkqaGsqbMKRveyLWjN76kjbId8FQI4TXgeeDR2kAmSdJmeeEFOOkk
   Vu6+Bw/+aTJH9/46vZ6s4vDi6bz6Wj8qKm6grrsnc6bY4cDl5OevNJCpRayvp+wc4FwgP4QwNeOp
   XsC/WrKoGOO7wL4t+TUkSR1DWdkUrh03kSFvvcDxC1+jf6zguk4DuWX1sXzy3hkk25KB+nPGau+m
   rBtlUbtCVlJiIFPLWN9IjLuBvwNXAT+jrq/s8xjj4pYuTJKkTVU76HXBm1M5+sMPuSm+x1y6cRVF
   PMxyqqs7Ubc9mXkMUmOjLQ4nGWdxsYFMLWqd25cxxk9jjHNjjCcAHwArSQ4i7xFC2KG1CpQkaWOU
   lU2h5Jw/8e1JU/nn/L8zJO7BsXyTI3iPv1FBNb+mbk2i4dDX2jB2ODCC5M7KU9h///MoKXHqvlrW
   Bo9ZCiEUApcCH5HMDKs1tKWKkiRpo8XI85f/jm5X/I47V63mRnZlCIUs5HfUrYQ1DGGNrYxB7ZiL
   IUN6cdlljrZQ69hgKCM5fHw3tywlSan0xRdw5518/Iti8hav5MZ4KPdwH5Vcxdrhq2EIG4FhTGnR
   lFD2HsnB4JIkpccHH8B111F5/Q08G7bksk935kmmkDTl55IEsIbhq2EIm0yXLlPJzf0uO+44sGbm
   mGFM2dGUOWW3AbsCZSR9ZZAMj72mhWtbX03OKZOkjuq556CkhJWPlvHnvIFc+ek+TF+5E8k6QzF1
   g15HZPw6GfiInJwP2Xrrbqxe3Zl+/fo6+FWtYrOPWcrwXs1H15qPwNrHLkmS1HJWrYK//AXGjYNF
   i5i46wGcVvVdFn08gLpRFg3HWEwGPqFz59+y++75DBiwLYWFPzCAKbVSeyD5+rhSJkkdxOLFycT9
   666D/HwoKqIsZ0uOO+FGVqy4jySMFZOMthhO/aOQIC/vbB54wCCm7Gq2lbIQwrbAhcAQIK/mcowx
   Hrl5JUqStA4zZiRnUd53H3zrW/Dww5R9+DmXXHIHU6cuoqrqgJoXZjbu125VJoNe8/JmcOGFRxjI
   1GY0padsMnAf8N/A2cBpwMcxxgtbvLp11+RKmSS1N6tXw6RJfDT2UjpPe5N7t9yN3y3vzUc5fVi5
   cikrV24B7AF0IQljV1D/oPDkbMq6uyePN5ApFZrzQPJXYoz7hxDeiDHuXXPtpRjjfzRTrRvNUCZJ
   7cjy5XDHHVBayqeVVVy5bHdKPx5NJfcCfUlWv64DdqFuCn/mVmUSxkJ4h/3228owptRpzkb/2jsu
   F4YQvgl8CPTZnOIkSeL99+Haa1l540281G07bu6xK3fMW8Xq+AhJ8OpHXQjbI+ONjW1VzuTCC4+g
   uPjc1v4upGbTlFB2ZQihN/BTYDywBXB+i1YlSWqfYkxGWowbB5Mn8+yu+3Jm5VFM/+wc+HgCsKrm
   hZl/PXWmrncM6t9dmRwSPmHCea6Oqc1b59mXtWKMj8QYl8YYp8YYC2KM+8cYH26N4iRJ7cSqVXDP
   PSzZfU/eLxjBRY/MYptle/OV57dgeuU9wCSSlbHao5WrqD+FfziwgGTwKyTB7HL69v2UCRM8JFzt
   Q1N6yv7Y4FIEiDGe3lJFbYg9ZZLURixeDH/4Ayt+93teXx75dUU+j/I1VnMUSZ/YHtSNtQA4krqt
   yQnU9ZTVXrsDWE4IVey0U3dKSs4wkCn1mrOnrIy6YbF5wLEkfWWSJDVu+vRkpMX99/PqoN0569N9
   eamqD/Wb9fdg7TMpM7cmOwOvkZPzBnl5OeTkvFVzFFI/p/CrXdro4bEhhBzgXzHGQ1qmpCbV4EqZ
   JKXN6tUwcSKUlFDxwkvcnrsjv/lsK979oiewF3XrAMXUTeDPbNqvXRmrG/7at+/53HLLsQYwtWnN
   uVLW0K7AlzbhfZKk9mjZsmSkRUkJdO/O3wbtzSnLC1i2dHeSk/lq/6rJbNZvGMhqV8aeJTf3WPLy
   tmDw4J6Ot1CH0pSesmXUbV9GYBHw8xjjX1q4tvXV5EqZJGXbe+8lIy1u+gNPh95cXdmPSRU5wDbA
   UNY+k3I4jfeJJXdR1k7gd6yF2ptmGx6bRoYyScqOskf/yQMX/C/HzHmJI6oXc2fYjtI4hHfZvuYV
   y6ibKVZM3aDXzDCWNOvDEvLyupGfP5gBA3rZJ6Z2q1lCWQihG3ASsCfJuvJU4P4Y4+fNVeimMJRJ
   Uuv6vwf/waSzL+Kkj95hK6oo5cvczvl8zu0kzfu1MmeKZR6D5J2T6rg2O5SFEIYADwPPAC+RNAYc
   AHwF+CZwVIzx981W8UYwlElSyyorm8Ill9zB4rfn8YMvZnIeH/E2WzCOIyhjZ1bzK5JVsIatybW9
   YplN+8kxSF26vMvQoVvaJ6YOpzka/a8FzokxTm7wG38DeIJk1SwroUyS1Pxqg9j06XPYuTKHMbzP
   95jLXxnAUZzMVAY0eEfDSftQ17x/KsnK2InAKvLze1BScpZhTFqP9YWyAQ0DGUCM8fEQQiXwnZYr
   S5LUWsrKpjB6dAnvzlnNUSznaqazF8u4ngPYjaP5mC1rXtkwgGWuitXKbN7fnq5dp3HRRUfavC81
   wfq2L2cCe8cYKxpczwXeiDHu2gr1NcrtS0nadLUrYjNnLmD58k/pQR9OZT5jmMcyuvB7DuF+9mTl
   WqMsMgNYY5P2FwArCKEH3bv3Yrfd+rhVKdE8PWW/AL4M/CTGOLfm2mCgFHghxnh585W7cQxlkrTx
   alfE5syJQB92YBk/4XVO5z3KGcQ4DuZpdgCqG7yzsbsnFwA5dOlSTW5uXs2kfe+glBrTXHdf/gS4
   EOhRc2k58NsY4/hmqXITGcokaeOUlU3hzDMnsHDh53yVPMbwAkcyj9vZh2s5iLn0ynh1wy3JhqMs
   qsjP9+5JqamadU5ZCGELgBjjZ81Q22YzlEnSxhk17CL6PD6dIl5kSyop4WAmsA/L6FTzisa2Jt2S
   lJqDw2MlSfDxx7x9wUX0uutPTKcf4ziQ/2NnIrV/P6x7azI3tztDhmxjCJM2k6FMkjqg2ib+Lm+9
   zVkr5vAdFvEXtqeEHZnGYbg1KbU+Q5kkdSBlZVMYUziO3d9dQBHzGMJSrmcPbmJ7PmEo8DHJXZRu
   TUqtrdlCWQihB3ABsEOM8UchhF2A3WKMjzZPqRvPUCZJdSY+MJEnTv0lP1oxg0/pyTgO4n6GsIpO
   UG+sxXDqVsS6Aj3Zb79KXnnllixVLnUMzTHRv9YfgZdJjlcC+BD4M5C1UCZJAubOhfHjOXjctXy+
