Robust Linear Models
====================


.. _robust_models_0_notebook:

`Link to Notebook GitHub <https://github.com/statsmodels/statsmodels/blob/master/examples/notebooks/robust_models_0.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">import</span> <span class="nn">matplotlib.pyplot</span> <span class="kn">as</span> <span class="nn">plt</span>
   <span class="kn">from</span> <span class="nn">statsmodels.sandbox.regression.predstd</span> <span class="kn">import</span> <span class="n">wls_prediction_std</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>
   Populating the interactive namespace from numpy and matplotlib
   
   </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="estimation">Estimation</h2>
   <p>Load data:</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="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">stackloss</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>
   </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>Huber&#39;s T norm with the (default) median absolute deviation scaling</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">huber_t</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">RLM</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">M</span><span class="o">=</span><span class="n">sm</span><span class="o">.</span><span class="n">robust</span><span class="o">.</span><span class="n">norms</span><span class="o">.</span><span class="n">HuberT</span><span class="p">())</span>
   <span class="n">hub_results</span> <span class="o">=</span> <span class="n">huber_t</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">hub_results</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="n">hub_results</span><span class="o">.</span><span class="n">bse</span><span class="p">)</span>
   <span class="k">print</span><span class="p">(</span><span class="n">hub_results</span><span class="o">.</span><span class="n">summary</span><span class="p">(</span><span class="n">yname</span><span class="o">=</span><span class="s1">&#39;y&#39;</span><span class="p">,</span>
               <span class="n">xname</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;var_</span><span class="si">%d</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">hub_results</span><span class="o">.</span><span class="n">params</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>
   [-41.02649835   0.82938433   0.92606597  -0.12784672]
   [ 9.79189854  0.11100521  0.30293016  0.12864961]
                       Robust linear Model Regression Results                    
   ==============================================================================
   Dep. Variable:                      y   No. Observations:                   21
   Model:                            RLM   Df Residuals:                       17
   Method:                          IRLS   Df Model:                            3
   Norm:                          HuberT                                         
   Scale Est.:                       mad                                         
   Cov Type:                          H1                                         
   Date:                Wed, 27 Apr 2016                                         
   Time:                        01:50:56                                         
   No. Iterations:                    19                                         
   ==============================================================================
                    coef    std err          z      P&gt;|z|      [95.0% Conf. Int.]
   ------------------------------------------------------------------------------
   var_0        -41.0265      9.792     -4.190      0.000       -60.218   -21.835
   var_1          0.8294      0.111      7.472      0.000         0.612     1.047
   var_2          0.9261      0.303      3.057      0.002         0.332     1.520
   var_3         -0.1278      0.129     -0.994      0.320        -0.380     0.124
   ==============================================================================
   
   If the model instance has been used for another fit with different fit
   parameters, then the fit options might not be the correct ones anymore .
   
   </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>Huber&#39;s T norm with &#39;H2&#39; covariance matrix</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="n">hub_results2</span> <span class="o">=</span> <span class="n">huber_t</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">cov</span><span class="o">=</span><span class="s2">&quot;H2&quot;</span><span class="p">)</span>
   <span class="k">print</span><span class="p">(</span><span class="n">hub_results2</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="n">hub_results2</span><span class="o">.</span><span class="n">bse</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>
   [-41.02649835   0.82938433   0.92606597  -0.12784672]
   [ 9.08950419  0.11945975  0.32235497  0.11796313]
   
   </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>Andrew&#39;s Wave norm with Huber&#39;s Proposal 2 scaling and &#39;H3&#39; covariance matrix</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="n">andrew_mod</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">RLM</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">M</span><span class="o">=</span><span class="n">sm</span><span class="o">.</span><span class="n">robust</span><span class="o">.</span><span class="n">norms</span><span class="o">.</span><span class="n">AndrewWave</span><span class="p">())</span>
   <span class="n">andrew_results</span> <span class="o">=</span> <span class="n">andrew_mod</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">scale_est</span><span class="o">=</span><span class="n">sm</span><span class="o">.</span><span class="n">robust</span><span class="o">.</span><span class="n">scale</span><span class="o">.</span><span class="n">HuberScale</span><span class="p">(),</span> <span class="n">cov</span><span class="o">=</span><span class="s2">&quot;H3&quot;</span><span class="p">)</span>
   <span class="k">print</span><span class="p">(</span><span class="s1">&#39;Parameters: &#39;</span><span class="p">,</span> <span class="n">andrew_results</span><span class="o">.</span><span class="n">params</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>
   Parameters:  [-40.8817957    0.79276138   1.04857556  -0.13360865]
   
   </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>See <code>help(sm.RLM.fit)</code> for more options and <code>module sm.robust.scale</code> for scale options</p>
   <h2 id="comparing-ols-and-rlm">Comparing OLS and RLM</h2>
   <p>Artificial data with outliers:</p>
   </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">nsample</span> <span class="o">=</span> <span class="mi">50</span>
   <span class="n">x1</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">linspace</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="n">nsample</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">x1</span><span class="p">,</span> <span class="p">(</span><span class="n">x1</span><span class="o">-</span><span class="mi">5</span><span class="p">)</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">sig</span> <span class="o">=</span> <span class="mf">0.3</span>   <span class="c1"># smaller error variance makes OLS&lt;-&gt;RLM contrast bigger</span>
   <span class="n">beta</span> <span class="o">=</span> <span class="p">[</span><span class="mi">5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.0</span><span class="p">]</span>
   <span class="n">y_true2</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">beta</span><span class="p">)</span>
   <span class="n">y2</span> <span class="o">=</span> <span class="n">y_true2</span> <span class="o">+</span> <span class="n">sig</span><span class="o">*</span><span class="mf">1.</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">normal</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">nsample</span><span class="p">)</span>
   <span class="n">y2</span><span class="p">[[</span><span class="mi">39</span><span class="p">,</span><span class="mi">41</span><span class="p">,</span><span class="mi">43</span><span class="p">,</span><span class="mi">45</span><span class="p">,</span><span class="mi">48</span><span class="p">]]</span> <span class="o">-=</span> <span class="mi">5</span>   <span class="c1"># add some outliers (10% of nsample)</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="example-1-quadratic-function-with-linear-truth">Example 1: quadratic function with linear truth</h3>
   <p>Note that the quadratic term in OLS regression will capture outlier effects. </p>
   </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="n">res</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">y2</span><span class="p">,</span> <span class="n">X</span><span class="p">)</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">params</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">bse</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">predict</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>
   [ 5.16960323  0.50126716 -0.01185602]
   [ 0.45071512  0.06958433  0.00615714]
   [  4.87320265   5.12421824   5.37128347   5.61439833   5.85356284
      6.08877698   6.32004076   6.54735418   6.77071724   6.99012993
      7.20559227   7.41710424   7.62466585   7.8282771    8.02793798
      8.22364851   8.41540867   8.60321848   8.78707792   8.966987
      9.14294571   9.31495407   9.48301206   9.64711969   9.80727696
      9.96348387  10.11574042  10.26404661  10.40840243  10.54880789
     10.68526299  10.81776773  10.94632211  11.07092612  11.19157978
     11.30828307  11.421036    11.52983857  11.63469077  11.73559262
     11.8325441   11.92554522  12.01459598  12.09969638  12.18084642
     12.25804609  12.33129541  12.40059436  12.46594295  12.52734118]
   
   </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>Estimate RLM:</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">resrlm</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">RLM</span><span class="p">(</span><span class="n">y2</span><span class="p">,</span> <span class="n">X</span><span class="p">)</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">resrlm</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="n">resrlm</span><span class="o">.</span><span class="n">bse</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>
   [  5.08999767e+00   4.89213552e-01  -1.52913844e-03]
   [ 0.12482285  0.01927096  0.00170518]
   
   </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>Draw a plot to compare OLS estimates to the robust estimates:</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="n">fig</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">figure</span><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">12</span><span class="p">,</span><span class="mi">8</span><span class="p">))</span>
   <span class="n">ax</span> <span class="o">=</span> <span class="n">fig</span><span class="o">.</span><span class="n">add_subplot</span><span class="p">(</span><span class="mi">111</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">y2</span><span class="p">,</span> <span class="s1">&#39;o&#39;</span><span class="p">,</span><span class="n">label</span><span class="o">=</span><span class="s2">&quot;data&quot;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">y_true2</span><span class="p">,</span> <span class="s1">&#39;b-&#39;</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">&quot;True&quot;</span><span class="p">)</span>
   <span class="n">prstd</span><span class="p">,</span> <span class="n">iv_l</span><span class="p">,</span> <span class="n">iv_u</span> <span class="o">=</span> <span class="n">wls_prediction_std</span><span class="p">(</span><span class="n">res</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">res</span><span class="o">.</span><span class="n">fittedvalues</span><span class="p">,</span> <span class="s1">&#39;r-&#39;</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">&quot;OLS&quot;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">iv_u</span><span class="p">,</span> <span class="s1">&#39;r--&#39;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">iv_l</span><span class="p">,</span> <span class="s1">&#39;r--&#39;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">resrlm</span><span class="o">.</span><span class="n">fittedvalues</span><span class="p">,</span> <span class="s1">&#39;g.-&#39;</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">&quot;RLM&quot;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">legend</span><span class="p">(</span><span class="n">loc</span><span class="o">=</span><span class="s2">&quot;best&quot;</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[9]:</div>
   
   
   <div class="output_text output_subarea output_pyout">
   <pre>
   &lt;matplotlib.legend.Legend at 0x7f89bd6b7a50&gt;
   </pre>
   </div>
   
