Kernel Density Estimation
=========================


.. _kernel_density_notebook:

`Link to Notebook GitHub <https://github.com/statsmodels/statsmodels/blob/master/examples/notebooks/kernel_density.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">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
   <span class="kn">from</span> <span class="nn">scipy</span> <span class="kn">import</span> <span class="n">stats</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.distributions.mixture_rvs</span> <span class="kn">import</span> <span class="n">mixture_rvs</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">
   <h4 id="A-univariate-example.">A univariate example.<a class="anchor-link" href="#A-univariate-example.">&#182;</a></h4>
   </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">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="mi">12345</span><span class="p">)</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[3]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">obs_dist1</span> <span class="o">=</span> <span class="n">mixture_rvs</span><span class="p">([</span><span class="o">.</span><span class="mi">25</span><span class="p">,</span><span class="o">.</span><span class="mi">75</span><span class="p">],</span> <span class="n">size</span><span class="o">=</span><span class="mi">10000</span><span class="p">,</span> <span class="n">dist</span><span class="o">=</span><span class="p">[</span><span class="n">stats</span><span class="o">.</span><span class="n">norm</span><span class="p">,</span> <span class="n">stats</span><span class="o">.</span><span class="n">norm</span><span class="p">],</span>
                   <span class="n">kwargs</span> <span class="o">=</span> <span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">loc</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span><span class="n">scale</span><span class="o">=.</span><span class="mi">5</span><span class="p">),</span><span class="nb">dict</span><span class="p">(</span><span class="n">loc</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span><span class="n">scale</span><span class="o">=.</span><span class="mi">5</span><span class="p">)))</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[4]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">kde</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">nonparametric</span><span class="o">.</span><span class="n">KDEUnivariate</span><span class="p">(</span><span class="n">obs_dist1</span><span class="p">)</span>
   <span class="n">kde</span><span class="o">.</span><span class="n">fit</span><span class="p">()</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[5]:
   </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">hist</span><span class="p">(</span><span class="n">obs_dist1</span><span class="p">,</span> <span class="n">bins</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="n">normed</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="s">&#39;red&#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">kde</span><span class="o">.</span><span class="n">support</span><span class="p">,</span> <span class="n">kde</span><span class="o">.</span><span class="n">density</span><span class="p">,</span> <span class="n">lw</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="s">&#39;black&#39;</span><span class="p">);</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   
   
   <div class="output_png output_subarea ">
   <img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAsEAAAHfCAYAAACxhQUCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzs3Xl8lOW9///XBWERZBMVFNzFHanI5npi3UBPq1VbXGrr
   Umtr7Wpb9bSn0l/b47E9XWy1LqeL1eqxLj+XalVqJYIbKghuYNVSK4gLIIIIhCT394+ZhIAhmcDM
   XPfM/Xo+HnnMncyd6/oYNfPONZ/7ukOSJEiSJElZ0iV2AZIkSVK5GYIlSZKUOYZgSZIkZY4hWJIk
   SZljCJYkSVLmGIIlSZKUOR2G4BDC+BDC3BDCyyGEC9t4/pshhGfyH8+FEBpCCP1LU64kSZK06UJ7
   +wSHELoCLwFHAAuAp4BTkiSZs4Hz/x34WpIkR5SgVkmSJKkoOloJHgO8kiTJP5MkWQPcDBzXzvmn
   Av9XrOIkSZKkUugoBA8BXm/1+fz81z4khNALOBq4vTilSZIkSaVR08Hznbmn8seAR5IkWdrWkyEE
   788sSZKkskiSJLT3fEcrwQuA7Vp9vh251eC2nEwHrRBJkvhRpI9LLrkkeg3V8uHP0p9nmj/8efqz
   TOuHP09/nmn+KERHIfhpYFgIYccQQndgInD3+ieFEPoBhwJ3FTSrJEmSFFG77RBJkjSEEM4HHgC6
   Ar9NkmROCOHc/PPX5E89HnggSZKVJa1WkiRJKoKOeoJJkuQ+4L71vnbNep//AfhDcUtTe2pra2OX
   UDX8WRaXP8/i8udZPP4si8ufZ3H58yy/dvcJLupEISTlmkuSJEnZFUIg2cQL4yRJkqSqYwiWJElS
   5hiCJUmSlDmGYEmSJGWOIViSJEmZYwiWJElS5hiCJUmSlDmGYEmSJGWOIViSJEmZYwiWJElS5hiC
   JUmSlDmGYEmSJGWOIViSJEmZYwiWJElS5hiCJUmSlDmGYEmSJGWOIViSJEmZYwiWJElS5hiCJUmS
   lDmGYEmSJGWOIViSJEmZYwiWJElS5hiCJUmSlDmGYEmSJGWOIViSJEmZYwiWJElS5hiCJUmSlDmG
   YEmSJGWOIViSJEmZYwiWJElS5hiCJUmSlDmGYEmSJGWOIViSJEmZYwiWJElS5hiCJUmSlDmGYEmS
   JGWOIViSJEmZYwiWJElS5hiCJUmSlDmGYEmSJGWOIViSJEmZYwiWJElS5hiCJUmSlDmGYEmSJGWO
   IViSJEmZYwiWJElS5hiCJUmSlDmGYEmSJGWOIViSJEmZYwiWJElS5hiCJUmSlDmGYEmSJGVOTewC
   JEkqlxBCwecmSVLCSiTFZgiWJGVKIdG28KgsqVJ12A4RQhgfQpgbQng5hHDhBs6pDSE8E0J4PoRQ
   V/QqJUmSpCIK7b3dE0LoCrwEHAEsAJ4CTkmSZE6rc/oDjwJHJ0kyP4SwZZIki9oYK/GtJUlSTCGE
   gleCfc2SKlcIgSRJ2n1Tp6OV4DHAK0mS/DNJkjXAzcBx651zKnB7kiTzAdoKwJIkSVKadBSChwCv
   t/p8fv5rrQ0DtgghTAkhPB1COL2YBUqSJEnF1tGFcYW8F9QNGAkcDvQCHg8hPJEkycvrnzhp0qSW
   49raWmprawsuVJIkSWpLXV0ddXV1nfqejnqCxwGTkiQZn//8YqApSZLLWp1zIbBZkiST8p//Brg/
   SZLb1hvLnmBJUlT2BEvZUIye4KeBYSGEHUMI3YGJwN3rnXMXcHAIoWsIoRcwFnhxY4uWJEmSSq3d
   dogkSRpCCOcDDwBdgd8mSTInhHBu/vlrkiSZG0K4H3gWaAL+N0kSQ7AkSZJSq912iKJOZDuEJCky
   2yGkbChGO4QkSZJUdQzBkiRJyhxDsCRJkjLHECxJkqTMMQRLkiQpcwzBkiRJyhxDsCRJkjLHECxJ
   kqTMMQRLkiQpcwzBkiRJyhxDsCRJkjLHECxJkqTMMQRLkiQpcwzBkiRJyhxDsCRJkjLHECxJkqTM
   qYldgCRJ7QkhFHRekiQlrkRSNTEES5JSr6N4W1hMlqS1bIeQJElS5hiCJUmSlDm2Q0iSqt7SpUuZ
   MmUKAD8AtgEOBPaKWZSkqEK5LiQIISRetCBJ6qwQQkE9wW29xrzyyitccskl3HbbbdTX13/o+f3J
   heIJBY4nqTKEEEiSpN3LBWyHkCRVnaamJi677DL23HNPbrrpJtasWcOhhx4KwHeAk4H+wAzgGOB0
   4INo1UqKwZVgSVKqdXYleMWKFUycOJF7770XgDPPPJNLLrmEHXbYYZ2xVgJXApOAFeRWhScDW1D4
   bhO+rknpVMhKsCFYkpRqnQnB7733HscccwyPPfYYAwcO5IYbbmDChLXNDm2N9QJwHPAqMBJ4iNwq
   8ca2YEiKzxAsSap4hYbg1atXM2HCBB566CG22247Jk+ezB577FHQWAuAWuAV4GPAnzEES5XMECxJ
   qniFhuBPf/rT/PGPf2Tw4ME8/vjj7Ljjjp0a61VgNPBu/nNDsFS5DMGSpIpXaAgG6N27N1OnTmXk
   yJEbNdZk4Oj88Qxy7RHtzenrmpRO7g4hSap6z7Y6vvbaazcYgAtxFPCV/PEZwJqNL0tSyhmCJUkV
   aw3wmfzx2WefzamnnrrJY/5X/vE54KpNHk1SWtkOIUlKtfZaGH4CfLuT4xXyStT8HuoA4GVg4AbO
   8XVNSifbISRJVeufwCWtPk8K+OiMw8ldJPfDTS1UUioZgiVJFekicje8OLlE4/9P/vFq4M0SzSEp
   HkOwJKniPA38CegB/LhEc3yE3E00VrE2EEuqHoZgSVJFSYAL88dfAbYr4Vz/mX+8CninhPNIKj9D
   sCSpojyU/xgAXFziufYHJgAfANe28XwIoaAPSeljCJYkVZRL848XkAvCpfb1/ONVfHjf4GJfjCep
   fNwiTZKUaq23SHsKGAP0Af4F9G8+h8K3PuvseQmwFzCXXB/ypzZmLF//pLJyizRJUlVpXgX+ImsD
   cKkF4Mv541+WaU5JpedKsCQp1ZpXgl8Gdge6A/OAbVqfQ+lWggHeB7YFlgMvAnt2dixf/6SyciVY
   klQ1riYXOk9h3QBcDpsDE/PH15V5bkml4UqwJCnVQgisAIaSu4PbU8Co9c+htCvBAI8BB5EL4P8C
   unVmLF//pLIqZCW4plzFSJLUWme2DvsTuQA8mg8H4HI5ABhGri1jcqQaJBWP7RCSpGgK3WLsqvzj
   eeUusJUAnJE//n3EOiQVh+0QkqQoWm991u55+ccBwAJgsw2cU+p2CIDXge2BnuRup2w7hJROXhgn
   Saoap9B2AC6n7cj1Ba+KXIekTWcIliSlVkOr489Eq2Jdn+r4FEkVwBAsSUqtB/OPw8jdKS4NTmRt
   i8bymIVI2iSGYElSat2Qf/wMa4NnbEOAg/PHf45ZiKRNYgiWJKXScuCO/PGnYxbShuaWiFuiViFp
   UxiCJUmpdA+wMn+8Y8Q62nJC/vEB4IOYhUjaaIZgSVIq3R67gHZsm39cBfwtZiGSNpohWJKUOh8A