   eidO4zieYSCQ+Wd/5oyxx4C6AJaXdzaXX35Kq5Uraf2aEsryY4zfDyGcABBjXB7CBsOeJKklxAhP
   P82Cn/+CvOef5za2pXT1kczjYJIAtq4ZY7VDXi8BOtG16zQuvPBItyqlFGlKKKsMIeTVfhJCyAcq
   W64kSdJaKit57eLL6HbDTXSu+IJxcVcm8H2WU0myMtbYkUdQ/xzKG6hr5B9tIJNSpik9ZcOBscAQ
   ksPMvgqcFmN8suXLW2dN9pRJ6hg++ghuuonPf/O/PL8sl9+zD3+nN5Hak+46Ax8Akcaa+AFycnqS
   l9fTRn4pS5p7eOw2JEcuATwXY/xkM+vbLIYySe3eG2/w/n9fxJZPPM6f49Zcs3pn3qQ2TGVucmSu
   kAVqm/hD+De//OVRHgQupUBznH15AMn/eq25VPNrBIgxvrK5RW4qQ5mkdqm6GsrK+OSSYlZNm874
   1TvxB/ZjMVVALjC45oVVGW+qbeAfQbKZ0YmcnNe55JJhBjIpJZojlJVTP5TVE2P82iZXt5kMZZLa
   k4kPTOSFc37GSYtnsYQcfs9g/sxOrGJozSs6A28BO9d83tiRSEkg69p1GhdddKSBTEoRh8dKUkrV
   Tt2vfGs2Z6yYyal8zD/YjnHsw7N0J9mY2CPjHVXAQur+P9kjkaS2pDmHx+YB5wKHkvyJ8BRwQ4yx
   ojkK3RSGMkltVfGl1/HPK+6ncPU8DmchtzGI69iZ99i35hWdgbnA9hnvylwZCyRBrDPQmfz8nh6J
   JKVcc4ayB4DPgLtI/jQ4CdgyxnhccxS6KQxlktqcykr+dvyP2PGhh+hBZ0o4kDvYm+V0Jwlhg2pe
   WAXMAs5j7S1Kz6eU2qLmnOi/Z4xxSMbnT4QQpm96aZLUgSxaBDfeyJKrfkv3iu6M5UAe46vENfdO
   VZGMrsicvD8duJu6+WKvAa/TpUseQ4du6xal1E41JZS9EkI4JMb4LEAI4cskxy5JktbhqfG3sqT4
   ag7797vcTx9KOYjpHE7SsJ85db82hM0EepHcSVkElAC/BXLJy+vMhReOsHlfaueasn35FrAr8D5J
   T9kOwNsk/1sXY4x7t3SRjdTk9qWk1Cl7+EkeL/oV3577EvmxguvYk5vZjcV8BhzA2g37ULc1WQIs
   qbnWndzcHjbuS+1Ec/aUDVrf8zHGuRtTWHMwlElKlc8+446vHctXX3mexeTxe3bkzwyjik41L/iA
   pHG/sYb9SiDXECa1Y83WUxZjnBtC6AMMzHx9Sw6PDSGMBMYBnYBbYoxXt9TXkqRNNmcOcy74Ob0f
   fpBucVv4iuDZAAAgAElEQVRO5ns8xwCSENYt44UrqBvyWtsnthzIIz9/Gxv2JQFNWym7HDgNmAOs
   rr3eUsNjQwidSLZHvwHMB14ETowxzsh4jStlkrIjRp69qpSKq69h6KcfcguDuY4d+IBDM16UOegV
   oD/wBsnN68mQV3iNE0/cjbvv9v85pfauOe++PB7IjzGu3PyymuQg4J3abdEQwr3At4AZ63uTJLWo
   igoePOFHDH74b/SJgXHszDfZmy/Yh2RlLPPoo54kW5O1IrA3cD2QSwifcMIJexrIJNXTlFD2JtAH
   WNTCtdQaQHJTQa0PgINb6WtL0hplZVO47NyrOfq96ZzNB+SyFT9jfyZxGJF3qJu6X7s9OaHB71Db
   NzaPur6xHlx22eluV0paS1NC2a+AV0MI00g6UiG56/KYFqqpSfuSxcXFax4XFBRQUFDQQuVI6ihq
   jz+aPn0Oe1QuZgwfM5FPuI+dOJKvMoNDqftjM4+61bEjqD9XbAFJUOtBjx5bsttufWzglzqQ8vJy
   ysvLN/p9TekpmwHcAEyjrqcsxhj/udFfrSkFJXPQimOMI2s+vwhYndnsb0+ZpOZUXHw9V1/9ACsr
   enMMCxjDHHZmGdeyMzfzDf5Nd5JF+0HUBbHMqft9SRb5p+D2pKSGmnMkxosxxgObrbINCCF0Jmn0
   /zrwIfACNvpLagFlZVM444wrWbEol9OZRyHz+Igcfs8R/JU9qeJ96o4/mgHsQt025RJgW5Lm/dq7
   KVfRt28Ot9zyE1fFJK3RnKHsGpJty4ep275s6ZEYR1E3EuPWGOOvGzxvKJO00YqLr+d3v3uU5ctX
   EuNn5LMlhbzDD1nIY+xMCQfzPFXUrYjNIglikNxBWV7zee05lHNIVsZ60LPnai644OtO3Ze0luYM
   ZeU00ufVUiMxmsJQJqkpanvEZs5cwPLln5AMcN2SAmZRxDt8hc+4hZ24nm/wAT1q3lUbxIaT/L9h
   Z5Ljj2q3KMtqrnWmb99OropJ2qBmC2VpZCiTtD5lZVMYPbqEOXNWA1sB0I0FnEgniniBrqxgHIdz
   F3vzBbNZe1uyM3UrYh5/JGnzNGsoCyF8ExgC5NZeizFetlkVbgZDmaR1Oemkn3HPPbNI7kvai+1Y
   xjm8zI95iVfYnnEczGQ6ERlY8451bUtGoCc5Od0YPLiHU/clbbJmGx4bQriJ5N7vI4GbgeOA5ze7
   QklqRrVN+4sWdQf2ZD9eo4hH+E9mcg97cQQFvM0BNa+eRd3KWAQKSLYlp5FsS27jtqSkVteUnrKp
   McahIYQ3Yox7hxB6AhNjjIeu940tyJUySVDXMzZ16gyqqrYlh1V8ix4U8RyD+ZjxHMIt7MsS8qhb
   EeuFd05Kak3NeczSippfvwghDAAWk3S8SlKrq+sXW0gSrAJb0IczWEYhz7GALRnHQfyN3lQRgKU1
   H5krYpUkh5RcRU5OT3r0qPbOSUlZ15RQ9kgIoQ/wW+AVkj/Zbm7RqiSpgbow9jnQG9iendmaQiZz
   Mh8wkZ05gYN5gV9S/7ijhkcd9WTIkEE26ktKnY26+zKE0A3IjTF+2nIlNakOty+lDqS4+Hp+/ety
   Vq4MQORIujCGlziED7iZfK6ngPlsQbJF+QZ125ILgECXLnkMHbqtQUxSVmz23ZchhIOA92OMC2o+
   PxX4LjCX5BikfzdfuRvHUCa1f5nnUFZW9iKX3TmJGRTxFDl0YRwH8if2YgVz8bgjSWnWHKHsVeDr
   McZ/hxAOB+4DfgLsB+weY/xecxa8MQxlUvuz9qDX/sBW9GU+5/IFZ/EKL9GXcQzgcQ4lGV/hcUeS
   0q85QtnrMcZ9ah5fB3wcYyxu+Fw2GMqk9qVutlgfkpAV2Z+tKOIFvslM7mYopRzITE6kbsq+xx1J