   </div>
   
   <div class="output_area"><div class="prompt"></div>
   
   
   <div class="output_png output_subarea ">
   <img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAsMAAAHfCAYAAAC1cNU/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzs3Xd4lGXa9/HvJPRIQEqAhI70DoJUKUoRBSmi0kOx4eqD
   rrvqsxsB2V3UV31cWLAREjqCLiIIKCpIqFISWqghBAgt9EkCqff7x8WkkASSkGRSfp/juI/AzNxz
   XxkjOeeas9gsy0JEREREpChycfYCREREREScRcGwiIiIiBRZCoZFREREpMhSMCwiIiIiRZaCYRER
   EREpshQMi4iIiEiRdc9g2Gaz+dpstgs2m23fHbe/ZrPZDttstv02m+2D3FuiiIiIiEjuKJaJx/gB
   M4H5jhtsNlt3oD/QzLKseJvNVil3liciIiIiknvuuTNsWdZm4OodN78CfGBZVvztx1zKhbWJiIiI
   iOSq7OYMNwAetdls22022wabzfZwTi5KRERERCQvZCZNIqPzyluW1cFms7UDlgF103ugzWbTvGcR
   ERERyROWZdmy8vjsBsOngf/evuBOm82WaLPZKlqWdTmDRWXzMiK5Z8qUKUyZMsXZyxBJl34+Jb/S
   z6bkZzZbluJgIPNpErbbh8P3wGO3L9oAKJ5RICwiIiIikl/dc2fYZrMtBroDFW022ylgMjAX8LPZ
   bPuBGGB0bi5SRERERCQ33DMYtixreAZ3jcrhtYjkqe7duzt7CSIZ0s+n5Ff62ZTCxpbb+bw2m81S
   zrCIiIiI5DabzZZnBXT3rXbt2oSFhTnr8vlarVq1OHnypLOXISIiIlLoOW1n+HbknqvXLqj02oiI
   iIhkXXZ2hrM7dENEREREpMBTMCwiIiIiRZaCYREREREpshQMi4iIiEiRpWA4k8aOHct7773n7GWI
   iIiISA5SMJzDevTowdy5c529DBERERHJBKf1Gc5IaGgYPj7+hIcn4uXlwrRp3tSpUyvPn0NERERE
   Cr98tTMcGhpGr14zWbToLTZunMqiRW/Rq9dMQkMzP5wjJ54DIDAwkLZt21KuXDmef/55bt26BcC1
   a9fo378/Hh4eVKxYkf79+3P27FkA/v73vxMQEMCf/vQn3N3def311wGYNGkSNWvWpFy5crRr147N
   mzdnaS0iIiIicptlwZkzsGoV3Lhx30+Xr4JhHx9/QkKmAm63b3EjJGQqPj7+efoccXFxDBo0iDFj
   xnDlyhWGDh3Kd999B4BlWYwbN47Tp09z6tQpypQpw6uvvgrAP/7xD7p27cp//vMfbty4wYwZMwBo
   3749+/bt4+rVqwwfPpyhQ4cSGxub6fWIiIiIFGlr1sBf/wq9eoGHB7RtC7NmQUTEfT91vgqGw8MT
   SQ5iHdw4ezYxT59j+/btxMfH8/rrr+Pq6sqQIUNo164dAA8++CCDBg2iZMmSuLm58e6777Jp06a7
   Pt/w4cMpX748Li4uvPHGG8TExHDkyJFMr0dERESk0IuOhsjI9O87ehTKlYM33oB9++D8eVi3DurV
   u+/L5qucYS8vFyCK1MFsFJ6emY/Zc+I5zp49i5eXV6rbatUyOcc3b95k0qRJ/PTTT1y7dg3LsoiM
   jMSyLGy29Kf/ffLJJ/j6+nLu3DkA7HY7ly5dyvR6RERERAqVq1dh924ICoLAQHOEhsKcOTBiRNrH
   T5qUa0vJVzvD06Z5U6/eZEwwCxBFvXqTmTbNO0+fo1q1aoSHh6e67dSpU4AJbI8dO8bOnTu5du1a
   0q6wZVkAaQLizZs389FHH/Htt99y9epVrl69iru7e9LjRURERIocPz+YNs3k/vbqBYsXw/Xr6QfC
   uSxf7QzXqVOL9etfw8fnY86eTcTT04Vp017LUieInHiOjh07UqxYMWbOnMnEiRNZuXIlf/zxBz17
   9sRut1O6dGnc3d25cuUKU6ZMSXVulSpVOHHiRNLf7XY7xYsXp2LFisTGxvLBBx9gt9szvRYRERGR
   AiEuDg4dSt7pDQqC9u3ho4/SPvbNN82RQxydxLLDlts7lDabzUrvGjabLV/vju7Zs4cJEyYQEhJC
   v379AKhfvz4TJ05k2LBh7Nq1Cy8vL/785z/z8ssvExcXh4uLC9u3b2fMmDFcunSJUaNG8X//93+8
   8MILLF++nAceeIA33niD2bNnM2fOHHr27JnutfP7ayMiIiKSyi+/wIABULs2tGpljtatzVGpUq5e
   2tFJzDRQeADLstLPW82AguF8SK+NiIiI5BvnziXn9t66Be+/n/Yxt25BQgK43dnEIPeNHGla6Zp6
   MVuWg+F8lSYhIiIiIvnA5csmfzcoyKQ/OHZ5O3RI//GlSuXt+lJIv5NY5ikYFhERESlqYmLg4EHY
   vx9Gj4Y7O2KVLw8TJ5oAuHr1tPfnI+l3Ess8pUnkQ3ptREREJMd98QXs2GHSHY4eNT16W7WCL7+E
   MmWcvbpsU85wIaTXRkRERLLlwgVwd4fSpdPe989/QuXKZre3WbP0H1NAObpJLFo0RcFwYaDXRkRE
   RO7p1CnYuTO5lZmjwG3dOtPSrAixLJPx0bKlCuhEREREioZ//xuOHTM7vS+8YL7WrJmv83tzWlSU
   mdcxe3bGk5zvRTvD+ZBeGxERkSIqJgYOHIA9e8wRGAijRsGrrzp7ZfnK0aPw+eewYAF07mxq/Xr1
   AldX7QyLiIiIFExffw2vvw7165td3jZtYNgw82chPh5+/BFmzTId38aPh127zJyP+6Gd4XxIr42I
   iEghc/262eXds8cUuE2YkPYxN25A8eKFqrAtJ1y8CHPmmKYXnp5mk/yZZ9JvbXw7hsrSzrBLTi20
   sChbtizu7u64u7vj6upKmTJlkm5bsmSJs5cnIiIiBcXx4/Dcc/DQQ+DlBX/7G4SGQpUq6T8+oy4Q
   RZBlwdatZu5HgwYQEgIrVsC2bTByZM7O+NDO8F3UrVsXX19fevTokeFjEhIScHV1zdHrFoTXRkRE
   RDDbliEh0LFj2vsiIuCnn6BtWxPR5XC8UBhFRcGSJSYVwm43ucDe3lChQubO185wDrMsK01Q6uPj
   w/PPP8/w4cMpV64cixYtYtSoUbyfYk73r7/+Sp06dZL+Hh4ezuDBg/Hw8KBevXrMnj07z74HERER
   ySHx8bBmDUybBgMHQo0a0LAh/Otf6T++cmWzjdm4sQLhezh6FN54wzTD+OEHmD7d3Pbmm5kPhLNL
   wXA2fP/994wcOZLr16/z7LPPpvsY2+22JomJiTz11FM88sgjnDt3jvXr1/Pxxx+zYcOGvFyyiIiI
   3C8Xl+QeXsOHw8aNcOUKrFrl7JUVSPHxsHIl9O4NXbqY1Ifdu00w3LevebnzQr7tJpFTLfJyI9ug
   S5cu9OvXD4BS90ha2bZtG3a7nbfffhswqRfjxo1j6dKld02/EBERkTxy6ZKJwnbtSj5+/x3q1k39
   OBcXWL3aOWssRO4siJs40QTAOZkHnBX5NhjOzymzNWrUyPRjT506RVhYGBVu7/FblkViYqICYRER
   kfzg6afNDm/btvDww6aV2aef3n+/LknFskzx2+zZpj3akCGmIK5NG2evLB8Hw/mZ7Y5tazc3N6Kj
   o5P+fu7cuaQ/16hRgwYNGnDw4ME8W5+IiIhgKrB27zZHjx7pR16+viYpNa8+ky8iQkPD8PHx59Qp
   V2JjW2C39yU2tgSvvAIzZ8KDDzp7hckUDOeAVq1aMWvWLN555x1u3rzJzJkzk+7r2LEjJUqU4NNP
   P+XVV1+lWLFiHDp0iNjYWNrkh7dDIiIihckvv5ixZDt3QlgYtGgB7dplHOxWqpS36ysCQkPD6NZt
   CadP/y9QHIinWrW5BAT0oV69Wrl2XXuMPVvn6W3QXdy5A5wRb29vGjVqRK1atejXrx/Dhg1Lus/V
   1ZU1a9bwxx9/ULt2bTw8PHj55Zex27P3H0xERKTIS0gwhWvpcXEx83kXLYJr18xn8zNmQKtWebvG
   IighwRTEdeoUz+nTb2MCYYBinDs3gsmT/XPt2vYYOx18O2TrXPUZzof02oiIiNxmWWZQxY4dZrd3
   504zi3fcOPj3v529OsEUxPn6whdfmIK4a9e+4/DhIWke16PHZH77bWqOXjsyNpLvgr9jxo4Z7Dm/
   B6agPsMiIiJSiGzYAI8+CsuXg4cHTJkCp08rEHYyR0HcyJGm1XLKCXFt2x4Aou44IwpPz5wJOxOt
   RH498SujV4ym+qfV+fbQt0zqMInmHs2z9XzaGc6H9NqIiEiRcPOm2eX94w84exY+/DDtYywr5/qt
   yn2LjobFi01XCLsdXnkFxo5NXRAXGhpGr14zCQmZCrgBUdSrN5n161+jTp3s5wwfuXSEeXvnsXDf
   QiqWqciYlmMY3nw4Hm4egEmVcC/lnuWdYQXD+ZBeGxERKbRiY2HSJBMABweb6Wzt25txxqNHO3t1
   koFjx+Dzz2H+fOjUCV59FXr1yrgu0dFN4uzZRDw9XZg2zTvTgbA9xs6Biwdo5tGMuMQ4lh5Yyvy9
   8wm7HsaI5iMY3XI0Laq0SPfc7IxjVjCcD+m1ERGRAu/KFShXLv0xxF98AS1bmqK20qXzfm2SKQkJ
   pifwrFkQGAjjx8NLL+VuC2Z7jJ0uc7twMOIgD5R4gEQrkSfqP8GYlmPoXa83xVzu3ghNwXAhoddG
   REQKlPh42L8ftm9PPs6dgz174KGHnL06yaI7C+JefRWeeSZ3J8RZlkXQ+SA+2PwBy4KXAeBqc2Xt
   iLX0qtcr08+TnWBYfYZFRETk/jz9NJw8CR06QJcu8NZb0KRJ+rvCki9ZlnkPM2tW3k6IOx95nkX7
   FjFv7zyux1znuSbP0ahiI0KuhtCkchM6VM9eu7Ss0M5wPqTXRkRE8o24ONi3z9EmwOT23ik+Hopp
   f60gioqCJUtMEBwZmX5BXE67FX+LH478wLy989hyagsDGw1kTMsxdKvdDRebC/YYOwcjDtK0clPK
   liybpedWmkQhoddGREScau9eWLoUtm41o4xr1zZB8PjxZvdXCryjR5ML4jp3vndB3P2yLIvtZ7Yz
   b+88lgcvp3XV1oxpOYbBjQfjVsItx66jNAkRERG5f5cuQcmS8L//C488AuXLO3tFkgMSEmD1arML
   vHevmVvieK+TG+wxdn458QuB5wL5JvgbAMa0HEPgS4HULFczdy6aDdoZvgt/f38+/fRTQkJCKFeu
   HAMHDmT69OmUK1eOqVOncvz4cRYsWJDmvM2bN/P2229z8OBBihUrRuPGjfnss89o27Ztpq5bEF4b
   EREpgCIjTUuzLVvMUb682QGWQu3iRZgzB778MrkgbuhQ834nMxxt0sLDE/HyunebtKjYKBbuW8if
   f/4zUXFRVCxdkW+e+YaedXpiy+We0bmyM2yz2XyBp4ALlmW1uOO+t4CPgEqWZWUwJLxg+uSTT/j4
   44+ZP38+PXv2JDw8nFdeeYXevXuzZcsWgHT/g9rtdvr378+XX37J0KFDiY2NJSAggJKZ/YkTERHJ
   aadOwaBBcPiwaWfWubNJDu3Uydkrk1zimBA3e/b9FcSlN0Bj+/a0AzQSrUQ2hW1i3t55fH/4e5pU
   asKt+FsA3Ii5gVsJt1wPhLPrnjvDNputCxAJzE8ZDNtsturAHKAh0DajYLgg7gzb7XY8PT3x9/dn
   yJDk2dpRUVHUq1ePDz74gLCwMEJCQpg/f36qc3fv3k2vXr24ciX77w3y82sjIiL5VEKCCXabNk17
   X2ws7NxpCuBysz+WON2dBXETJ4K3d/YL4kaOnMqiRW9hAuGkqzBixMcsXDiZkCshzN87n/n75lO2
   RFnGtBzDiBYjcCvuRle/rgRHBNOkchMCxgZkuRguO3JlZ9iyrM02my29vfD/A/4C/JCVCxYEW7du
   JSYmhkGDBqW63c3Njb59+7J+/XoaNGiQ7rkNGjTA1dUVb29vnn/+eTp06EB55VqJiEhOu3XLBLgB
   AbB5syl2q1LFJIE+8EDqx5YoYXaDpdByFMQtWGD+U3/wQc4UxIWHJ5I6EAZKJrArcTdd/bpy5NIR
   hjUbxn+f/S+tqrZKtfsbMDYg210h8lK2XiKbzdYfOG1Z1v4cXk/Ki+TMkQ2XLl2iUqVKuKTzE1St
   WjUuXbqU4blly5Zl8+bNuLi48OKLL+Lh4cHTTz9NREREttYiIiKSri5d4M03TbHbhAkmGjpyJG0g
   LIVWQgKsXAm9e0PXrmbTf9cuc1ufPjnTGcLLywWIgpLX4JHP4Jln4Y2aRHsd462Ob3HmzTP8+4l/
   07pa6zRpEGVLlqVD9Q75OhCGbHSTsNlspYG/ASnHgdw16pwyZUrSn7t370737t3vfSEnpglUqlSJ
   S5cukZiYmCYgPnfuHJUqVbrr+Q0bNmTu3LkAHD16lBEjRjBp0iQWLVqUa2sWEZFC5swZs+Pbti3U
   r5/2/u3b1du3iEpvQlxWCuKywvutLqyO68b1hnvBJR5uVKPmmmfY+L3PXYvo8srGjRvZuHHjfT1H
   prpJ3E6TWGVZVgubzdYM+AWIxgTB1YFwoL1lWRfTObfA5QzfuHEDLy8v/Pz8eOaZZ5Juj4qKom7d
   ukyfPp3Tp0+nmzOcnlmzZvHVV1+xd+/eTF0/P782IiKSS86cgV9+gd9/h02b4Pp1s9337rvQvr2z
   VydOlt6EuIkTc2dC3NWbV/nm4Df4B/kTdj2M9pUeYVXoKixbIi6JLix/8lsGtx907ydyguzkDGd2
   A912+8CyrAOWZVW1LKuuZVl1gDNA6/QC4YLK3d2d9957j9dee42ffvqJ+Ph4Tp48ybPPPkvNmjUZ
   NWoUAAkJCcTExCQdsbGxHDlyhE8//ZTw8HAATp8+zZIlS+iY3sQeERERh7VrYd06E/j+8IPZ/lux
   QoFwERcVZdqitWkDo0ebrydOJN+WU+IT41lzbA3Pffsctf9dm99Cf+O9bu9x+o3TLHx+AS2qNqe4
   S3GaV2tOr5aP59yF84HMdJNYDHQHKgIXgMmWZfmluP8E8HBh6ibh4Ofnx6effsqJEydwd3dn0KBB
   qfoMv//++0mPtSyL6tWrs2PHDiZNmsSWLVu4fv065cuXp3///nz00Uc8kMk8roLw2oiISBYkJsL+
   /WbHt3hxePllZ69I8rm8mhB34OIB5gXNY9H+RdQsV5MxLcfwXLPnqFC6QqrH3c+I5LykccyFhF4b
   EZFC4OpV8PeHjRtNx4fKleHRR2HAAOjf39mrk3wo5YS4oCAz/fqll3J2Qpw9xs6WU1s4EHGApQeW
   cj7yPKNajGJMqzE0qtQo5y7kJBrHLCIikl/Ex5vtveHDTaVTtWrOXpHkU+lNiPvhh5xtCR2XEMd/
   D/2XF1e/yI2YG5QvVR6/p/3o36A/ri6uOXehAkjBsIiISFYlJsKBA8m7vgsXpi3lr1zZfM4tko6U
   E+JWr87ahLisjEfed2Ef/kH+LNq/iCpuVYiMjQTMyOSqD1Qt8oEwKBgWERHJPD8/E7n8/rsZ6dW9
   uxlzrNQ2yaSoKFi82ATBkZFmKvaMGVChwr3PhcyNR46IimDx/sXM2zuPS9GXGN1yNJvHbqbqA1VT
   TYVrWjmdaYVFkHKG8yG9NiIi+dTMmclBcPXqzl6NFCA5VRCX0XjkYSM+5Lm/t8V/rz8bQjfQv2F/
   vFt606NOD1xsyRcpKIVw2aWcYRERkew6dw5++80c/fvDwIFpH/Paa3m/Limw4uNNT+CUBXG7d99f
   QVzSeOQSdvA4ALZEaLqcb2vN4fS21ni39GbewHm4l3RP93zHVDhJpmBYRESKrqAgU7n0229w/rzZ
   8e3ZM3cmGUihljKPt2LFB6hdewLLlz+Y4wVxXl4uUH4/jOsLZc9CQnHY/ipPnB3Hyn/OuP8LFEEK
   hkVEpOiKjoaaNWHBAmjVClxVTCRZFxoaxuOPz+TEiWlAacCibNk/WLSoJv3750wXkdiEWNYcW8PF
   nluw1f4nlmv87XFo4GW/wGfvTc+R6xRFyhnOh/TaiIjkgMREs/P7yy8QEQH/7/85e0VSCEVFwWOP
   rWLHjn5AyjdTUYwY8TELF06+r+ffe34vfkF+LN6/mEaVGuHdypvGxZvSb9HTXC8eQbm4ymwa+yvN
   G6gYDpQzLCIiRV1sLMybZwLgX3817c0efxyeeMLZK5NCxlEQt2ABQH1SB8IAbpw9m5it53Z0g/Df
   68+Vm1cY03IMW8dv5aEKDyU95tSUY4W6EC4v5fBQv8Khdu3alClTBnd3dzw9PRk7dizR0dEAjB07
   lvfeey/d81xcXKhWrRqJick//AkJCXh4eOCqj95ERHJfsWLwxx8m+A0KgkOHTAeIfv2cvTIpBBIS
   YOVK6N0bunQxOcC7dkHfvt8AUXc8OgpPz8yFWfYYOwFhASzdv5RB3wyi/sz67D63m096f0Lo/4Ty
   fo/3UwXCkFwIp0D4/ikYTofNZuPHH3/kxo0bBAUFERgYyPTpmcvFKV++PGvXrk36+5o1a6iQ2eaB
   IiJyd/HxsGULvPcenDqV9n4XF/j6a/D2VuszyTEXL8L06VC3LnzwAYwebX78pk83nSGmTfOmXr3J
   JAfEUdSrN5lp07zv+dxbT22l7r/r8qj/o0xYNYHH6z7OqTdOMX/QfHrW6ZmqLZrkjnz5Cttj7Gw7
   vQ17jN1pz+HI2fXw8KBPnz4EBQVl6rxRo0Yxb968pL/Pnz+fMWPGZGsNIiIChIWZccaDB5u0hz/9
   CWJist6gVSQLHBPiRo6Ehg0hJMRMiHPclrIzRJ06tVi//jVGjPiYHj0mM2LEx6mGYNzpUvQlZuyY
   QesvWzN42WCu3LwCmCK5ttXaZtgWTXJHvssZtsfY6erXNSkPJmBsQJY/AsiJ53A4c+YMa9eu5fHH
   H7/nY202GwMHDmTGjBncuHEDy7LYvHkzU6dO5e9//3u2ri8iUuQtXAiHD5tgePZsqFrV2SuSQiw6
   OnlCnN0OEycmz1q5mzp1at21WC4uIY51x9fhF+THb6G/0b9hfz7u9TEPez5MN/9umgrnRPkuGD5w
   8QAHIw4SnxjP3gt7cf/g/t4dBUcEczDiYJYbTA+83Ww9MjKSxx57jClTpmTqvFKlSjFgwACWLl2K
   ZVkMGDCAknfOqxcRkWSOrg+RkfDoo2nv/9vf8n5NUuSkLIjr1MmkQGRnQtyd9l/Yj3+QP4v2L+Kh
   Cg/h3cob/4H+qXZ/A8YGqBjOifJdMNzMoxlNKzdNeod0PzvD9/Mua+XKlfTo0YOAgACGDx/OpUuX
   cHe/e2DuSK0YNWoU7777LgAffvhhlq8tIlLoXbkCP/8M69aZo1w5swWXXjAskk0pB2F4ebkwbZp3
   qtSFhARYvTr1hLhdu7I/Ic4eY+fAxQNUK1uN1UdX4x/kz4WoC4xuMZqAsQHUr1g/3fM0Fc658l0w
   XLZk2ft+h5QTz+EIbLt27cqYMWP485//zIoVKzJ1bteuXTl37hyurq507tyZkJCQLF9fRKTQOnHC
   DLjo1s10fXjvPVOZJJKDQkPD6NVrJiEhUwE3IIrt2yezfv1ruLnVwtfXpKLn1IS4qzev0vartpy8
   dhKbzcaQxkOY/th0etbpiauLOkrlZ/kuGIaceYeUk++yJk2aRJ06ddi7dy8A8fHxxMTEJN3v4uJC
   8eLFU52zevXqVH/XEA0RKXIuXYKKFcF2R//7OnXMEAylkEku8vHxTxEIA7gREjKNnj2Pce2aSUFf
   seL+J28HRwTjH+SPb6BvUiFcMVsx3uz4pnZ7CwiV4qbDdsc/3JUqVWL06NH84x//wGaz8eGHH1Km
   TJmk47HHHktzXuPGjWncuHGGzykiUugkJpoev5MnQ/v2UK8ehIenfZzNpkBYcl14eCLJgbBDaVxd
   zxISAr6+2Q+Er926xhe7vuCROY/w+PzHcbG58PPIn2lZpSXFXYqrEK6A0TjmfEivjYgUOP/4B8yY
   YVqf9etnjs6doUQJZ69MiqgBA2ayatXLQMpPbrM/IjkhMYFfQ3/FL8iPtcfW0uehPni39KZXvV4U
   czEftNtj7CqEc7LsjGNWMJwP6bURkQLnjz9MIFynjrNXIkVYyoK4PXsSSEjYyLVrHYEyOAZh3K3/
   r4OjEK6ZRzPORZ5jXtA85u+bT9UHquLd0pthzYdRobQGauVHCoYLCb02IpKv3LwJGzbAjz+aYPet
   t5y9IpFULl6EOXPgyy9NQdzEiTB0KJw7Z7pJnD2biKdn2m4S6bHH2Onk24ngS8GUci2FWwk3Rrcc
   zZiWY2hepXnefEOSbQqGCwm9NiLidNeuwdKlZptt0ybT/eHJJ2HgQDOOS8TJHBPiZs8279OGDDFB
   cHbzgBOtRH4/+TsfbfmIdSHrACjmUowNozfQpVaXHFy55KbsBMP5spuEiIg42bVrsHmzmTu7YMG9
   x2+J5JGoqOQJcZGR8MormZsQl5GT107iH+TPvL3zcC/pzrBmwzh14xTHLh+jSeUmtKzaMme/Acl3
   tDOcD+m1EZE8ER0NGzdC3773P2ZLJJcdO2YC4PnzTW3mq69mf0JcdFw03wV/h1+QH/sv7mdYs2GM
   bTWWVlVbYbPZVAhXgGlnWERE7u7cOZP6sGqVCYTbtIGHHwYPD2evTCSN9CbE7d6dtQlxjmK4ppWb
   sv+iGY383aHv6FijIxPbTaR/g/6ULJa61Z8mwhUtTguGa9Wqpd67GahV6+7J/SIi2fLyy7BsGfTp
   A88/D/PmKf1B8qWLF8mRCXH2GDsd5nTg8OXDFHcpTs1yNRnfejwHJh7As6xn7ixeChynpUmIiEge
   O3MGqlSBOyZmiuQHOVkQFxMfw8ojK/l026fsCN8BmGK4Td6b6FijYw6vXPITpUmIiBRVkZHw00+w
   ciXUqAH//Gfax1SvnvfrErmH6GhTEDdr1v0VxFmWxZ5ze/AL8mPpgaW0qtqKCa0nEB0XzeFLh2lS
   uQnNPJrlzjchBZp2hkVECiq73bQ/W7nStD/r0AGeftocCnwln8upgriIqAgW7V/E3MC5RMZG4t3K
   mzEtx1CrvEk5VDFc0VKg+gyLiMh9unABXn/d9P594gkoX97ZKxK5q4QEkwIxaxYEBpqCuJdeylpB