   98UuokD2BUuVyRAsSUqd+8kF4bTsCNGee4Cm2EVI6jRDsCQpdZpbIU6MWkXHtgMWAjNjFyKp0zoM
   wSGE8SGEuSGEl0MIF7bxfG0I4b0QwjP5j++WplRJUhasJre6CukPwf+ef7QlQqo87YbgEEJX4Apg
   PLAXcEoIYc82Tn04SZL98h8/LEGdkqSM+BuwDBgB7BK5lo58LP94d9QqJG2MjlaCxwCvJEnyzyRJ
   1gA3A8e1cV5a9jCXJFW4e/OPbb3YpM1hQC9gFrm2CEmVo6MQPAR4vdXn8/Nfay0BDgwhzA4h/CWE
   sFcxC5QkZUfC2hB8bMxCCtQT+Lf88YPtnSgpdWo6eD4pYIyZwHZJknwQQpgA3Ans1taJkyZNajmu
   ra2ltra2sColSZkwB3gN2AoYFbmWQh1Fbju3ycDpkWuRsqquro66urpOfU9Ikg3n3BDCOGBSkiTj
   859fDDQlSXJZO98zD9g/SZIl6309aW8uSVK2hBA+tNLyP8C3gM8Af2g+j45XZAo5p9jnNZ/zIrA3
   MAh4gw+/xRoAX/+k8gohkCRJu+26HbVDPA0MCyHsGELoDkxkvf7/EMKgEELIH48hF6yXfHgoSZLa
   19wKcUzUKjpnT3J9gm8Bz0WuRVLh2g3BSZI0AOeTuz36i8CfkiSZE0I4N4Rwbv60k4DnQgizgF8A
   J5eyYElSdXoPeAToSq7FoFIE1tb715iFSOqUdtshijqR7RCSpFbWb4e4DfgkcAgwtfV5pLsdAnJb
   J50CHEmuN/hD5/n6J5VVMdohJEkqi/vyj5XUCtHsCHJhdyqwMnItkgpjCJYkRZewtpXg6JiFbKQt
   gZHk7nY3LXItkgpjCJYkRfcKuU3pB5K7U1wlOjz/WBezCEkFMwRLkqL7W/7xMCr3hak2/1gXsQZJ
   havU3zWSpCrSHIKPiFrFpjmI3M4WTwHvR65FUscMwZKkqJqAh/LHh7d3Ysr1BfYHGoDHItciqWOG
   YElSVLOAJcD2wC6Ra9lUtfnHuog1SCqMIViSFFXrVoh2N/WsALX5x7qINUgqjCFYkhRVcwiu5FaI
   ZvYFS5XDECxJiqaetfvqVkMIti9YqhyGYElSNE8CHwB7A4Mi11IstfnHuog1SOqYIViSFE3zKvCh
   Uasortr845SYRUjqkCFYkhRNNYbgg8i9uD5NbpVbUjoZgiVJ0TyafzwkahXF1RcYTq4v+KnItUja
   MEOwJCmaZcBOwJDYhRTZwfnHR9s9S1JMhmBJUlTVtArc7KD8oyFYSi9DsCQpqmrqB27WHILdJk1K
   L0OwJKnskiRpOa7GleDtgaHA0tiFSNogQ7AkqexefvllALYGhsUtpWQO6vgUSREZgiVJZTd16lQg
   1woR4pZSMoZgKd0MwZKksps2LbdDcDW2QjQ7uONTJEVkCJYklV0WQvBwYPP88cKFC2OWIqkNhmBJ
   UlktXLiQefPmAbBv5FpKqQYYlz9+9FE3S5PSxhAsSSqrJ554ouW4a8Q6yqFlv2BDsJQ6hmBJUlk9
   /vjjsUsoG0OwlF6GYElSWbVeCa52Y/OPs2bNYtWqVVFrkbQuQ7AkqWzWrFnD008/HbuMsumbf1yz
   Zg2zZs2KWoukdRmCJUllM3v2bFauXMluu+0Wu5Symz59euwSJLViCJYklU1zP/C4ceM6OLP6GIKl
   dDEES5LKprkf+IADDohcSfkZgqV0MQRLksqmeSU4ayG4V69e/OMf/+Cdd96JXYqkPEOwJKks3nrr
   LebNm0fv3r3Ze++9Y5dTVqNGjQJcDZbSxBAsSSqL5laIMWPGUFNTE7ma8mrugTYES+lhCJYklUVW
   WyEAxo7N7RhsCJbSwxAsSSqLLO8M0ToENzU1Ra5GEkBIkqQ8E4WQlGsuSVK6NDQ00LdvX1auXMnb
   b7/NVlttRQiBQl4VAnR4XiHnFPu8To2VJAwdOpQFCxbw4osvsueeexbwnZI2VgiBJElCe+e4EixJ
   Krlnn32WlStXsuuuu7LVVlvFLicK+4KldDEES5JKrvmiuCy2QjSzL1hKF0OwJKnknnrqKSC3M0RW
   NYfg5j8IJMVlCJYklVxzCB49enTkSuLZf//96dq1K8899xwrVqyIXY6UeYZgSVJJvf/++8yZM4ea
   mho+8pGPxC4nmt69e7PPPvvQ2NjIrFmzYpcjZZ4hWJJUUjNnzqSpqYnhw4fTs2fP2OVE1bwS3rwy
   LikeQ7AkqaSefvppYO2tg7Os+WfQ/DORFI/7BEuSii6EdrfnbJGlfYIBZsyYwahRo9h9992ZO3du
   Ad8taWMUsk+wIViSVHStb4SxK/Aq8AzQuiM4WiCNMWf+9a++vp4+ffpQX1/Pe++9R9++fQsYQVJn
   ebMMSVJUS8gF4J7A3pFrSYPu3bszYsQIILcqLCkeQ7AkqWSaO1/3A7rFLCRF7AuW0sEQLEkqmeY9
   ELK7O/CHNe8QYQiW4jIES5JKxhD8Yc0rwW6TJsXlhXGSpKJrvjBuCPAGMBfYff1zyN6FcQANDQ30
   7duXlStXsmjRIgYOHFjAKJI6wwvjJEnRvJH/6AsMi1xLmtTU1LDffvsBXhwnxWQIliSVRHPH6/74
   YrM+7xwnxefvJUlSSdgPvGHuECHFZwiWJJWEIXjDDMFSfF4YJ0kquhACW5C7WcY/gR3aOodsXhgH
   0NTURP/+/Vm+fDkLFy5k8ODBBYwkqVBFuTAuhDA+hDA3hPByCOHCds4bHUJoCCGcsDHFSpKqyxJg
   K2D72IWkUJcuXdh///0BV4OlWNoNwSGErsAVwHhgL+CUEMKeGzjvMuB+cn/0SpLEaHxR2BBbIqS4
   2m2HCCEcAFySJMn4/OcXASRJ8t/rnfc1oJ7c77t7kiS5vY2xbIeQpIwIIRd9vwd8f0PnkJ12iEL4
   GikVTzHaIYYAr7f6fH7+a60nGQIcB1yV/5L/F0uSAC+Ka5a08fFq/rmtYxUlZVxNB88XEmh/AVyU
   JEkScn/6bzB1T5o0qeW4traW2traAoaXJFWSxsbGlmND8IbtBAwA3o5diFQF6urqqKur69T3dNQO
   MQ6Y1Kod4mKgKUmSy1qd8w/WBt8tgQ+Ac5IkuXu9sWyHkKQMePHFF9l7773ZDvhXO+dlqR1iQ+cd
   Bfw1f+xrpFQ8xWiHeBoYFkLYMYTQHZgIrBNukyTZOUmSnZIk2Qm4Dfji+gFYkpQdzXdBcxW4Y/vH
   LkDKsHbbIZIkaQghnA88AHQFfpskyZwQwrn5568pQ42SpApiCC6cIViKx5tlSJKKauzYsTz55JM8
   CBzeznlpa02IMec/gF3yx01NTS27akjaNIW0QxiCJUlFU19fT58+faivr+ddoH8756YtkMaYMwG2
   AJYC8+fPZ8iQIRs4U1JnFOWOcZIkFer555+nvr4eaD8AKycAI/PHM2fOjFmKlDmGYElS0TT3A6tw
   zSF4xowZUeuQssYQLEkqGkNw5zVfHOdKsFRehmBJUtEYgjvPdggpDi+MkyQVxQcffEDfvn1JkoSm
   pqayXsxWqRfGATSR24MU4M0332TQoEEFjCqpPV4YJ0kqm1mzZtHY2Mjee+8du5SK0vqF2NVgqXwM
   wZKkonj66acBGD3a22RsLEOwVD6GYElSUTT3A48aNSpyJZXLHSKk8jEES5KKwpXgTedKsFQ+Xhgn
   Sdpky5Yto3///tTU1LB8+XJ69uzphXGdHGuzzTZj5cqVLFq0iIEDBxYwsqQN8cI4SVJZzJw5kyRJ
   GDFiBD169IhdTkX6yEc+ArgaLJWLIViStMnsB950+++fu22GIVgqD0OwJGmT2Q+86UaOzN02w4vj
   pPKwJ1iStMl23nln5s2bx+zZs9l3331z/XgdfE9a+3NjzNlu4+J6fC2VOlZIT7AhWJK0SRYvXsyW
   W27JZpttxrJly6ipqTEEb8RY9UAfYDXwLtB/Q2P5Wip1yAvjJEkl19wKsd9++1FTUxO5msrVDdg3
   f/xMzEKkjDAES5I2if3AxbN//tFL46TSMwRLkjaJO0MUz8j8o5fGSaVnCJYkbRJXgounOQS7EiyV
   nhfGSZI22sKFC9l2223p27cv7777Ll265NZWvDBu48ZaTe7iuAbgvfzxh87ztVTqkBfGSZJKqnkV
   eP/9928JwNp4PYB9yAXiWZFrkaqdv7EkSRvNfuDisyVCKg9DsCRpo9kPXHzuECGVhyFYkrRRkiRx
   JbgE3CFCKg8vjJMkbZTXXnuNHXfckYEDB/LOO+8QwtprULwwbuPHWknugrgEWA70Wv88X0ulDnlh
   nCSpZFqvArcOwNo0mwF7AU3A7Mi1SNXMECxJ2ij2A5eOF8dJpWc7hCSpYJ1Z8bUdYuPH+hXwFeAs
   4Lfrn+drqdQh2yEkSUWXAI1Av/znC/Jfa/2hTePFcVLpGYIlSZ32Krk7mm0DbBu5lmo0gtyq7wvA
   qsi1SNXKECxJ6rSn8o92A5fG5sAe5G6f/FzkWqRqZQiWJHXa0/lHdwcuHS+Ok0rLECxJ6rQn84+u
   BJeOfcFSaRmCJUmdsoa1wcwQXDrNt082BEulYQiWJHXK8+Qu1toVGBi5lmq2X/7xOWB1zEKkKmUI
   liR1yvT849ioVVS/vsBu5Fben49ci1SNDMGSpE4xBJePLRFS6RiCJUmd0hyCx0StIhsMwVLpGIIl
   SZ0yF+gOfCR2IRlgCJZKxxAsSeqUhFwA7hG7kAxofXFcfcxCpCpkCJYkdZr9wOXRj9zFcfV4cZxU
   bIZgSVKn2Q9cPrZESKVhCJYkFSRJkpZjV4LLxxAslYYhWJJUkNdffx2ALcjdKEPlYQiWSsMQLEkq
   yPTpuc3RxgAhbimZ0nxx3LNRq5CqjyFYklSQ1iFY5dMPGIa7Q0jFZgiWJBXkySefBOwHjmH/jk+R
   1EmGYElShxoaGpgxI9eV6kpw+RmCpeIzBEuSOvT888/zwQcfALBl5FqyyBAsFZ8hWJLUoeZ+YMUx
   stXxmjVrotUhVRNDsCSpQ839wIqjH2u3pXvhhRdiliJVDUOwJKlDrgTH17Jf8Ax3DJaKwRAsSWrX
   0qVLefHFF+nevXvsUjLNECwVV4chOIQwPoQwN4TwcgjhwjaePy6EMDuE8EwIYUYI4aOlKVWSFMP0
   6dNJkoT99/fyrJgMwVJxtRuCQwhdgSuA8cBewCkhhD3XO+3BJElGJEmyH3AGcG0pCpUkxfH4448D
   cMABB0SuJNuaL46bPXu2F8dJRdDRSvAY4JUkSf6ZJMka4GbguNYnJEmyotWnmwOLiluiJCmmxx57
   DIADDzwwciXZ1j//uHr1al588cWotUjVoKMQPAR4vdXn8/NfW0cI4fgQwhzgPuArxStPkhRTY2Mj
   TzzxBOBKcJrYEiFtupoOnk8KGSRJkjuBO0MIhwA3ALu3dd6kSZNajmtra6mtrS2oSElSHC+88ALL
   ly9nxx13ZNttt41djvJmzJjBWWedFbsMKTXq6uqoq6vr1Pd0FIIXANu1+nw7cqvBbUqSZFoIoSaE
   MDBJksXrP986BEuS0s9WiHRyJVha1/qLq9///vc7/J6O2iGeBoaFEHYMIXQHJgJ3tz4hhLBLCCHk
   j0cCtBWAJUmVxxCcTrNnz6ahoSF2GVJFazcEJ0nSAJwPPAC8CPwpSZI5IYRzQwjn5k87EXguhPAM
   cDlwcikLliSVjyE4fXbZZRdWrVrlxXHSJgpJUlDb76ZPFEJSrrkkSZvu7bffZtCgQfTu3ZulS5dS
   U1NDCKGgi0UCHV9UUsg5McaKMWdnxvrUpz7FLbfcwu9+9zvOPPPMAr5Lyp4QAkmShPbO8Y5xkqQ2
   Ne8PPGbMGGpqOrqEROXSfNMS+4KlTWMIliS1yVaIdDIES8VhCJYktckQnE4jR+buHefFcdKmMQRL
   kj6kvr6ep556CoBx48ZFrkatDRgwgJ133pmVK1cyZ86c2OVIFcsQLEn6kGeeeYbVq1ez5557ssUW
   W8QuR+tpbol4+umnI1ciVS5DsCTpQ5pbIbxVcjqNHj0aoGW1XlLnGYIlSR9iCE63MWPGAIZgaVO4
   T7AkaR1JkrDNNtvw1ltvMXfuXHbfffeW59wnOAVjJQnLly+nX79+1NTUsGzZMnr27FnAd0vZ4T7B
   kqROe/nll3nrrbfYeuut2W233WKXozb06dOHvfbaizVr1jB79uzY5UgVyRAsSVrHtGnTADjkkEMI
   od2FFEVkS4S0aQzBkqR1tA7BSq/mi+OefPLJyJVIlckQLElax9SpUwE49NBDI1ei9jSvBBuCpY3j
   hXGSpBbz589nu+22o2/fvixZsoSuXbuu87wXxqVgrPxraX19PX369KG+vp53332X/v37FzCClA1e
   GCdJ6pTmVogDDzzwQwFY6dK9e3f2228/AGbMmBG5GqnyGIIlSS2aQ7CtEJXBlghp4xmCJUktvCiu
   snhxnLTx7AmWJAGwePFittxyS3r06MF7771Hjx49PnSOPcEpGKvVa+lLL73EHnvswZAhQ5g/f34B
   I0jZYE+wJKlgjz76KABjx45tMwArfYYNG0a/fv1YsGABCxYsiF2OVFEMwZIkYO3WaLZCVI4uXbow
   atQowJtmSJ1lCJYkAV4UV6m8OE7aODWxC5Akxff++++3hKijjz46cjXqDG+fLG0cQ7AkiSeeeAKA
   UUB7Uardq0xUFiG0/W/hwQcfbHnOC9GljtkOIUmirq4OABsh0i9p42Pb/HNzYxUlVSBDsCSJhx56
   CICPRq5DG2dM/tGGCKlwhmBJyrj333+/pZ/UfSEq0+j8o5fGSYUzBEtSxj3yyCM0NDQA0DdyLdo4