   ahua4+7LTiGELjHGVcA3gLOa+D5JapKGs8U6sZpv8RZFfMCOLGU8BzGaXVhKEcmq2GNAEcmU/WeB
   NwihKzvtNNDhrpLavPWFq3uAf4YQPgG+AJ4CCCHsQnJ/uSRttPq9Yr2BrmzJbpzBCxTyAvPpyjgO
   42/sRjU5wEKSMHYqyarYDUAOeXndeeCB/2cQk9RurPfuyxDCISSds5NijMtrru0K9IwxvtI6JTZa
   l9uXUhtSP4htAWwNLGMXtmI0T/ID5lHGzpRwIC+xnLrG/Uz9gU5ANb17v8tdd51lIJPUJngguaSs
   Ky6+nquvfoCKij4k/WKLgT35OnMp4kUOYj5/YEdu4HI+5P9q3tWwcX8ByQzrHvTo0YvdduvjaAtJ
   bYqhTFLW1PWK9SJZ3dqFXFbxA56iiHcA1oy0qGBH1p4tthTY0mn7ktoFQ5mkVrV2r9gqYB/6sYJz
   eZGzeJkX2JJxfI1/MIi6kRbOFpPUvhnKJLW4hgeCw1bAMmAXDuA1iniPUcziT+xJKQcyi1UkJ7VB
   EsZqR1osB6rIz+/uXZSS2h1DmaQWVXf0URVJ0EpGWnybdyjiOQaymFIO4VbO51P+2uDdtedRdgY6
   k5/f0zAmqd0ylElqNpnT9lesqGT16hXANsBQYBa9GcSZvMJPeJH32IJxHMRDHEE1T1F/yGvStB9C
   D7p3t2lfUsdgKJO02crKpjB6dAlz5kSSuydrLQP2YFc+YTSPcxLzeLRmpMXLnEb9XrEyalfE+vbt
   5NFHkjocQ5mkzVJcfD1XXPEE1dXJ3ZN1It/gPYp4lgNZwE3syA1cwQLKap63V0ySMhnKJG2y4uLr
   ueyy/yPGfak9+COXVZzMGxTxPKuBcfwXd7OQCj5n7bligS5d8hg6dFu3JyV1eIYySRutbruyGtgS
   GEx//s25vMyPeI3n6c84DuIJzgIm4YHgkrRhhjJJG5TZwL98+afAl4CuwB4cyL8oYgEjeY+7GMh4
   9uAdtqx5Z+0W5WSgE127TuOii440iElSIwxlktap8Qb+ZXQin+8wiyKepT+fUsoQbuNQPuVb1D/y
   CHJyepKX19M7KCVpAwxlktZSP4x1obaBvw8rOJM3+AkvMJctGcdZPMxsqskhmSm2HOhK585LGDt2
   pCtikrQRDGWSgMaOP6oNY53ZjU8YzfOcyDQeYRdKOJBXOBV4jPp3UK4iP7+Hd1BK0iYwlEkdUG0A
   mzt3GZWVK6iqWsLKlduQbFEmxx9BJ4YxhyKe5QAWchP7cQP7s5DvUjdfzH4xSWouhjKpg6k79qh2
   gv4E6oIY5BH5Ia8zhudZRQ7j+C/uYQGVNSMvnC8mSS3DUCa1c2vfObk1ybFHVwC/qHlVZwbwGefx
   AmfyKs8wgHGcSzlvAP3w+CNJanlNDWWdN/QCSelRVjaF0tJJvPXW27z3XjXJtmRfoCewR8YrO3MQ
   H1DEs4xgDncylEO4mdn8A/gYOI0kjN1AsiK2jStikpRlrpRJbUDtXZPvvtubGE8FrqP+0UedgSo6
   U8132JcifkpfllHKydzGp3xGV9yelKTscPtSaifqesUCcB/J1mT9Re4+fM6PWM5PuIs5bLVmpMVq
   +lN/izKH3NzuDBmyjduTktRK3L6U2rD625SrgL2o+881WRUD2J1PGM2LnMBMHmIwxzCO13gOeBNY
   Qteu79O169t06dKDwYMHGcQkKcUMZVJK1J8nNoik72sWsG/NK5IgFljFcHpTRAn78m9uZDf24HQW
   8V2SMRbb14yxOMYxFpLUhrh9KaVAWdkUzjxzAgsXQjLGInObMglj3TmMHzKOMUynkgrGcTr3soBK
   PsY7JyUpvdy+lNqIsrIpnHrqdSxeXNu4X3+bcnv25Twu40yu4WkO4BwO55/kEcJUdtihH7vvvj+F
   hcMMYZLUxhnKpCwqLr6e3/zmDVasyBxnkayMHcw8iniP4fyOO/gmB7M7c+gErCA/P4eSkgsNYpLU
   jhjKpBbW8OijGFfQqdMWrFy5lJUrewIPUjvstTPVfJeuFDGALwGlDOEs/srnPAN0Ii9vBhde6JFH
   ktQeGcqkFlB/2n4usDtwCvXPlryO2oGvW3EwZ/E/nMcMZrENv+Y8HmU5q/mEEK5jxx36sfvufSks
   PM/VMUlqp2z0l5pZXdN+X6C2rzPz6KPax53ZgwWMAb7P/TzIlykhl9dZCeTQo4dN+5LUHtjoL7WC
   xrYmKyu7snr1viThqzjj1cl/boHVjOBdiniOfVjKDezJ7rzFR2wHQF7e2TzwwA8MYpLUwRjKpE1Q
   G8amTfucVat2pv7WZJeMV1atedSdLziFqYxhCCtYyjhO5xiqWcko4FqgEzk5r3Phhd5JKUkdUU62
   C5DamrKyKYwZ8xivvtqXVat2Aa4EJgH9ah5XURfGhjOQWVzFIczjDwxjBmdxIPtzH3cQagLZZGqb
   +C+5ZJhN/JLUQblSJjVR7erY1KmLqKp6hMa2JhPDgds5hFMpYgVf5zEmMJCDOIAPu+WRk/MRPTuN
   J8ZV5OS8xY47DmTAgF428UtSB2cok5qgfvP+9jVXqzJekTzuwkq+xwcU8SxbMZ9SduHHnY5k8D79
   GW/DviRpPVK3fRlCKA4hfBBCeLXmY2S2a5JKSyexcGHm9iQkK2ILgLFszUFcxETeZWvO5Bau4Gp2
   YwkP9D2cOx86n5dfvs5AJklar9SNxAghXAp8HmO8Zj2vcSSGml1Z2RRKSycxf/7HLFy4lJ49O7Ns
   WRU9e3Zm/vyVVFXtSbJlOQV4DLiSIUxgDL/mOObwcM52XN9lINO79KdLlx4MHtzTcRaSpDY/EmOD
   hUvNpbZXbMaMLlRUnEgSuH7A4sWPASNqfg3UrpAFDmUkz1HETgzlY27PG8RLNz/AqT/4Fqdm79uQ
   JLVxaV0p+y/gU+Al4KcxxqUNXuNKmTZZ5orYvHnvU1m5PatWbUvdUNfGfp1CD27hVBYxmrkspwe/
   53ymbPcC1996nKthkqR1aupKWVZ6ykIIk0MIUxv5OAa4ARgM7EvSsPO7bNSo9ql2nMWkScN5881t
   WLZsf1at+gN1i8Zr/7oD8/gNjzCXhzmSmZzJ9hyUk8/0/Z8zkEmSmk1Wti9jjMOa8roQwi3AI409
   V1xcvOZxQUEBBQUFzVGa2rGysimceup1LF58H8kK2JXUjbWoavDrKr7CvyjiPo5kPLdzGgfyKnMZ