   HEB8YjzsBVAHAAAgAElEQVRrj63FL8iP30J/Y0DDAYxrPY5Haz2Ki02dUYoyBcMiIoWNZZmooXlz
   5fpKgZWyIK5aNbMLPHRo1gri7DF2Vh1dxY4zO1gWvIy6D9ZlbKuxPNv0WdxLuufe4qVAUc6wiEhh
   kJAAW7fCf/8LK1aYIHjdOqhXz9krE8k0y4Lt280u8I8/wuDB5ke6bdusPc/1W9fxD/Ln3V/f5Wb8
   TSqXqczaEWtp65nFJxLJgIJhEZH8ZOZM+Mc/zPbZ4MGmyWrTpqBWlFJApCyIs9tNR4gZM6BChcw/
   R6KVyIbQDfgF+bH66GraVGtDbEIsANduXSMuMS6XVi9FkdIkRETyk717oWxZqFvX2SsRyZKjR+Hz
   z++vIM4xGtk/yJ8HSz/I2FZjGd58OCVdS9LVryvBEcE0qdyEgLEBKoaTdClnWEQkv7t+3ez2Xrtm
   ogWRAiy9CXF3K4gLDQ3Dx8ef8PBEvLxcmDbNmyrVK/PfQ//FL8iPfRf2JY1Gbl2tdapz1RVCMkM5
   wyIi+dGVK2Z81rffmhZo3bvD6NHOXpVItl28CHPmwJdfJhfE3WtCXGhoGL16zSTk9FvgcQLCrrLq
   7wOwNQujU81OvNz2ZQY0HJBmNLKDRiRLhiwLIiLg5Mlsna5gWEQkN0VHQ8OG0LUrDB9ukindVfku
   Bc+dE+KyWhDn4+NPyJXR8Kc2UPYcJJTgRsCfGVQshv+++0nuLl4KtpTBbnpHWBiULp31Hn23KRgW
   EclNZcpAeDiUKOHslYhkS1QULFmSekLcjBlw/XralIc6dWqlOT8uIY4fj/3IugcXw8sfQ/FosAFY
   EDKAay5r8/pbkvzoxg04ccIcISFpA15HsOs4mjSBfv3Mn2vVMrUWkK1iYwXDIiL34+xZ+O47kwLx
   l7/AU0+lfYwCYSmA7iyI++CD5IK4pJSHkKmAGxDF9u2TWb/+taSA+ODFg8wNnMvC/QtpWLEh9RMa
   c3nmGhg5BCoFw6UmcLE2nt00JKNISEiAM2dSB7yOP584AbdumcLhunWhTh1o1Aj69k0OfsvmXp64
   CuhERLLq4kVYvhy++Qb274f+/c0EgV69sjZFQCSfyWxB3MiRU1m06C1MIOwQxdBR0+j5em38gvw4
   c+MMY1qOwbuVNw0qNrgjZ/gkXKxNvRofpwqgpYCLiYHQUDNr+/hxc4SEmOPUKahc2QS79eolB76O
   w8MjR1pIqoBORCQvBASYaQJ/+Qv07g0l0y/4EclL6XVqyGyQmbIgztPz3gVx4eGJgBuUsEOVfVDq
   CjRfyopa30HoAKZ0m0Lver1xdXFNOqdOnVqsX/8aPj5fcvZsIp7dXJg2TYFwgXPzptnJdQS7KQPf
   8+ehZk146CFzNGxoUhnq1TPvqPLpZoF2hkVEMhIdbXJ+RfK59NIW6tWbfNdd1/QK4l59Fdq0uff1
   Ro6cyqKf+8GY/uB2AeJLwYb/ZUg9O9/O/yhHvzdxgrg4k6d75IjJl3Ecx46ZQrbataF+/eSg13HU
   rOn0sfHqMywicr8uXzYjkJctg+Bg8wuhmD5Ek/wto7SFESM+ZuHCyakem3JCnKMgbuxYePDBe1/n
   ZtxNVhxewayts9kWthOreDy4JEJ8cbzWP0PAkuna6S0oLAvOnUsd7DqC37Aw8xFBw4bQoEHyUb8+
   1KgBrq73fn4nUZqEiEh2LV0K8+bB1q0m9eGFF+DJJxUIS4GQlLaQihtnzyYm/e3YMbMLnF5B3N1Y
   lsXuc7uZGziXbw5+QzvPdvxPl9eZ8Wg9Hp//JNeLR1AuvgJr5/9NgXB+dOuW+Y9/+DAcOmS+OoLe
   0qVTB7xdupivdevm25SG3KB/5UVEAE6fhjFjTGHcAw84ezUiWeLl5QJEcefOcNWqrqxcaYLgwEBT
   ELd7d+basUZERbBw30L8gvyIiotibKuxBL0URI1yNZIec2rKMU2Fyy+uXEkOdlMGvmfOmO4MjRsn
   d2iYNMns8mbm44AiQGkSIlJ0xMaaXxhVqzp7JSI5Kr2c4QoVfqdUqd7UrFmMiRNNw5OMNvvsMXYO
   XDxAo0qN2Hp6K3OD5vLriV8Z0HAA41qP49Faj+JiUws0p7Ms084xODj5cAS9t24lB7wpv9at6/Q8
   3ryknGERkTslJMCGDSYNYsUKePll+Oc/nb0qkRx34kQYr7zyC3v3PszVqw14+ukE3nnngXsWxNlj
   7LT/uj1HLx/FxcWF1lVb80KbF3i26bOUK1UubxYvqVmWGdYTHAwHD6b+WqIENG1qhk40aZIc+Far
   liOtyQq6XAmGbTabL/AUcMGyrBa3b/sI6A/EACHAWMuybmRwvoJhEcl7ly7B1Kkm7aF6dRg2DJ59
   1hR/iBQijoK42bPNEC9HQVyFCnc/LzI2kuUHl/PZjs/Yd2EfAMVcihEwNoAO1Tvkwcolaad3//7U
   AW9wsMnnTRn0Nm1qAt/KlZ296nwttwro/ICZwPwUt/0MvGNZVqLNZvsAePf2ISKSP7i5mXSIgACT
   GydSyNxZEDd9+r0L4izLYtuZbcwNnMt3h76ja82ujK8/gclh/+R68QgeuFURt2jl/uaKq1fhwAET
   +Kb8WrKkCXSbNYP27c07mcaNoWJFZ6+4yMhUmoTNZqsFrHLsDN9x30BgiGVZozI4VzvDIpJ7Tp0y
   vzTc7qykFyl8HBPiZs82E+LGjUt/QtydzkeeZ/7e+cwNnAvAuNbjGNViFLcuxWoqXE67edPk8d4Z
   9N64YYLe5s1N4Ov4qp3eHJVrOcP3CIZ/AJZalrU4g3MVDItIzrp82aQ/LF5sPk5ctQo6dnT2qkRy
   zcWL4OsLX3yRPCHumWfSFsQ5CuGaeTSjVLFSrDm2hrlBc9kUtonBjQYzvs14OlbviO12bmlW+hPL
   HSzLvBnftw/27jVf9+0zPXrr108OeB1Bb82a9+5jJ/ctz/sM22y2vwFxGQXCDlOmTEn6c/fu3ene
   vfv9XFZEiqqtW81nwZs2mfZAb71lvpYo4eyVieS4OyfEDRliakAzKoizx9jp6teVgxEHebCUaZnV
   sFJDxrUax6LBi3igRNqWgZnpTyyYxOwDB9IGvqVLQ4sW0LIlPP00+PiYYrYi1L3B2TZu3MjGjRvv
   6zmyHQzbbLYxQD+g570emzIYFhHJNldXsx22aBG4uzt7NSK5IioKliwxQbDdDhMnwsyZd28Ja4+x
   86+Af7H3wl4ALt+8zOLBi3mu2XN3vVZG/Yk9PYvoDqajoC0w0OShOILfU6dMkOsIfAcONH9WioPT
   3bnJOnXq1Cw/R2bTJGpj0iSa3/57X+AT4FHLsi7f41ylSYhI5lkWhIaa3pgiRcjRo/D557BggSmI
   mzjx7gVxlmWx+dRm5gbNZcWhFXSp2YWDEQcJvxFOk8pNCBgbcM9BGOn1J65Xb3LRyBlOSDBViIGB
   ycFvYKC5r3VraNXKBL4tW5opbdrtLRByq7XaYqA7UBG4AEwG/hcoATgC4e2WZU3M4HwFwyJyb6dO
   mR3fhQvNL6n9+/XLRwo9R0HcrFlmA3LcONMKu9Zd4tBz9nPM2zuPuYFzcXVxZXzr8YxqMYoqD1TB
   HmPP8kS40NAwfHz8OXs2EU9PF6ZN8y58gfDNm+bfFEfAGxRk/l6lSnLg6/jq6al+vQWYhm6ISMGz
   dCl8+aX5OHLoUBg1Cjp10i8jKdTSK4gbOtR02UpPXEIcPx77Ed9AXzaf2swzjZ9hXOtxdKjeIakY
   Tm6LjDTB7u7d5tizB0JCzO6uI+ht3drs+JbTUJHCRsGwiBQ8X3wBHh7w5JMZRwIiBZRj1zU83Oy6
   Dhr0Et9/XzWpIG7ixLsXxK0+uprtZ7bzzcFvqF+xPuNbj2dok6G4lVArQcC0KwsMTA56d+823Rya
   NYO2bc3Rpo1paaZ/X4oEBcMikj9ZFly/DuXLO3slInkmbT5uAsWLX+Evf3HlrbcqZFgQZ4+xM2/v
   PN5e/zbR8dFULlOZdSPX0abaPeYqF3bXr6cOenfvNiOLW7RIDnrbtjXT2pRiVWTleWs1EZG7OnPG
   5ADPmwcPP2wqg0SKiP/5nx8ICZkOOAIzV+LiyhAW9jEPPpi6h69lWWw5vQXfQF9WHFpBw3INiY67
   CTa4HHmZk6fDilYwHBVlUh127kw+zp41aQ5t2piWin/7m+nwUEyhjNwf/QSJSM6Ki4NvvjEB8O7d
   JhHS11dDMSTHpUxB8PLKH4VfKQviNm4cS3Ig7JC6h++dk+HGtx7PKwNe5fnB86HHTah0mMRLjXhr
   9AZar23j9O8vV8TGmpqBXbuSA9/jx01qQ7t28Pjj8M47ZkSxAl/JBfqpEpGcZbPBmjUwYQL88INp
   Si+Sw9JrCbZ9u/Nagl28CHPmmFpQR0FcxYqfsXTpG9zZw7eqp8UPR37AN9A3aTLc3KfnJk2GGzly
   KqFHpkNoIngchItNCY11wcenEEyFS0yEw4fhjz+SA9+DB6FePfPpUbt28MorZmqbcnwljygYFpHs
   s6y0XR+KFTNjkkVykY+Pf4pAGMCNkJCpeRow3jkhbvDg1BPiOncexc6dkwk5/RZ4hEJ8AuW7vMkv
   LU4StsUUw6U3GS5pKlwscKZD0u0Fcirc+fOwY0fysWuXGVTRvr05hg0znR3cVBAozqNgWESy5vp1
   WL4c/P1hxAiziyOSx/J6jHDKlIwqVUrSsuVLLFtWMWlC3IwZUKFC6nPq1KnFopXP0XNJQ6KL3cCG
   jYGNvflrz3k0rtw4w2sV2Klw0dEmNSpl8BsVZYLeRx4x49PbtYNKlZy9UpFUFAyLyL0lJsKGDeDn
   ZxIiH3sM/vpXeOIJZ69Miqi8DBiTUzLeB8oAFqtWBTNrVjyjR1dJMyHOsix2hO/Ad48vSw8u5Wbx
   KACKuRTjpc4v3jUQBpg2zZvt2yenmQo3bdprOf69ZVtiIhw5YrbGHYHvsWOmpdkjj5hxxf/6Fzz0
   kHqGS76n1moicm/btpntr7FjYfhw7eyI0+XVGOH4eHjssaVs2jQUcE1xTxQjRqROyYiIimDBvgX4
   BvoSmxDLuFbjGNJkCM8uf5bgiOBMj0h2fH/5airc9esm4N22LTkAfvBBUxjboYPZ/W3VSnm+4nTq
   MywiuSO93GARJ8tuwJiZLhQpC+KuXTvNjRs10jxPjx6TWf/Le/wc8jO+gb78cuIXBjQcwPjW43m0
   1qNJk+GyMyLZqRxFbo7Ad9s2M8iibVsT/DoC4CpVnL1SkTQUDItI9lgWbNli8oB9fKBWIWzfJMLd
   d5Rr166VpiDu1Vfh00+nsmjRW1AiETwOwMVm4BZGs5Gvcq3OCao9UI3xrcfzfLPnKVeqAI73vXED
   tm9Pf9fXcbRooUEWUiAoGBaRrDlzBubPN0Gwq6tJg5gwIW0lkEghMXLk7cD2jlzjRx75jZiY/kRG
   mppQb+/k/w1CQ8N47IlPCO3xG1Q+DPGlsFkJjGk9jDe7vUHzKs2d8J1kk2XBqVPmza/jOH7ctMDo
   1Em7vlLgaQKdiGTeV1+ZRvZDh5qA+JFHlAohhV5GXSiOH6/PokXQqxdpCuKulbpCw7ePExp2EGxg
   c4lmcd+lPN/h2bxadvbFx8PevamD37g46NzZHKNGmUC4RAlnr1TEaRQMixRVzzwDI0dCmTLOXolI
   nqlWzRW4BZRKcWs0fft+Q58+ycVw125dY/H+xczZM4fLNy8zotkIwqJPcvzKcZpUbsKTrfNpJ5Ub
   N0yqgyPw3bkTatY0u779+sE//2kGXOiNr0gSpUmIFGY3bsDPP5vAV6QIu3jRTAX/z3/iuXz5DDEx
   VTEBccqc4Zr8HvY7c/bMYfXR1fR5qA/jW4/nsTqP4erimj8L4S5cgICA5OPoUVPo1qWL2fnt2NHk
   /4oUEcoZFhGTE7h5s/nN//330LMnLFqkschS5FiWqQubNcsUxA0ZYjoEPvhg6i4Uf3r3CX678gtz
   A+dSunhpJrSewIgWI6hUJp+1ELQsOHEidfAbEWGC3q5dzdG2rdqbSZGmYFikqPPzgw8+MEmP48eb
   fEAVwkgREx1tJoLPmgWRkSYA9vZOvUF6JfoKX+35it/DfmfHmR0MbTKU8W3G086zXVJLNKdLSIAD
   B1IHvzZbcuDbtasZcnFnkrNIEaZgWKSoW73alMB37KicQClyjh0zbdEWLDCbpRMnpi2IO3r5KLN3
   zmbWzlnEJ8ZTw70Gf0z4g6plqzpv4Q7x8RAYCL//bo7Nm82bWUfg26UL1Kmj/7dF7kLdJESKips3
   0097eOqpvF+LiBMlJJgUiFmzICgIxo2DXbugdu3kx0TFRvFt8Lf4Bvpy9PJRHq/7eNJ95yPPc/L6
   SecEw3FxZrGO4HfrVlPs1q0bjB5tpn7okx2RXKdgWKSgiI2FH34wvyCvXTPJkCKFQGYmwt3JURD3
   xRdQrZoZjrFyJZS63STCsix2n9vNnD1zWHZwGZ1qdOLNjm/yZP0nuRV/iwMXDySNSG5auWnuf5MA
   MTGmu4Mj+N2+3XR26NYNXnzRbGlr1LlInlOahEh+d/SoCYDnzYNGjeCFF0wlkAripBC420S4OwPi
   OwviHBPi2rRJfsyVm1dYuG8hvoG+2GPsjG89Hu9W3ni5e6V6rjzpDBETA3/8ARs2wMaNJhBu2NAE
   v926mdQHdXoQyVHKGRYpjPr1g6ZNzWS4hg2dvRqRHJXRRLgRIz5m4ULT9zdlQZzdnlwQV6GCCWr3
   XdjHlZtXWHxgMWuPraVf/X5MaDOB7rW742LLw+IyR9rDhg3m2L7dvIHt0QO6dzeJzOUK4LhmkQJE
   OcMihdGaNc5egUiuyWgi3NmziRw9Cp9/bgYkdu5sGqWkLIg7fOkw3f27cyHqAqWKleL97u8zq98s
   KpTOo3HiCQmwZ09y8LtlC9Sta4Lf116D5cuhfPm8WYuIZJuCYRFnu3nT/NK8eRNeesnZqxHJU15e
   LkAUqQPiWxw6NJouXUyHwN27kwvi4hLiWHloNb6BvmwK20RUbBQACYkJdK3VNXcD4cRE2LcvOfgN
   CAAvLxP8vvACLFwIFSvm3vVFJFcoTULEWYKD4csvzUCMRx6B11+HPn2cvSqRPJU2ZziRkiVP869/
   uTFxYqWkgrijl4/iu8eXeXvn0aBiA8a3Hk+fen3ou6hvUiFcwNiAnM3/tSwICYFff4VffjEBcMWK
   Jvh1pD6o24NIvqKcYZGCICbGfNYbEmL6QE2YALXuXjkvUhhZFmzbBh9+GMXata5UqhRMy5a7mD27
   D3Xq1CI6Lprvgr9jTuAcDl86zJiWYxjXehyNKjVKeo4cL4Q7f94Ev44jPh4eeyz5qF79/q8hIrlG
   wbBIQREQYAZjFFOmkhQ9UVGmIG727OSCuCHD7ZyNO0Azj2Ycu3KMOXvm8M3Bb+hQvQMTWk/gqQZP
   Udy1eM4v5vp10+bMsft79qzZ8XUEv40aaciFSAGiYFgkP7l508yCrVzZ2SsRyRfuLIh79VXzIUlU
   nJ1Ovp0IvhRMCdcSeLh5MKH1BLxbeVOjXI2cXURsrNmOXr/eBL8HDkCHDibwffxx06fN1TVnryki
   eUbdJETyg6NHTS7w/Pnw7rvw5pvOXpGI0yQkmCnhjglxKQviLMsi4FQA0wOmcyDiAADxifEsGbKE
   TjU65cwCLAsOHYKffzYBcECAaVHYqxf861/QqVPypA4RKZIUDIvkhLg4M/7q88/NTtPYsbBjh2mz
   JFIEpZwQ5+lpdoF/+MHEnecjz/PRlvnM2TOH4q7FGdViFKdvnObo5aM0qdyE5h7N7//iv/ySHAAX
   L26C3zFjzJtUdXwQkRSUJiGSEyIiYNgwUww3aBCULOnsFYnkuTsnxA0ZYvKB27Qxrc9+CvmJOXvm
   sOHkBoY0HsKENhN4xOsRbDbb/RXC3bwJmzcnB78nT5q83969TRD80EPK+xUpIpQzLCIieS7lhLjI
   SHjlFfPhyIMPwslrJ5kbOBe/ID+8ynoxoc0Enmv63P11frAs05pw3Tr46SeTA9yihQl8e/eG9u1V
   nCpSRCkYFslNFy7A3LmmC0T37s5ejUimhIaG4ePjT3h4Il5eLkyb5k2dOjnTyu/YMdMRYsECUxA3
   caKJR6/cvMQXu7/gt9Df2H9xPyOaj2B86/E0r3If6Q9XrpjUh59+Mkfx4qYvd58+0LOnxhyLCKAC
   OpGcZ1mwaZPJBf7pJ3jmGZMGIVIApB1oEcX27ZNZv/61bAfECQkmBcJREDduHOzaZQrigiOCeX3d
   bL7Y9QWJViI1ytUgeGIwld2y0VElIQF27kze/T14ELp2NcHv229D/fpKfRCRHKFgWCQjhw+bpEfL
   MlteX3wB5cs7e1Uimebj458iEAZwIyRkKj4+H7Nw4eQsPVd6BXErV0KCSxTLDi5jzm9zCL0aSq+6
   vRw7M5yznyPkakjmg+HwcBP4rltn+v56eZngd9o06NJFXR9EJFcoGBbJSM2aZvurWzftQEmBFB6e
   SHIg7ODG2bOJmTo/vYK4FSugdWuL3ed2M+mXOSw7uIwuNbvwdue36Ve/HzfjbrL3wt6kEclNKzfN
   +AJxcbBlC6xda46zZ02v3yeegP/7PxMMi4jkMgXDIjExJtgtUSL17WXKKDdYCjQvLxcgitQBcRSe
   ni53PS86GpYsMUGw3W4K4mbOBEpdZfH+xYz78mtuxNxgfOvx7H9lP17uyUFr2ZJlCRgbkHFniPBw
   s/O7Zg389pvp9PDEE/DVV9CunQZeiEieUwGdFF2nTpnhGL6+4OdnfiGLFCLp5QzXq5dxzvCxY8kT
   4jp1grEv26ncdD+RcTdYtH8Rq46sou9DfZnQZgI96/TExZY2qE5TsPfeCOqcP2t2ftesgTNnTMeH
   J54wKRBVquT+CyEiRYa6SYjcS2Ki6UM6e7bpSzpqFLz8MjRq5OyVieQKR3B69mwinp5pu0k4JsTN
   ng2BgWZC3EsvQej13+n37VPcco3ExXLlzbZv8vbjf6VSmUp3vVavXjOJCnmFJ/idJ1hFb5e1lGpS
   n5IDB5oAWG3PRCQXKRgWuZeffoJ33jHVP8OGgdud+ZQiRUPKgrhq1cz/EoOHJBBwdj2fBfybn0N+
   xXKNBxcL4ovjtf4ZApZMT78LRWIi7NrFivF/oeaBG9TlJD/Tm7U8wToe5fERC7JcsCcikh1qrSZy
   L717m0MFcVIEWZaZTzF7ttkNHjIE/vtf8HjoNHMD59Lkq7l4uHngElgVa+FBGDEUKgXDpSaEB36K
   j8+XyUHtjRtm4tvq1SYFomJFYiLL8yafsZVOxFM86bqZLdgTEXGGu1dRiBREsbGm+ufKlbT32WwK
   hKXIiYqCOXPMWOTRo83XI8fieOqtFfgc7kerL1sRER3ByudXsvOFnZQ51Abs9WFuAPhvMl9jq+Jy
   PAI+/RQee8x0epgzBx5+2LScCA5m9aN92MTDqQLhzBTsiYg4k3aGpfAIDzcFcV9/DU2amN/4FSo4
   e1UiTnP0qCmIm7fETpPuB/D5RzOatj+P315fWs2fR/0K9XmhzQt8++y3lCleJuk8RxeK4rElefRM
   JE/yHk+xior7LkKL5+H1101A/MADqa43bZo327dPTlOwN23aa3n5bYuIZIlyhqXgO3AApk41TfqH
   DzcDMpo0cfaqRJzCURDnmBA3crydNVU7c/x6MKWKlaJ08dJ4t/RmQpsJNKzUMO0TXL5MxLz57Hzv
   CzpFXeAIDVlNb/ZWP8m/f59Gnbq173r9exXsiYjkJhXQSdEUGAhbt5rOEO7uzl6NiFNcvGiyFr78
   0kyImzgRmnQ/wIfb3mf5oeUAuNpc2TBmA11rdU198pEjsGoV/PCDiaB79iSiY2cm/3GRw1fLKKgV
   kQJDwbCISBGSsiDuxx9h8GAY+1IkR4p9w5zAOZy+fpoRzUfww9EfCLkSQpPKTQgYG0BZ19LmDaQj
   AI6MhP79zdGzJ5Qu7exvTUQkWxQMS+GUmGhaov3nP+aoU8fZKxJxquhoWLzYpEJERsLLL1u06reb
   Zce/ZnnwcrrW6soLbV6g70N9KeZSDHuMnYMn/6BpYDhlf1xvuj/UrGmC3wEDTH69CktFpBDIlWDY
   ZrP5Ak8BFyzLanH7tgeBb4BawEngWcuyrmdwvoJhyZ7r181kuFmzTPrDa6/B889DqVLOXpmIUzgK
   4hYsMBPixrx0jfOVFzMn8Guu37rO+NbjGdt6LJ5lPc0J4eFm5/f7780WcufOJvh96imoUcO534yI
   SC7IrWC4CxAJzE8RDH8IXLYs6yObzfY28KBlWe9kcL6CYcm6776DCROgb18TBHfsqJ0rKTTSjCye
   lnE+7p0FcSPG36BSt8UcjNrEmmNr6PNQH15o84IZj4wNgoNN8LtyJRw/Dk8+CU8/bUYfly2bt9+o
   iEgey7U0CZvNVgtYlSIYPgx0syzrgs1mqwpstCwr3Xm2CoYlWy5cMFGAp6ezVyKSoxwji+9sP7Z+
   /WupAuKUE+I8PWH0y5eIqPEV/9r6PjEJMVR7oBpbxm2hjntNs+vrCIBjYmDgQBMAP/ooFC+e4VpE
   RAqb7ATD2e2E7mFZ1gUAy7LOA5Wz+TxS1F1PN7sGqlRRICyFko+Pf4pAGMCNkJCp+Pj4Y1mmrm3k
   SGjYEI6HJPLuV79S68/P8+65h9h2NoCExAQALkVGcOF/XzezlP/0JzNafNkyCAuDGTNMH2AFwiIi
   95QnQzemTJmS9Ofu3bvTvXv3vLis5GcHDphf2MuXm9ZotWs7e0UieSI8PJHkQNjBjV27WtGmjSmI
   G/HSeV4b7cfiw77sCnXjhTYv8Hnn6RT7eT1do7YSXPIGTW6WpGmDzrBjhopKRaTQyEoaGcDGjRvZ
   uHHjfV0zu2kSh4DuKdIkNliW1TiDc5UmIYYj+XHGDDh0CF5+GV56yewCixQRI0dOZdGit0gdEFt4
   Vj/EK/8vjN18zcawDQxpPIQXaw2m3dYwbCtWmJHHPXtif7ovB9vXoelDnShbUjnAIlJ4ZDaN7G5y
   M0n6ExMAACAASURBVGe4NiYYbn777x8CVyzL+lAFdJJpM2fCokVmlOszz0CJEs5ekUieO348jK5d
   f+P8lUHgcQhulqFc5zdx63oEz3LVeKHGQIYdgLIr1phiuH79YNAgU0x6x/hjEZHCJP3NgihGjPiY
   hQsnZ+o5shMM3zNNwmazLQa6AxVtNtspYDLwAbDcZrONA04BQ7NyUSmiJk40nSFEiqDkCXG1qFzj