   zSvBhmCpcIZgScq45lYIVa5R+cdnolYhVRZDsCRl3JQpU2KXoE3UH9gTqI9diFRBDMGSlGFLly5l
   5syZdOvWLXYp2kQHxC5AqjCGYEnKsKlTp9LU1MTYsWNjl6JNZAiWOscQLEkZ1twKcdhhh0WuRJvK
   ECx1jiFYkjKsZX/gj7pDcKXbE+iXP54/f37MUqSKYAiWpIxatGgRzz77LD169GDcuHGxy9Em6gI0
   N7U03wZb0oYZgiUpox5++GEADjzwQHr27Bm5GhVDc0vE448/HrUOqRIYgiUpo2yFqD7N6/mGYKlj
   hmBJyigviqs+ze0QM2bMYPXq1VFrkdLOECxJGTR//nzmzJnD5ptvzujRo2OXoyIZkH+sr6/nmWe8
   f5zUHkOwJGXQX//6VyC3Cty9e/fI1agUbImQ2mcIlqQMmjx5MgBHHXVU5EpUKoZgqX0hSZLyTBRC
   Uq65JEkb1tTUxKBBg1i0aBFz585l9913ByCEQEe/pQN0eE6h56V1rBhzFnssgKFDh/L6668XMKpU
   fUIIJEkS2jvHlWBJyphZs2axaNEitt9+e3bbbbfY5agE+vXrx/z5871phtQOQ7AkZUzrVogQ2l0o
   UYUaOza3T4Q3zZA2zBAsSRnTfFHckUceGbkSlcoBB+Rum2FfsLRhhmBJypAVK1bwyCOPEELg8MMP
   j12OSsQQLHXMECxJGTJ16lTq6+sZNWoUAwcOjF2OSmTs2LGEEJgxYwarVq2KXY6USoZgScqQ5n5g
   WyGqW/9ndDC7AAAgAElEQVT+/Rk+fDj19fU89dRTscuRUskQLEkZ0twP7P7A1e/ggw8GYNq0aZEr
   kdLJECxJVS6E0PLxwgsvAFBbW7vO190lovoccsghADzyyCORK5HSyRAsSRmQAL/LHx+b/3z9D1WX
   5pXgRx99lMbGxsjVSOljCJakjLg3/3hM1CpULkOHDmXHHXdk2bJlPP/887HLkVLHECxJGbAGmJw/
   nhCzEJWVfcHShhmCJSkDHgWWA3sCO0WuReXT3BdsCJY+zBAsSRnQ3ApxbNQqVG7NK8GPPPIISWLn
   t9SaIViSMuAv+Uf7gbNlzz33ZODAgbzxxhvMmzcvdjlSqhiCJSkDXgT6AAfFLkRlFULgoINy/9bd
   Kk1aV0EhOIQwPoQwN4TwcgjhwjaePy2EMDuE8GwI4dEQwr7FL1WStCmOArrHLkJlZ1+w1LYOQ3AI
   oStwBTAe2As4JYSw53qn/QM4NEmSfYEfANcWu1BJ0qaxFSKbWvcFS1qrkJXgMcArSZL8M0mSNcDN
   wHGtT0iS5PEkSd7LfzodGFrcMiVJG2PlypUtx26Nlk0jR45ks802Y+7cubzzzjuxy5FSo5AQPAR4
   vdXn8/Nf25CzWXsNhiQporq6OgBGAttErUSxdO/enbFjxwKuBkut1RRwTsF7qoQQDgPOYgPXXkya
   NKnluLa2ltra2kKHliRthHvuuQdwFTjrDjnkEOrq6pg2bRqf+MQnYpcjFV1dXV3LH/2FCh3tGxhC
   GAdMSpJkfP7zi4GmJEkuW++8fYH/HxifJMkrbYyTuEehJJVPkiRsv/32zJ8/n+nketvaE+h41aOQ
   cyp9rBhzFn2s9V5vH3zwQY488kj2228/Zs6cWcBMUmULIZAkSWj3nAJCcA3wEnA48AbwJHBKkiRz
   Wp2zPfAQ8OkkSZ7YwDiGYKkKhdDu75gW/v9ffjNmzGDUqFEANNJx/1vFB78ijRVjzlKH4A8++ID+
   /fvT0NDA4sWLGTBgQAGzSZWrkBDcYTtEkiQNIYTzgQeArsBvkySZE0I4N//8NcD3gAHAVfkXxDVJ
   knS06CCpShTyoqzyu/POO1uO3RQ+W9r743SLLbZoOfaPU2VZhyvBRZvIlWApNYq5ehtC2KiVKZXe
   8OHDef7554EUr1imcKwYc5ZjrO+R28P0q8Av8P9LVbdCVoJdHJAyKungQ5Xt1Vdf5fnnn6dv376x
   S1FKHJZ/rItZhJQihmBJqkJ33XUXAMcc4y0ylHMA0AOYDSyOXIuUBoZgSapCzf3Axx9/fORKlBY9
   gXH544djFiKlhCFYkqrMO++8w6OPPkq3bt2YMMEdgrWWLRHSWoXcLEOSWjQ1NfHCCy8we/Zs/v73
   vwPwKWAVsDnQD9gZ2AMYC2wdq9AMu+eee2hqauLII4+0J1jrOAyYBEyJXIeUBoZgSR1auXIl99xz
   D7fccgtTpkxh8eJ1Owpvbed7h+cfX3jhBfbee++S1ai17rjjDgCOO+64yJUobcaSa4t4PnYhUgq4
   RZqUQYVua/bKK6/w85//nOuvv57ly5e3PDdkyBDGjRvHHnvswY9+9CP+BHQHVgBLgJeBF4DHgZWt
   xhw1ahTf/OY3Oemkk+jatWtR/5mUs3TpUgYNGkRDQwMLFixg8ODBBf37hvRs5RV7rBhzlnOsw8nd
   3QrcIk3Vqyh3jCtiMYZgKSU6CkUvA7vR8ksEgNGjR3PqqafysY99jJ133rllr+H2xloNPAZ8FOjf
   vz9Lly4FYJddduGHP/whEydOLHjPYhXm+uuv57Of/SyHHXYYDz2UizqG4PTPWc6xfgj8Z/7Y12VV
   K/cJltQpS4FvAM1NC61fIJ966im+/vWvs+uuu9KlSxdCCB0G2B6svRBn4cKFXHPNNeyyyy68+uqr
   nHLKKRx88ME8/fTTJfgnya5bbrkFgE996lORK1Fa1cYuQEoJV4KlDGprZfBe4PPAG6xdSXodGNrR
   WBS4MpX//7+hoYHrrruO73znO7z99tt06dKFCy+8kEsuuYQePXp09h9Frbz77rsMGjSIxsZGFi5c
   yNZb5y5LdCU4/XOWc6x6YADwAbk/TgcPHlzAzFJlcSVYUoeWA2cA/04uAB8AzMw/11EA7ozmleNu
   3bpxzjnn8PbbbwO53SYuvfRSevbs2XJORx9q21133cWaNWs47LDDWgKwtL7uwKH54wcffDBmKVJU
   hmApw14ARgN/IHfF+M+AacBHSjDXhm7P/CgwrNV517Vzru8ltc9WCBXqyPzjX//616h1SDHZDiFl
   UAiBm4GzyL0lug+5bc72aH0O5Xt79gPgy8Dv8p+fA/yKXE9xm2P5u+RDlixZwqBBg0iShIULF7LV
   Vlu1PGc7RPrnLPdYzwH7Attssw0LFizwHRZVHdshJH1Ic4A8mVz4/DTwBOsG4HLrBfw2f9wD+F/g
   KHLbrakwd955Jw0NDXz0ox9dJwBLbdkn/7hw4UJeeOGFqLVIsRiCpQxpbGzkS1/6EpBbLfopcD3Q
   O2ZR63kU2BaYSq4/+dW45VSMG2+8EbAVQoVpvTxmS4SyynYIKSPWrFnDaaedxq235u7vdgvwyXbO
   j/lW73zgWOBZYEtyO1eMaX2Ov0vWMX/+fLbffnu6d+/Om2++Sf/+/dd53naI9M8ZayyACRMm8Je/
   /KWA75Aqh+0QkoBcAD7llFO49dZb6du3L9B+AI5tKLkL9MYDi8jd4Wpq1IrS7cYbbyRJEj7+8Y9/
   KABLHamrq2P16tWxy5DKzhAsVbnmAHz77bfTr1+/innrsy9wN7ne5ffJBeIHolaUTkmScMMNNwBw
   +umnR65GlWb48OGsXLmSxx57LHYpUtkZgqUq1tTUxJlnnrlOAB4zZkzH35gS3YA/Ap8DVgIfi1tO
   Ks2aNYsXXniBLbfckvHjx8cuRxXmyCNzm6VVyh/HUjEZgqUqduGFF3LjjTfSu3dv/vrXvzJ69OjY
   JXVaV+Ba4GvAmvzX7r777ngFpcz1118PwMknn0y3bt0iV6NKYwhWlnlhnFSlfvazn3HBBRdQU1PD
   vffey1FHHdXyXCEXSqXtop8EuAj4MdC9e3fuuuuuzK98NjQ0MHToUN566y2efPLJDf6R44Vx6Z8z
   1lgrVqxgwIABrFmzhnfeeYeBAwcW8J1S+nlhnJRRt912GxdccAEA11133ToBuFIF4L/zx/X19Xzi
   E5/gb3/7W8ySouvWrRtvvfUWAGPGjPE20+q0Xr16cfDBB5MkSeb/f1L2GIKlKjN79mw++9nPAvDj
   H/+Y0047LXJFxdMc577whS+watUqPv7xjzN1qvtGXIa3mtbGa/4j+f77749ciVRetkNIVaQzq35p
   fXu2kLEaGxs555xz+N3vfkefPn14+OGH2W+//QqYoXosWLCAoUOH0o3cvspbt3Numv9dpnGsGHNG
   GytJePbZZxkxYgSDBw/mjTfe8N0DVQXbIaQMWbNmTcvxGHK7KVTrymCXLl249tprmThxIsuXL2fC
   hAm8+mq27i33+9//HoDjaT8ASx0ZPnw4Q4YM4c033+SZZ56JXY5UNoZgqUpcfPHFAGwD3AH0jFpN
   6XXt2pU//OEPHHHEEbz11lscddRRLf2x1a6xsZHf/OY3AJwTuRZVvhACxxxzDIB3jlOm2A4hVYF7
   772Xf//3fwfgEeCgDs5P9duzBZxTqGr9nXP//fczYcIEABrpeDUjzf8u0zhWjDljtkMA3HXXXRx/
   /PEccMAB3jhDVcF2CCkDFixY0HIhHHQcgKvB+u0dbwHD8s8dRq4VpJpdc801Lcf+ElcxHH744XTr
   1o0nnniCRYsWxS5HKgt/f0oVrKGhgVNPPZXFixdz9NFHxy4nmq3J3VJ5MDAF+Ezcckpq3rx53H33
   3d4YQ0W1+eab82//9m8kScIDD3iDcmWDIViqEG3t/9qtW7eWLcKy/sK1E7kg3Be4NXItpXTFFVfQ
   1NTEKaecErsUVRn7gpU1hmCpgrRuAZgJ1OS//iDVsevDptoXuJ21P5err746YjXFt3z58pYL4r76
   1a9GrkbV5thjjwVyPeeNjY2Rq5FKzxAsVaDVwGeBBuB84PC45aTKEUBzx+yXvvSlqlrVuu6661i2
   bBmHHHIII0eOjF2OqsywYcPYZZddWLJkCdOnT49djlRy7g4hVYgQQstq73eA/wJ2BWYBvZvPoQqu
   Vi/iWAC9e/dm2rRpFX8zjaamJnbffXdeeeUVbr/9dk444YR1/ptoTzX8u3R3iNKMVQhfu1WJCtkd
   whAsVYjmwDMdOJDci9w01t0NohpelMv9Ag+V8SJ/22238clPfpIdd9yRV155ha5duxqCSzRWjDnT
   Mtb9wARgBLk/sFtvoyZVErdIk6pMPXAm0ARcQDa2Q9sUq4B/yx/vAyylMu+elyQJP/zhDwH49re/
   TdeuXSNXpGpVS+6dpdnAa3FLkUrOECxVkJ8Ac4DdgB9ErqUS9CB397w9gOeBTwJr2v2OdLr33nuZ
   PXs222yzDWeeeWbsclTFepJbCQa4K2YhUhkYgqUK0hx8r6b6b4tcLAOAv5DbS/ivwBeonBVgWHcV
   +Fvf+hY9e/pvXqV1XP7xzqhVSKVnT7BUAZIkoUuX3N+snwH+sIHz0tJXmMaxniT3Vu9K4PvA91qf
   l+LfTZMnT+boo49myy235J///Ce9e/duec6e4NKMFWPONI31LrBV/riRdP//IW2IPcFSlbjpppsA
   2AL4n7ilVKwxwM3kfuldAvw+bjkFaWpq4uKLLwbgggsuWCcAS6UygNwfjO4UrGpnCJZSbsmSJXzj
   G98AcgF4q/ZPVzs+DlyRPz6H3B3m0uxPf/oTM2fOZMiQIXzlK1+JXY4y5PjYBUhlYAiWUu773/8+
   b7/9NgBnxC2lKnwRuIjcKtdJkWtpT319Pd/5zneA3H8DvXr1ilyRsuS4VscrV66MVodUSoZgKcX+
   /ve/8+tf/7qlH7gze99qw34EnAa8n//8tdfStxnUlVdeybx589hzzz357Gc/G7scZcx2wP754wcf
   fDBmKVLJGIKlFLvoootoaGhwW6wi6wL8Dvho/vMJEyawZMmSiBWt64033uCSSy4B4Cc/+Qk1NTWR
   K1IWtewScaf7RKg6uTuEFFkIha/vVtIV5pUw1ntA//zxIYccwuTJk1OxBdkpp5zCzTffzHHHHddu
   AHF3iNKMFWPONI71HLAvsOWWW/Lmm296kxZVFHeHkCrE+ncxawRG55+bRGXta1tJ+uUfhwwZwrRp
   0zjppJOor6+PWtPkyZO5+eab2Wyzzbj88suj1qJs2yf/uGjRIqZNmxa1FqkUDMFSCt0MPAVsA3wz
   ci1ZcP/99zNw4EDuvfdeTjvtNBoaGqLU8e6773L22WcD8L3vfY8ddtghSh0SrHsNwq233hqtDqlU
   bIeQIlv/Le1VwO7Av4DfAmc1n0dlvqWa5rFazksSZs6cyUc/+lHee+89Tj/9dK677rqWCxLL5bTT
   TuOmm25i3LhxTJs2rcNeYNshSjNWjDnTPBbA1ltvzRtvvGFLhCqG7RBSBfoluQC8L+CeAOUzcuRI
   7rvvPnr37s0NN9zAueeeS1NTU9nmv+GGG7jpppvo1asX119/vRfDKTV23XVX3n77baZOnRq7FKmo
   DMFSirxDbvsuyN0YwzWX8gghEELgwAMPZMWKFQD85je/oWvXri3PldLMmTP5/Oc/D8AvfvELhg0b
   1jJvex9SOXzqU58C4JZbbolciVRchmApRf4/YBkwHjgyci1Zsv6FiVOAPvnnJpR47jfffJMTTjiB
   VatWcfbZZ/O5z31ug3Wt/yGVQ3MIvv3226P1y0ulYAiWUuIl4Gpy/1P+JHItWVcLPAQMBO7Lf23h
   woVFn+fdd9/lqKOO4rXXXmPs2LFceeWVrvAqdfbdd19222033nnnHR5++OHY5UhFYwiWUuJCoAE4
   m7VbEymeUcA0cnfOAhg1ahRPPvlk0cZfvHgx48eP57nnnmOPPfbgz3/+Mz169Cja+FKxhBBsiVBV
   cncIKbIQAnXkVh97A68Ag9s6j8q+wjyNYxVy3tvAoPxx9+7d+dGPfsTXv/71TbpK/p///CcTJkxg