   DMCIYZcwceLlrVm+JKmNKC8vp7y8fKPfl8bty34xxgU1j88HDowxntTgNW5fqsnq94xtRxLEaj/q
   tifhMbpwJMdRShFv04ePKOGH3E4XlvG/a36//PyLKSkZ6QqZJKlJ2nKj/9UhhH2BCLwLnJ3letSG
   1W5Xzp7dl/qHgmeOtRjLNhRxFndyLsfydujGb3N34cUv7c/nyxexdc9OdFt2Av369a0Z8mogkyQ1
   v9SFshjjKdmuQe1HaekkZs/O3KZMQhiMAMayFycwhtf5LjvwYKftuWCXozjlf8/jfkOXJKmVpS6U
   Sc2psrL2X/HalbHDCazmaK6niKcZwu/4y7b78+M9z+GUn36b+wxjkqQsSV1PWVPYU6Z1aTgAtrKy
   mmXL/kwy0uIRTmNHRlPK5/Ti7m0H8PWbxnD0t7+e7bIlSe1YW+4pkzZKZhCbMyewYsVJJANgbwKm
   sCPn8RPy+C9u5kn6c07XnVi6505cdvkJHO3KmCQpJVwpU5tV/67KG6g/8PVyvsq/KGIcX2Myf2QI
   d27Rn36HDKGwcJiN+pKkVuNKmdq02tWvysrOfPbZB0BXtthi2zWPV66srlkVq72rEqAzXVjJ8bxJ
   Ef9BLz6nhDGcxu0spydH7FfMxInFWfueJElaH0OZUmPtbcgbyTz8u/7j2lWxYgC+xEeczZOcwx94
   k1x+yXj+zlHEjEMrcnOrW/cbkiRpIxjKlDUNV8MWLNiChQuvoS5wAUwiCWENHyf/6g5lPmM4g+/w
   V/7MVxnOKN7khyThbdSar5WffzGFhSNb4buSJGnTGMrUatYdwqB+EMv813Ltx4HVjGI6RXyd3XmD
   69mTXZnJJ3wJmEJe3nVsu21nljnwVZLUhhjK1GKaHsKg/r+KVY0+7slyTmM8YyhhCZ0Zx248wHxW
   8RxQSm7uPIYM6cVll51nAJMktTmGMrWIuuONarcb1xfCoH4Qq526fyUwnEGcRyHdOJVb+Qf9OZUJ
   PMNXgKfIy/shu+X3q1kNO9MwJklqswxlahF1xxvVWl8Ig/pB7HAg8o2uR/Kz3Pc4YPkHPLz1Hpw7
   +L+YtXIZIdzNEb0mk5tbTWGhq2KSpPbBOWVqNpnbla+//i5Ll07IeLbhSlnmnZSJvn1PZ8e+XTlm
   xSK+/+Fz9N2iCz0v/jmccgr07Nk634QkSc2sqXPKDGXaJJkBrFu3Kg45pD933TV/PduVjYew/v3z
   6NXrS2wXPuOyAUvZ7R9/h6FDoagIRo6EnBwkSWrLDGVqNhsOYJCXdzwrVtyX8a71h7Bk63EYo7bf
   EkpK4G9/g+OOgzFjYM89W+17kySppTnRX81i7YZ9eOqphgEMVqzYo8E7kz6vPn1OZO+9d6sJYacl
   /V/V1fDoo/C/l8KsWXDeecmv22zT0t+OJEmpZSjTeq3dsN9YAIO1G/cBDueggybXHW302WfJqlhp
   KWy9NZx/Pnzve9ClS3OXLUlSm2PDjtarsrKx3N5YABtOXt6P611JpugPgzlzkgA2aBA88wzcdRc8
   /zyceKKBTJKkGq6UaY2GvWOjRw+nW7d1B7DkbMpEfv5ETj55b5577hIqKjqR262KS7/Wl0Nu+T08
   9RSccQa89hrssEPrfUOSJLUhNvoLaLx3LD9/LCefPGCtpv78/Is5+eTtee65BUkAq23aH3U4VFbC
   vffCuHGwYkXSuH/KKdCjRza+LUmSss67L7VRRoz4BZMmXdHI9UsoLBzG+PGT1w5gmRYtghtugBtv
   hH33TcLYiBGOtJAkdXjefamN0njvGFRUdGLUqMPXPTX/tdeSVbGHHoLjj4cnnoAhQ1qwUkmS2ieX
   MQSwjt4xyM2tXvtidTU8+CAUFMA3vwm77w7vvJOskhnIJEnaJK6UdTCNNfOPGnU4o0cPZ/bssWv1
   jhUWjqx782efwW23JSMttt02mbr/3e96B6UkSc3AUNaBNNbMP3v2WIA125Pjx1+S0Ts2Mrk+ezaM
   Hw933AHDh8Pdd8OXv5yV70GSpPbKRv8OZH3N/BMnXl7/YoxQXp70iz3zDJx5Jpx7Lgwc2DrFSpLU
   Ttjor7Wsr5k/4xO4554kjK1cmWxR3n23Iy0kSWphhrIOZL3N/AsXJiMtbroJ9tsPfvMbGDbMkRaS
   JLUS/8btQEaPHk5+/th6147Z/nRuWfUi7LEHfPQRPPkk/P3vzhiTJKmVuVLWzqzr7kqoa+a/rnQs
   +89/h+9/+By7VKwgb/hP4YG7Yautslm6JEkdmqGsHdng3ZWffsqot19i1My7oV8/uOQ38J3vONJC
   kqQU8O7LdmRdd1eeduh5/HG/TnDXXTByZHIE0sEHZ6FCSZI6Hu++7IDq310Z+RpPUsQ4Dn/+H3DY
   GHjjDdh++6zVJ0mS1s1Q1o5061ZFNyo4ibspYhydqWIcRdx6xBAe+tWvsl2eJElaD0NZG7G+Bn4A
   Fizg2q3ep0+nrXmh+gj+m/9lMsPIzx9LSdHR2StckiQ1iT1lbUBjDfz5+WMpKRnBqL49kkGvjz4K
   J51E+dAvc9WDMzOOShpWP7xJkqRW1dSeMkNZG9Cwgb8TVXyLh/if3uezVy+gsDA5BqlPn+wVKUmS
   GmWjfztS28C/JUs5g1spZDzzGcAD/Q9mr9fvgc7+Y5Qkqa1zZHsbMLjqI0opZA47sT+v8H3u51D+
   xfMDdzeQSZLUTvg3eivbYMN+rRjhiSdg3DhunPY0t/YewtClU/mQAQDk519MYeHIVq5ekiS1FENZ
   K9rgxH2AFSvg7ruT5v0YoaiIbvffz45PvMjQ8Teyy5oG/pE28EuS1I7Y6N+K1jVxf8SIS5h42zlw
   /fVw881w4IFQVARf/zqEDfYFSpKkFGtqo789Za2o/sT9xAG8xE9ffQj23BOWLoUpU5LxFt/4hoFM
   kqQOxO3LdWhy79dG6NatCkhGWnybByliHAN5n0m9d4Hn/ulIC0mSOjBDWSOa1Pu1CS44/RAKXv46
   Jy1+h/cZyDiKmLrTS1xzzdEGMkmSOjh7yhqx3t6viZdv/G84cyaUlsLdd/PBvv/B1SsGMrXbQCfu
   S5LUATg8djM01vsFUFHRqem/SYzw+OPJXZQvvghnnw3TprF9//6Mb6Y6JUlS+5GVRv8QwnEhhDdD
   CNUhhP0bPHdRCGFWCOGtEMLwbNRX2/vVUG5u9YbfvGJFcgfl0KFwwQXwne/AvHlw+eXQv38zVypJ