   Ca6ObkBM6QjARr/KffjrpadotXA7nJthit98fKBHDyhZ0tlLFxHJExmlkZ09m5ir171nMGxZ1vAM
   7no8h9cihUFiIqxfD716gcsd9Zmurs5Zk4iT3DkhrtfQUB7/1xxWhn9JzM3LABRPsHjdP4hWXRqZ
   T086ddL/KyJSJHl5uQBR3Lkz7OmZ3X4PmaMJdJIzHAMy/vMfKF/eNPpXNwgpoqKizIS42bPBHh1L
   53ErOVX5K/af38koex2GrQvnxW43CC4fR5Ny9Qh4ZRdlS7nf83mzWlgiIlKQ5Ouc4fuhYLiQO3EC
   PvsMFi6E3r3hf/4HOnTQgAwpkhwT4ubPh5Y9j1Lp8a/4/fJcmkSV5oWAaAbbq1Nq0FB45hns9Wpw
   MOIgTSs3zVQhXE78khARye8cb/rPnk3E0zPrb/oVDEveW7bMjMWaOBGqV3f2akTy3LVoO19+f4Cf
   FjRjf1BxOnsvI6L8JxyPOsaYvTDhah0aPDEShgyBBg2yfZ2cKCwRESnscqWATuSunn3WHCJFzMWL
   MOtrO9MvdCXuwYOUa18G13a3iA63mHSoFk93fo8Snz2XYz2AnVVYIiJS2CkYlns7cwa+/hreeQdK
   l3b2akScJmVB3M/rrtL66ZeJq7EXbGBPvMGyst4MmfI+1KiR49d2VmGJiEhhp39FJWPbt8Pzz0OL
   FnDtGty65ewViThFdLRpi9a+VSwfv/gfrGKNSJhQEdx+prZrBYq7FKN5tZb0fn1GrgTCANOmeVOv
   3mRMQAyOnOFp07xz5XoiIgVOTEy2TlPOsKS1YYPZBb50yfQFHjsWypVz9qpE8tzRo/DVf2I5uXA1
   tVt/SsBD2zlbwZVx5Xsw7ump1Gr0CPYYe5YK4e7H/RaWiIjkG5ZlWu9cvmw+dfbwSPuYZctgwQKz
   IXf9uvl67Rq8/Tb87W9pH2+3Y3N3VwGd5IBt2yAiAp58Uv1OpchJSIAfv49j+z9/xe3KbE62/Jnv
   miXQpUxDXuzxFn07jKSYizLMRETSiIqCCxfMsCAvr7T3z58Pn3xiAuBLl0yMUakSvPVW+kO5Dhww
   XavKlzebco6vZctmGJ+om4SIFHnZ7cV7MTyOH31WE7L9K8qW+50l7Vy4WqkEE1qPY2y3SVR3V7cU
   ESmCEhNNmmSZMmnv++EH+H//D86fN0d8PFStCn/6E/z5z2kff+aMCYIrVjRHes95nxQMS+YkJsLP
   P5sqoLlzzbsykUIgq714rfgEgr8M4NxnS4iM/wbv5yK5XioB9xIP4DdoHk83fBpXF306IiJFRFCQ
   mRtw5kzyce4cvPiimZB5p5MnISzMBMBVq4K7u9PnDKi1mtxddLTJvfnsM/MRxhtvmI8aRAoJHx//
   FIEwgBshIVPx8UnRi9eyuPX7Do7/Yymlty9lWfNiLBmUiL1CSeyxdrDgZkIMnmU9FQiLSMF26xYc
   O2aCVkfgevIkNG4M06alfbyLC1SpAm3bmtkBXl5mmmypUuk/f+3a5ijgFAwXFcuXm8EYnTubEVnd
   ujn93ZtITsuwF294AgQFcWX2UqylS9hQHv7TvSK7/3qTvo36MPvhF2nn2Y5u/t0IjgimSeUmNK3c
   1BnfgohI5l27ZoLb2Fho3z7t/du2mZSF2rWhVi3ztV07aJrBv28t/n979x0dRb3+cfw9gdC7Akqv
   ipSLCggKaFDgCgIqRUVCbwJi74iI8XfxWvEqoQoBDIggzYagGOkdpEuLQQgQEEijpOz8/vjSTEDT
   dmc3+3mds0dIJjtPPMvmycxT/mUefkZlEv7iwAHTuVm9utORiLhN2i1ttdjFY0yjV8FpnMuXh2F1
   a7Hqnt/Jd52LwY0H0LN+T8oWKXvp6z05GUJEJNOiosy0p337YP9+SE42Ce5995m7vqKaYcHUAwdo
   fLT4p8jIKHoFvU2Do6W5tcyX3BGTwNiyd/FNi7McrbGatjfdz6A7BhBUJYgAS/9ORMQLpKSYJPdi
   grtvn5mXO2ZM+mNPnYLvvjMXtqpXNz0/mbjLm9UGY1+iZNifxcaarQBjxsAvv7ht8L+IV4qJgdmz
   sWfM4M/du7j18VQOl0wAOy83FirH8/c8SY/6PShduLTTkYqIXHbyJK5y5fgzbwEOBpYi9vpS3Nqp
   FaXuuhM6dMjRU2W2wdhXZSUZ1qURX3fgADzzDFStChs2wBdfKBEW/xAfbxpC27TBvukm9k5bSefU
   DlTu2JDD18dBHhd587n4KngGz9/1vBJhEXE/2zazcefOhVGjoFcvuPNO05SWnJzu8MjTcdQrN5Ay
   iYdpePoA9+37hTvmJBNZr36Oh3btBuOwHD+Xr1Ey7MumTDEF8/nzw6+/wsyZVy+gF8ktzp+HBQvg
   0UehQgUSpswmNG8nSt7+Gre32MK6h6cwrHsL6pSuQ2BAIHVK16FumbpuCycyMorg4JG0aDGC4OCR
   REZGue1cIuJFzpwxG3rSsizo3x+mToWTJ6FZM3j3Xdi2DfKmn1kw/I2p7Iz8D55IUK/ZYBztyvFz
   +RpNk/BlDz0EXbpAkSJORyLiPqmppvRn5kyYOxe7bj221OnKM0HdWVv4C7jpBe6v3o7n7h5H80rN
   sSyLoY2fdHsj3NVuOa5Zk/tuOYr4vV9/NfN3d+68/IiOhq1boWbN9MevXp3hp/Zkglq+fACQmOZ8
   iZQrp+ui+j/gC2Jjr/7xkiWVCEvuZNuwebNZ0VmpErz4IvHlb+advj9TqvCD3FV4NPsav0jIoIYc
   fmk/87t/zt2V78a60EhSNH9RmlRo4taJELrlKJKLJCWZO09X8+mnZlFVsWLQp49pYIuPv3oinEmX
   E9QruSdBDQnpRfXqI644n6kZDgnplePn8jW6MuzN9uyBjz+GGTNg40aoVs3piESyJMMdzFFR5vX+
   +eckx8Ux+7pKjK/Wlt2u2zi1eyXWzW/TsmN7Xmk1gWaVml1Kfj0a4wW65Sjio44cMb9sb91qyhe2
   bjUTHGbPhnbt0h8/caLbQgkJ6cWaNSPSNbWFhAzN8XNVrVqZJUuGMnz4+0RHuyhXLoCQEN3JAiXD
   3se2zS3hjz4yt1oGDDC3ZG680enIRLLkH8sJTp2COXPMCtAdO6BLFw688haNRhzh5H3/gaKrICU/
   Jbc05aeuv3BbrZxvLMlKyYNuOYp4Odu++tix0FBYuxbq1YNWreC556B2bShY0OMhejpBrVq18uVt
   nHKJRqt5m88+g/feM6uSu3eHQoWcjkgkW9IuwgDIx0n+e/dgnrk+GX78EVq3huBgfqt2P69PXcvc
   qDG4an4LgWcgwIaUQAj7gW73LHPLG/nVYoREunV7/5rn85cxRSI+4dgxU9d78bF5Mzz+OLzxhtOR
   iYdlZbSargx7m+Bg6N1bizMk17hYTmDhoikrCeZzOjOHg1uLwvvDSZ3wGTMiUnl73jT2F7+VEiUs
   KgbcTFToDuj6IFy/E07UhpiGREdHuDXGv/r7kgfdchTxEp99ZvoLbr0VbrsN2rSB116DWrWcjkx8
   hJJhp+zbZ2YD58nz14/nz+9MPCJu0qDoSe7lZboziwSKMJ3u3Moq7rhvAdcdrUn4M09yvvK3NKnX
   ntAHJ3Jv9aZ07/4WUbHXw+TlUGYHxNSBpAC3lSBkteRBtxxF3Cg1FXbvNj0zGzdC8eLw1lvpj+vR
   wzS25WAPgfgXlUl40sV64A8/hDVrYNky/eYqudPJkzBrFkybRsq+fUxNrszos++wvUwhiC9Fvlsn
   kPKv7ylWzKLvrQN57YHulCpY6tKXe7oEQSUPIl5k3z6zrGLLFtMv06CBeTRrZhZYiPwNrWP2VklJ
   8OWXJgk+c0b1wOI4t+ynT0qC77+HadPgp5/MrcoePaBVK9Zt/427Z7TkfMFjgMUtdgc+ePR57q/d
   9JoTIS7GeLkEIQdi/BuePp+I37p4xXfPHnj44fSfT0w0DW633w4lSng+PvFpSoa91YwZpqbpuedM
   gqB6YHFQjl4FtW2zBnzaNLMKvHZtkwB37gzFi7N++0le+HwaK5JH4yoaBRYEBgSyrPcymlRo4o5v
   T0S8jW3DV1/BunXmsWmTWU/cuLFZqa7yBslBSoa91bXGu4g4ICuTE9I5eBDCw00SnJJiEuDgYKha
   lZQUm/dmreSTVeM5Wvxraudtx4v/7s6H215i1/Fd1C5dm+W9l7t1IYaIeJlevaBGDbjjDmjUyCyN
   EnEDTZNwkm3DypXmtk7a8gclwuJFsrwsIjER5s2DsDAztqhLF3PH4847wbLY88cpnnv7YxafmECe
   wFQ63jKQd7uNpnzJ6wDo2PAut69IFhEPOnfOXOW9eMV3/XrTK3D77emPDQvzeHgiGaVkOLtSUszC
   gA8/NMsD5s+HOnWcjkrkmjI1OeHiL3lhYeY25113wcCB0L49FCiAy2Uz4ftVvPvTeCLzL6RaSlvG
   tA2lX6u709UCX1yRLCK5wNChMHmyaQJv3NjMCh82TE3h4pNUJpFVsbEwaRL8739QpYqpB27XLv2o
   NBEvk6Ga4YMHTQlEWBjky2dmXwcHw403En8+nqV7VzF9ya98e2gaqXYy95cZwAfde1Kz/PUOfmci
   kmPOnDHjzK6/Hm65Jf3no6LM5wqnvcsk4izVDHvSkiUwZYpJghs2dDoakUy56uSEsqVh7tzLZRCP
   PmqS4IYNwby58N5Xs3h10wBc+eKxzhfl6YpjeX/g4+TJo1IgEZ929KjZBrlmjXns2mXucr7yCnTs
   6HR0IhmmZFhEMidtGcSdd5pGlw4doEABAE4mxvLKzOmE7x7PGdcpKHIE8rggJZDySzqzfOYojSAT
   8XULFpjJDnfeaR633QYFCzodlUimKRnOaampsHChGfRdurTT0YjknEOHTBnElCmQN+/lMohy5QCw
   bZtF29fx+rzxbD43l5InW3PDoTrs/LE/9G57eUXy5EV06zJeW9hEvNmpU7B6tfnFNyUF/vtfpyMS
   cRtNk8gpiYkmSRg9Gq67znTMKxkWX3f+PHz9tWl6WbMGHnkEPv/cjDq60OwWey6OtxeE89mv44k9
   G89t9OeHR36j1Z1ladFiBDvPl0uzIrnoP0+hEBHPO3kSXn3VJMBRUebfedOm0LKl05GJeB0lw1c6
   dgw+/hgmToS774apU033vEajiS/butUkwOHhULcu9OkDc+YQnyeV7THbqZuUwJZDvzFs7nhWnZ5D
   gSP30a3We/zf8/dx/XWXJ0xcmkKRVBQOXZwKcY0pFCLiGS7X1Rc5FSlian4HDID69c0dIBG5Kv3r
   uNKRIxAfb66aVa/udDQiWXf6NMycaZLgo0dNHfAVr+v48/Hc9dld7Dy+E8vOjyuuNDcnDGRa+508
   9sCNV/3ZGhLSizVrRqSbQhESMtSD35iIn0tKMlMeli2D5cth1SrT7Fa27F+Py5cPnnrKmRhFfIxq
   hkV83KXJEIdSaZU3iqGFYynyS4SZ+9mnD7Rq9ZeRfxsOb+bJL0eyNnYBWBBg52VWmwg6N26a8XNd
   OYVCzXMintGvn1l7XrOmuXvZvLnpabnhBqcjE/EaaqDLiHPnzO3ioCBd/RWfFxkZRY8W/0eLqDL0
   Jpw4irDgutL0/OEDKje47dJxiUmJTFw9iw9+Gc+R+COUPdoDbpnH8dS9Wo8s4k3i402T29XWFe/Y
   ARUqQPHino9LxEeoge7vHD8OY8dCaCg0aABNtAlLfFhyMnz9NbFDX2ZB9J98wWN0Zg6buB3+PMOe
   j97n889vY9ux7bz17XgW/j4DV9RdBBUZztw+bWjUIA/x51/WemQRp8XGwooV8MsvEBFhSh5CQ6F7
   9/THarupiFvk/ivDhw9DSIjZl965Mzz7LNSu7Vw8ItmxZ4+ZbjJ1Ktx0E6OOlyJk9wzOUujyMXnP
   cnPHYFJuPcrB2N8psrcfQ+7sy7N9KlGqlHOhi0gaYWHw5JNm0kNQkHncccelGd/ijIvlYIcPuyhf
   XuVgvkZXhq8mNdU0Fuzenb7BQMQXnD0Lc+aY9d+7d0PPnuYq0s03syN4JGd325AvHm76BiqugHqz
   2HPkdhrsfJH/dWvH/f/Je9WGOBHxgLg4M9qsXr30n+vUCbp2hfz5PR+XXNXV1tWvWZNmXb3kOrn/
   yrCIr9qyxSTAM2eaq0X9+kH79qZL/ILd+/bQfPBTnGi4HPKdgcQyFJn7Nt+FtaF58woOBi/ip86c
   MRMeli41jx07zF3JKVOcjkwyIDh4JOHhL2AS4YsS6dbtfS0X8hH+e2X49GkzGzgoCBo1cjoakayL
   izPJ78SJEBMDffvC5s1QqdJfDtt3ch+jl08gbEsY52tWhrznzGSIQieYOvN6mt+hRFjE42JjoWJF
   +Ne/4N574Z13TH+Kyh58xuHDLv6aCAMU1nKhXM63k+HffzdLMqZNgzZtoEMHpyMSyTzbhvXrYcIE
   +Oor80P07bfTjURLTk1m/u4FvLd0PFtjfoUtvWhXbiVP9bmBpzY3Z+fxndQuW5tW9bVhSsRtUlNh
   0yaT8KYtbyhe3Mz1LlTo6l8rXu/ScqE0V4a1XCh3880yiUOH4LnnzC2ovn1h6FAzbkbEl8TGmjF/
   EyaYcUr9+0Pv3ulq238//TuhaycyYd1kUmJuosjugTx3fyf69c5/qSEu/ny8JkOIuINtw2+/wY8/
   mscvv5ifNwsWQLVqTkcnOexqNcPVq6tm2Jd4fM6wZVnPAn0BF7AN6G3bdlKaY3I+GY6NNd30vXtD
   Uf3gFx9i27Bu3eWrwK1awcCB5mpwQADx5+PZHrOdWtfXYvnB5XzwyzjWHV4LW7vTJHAAr/StTatW
   V9++KiJu0LMn/Pyz+bfasqX5t6pm7FxNy4V8m0eTYcuyygErgFq2bSdZljUL+Na27WlpjlMDnUja
   q8ADBpgVyVf8UI0/H0/jSY357cRvWARQOO427PVDGNC0C08OLESVKo5FL5K7xcebev3y5dN/LiEB
   ChcGK1M/W0XEIVlJhrN7fSkPUNiyrLxAISA6m893WXQ0vPoqfPddjj2liEfZNqxda1YiV65sBuq/
   /z7s3Qsvv3wpEXbZLhbtW0SrsAfYdWIXLlykpsKzt/yP40t68v4oJcIiOSo5GVauhJEjzTrjG2+E
   6dOvfmyRIkqERXK5LDfQ2bYdbVnWB8BB4Ayw2LbtH7Md0a+/wocfwsKFEBwMt9yS7acU8aTft27n
   536vcPfODRSxkggcPIBSv/2W7tbqsYRjfLZ5MmNWT+TsqRKcWdWTwNuiSS72OyWSr6PT3UU1flQk
   p61ebRquq1aF1q1hxAho2lRNbyJ+LMtXhi3LKgE8CFQGygFFLMt6PMuRHD5s6rHatoVatWD/fvjk
   E/OGJeILtmwh7vHHKXlbQ4quz8sTidO5MSGKO75KIfLMOQBs2+bnyJ/p9MWjVP3wZj6Yso+AubMY
   lGcJNx48QfLYFTBlBac/3MLDbacQGRnl8Dcl4qPOnr36x+vXNw1xmzfDf/9raoGVCIv4teyMVmsJ
   HLBt+ySAZVlzgbuAGWkPfPPNNy/9OSgoiKCgoPTPVrq0uZ3cufNflgqIeLWzZ82q73HjIDqaH0rW
   4GnXdo5Q49Ih+/eP5KURb3HnoLJ8sno88acDObviCYJKjOfpgSVo1Qp69BjJ77+/AhSGQzdc+rrh
   wzXoXSRDUlLMiMLFi81jzx5TbhcY+NfjChVS8iuSi0RERBAREZGt58hOA90dwGdAI+A8MAVYb9v2
   mDTHqYFOcp/ffjMJ8PTp0LgxPPEEtGlDi1YhRESMNOuRy2yDfIlQfzoBt3xF2dMdObtiIAPbNuWJ
   gdZf6oBbtBhhvi6NFi1GsHRp+o+LyBX69zfTWSpWNKUPrVtD8+ZadiHihzy6gc627XWWZc0BNgPJ
   F/474W+/aPduGD3arJbt0yerpxZxRlKSmS06dizs3Glewxs2cGVWW758ABTdA/3uhWKHITUfRAyn
   xPpVvDuqPp0/uPrPZw16F8mG4GB46y3TCCcikknZ2kBn2/ZI4J8vW/38s2mKW7cOBg2Cdu2yc1oR
   z4qKMiPRJk829exPPAEPP5yunGdj9EaS2+yGyvUgbzJYADalE4+zdlmJvy1/DwnpxZo1I9INeg8J
   Geq+70vE29k27NsHixaZR9euJvFN6557PB+biOQantlAd/PNZmNc9+5QsKBbzyeSI1wuU3cYGgqr
   VpnX7sCBJhm+QmJSIrN2zCJ03Th+Px5Dvm0DsHY+zKlWD3CuSBTFk0uzrPdP1Lupzj+eUoPeRS7Y
   tg3Gj4fvv4dz5+D++82jZUsoWdLp6ETEi3l8A12GTmBZtp2aqpVZ4qiLiebhwy7Kl/+bRPPkSZgy
   xZRCFCsGQ4aYq1FpGm52xOxg/MbxTN8STqnEpsR89wRBFf7Nk0Py0KoVJCZrPbJIlq1da9Yet2kD
   detqzq+IZJj3JsNqoBMHZWjX/IYN5irwvHnQvj0MHmwa4yzr0orkmqVqsvjAYsauH8eOI/soEdmP
   2KX9GPBoJQYORIsxRDLqzBmzhGbXLnj+eaejEZFcxKMNdCK+YvjwsCsSYYDC7N8/krdeHcWUNjVh
   zBiIiTH17Hv2mDF/F8Sfj+eOiXew5889WJZFZftu4n56hhrJ7Rk6OJAun6phXSRDDhwwG0W/+w5W
   rIDbbze/eIqIOEzJsOR6hw+7uHJKQ1UOMIix9J8bCnH3wBtvmNuxefJcOiY5NZmv93zNOyveYfef
   u80HU/JS+/h/ePOjJjRo4OFvQsSX2TZ06gS33gq9e8OMGVCihNNRiYgASoYlB2S4Htch5csHYBFP
   G5YxhDE0Yj1hdOOtNv34cMHHfzn2j9g/mLRpEhM3TaJwUjXOrRlAYNVzpJbczS1lajNjWB2KakWy
   yNVFR5sm6bRNbpZlNr6JiHghJcOSLVerx12zJk09rpNOneLjyin8J29FYlKqMYahdGIa5au/w5LR
   ZmyZy3axeP9ixm0YR0TkMqrEP07i7B9oeEtdhgyBJnc/yq4/1Qwnko7LBZs2wTffmMf+/RAeDm3b
   Oh2ZiEiGqYFOsiU4eCTh4S+QdllEt24OrxHetg0+/RS+/BLatiW6U2de+upXoo/Yl8aWFS5TkMmb
   JzNh4wSs8yXJv20Qx5c+Rr8eRdQQJ/JP5syBoUOheHEzO75dO2jaNP36YxERD1IDnXhc2npcozDR
   0S7PB5OSYjbEffKJaYR74gnTrX7DDZQDxj7Qkm3HthF7PpbXNr3C93sWUSO5I2cWzKJqvkYMGQKd
   J6ohTiRDGjeGZcugZk2nIxERyRYlw5ItXrFGOCYGJk0ys4ErVzZXq9JsiPsj9g+afNaE6PhoAq38
   1I0JwZ4zllvblWDCRNPYLiIXpKaajaELF0JkJHzxRfpjKlb0fFwiIm6gTRiSLSEhvahefQQmIYbL
   a4R7uf/k69dDz55w882mVnHhQjOy6dFHLyXC6w+vp++CvtQeU5vo+CMAJKe4aF65Ob/vKsGkSUqE
   RQBT/zt/PvTpA+XKwYABZlnSM884HZmIiFupZliyzaNrhJOSYPZsUwpx9KhZjtG3L1x33aVDEpMS
   mbl9JuM2jONo3J9UOTGQHV8+gqtLR84U2kntsrVZ0Xt5hprhvH1ShkiOsW3o0QMaNTLzf6tWdToi
   kUv0XiwZpQ10knsdOwbjx8O4cXDLLaYUon37v8wG3hGzg3EbxjFj+wxqBDYjefUTHPrl3/TtE8DA
   gXDdjZlbkZyhzXUivsS2TXNp6dJw441ORyOSIXovlsxQMiy5z6ZN8PHHpgSiSxeTBNerd+nT51PO
   M3fXXMZtHMfu43uoc64fv83sT6XilRgyxHxJ/izOBfbaSRkimZGcbBrd5s+Hr782pQ/jx0OrVk5H
   JpIhei+WzNA0CckdUlJg3jz43/8gKgqGDIEPP7xUChF/Pp7F+xez8uBKwreHUyl/PQruGMr52Q9S
   7eFA3v88Z+qAvWpShkhWzJ0L/fqZiQ8PPmhmAdepY5ZgiPgIvReLuykZFu/x558wcSKEhpqpEE8/
   DQ89BHnNyzTVlcqcnXPo/3V/4pPiKWJdz41LF3H6cAO6DoIF+9IvvsoOr5iUIZIdzZqZsojy5Z2O
   RCTL9F4s7qYyCXHetm3mKvCcOebq1VNP/eXS7tGEo0zaNIkJGyeQn6Lsj92NbbmwXIF8WG8ZT3Vs
   QoAb3hNVpyZeb+9eU/6weTPMmOF0NCJuofdiyQzVDIvvcLng229h9GizGGPQIDPKqWxZAGzbJuL3
   CMZuGMuSA0toVLgL8UsHsXdtDQL6NedU3p3UKV2b5RmcCpFVHp2UIZIR69aZBHj+fDh92vwC+dBD
   0Lq1yh8k19J7sWSUkmHxfgkJEBZmmuKKFzczTB955NJc4FNnTzH116mM2zAOXHm4KW4wm8OCqVC6
   uNkQ1xmSrcxNhRDJVTp1MrO1H3oIGjbELbdFRER8lJJh8V4HD5rZwJMnQ1AQPPssNG1KfFIC22O2
   cz7lPNO2TmPurrncUbItrB/Euq+a0bmTxeDBl6smNGtS/MK5c+ZRooTTkYiI+BRNkxDvs3q1KYX4
   8UezLW7DhkvD/I8lHKPhxIYcijtEYEAg9xceRoV5e4g8WYZBg2DWe39tiLta3diaNaobk1wiLg6+
   +85MUvnhB3jnHXjiCaejEhHJ9XRlWHJecrIZ6fTRR3D8uGmI690bihUDYNfxXYzbMI4pW6aQkJSA
   jQ2pgTTbu4zXezWhVaur3/nVrEnJlbZuhddeM7OAmzeHhx+GDh2gTBmnIxMR8Tm6MizOOnXKcGUN
   TwAAH5tJREFUjEb79FOoVg1eeeXSlrik1CTm7/iSsRvGsuv4LpoX6UvdtatZV7Eb9nU7uen62nw3
   rA5F/2ZBhmZNSq5UsiR06wbh4aaOXkREPErJsGTfvn2mFGLGDGjXznS5XyjyPRh7kAkbJ/DZ5s+o
   VuxmKh0bxP7PHubQDfkYMgQWtF/O/viMNcNp1qT4rKgoUwLxxBPpJz5UrAhduzoTl4iIKBmWLLJt
   WLkSPvgAVqyAgQNhxw648UZctovF+xYRuj6UlX+s5N7S3Wi44ydWzKvNLZ1g/ldXjhEuSuniTTJ0
   ypCQXqxZMyLdrMmQkKHu+R5FsmPfPvjqK/M4cMCMQEtIgKKagCIi4k1UMyyZk5Jifrh/8IGZcfrs
   s9CjB/F5XSw/uJyN0RsJ+zWMooHF+VfSILZMf5yzsYUZPBh69cr+hjjNmhSf0KsXLFpk6n87dYJ7