   7ty57LDDDkybNo3ttttunXMK2fnBHRFKM1aMOVM9VpLw3HPPse+++zJw4EDefPNNL9xU6rk7hFQh
   Lsg/XkjbAVjxbJ1//NKXvkR9fT3f+ta3OOyww3j++ec3arw77riD/fbbj7lz57LPPvvw6KOPfigA
   S2mzzz77sMcee7B48WIeeuih2OVIRWEIllJgBrAta8Ow0ueKK67gnnvuYfDgwUybNo0RI0Zwzjnn
   8MorrxT0/S+//DKf+MQnOOGEE1i6dCnHHnss06ZNY8iQISWuXNp0IQROPvlkAP74xz9GrkYqjoLa
   IUII44FfkNux6TdJkly23vN7AL8H9gO+kyTJT9sYw3YIaT0rV66kV69eQO5/oDPaObfi31JN4Vid
   mjP/+2vx4sVccsklXH311TQ2NgJw5JFHctxxx3HooYey6667stlmm7FmzRpee+01pk6dyu233859
   991HkiT07t2bH/3oR3zlK19p9yI42yHijRVjzlSPlf9v/9VXX2XXXXeld+/evPXWW/Tu3buAWaQ4
   CmmH6DAEhxC6krtw/QhgAbm7uZ6SJMmcVudsBewAHA+8awiWCnPppZfyH//xH3wEeJr29wWu+BfS
   FI7VqTnX+/310ksvcdlll/F///d/rFq1ap3nunXrRkNDwzrf06NHD04//XS+//3vs+2223ZclyE4
   2lgx5kz1WK3+Oz7ooIN47LHHuOGGG/j0pz9dwCxSHMUKwQcAlyRJMj7/+UUASZL8dxvnXgK8bwiW
   Ovb222+z6667snz5ch4EDu/g/Ip/IU3hWJ2acwO/vxYvXszdd9/N/fffzzPPPMO8efNoaGgghMDQ
   oUP5yEc+wtFHH83EiRPZcsstC6goP6chONpYMeZM9Vit/tu/+uqr+eIXv8iRRx7J5MmTC5hFiqNY
   Ifgk4OgkSc7Jf/5pYGySJF9u41xDsFSg8847j6uuugpI8YtflY/VqTkL/P3V1NREQ0MDXbp0afMK
   +s7sA5zan0WVjxVjzlSP1eq//SVLlrDNNtvQ0NDA66+/XtC7GlIMhYTgQvY4KVpynTRpUstxbW0t
   tbW1xRpaqihz5szh2muvpWvXri19paoOXbp0oXv37u2eU2hAkdJmiy224Nhjj+WOO+7gpptu4pvf
   /GbskiQA6urqqKur69T3FLISPA6Y1Kod4mKgaf2L4/LPuRIsFeDjH/84f/7zn/nCF77A1Vdfnd4V
   oCofqzNzFqqA36kV/7Oo9rFizJnqsdb7b/qOO+7ghBNOYN9992X27NkFzCSVX7H2CX4aGBZC2DGE
   0B2YCNy9oTk7WaOUOVOmTOHPf/4zm2+++TrvjijdkgI+pCw45phjGDBgAM8++yzPPvts7HKkjdZh
   CE6SpAE4H3gAeBH4U5Ikc0II54YQzgUIIQwOIbwOfB34bgjhXyGEzUtZuFSJmpqauOCC3G7AF198
   MYMGDergOyQpXXr06NGyZ/Dvf//7yNVIG8/bJktldP311/PZz36WoUOH8tJLL9GrV6/Uvj2ehbFK
   MqftEBU/Vow5Uz1WG/9Nz5gxg1GjRrHFFluwYMECevbsWcCMUvkUZXeIIhZjCFamffDBB+y+++7M
   nz+f66+/ntNPPx1IbyjKwlglmdMQXPFjxZgzzWMVytd4pUmxeoIlFcHPfvYz5s+fz8iRIznttNNi
   lyNJBdlQD/yv888fFqkuaVO5EiyVwRtvvMFuu+3GihUrmDJlyjrbA6Z1ZTALY5VkTleCK36sGHNW
   4ljvAdsAK/Of+xqvNHElWEqJ7373u6xYsYLjjz/e/bElVYV+wKdiFyFtAleCpRJ75pln2H///amp
   qeHFF19k1113Xef5tK4MZmGskszpSnDFjxVjzkod61Hg4PxxfX093bp1K2BmqfRcCZYiCiEQQmDk
   yJEkScKaNWsYNmxYy9ebPySpUh0I7Jk/vvvuDd1CQEonQ7BUQnfkHwcCS2j74hJVl/X/yPGPHlWz
   AHwxf/yrX/0qZilSp9kOIZVICIFdgVeAX5G740yb51GZb4NWw1gx5kzrWDHmTOtYMeas5LGWkesP
   Bpg1axYjRowoYHaptGyHkCJ7BdgDODd2IZJUIn1bHbsarEpiCJZKYP78+S3HPwe8VERSFtx4440s
   WrQodhlSQQzBUgl84xvfAOAEYHzcUiSpLI455hhWrVrFb37zm9ilSAWxJ1gqssmTJ3P00UcD8Bqw
   fQfnV3IvYKWPFWPOtI4VY860jhVjzmoY6/7772f8+PEMHTqUefPmUVNTU8B3SqVhT7BUZqtXr+bL
   X/5yy+cdBWBJqhZHHnkku+++O/Pnz+eWW26JXY7UIUOwVEQ//elP+fvf/87uu+8euxRJKqsuXbrw
   zW9+E4DLLrvM2ygr9WyHkIrkpZdeYsSIEaxevZoHH3yQI444wrdnUz5WjDnTOlaMOdM6Vow5q2Ks
   JGH16tXstNNOLFy4kHvvvZdjjjmmgO+Wis92CKlMGhsbOeuss1i9ejVnnHEGhx9+eOySJKnsevTo
   0XJh8H//939HrkZqnyvBUhH88pe/5Ktf/SqDBw/mxRdfZMCAAbm/Qgv43qpYAarQsWLMmdaxYsyZ
   1rFizFkVY+Vf45cvX87222/P0qVLeeSRRzjooIMKGEEqLleCpTKYN28eF198MQBXXXUVAwYMiFyR
   JMXTp08fzj8/d4/MSy+9NHI10oa5EixtgsbGRo488kimTJnCxIkTufnmm1uecyU4/WPFmDOtY8WY
   M61jxZizKsZq9Rr/zjvvsOOOO/LBBx8wffp0xowZU8AoUvG4EiyV2E9/+lOmTJnC1ltvzS9/+cvY
   5UhSKmy11VYt20X+53/+Z+RqpLa5EixtpBkzZjBu3DgaGhravAraleD0jxVjzrSOFWPOtI4VY86q
   GGu91/glS5aw0047sWzZMh5++GEOPfTQAkaSisOVYKlEVqxYwamnnkpDQwNf/vKX3QZIktazxRZb
   tOwU8d3vftd9g5U6rgRLnZQkCWeddRbXXXcd++yzD0899RQ9e/b80HmuBKd/rBhzpnWsGHOmdawY
   c1bFWG28xi9btoyddtqJJUuWcP/997fcUl4qtUJWgg3BUiddc801fOELX2CzzTZj+vTpDB8+vM3z
   DMHpHyvGnGkdK8acaR0rxpzVMFahzAIqB9shpCKbPn16y8Ue11577QYDsCRlTbKBj5XAjvHKkjbI
   ECwV6O233+bEE09kzZo1nH/++Xz605+OXZIkpV5P4CetPl+6dGmsUqR1GIKlAqxcuZLjjjuOBQsW
   cOCBB/LTn/40dkmSVDFOBA7JH//gBz+IWYrUwp5gqQNNTU1MnDiR2267je22247p06ezzTbbdPh9
   9gSnf6wYc6Z1rBhzpnWsGHNmYayZwP5ATU0Ns2fPZq+99ipgZGnj2BMsFcHFF1/MbbfdRt++ffnL
   X/5SUACWJK1rZP6xoaGBc845h6ampqj1SK4ES62E0JlrnDvmylS6x4oxZ1rHijFnWseKMWcWxmo+
   b/Dgwbz55pv8+te/5otf/GIB3yV1nivB0kZovqL5N62+9rtWX0/WO29DH5KkD/vVr34FwIUXXsj8
   +fMjV6MsMwRLbbgJOCd//AvgzIi1SFI1OfHEE/n4xz/O8uXL+fznP+++wYrGECyt5xbgM+RWc/8L
   +GrcciSpqoQQ+PWvf82AAQO47777uPLKK2OXpIyyJ1hqJYTQ0tv2HeCHGzoPexSrYawYc6Z1rBhz
   pnWsGHNmYayW8/JZ4Pbbb+ekk06iR48ezJgxg7333ruAEaTC2BMsdcLPf/5zIPeL/IeAO1lKUumc
   eOKJnHXWWaxevZpTTjmFlStXxi5JGWMIVuY1NTXxne98h2984xsAXE5uFbi4+0RIktZ3+eWXM2zY
   MJ577jn7g1V2tkMo01auXMkZZ5zBLbfcQteuXWlsbEz324iO5c+1RGPFmDOtY8WYMwtjtZy3XhZ4
   /vnnGTduHCtWrOBnP/sZX//61wsYSWqf7RBSO9566y0OO+wwbrnlFvr06cM999wTuyRJypx99tmH
   6667DoBvfetbPPjgg3ELUmYYgpVJTzzxBKNGjWL69OnssMMOPPbYY4wfPz52WZKUSSeddBL/8R//
   QWNjIyeccALPPPNM7JKUAYZgZUqSJFx++eUccsghzJ8/nwMOOIDp06ezzz77xC5NkjLtBz/4ASef
   fDLLly9nwoQJvPrqq7FLUpWzJ1iZ8e6773Luuedy6623AvC1r32Nyy67jO7du7ecE0JIdy+dY/lz
   LdFYMeZM61gx5szCWM3nFWrnnXdmypQpbL/99p34LinHnmApb/LkyQwfPpxbb72VPn36cNttt/Hz
   n/98nQAsSSq9Qm45P3r0aP7xj39w6KGH8o9//CNOoap6hmBVtffff5/zzjuPo48+mgULFjBu3Dhm
   zJjBiSeeGLs0SdIGTJ48mXHjxvHaa69x6KGHMmfOnNglqQrZDqGqlCQJd9xxB1/72td4/fXX6dat
   G2vWrCnsews4x7dnq2OsGHOmdawYc6Z1rBhzZmGsTs2ZJCxfvpxjjz2WadOm0a9fP2677TaOOOKI
   AmaRbIdQRr366qsce+yxnHjiibz++uuMHDmSp556CijsbThJUnx9+vTh/vvv54QTTuC9995j/Pjx
   XHXVVd5QQ0VjCFbVeOedd/ja177GXnvtxX333Ue/fv244oorePLJJxkxYkTs8iRJndSrVy9uvfVW
   LrroIhobGznvvPM47bTTWLZsWezSVAVsh1DFe++997j88sv5n//5H5YvX04IgdNPP50f//jHDBo0
   qOW8QnZ+qIq3ER0r1XOmdawYc6Z1rBhzZmGsTs3ZRl648cYbOffcc1mxYgW77LILN9xwAwcccEAB
   s6fLNTYAAAp2SURBVCqLCmmHMASrYr3xxhtcfvnlXH311S2rAscccwyXXnop++6774fONwQ7Vhrm
   TOtYMeZM61gx5szCWJ2acwN54e9//zsTJ05k1qxZhBA477zz+K//+i/69u1bwOzKEnuCVXWSJOGJ
   J57gzDPPZKedduLHP/4xy5Yt47DDDuPhhx/m3nvvbTMAS5Iq32677cbjjz/ORRddRNeuXbnyyivZ
   a6+9+MMf/kBjY2Ps8lRhXAlWRVi8eDE33XQT//u//8tzzz0H5P7KO+GEE7j99tsLHicTKyiOleo5
   0zpWjDnTOlaMObMwVmfmLNSYMWN48sknARg+fDiXXnopxxxzDCF0ZhRVI9shVNEWL17MnXfeya23
   3srf/vY3GhoaANhyyy0544wz+PznP8+wYcNSe5c3X5TTP1aMOdM6Vow50zpWjDmzMFYp5mxsbOTG
   G2/ku9/9Lv/6178AGDFiBN/+9rf55Cc/Sbdu3QoYSdXIEKyKkiQJs2fP5oEHHuCBBx5g2rRpLcG3
   a9euHH744Xzuc5/juOOOq4hbHaf9xcOx4syZ1rFizJnWsWLMmYWxSjJnPlesWrWKX//61/zkJz/h
   zTffBGC77bbj7LPP5owzzmCHHXYoYERVE0OwUq2pqYkX/1979xsbVVrFcfz7K4VWutGlaUBoK0vK
   P60IbMjuRg0pocif2IV9YZTErKtvfKFxYzb+W16YjTHrn0Q3ajQmuxqNWYWoEAgra7NlIqRAlNAR
   bKElQcuWCrXYBgqFXXp8MbO1hbYznU7nmTtzPslNp73PnOfkdnrv6b3PvU97O62trRw7dozm5mau
   Xr06un7OnDlpj/HKxx1+3h88PFaQPvM1Vog+8zVWiD6LIdZs9JkOSTQ2NrJ7926ampqoqqpK850u
   yrwIdnnDzOjt7SUej3P69GlaW1s5ceIEAwMD49otWbKErVu3snXrVhobG6mqqorsDj/fDx4eK0yf
   +RorRJ/5GitEn8UQK5d9jgAtwBagrKyMO3fuAFBSUsLGjRvZtWsXmzdvpr6+3scPFygvgl0QN2/e
   pLOzk46ODuLxOG1tbbS1tdHX15dRvKju8KN68CimWCH6zNdYIfrM11gh+iyGWCH6FIn7S/bt28f+
   /ftpaWkZHWYHsHDhQhoaGti4cSMbNmxg7dq1lJeXp9G7y3dZKYIlbQNeAuYAL5vZdydo8yNgO3AL
   eMbMzkzQxovgLIrFYjQ0NATp28wYHByku7ub7u5uurq66Ozs5MKFCxw9ejTtON1AbYo2udhhxoCG
   LMXKZl6h+8w0Voz/b898yitf+pxurBgPbs/ZyCvddlGOFQM25bjPQo4VI//3nYJxzxweGBjg8OHD
   HDlyhJaWFq5cuTKufWlpKfX19axfv57Vq1ezcuVKVq1aRV1dHWVlZWlklbmQx/VClE4RXJoiwBzg
   J0Aj0AP8VdJBM+sY02YHsNzMVkh6HPgZ8MSMs3dTmo0/lnv37tHf309fXx99fX1cu3Zt9HVvb+9o
   0Xv58mVu3LgxaZx5wHJgFbAWWJdc3gejY7hE6gI4V2JMXmS46Yvh2zObYvj2zJZY6AQKTIxofDbT
   He5QX18/egUzHo+PW1dSUsLixYuprq6murqampoaqqurWbRoEZWVlaPLggULqKyszKhg9iI496Ys
   goHHgItm9k8ASb8DdgIdY9o8CfwKwMxOSXpY0iIzu3p/sGIxMDBAV1cXZjbpMjIyMuX6VG3Pnz/P
   gQMHGBkZ4e7du2ktw8PD3LhxY9wyODjI9evXuX37Nrdu3Zp0lp77VVRUsHTpUmpra6mrqxv9b3n7
   9u3cInHZwDnnnAst3bPK586dY2hoiLa2NuLxOF1dXVy4cIHOzk4uXbpET08PPT09afVZXl5ORUUF