   ktqLbN19ORU4FpiSeTGEMAQ4HhgCjASuDyG0eo2jRw8nP39svWvJsNZh637T/PkwdizsuCM8/DCU
   lMAbb8AZZ0BeXgtXLEmS2rqsbF/GGN+CZI+1gW8B98QYVwFzQwjvAAcBz7VmfbU9XuPHX0LFhoa1
   vvBCEsD+/nf4wQ/gX/+CXXZpzXIlSVI7kLaesv7UD2AfQM25Qq1s1KjD192AX1UFf/tb0i82fz6M
   Hg3XXQe9e7dukZIkqd1osVAWQpgM9G3kqYtjjI9sxG+VnttDlyxJ+sWuvRYGDYKf/hSOOcZDwSVJ
   0mZrsTQRY1xPA9Y6zQcGZny+fc21tRQXF695XFBQQEFBwSZ8uSZ6661kpMU998B//meySnbAAS33
   9SRJUptVXl5OeXn5Rr8vq3PKQghPAv8dY3y55vMhwN0kfWQDgMeBnRsOJWu1sy8ffxyuuQZefjkZ
   aXHOOdCvX8t/XUmS1G6kek5ZCOFYoBTYBigLIbwaYzwqxjg9hHA/MB2oAs7N6snjTz4J3/se/PWv
   kJubtTIkSVL750R/SZKkFtTUlbJszSmTJElSBkOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmS
   JKWAoUySJCkFDGWSJEkpYCiTJElKAUOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUyS
   JCkFDGWSJEkpYCiTJElKAUOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWS
   JEkpYCiTJElKAUOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiT
   JElKAUOZJElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKWAoUySJCkFDGWSJEkpYCiTJElKAUOZ
   JElSChjKJEmSUsBQJkmSlAKGMkmSpBQwlEmSJKVAVkJZCOG4EMKbIYTqEML+GdcHhRBWhBBerfm4
   Phv1SZIktbZsrZRNBY4FpjTy3Dsxxv1qPs5t5bq0DuXl5dkuocPxZ976/Jm3Pn/mrc+feXplJZTF
   GN+KMc7MxtfWpvE/4tbnz7z1+TNvff7MW58/8/RKY0/Z4Jqty/IQwqHZLkaSJKk1dG6p3ziEMBno
   28hTF8cYH1nH2z4EBsYYl9T0mj0YQtgzxvh5S9UpSZKUBiHGmL0vHsKTwE9jjK9szPMhhOwVLUmS
   tJFijGFDr2mxlbKNsKbIEMI2wJIYY3UIYSdgF2BOwzc05RuTJElqS7I1EuPYEML7wJeBshDC32ue
   OgJ4PYTwKvAAcHaMcWk2apQkSWpNWd2+lCRJUiKNd182SQjh8hDC6yGE10II/wghDMx2Te1dCOG3
   IYQZNT/3v4YQtsx2Te3dugYtq/mFEEaGEN4KIcwKIfws2/W0dyGE20IIi0IIU7NdS0cRQhgYQniy
   5s+UaSGE0dmuqb0LIeSGEJ6vySrTQwi/Xu/r2+pKWQihV+1dmSGEQmCfGOOZWS6rXQshDAP+EWNc
   HUK4CiDG+PMsl9WuhRB2B1YDN7Gem2K0eUIInYC3gW8A84EXgRNjjDOyWlg7FkI4DFgG3BFjHJrt
   ejqCEEJfoG+M8bUQQk/gZeDb/nveskII3WOMX4QQOgNPA/8dY3y6sde22ZWyBmMyegKfZKuWjiLG
   ODnGuLrm0+eB7bNZT0fgoOVWcxDJaSJzY4yrgHv/f3t3HyNXVYdx/Pu0UEBog9CYiKmpJbUIal8o
   pq3EEJsa0ehCJMFAlBfDH75AI0LUrEGNbyhRUIghJA0aEIhAfOG1EaEpukXD2oKlikQxiqHgS0Ga
   soLw+Mc9g7PLzOy27O6dmX0+yWTPnHvu3t+5aTa/nnPuPcBAzTH1Ndv3ArvqjmMmsb3T9rZS3g38
   Djii3qj6n+09pTgHmA38q13bnk3KACR9RdJfgDOAi+uOZ4Y5G7i97iAiJsnrgL82fX+s1EX0JUkL
   geVU/8GOKSRplqRtwBPAPbZ3tGvbDa/EaGu8F9DaHgQGJX0GuBQ4a1oD7EMTeemvpEHgOdvXTWtw
   fWofX7Qck6s313FE7IMydXkTsL6MmMUUKjNMy8o67I2STrC9qVXbrk7KbK+bYNPryKjNpBjvnks6
   E3gPsHZaApoB9uLfeUydvwHNDwstoBoti+grkvYHbgautf3juuOZSWw/Lek2YCWwqVWbnp2+lLS4
   6esAsLWuWGYKSe8GLgQGbI/UHc8MlJcmT537gcWSFkqaA5wK/LTmmCImlSQBG4Adti+rO56ZQNJ8
   SYeW8kHAOjrkK7389OVNwBLgBeCPwEdtP1lvVP1N0iNUCxUbixS32P5YjSH1PUknA98B5gNPA1tt
   n1hvVP1J0onAZVQLcTfY7vjoerwykq6nemH44cCTwEW2r643qv4m6XhgM/Ag/5+y/6ztO+uLqr9J
   egvwfapBsFnANbYvadu+V5OyiIiIiH7Ss9OXEREREf0kSVlEREREF0hSFhEREdEFkpRFREREdIEk
   ZRERERFdIElZRERERBdIUhYR+0TS4ZK2ls/jkh4r5V2SHprmWAYkvanp+xcl7fWuE+Xlsb9tc+wY
   SXdL+r2kP0j63CuJuUMMrfryzlLeJOnYqbhuRNQvSVlE7BPb/7S93PZy4ErgW6W8DHhxsq8naXaH
   w5YUMwAAAAPFSURBVCcDRzfF9nnbP5/Eax8E/AT4qu2jgKXAGklT8fLkVn25u/GV7NMZ0beSlEXE
   ZFHTz9mSrpK0XdJGSQcCSDpS0h2S7pe0WdKSUr+wjEI9IOkuSQtK/fckXSnpPuDrrc6XtAZ4H3CJ
   pN9IWlTO+0D5HcdJ+qWkbZJ+JemQcr3NkobLZ/U4fTsN+IXtuwBsPwt8Avh0ucYXJH3qpRtR9fv1
   pfyjEu92Sec0tdkt6cslri2SXjNeX0bdbOldkoZK/D+UdHCpv1jSQ+Vetn1zeER0nyRlETEVFgNX
   2H4z8BTQSCquAs61vZJqH9XvlvrLgattLwV+QLW1VMMRwGrbF7Q63/YQ1T6VF9heYftPlBGlso/l
   DcB5tpcBa4FngSeAdbaPBT445nqtHA0MN1eU68yVdAgvH71q/n52ifc44DxJry71r6LaqmwZ1dY3
   53TqS/MvlzQfGATWlj4MA+dLOgw4yfYx5V5+aZx+RUQX2a/uACKiLz1q+8FSHgYWlpGcNcCN1b7I