   7oHAQKejEhHJ9TRaTdwnLg4mTTLzgStXhuefh/btsS2LHw/8yCNzHuH0udMUCyxJy5NziAhrQbOm
   ZizatRriNCZNcq3oaLNAJk8epyMREfEraqCTbLlqcprHMquSp0wxG67mzIFGjYg/H0/4pgmM3TCW
   k2dOEncuDoC4cwkUzleIjRssqlT5+3NpTJr4JNuG7dth9mxT8vDii+mPKVfO83GJiEiWqPNIgMvJ
   aXj4C0REjGR3+L1s/9e/Sa1f3xyweTPMnMn2ygUZ8u0QKo+uzNc7F9Pgz/exx2ynQFw98hBIvRtq
   M2ZEnb9NhAGGDw+7IhEGKMz+/SMZPjzMfd+kSFbZNmzbBm+8AbVrm0bRxES47z6nIxMRkWzSlWEB
   THJ6YP8I2vMTL/A+lTjIxwmDWPjIaT59503m7prL2CnB7Du5jzZl+hO0ays/v1OBTp1g4WyoWWd5
   plYka0ya+JRjx8zs344dzTrxO+5IPxVCRER8kpJhgXPnqL9+A8O4g5h8BXirzMP8HDMUV6FYKhUJ
   ptLoStxyXV3qJDxF/IwHWRYXyKBB8NlHVzbEFaVJhYxNhQCNSRMvdbG/IW2ie8MNZiKEEmARkVxH
   DXT+7ORJGDsWPv2ULQFFefLEKFb2eQtK74DkwuDKQ9X4f9G84Di+nVqLu+6CIUOu3RCXGVerGa5e
   XTXD4pBdu2DWLPMYPx7uvtvpiEREJAvUQCcZExlplmRMn25mn/74IykB59ka0gfKbgULIJF8X35G
   3IlgyvXPw4YN/GMdcGZUrVqZJUuGMnz4+1eMSVMiLB4UFWW2vs2aBSdOQJcuMHkyNG7sdGQiIuJB
   ujLsTzZuhPfegx9/hH79sJ98ktX2QcZuGMs3e76hSckglu5ZT1LBGPKcqkFIte94dnAVChRwOnAR
   NwgPh1Wr4NFHoVmz7N/uEBERx2nOsKRn22b4/3vvmY1YzzxDQo/HmBH1DaHrQ0lMTqTN9YM48n0v
   fvy6FO07xXPvYzvo1DxjjXAiXi8xEQqnbdYUEZHcSMmwXJaUBDNnmiQ4b1548UV2tqjL2C2TCN8W
   TrMK91Dj1GB+nnwf8XEBlzbElSrldOAiOeD4cTMTe9YsswDjt9/U/CYi4geUDAvEx8PEifDRR8TX
   qcHmfu2IrH4dYVunsvvEbjpW7s/5Vf2ZN7UiTZvmXEOciFcIDze18GvWQJs2pgTi/vtRrY+IiH9Q
   A50/O3bMbIobPx5atmT356MJWj+EYzsiKLynMP1uDCXP4q7M3hxI376mfDgnG+JEvMLeveYWx1df
   qTRCREQyRFeGfd3+/fD++zBrFq6uj/FT1yaEHp7HTwd+IjEpERcuSA2k9rplvNKtCV266CKZ+LiU
   FIiLU02PiIikk5Urw7o57iGRkVEEB4+kRYsRBAePJDIyKntPuHEjPPIINGnCqesL89GsZ6hV60de
   3P4hN1ltaLnrN4ipR4ArkJola7NmQR26d1ciLD7K5YKVK+HJJ6F8efjkE6cjEhGRXEJXhj0gxxZM
   2LYZi/bf/8KePWx8qjOhVU8wd9/X3F+tHZVjBrNoUhMS4i0GD4ZOj8dzJCXjK5JFvM7x4/DBB6YZ
   tEgR6NoVHnsMatRwOjIREfFCaqDzUsHBIwkPf4G0q4e7dXufzz8f8c9PkJJiOuPffZezKeeYNbAp
   oYFbOH72BJ0qP0H8sj7MmVpaDXGS+5w6Be++a5LgevU0EUJERP6WGui81OHDLv6aCAMUJjra9fdf
   eO4cTJ1K/IfvsKhufpb3q8HMxLU0KhHNv1PfZM2c+5m2JY8a4sT3nTxprvzmy/fXj5csCaNGOROT
   iIj4BSXDHlC+fACQSNorw+XKXePybVwcjBtH6scfMfveG+nf/RgJqWe5Lv4k3VKWMv+1epwqB4MH
   Q5eFqgMWH3X2LHzzDXz+OUREmBKgRo2cjkpERPyMbqZ7QEhIL6pXH4FJiOFizXBISK+/Hnj8OLz+
   OsfqVuU/f8yg2tMWIxokkpB8HoA/E06zY28M8+bB6tWoIU5806ZN0Ls3lCsHEybAww/DH38oERYR
   EUf4dc1wZGQUw4eHcfiwi/LlAwgJ6ZW5hrYsnCs62kW5cmnOFRWF/cH7rFw6ldB2Zfm+eAwP1XqE
   Iru6Mn5UeZKDH4Hrd8GJWlT9OYifvn/ebXGKuN3ixbB9u2mEK1fO6WhERCQXUQNdJuTYhIfs2LmT
   hHffJjxyAaFBhTlbsiidqw3lVERPZk8rScGCuzl0qArkS4YyOyCmDiQFZLzxTsRJcXFQrJjTUYiI
   iB/x+Jxhy7KKW5Y127KsXZZl7bAsq3F2ns+Thg8PuyIRBijM/v0jGT48zG3njD8fz+o/VhO/6md2
   PnYfQ4c3pFLV+Szqdy+das6g8nd7mdTvGUrkL8mGDVCjxkygACQVhUNNzH8z0ngn4pSEBJg2DVq2
   hLp1zSQUERERL5bdBrqPge9s2+5iWVZeoFAOxOQRWZ7wkEXx5+Jo9smt7EiIpECqReFbihD8r6fp
   t3Mws16vyNFyZixa5ysa4jLdeCfilJ9+gilTTENc8+YwcCC0bw951aMrIiLeLctZlWVZRYHmtm1P
   AbBtO8W27bgci8zNLieaV3JDomnbHP4qjGeerM7WxEhSA+BsYAD/+uNbJvcZxZ8HKl5qiAsO/mtD
   XIYb70Sc9ssv0Lgx7N0LX3+N9n6LiIivyHLNsGVZ9YEJwE6gPrABeNq27bNpjvPLmmE7JYWIaW8R
   uvp//FgmgYeuu4fvzxziWFIk+WJrM6LScp7oXZRSpf45zms23ol4msuljS4iIuK1PNpAZ1lWA2AN
   cKdt2xssyxoNxNq2PSLNcfaIEZc/FBQURFBQUJbOmdPckWjGxZ9g2uSnCY2ag5UnD4+X78Xh30cx
   a3pxGjePp1W3HfRpV4fiBbUeWXzEuXOwYAFMnWqWYISHOx2RiIgIABEREURERFz6+8iRIz2aDJcF
   Vtu2Xe3C35sBL9u23T7NcV55ZTinbTu4ntAZz/FF3EpaxpXm7rKvsnDZU/z6awB9+5oSSk9uiPPk
   2DjJhWwb1qwxCfDs2XD77dCzp5kJXDhtrb2IiIh38Og6Ztu2j1mW9YdlWTfZtr0HuA9TMuEX4s/H
   s/noZvZHb2fKj++zPz6KPidr8kb+hYz+ph2HLjbEdfZ86eTVSkDWrPHw2DjxbefOwdNPw0MPwZYt
   ULGi0xGJiIi4RbbmDF+oG54EBAIHgN62bcemOSbXXRnefWI390y+m5gzxymcDP+NbExU3BgmrmxA
   p05mTfLttzsXX3DwSMLDXyDtFArNJxYREZHczKNXhgFs2/4V8IsdqrZtszRyKaErPmLJgSUk2kkQ
   AGfy5OWdyNE826UBB6abkkqneXpsnPgg24blyyEsDP79b3j0UacjEhERcYSGgP6D2HOxTPt1GqFr
   /keeP08xKOIsj8Z3pHuTzSSV3k+hs+X4ZkpR6tdyOtLLNJ9YrunQIVMHHBYG+fJB795wzz1ORyUi
   IuIYv13H/E+2HdvGmPVjmLVtJq3jyjBg/lFOn+nDiLjnOcxeTp+pC2UiIaYK1Su+71X1uF6xalq8
   z9q10KYNPPII9OkDjRqBlak7SSIiIl7No6PVMnwCH0qGk1KTmLtrLqHrQzlwYi+9/yhP75n7+eH8
   AL6u+RyPP1uWb799my++eBZvr8fVfGJJJzUVkpKgYEGnIxEREXELj9cM5wbx5+NZGrmUlQdXMn3b
   dG4pVJleKwry0LwkPnO14ePOz9DzuesYdKEh7rPPkvGFetyqVSt7VXIuHnL8uJkDHBwM11//18/l
   yaNEWEREJA2/TYZt2+bbvd/SbW434s7HcV1gCcZH3EGLnzczrdhQvnh9Hv0GlUjXEKd6XPE6KSmw
   aBFMngxLl0KHDtCxo9NRiYiI+AS/S4bjzseZhrj1oZxLOUfC+QTz8bOn2XK2BsW/nMNTDxa95sbZ
   kJBerFkzIl09bkjIUE99CyKXzZsHTz5p5gD37QtTpkDx4k5HJSIi4jP8pmZ4R8wOxqwfwxfbv+C+
   qi1pGtWaOqPn8UyHxewp7aJmqTqsHbSSovn/eU2y6nHFa+zbZxZk1K3rdCQiIiKOUwNdGsmpyczf
   PZ8x68ew5889dKs1gBt/aEK9SaHcmrKR3x99iSrvd2V/8gHqlK6ToURYxBH790P16k5HISIi4tVy
   RTJ88arr4cMuypfP+FXX+PPxbI/ZTt0ydYlPimfixolM2DSBGiVr0LL4EM5NqsjdS/6PRvm2kDjk
   ZSq+1d/ze5JFMiM2FmbOhEmT4MQJ2LEDCqdt3hQREZGLfD4Zzup83Pjz8TSb0oydMTspnM8kC51r
   daXCkcHs/+gMfQ+PpEHgNvIMe4VCQ/sqCRbvtmYNjB0LCxZAq1amFrhVKzMNQkRERK7J55Ph4OCR
   hIe/QGZm+CYkJfDWL2/x3qr3AAggDw/GLyJxQmFGFRjJLewk/4hXCejXB/Lnz+Z3I+IBo0ebmcDd
   u0OZMk5HIyIi4jN8fs7w4cMuMjrDd/eJ3YSuDyV8Wzh3VriLsvmqEXP2Dwr/WYnhi/9DvaL7yfvG
   a9BrgZJg8S3PPON0BCIiIn7Dq5Lhf5rhm+JK4Zs93zBm/Ri2HttK15v70Td5M7NerUSbkkvoVGwY
   zaOPUfzlrtCzJ+TL58S3IfL3YmIgLAw2bIAvv3Q6GhEREb/mVWUS16oZnrmwK0v+/IFxG8ZRoVgF
   WpUYwp75nVn0TX5ebLaaJ4+PoNixvTBsmEmCAwPd+j2JZJrLZRZiTJgAixebpRgDBkDjxmBl6m6O
   iIiIXIPP1wyDSYhfeWM8e+OPUqp0CkXvTiAi+mc61OhIxaND+HbS7SQkwMi2a+m8fQT59u2C11/X
   lWDxbq1bmyvCAwfC449rMYaIiIgb5IpkOCYhhgYTG3Ao7hD5AvIxuM4bnFsxiC+nlqJpU3i15Xqa
   LHoTa/s2eO016NNHSbB4v+PH4frrdRVYRETEjbKSDF9j6bDnRZ6K5KUlL3HTpzdxOO4wAMnJNmEj
   7qNE/lJsC9vIQrs9d777MFa7B2DvXnjiCSXC4j1OnIC1a6/+udKllQiLiIh4IUeTYZftYtG+RbSf
   2Z5GExuRkOiie8ov5P3zX5AaSMWCtdk7NoVROx+k3BMdzK3mfftg8GBNiBDvYNuwYgUEB0ONGrBw
   odMRiYiISCY4UiZx6uwpwraEEbohlCL5itCm1FAOLHyMH74pRKdO0HNAPIGJ86nz6SyKrt4EL79s
   mo0KFrzqObK6tU4ky1wusxhj3DhISjJ3KXr2hFKlnI5MRETEb3ltzXC3bm8SEtKLuIKnGbN+DLN3
   zqZ11bZUPT6ERZPuJDHBYtAg6N0bSkbvgBEjYOVKeOkl03BUqNA1nz+rW+tEsu3VV81muBYtVAIh
   IiLiBbw2Gab+WArc9TYlq7p4pPpgzqzoz9xpZbnrLhgyxOQTAfv2wJtvwk8/wQsvmFKIwmkXcKSX
   la11IiIiIpL7eO8GurYvcO6b/+Ga35QZKTfTt6/ZN1ClCnDgAPR5C7791mzeGj8eihbN8FNnZmud
   SKbs3WtKIUqUgDfecDoaERERcQPPNNDlSYJTtSlVYjsHD8KoUVAlzx+mBKJRI6hUySQew4ZlKhGG
   K7fWXeny1jqRTElNhQUL4N//hmbNTKNmjx5ORyUiIiJu4pmM8URtiKnC7bdvp8CpIzB0KNSvDyVL
   wp498NZb5upbFoSE9KJ69RFcTohNzXBISK+ciV38x5kzULMmvPMOdO8OUVEXfnOr4nRkIiIi4iae
   qRnOd4RG5d5iScsUin81B3r1MhMiypbNkXNcnCYRHe2iXDlNk5Bs2LfPjEgTERERn+O1DXQL6jTj
   gcPbydOtm9kaV66cW88p8rfOnIG4OLjhBqcjERERkRzktRvoOtxZizxbtsCnnyoRFufs2wfPPQcV
   K8KMGU5HIyIiIl7AkaUbIh7jcsGSJfDJJ2ZVcp8+ZkFG1apORyYiIiI5zGvLJJQMi2NOnoQHHoD+
   /aFr12tuMRQRERHfp2RYRERERPyW19YMi7iVywXffQdr1jgdiYiIiPgYJcPiu2Jj4eOP4eab4fXX
   zYQIERERkUxQMiy+5+RJePJJ0wS3ahWEhcHGjdC6tdORiYiIiI/J63QAIplWqBCUKQPbtkH58k5H
   IyIiIj5MDXQiIiIikiuogU5yj+hoGD4cvvzS6UhEREQkF1MyLN5l40bo3h3q1oVTp+D2252OSERE
   RHIxlUmIdzh2DDp3hoMHYehQ6NsXSpZ0OioRERHxIVq6Ib7L5YJvvoG2bSGv+jpFREQk85QMi4iI
   iIjfUgOdeLcNG6BrV/jgA6cjEREREQGUDIu7uVywcCHccw907AgNG0K/fk5HJSIiIgJo6Ya406lT
   0KQJFCsGzz8PnTpBYKDTUYmIiIhcopphca9Nm+C228DKVPmOiIiISKapgU6c43JBgKpuRERExDlq
   oBPPsm1YsQI6dIBhw5yORkRERCTTVDMsmXexKe7ddyEmxtQD9+rldFQiIiIimZbtZNiyrABgA3DI
   tu0O2Q9JvNq5c9CgARQqBC+/DA8/DHnyOB2ViIiISJbkxJXhp4GdQLEceC7xdgUKwKxZUKeOmuJE
   RETE52WrZtiyrApAW2BSzoQjXuVajY916yoRFhERkVwhuw10HwEvAhoXkZvs2GFqgPv3dzoSERER
   EbfKcpmEZVkPAMds295iWVYQcM1LhW+++ealPwcFBREUFJTV04o7rV4No0bBunUwdCgMGuR0RCIi
   IiLXFBERQURERLaeI8tzhi3L+g8QDKQABYGiwFzbtnukOU5zhr2dbUO7drBzJ7z4IvTuDQULOh2V
   iIiISKY4tnTDsqx7gOevNk1CybCPWL8ebr1V65JFRETEZ2UlGdacYTEaNXI6AhERERGP0zpmf5GY
   CJMmwYYNMH2609GIiIiI5DitY5b0Tp2CkBCoVg2WLYOnnnI6IhERERGvoWQ4Nxs1CqpXh/37ISIC
   vvpK5RAiIiIiV1DNcG7WoAFs3gyVKzsdiYiIiIhXUs2wiIiIiOQKqhn2R3v2wGuvgcvldCQiIiIi
   PkfJsK/avh0efxyaNoUCBSA52emIRERERHyOkmFfs3UrdOoELVtC/fpw4AC88Qbkz+90ZCIiIiI+
   Rw10vua336B5c5g2DQoXdjoaEREREZ+mBjoRERERyRXUQJebrF4N5887HYWIiIhIrqZk2NusWgWt
   W0PXrmZZhoiIiIi4jZJhb3ExCX78cejSxYxMq13b6ahEREREcjU10HmDVatMEjxsGPTsCfnyOR2R
   iIiIiF9QA503sG0zJ1hJsIiIiEiWqYHOF1xtU5xlKREWERERcYCSYU9Ztw7uvx8++MDpSERERETk
   AiXD7rZlC3ToYLbGPfQQPP200xGJiIiIyAVqoHOXpCQIDobly+GVV+DLL6FAAaejEhEREZErqIHO
   nb78Eh54QGuTRURERDwgKw10SoZFREREJFfQNAknREfD7NlORyEiIiIiWaBkOKtiYuD556FuXdi8
   2eloRERERCQLlAxnVmwsDB8Ot9ximuS2b4f//MfpqEREREQkCzRNIrOGDYOEBNi4EapUcToaERER
   EckGNdBllssFAbqgLiIiIuJt1ECXk66VwCsRFhEREck1lNmlZduwaBE0agS7djkdjYiIiIi4kWqG
   r7R6Nbz6Khw9Cm+/DbVqOR2RiIiIiLiRkmGAqCh46ikzIm3ECOjZE/Lqf42IiIhIbqeMD6BgQQgK
   glmzoEABp6MREREREQ/RNAkRERERyRU0TeKfnDsHBw86HYWIiIiIeAn/SIZdLpg+3TTETZjgdDQi
   IiIi4iVyf83w4sXw0kumLvjzz6FZM6cjEhEREREvkbuT4W7dYMMGGDUKHn4YrEyVkIiIiIhILpe7
   G+i2b4ebb4bAQGfOLyIiIiIek5UGutydDIuIiIiI3/DPaRJJSTB5MqSmOh2JiIiIiPgY302GbRvm
   zoXatWHOHDh92umIRERERMTH+GYD3fr18PzzJgEeOxZatXI6IhERERHxQb53ZXjZMnjwQejRAzZv
   ViIsIiIiIlnmew10LhckJkLRojn3nCIiIiLi8zRNQkRERET8Vu6aJvHDDzBzptNRiIiIiEgu5n3J
   8K5d0KYNDB0KxYs7HY2IiIiI5GLekwyfOgXPPAN33w2tW5vtcW3bOh2ViIiIiORi3jNarW9fKFsW
   du6E0qWdjkZERERE/ECWG+gsy6oATANuAFKBibZt/+8qx2WsgS45GQIDsxSLiIiIiIhHp0lYlnUD
   cINt21ssyyoCbAQetG17d5rjNE1CRERERNzOo9MkbNs+atv2lgt/TgB2AeX/9ovi42H4cDhyJKun
   FRERERHJMTnSQGdZVhXgVmDtVQ9wuWDqVKhVC6KiIMB7+vZERERExH9lu4HuQonEHODpC1eI03mz
   YkWwLGjThqDgYILKls3uaUVERETEz0VERBAREZGt58jWBjrLsvIC3wDf27b98TWOse1p06BbN10R
   FhERERG38fg6ZsuypgEnbNt+7m+OUQOdiIiIiLidp6dJNAWWAdsA+8LjNdu2F6U5TsmwiIiIiLid
   x68MZ+gESoZFRERExAM8OlpNRERERMTXKRkWEREREb+lZFhERERE/JaSYRERERHxW0qGRURERMRv
   KRkWEREREb+lZFhERERE/JaSYRERERHxW0qGRURERMRvKRkWEREREb+lZFhERERE/JaSYRERERHx
   W0qGRURERMRvKRkWEREREb+lZFhERERE/JaSYRERERHxW0qGRURERMRvKRkWEREREb+lZFhERERE
   /JaSYRERERHxW0qGRURERMRvKRkWEREREb+lZFhERERE/JaSYRERERHxW0qGRURERMRvKRkWERER
   Eb+lZFhERERE/JaSYRERERHxW0qGRURERMRvKRkWEREREb+lZFhERERE/JaSYRERERHxW0qGRURE
   RMRvKRkWEREREb+lZFhERERE/JaSYRERERHxW0qGRURERMRvKRkWEREREb+lZFhERERE/JaSYRER
   ERHxW0qGRURERMRvKRkWEREREb+lZFhERERE/JaSYRERERHxW0qGRURERMRvKRkWEREREb+lZFhE
   RERE/Fa2kmHLsu63LGu3ZVl7LMt6OaeCEvGEiIgIp0MQuSa9PsVb6bUpuU2Wk2HLsgKAT4F/A3WA
   rpZl1cqpwETcTW/o4s30+hRvpdem5DbZuTJ8B7DXtu0o27aTgS+AB3MmLBERERER98tOMlwe+OOK
   vx+68DEREREREZ9g2badtS+0rM5Aa9u2B1z4ezDQyLbtp9Mcl7UTiIiIiIhkkm3bVmaOz5uNcx0C
   Kl3x9wpAdHYDEhERERHxlOyUSawHaliWVdmyrHzAY8DCnAlLRERERMT9snxl2LbtVMuyngQWY5Lq
   z2zb3pVjkYmIiIiIuFmWa4ZFRERERHyd2zbQaSGHeDPLsn63LOtXy7I2W5a1zul4xL9ZlvWZZVnH
   LMvaesXHSlqWtdiyrN8sy/rBsqziTsYo/ukar80RlmUdsixr04XH/U7GKP7JsqwKlmUttSxrp2VZ
   2yzLeurCxzP93umWZFgLOcQHuIAg27Zvs237DqeDEb83BfN+eaVXgB9t274ZWAq86vGoRK7+2gT4
   0Lbt2y88Fnk6KBEgBXjOtu3awJ3AkAu5ZqbfO911ZVgLOcTbWbjxzohIZti2vQI4lebDDwJTL/x5
   KvCQR4MS4ZqvTTDvoSKOsW37qG3bWy78OQHYhZlslun3TnclA1rIId7OBn6wLGu9ZVn9nQ5G5CrK
   2LZ9DMybPlDa4XhErjTEsqwtlmVNUgmPOM2yrCrArcAaoGxm3zvdlQxf7TdGdeqJN7nLtu2GQFvM
   m3ozpwMSEfERoUB127ZvBY4CHzocj/gxy7KKAHOApy9cIc50vumuZDhDCzlEnHLht0Vs2z4OzMOU
   9oh4k2OWZZUFsCzrBiDG4XhEAPO+aV8eRTURaORkPOK/LMvKi0mEp9u2veDChzP93umuZFgLOcRr
   WZZV6MJvkliWVRhoDWx3NioRLP56V20h0OvCn3sCC9J+gYiH/OW1eSHBuKgjev8U50wGdtq2/fEV
   H8v0e6fb5gxfGLXyMZcXcrzjlhOJZJJlWVUxV4NtzOKZcL0+xUmWZc0AgoDrgGPACGA+MBuoCBwE
   uti2fdqpGMU/XeO12QJTn+kCfgcGXqzRFPEUy7KaAsuAbZif5zbwGrAO+JJMvHdq6YaIiIiI+C2N
   lhIRERERv6VkWERERET8lpJhEREREfFbSoZFRERExG8pGRYRERERv6VkWERERET8lpJhEREREfFb
   /w/sf5H763QZcAAAAABJRU5ErkJggg==
   "
   >
   </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="example-2-linear-function-with-linear-truth">Example 2: linear function with linear truth</h3>
   <p>Fit a new OLS model using only the linear term and the constant:</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">X2</span> <span class="o">=</span> <span class="n">X</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">res2</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">y2</span><span class="p">,</span> <span class="n">X2</span><span class="p">)</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">res2</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="n">res2</span><span class="o">.</span><span class="n">bse</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>
   [ 5.64747354  0.38270693]
   [ 0.38670553  0.03332011]
   