   FRUVzJ8/f8Kv8+bNG13mzp3LyZMnAcb9bOzX0tJSSkpKZrRIGvdPwf3/IEy2bs2aNQU5TCRVEVwN
   XB7z/ZvA42m0qQGKtgg+fvw4TU1Ns97P3r17Z72PyQwNDdHe3k57e/sD67wAds45FzXZvEFueHiY
   4eFh+vv7p/W+48ePZy2HbLp48SJ1dXWh08i6VEVwuoN47//kTPg+vwOzOKT7W85mu5nGeiGLsabb
   Jp/7zDTWC2m0mUmfxbZdJ9qemcbKRrtiiBWizyjGisK+0yuPmVu+fHnoFGZFqiK4h/FDN2tJnOmd
   qk1N8mfjpBqc7JxzzjnnXK6UpFj/N2CFpEckzQM+CRy8r81B4GkASU8AA8U8Htg555xzzuW/Kc8E
   m9nbkr4IvE5iqOcrZtYh6fPJ9T83s9ck7ZB0ERgCPjvrWTvnnHPOOTcDOZsswznnnHPOuXyRajhE
   1kl6TtKIpMpc911IJH1LUlxSm6Q3JOXLY3cjSdL3JXUkt+kfJb0ndE5RJukTkv4h6Z6kR0PnE0WS
   tkk6L6lL0tdC5xNlkn4h6aqks6FzKQSSaiUdTf6Nn5P0pdA5RZWkckmnksfydkkvhs6pEEiaI+mM
   pENTtctpEZws1LYA/8plvwXqe2a21szWAQeAb4ZOKOL+DNSb2VqgE/hG4Hyi7izwFPCX0IlE0ZiJ
   irYBHwB2S3p/2Kwi7ZcktqXLjreAL5tZPYnJsb7gn8/MmNkwsCl5LP8QsEnSRwOnVQieBdpJ8ZSz
   XJ8J/gHw1Rz3WZDMbOyUbQ8B/wmVSyEws2YzG0l+e4rEU05chszsvJl1hs4jwkYnKjKzt4B3Jipy
   GTCzY8B/Q+dRKMzs32bWlnx9k8QEWkvCZhVdZnYr+XIeifuvrgdMJ/Ik1QA7gJdJ8YS8nBXBknYC
   b5rZ33PVZ6GT9G1J3cBngO+EzqeAfA54LXQSrqhNNAlRdaBcnJuUpEeA9SROHrgMSCqR1EZikrGj
   ZvbgLFRuOn4IfAUYSdUw1XOCp0VSM/DeCVbtIXF5+WNjm2ez70I0xfZ83swOmdkeYI+kr5P4pfuT
   OaaQansm2+wB7prZqzlNLoLS2Z4uY37Hsst7kh4Cfg88mzwj7DKQvAq5LnkvyuuSGswsFjitSJL0
   ceCamZ2R1JCqfVaLYDPbMklSHwSWAfHkrHE1wGlJj5nZtWzmUEgm254TeBU/c5lSqu0p6RkSl1A2
   5yShiJvG59NNXzoTFTkXjKS5wB+A35jZgdD5FAIzG5R0GNgAxAKnE1UfBp6UtAMoB94t6ddm9vRE
   jXMyHMLMzpnZIjNbZmbLSOzMH/UCOHOSVoz5didwJlQuhUDSNhKXT3Ymb1Rw2eNXfaYvnYmKnAtC
   ibNZrwDtZvZS6HyiTFKVpIeTr99F4uEBfjzPkJk9b2a1yVrzU0DLZAUwBHhEWpJf6pu5FyWdTY4j
   agCeC5xP1P2YxA2GzcnHqvw0dEJRJukpSZdJ3Dl+WNKfQucUJWb2NvDOREXtwF4z6wibVXRJ+i3Q
   CqyUdFmSDx2bmY8AnybxJIMzycWfvpGZxUBL8lh+CjhkZm8EzqmQTFlv+mQZzjnnnHOu6IQ6E+yc
   c84551wwXgQ755xzzrmi40Wwc84555wrOl4EO+ecc865ouNFsHPOOeecKzpeBDvnnHPOuaLjRbBz
   zjnnnCs6/wPRT0Hoggmn8AAAAABJRU5ErkJggg==
   "
   >
   </div>
   
   </div>
   
   </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">obs_dist2</span> <span class="o">=</span> <span class="n">mixture_rvs</span><span class="p">([</span><span class="o">.</span><span class="mi">25</span><span class="p">,</span><span class="o">.</span><span class="mi">75</span><span class="p">],</span> <span class="n">size</span><span class="o">=</span><span class="mi">10000</span><span class="p">,</span> <span class="n">dist</span><span class="o">=</span><span class="p">[</span><span class="n">stats</span><span class="o">.</span><span class="n">norm</span><span class="p">,</span> <span class="n">stats</span><span class="o">.</span><span class="n">beta</span><span class="p">],</span>
               <span class="n">kwargs</span> <span class="o">=</span> <span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">loc</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span><span class="n">scale</span><span class="o">=.</span><span class="mi">5</span><span class="p">),</span><span class="nb">dict</span><span class="p">(</span><span class="n">loc</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span><span class="n">scale</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span><span class="n">args</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span><span class="o">.</span><span class="mi">5</span><span class="p">))))</span>
   
   <span class="n">kde2</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">nonparametric</span><span class="o">.</span><span class="n">KDEUnivariate</span><span class="p">(</span><span class="n">obs_dist2</span><span class="p">)</span>
   <span class="n">kde2</span><span class="o">.</span><span class="n">fit</span><span class="p">()</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[7]:
   </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">hist</span><span class="p">(</span><span class="n">obs_dist2</span><span class="p">,</span> <span class="n">bins</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="n">normed</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="s">&#39;red&#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">kde2</span><span class="o">.</span><span class="n">support</span><span class="p">,</span> <span class="n">kde2</span><span class="o">.</span><span class="n">density</span><span class="p">,</span> <span class="n">lw</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="s">&#39;black&#39;</span><span class="p">);</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   <div class="output_wrapper">
   <div class="output">
   
   
   <div class="output_area"><div class="prompt"></div>
   
   
   <div class="output_png output_subarea ">
   <img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAsEAAAHfCAYAAACxhQUCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xuc1VW9//HXGhi8gZpyURBDQfIGpqZ4LdJKRLTStDSj
   lNJup46dU+dUdrKsh1anm3lKf0c8J5Xj5ZSpKR4SY7yjoQiIqIAiMAhyUeQ2F2bW74/ZMw3DwGyY
   Pfu7Z6/X8/H4PvZ377329/txOzP7zdrru1aIMSJJkiSlpCLrAiRJkqRiMwRLkiQpOYZgSZIkJccQ
   LEmSpOQYgiVJkpQcQ7AkSZKSs90QHEIYHEKYFkKYG0J4IYTwtXbajA4hrA0hzMxtV3ZduZIkSVLn
   9ezg+Xrgihjj8yGE3sCzIYSHYozz2rR7JMZ4TteUKEmSJBXWdnuCY4zLY4zP5/bXA/OAge00DV1Q
   myRJktQl8h4THEIYAhwNPN3mqQicFEKYFUKYHEI4vHDlSZIkSYXX0XAIAHJDIf4AfD3XI9zac8Dg
   GOPGEMKZwD3A8HaO4frMkiRJ6nIxxg5HKXTYExxCqAT+CNwWY7ynnZOsizFuzO0/CFSGEPbZRkFu
   GWzf//73M68h5c333/c/1c333vc/5c33P7stXx3NDhGAicCLMcZfbaPNgFw7QgjHAyHGuCbvCiRJ
   kqQi62g4xMnAxcDsEMLM3GPfAQ4EiDHeCHwC+FIIYTOwEfhUF9UqSZIkFcR2Q3CM8XE6nkHiP4D/
   KGRRKqzRo0dnXULSfP+z5fufHd/7bPn+Z8v3v/SFHRk70akThRCLdS5JkiSlKYRALMSFcZIkSVK5
   MQRLkiQpOYZgSZIkJccQLEmSpOQYgiVJkpQcQ7AkSZKSYwiWJElScgzBkiRJSo4hWJIkSckxBEuS
   JCk5PbMuQJIkqTsJocMVeQGIMXZxJeoMQ7AkSdIO6ije5heTlSWHQ0iSJCk5hmBJkiQlxxAsSZKk
   5BiCJUmSlBxDsCRJkpJjCJYkSVJyDMGSJElKjiFYkiRJyTEES5IkKTmGYEmSJCXHECxJkqTkGIIl
   SZKUHEOwJEmSkmMIliRJUnIMwZIkSUqOIViSJEnJMQRLkiQpOYZgSZIkJccQLEmSpOQYgiVJkpQc
   Q7AkSZKSYwiWJElScgzBkiRJSo4hWJIkSckxBEuSJCk5hmBJkiQlxxAsSZKk5BiCJUmSlBxDsCRJ
   kpJjCJYkSVJyDMGSJElKjiFYkiRJyTEES5IkKTmGYEmSJCXHECxJkqTkGIIlSZKUHEOwJEmSkmMI
   liRJUnIMwZIkSUqOIViSJEnJMQRLkiQpOYZgSZIkJccQLEmSpOQYgiVJkpQcQ7AkSZKSYwiWJElS
   cgzBkiRJSo4hWJIkSckxBEuSJCk5hmBJkiQlxxAsSZKk5BiCJUmSlBxDsCRJkpJjCJYkSVJyDMGS
   JElKjiFYkiRJyTEES5IkKTmGYEmSJCXHECxJkqTkGIIlSZKUHEOwJEmSkmMIliRJUnIMwZIkSUqO
   IViSJEnJMQRLkiQpOYZgSZIkJccQLEmSpORsNwSHEAaHEKaFEOaGEF4IIXxtG+2uCyHMDyHMCiEc
   3TWlSpIkSYXRs4Pn64ErYozPhxB6A8+GEB6KMc5rbhBCGAsMizEeEkIYBfwOOKHrSpYkSZI6Z7s9
   wTHG5THG53P764F5wMA2zc4Bfp9r8zSwdwhhQBfUKkmSJBVE3mOCQwhDgKOBp9s8NQhY0ur+UuCA
   zhYmSZIkdZW8QnBuKMQfgK/neoS3atLmfuxsYZIkSVJX6WhMMCGESuCPwG0xxnvaaVINDG51/4Dc
   Y1u56qqrWvZHjx7N6NGjd6BUSZIkaUtVVVVUVVXt8OtCjNvutA0hBJrG+66OMV6xjTZjga/GGMeG
   EE4AfhVj3OrCuBBC3N65JEmSuoMQQodfeQfA3JONEAIxxrajFLZu10EIPgV4FJjN34c4fAc4ECDG
   eGOu3fXAGGADcEmM8bl2jmUIliRJ3Z4huLQVJAQXkiFYkiSVA0Nwacs3BLtinCRJkpJjCJYkSVJy
   DMGSJElKjiFYkiRJyTEES5IkKTmGYEmSJCXHECxJkqTkGIIlSZKUHEOwJEmSkmMIliRJUnIMwZIk
   SUqOIViSJEnJMQRLkiQpOYZgSZIkJccQLEmSpOQYgiVJkpQcQ7AkSZKSYwiWJElScgzBkiRJSo4h
   WJIkSckxBEuSJCk5hmBJkiQlxxAsSZKk5BiCJUmSlBxDsCRJkpJjCJYkSVJyDMGSJElKjiFYkiRJ
   yTEES5IkKTmGYEmSJCXHECxJkqTkGIIlSZKUHEOwJEmSkmMIliRJUnIMwZIkSUqOIViSJEnJMQRL
   kiQpOYZgSZIkJccQLEmSpOQYgiVJkpQcQ7AkSZKSYwiWJElScgzBkiRJSo4hWJIkSckxBEuSJCk5
   hmBJkiQlxxAsSZKk5BiCJUmSlBxDsCRJkpJjCJYkSVJyDMGSJElKjiFYkiRJyTEES5IkKTmGYEmS