   QLWXKsAq4KRSvhb4RikbuNG2S/Kzus358PIN20W1P+7jtocBbO8GKMnaFZKWUu2f+8YJ9KndhvD7
   j3PeekmNvi2gSlh/DTxn+7ZSP0y1UfF412ocW0WVKA6VezEHGKLaH3VE0gbg1vKJiB6RpCwipsJ/
   msovAAdSjczvKuvOWmmXiOwpP2cBT3U4v9Vaq3brrz5Jlax9qKxVG2nTrmEH8I5RwUqLgD22d0n6
   L6NnHhrTtSdQjc6tsj0i6Z7GMeD5pvYvMvrv8UTWjf3M9mljKyW9rVzzFKop1r1+4CEi6pHpy4iY
   DrL9DPCopFMAVHlrOT5ENY0IcDrVdN4otv/d4fxngHljTwEeBl4raWU5Z25JwuYBO0u7DwOdHiKA
   akr1+MYTnWXh/7eBb5bjfwZWlGMrgDeU+nlUieiIpKOoRrjG06ovY/t1H/B2SUeWax4saXEZjTzU
   9h3A+VQPJEREj0hSFhGTxW3Kzd9PBz4iaRuwHXh/qT8XOEvSA6XN+ja/q935NwAXlkXvi1460X4e
   OBW4vJyzETiAai3bGaVuCbC7Q+zYHinXGpT0MPB34BHbl5YmNwOHSdoOfJwqGQS4E9hP0g7ga8CW
   NtdpXjfWsi9j4vkHcCZwfblnQ6Ufc4FbSt29VCOCEdEjZOfp6oiIvSFpALgIeK/tneO1j4iYiCRl
   EREREV0g05cRERERXSBJWUREREQXSFIWERER0QWSlEVERER0gSRlEREREV0gSVlEREREF0hSFhER
   EdEF/gdnB2p+pQ+LLgAAAABJRU5ErkJggg==
   "
   >
   </div>
   
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <h2 id="glm-gamma-for-proportional-count-response">GLM: Gamma for proportional count response</h2>
   <h3 id="load-data">Load data</h3>
   <p> In the example above, we printed the <code>NOTE</code> attribute to learn about the
    Star98 dataset. Statsmodels datasets ships with other useful information. For
    example: </p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[16]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="k">print</span><span class="p">(</span><span class="n">sm</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">scotland</span><span class="o">.</span><span class="n">DESCRLONG</span><span class="p">)</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   <div class="output_subarea output_stream output_stdout output_text">
   <pre>
   
   This data is based on the example in Gill and describes the proportion of
   voters who voted Yes to grant the Scottish Parliament taxation powers.
   The data are divided into 32 council districts.  This example&apos;s explanatory
   variables include the amount of council tax collected in pounds sterling as
   of April 1997 per two adults before adjustments, the female percentage of
   total claims for unemployment benefits as of January, 1998, the standardized
   mortality rate (UK is 100), the percentage of labor force participation,
   regional GDP, the percentage of children aged 5 to 15, and an interaction term
   between female unemployment and the council tax.
   
   The original source files and variable information are included in
   /scotland/src/
   
   
   </pre>
   </div>
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p> Load the data and add a constant to the exogenous variables:</p>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[17]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">data2</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">scotland</span><span class="o">.</span><span class="n">load</span><span class="p">()</span>
   <span class="n">data2</span><span class="o">.</span><span class="n">exog</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">add_constant</span><span class="p">(</span><span class="n">data2</span><span class="o">.</span><span class="n">exog</span><span class="p">,</span> <span class="n">prepend</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span>
   <span class="k">print</span><span class="p">(</span><span class="n">data2</span><span class="o">.</span><span class="n">exog</span><span class="p">[:</span><span class="mi">5</span><span class="p">,:])</span>