   </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>Estimate RLM:</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="n">resrlm2</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">RLM</span><span class="p">(</span><span class="n">y2</span><span class="p">,</span> <span class="n">X2</span><span class="p">)</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">resrlm2</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="n">resrlm2</span><span class="o">.</span><span class="n">bse</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>
   [ 5.14466458  0.47513088]
   [ 0.10270075  0.00884911]
   
   </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>Draw a plot to compare OLS estimates to the robust estimates:</p>
   </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">prstd</span><span class="p">,</span> <span class="n">iv_l</span><span class="p">,</span> <span class="n">iv_u</span> <span class="o">=</span> <span class="n">wls_prediction_std</span><span class="p">(</span><span class="n">res2</span><span class="p">)</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">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">8</span><span class="p">,</span><span class="mi">6</span><span class="p">))</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">y2</span><span class="p">,</span> <span class="s1">&#39;o&#39;</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">&quot;data&quot;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">y_true2</span><span class="p">,</span> <span class="s1">&#39;b-&#39;</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">&quot;True&quot;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">res2</span><span class="o">.</span><span class="n">fittedvalues</span><span class="p">,</span> <span class="s1">&#39;r-&#39;</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">&quot;OLS&quot;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">iv_u</span><span class="p">,</span> <span class="s1">&#39;r--&#39;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">iv_l</span><span class="p">,</span> <span class="s1">&#39;r--&#39;</span><span class="p">)</span>
   <span class="n">ax</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">resrlm2</span><span class="o">.</span><span class="n">fittedvalues</span><span class="p">,</span> <span class="s1">&#39;g.-&#39;</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">&quot;RLM&quot;</span><span class="p">)</span>
   <span class="n">legend</span> <span class="o">=</span> <span class="n">ax</span><span class="o">.</span><span class="n">legend</span><span class="p">(</span><span class="n">loc</span><span class="o">=</span><span class="s2">&quot;best&quot;</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,iVBORw0KGgoAAAANSUhEUgAAAeMAAAFwCAYAAACLhRPVAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzs3XdclWUbwPHfw3CDGw0HIjlRKzVnFqiZmaaWucDXUWll
   rrYVjqheLSXLN7XhqEAsy7JMc5Q4UrTcSI5YDlBRRA+oIJz7/eOWpaDsc4Dr+/nwUc45z/Pc53g8
   17nXdRlKKYQQQghhOTaWboAQQghR1kkwFkIIISxMgrEQQghhYRKMhRBCCAuTYCyEEEJYmARjIYQQ
   wsLuGIwNw1hsGMZZwzAOZrrtHsMwdhqGsc8wjN2GYbQv2mYKIYQQpVduesZLgUduuu0DYLpS6j5g
   OvBhYTdMCCGEKCvuGIyVUtuBizfdbAaq3vh7NeB0IbdLCCGEKDPs8nncFGC9YRhzAQPoUnhNEkII
   IcqW/C7geh6YpJRqiA7MSwqvSUIIIUTZYuQmN7VhGC7AL0qpNjd+j1dKVct0/yWlVNUcjpXk10II
   IcoUpZSRl8fndpjauPGT5rRhGA8ppbYYhtEDOHaHRuWlTcKKzJgxgxkzZli6GSIf5N+uZJN/v5LL
   MPIUh4FcBGPDMJYDHkBNwzBOoFdPPwt8YhiGLXANGJvnKwshhBACyEUwVkoNz+Eu2VsshBBCFALJ
   wCVuy8PDw9JNEPkk/3Ylm/z7lS25WsBVoAsYhpI5YyGEEGWFYRhFtoCr0DVq1IioqChLXd6qubi4
   EBkZaelmCCGEKCYW6xnf+OZQpNcuqeS1EUKIkis/PWOZMxZCCCEsTIKxEEIIYWESjIUQQggLk2Cc
   S6NHj2batGmWboYQQohSSIJxIfP09GTJEqmbIYQQIvckGAshhBAWZnXBOCIiCm/vmXh6TsfbeyYR
   EXnfi1wY59i3bx/t2rWjatWqDB06lGvXrgEQHx9Pv379cHJyombNmvTr14/o6GgA3n77bbZt28aL
   L76Io6MjEydOBGDy5Mk0bNiQqlWrcv/997N9+/Y8t0cIIUQpppQq0h99iVtld3t4eKRyc3tZQYIC
   pSBBubm9rMLDI7M9R3YK4xzJycnKxcVFffzxxyolJUV9//33yt7eXvn4+Ki4uDi1atUqde3aNZWQ
   kKAGDx6sBgwYkH6sh4eHWrx4cZbzBQQEqIsXL6rU1FTl5+en6tatq5KSknK8fk6vmRBCCOt34zM8
   b7Eyrwfk+QJ5CMZeXjMyBVGVHky9vGbk+kUojHNs3bpV1atXL8ttXbp0UT4+Prc8dt++fapGjRrp
   v2cXjG9WvXp1dfDgwRzvl2AshBAlV36CsVUNU58+bQYq33RrZaKjzcV6jujoaOrVq5flNhcXFwCu
   Xr3KuHHjaNSoEdWqVeOhhx4iPj7+thmz5s6dS8uWLalevTrVq1fn8uXLnD9/PtftEUIIUbpZVTCu
   V88GSLzp1kScnXPfzMI4x1133cXp06ez3HbixAlAB9bjx4/z119/ER8fz9atWwHSg/HNRaW3b9/O
   Bx98wPfff8/Fixe5ePEijo6Oku5SCCFEOqsKxr6+o3Bzm05GME3EzW06vr6jivUcnTt3xs7Ojvnz
   55OamsqqVavYvXs3ACaTiYoVK+Lo6EhcXBwzZszIcmydOnUIDw9P/91kMmFvb0/NmjVJTk7mnXfe
   wWQy5botQgghSj+rCsauri5s3DgBL685eHpOx8trDhs3TsDV1aVYz2Fvb8+qVatYunQpNWrUYOXK
   lTz55JMATJkyhStXrlCrVi26dOlCnz59shw7adIkVq5cSc2aNZk8eTK9e/emd+/eNG3aFFdXVypV
   qkSDBg1y3RYhhBCln1RtskLy2gghRMklVZuEEEKIEkiCsRBCCGFhEoyFEEIIC5NgLIQQQliYBGMh
   hBDCwiQYCyGEEBYmwVgIIYSwMAnGQgghhIVJMBZCCCEsTILxTRwcHHB0dMTR0RFbW1sqVaqUfltg
   YKClmyeEEKIUknSYt9G4cWMWL16Mp6dnjo9JTU3F1ta2UK9bEl4bIYQQ2ZN0mIUsrehzZj4+Pgwd
   OpThw4dTtWpVAgICGDFiBO+88076Y37//XdcXV3Tfz99+jRPPPEETk5OuLm5sWDBgmJ7DkIIIayf
   BON8+Omnn/D29ubSpUsMHjw428ek1TU2m8307duXjh07EhMTw8aNG5kzZw6bN28uziYLIYSwYhKM
   8+GBBx5IL51YoUKF2z52586dmEwmXn/9dWxtbWncuDFjxoxhxYoVxdFUIYQQJYCdpRuQEyNPo+05
   K4qp17zUIz5x4gRRUVHUqFHjRnsUZrP5tvPQQgghypY7BmPDMBYDfYGzSqk2mW6fAIwHrgO/KqXe
   KMyGWfP6JeOmbwqVK1fmypUr6b/HxMSk/71BgwY0bdqUw4cPF1v7hBBCWMDx4+Dvn69DczNMvRR4
   JPMNhmF4AP2AVkqp1sCcfF29lLj33nv59ddfiY+PJyYmhvnz56ff17lzZ8qVK4efnx9JSUmkpqYS
   EhLC3r17LdhiIYQQhSI+Hj7/HLp0gW7dwGTK12nuGIyVUtuBizfd/DwwSymVcuMx5/N1dSt3cw84
   J6NGjaJ58+a4uLjQp08fhg0bln6fra0ta9euZffu3TRq1AgnJyeee+45TPn8BxNCCGEl5s2DRo1g
   wwZ48004eRL8/PJ1qlztMzYMwwX4JW2Y2jCMfcBqoDdwFXhVKfV3DseW2H3GliKvjRBClADh4VC1
   KtSsmeXm4txnbAdUU0p1Al4DvsvneYQQQgjrFRcHv/2W/X2NG98SiPMrv6upTwKrAJRSfxmGYTYM
   o6ZS6kJ2D54xY0b63z08PPDw8MjnZYUQQogidv06rF8Py5bBxo0wcCA88kiO23yCgoIICgoq0CVz
   O0zdCD1M3frG72OBekqp6YZhNAU2KqVccjhWhqnzSF4bIYSwkGnT9IIsNzcYORIGD4Zq1fJ0ivwM
   U+dma9NywAOoaRjGCWA6sARYahjGISAJ+E+eWiqEEEJYo3vuga1boWnTYr2sFIqwQvLaCCFEEUpK
   gvPnoV69Ijm9FIoQQgghsqMU/PUXvPgi1K8Pn3xi6RZlYbXpMIUQQogCS0yETz+Fr76Ca9f0PPDu
   3ZCpsp41kGAshBCi9LK318k4Fi2CBx4ovMIHhUzmjK2QvDZCCJFHSkFKig6+FiZzxoVs2bJltGnT
   hsqVK+Ps7MwLL7zApUuXAJg5cyYjRozI9rjt27fTtWtXqlWrRq1atejWrRt79uwpzqYLIUTZEBkJ
   77wDTZpACS5NK8E4B3PnzmXq1KnMnTuXy5cvExwcTFRUFL169SIlJQXIPne1yWSiX79+TJo0iYsX
   L3L69GmmT59O+fLli/spCCFE6WQywdKl4OEB7dvDuXMQGAje3pZuWb7JMHU2TCYTzs7OLFu2jCef
   fDL99sTERNzc3Jg1axZRUVGEhYXx9ddfZzl2z549PPzww8TFxeX7+tb82gghhMVt2aILMowcCY89
   BlbW2ZFh6kKyY8cOkpKSGDhwYJbbK1euTO/evdm4cWOOxzZt2hRbW1tGjRrFb7/9Rnx8fFE3Vwgh
   ypaHHoLVq+GJJ6wuEOeXBONsnD9/nlq1amFjc+vLc9ddd3H+fM4VIx0cHNi+fTs2NjaMHTsWJycn
   +vfvT2xsbFE2WQghSo8LF2DBAujcGU6ftnRrioX1BmPDKJyffKhVqxbnz5/HbDbfcl9MTAy1atW6
   7fHNmjVjyZIlnDhxgpCQEKKjo5k8eXK+2iKEEGXC9evw88/w5JO6GtLWreDjA3XqWLplxcJ6g7FS
   hfOTD507d6Z8+fKsWrUqy+2JiYmsW7eOHj165PpcTZs2ZdSoUYSEhOSrLUIIUSa8/TZ88AH07g1R
   UXpldJ8+YFdy0mFERETh7T0zX8dabzC2IEdHR6ZNm8aECRNYv349KSkpREZGMnjwYBo2bJi+pSk1
   NZWkpKT0n+TkZI4ePYqfnx+nbwytnDx5ksDAQDp37mzJpySEENbt/fdh+3Z49tk8V0myBhERUTz8
   8HwCAl7J1/ESjHPw6quv8v777/PKK69QtWpVOnfujIuLC5s2bcL+xqbyFStWUKlSJSpVqkTFihW5
   ++67cXR0ZNeuXXTs2BEHBwe6dOlCmzZtmDNnjoWfkRBCWNDVq7q3+/LL2d9va1u87SlkPj7LCAub
   CVTO1/GytckKyWsjhCgVlII//9R5oX/4Qe8JHjUKhg2z2rSU+eXpOZ2goLQh6iKoZyyEEELkS48e
   cOaM3g986FCRlSy0BvXq2QCJSM+4FJHXRghRKpw5o1dDl7JecHbS5oz1UHWVPPeMJRhbIXlthBAl
   QkoKbNqk/+zb19KtsbijR6MYNWo/wcEDJAOXEEKIInboELz6KjRsCNOm6ZrBZVhCgs7O2aOHCw4O
   /fN1DgnGQgghcicuDtq2hUcf1ft/N22C3bthyBBLt8wizp+H6dPB1RV27dI5SzZsyN+5ZAGXEEKI
   3KleHT7+GLp0KfFbkQoiKkr3hL/5Bp56Cnbs0BUcC0J6xkIIITIoBTt3wqlTt95nGNCtW5kNxIcP
   64XhbdtChQr6988+K3ggBukZCyGEAIiM1F29r7/Wwfazz6B+fUu3yirs2AGzZukR+QkTICys8JOE
   Sc9YCCHKsj17wMMD7r9fb0UKCIB//tFlCsswpWDtWnjwQfD21tPkERHw1lu3D8SmJFO+rifBOBuN
   GjWiUqVKODo64uzszOjRo7ly5QoAo0ePZtq0adkeZ2Njw1133ZWl2lNqaipOTk7YltFhHSGElatV
   CyZN0qUKP/0UOnQoE/uCc5KSAsuXw733whtvwHPPwbFj8PzzULHi7Y81JZnosrhLvq4rwTgbhmHw
   66+/cvnyZfbv38++ffv473//m6tjq1Wrxrp169J/X7t2LTVq1CiqpgohRO7880/2lexcXGDgQChX
   rvjbZCUiIqIYOvQ9mjZdQ/XqF5k37xr//S8cOADDh+eucFRYXBhjVo8hJDZ/FfokGOcgLemGk5MT
   jzzyCPv378/VcSNGjOCrr75K//3rr79m5MiRRdJGIYS4rTNn4KOPdDevVy84e9bSLbI6Bw6coH37
   w3z77VSOH+9LQkIF4uLepkWLqDsOECil2H5iO098+wSdFneiYdWGtKzVMl/tsMpgbEoysfPkznyP
   vRfWOQBOnTrFunXraJKL5XKGYTBgwAC2bt3K5cuXuXTpEtu3b6d///xtAhdCiHzZsAEeewyaN9fd
   Oz8/vR+nbl1Lt8xqREfDa69Bhw61iIt7mIxwWJGwsJn4+Cy75Zi0uBJ3JY4VISvo+GVHRq8eTc/G
   PYmcFMncR+YS/ExwvtpjdaupTUkmui3txuHYw7jXdmfb6G04lHco9nMMGDAAgISEBHr06MGMGTNy
   dVyFChV4/PHHWbFiBUopHn/8ccqXL5+nawshRIFcvqwrI333HVTOX+GC0ur4cfjwQ/j+exgxAtq2
   XURw8Es3Paoy0dHmLLekzQeHng/FxrChQ70OvNXtLfo27YutTcaaoLzGmjRWF4xDzoVwOPYwKeYU
   Dpw9gOMsxwKdLzQ2lMOxh+lUv1Oejlu9ejWenp5s27aN4cOHc/78eRwdb9+WtKHtESNGMHXqVABm
   z56dv4YLIcSdXL4M2X0uDRpU/G2xcnv2wOzZsHkzvPACHD0KtWuDt7eJ4OCbqy0l4uycMXAccTGC
   Nza9kT4fbGPYMLfX3DzHlduxumDcyqkV7rXdCY0NpWXtlgXqGaedw722e57bkRZYu3XrxsiRI3n5
   5Zf58ccfc3Vst27diImJwdbWlq5duxIWFpbn6wshRLYuXtQ93q+/huvX9eZXkS2ldPCdNQtCQ+Hl
   l2HJEqhSJeMxvr6jCA6efqPaUmUgETe36fj6TmDnyZ34BfuxOWIz3m28aVGrBf/G/ZvvuHI7VheM
   Hco7sG30tvQh5vx0+QvjHJlNnjwZV1dXDhw4AEBKSgpJSUnp99vY2GBvb5/lmDVr1mT5XaowCSEK
   5JdfdADeuBEeeQTefFMvyhK3MJvhp590EL58GV5/Hby8sl8w7urqwsaNE3hj2nv8azpDY4faeIxp
   zPA/hnIu8RyTO05maf+lVClXBVOSqdDiys2khGI2GjduzJdffkn37t3Tbxs/fjznzp3DwcEhy2pp
   gK5du7J161ZsbW05fvw4jRs3znJ/WFgYTZs2JTU1NVfXt+bXRghhIS+8APfdp5MhF3b6p1IiORn8
   /eGDD6BqVb1PuH9/sLnDUuXM88G2hi3tndvzapdXebzZ41nmg3Prxme41DMu6eS1EaIMM5vvHD1E
   FiYTfPGFXjTu7q6DsIdH7nKXRMVH8camN1hxeAUAdjZ2bBu9rUDzwfkJxnf8FzcMY7FhGGcNwziY
   zX2vGIZhNgxDsloIIUR+mUywbBl0767HVEWuxMbqcsqNG2eUMFy/Hjw9MwJxREQU3t4z8fScjrf3
   TCIiogDYdWoXQ74fQrvP21GnSh1a1GqBvY097rXdC30+ODdyM2e8FJgPfJ35RsMw6gM9gagiaJcQ
   QpRuqam6HvA338CaNToX9Pjxen+wuK2oKJg7Vw9J366EYUREFA8/PJ+wk6+AUwQEN2BT9AvUHxRN
   3PU4JneazJf9vsShvEORzgfnxh2DsVJqu2EYLtnc9RHwKvBzobdKCCFKu7NndWV6b2+dJat2bUu3
   yOqFhOj54F9/hWee0SUM77or58f7+CzTgfjph6FWKChbzsbcS9ODbuxasOuW/cGFuVUpr/K1mtow
   jH7ASaXUIaMMJxQXQoh8c3aG4PxlayprMpcwnDQJPvkkd2vYws5fhL4vgVMIGECqDaz/BLsm6/K1
   MKso5XmVgGEYFYG3gOmZby60FgkhRGlw5You/9O7NwQFWbo1JU5OJQynTr1zIN59ejfDfhjG3g6f
   wxVHiG0OKfYQ6w7nGmVJ6GEt8tMzdgMaAQcM3S2uD+wxDKODUupcdgdkTiXp4eGBh4dHPi4rhBBW
   zmzWgfebb/RG186dYeRIXZZQ5EpKis5pkpa88PXXYfDgnCsnmZJMhJwLoUWtFmyO3IxfsB8nL51k
   UsdJTG31Fk8sX0bYH5vBKRLONcKtwRx8fScUapuDgoIIKuAXrlxtbTIMoxHwi1KqdTb3RQBtlVIX
   czhWtjblkbw2QpRQS5fqMdQRI3TtPSnMkGtXr+qXb84caNBAb0/q3fv225NMSSa6LOlCaGwodoYd
   beq04bWurzGwxUDsbHT0joiIwsdnGdHRZpydbfD1HYWra3bLoApPkewzNgxjOeAB1ATOAtOVUksz
   3R8OtFdKxeVwfLbBuFGjRkRFyULs7Li4uBAZGWnpZggh8kr2COdZfDwsXAgffwwdO+qecJcudz7u
   1OVTvLHpDQIOBQCFsz+4sOQnGOdmNfXwO9zf+Hb350SCjRCixLl6VaelXLVKp6a8Ob+iBOJci4mB
   efPgyy+hb1/4/XedsCNNWo/29Gkz9epl9Gj/jv6bj4I/Yt3xdQxrNYzmtZoTFhdWJPmii5PV5aYW
   QgirYjbDtm16HnjVKmjfXg9Di3zJXMLQ2xv27gWXm0aNb9kfvLMhv58aT8OhMcRcjWFix4ks6LOA
   qhWqWnx/cGGRYCyEELczahTs2wf/+Q8cOgT16lm6RSVSTiUMs5O+P3hML6h9GJQdZ861wG3/3YR9
   uh1724zCPJbeH1xYJBgLIcTtfPqprrknORVyJfPwsrOzDX36PMdXX9XJsYRhdsJj46HPa1Dn0I39
   wWZYu5ByTX7LEohLEwnGQoiy7do1PQ8cEwMTJ956v0PJHfosbunDy+m1gVNZufIC7757njVramVb
   wjCzfTH78Av2Y0/H72HvcDjfHKqHwfmWcM4V54dK75x86X1mQgiRE7MZtm6FZ5/Vw86ffy7bkArB
   m29+TVjYe+hADGDL9euVOXjw0xwDsVmZ+eXoL3h+5Um/wH60dmrNruG7cDtSHb7YDMu2wpLfbuwP
   HlU8T8QCpGcshChbUlKgVSuwt9cLsQ4cgPr1Ld2qEi2thOGqVROB8jfdW5noaPMtx5xNOMucHXP4
   6ehPOJZ35OXOL/NUy6fSh6E3bpyAj89nen/wQzb4+k4o8v3BlmSxesZCCGExUVHQsKHMAxdQbCzM
   n6/3CXfvDibTZ6xb501GzxggES+vOfj76wzKMaYY/Hb68VHwR5iVmcbVG7N37F4cKzha5DkUhSKp
   ZyyEECXO1as6p+LOndnf7+IigbgAoqL09HqzZrr41I4d8O238OmnvXFzmw4k3nhkIm5u0/H1HcWB
   MwcY9dMo3Be4ExEfoQMWihOXThB6PtSCz8Y6yDC1EKJ0SJsH9vfX+4HbtYO33rJ0q0qVO5UwdHV1
   uTG8PIfoaDN3OUOPca14dtvT/HP+HyZ0mIDfI37Y29jTbWk3QmNDS3yyjsIiw9RCiJLv0CGdxqlq
   1Yy80LIfONdyynaVJnMJw4kT9T7h21VOOpdwjrnBc/nxnx+pXK4yL3d+mcHugylnm7GKq7Qk67hF
   SgqGvX3h56YuKAnGQogid+WKTu10zz2WbkmJc+t2JD20vGHDBI4ccWHWLDh1Cl59Vec/qVgx53Od
   STjDRzs/Yu7OuaV2PjhbSulUYv7+sGIFxpkzMmcshCilrlyBFSsgIeHW+ypVkkCcTz4+yzIFYoDK
   hIW9S7t25Zk6FZ5/Ho4d03/mFIgPnT3EmNVjaPFpC45dOFZ25oMjIuC996BlS13n0dERtmzJ16lk
   zlgIYb1SU/WHW1p94A4ddGmfO6VwErl2+rSZrKufASrQsOFG9u8fkeM6N6UU68PW47fTj5BzIYy/
   fzzHJxynvG350j0fHBcHK1fqXvCRIzoIL1kCnToVaFGgBGMhhHUKDNRjo7Vr63ng99/PulpIFIra
   tSsCyUDmrByJtG4dfktsMSWZ2BOzh5BzISz8eyF2Nna81OklhrYaSnm7jP3F20ZvK13zwdeuwZo1
   EBAAf/yhCy2/9ho88sitlbvySeaMhRDW6fBhPRfXqpWlW1IqpZUw/PzzVFJS9pGQ0BKoRNqc8caN
   WZNshF8Mp8viLpxNPItDOQcCngigb9O+GKV1i9jNq/Pvu0+XmXriCb1Q8DaKpJ6xEEIUmYQE+Osv
   8PS89T73Uja8aSX+/VeXMFy5Ug847N9vi9lcGx+fD3W2K+es2a5CY0P5aOdHrDi8givJVwC4lnKN
   2pVrl85AfOiQDsDLl0PNmjoAF0O1LgnGQojilZKiK8l/840e+uveHR56CGxkPWlRun0JQ5f0DFmg
   54M3hm3EL9iP/Wf280L7Fzj43EEGfjuwdM4Fnzqlp0X8/eHiRfDygnXrinVURoaphRDFZ8YM+Owz
   nYrS2xuGDAEnJ0u3qtRSSgff2bP1qP9LL8HYsdmvfzMlmdgbs5fDsYdZ+PdCAF7q9BLDWg+jgl2F