   JCXHECxJkqTkGIIlSZKUHEOwJEmSkmMIliRJUnIMwZIkSUqOIViSJEnJMQRLkiQpOYZgSZIkJccQ
   LEmSpOQYgiVJkpQcQ7AkSZKSYwiWJElScgzBkiRJSo4hWJIkSckxBEuSJCk5hmBJkiQlxxAsSZKk
   5BiCJUmSlBxDsCRJkpJjCJYkSVJyDMGSJElKjiFYkiRJyTEES5IkKTmGYEmSJCXHECxJkqTkGIIl
   SZKUHEOwJEmSktNhCA4h3BxCWBFCmLON50eHENaGEGbmtisLX6YkSZJUOD3zaPNfwG+AW7bT5pEY
   4zmFKUmSJEnqWh32BMcYHwPe6qBZKEw5kiRJUtcrxJjgCJwUQpgVQpgcQji8AMeUJEmSukw+wyE6
   8hwwOMa4MYRwJnAPMLy9hldddVXL/ujRoxk9enQBTi9JkqRUVVVVUVVVtcOvCzHGjhuFMAT4c4xx
   RB5tXwOOjTGuafN4zOdckiRJpSyEQEeJJgDmnmyEEIgxdjhUt9PDIUIIA0IIIbd/PE3Bek0HL5Mk
   SZIy0+FwiBDC7cAHgL4hhCXA94FKgBjjjcAngC+FEDYDG4FPdV25kiRJUuflNRyiICdyOIQkSSoD
   DocobUUbDiFJkiR1N4ZgSZIkJccQLEmSpOQYgiVJkpQcQ7AkSZKSYwiWJElScgzBkiRJSo4hWJIk
   SckxBEuSJCk5hmBJkiQlxxAsSZKk5BiCJUmSlBxDsCRJkpJjCJYkSVJyDMGSJElKjiFYkiRJyTEE
   S5IkKTmGYEmSJCXHECxJkqTkGIIlSZKUHEOwJEmSkmMIliRJUnIMwZIkSUqOIViSJEnJMQRLkiQp
   OYZgSZIkJccQLEmSpOQYgiVJkpQcQ7AkSZKSYwiWJElScgzBkiRJSo4hWJIkSckxBEuSJCk5hmBJ
   kiQlxxAsSZKk5BiCJUmSlBxDsCRJkpJjCJYkSVJyDMGSJElKjiFYkiRJyTEES5IkKTmGYEmSJCXH
   ECxJkqTkGIIlSZKUHEOwJEmSkmMIliRJUnIMwZIkSUqOIViSJEnJMQRLkiQpOYZgSZIkJccQLEmS
   pOQYgiVJkpQcQ7AkSZKSYwiWJElScgzBkiRJeVi6dCnjxo0D4LPA+mzLUSeFGGNxThRCLNa5JEmS
   CmndunUce+yxzJ8/v+WxccB9QGinfQDMPdkIIRBjbO9/yxbsCZYkSerAlVdeyfz58xkxYgQAewP3
   0xSC1T3ZEyxJkrQd1dXVHHTQQTQ0NPDss89y9NFH8yvgH4ETgKfaeY09wdmxJ1iSJKkAfv3rX1Nf
   X895553He9/7XgA+D+wFTAfmZVmcdpohWJIkaRvq6uqYOHEiAP/8z//c8vgewHm5/duLX5YKwBAs
   SZK0Df/3f//HmjVrOPLIIzn++OO3eO6Tudt7i1+WCsAQLEmStA2TJk0C4NOf/vRWz70f2BWYDawo
   alUqBC+MkyRJasfGjRvZd999qampYdGiRbz73e8Gchde5dqcAfwFuA1oHZO9MC47XhgnSZLUCX/9
   61+pqanhuOOOawnAbX04dzuteGWpQAzBkiRJ7Zg8eTIAY8eO3Wabk3K3TxehHhWWIViSJKmNGGNL
   CD7rrLO22e5ooCcwF1hXlMpUKIZgSZKkNubNm8frr79Ov379OPbYY7fZbjfgKCACM4pVnArCECxJ
   ktTGgw8+CMCZZ55JRcX249Ko3K1DIroXQ7AkSVIbjz76KACnn356h22b+4lndWE9KjxDsCRJUiuN
   jY088cQTAJx66qkdth+Ru53ThTWp8AzBkiRJrbz88susXr2aQYMGMWTIkA7bH0HTvMAvA7VdXJsK
   xxAsSZLUymOPPQbAKaecQggdrrnA7sAwYDPwUpdWpkIyBEuSJLXy+OOPA00hOF8Oieh+DMGSJEmt
   GILTYAiWJEnKqa6u5rXXXmPPPfdkxIgRHb8g54jc7ctdU5a6gCFYkiQpp3lWiJNOOokePXrk/brh
   udtXuqAmdQ1DsCRJUk7ri+J2xLDc7QKgobAlqYsYgiVJknJ2ZjwwwB7AIKAeeL3gVakrGIIlSZKA
   tWvXMnv2bCorKznuuON2+PXNQyLmF7YsdRFDsCRJEjB9+nQaGxs59thj2X333Xf49Y4L7l46DMEh
   hJtDCCtCCNuc9SOEcF0IYX4IYVYI4ejClihJktT1mscD57NUcnsOyd0agruHfHqC/wsYs60nQwhj
   gWExxkOAy4DfFag2SZKkotnZ8cDN7AnuXjoMwTHGx4C3ttPkHOD3ubZPA3uHEAYUpjxJkqSuV1dX
   x9NPPw00TY+2M5p7ghcUqCZ1rUKMCR4ELGl1fylwQAGOK0mSVBTPPfccNTU1HHbYYfTt23enjvHu
   3O3iwpWlLtSzQMcJbe7H9hpdddVVLfujR49m9OjRBTq9JEnSzmseCrGz44EBdgP2A5YXpiTlqaqq
   iqqqqh1+XSFCcDUwuNX9A3KPbaV1CJYkSSoVO7tIRltDMAQXW9uO1R/84Ad5va4QwyHuA8YDhBBO
   AN6OMa4owHElSZK6XGNjY8tyyZ0NwQcVoiAVRYc9wSGE24EPAH1DCEuA7wOVADHGG2OMk0MIY0MI
   C4ANwCVdWbAkSVIhvfzyy6xevZqBAwcyZMiQTh2rc69WMXUYgmOMF+bR5quFKUeSJKm4Wk+NVlHR
   uS/JhxSgHhWHK8ZJkqSktV0kI3awbY/DIboPQ7AkSUpaZxfJaG1Ip4+gYgkxdvRvmgKdKIRYrHNJ
   kiTlo7q6mgMOOIA+ffrw1ltv0bNnzw57ewPb7hGupWmqtAjU19fTs2ehZqNVvkIIxBjbTt+7FXuC
   JUlSsppnhTjppJPo0aNHp4+3CzAwt79kyZLtNVXGDMGSJClZhRwK0WxI7nbRokUFO6YKzxAsSZKS
   VahFMlprXkFs6dKlBTumCs8QLEmSkrR27VpmzZpFZWUlo0aNKthxD8jdGoJLmyFYkiQl6cknnyTG
   yPve9z522223gh23uSfYMcGlzRAsSZKS1DwU4v3vf39Bj2tPcPdgCJYkSUl69NFHgb8vklEojgnu
   HpwnWJIkJaempoa99tqL+vp61qxZw9577w3k5pjt4LXbmycY4A2apknr27cvK1euLEzBypvzBEuS
   JG3DM888Q11dHSNGjGgJwIXSP3e7atUqampqCnpsFY4hWJIkJaerxgMDtF5yo7q6uuDHV2EYgiVJ
   UnKaQ3ChxwO35QwRpcsQLEmSkrJ58+aW5ZK7OgR7cVzpMgRLkqSkzJo1i/Xr1zN06FD233//Lj2X
   Ibh0GYIlSVJSijUUAhwOUcoMwZIkKSnTpk0DuuaiuLbsCS5dhmBJkpSMzZs3U1VVBcDpp5/e5ecz
   BJcuQ7AkSUrGc889xzvvvMOwYcM48MADu/x8DocoXa4YJ0mSyl4IHS4g1qKzK8Y1t6moqKCxsZHa
   2lp69eqV9/nVOa4YJ0mS1EoEmgdA3Jm733YrpP322w+A5cuXF/jIKgRDsCRJSkIN8ERu/4NFON/A
   gQMBeOONN4pwNu0oQ7AkSUrCUzQF4aOAfkU4X/McxMuWLSvC2bSjDMGSJCkJD+duTyvS+Zp7gg3B
   pckQLEmSktAcgrt+YrQmDocobYZgSZKUhGeAnkDXL5HRxOEQpc0QLEmSktAInAL0KdL5HA5R2gzB
   kiQpGWOLeC6HQ5Q2Q7AkSSprjY2NLftnFvG89gSXNkOwJEkqazNnzgRgMHBEEc/br18/evTowapV
   q6irqyvimZUPQ7AkSSprDz74INDUC5z/4smdV1FR4apxJcwQLEmSytrkyZOB4o4HbuaQiNJlCJYk
   SWVr9erVPP3000DxFslozWnSSpchWJIkla0HHnig5cK4Yk2N1pozRJQuQ7AkSSpbf/rTnzI9v8Mh
   SpchWJIklaUNGzYwZcqUTGtwOETpMgRLkqSyNGXKFDZt2sSoUaMyq8HhEKXLECxJkspS81CIj3/8
   45nV4HCI0mUIliRJZae+vp77778fyDYEOxyidBmCJUlS2amqquLtt9/m8MMPZ/jw4ZnV0bxq3OrV
   q6mtrc2sDm3NECxJksrOXXfdBcC5556baR0VFRUtvcGuGldaDMGSJKms1NbW8sc//hGAT33qUxlX
   45CIUmUIliRJZWXKlCm89dZbjBw5kiOOOCLrcrw4rkQZgiVJUlm5/fbbAbjwwgszrqRJc0+w06SV
   FkOwJEkqG+vXr+fee+8FSmMoBDhXcKkyBEuSpLJx7733smnTJk466SSGDBmSdTmAY4JLlSFYkiSV
   jUmTJgFw0UUXZVzJ39kTXJoMwZIkqSxUV1czZcoUKisrueCCC7Iup4U9waWpZ9YFSJIkdUYIYYv7
   jY2N9O/fP6NqtuaFcaXJnmBJktTtNQAH5/YfBGKbLUvNq8atWrWKurq6jKtRM0OwJEnq9h4BXgUG
   Ax/OuJa2evTowYABAwBXjSslhmBJktTtTczdfg7okWEd2+LFcaXHECxJkrq9P+ZuL8m0im3z4rjS
   YwiWJEndXg3wEeCgrAvZBnuCS48hWJIkdVsNDQ0t+/+QYR0dsSe49BiCJUlSt3X//fcDMBQYm20p
   2+U0aaXHECxJkrqt6667DoCvUNqhpnk4hD3BpaOUf14kSZK2ae7cufz1r38FSveCuGb2BJceQ7Ak
   SeqWfv7zn7fs751hHfnwwrjSE2IszjoqIYRYrHNJkqTytnjxYoYOHUpjYyONjY0drgoXyG/luHza
   5d2mVe5paGigV69eNDY2UldXR2VlZR7VaGeEEIgxho7a2RMsSZK6nZ///Ods3ryZCy64IOtS8tKj
   Rw/69+8PwIoVKzKuRmAIliRJ3czKlSv5z//8TwC+/e1vZ1xN/rw4rrQYgiVJUrdy3XXXsWnTJs46
   6yxGjhyZdTl58+K40mIIliRJ3caqVav49a9/DXSvXmDw4rhSYwiWJEndxrXXXsu6desYM2YMJ598
   ctbl7BBXjSsthmBJktQtLF26lOuvvx6AH//4xxlXs+PsCS4thmBJktQtXH311dTW1nL++edzzDHH
   ZF3ODrMnuLQYgiVJUsl78cUXmThxIhUVFfzwhz/Mupyd4oVxpcUQLEmSSlqMka9//es0NDTwhS98
   gUMPPTTrknaKU6SVFleMkyRJJe2ee+7h4x//OHvvvTfz58+nb9++WzwfQij5FeMANm/eTK9evQCo
   q6ujZ8+eeVSkHeWKcZIkqdurqanhG9/4BtA0JrhtAO5OevbsSf/+/Ykx8uabb2ZdTvIMwZIkqWT9
   +Mc/5rXXXuPII4/ki1/8YtbldJoXx5UOQ7AkSSpJM2fO5JprriGEwA033FAWwwecJq10dP+fJkmS
   VHbq6+u59NJLaWhoAOCUU07JuKLCsCe4dNgTLEmSSs61117L888/D8A6mi5E29bWnThNWukwBEuS
   pJLy+OOP84Mf/KDlfu8Mayk0p0krHYZgSZJUMtasWcNFF11EQ0MD3/rWt7Iup+DsCS4dhmBJklQS
   GhsbufTSS1myZAmjRo3iRz/6UdYlFZwXxpUOQ7AkSSoJV111Fffeey977bUXt99+O5WVlVmXVHBe
   GFc6OgzBIYQxIYSXQgjzQwj/0s7zo0MIa0MIM3PblV1TqiRJKld33HEHV199NRUVFdx5550cdNBB
   WZfUJQYMGADAihUrWma+UDa2G4JDCD2A64ExwOHAhSGEw9pp+kiM8ejcVn7fXUiSpC7z6KOPcskl
   lwDwi1/8gjPOOCPjirpOr1696NevH42Nja4al7GOeoKPBxbEGBfFGOuBO4CPttOuw/WZJUmS2pox
   Ywbjxo2jpqaGL37xi3zta1/LuqQu58VxpaGjEDwIWNLq/tLcY61F4KQQwqwQwuQQwuGFLFCSJJWn
   OXPmMGbMGNatW8cnP/lJrr/+ekIo/341p0krDR2F4HzmoH4OGBxjPAr4DXBPp6uSJEll7cknn2Tk
   yJGsXr0agDvvvJOePXsSQthiK0f2BJeGjpZNrgYGt7o/mKbe4BYxxnWt9h8MIfw2hLBPjHFN24Nd
   ddVVLfujR49m9OjRO1GyJEnqziZPnswnPvEJAD4O/A+w6zbalmMMdpq0wqqqqqKqqmqHX9dRCJ4B
   HBJCGAIsAz4JXNi6QQhhAPBmjDGGEI4HQnsBGLYMwZIkKS0xRq699lq++93vEmPTl8130XEYKTdO
   k1ZYbTtWW682uD3bHQ4RY9wMfBWYArwI3BljnBdCuDyEcHmu2SeAOSGE54FfAZ/a4eolSVJZW7Nm
   Deeffz7f+c53iDG2BJXUAjA4HKJUhOZ/iXX5iUKIxTqXJEkqHZMnT2bChAksX76cPffck0mTJjFu
   3DhCCB1efBTo+AKlQrUp+Pm2kXumT5/OiSeeyPve9z7+9re/5VGVdkQIgRhjhyNpXDFOkiR1iblz
   53Luuedy1llnsXz5ck455RSee+45xo0bl3VpmbInuDQYgiVJUkEtWLCAiy++mBEjRvCnP/2J3Xbb
   jZ/+9KdUVVUxdOjQrMvL3H777QfA8uXLXTUuQ4ZgSZJUEEuXLuXyyy/nsMMOY9KkSfTs2ZOvfvWr
   LFy4kG9+85v06NEj6xJLwi677MK+++5LQ0MDq1atyrqcZDkmWJIkdcrKlSu55ppr+O1vf0ttbS0V
   FRU0Njbm9doUxwQDjBw5kjlz5jBz5kze+9735lGZ8uWYYEmS1KXWrl3L9773PQ466CB++ctfUltb
   ywUXXMDcuXOBpqC4vS1lTpOWvRRnJpEkSZ1QV1fH7373O66++uqWFd/GjRvH1Vdfba9mnrw4LnuG