   <span class="k">print</span><span class="p">(</span><span class="n">data2</span><span class="o">.</span><span class="n">endog</span><span class="p">[:</span><span class="mi">5</span><span class="p">])</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   <div class="output_subarea output_stream output_stdout output_text">
   <pre>
   [[  7.12000000e+02   2.10000000e+01   1.05000000e+02   8.24000000e+01
       1.35660000e+04   1.23000000e+01   1.49520000e+04   1.00000000e+00]
    [  6.43000000e+02   2.65000000e+01   9.70000000e+01   8.02000000e+01
       1.35660000e+04   1.53000000e+01   1.70395000e+04   1.00000000e+00]
    [  6.79000000e+02   2.83000000e+01   1.13000000e+02   8.63000000e+01
       9.61100000e+03   1.39000000e+01   1.92157000e+04   1.00000000e+00]
    [  8.01000000e+02   2.71000000e+01   1.09000000e+02   8.04000000e+01
       9.48300000e+03   1.36000000e+01   2.17071000e+04   1.00000000e+00]
    [  7.53000000e+02   2.20000000e+01   1.15000000e+02   6.47000000e+01
       9.26500000e+03   1.46000000e+01   1.65660000e+04   1.00000000e+00]]
   [ 60.3  52.3  53.4  57.   68.7]
   
   </pre>
   </div>
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <h3 id="fit-and-summary">Fit and summary</h3>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[18]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">glm_gamma</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">GLM</span><span class="p">(</span><span class="n">data2</span><span class="o">.</span><span class="n">endog</span><span class="p">,</span> <span class="n">data2</span><span class="o">.</span><span class="n">exog</span><span class="p">,</span> <span class="n">family</span><span class="o">=</span><span class="n">sm</span><span class="o">.</span><span class="n">families</span><span class="o">.</span><span class="n">Gamma</span><span class="p">())</span>
   <span class="n">glm_results</span> <span class="o">=</span> <span class="n">glm_gamma</span><span class="o">.</span><span class="n">fit</span><span class="p">()</span>
   <span class="k">print</span><span class="p">(</span><span class="n">glm_results</span><span class="o">.</span><span class="n">summary</span><span class="p">())</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   <div class="output_subarea output_stream output_stdout output_text">
   <pre>
                    Generalized Linear Model Regression Results                  
   ==============================================================================
   Dep. Variable:                      y   No. Observations:                   32
   Model:                            GLM   Df Residuals:                       24
   Model Family:                   Gamma   Df Model:                            7
   Link Function:          inverse_power   Scale:                 0.0035842831735
   Method:                          IRLS   Log-Likelihood:                -83.017
   Date:                Thu, 21 May 2015   Deviance:                     0.087389
   Time:                        05:58:08   Pearson chi2:                   0.0860
   No. Iterations:                     6                                         
   ==============================================================================
                    coef    std err          z      P&gt;|z|      [95.0% Conf. Int.]