   9MeUmrngS5fghx90AN6/H558UgfhBx8s8BfD/AxTSzAWQhSfH3/U20CaNbN0S0o1s1kvPp81Cy5f
   1muNvL1zXmsUcTGCzos7p88HfzPwGx5v9njpG4ZOTobfftMBeP166NFDvzB9+kCFCoV2GZkzFkJY
   Xny8riDQpMmt9w0cWPztKUOSk3Wc+eADveX1jTegf3+wtc3+8f/E/sO84HkEhgSSmKzzSV9LuUad
   KnVKTyBWSuco9/fXE+UtWugAvGgR1Khh6dalk0kaIUTBJSfD6tXw1FO6CMOKFZZuUZmSkAB+ftC4
   sX7pFyyAXbv0wt+bA7FSik3hm3hs+WN4fuWJs4Mz+5/bT+s6rbG3sS8988FHjoCPD7i56UTa9erp
   xYJbt+qxeisKxCDD1EKIgoiPhzff1BWSWrbUy3MHDYLq1S3dsjLh5hKGr72m62PcLG0+ODQ2lIV/
   LyRVpfJSp5fwauNVuuaDz57V30b8/fWirOHDdS/43nuLtUqXDFMLIYpXlSrg6gp//w2NGlm6NWVG
   VBTMnatjzqBBupBDdrMCAJHxkXT6shNnE89SpVwVvh7wNQOaD7hlGNqhvAOd6ncqhtYXssREPUHu
   7w/BwfD44zpBTPfuOY/PWyEJxkKIO4uNhfLl9URkZnZ2OkuWKBZ3KmGY2ZHzR5gXPI+AQwHp+4OT
   UpK4y+Gukj8fnJICmzbpALxmDXTpAv/5D3z/PVS+ObVnySBzxkKI7KUVZujbV3e7goMt3aIya8cO
   3eHr2VOvPwoL09uVrl2Lwtt7Jp6e0/H2nkl4eCR/RPxBv8B+PLTsIepUrsP+caVkPlgpPQIzeTLU
   r6+3yXXqpKtYrF0Lw4aV2EAMMmcshLhZSAjMmaMXZHXsqOfcBgyQ4gzFTCmddyKnEobppQ9PvgJ1
   j0Gtg5R74B0auDryerfX8W7jTUV7/eASPR8cHq5zQgcE6B6xt7feD5zTuLwVkDljIUTBJSXpcoSz
   ZkHdupZuTZmTkqLXw/n6JnPmTBx33bWdTp1C6d17JBUrZuSK9vFZRtj5p2HCfVDlDCRXIfnHz+jY
   7ijPTn42yzlL3HzwhQv6RfD313WqBw+GZcv0l8OSPsSeAwnGQpRVsbGZ8yFmaNcu+yW5okhdvQpL
   l+q80U5O14iP9yc+fhjx8YP4559Edu/OKN5w7MIxNldaAy/MAftEMADbJEhoTEz0UUs/lfy5ehV+
   +UUH4C1bdCKOqVN1ZSR7e0u3rsjJnLEQZUl8PCxerAsztGyp0zMJi4qP14t/XV11UqiAAGjSZDZn
   zgwjo85wZcLCZjD2/Rn0X9GfB5Y8QI0KlWDRdjjXBlLs4XxLONcIZ+cS9LGemqrzlI8ZA87O8OWX
   Oi3lyZM6V3TfvmUiEIP0jIUoGzZsgC++0H/27AkTJ+qeR/nydz5W5ElERBQ+Pss4fdpMvXo2+PqO
   ylKKME1MDHz0kf5u1LevjklphareessMVIZyJqi7H2oehfsXsqNaFH53v0fgk4GcPRXLw2vnE7bk
   N3CKhHONcGswB1/fCcX5dPNOKTh4MKMyUp06eh743Xd1QC6jJBgLURaEh8PDD8Pnn0tCjiKUvqgq
   bCa6V5uTbysvAAAgAElEQVRIcHDW2sDHj+uh6O+/1zFo716dtCyzevVswPEIPOt5Yz64Mvy0iAFt
   jzOu/TgAXF1d2LhxAj4+n+nShw9lLX1odU6e1MHX3x9MJp2QY8MGKZV5g6ymFqI0SUiQVc8W5O09
   k4CAV8gYXgZIxMtrDlOmTM9SwnDCBKhV69Zz/Bv3L74b3uWbQ4Eou+tgoyDFnnobB7Et8L/WG2yz
   Ex+vv3X4++uawIMG6W8gXbuW6pKZ+VlNXXpfDSHKirTxzvbtdUlCYTGnT98YXs6iMmvXejFgAHTu
   DBERMHNm1kCslGJb1DYGfjuQzos7U6+2MxueWke1ZCeMVBuqpdRg3ddvlYxAnJSkM2INGqS7/L/9
   BpMmQXS0Lp/ZrVupDsT5dcdhasMwFgN9gbNKqTY3bvsA6AckAWHAaKWUrAQRorikpGQUQ9+9W5fm
   mTVLL8wSFlOvng2QSNaAbKZZs8Ns2XJ3lhKGpiQT+8/s59+4f1nw9wLir8UzpdMU/Af6U7mcPv5E
   i+MlY3+w2awzk/j7656wu7vOU/7FFzItkkt3HKY2DOMBIAH4OlMw7gn8oZQyG4YxC1BKqak5HC/D
   1EIUNqV0PsRevaBfP6hUydItEsDRo1F06xZMbOxT6IHHazRu7MOmTS9m6dXuCNlJjxW9uGaXgK3Z
   no88/Bjv+QI2RgnrMf7zjw7AAQE6+9WIEXouuGFDS7fMovIzTJ2rOWPDMFyAX9KC8U33DQCeVEqN
   yOFYCcZC5JdScP16zlXhhVVISNBr43QZw6uUK/cdqanht6ymjrgYwTsbffnqQEDJnQ+OicmojHTm
   jA6+Xl46UUwpTciRV5bKwDUGkOKlQhSm48d1b8PfX8+3TbDy7Spl1PnzuoThggW6SNDPP0PbthWB
   kemPUUqx4+QO/Hb6ERQZRJ3TzVEBO+GpMVArFM635PQ+P3x8PsPff7rlnsztmEwZlZF279bpUT/4
   ADw8SlRlJGtWoGBsGMZbwHWl1PJCao8QZVdcXMaQX1QUDB2qeyCSDcvqZC5h+NRTt5YwNCWZ2H92
   P+Fx4Sz8eyGxV2KZ0mkKywYso98jHxJ6oS0s2QZOh+GcOyQ7EB1tttwTys7167Bxo36Sv/4KDz6o
   k3P8+KNMixSBfAdjwzBGAn2A7nd67IwZM9L/7uHhgYeHR34vK0Tpdfo0/PUXvPMO9OihyxMKq5Kb
   EoanLp2i45cdiU6IppJ9Jb7o+wVDWg3B1kb3INMXeSU7wKm0fNGJ1pE5Syn9HvT3h2+/BTc3PQT9
   8cfZp04VAAQFBREUFFSgc+R2zrgRes649Y3fewNzgQeVUhfucKzMGQuRWWqqDO2VMDt26MXqu3fr
   GYPx46FatayPiYyP5JNdn/Dl3i9JSE5AobC3sWfr6K1ZijRklxjEzS1rYpBiFxaWMS0Cei/w8OFw
   992WaU8JVyQLuAzDWA54ADWBs8B04E2gHJAWiIOVUi/kcLwEYyFu7nHs3AmNG1u6VSKTm9NYvvPO
   KI4cccmxhGGa4FPB+O304/eI3xlz7xhG3zea4T8MJzQ2lJa1W7Jt9LZbtiWlXSs62oyzc84pM4tU
   bGxGZaTwcL1H3csLOnSQhVgFVGSrqQtCgrEo08LD4Ztv9AeeYUiPw0rd2lu9Rrlycbi61mLatHIM
   Hpwxa5A2Hxx5MZKFfy8kJiGGyR0nM+a+MelB12rrB1+5klEZads2eOwx/Z7s2bPMFGQoDlLPWAhr
   s2aNXpi1fLnOkCU9Dqvk47MsUyAGqEBycg3atfsvw4dnrHAOPryb7oE9uGqXgK3Zjg8e/JBJ3Sek
   zwensar6wampOgdnQIBeEd2xow7AgYGSOtWKSDAWojCYzdmn+Js4sfjbUkrktvpRQcXHw44dXbk1
   jWUFYmL0CucTl07w7ob3+HL/Mr0/2IBUZeD39m4GBp6yvv3BSsGBA7oHHBioV5l5ecF//wt161q6
   dSIbEoyFyK/MWz/CwmDXLku3qNTITfWjgoqOhnnzdAnDqlVrAVeAzFt2EinnGs2wH4axIWwDTtHN
   UMu3w5PPWu/+4KiojMpIV67oHvDvv0Pz5pZumbgDK1hLL0QJExwML74I9erpGqwPPKCHo0WhuXXY
   uDJhYTPx8VmW53NFRETh7T0TT8/peHvP5I8/TjN2LLRqpWsa7N0Lv/9eHTe3aVDuDDTYDq2WUOH5
   ZoS0WEcH5w5ETIqg7oGHIfZ+vT942Vb9Z3Jdy+8PvnhR54B+6CG9J/3ECZ0OLDwcfH0lEJcQ0jMW
   Iq/mzoU2bXRQlhXRRSKn6kd5DXy39rBTCAy8xvjx8Rw7Vi1T5SQXAlYPwTOwKVftTNia7Xi322wm
   9ZiInY3+mLSq/cFJSXqzs7+/7vn26gUvvQSPPiqpU0soCcZC5ESp7BdcrVxZ/G0pY7KvfnRr4LvT
   vPLbby8jLMwXSNuPZIfZbBAX9zG1aumh5VOXTzF/13wW/b2Ia/YJANjYG3Rt0SU9EAP4+o4iOHj6
   LfuDfX2LKVWp2Qzbt+sA/MMPOhe0tzcsXQpVqxZPG0TRUUoV6Y++hBAlRHy8UkuXKtWzp1Jvv23p
   1pRZ4eGRys3tZQUJSn8rSlBubi+r8PDIXD0mNVWpH35QysHh5I37sv54ek5Tf53+Sw3/YbiqMbuG
   mvLbFHXwzEF1z8J7lP079uqehfeoy9cuZ9suL68ZytNzmvLympGlPUUmJESpqVOVathQqdatlZo9
   W6kTJ4r+uiLfbsS9PMVK2WcsRHIyrFunexwbNujk915eujThzRkeRLG5U2IMb++ZBAS8ws29506d
   NnHxYn+qVoUKFb5l69a+UM4MTiEQ2wIarcep/+tUuEsxqeMknr7vaapW0D1Lq9kfHB2dUa86Nla/
   H7289PSIsHqS9EOI/IiI0KmVvLxg0CCoUcPSLRK54Ok5naCgmbfcXr36v/zww914eEBkZBQ9Hp1L
   hOfvUPsIKDvKXarGnAE+PO/xXJZhaIu7fFkXYfD3hz17YOBAPQz94IOSPrWEkaQfQtxJdvPArq6w
   ZYtl2iPyLft55av06ROAp6eeDy5X04573jpFRFgoGGCYU1jutYgnOw60RJNvdf06rF+vE3KsXatH
   ZcaOhb59ZVSmjJGtTaL0i4rSWf5bt9aZ/kWJFxUF9vZTsLExgOs3bk3Ezc0HX99R7I3Zy4gfR9B6
   YWvqVq9D81rNsbexp81drel1b08Lthz9hTDz9rhZs3TvNywMVq/WNRklEJc50jMWpdOFC3rVc0AA
   /POPHn5esADuv9/SLRMFkLWEoSM7dpzC738L+Nd0BjcHJ3o924IxW0fxb9y/TOwwkfmPzqdahWrW
   MRd8/HhGZSRbWxgxQrbHiXQyZyxKp0WLIChIzwM/8ojsvSzhMpcwnDQJnn9elzA0JZnouqQrh2MP
   Y2djR8taLXmt62sMajkIe1srKHxw7pyu0uXvr7vzQ4fqeeB27SRPeSkmC7hE2ZPTXmBh1XKTd1op
   vcg9pxKG0aZopm6aytcHvwbAzsaOraO20rlB5+J9Mje7ckUPN/v7w59/6vnftMpIdjIYWRbIAi5R
   Niil80AvX66TIPz9d/ZFGoRVulPe6ZQUXWZ39mz9T/3667rUbloc239mPx8Ff8QvR3/hqZZP0bxm
   c8IuhtGydktaObWyzJNKSYE//tAB+JdfdGWkESN0r1gqI4lckJ6xKDmOHNEBePly/cns5QXDhklt
   4BImp/3BQ4bM48EH32LOHKhfH954Ax7obuJwbAgta7dk+4nt+AX7ceT8ESZ0mMDYdmOpUbGG5eaD
   lYJ9+zIqI9Wvr3vAQ4ZIZaQyTnrGonSbMQOcnXVvo21bGZ4uoXLKO/3jjxO5elXHti5dss4H29vY
   06xmM17t+iqD3QdTzjZjDUCx1w6OjMxYiJWUpANwUBA0a1Z8bRCljgRjUXKsWGHpFohCkP3+4Os8
   /PA3rF79AgBnEs4wddNUDp07BECqSmVR30WWmw/OvDr/yBG9/WjxYujcWb4UikIhE23COly7ppPf
   P/EETJli6daIIjRmzDM4OBwC0qavruDmNpX58x/j4NmDjF49mhaftsDWxpZmNZthb2OPe2334p8P
   vnYNvv8eBgzQ2482b4bXXoPTp/U2uS5dJBCLQiNzxsJyUlP1B1xAgF592rYtDB+uA3K1apZunShk
   e/boRVmbN8OwYfFEnZnPqeQI3ByceHRcc5ZHBHD43GFe7PAi49qNo2almsU/H2w2w9ategh61Sr9
   nvT21u9JR8eiv74oFWRrkyhZYmP1to+hQ/WiF2dnS7dIFDKldPCdNQtCQ+Hll+HZZ0HZZ50PblKj
   Ca92fZUh7kMob1e++BsaEqID8PLlOje5t7deHFivXvG3RZR4EoyF9ZL9wGWK2Qw//aSD8OXLenuS
   l5fOvXI24Sxv/v4mS/YvASy4P/jUqYzKSHFxGZWRWrcu3naIUic/wVjmjEXRiY4GPz9o3x42brR0
   a0QxSE6GJUugZUsdiKdO1T3i0aPhePxhnvn5GZp/2hyFssx88KVLsHQp9OihyxEeOwaffJI1f7kQ
   FiA9Y1G44uP1Qqzly/UezAEDdG/Dw0PKwFm53GTFyonJBF98ob97ubvDxFdMVG8WQisnd4JPB+O3
   048DZw8w/v7xPNf+OWpVqlV888HJyboykr8//PYbdO+uh6EfewwqVCi664oyS4apheUFBOiarMOH
   Q58+8mFXQmSXFcvNLSMrVk5iY2H+fFi4UMe411+HJu5Z54PdqrvxatdXGdZqWPHNBysFO3fqALxy
   JTRvrr8UDh4s9apFkZNgLIqPzAGXKjllxfLymoO///RbHh8VBXPn6lj31FPwyivQpAnEJsby5u9v
   8uW+LwELzAcfPaq/EAYE6AnqESP0F8NGjYrn+kIgc8aiqKXVYZ04EVq00MN/olTIKStWdLQ5yy0h
   IfCf/+gdPxUrwuHD8NlnkFLtH8b+Mpam/2vKxcvxOCbXxEi1ocqVmlS5WsRbgs6e1fO+HTro6ZCE
   BN0bDg2FN9+UQCxKBMnAJe7s8GE9BxwYqHsbXl6wZo2UJSxFss+KlYizs/6+nlbCcOfOVOq6rKVe
   p7VERFfj94jWLP/Dn70xe3nh/hfY0G8Twx4P5PLJEHCKJP5cIwaunHPH4e48S0zUy7X9/fVwdL9+
   8O67eqxcKiOJEkiGqcWdjRunEx4MHw733ivD06VQdnPGjRtP5623XmXZsjqcOgWjR19g8TfvEtVj
   I9T+B8z22CVW5t1H32BS9wlUsKuQ5+HuPElJgU2bdABeswa6dtULsR5/HCrf3KsXwgKuXYMNGzD6
   95dCEaIAcpoH/uyz4m+LKFauri5s3DgBH585nDoF16+3Ii7ufT7+uBxvvKHnhYeOmU1U00tQ5zAY
   AKmkfL+SQ7HbqNBLL9TL7XB3rimlS2QGBOjc5I0a6ZEZPz9wcsr/ExaisFy/Dr//rt+fP/8M99yT
   r9PInHFZZzLpnsZjj8HTT1u6NcKC6tZ1oWvX6Zw4MR07uyfx8yvH/v3Q9uGjTPjteVY3nA/2KXCh
   KaTYQ6w7nLs/S6DNGO7OLGO4O9fCw8HXV6+CHjZMp0fdtk2vWZgwQQKxsA6ffKKztM2cCffdpxdV
   bN6cr1NJz7gsun5d77cMCIB166BbN93bePxxS7dMWEB8vN6a9PHH0K6ziTf+F8LQ7u78HfM3j6/4
   iN2nd/N8++d5/OSLrPppBpQzg9NhOOcOyTZZAq2v7yiCg6ffskXK13fCnRty4QJ8953+cnj8uE6R
   +tVX0LGjTI0I69StG+zaBa6uBT6VzBmXRSaTTnz/5JMwaBDUqmXpFgkLiI6GefN0JcC+fWH8FBPP
   7OxKaGwo9rb2NHRsyKtdX8WrtRcV7Svmei9yWvKQ6Ggzzs53SB5y9Sr88osOwFu26L3p3t7QqxfY
   2xfHyyBEzpTSvd2wMJ3AKJeKZJ+xYRiLgb7AWaVUmxu3VQe+BVyASGCwUupSDsdLMLYUpfSPjcxG
   iAzHj8OHH+rqgCNGwEsvQZXaF3jrj7f4bI9eH2BnY8eWUVvo0qBLlmPzFGhzkpqqA6+/v04Q0769
   DsADB0plJGEdjh/Xc8ArVuitcuPG6W1yuVRUwfgBIAH4OlMwng1cUEp9YBjG60B1pdQbORwvwbi4
   HT2qtyEFBur9KAMHWrpFwgrs3avfDps3wwsv6KnXOOMY84LnERgSSN8mfdkdvZuIixG0rN2SbaO3
   FW6ayoMHMyojOTnpqZFhw6Ral7AeKSl66DkiQmdrGzoUOnXKc4emyDJwGYbhAvySKRgfAR5SSp01
   DKMuEKSUap7DsRKMi8OZM3oOODBQFz8fMkRvRbr/fplvK+Vul1P65hKGL70Ezz6r2HNhC347/Qg+
   Fcy4duMY32E8davULfx80SdP6uDr76/LN6VVRnJ3L/i5hSgKe/fqIiIF2K9enME4TilVI9P9F5RS
   NXM4VoJxcVi7Vo87Dh8Onp5SlKGMyGked/36CRw44JJewvC11+DRJy6waN8n/HTkJ5JSk5jSaQoj
   7hlBJftKhduotGIh/v66NzxokA7ADzwgUybC8uLjdcKYli111rYikJ9gXCyrqWfMmJH+dw8PDzw8
   PIrjsqXT9evZL2zp00f/iDLFx2dZpkAMUJmwsPdo29ZEs2a6hOGDvS7y6V/zaTjfl1RzKo2qNWLf
   uH1UrVC18BqSnKxX5vv7w4YN0LOnHgd/7DEoX0zFIYTISWKiXii4YoUeKureXW+by4PbjUAFBQUR
   FBRUoCbmt2f8D+CRaZh6s1KqRQ7HSs+4oJKT9Qfc8uXwxx96PqNiRUu3SlgBT8/pBAXNvOX2e+9d
   ynebuvHJro8JOBRAp/qd2Bi+kRRzCvY29mwdvZVO9TsV7OJms86T6e+vR2Xc3fVCrEGDoHr1gp1b
   iMKyZQv076/nfocN06uiq+bti2heq5oVZaEI48ZPmp+BUTf+PhJYnZeLilzavh3GjtULXGbP1gsL
   Dh2SQCzS1axZBchcsEOBy3rO9/yALks641jekZAXQvh20Le413bH3saelrVb4l67AHO2R47A22+D
   m5teZdqoEezZoz/0nn1WArGwLu3b69XRv/0GI0fmORBDTiNQM/HxWVZozbzjMLVhGMsBD6CmYRgn
   gOnALGClYRhjgBPAU4XWIpHh9991Xbq9e6FhQ0u3RliRtBKGmza9hKPjbi4nN4AOi6H5j9hXOcHY
   Hi/xUvcpVC6nPzwiIqJo9mcfbC63o4ljHc4/EoeDax4WaJ05o4f4/P31BuVhw/S2pHvukQWCwrLS
   ald//z28//6tNdQrVy5w7vJCT/OajTsGY6XU8Bzu6llorSjrrlyBStksoplewMT6otQJCYEPPoBf
   f4VnnoHg/SY+3/898/bNQxlmKqdU488RW7mnWev0Y24eYttHInt25jzEli4hQQdcf3/YvVsP9c2a
   JQsEheUpBQcOZOwFrlRJf0FMTr41GBeCO1U1KwyytNFSTpzQn6r33aeH9oS4jR07dLbSnj11Kenf
   94ZzzWMSXb5tTGjCYWztbMCA5PKJXK2cNTd0nobYUlL0QiwvL6hfX6enHDNGb5dbtkw3QAKxsLTx
   43X+BMOA1at1mVcfnyJLGuPrOwo3t+lk5F1PS/M6qtCuIbmpi9PVq7B0qd4L/M8/OiWlnx88+KCl
   WyaskFI6Ls6aBadOwSuvKCbP3cGn+/yY++0Wnm37LIeeP4RjeUe6Le1GaGxotvPBdxxiUwr++kv3
   gL/9Vs8Fe3vrZNWSKlVYo/feg08/LbYpksxVzTKyzxVujW4JxsXJ1lYvdHn9dZ17t1w5S7dIWKGU
   FN0hnT0bUu1MPPH8flzuC+PzfQu5sO4CkztN5qsBX1GlXJX0Y7aN3pZjso6chtjudYiHd97RQRh0
   AN6xQwdjISwpNlbPAV+4oBcL3swCiwRdXV0KXpP7NqRQRFG4elX/KaueRR6kDZzMmQMNGsAzU07x
   elhHYhKiqWxfmS/6fcFg98HY2uRtmDjznHEtrjCYb3im/BzaVLmOrddwHYTbt5eFWMKyLl/WyTgC
   A/WCrD594D//gd69Ld2yPLPapB9lQkoKbNqk30g//wxffw39+lm6VaIEyFzCsGNH+OCLCP68/gnj
   9y0mITkBgOTUZFyru+Y5EAO41qnNjokunPqgLU3PRnGgflPumvY+tt5eUhlJWIfr16FZM52+d+RI
   3Ssu4ArokkYWcBXUkSN6MUG9ejBjBrRtq5MASyAusyIiovD2nomn53S8vWcSERGV7eNiYvSMhZub
   fhv5fRdMOe+nGLenPfa29ux6Zhdt6rTJ397g1FT95XDUKKhXD6df19D2/beoEhdL14iD1B09SgKx
   sB729hAerjsyQ4eWuUAMMkxdcLt26f3AQ4dC48aWbo2wsNxk6vn3X13C8LufTPTw2k/XxyJZGbmQ
   MwlnmNxpMqPvHZ0+75unwg1p2z3SKiM5O+tV0UOHwl13Fe0TF+J2zGadxCgwUA8/l/LOSpEViiiI
   UhOMT53SWz2EuA1v75kEBLzCzYulvLzm8NJL05k9W2c09X7hNIFVOnD2SjSV7Crxeb/PGdpqaL6G
   oTlxIqMyUkKCngP28tJ7oISwFKVg3z4dgFesgGrV9F7gESP0oohSTOaMC9vJk/pNFBgI587plGqy
   KEvcRk7biNau9WLLFhg9+QR1RnzC4kOfk3BFzwdfN1/HrYZb3gLxxYt6Xs3fX2cCGTQIFi2CLl2k
   MpKwDuvWwYsv6gC8bh20alXol7hd8YaSRoJxdvz94bPP9NzvE0/o5a0PPSTJDsQdZb+NyEy9Dj/S
   YswePo3cyCj7Uex8eideq7xy3BucraQkXSrT31/PB/fqBVOmwKOPSmUkYX0eeQTCwrJdpV8YQTS7
   KaHg4FxklrNSMkydna++gho19JtJ9gKLPDh6NIpu3YKJvdQb6hyCascp382HWq7wcteXebrt0ziW
   11mCcjUfnDbXFhCge8Jt2uhh6Cef1MN+QljK+fOwcqV+X65alesCDHmtgJST200JFeV+4NyQYeq8
   uHJFL2fNLsHByJHF3x5RoiUkwOefg5+fC65tUrncoRFJ5eKxNdvxXrfZTOoxETubrP/dHMo75FzG
   MDSU+P99SspXAVw2yrO7SRu6rP6Fhg90KYZnI0QOTCadfnL5cp0g5tFHYdKkPE3f5ZyeNW9BtDiK
   NxSnsjW5lJysM+x7e+uVpp9+aukWiRIuNhamTQNXV9i85yQ9Zr3GkR73kVz+EhhgY2/QtUWXWwJx
   tqKjdXrUtm1J6dGD7wJ30/3KetwSzzJs/090H7Uqx21SQhSLV17RKVNHjNCLWgMDddL0PIwgFlYQ
   zZgSyqxwizcUp5LZ6rwymTLqAr//vi4yffSo/uAT4obc7A9Oe0znzn40b76LJk1SCYn7m04fDufP
   NvdQs3YK28dsv+P+4LTz9On2Bp91GcjVB7qBu7tejDVnDqM9xzIuPohDdLxxROHXTxUizxYtgl9+
   0YuyqlS58+OzUVhBtDiKNxQrpVSR/uhLWFhqqlIff6xUZKSlWyKsVHh4pHJze1lBgtJ7MhKUm9vL
   Kjw8Mstj6tf/UFHugqLBNkWrr1T55xoq5w/rqbk75qr4q/Hpj7187bLaeXKnunzt8q3XOnpcPV13
   oFrOIHWRquonHlMT6vRVEaFH0h/j4THtRjuy/nh6TivaF0KUXWazUjt3KjVhglIjRxbZZXLzfy0v
   5/LymqE8PacpL68Z+TpHUbgR9/IWK/N6QJ4vUJzB+OBBpc6dK77riVLDy2tGpg8Hlf4h4eU1Qyml
   1J9/KlWv3hFF5dOKKfUU01G8WVFxzyI1zMvnzhdI+6AbP17Fl6+kttNJPccCVZPYW66Vm/YIUWgO
   HVJq6lSlXF2VatZMqZkzlTp2rEgvaa1BtLDkJxiX/AVc//6bUWD68mX45hu9DUmIPMhpHuvQITce
   fBAi405xpctb0HgTlL8MBmCTAhfu4Ux0dM4nPnZMr4QOCNBb40aM4Pl7nyZw1ye3XCvznJmv7yiC
   g6ffsuLU13dCYTxdIbTr1/Uamocfhh9+gHvvLZaCIUVdAakkKrnBeMsWvZjgxAl46im9L7hzZ0l4
   UAYVxp7F7PcHpxJ+1Yl7RnqTcH0tTjFNubh0PTwxDmqFwvmWcK4Rzg/d9J47d04vcvH3h6gonY5y
   xQpo1w4MA5sjM2HXrSUNM8+ZFUf9VCGwt4f9+y3dCgEleJj62DGlNmxQ6vr1ojm/KBEKa/4pPDxS
   ubq+rigXq2iwXeG+XNmPbaru+sBZffjnh+ri1YsZ1yoXo6i/U1EuJuNaCQlKBQQo9eijSlWtqpS3