   YEmSlLeHH36YD33oQ1s9fv/993P//fdnUFH31LxqnD3B2TEES5KkFiHkt1DxYcBPgbNof2njclzu
   uJAGDRoENF1MqGw4JliSJG2h7djd+cCRued65W5nAeMw7O6swYMHA7BkyZKMK0mXIViSJG3Tk8Bx
   wAvAocCzuccrM6uoPBiCs2cIliRJ7XoY+DDwNvBR4Gn+3iOszjEEZ88QLEmStjIdOBvYCHwO+COw
   Z5YFlZl9992XXXfdlbVr17Ju3bqsy0mSIViSJG1hAU0BeBNwCTARcK23wgohcOCBBwL2BmfFECxJ
   krbwMWAVMAa4EcNCV2keErF48eKMK0mTU6RJkpSIfKc/m0vTRXB34QVwXclxwdnyH3eSJCVke8sY
   35lrs2tuv08WBSbEEJwtQ7AkSWIN8A+5/Z8DIzOsJRWG4GwZgiVJEv8CvJnb/2KWhSTEEJwtQ7Ak
   SYl7CriJv68GZzgojubZIbwwLhv+nEuSlLAI/HNu/5+311AF17onOMaYcTXpMQRLkpSwe2laGrkv
   TUMiVDx9+vRhr732oqamhtWrV2ddTnIMwZIkJWoz8O3c/r/hinBZcFxwdgzBkiQl6i7gJeBg4PKM
   a0mVITg7hmBJkhLUCFyT2/82f78oTsXl0snZMQRLkpSgB4AXgIHAZzKuJWXNIXjRokXZFpIgQ7Ak
   SYmJ/L0X+J+AXTKsJXUHHXQQAK+99lrGlaTHECxJUmKeym37AJdlXEvqDj74YMAQnAVDsCRJibk+
   d3sZ0DvLQtTSE/zqq69mXEl6QrEmZw4hRCeCliQpOyEElgODgQbgVeDdbdvQNFxiu8cp0zYFP18e
   uSfGSJ8+fdiwYQNr1qzhXe96Vx5VantCCMQYQ0ft7AmWJCkh/wnUA2ezdQBW8YUQHBecEUOwJEkJ
   uSF3+5VMq1BrhuBsGIIlSUpINTAcOD3rQtSi+eI4xwUXlyFYkqTEXI4BoJTYE5wNfwckSUrAypUr
   AegBfDrbUtSGPcHZMARLkpSAO++8E4AzgAHZlqI27AnOhiFYkqQE3HLLLYBLJJei5hC8aNEiGhsb
   M64mHYZgSZLK3EsvvcTf/vY3AD6acS3a2h577EH//v2pq6tj2bJlWZeTDEOwJEll7tZbb23Z3y3D
   OrRtQ4cOBWDBggUZV5IOQ7AkSWWssbGR2267Lesy1IHhw4cD8PLLL2dcSToMwZIklbHHHnuMxYsX
   c+CBB2ZdirbjPe95D2AILiZDsCRJZaz5griLL74440q0PYbg4jMES5JUpjZt2sT//u//AvCZzzgv
   RClrDsGvvPJKxpWkwxAsSVKZuvfee1m3bh3HHXcchx56aNblaDuGDRtGCIHXXnuNurq6rMtJgiFY
   kqQy1TwrxPjx4zOuRB3ZZZddGDJkCA0NDSxcuDDrcpJgCJYkqQytWLGCKVOm0LNnTz71qU9lXY7y
   4Ljg4jIES5JUhm6//XYaGhoYO3Ysffv2zboc5cEQXFyGYEmSylDLMsleENdtGIKLyxAsSVKZmTt3
   LjNnzmTvvfdm3LhxWZejPDVfvDhv3ryMK0mDIViSpDLTfEHcBRdcwK677ppxNcrXkUceCcALL7xA
   Y2NjxtWUP0OwJEllpKGhoWWZZGeF6F769evH/vvvz/r161m0aFHW5ZS9nlkXIEmFUF9fz6JFi3j9
   9deprq6murqaZcuWUV1dzcqVK1m3bh3r1q1j/fr11NbW0qNHD3r27EllZSX77LMP/fv3p3///gwd
   OpTDDz/49HsfAAAUw0lEQVScww8/nCOOOILKysqs/9OkvIQQtnrslFNOyaASdcaIESN44403mD17
   NgcffHDW5ZQ1Q7CkbmPz5s28/vrrzJ8/f6tt0aJFNDQ07NRxly1bttM1xRh3+rVSoUXgs8AtwL8B
   P2jz/NYxWaVm5MiR/OUvf2H27Nl87GMfy7qcsmYIllRy3nrrLebOncuLL77IvHnzeOWVV1iwYEHe
   y4l+GhgIDMrdDgD2BHoDfYD9gFVAA1ALrAHeBJYDrwAvAne3c9wDgI8BnwJOwvFkKj3rgT/m9h0I
   0T2NHDkSgNmzZ2dcSfkzBEvKTH19PS+++CIzZsxg1qxZvPjii8ydO5fly5dv8zUHAIe0sx0M7EpT
   T9dteZx731b7g9t5PtAUih8D/grcCywFrs9tw3Ptli1bxsCBA/M4o9T1/ghsAE4BhmZci3ZOcwie
   M2dOxpWUv1Csr/JCCNGvDaW0LVu2jKqqKqZPn86MGTOYOXMmNTU1O3SMjv6KhC5q0wjMAP4A3EpT
   QAaoqKhg7NixXHbZZZx55pn07GnfgrIRQuCDwDTgP4HPt9eG7H6HukObgp9vJ3JPbW0tvXv3pqGh
   gfXr17P77rvv8DFSF0Igxtjh6B9DsKQu8+abbzJgwIC82/8ZOAJ4N+0PNSiVD8zNwBRgHFBZWUl9
   fT0AgwYNYsKECUyYMIEDDzywgzNIhdV8YdyuNP0jba/22lAav0Ol2qbg59vJ3DNixAheeOEFnnzy
   SU488cSdOkbK8g3BDmmTVDAxRmbNmsWPfvQjTjjhBPbbb78tnu8NjAF+BPwFWE3TB0nzx8Q44CBK
   /w9TT+Cs3H51dTU/+9nPOOSQQ6iuruaHP/whQ4YM4ayzzuLee+9l8+bNWZaqBH2M9gOwuo/jjz8e
   gGeeeSbjSsqb39tJ6pQYIzNmzOD222/nD3/4A0uWLGl5bpdddqG2tpZrgdHAMUC5TTjWv3//rR6L
   MTJ58mQmT54MwJVXXsnnP/953v3udxe7PCWidY/jZzOsQ4Vx/PHHc/PNNxuCu5jDISTtlJdffpnb
   bruNO+64gwULFrQ8vt9++zFu3DjOPvtsTj/9dHr37l38ryAzbrOKpimq/h/wcgfHaObfR3XGk08+
   ycknn8z+wBKgxzbalcLvRym3Kfj5dvL3+vnnn+foo49m2LBhzJ8/f6eOkTLHBEsquNraWu6++25u
   vPFGHnnkkbxfl1oIbhZpGtpxEU0X1NXlHt8PuJSmC5cOonMflhLAJZdcwn//93/zLeAn22lXSr8f
   pdim4Ofbyd/rzZs3s+eee7Jp0yZWrVrFvvvu2/GL1MIQLKlT2lt9qj1TaRrq0Jmep3zbdec2q/l7
   7/BLrZ77CE0X2dXV1bk6nXbKW2+9xcCBA6mpqWEB258arVR/P0qlTcHP14ncc+qpp/L444/z4IMP
   MmbMmJ0+Toq8ME5Sp82iaeGJ1gH3KOC3wNrc/dPZdgDW3+0LXEHTQhyPAhcDvWgKwACDBw/mO9/5
   Dq+++mpGFaq7uvXWW1umGnRu4PLRfHHc9OnTM66kfBmCJW0hxtgy1OEoYFLu8U8D04GZwJdoWoFN
   Oy4Ap9I01/Ay4Fe5x1esWME111zD0KFD+chHPsIf/vAH6urqtnkcCZp+X2+44Yasy1AXOPXUUwGo
   qqrKtpAyZgiWBEBDQwN33303J5xwAqNHjwZgd+BrwEKaVmEbRVOIU2HsA3w9t//4448zfvx4dt11
   Vx566CHOP/98Bg8ezL/+679uceGh1Npjjz3GvHnz2H///bMuRQX2gQ98gBACTz31FBs3bsy6nLJk
   CJYSV1tby0033cThhx/OeeedxzPPPEPfvn0BWAz8mqbFK9S1TjnlFG655ZYtVtB78803+clPfsIh
   hxxCCIEbbriB1atXZ1ilSs11110HwIQJEzKuRIX2rne9i6OPPpq6ujqefPLJrMspS4ZgKUEhhJZt
   11135Qtf+AKvvPJKy/OrVq0Cmsaxqjhim60ReIKmOV93y7X50pe+xH777cc555zDHXfcYe9Q4hYu
   XMjdd99NZWUlX/7yl7MuR13ggx/8IADTpk3LuJLyZAiWElNdXQ1An1aPHQX8D1DPliu4KTsBOAn4
   b2BF7rEzzjiDxsZG/vznP3PhhRcyYMAAxo8fz5QpU1yZLkG//OUviTFy8cUXOxyiTJ122mkATJ06
   NeNKypNTpEmJePbZZ7n++uuZNGkS9fX1AJwG/AvwYbYe69utpyUq1zYxsmLFCu68804mTZq0xWpS
   /fr14/zzz+eiiy7ixBNPpKLCPo5ytnr1agYPHsymTZt44YUXOOKII5qmhergdSX5c11CbQp+vk7m
   ng0bNtC3b19qampYtmyZ/9jJk/MES6Kmpoa77rqL//iP/2gJTLk/DjwDHLed13brD54ybZOvAw88
   kAsvvJALL7yQkSNH5j3ns7qP733ve/zoRz9izJgxPPjggwCG4AK0Kfj5CpB7zj77bO6//35uvPFG
   Lrvssk4fLwWGYClRMUaef/55br31Vm699daW8b177703l1xyCV/+8pc55JBDyvuDJ7E2EXgeOKaD
   Y7S0929xt7Zy5UoOPvhg1q9fzxNPPMFJJ50EGIJL8m9RAX7XJk6cyOc//3nGjh3LAw880OnjpSDf
   ENyzGMVI6nrV1dVMmjSJW2+9lRdeeKHl8aOPPpqvfOUrXHjhhey+++4ZVqiuEoCjc/sNNF1Q9z/A
   /9K0Ul2z44FngDfeeMOvVbuxn/70p6xfv56xY8e2BGCVr3HjxhFCYOrUqaxdu5a99tor65LKhj3B
   Uje2cuVK7rnnHu666y4efvjhHep1KOveF9sATRc6TqUpEN8DrG9uFwKnnXYa48eP59xzz6V3794d
   HFmlYvHixbznPe+hpqaGGTNmcOyxx7Y8Z09w59sU/HwFyj2nnXYa06ZN44YbbuDyyy8vyDHLmcsm
   S2VqxYoV3HDDDXzoQx9i//3357LLLmPq1KlUVlZy3nnnAVDL1lNutd6UhkrgTJpWp1sB3NX8eGUl
   Dz/8MJ/97GdbZpiYOnUqDQ0NmdWq/HzjG9+gpqaGT37yk1sEYJW3Sy+9FICbb74540rKiz3BUjfw
   xhtvcPfdd/PVr341r/al1LNiT3DptcmXf7NLy0MPPcRHPvIR9thjD1566SUOOOCALZ63J7jzbQp+
   vgL9Dm3cuJH999+fd955h9mzZzNixIiCHLdc2RMsdXPV1dX85je/4f3vfz+DBg1qCcCVwFnAfwFr
   sJdXO671z8sC4Crg4Hba/epXv2LFihXtPKNie+edd1pmBvje9763VQBWedt99935zGc+A8C///u/
   Z1xN+bAnWCoRMUbmzp3Lfffdx3333cfTTz/d8twuu+zCGWecwX333cdbwN7bOU6p9azYE9w92kTg
   SZqGTtwJvJ17vEePHpxxxhmMHz+ec845h912262dV6urfe5zn+P3v/89xxxzDE899RS9evXaqo09
   wZ1vU/DzFTD3vPrqqwwfPhyABQsWMGTIkIIdu9w4RZrUDdTV1fH4449z33338etf/zqv15TSB0bJ
   fvDYplNtamhaqvmcc85h8uTJLavR7bbbbnzoQx9i3LhxnHXWWQwaNKiDI6kQbr75ZiZMmMBuu+3G
   c889x6GHHtpuO0Nw59sU/HwFzj2f+cxnuO222xg/fjy///3vC3rscmIIlkpQY2Mjc+bMYerUqUyd
   OpVHH32UjRs3tjzfDzgbOAf4ELBHm9eX2gdGyX7w2KZTbZrb5eOKK67g/e9/P6eeeir77rtvnq9S
   vh555BE+/OEPU19fz0033cSECRO22dYQ3Pk2BT9fgXPPwoULOfzww6mrq9tijmhtyRAslYBNmzbx
   7LPP8tRTTzF9+nQee+wxVq5cuUWbI444grPPPptrr72WzUCP7Ryv1D4wSvaDxzadarOtdm8Ak4H7
   gb8AG9s8f+SRR3LiiSdyzDHHcMwxxzBixAiHT3TC448/zplnnsn69eu54oor+MUvfrHd9obgzrcp
   +Pm6IPc0rxY4fPhwZsyYQZ8+fQp+ju7OECwV2dq1a5kzZ07L9swzzzBr1qyWr5LzUUofBt36g8c2
   nWqTT7vmIRP/9m//xiOPPML06dOpra3dok2PHj049NBDOeywwxg+fPgW2z777ONyzttx9913M378
   eDZs2MBFF13ELbfcQo8e2/snsiG4JP8WdUHu2bRpE6NGjWLOnDmce+653HXXXR3+bKTGECx1gYaG
   BhYvXszChQtZsGABCxcu5KWXXmL27NksXrx4q/YVFRUceeSRzJ49m/8CTgSG0/5XzaX2YdCtP3hs
   06k2O3KsndW7d28OPPBABg8evNXt4MGDGTRoUJIrHK5bt44rr7yS6667Dmi6IO6mm27KK+QYgjvf
   puDn66Lc8/LLL3Pcccexbt06Pv3pTzNx4kR22WWXLjlXd1SwEBxCGAP8iqZvaW+KMf6knTbX0TQn
   +0bgczHGme20MQRnpKqqitGjR2ddRsmLMfL222+zdOlSqqurW26rq6tZsmQJr776Kq+99hr19fU7
   d/wOni+1D4Nu/cHT6n4VMLpI5yqXNoU61hRgTB7nyte3v/1tBg4cyKBBg1puBwwYQGVlZQHPko2N
   GzcyceJEfvKTn1BdXU2PHj342c9+xj/+4z/m3WPeNgRX4c/+jrYp+Pm6MPc88cQTnHHGGWzYsIHj
   jz+eiRMncuSRR3bZ+bqTfENwzw4O0gO4nqZrdKqBv4UQ7osxzmvVZiwwLMZ4SAhhFPA74IROVa+8
   xRhZsGABQ4cOpaKi/WmfyzUExxipq6ujpqZmm1ttbe0W99evX8/q1atZtWrVVrcrVqxg06ZNO1XL
   PGAY7f9CXQX8YOf/M9VJVWwdBFQcT+Vu28aACKwFFue2s4F/BZbk7i8BlgF1bV53zTXXbHWOEAL9
   +/dvCcZtQ/LAgQMZMGAAffr0Yffddy+ZIRgxRhYtWsT06dN54IEHuO+++1i3bh0Axx13HDfccAPH