   ------------------------------------------------------------------------------
   x1          4.962e-05   1.62e-05      3.060      0.002      1.78e-05  8.14e-05
   x2             0.0020      0.001      3.824      0.000         0.001     0.003
   x3         -7.181e-05   2.71e-05     -2.648      0.008        -0.000 -1.87e-05
   x4             0.0001   4.06e-05      2.757      0.006      3.23e-05     0.000
   x5         -1.468e-07   1.24e-07     -1.187      0.235     -3.89e-07  9.56e-08
   x6            -0.0005      0.000     -2.159      0.031        -0.001 -4.78e-05
   x7         -2.427e-06   7.46e-07     -3.253      0.001     -3.89e-06 -9.65e-07
   const         -0.0178      0.011     -1.548      0.122        -0.040     0.005
   ==============================================================================
   
   </pre>
   </div>
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <h2 id="glm-gaussian-distribution-with-a-noncanonical-link">GLM: Gaussian distribution with a noncanonical link</h2>
   <h3 id="artificial-data">Artificial data</h3>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[19]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">nobs2</span> <span class="o">=</span> <span class="mi">100</span>
   <span class="n">x</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="n">nobs2</span><span class="p">)</span>
   <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="mi">54321</span><span class="p">)</span>
   <span class="n">X</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">column_stack</span><span class="p">((</span><span class="n">x</span><span class="p">,</span><span class="n">x</span><span class="o">**</span><span class="mi">2</span><span class="p">))</span>
   <span class="n">X</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">add_constant</span><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">prepend</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span>
   <span class="n">lny</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="o">-</span><span class="p">(</span><span class="o">.</span><span class="mo">03</span><span class="o">*</span><span class="n">x</span> <span class="o">+</span> <span class="o">.</span><span class="mo">0001</span><span class="o">*</span><span class="n">x</span><span class="o">**</span><span class="mi">2</span> <span class="o">-</span> <span class="mf">1.0</span><span class="p">))</span> <span class="o">+</span> <span class="o">.</span><span class="mo">001</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">nobs2</span><span class="p">)</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <h3 id="fit-and-summary">Fit and summary</h3>
   </div>
   </div>
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[20]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">gauss_log</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">GLM</span><span class="p">(</span><span class="n">lny</span><span class="p">,</span> <span class="n">X</span><span class="p">,</span> <span class="n">family</span><span class="o">=</span><span class="n">sm</span><span class="o">.</span><span class="n">families</span><span class="o">.</span><span class="n">Gaussian</span><span class="p">(</span><span class="n">sm</span><span class="o">.</span><span class="n">families</span><span class="o">.</span><span class="n">links</span><span class="o">.</span><span class="n">log</span><span class="p">))</span>
   <span class="n">gauss_log_results</span> <span class="o">=</span> <span class="n">gauss_log</span><span class="o">.</span><span class="n">fit</span><span class="p">()</span>
   <span class="k">print</span><span class="p">(</span><span class="n">gauss_log_results</span><span class="o">.</span><span class="n">summary</span><span class="p">())</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   <div class="output_subarea output_stream output_stdout output_text">
   <pre>
                    Generalized Linear Model Regression Results                  
   ==============================================================================
   Dep. Variable:                      y   No. Observations:                  100
   Model:                            GLM   Df Residuals:                       97
   Model Family:                Gaussian   Df Model:                            2
   Link Function:                    log   Scale:               1.05311425588e-07
   Method:                          IRLS   Log-Likelihood:                 662.92
   Date:                Thu, 21 May 2015   Deviance:                   1.0215e-05
   Time:                        05:58:09   Pearson chi2:                 1.02e-05
   No. Iterations:                     7                                         
   ==============================================================================
                    coef    std err          z      P&gt;|z|      [95.0% Conf. Int.]
   ------------------------------------------------------------------------------
   x1            -0.0300    5.6e-06  -5361.316      0.000        -0.030    -0.030
   x2         -9.939e-05   1.05e-07   -951.091      0.000     -9.96e-05 -9.92e-05
   const          1.0003   5.39e-05   1.86e+04      0.000         1.000     1.000
   ==============================================================================
   
   </pre>
   </div>
   </div>
   
   </div>
   </div>
   
   </div>

   <script src="https://c328740.ssl.cf1.rackcdn.com/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"type="text/javascript"></script>
   <script type="text/javascript">
   init_mathjax = function() {
       if (window.MathJax) {
           // MathJax loaded
           MathJax.Hub.Config({
               tex2jax: {
               // I'm not sure about the \( and \[ below. It messes with the
               // prompt, and I think it's an issue with the template. -SS
                   inlineMath: [ ['$','$'], ["\\(","\\)"] ],
                   displayMath: [ ['$$','$$'], ["\\[","\\]"] ]
               },
               displayAlign: 'left', // Change this to 'center' to center equations.
               "HTML-CSS": {
                   styles: {'.MathJax_Display': {"margin": 0}}
               }
           });
           MathJax.Hub.Queue(["Typeset",MathJax.Hub]);
       }
   }
   init_mathjax();

   // since we have to load this in a ..raw:: directive we will add the css
   // after the fact
   function loadcssfile(filename){
       var fileref=document.createElement("link")
       fileref.setAttribute("rel", "stylesheet")
       fileref.setAttribute("type", "text/css")
       fileref.setAttribute("href", filename)

       document.getElementsByTagName("head")[0].appendChild(fileref)
   }
   // loadcssfile({{pathto("_static/nbviewer.pygments.css", 1) }})
   // loadcssfile({{pathto("_static/nbviewer.min.css", 1) }})
   loadcssfile("../../../_static/nbviewer.pygments.css")
   loadcssfile("../../../_static/ipython.min.css")
   </script>