   t1Lr1mX7/izMOTMhbuvSJaWWLVOqVy+lvvzS0q0pM8jHMLV1J/2Ij4egIBgwoFDbJEqPwtj4Hx8P
   CxbA3EWniR/SDnPls9gqO97v+j5TekzG3jajulFaLzw62kz9uooPejeh7qaNutpM5856yK9//zuu
   NM18Ht3rLblp/ISVuXZNZ2pbvhw2bgRPT736uV8/qFTJ0q0rE0pH0o/ERFizRg/r/fEHdO8u6f5E
   jgqyZzE6GubNgy9WRFP/if9xfdwCVMplAGxsDR5s2S1LIAZwbdQQ/5f66SHowED4t4EOwB9+CHXq
   5LrdMmcmiszOnfC//8Hw4fDFF1C9uqVbJHLBuiZYX3tN1wVeulT3Lk6cgB9/lEAscpSfPYvHj+tt
   58099vOL3X9Qz7fC85EEtj4dlPP+4MhIeO89vRd40CBdbzUoCHbvhokT8xSIhSgUOY04enrqjswz
   z0ggLkGsa5h6926dyqh27SJtkyg9cpvnNiIiinETfmJ3VA0SbOGuvl+QWi2cSZ0mMLbdWKpX1B9a
   WfJFJ17XuXf9/eGff2DwYN0L7ty5WFacCpGt0FA9BP3dd7Btm3wRtELWX8/YbNb5TBMTdREGIQrB
   7SeCY9AAACAASURBVOZflYLly8/y9MR/SRo5BBxPQ0oFav39INv/9z+a3d0k68muXdMpU/39de+i
   d28dgKVoiLCkEyf01N3y5bpAw9Chehj6vvvki6EVst5g/Pff+o307be6sseUKTBmTJFeV5RtZjP8
   9BP4fnSG0CofknzPEih/CWwUpNjDsvV4PbRVz9uazbqH4e+fsddyxAhdPjOXlWiEKFI+PnrL3PDh
   0K2bbOG0ctYbjO++W3+TGzKkSApMC5EmOVnH1Hc+P0hi64+46vITVaPuJnrNZzBgTMb+4CXbGH3P
   ayzpXlX3NqpX1z3gYcOgfn1LPw1RViklPd1SwHpXUx87Jm8wkS+5TegRE2fi/cUHWb76DNy/CKN/
   KC898CLj2v3LpLH/I+BMM1iyjVpOmxl27iBjkrvS4HAUdH9eD0u3bl38T04I0N8g16/XXwovXoTf
   frN0i4QFWNcCLiEyyc3irPPn4b/zzzEvsR3mKqcob1uBTx79mFH3jaKcrZ7jjTwYwsKer/BwbBJt
   OcAqHmez81Xe3ToLVzdXyz1BUXYpBVu36gD8ww/QooUegh40SBawlgLWO0wtwVjkw+0Serz33nR8
   /c4ScHwB5vbzSbaNBxT2NvZsHb2VTk5tdW/D3x9++43ETp348mpV1hpNqN2gnCTZEJZlNsNjj+k8
   +sOGgYv1vxcLI+1sWSHBWJQqnp7TCQqaecvtNVt8j6nVOoyWqxjccgiTHniWp39+mtDYUFpWcmFb
   +EM4fLcamjfX88BPPQU1aljgGQhBqZgHzu0WQqFZ75yxEPmQntCjnBmcDkHls3D/Qi7V38PrnlOY
   /MBxalWqBUePsi36EQ6vj8X9ioHDsMbw11/QqJGln4Ioq86c0fuAly/XC1enTLF0iwrEx2dZpkAM
   UJmwsJn4+OQ+7ay4PQnGwmq9884oNvz5ObED/cDxFKSUp8bfD/Hn9J00d6gKXwToYehTp3AYOpRO
   C3+RfZfCckwmWLVKl8vcvRsefxxmzICePS3dsgIrSNpZkTsFCsaGYUwBngbMwCFgtFIquTAaJsqu
   lBT4Yvk5Zv66jAvDPoZyF8EAG9vrfNOjJc0nTNL5d/v31ykqu3cHO/leKSzs2DEdjJ9+Wm9yL0VF
   GbIvMXr7tLMib/I9Z2wYhjOwHWiulEo2DONb4Fel1Nc3PU7mjEWuXL0K738Ryse75nHVdSU9nJ/i
   nT6jGfudF6GJUbQ8D9tO9MRh+Cjd66h88zd1IYqB2Vzmkm7InHHeFOsCrhvBeCdwL2ACfgQ+Vkpt
   uulxEoxFjkxJJnaEHcL/h/N8F7EIw3kv3s2e5/3GnXFauRZWrMDkWo/Dgx/C/akXcajf2NJNFmWR
   UrBvn54DXrFCZ2xzLVvb4qTsZ+4V+2pqwzAmAu8BV4ANSqkR2TxGgnEZk9stEL9tPUC/Nb1IqXQO
   UssxyWkCs+IrUyHgWz1W7e0NXl7QpMmtFxGiOISH6znggAC4fl3vBR4+XO8LFiIHxbqa2jCMakB/
   wAW4BHxvGMZwpdTy/J5TlHzZDWcFB2cdztp16DzPfvYxhyp9ChX1fLAdyTz64f9I9hhChWXLoGNH
   WYglLO/HH3VOaHlPiiJWkFUvPYFwpVQcgGEYq4AuwC3BeMaMGel/9/DwwMPDowCXFdbsdlsgBj47
   hNdWzSOi0re4x7ky+6cWfNMvmH9qQcXzLjx2dgtDzUvw79TJkk9BlEU5zQO//HLxt0WUOEFBQQQF
   BRXoHAWZM+4ALAbuB5KApcBfSqlPb3qcDFOXIemJOsqZwCkEzrlDvb+x7/YONnUPMOZ0I6YFRXDq
   Sg3mX5zOqnI9SXA6qR+X7ICn53T++OPWRB9CFLrkZFi3Ts8DnzoFf/5p6RaJUqJYh6mVUrsNw/ge
   2Adcv/Hn5/k9nygd6tWzgXJnYEwvqB2KYbaj5qVKTN2VzLhDblT28obZQ3nl9S8JCBgEyZXhVL0b
   R8tWCVHE0nJCBwTonNCtWmXkhBbCgiQdpihUwQf389jMF4lr/ScYYJsKk1e2ZPK8edR/5OH0x8lW
   CWERSsHgwdC+vc4J3bChpVskSiHJTS0KpCCJ4PeF7mHaZ68QVHE7fY4b/NnAjhjHJByv12br6N9p
   3dQ9x+vJVglRJMrgfmBhHSQYi3zLS0/VlGQi5FwI7lWbsG3FIub8vYCQamd4/Ggznu36Kp0meWEi
   mcOxh3Gv7Y5DeQeLPCdRBp0/r3NCBwRAr14wXfImi+InwVjk2+3KFWZOBG+6dpmu/2/vvqOrKrM+
   jn+fFEKoghQdihMB0SAoXVF546g0FX1VRmYCWFB5RceGjqAyMMPoOEqTXkUxASkWUBALGokCgiQI
   JNKLhBZqSAJJCDnvHw8BhATS7j03N7/PWqyVcnPPZt2cu3POfp69x7QgIW0r5bIdah4tz+3JD9Dv
   +f/SpO0fvB63CMeOwbx5NgHHxkLnznZ/eseOUK6c29FJGaSpTX7IWzNEL9oIfv16DkVPYcDGSay9
   JhUMZAUFMuaRxXRt3q7E4xEpsF274P33bQKeORMq606MlD5Kxj6sIA00SkpejeBrs5VHjv7Epv+5
   luE1thHVOIeKgbdSw2whJWAb4TXDuTW8aYnGIZKv3Dts5zbeaNQIFi3yfjwiJUi3qX1YQW8dl4Tc
   xL9n55PcUut9nkj+nvJ/WMbwLrVYWjWNkPV9eflPf+PZ3peTHZCqerB4z8aNZ1pSzpljx2SK+DDd
   pvYzXpshmp1N2PpEYpv+SocODfm6Bix2Agk4Vp+aW15ibLte9PxXxbOmFFbmhrrqkiUetHevveWc
   25Cje3c7oOH6692OTMQjlIx9mEdniDoOrFwJUVEwaxaHr6rPPzuHsu6E/XZOjmFo2yheGNrud3cF
   vVXDljLu44/hl1/gjTfsvOrAQLcjKrV0zpYOuk3twzzSGGPLFnu7LyrKfhrZhbfDDjF92+fkbOxA
   UP04MkO306RWOLGPxP7uNrQadUiJcxwNX/AgnbPu0NYmP1QijTFO7b1Mnfk+645spMmtf2ZNl5a8
   sXcRMduX4Kx6nLtqPs3gfnWo3zD/erA3a9jix3JybB/o6GhYsQJWrVJC9hCds+5QzdgPhYVdUbST
   5tgx+OwzewW8ZAmpd3Xg5ruTSchIJTjgA4J//Jrs2H48dN10+o+pxBWn83v+9WCv1bDFPyUknFmI
   VbmynVc9YIASsQfpnC09lIz9ycmTEBNjE/Cnn0KbNhAZScq08by64k3WrNxuH5Z1gu4BH/DWnJuo
   WbPgT+/RGrb4v8GDISwM5s+HZs2UhL1A52zpodvUpZ3j2IUu0dF25Wnt2tCzJ3TvzrbyGbzz0yje
   XfU+oXtv52DQapxLthNeM5ylvWMLvS1J9SeR0kXnrDtUMy5LfvvNJt+oKEhLIzXyAdZ1asG1be5m
   XfI6hi0bzlcbv6Pixt5UWPc0fbqHsuKXkWxN20OjKrV58199inQyariD5CkzExYutH8UhoXB22+7
   HZGconPW+5SM/d3hwzB3rn3DW7fOzmDt0YPUlk25+f32JCQnUC4whAo5tQhc8QJ1DzzCa3+vRLNm
   O+jYUX8dSwnLybG9oHNnAzdtaltSPvAAVKvmdnQirlEy9ke5VxxRUfDNN3DHHXbhS+fOEBLC0cyj
   DPx2IKNWjLKPPxlE64QY/vv0TURE2LKcVlSKR+zda38Pu3fXbGCRs2g1tb/IyYEffrBXHHPn2sUu
   PXrA1KlwySUA7Diyg1Exo5gW/x61j99KQEojnKrbaVgtnMUzmlE55MzTaUWleMRll0F8vNtRiPgF
   JWNfkphor4Bzt3707Anx8aTWrsa65HVcGxpIYtJPDF8+nK82f0PYkUfImRlP+071mfFsKplV8t4f
   rBWVUiQpKfb2c1QUvPaa7YQlIh6h29Ru273b9tyNioJ9+2zNLTLy9NaP1MxUbp52MwnJCYQEhlA1
   uAZ1dj7PlrmP8nivKjz3HGRkXLjdnVZUSoFlZsIXX9g/CL/6Cm67zd6V6dIFypd3OzqRUkE149Ii
   NRU+/pjjU6aSs2IlS6pfzeomzeg+YRBhDa8887DMVP7x3T8Y+dNI+4WcQKp9GsNL3W/mySftHeuC
   JlqtqJQCmToVpk+3CVgLsUSKRMnYl504Ya80oqLgiy9Ib92aAWvLM3nfNDKowdlJNKh6AKNXjGZq
   /FSuCmnP6t3ryAjZQZ1y4cQ9HUutS87chtbiLClR6hUtUmxFScYqGnqS48Dy5fD001Cnjp1A0749
   bN5Mn9o3M3rfh6cSMUBFthy/h1vH3sV1E65jXWI2NT9exbF3P2Fsszhiey/h15d+n4hBi7OkkHbv
   hmHDbP03K+v87ysRi7hCC7g8YdOmM5ORAgPtLb9ly6BBg9MPOZ1EQ45AqwnQeD5U2cWxTXdQ5bNh
   pF9WlRGDoFMnMKYykHe/aC3Okos6etSOJIyOtkMZ7r3XLsgK0ukv4it0m7qkJCfDrFk2Ae/YYfde
   RkZCq1Z5Xm082PMVZm+pCLf9CwKz4Eh9mBhH3Rr7mTXratq1K9hhtThLLqpbN3sVHBkJd98NoaFu
   RyTi11Qz9rZjx2DePJuAf/zRvtFFRsLtt+d71ZF0NIkxK8Yw6edJHNtehcxaSRB4ErKDqbXwCZbP
   fanQSVSLs+SCcnIgQHdKRLxFydgbTp6Eb7+1CXj+fGjb1u4HvuceqFQp3x+L2xPH8GXDWbhpIV2v
   6EXmkmdYOKc6mZGtyayylUtO1GTJI4tpelUTL/5nxC/klkWysuy6BBFxlTpweYrj2E5DUVEwcybU
   q2frwG+9Zack5SMlI4WJqyYyf8N8fkv5jfvqPEP7+DEsGHoJffvCqEQoXyWOhP15N+sQyde5ZZEH
   H4SHHnI7KhEpIl0ZX8j27WcmI2Vk2AQcGQmNG1/wx9Kz0pm4aiIDFg8g62QWtULqc8338WxeW51+
   /eDxxy94ES1yYcePw5VXnmnIcYGyiIh4n66MS8CO1Wv4ps+rtNqwhisz9uM8cD9VpkyBG2+86LaP
   3am7GbNiDJPjJhNeI5zsk3Z7UfKxPTzWdSNfzbuBcuW88b8QvxYaakdoBge7HYmIlBCt6gB71fvR
   R6R37ET1lq2psiKIgSmjuTRzFy2W12bb5XUumIjj98TT65NeXDvuWlKOp9Gv6nL2DPuckJQmBBFM
   s8vD6f9oEyViKRjHgdWr4cUX4csv836MErGIXym7t6lzcmDJkjOzWJs3Z9Kxyry0fBxH+cNZD8y7
   m1VKRgqT4yYzf8N8th7eSp/rn8HEP86EEdVo0gT694eWN6aSeED1YCmg3347UxZJS7O3oHv3hrAw
   tyMTkULQbeqCWLfOvtnNmGH77vboAWvWQN26zLx10DmJGM7tZnXsxDEmrZpE/2/6k3kykzqV6tM9
   ZQ2jHqzOn/5kF1i3aJH76MrcUDfvZh0iv7N4Mfz5z7Yf9IQJ0K6dtiOJlCF+kYxz99nmN7WIpCS7
   Cjo6Gg4etIuwFiyApk1/9zwX6ma1J3UPY1eOZdKqSfyx0h/JPHECAmDXkT2s2RXP0qW30aiRF/6z
   4p9uucW2qgwJufhjRcTvFOtPb2NMVWPMHGPMr8aYBGNM25IKrKByO1BFR79ITIwdmnDHHaPZvmYd
   TJtmV5w2awYbNsDIkXYbyJtvnpeIAYYMeZgGDQZhEzJAOnVbPUlGp7WEjwvnSMYR/tPoYxJffRuS
   r4XsYDhwNZuXziMoaIc3/9tS2jgOLF1q+5Snpp7//XLllIhFyrBi1YyNMe8B3zuOM80YEwRUcBzn
   6DmP8WjN+OypRcFk0ZEv6cF73B28gAp3dra3oe+8s8CzWLdt28HL/xhPnIkj9fKNmEszeK7dc1x/
   8gnGDavO11+nkZFRDsplQq0ESG4CWQGakiR527TJlkWiouyiq549bUKuWtXtyETEQ7xaMzZ2esEt
   juM8DOA4TjZw9II/5AG7kk5yI78QSTR/ZjbruZooejCjbQPmffJWoZ7r+InjfJY8j/mNR5J5MpN6
   Verx1pUJjHvlUiYlwUsvwZEjI4iNHQhZ5SDpTD1YU5LkPK+9BlOm2D7ls2fbxQSaiiQieShOzfhK
   4IAxZhpwHfAz8KzjOMdLJLKL2bABoqP5cNUYDjGLKHrRhhVsJwxIJ/KKoQV+qr1pexm3chwTV02k
   UfVGZOdkA7Dz8F5eG7GJIU9eSrdutq/Cjz/moClJUiDPPQeDB6shh4hcVHEySBDQAhjrOE4L4BjQ
   v0Siys++fTBqFLRpAxERkJZGdvR07r7yLt7gudOJuEGDQQwZ8vBFn27tvrU8Ou9Rrhl7DfvT9/NV
   9yXcd+wLAg5eizkZTFilcOIWNeEvfznzfppXXbmgxxM/k5MD330Ho0fn/f0aNZSIRaRAivNOkQTs
   dBzn51OfzwVezuuBgwcPPv1xREQEERERBT9Kejp8+qldCb10KXTtCv/+tx2OHhREHeDrpk0ZOHDo
   WVOL8h4fmJqZytp9a9mXvo/xP49nXfI6nmr9FD/32sSsaTXo+Jid+7CgXyyVr8x7f3BY2BV8/fXf
   Lnq8i67wltIrd3tcdDRceik8+qjbEYmIi2JiYoiJiSnWcxR3Adf3wOOO42w0xgzCLuB6+ZzHFH4B
   V3a23XcZFQWffWb3XEZG2qHoFSte/OfzsD99Py0mtSDpaBLlg8ozosMIOl3+CONGhTB1Ktx1F/z9
   79CkBIYmacawn3Icuzp/40b7+9ijR56r8kWkbPP6CEVjzHXAFCAY2Ao84jhOyjmPKVgydhxYtcpe
   bcycCVdcYd/sHnwQatUqcozJ6cmMXzmeEctGkJKZAgZMTiC37/ySnz+9jZ494YUX7OFKytkrvM/I
   u5OXlDIbNkDDhhAY6HYkIuKjvN6By3GcX4DWxXkOtm2zCTgqCk6csAl4yRK46qpiPW3i/kRGLBvB
   3F/n0rleZyp9chcpLddAjfU4B65h5YJUvvl6Jy1b1ivWcfKya1cOv0/EcG4nL/FR2dl2XnX58tC+
   /fnfv8jELhGRonBndcnBgzBnjk3AGzZAt262QccNNxR560duPXj/sf1MWDWB+D3xPNX6KTY8tZG/
   3ruQXSsj4Zfjp/cGH8kKYMQIz1ypXqiTl/ig3MEMH3xwZl71q6+6HZWIlCHeS8bHj8Pnn9sEHBMD
   nTvbaQodOlDccUYH0g/QfFJzko4mERIYwvCOw/mo2yd8uaA8d98Ga9d2AYIgq7JX9gYPGfIwy5cP
   Oq9mPGTI3zxyPCmG7dvtgoHcwQzffQdXX+12VCJSxngnGffuDZ98Ai1b2oUvH3wAVaoU+2n3p+9n
   ws8TGPnTSA4fPwxAjpPD7lUtaNGzPFWqwIABMHfuOGbMOL+G66kr1YKuuBYfULcujB8PN92kwQwi
   4hrvjFAcOtR2IapTp0Sec/2B9YxYNoLZibO5/5r7ebzF4zw2vw+J+xMJOBhO+02xvPb3ykRE2Lve
   Wt1cxmVnw1df2f3pNWq4HY2I+Dmvr6Yu0AEusJq6oHtxc+vBhzIOMeHnCazcvZInWz3Jk62eJDCj
   NqNHw5jJqVx/RwKDn2rCLW3Onx2ce6wzV6ra9+vXHAfi4uxdmA8/tDOBJ03SViQR8bhSlYwLerV6
   8NhBmk9szs6jOwkJDGFoh6H0bt6b5N2hDBtmS9DdusGLL6IRhmItWmT3q2Vm2jpwjx765RARrylK
   MnatSDZw4HtnJWKAimzZ8k8GDnwPsEn4jdg3aDymMUlHkwBbD652vBV9eofSogWEhkJCAkycqPda
   OUtYGEyeDJs3wz//qV8OEfF5riXj/Pbibj68n74L+tJwdEM2H9rM53/5nGa1mxFkgglNC+f5Hk24
   5hrYsgX++1+4/HI3ohfXnThh26PmpXFjuyBLE5JEpJRwrYv96b245XKg1loofwRaj2V1gxg6VOjH
   r0/9Su2Kl/HFF1BhViw10xN46aEm/N/GyoSGuhW1uCq3S1tuHbhhQ9ugIyTE7chERIrF1Zrxn+58
   i+0d50PVJDhZjkvjbiJ25HgahTVm9mx48017cdO/P6dHGEoZNWECvPMOZGWpDiwiPs3r7TCL6tDx
   Q8zaNZOUnjMh8zAYCAjIZsyAZ/ju68Z0eRvq17e3oTt10t1GAWrWhClT7NAQ/UKIiJ/x6pXxpoOb
   eOend5ixdgZdG3fliRZP0HdhXxL3J3JpTjgnp8RyY4vKvPyyfc+VMiY7G3bvtn+JiYiUUj57Zbxo
   8yIm/DyBH3f+SJ+WfUjom8DllS9n926I2BrLtgUJ3Nq6Ca8uqnzeCEPNBfZzjgPx8TB9uq0D33WX
   vQIWESlDvHJlHPCPQF5p8woDOvSnQnAFNm2Ct9+GuXO54AhDdc7yY1lZMHy4XYx1/Lj9RVAdWET8
   gM9eGefkBDBtyGZan0whKqoC330HffvagU01a+b/c/nvRdZc4FIvOBhSUuwmcW1DEpEyzjsLuA6E
   syt+HN27B/D66/Duu1Cp0sV/THOB/UB2tr0KrlDh9183Bv7zH3diEhHxMd5p+vFuLGRdQps2I3n+
   +YIlYjh7LvDZNBe4VPjlF+jXz84GjopyOxoREZ/mnayWVRlIp27dwtWnhwx5mAYNBnEmIefOBX64
   RMOTEnLgAAwdCtddB127Qvnydj7wE0+4HZmIiE/zygIuSCvywitNWypFEhLsoqxeveCWWzQfWETK
   JJ+d2hQZOVhJ1J/k5CjRiojkw2eTsaePIV6SmGi3IkVFweLFcNVVbkckIuJzStUIRSklkpNh1Cho
   1Qpuvx1OnoSFC5WIRURKkEYvyIV98AGsXg1vvAG33QaBgW5HJCLid3SbWkREpATpNrUU3pYtMHiw
   HY+lP5pERFyhZFwWHT4MkybBzTfDjTfaz19/3e2oRETKLN2mLosiImxT8F697BVxcLDbEYmI+A1t
   bZKC0T5hERGP8dmpTeJlu3ZBdLRtR/nMM+d/X4lYRMSn6F3ZX6Sn22YcHTpA06aweTO0bet2VCIi
   UgC6MvYHhw9DgwZ2MdZjj8G8eRAa6nZUIiJSQKoZ+4vDh6FaNbejEBEp87TP2J8dPAhjx9puWHlR
   IhYRKbWKnYyNMQHGmDhjzPySCEjOkpUFn34K991nb0P/+KPaUYqI+KGSqBk/CyQCVUrguSRXTAx0
   6wbh4XY/8LRpULWq21GJiIgHFKtmbIypC0wDXgdecBynax6PUc24KI4csXXgsDC3IxERkUJwo2Y8
   AngJULYtirQ0mDEDsrPP/94llygRi4iUEUVOxsaYO4F9juOsBsypf3IxOTmweDE89BDUqwczZ8Kh
   Q25HJSIiLipOzfgmoKsxpgsQClQ2xkx3HKfXuQ8cPHjw6Y8jIiKIiIgoxmFLsWnTYNAgqFHD1oHf
   fhtq1XI7KhERKYaYmBhiYmKK9Rwlss/YGPM/QD/VjC9ixQrbjKNpU7cjERERD1Fval+QlQXr10Oz
   Zud/r00b78cjIiI+Tx24SoLjQFwcTJ9ua8Bt28Jnn7kdlYiIuEAduNwwcqS97dytm+2CtWyZErGI
   iBSKblMXV2AgjB8PN92k0YQiIlIkuk1dEI4DR4+qA5aIiFyUblOXtK1bYfBg2xd6yBC3oxERET+l
   ZHyu48dh6lRo394uxDp0CObMsXuCRUREPEA143NlZ8OXX8ILL0CXLlCunNsRiYiInyvbNWPHAaMu
   niIiUnJUMy6IgwdhzBho3Ro+/tjtaERERMpIMs7Kgnnz4L777GKspUvh3/+Ge+91OzIREZEyUjNe
   uBCGDbOTkqZN0xYlERHxKWW7ZiwiIlLCym7NOCMDZs+2t51TUtyORkREpFBKbzJ2HNsHuk8fqFMH
   Jk+G+++HkBC3IxMRESmU0lsz7tcPFiyAhx+G1auhXj23IxIRESmS0lszTkuDihW1T1hERHyKf9WM
   c3Lg++/tiMK8VKqkRCwiIn7B95Lxli0waJDdD/z0025HIyIi4nG+VTP+3/+FH36Av/4VPvoImjfX
   1a+IiPg936oZr1kDV1+t4QwiIlJqFaVm7P1kvHEjHD0KrVp59LgiIiJu8N0FXEeOwMSJ0K6dnRO8
   cqVXDisiIlIaeOfKuGpVuOMO2xu6Y0cIDvboMUVERNziu7epDx6E6tU9ehwRERFf4LvJWIMiRESk
   jPDdmrGIiIjkS8lYRETEZUrGIiIiLlMyFhERcZmSsYiIiMuUjEVERFymZCwiIuIyJWMRERGXKRmL
   iIi4rMjJ2BhT1xjzrTEm0Riz1hjzTEkGJiIiUlYU58o4G3jBcZxw4EbgKWPM1SUTlviKmJgYt0OQ
   ItJrV7rp9StbipyMHcfZ6zjO6lMfpwG/AnVKKjDxDXpDKL302pVuev3KlhKpGRtj/ghcD/xUEs8n
   IiJSlhQ7GRtjKgFzgWdPXSGLiIhIIRRrhKIxJgj4HPjCcZx38nmM5ieKiEiZ4tV5xsaY6cABx3Fe
   KPKTiIiIlHFFTsbGmJuAJcBawDn17xXHcRaVXHgiIiL+r1hXxiIiIlJ8HuvAZYzpZIxZb4zZaIx5
   2VPHEc8wxmw3xvxijIk3xqxwOx65MGPMVGPMPmPMmrO+Vs0Y85UxZoMx5ktjTFU3Y5T85fP6DTLG
   JBlj4k796+RmjJK3/BpgFfb880gyNsYEAGOAjkAT4C9qCFLq5AARjuM0dxynjdvByEVNw55vZ+sP
   fOM4TmPgW2CA16OSgsrr9QMY7jhOi1P/VAL0Tfk1wCrU+eepK+M2wCbHcXY4jnMC+BC4x0PHEs8w
   qHd5qeE4zg/A4XO+fA/w/qmP3wfu9WpQUmD5vH5gz0PxYfk0wKpLIc8/T73Z1gF2nvV5EurOVdo4
   wJfGmJXGmMfdDkaKpJbjOPvAvmEANV2ORwrvKWPMamPMFJUZfN9ZDbCWA7ULc/55Khnn9decVoqV
   Lu0cx2kFdMG+IdzsdkAiZcw4oIHjONcDe4HhLscjF5BHA6xC5TxPJeMkoP5Zn9cFdnvoWOIBgSg5
   RAAAASJJREFUp/6Sw3Gc/cAn2NKDlC77jDG1AYwxlwHJLscjheA4zn7nzHaXyUBrN+OR/J1qgDUX
   +MBxnHmnvlyo889TyXgl0NAYc4UxphzQHZjvoWNJCTPGVDj1Vx7GmIpAB2Cdu1FJARh+f1dqPvDw
   qY8fAuad+wPiU373+p16A891HzoHfdm7QOI5nSgLdf55bJ/xqWX472AT/lTHcd70yIGkxBljwrBX
   ww4QBETr9fNtxpgZQARwKbAPGAR8CswB6gG/Ad0cxzniVoySv3xev1ux9cccYDvQJ7cGKb4jvwZY
   wApgNgU8/9T0Q0RExGXauiIiIuIyJWMRERGXKRmLiIi4TMlYRETEZUrGIiIiLlMyFhERcZmSsYiI
   iMuUjEVERFz2/wjGkx3JrSv/AAAAAElFTkSuQmCC
   "
   >
   </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>