   HHNMp85RhT/75ezkk0+mqqqK8847j2eeeYajjjqKCy64gAkTJvCBD3ygLP5x2NW2G4KB44EFMcZF
   ACGEO4CP0vSZ3+wc4PcAMcanQwh7hxAGxBidYb0IFi5cyPDhw9lzzz059thjGTZsGAcccAADBgxg
   jz32YPfdd2fBggU8/PDDhBC22CoqKlr2Y4w0NjZusXXmsebHN2/eTH19PXV1dTu8tRdi2wbcYvgt
   MIimxQQOBtp+QRuA9icsktSeQNNc13sDI3OPtY23EVhNUxheRtNXje2JMbJixQpWrFjBc889t93z
   VlRU0Lt3b/bcc0/69OlD79692WWXXaisrKRXr17tbpWVlVRUVFBRUUGPHj1a9tveb++5EAI1NTVs
   3LiRDRs2sGHDBt58800WL17M66+/zttvv71FfaNGjeJb3/oWH/3oRx3jqby8733vY+bMmXz/+9/n
   d7/7HXfccQd33HEHe+65JwsWLKBfv35Zl1jSOgrBg2j6R3mzpcCoPNocQNNS9epib7zxBgMHDmTZ
   smVMmzaNadOmtdtu0qRJRa6s9P0e6Avsm7vtB+zZpk0AvlTkuiQ1/e71zW3NQbm9L5Y3A8tpCspt
   P5zaamxs5J133uGdd94pWJ2d0bdvX0aNGsWpp57Keeedx7Bhw7IuSd3QPvvsw29+8xu++c1vcvPN
   N3PXXXcRYzQA52G7Y4JDCOcBY2KMX8jdvxgYFWP8h1Zt/gxcG2N8Ind/KvCtGONzbY7lgGBJkiR1
   uU6PCaZpHPDgVvcH09TTu702B+Qe2+FiJEmSpGJo/0qqv5sBHBJCGBJC6AV8ErivTZv7gPEAIYQT
   gLcdDyxJkqRStt2e4Bjj5hDCV2ma6aYHMDHGOC+EcHnu+RtjjJNDCGNDCAuADcAlXV61JEmS1AlF
   WyxDkiRJKhUdDYcouBDCP4UQGkMI+xT73CkLIVwdQpgVQng+hPBwCGFwx69SoYQQfhZCmJf7f3B3
   CGGvrGtKRQjh/BDC3BBCQwihcxOvKm8hhDEhhJdCCPNDCP+SdT0pCSHcHEJYEUKYk3UtqQkhDA4h
   TMv9zXkhhPC1rGtKSQhh1xDC07ms82IIYevJxVspagjOBa8PA68X87wC4KcxxqNijO8F7gG+n3VB
   ifkLcESM8SjgFeDbGdeTkjnAx4FHsy4kFa0WWhoDHA5cGEI4LNuqkvJfFHaxPuWvHrgixngETQuH
   fcWf/eKJMdYAH8xlnZHAB0MIp2yrfbF7gn8BfKvI5xQQY1zX6m5vYFVWtaQoxvhQjLExd/dpmmZR
   URHEGF+KMb6SdR2JaVloKcZYDzQvtKQiiDE+BryVdR0pijEujzE+n9tfT9PiYgOzrSotMcaNud1e
   NF3PtmZbbYsWgkMIHwWWxhhnF+uc2lII4cchhMXAZ4Frs64nYZcCk7MuQupC7S2iNCijWqRMhBCG
   AEfT1PGhIgkhVIQQnqdp0bZpMcYXt9W2o3mCd/TEDwH7tfPUd2n6+vcjrZsX8tza7vv/nRjjn2OM
   3wW+G0L4V+CXOJNHQXX0/ufafBeoizH+T1GLK3P5vPcqKq+4VtJCCL2BPwBfz/UIq0hy37q+N3ft
   zZQQwugYY1V7bQsagmOMH27v8RDCkcBBwKwQAjR9FfxsCOH4GOObhawhZdt6/9vxP9gTWXAdvf8h
   hM8BY4HTi1JQQnbgZ1/Fkc9CS1JZCiFUAn8Ebosx3pN1PamKMa4NITwAvA+oaq9NUYZDxBhfiDEO
   iDEeFGM8iKY/hscYgIsnhHBIq7sfBWZmVUuKQghjgG8CH80N3Fc2/AaqOPJZaEkqO6Gpp28i8GKM
   8VdZ15OaEELfEMLeuf3daJqMYZt5p+hTpOX4VVnxXRNCmJMbJzMa+KeM60nNb2i6IPGhEMLMEMJv
   sy4oFSGEj4cQltB0pfYDIYQHs66p3MUYNwPNCy29CNwZY5yXbVXpCCHcDjwJDA8hLAkhOPSteE4G
   LqZpVoKZuc2ZOopnf+CvuazzNPDnGOPD22rsYhmSJElKTlY9wZIkSVJmDMGSJElKjiFYkiRJyTEE
   S5IkKTmGYEmSJCXHECxJkqTkGIIlSZKUnP8Px40tvHEUMp8AAAAASUVORK5CYII=
   "
   >
   </div>
   
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing text_cell rendered">
   <div class="prompt input_prompt">
   </div>
   <div class="inner_cell">
   <div class="text_cell_render border-box-sizing rendered_html">
   <p>The fitted KDE object is a full non-parametric distribution.</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">obs_dist3</span> <span class="o">=</span> <span class="n">mixture_rvs</span><span class="p">([</span><span class="o">.</span><span class="mi">25</span><span class="p">,</span><span class="o">.</span><span class="mi">75</span><span class="p">],</span> <span class="n">size</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="n">dist</span><span class="o">=</span><span class="p">[</span><span class="n">stats</span><span class="o">.</span><span class="n">norm</span><span class="p">,</span> <span class="n">stats</span><span class="o">.</span><span class="n">norm</span><span class="p">],</span>
                   <span class="n">kwargs</span> <span class="o">=</span> <span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">loc</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span><span class="n">scale</span><span class="o">=.</span><span class="mi">5</span><span class="p">),</span><span class="nb">dict</span><span class="p">(</span><span class="n">loc</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span><span class="n">scale</span><span class="o">=.</span><span class="mi">5</span><span class="p">)))</span>
   <span class="n">kde3</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">nonparametric</span><span class="o">.</span><span class="n">KDEUnivariate</span><span class="p">(</span><span class="n">obs_dist3</span><span class="p">)</span>
   <span class="n">kde3</span><span class="o">.</span><span class="n">fit</span><span class="p">()</span>
   </pre></div>
   
   </div>
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[9]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">kde3</span><span class="o">.</span><span class="n">entropy</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>
   1.3343301918419768
   </pre>
   </div>
   
   </div>
   
   </div>
   </div>
   
   </div>
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[10]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">kde3</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="o">-</span><span class="mi">1</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[10]:</div>
   
   
   <div class="output_text output_subarea output_pyout">
   <pre>
   array([ 0.17992591])
   </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">
   <h4 id="CDF">CDF<a class="anchor-link" href="#CDF">&#182;</a></h4>
   </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">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">kde3</span><span class="o">.</span><span class="n">support</span><span class="p">,</span> <span class="n">kde3</span><span class="o">.</span><span class="n">cdf</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,iVBORw0KGgoAAAANSUhEUgAAAsEAAAHfCAYAAACxhQUCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xec1dWd//HXkRJbVCwYBRQUu1gXUWyjoiGYqNHYYoIF
   jcZYEjUY9ZcNu5sYW6JRElREBUXEQhRFxAITwUJEEVEpIhKKGqzEijPM+f3xHcxIYBp37rnl9Xw8
   5sFc58vMe+/q8t7D55wTYoxIkiRJ5WSN1AEkSZKkfLMES5IkqexYgiVJklR2LMGSJEkqO5ZgSZIk
   lR1LsCRJkspOgyU4hHBrCOGfIYTp9TxzfQjh9RDCtBDC7rmNKEmSJOVWY1aCbwN6r+qLIYQ+QNcY
   4zbAT4BBOcomSZIktYgGS3CMcSLwYT2PHAEMrX12MrBBCGHT3MSTJEmSci8XM8EdgAV1Xi8EOubg
   +0qSJEktonWOvk9Y4fV/3MUcQvB+ZkmSJOVFjHHFfvo1uSjBi4BOdV53rP1nKwuTgx8ngAEDBjBg
   wIDUMUqC72Vu+X7mlu9n7vhe5lYhvJ9LlsDcuTB/Prz9Nrzzztd/XbwYPvoIPv4Y1l0X2rWDDTbI
   fl1/fVhnHVh77a9/rLXW1z//xjegTZvGf7RuDa1awRprfP0jhJX/s+UK4f0sJSHU23+B3JTg0cA5
   wN0hhL2Bj2KM/8zB95UkSWWuuhpmz4aXX4ZXXoE5c7LiO3cufPEFbLUVbLklbLYZfOtbsNtu2a+b
   bQabbAIbbgjrrZcVU6muBktwCGEEcCCwcQhhAfAboA1AjPGmGOMjIYQ+IYQ5wKfAqS0ZWJIklaaa
   GnjtNXj6aXj2WZg2DWbNgo4doVu37ON734Ott87K7yabfH01VWqKBktwjPHERjxzTm7iqLEqKipS
   RygZvpe55fuZW76fueN7mVu5eD9jhOnT4dFHYfx4eO45aN8eevaEffaBs8+GnXbKxhZKnf9+5l/I
   15xuCCE6EyxJUnn77DMYOxbGjIFx42DNNeE734FevbLy27596oQqBSGEBjfGWYIlSVKLWro0W+0d
   ORIeeQS6d4cjj4TevaFr19TpVIoswZIkKZmZM+Hmm+GOO7KxhuOPh2OOcbVXLa8xJThX5wRLkiSx
   bBk88ADccENWgk89FSZPzjaySYXEEixJklbbl1/CnXfCVVdlZ/BeeCEcdRS0bZs6mbRylmBJktRs
   VVUweDBcfnk28nDjjXDggR5dpsJnCZYkSU0WI9x7L1x2WTbq8MAD8F//lTqV1HiWYEmS1CRTp8JP
   f5rd5jZoUHa8mVRs1kgdQJIkFYclS+C887KjzX7yE/j73y3AKl6WYEmS1KAxY2DHHeGLL7KrjU87
   DdawRaiIOQ4hSZJW6V//ggsugCefhLvuyja9SaXA/x9OkiSt1LPPwq67Zic9vPyyBVilxZVgSZL0
   NTHCn/6UHXs2eHB2xbFUaizBkiTpK0uWQL9+MG9edtNbly6pE0ktw3EISZIEwNy5sPfesPHGMGmS
   BVilzRIsSZJ45hnYd18455zs1rc110ydSGpZjkNIklTm7r4bzj0Xhg2D73wndRopPyzBkiSVsYED
   4corsyPQdtkldRopfyzBkiSVqd//HoYMgYkToXPn1Gmk/LIES5JUZmKESy6Bhx6Cp56CzTdPnUjK
   P0uwJEllJEbo3x/Gj4e//S07CUIqR5ZgSZLKyP/8Dzz2GEyYABtumDqNlI4lWJKkMnHVVTByZLYC
   bAFWubMES5JUBgYNgptuymaA27dPnUZKL8QY8/ODQoj5+lmSJOnfRo+Gs87KboHbaqvUaaSWF0Ig
   xhjqe8aVYEmSStjzz8Ppp8OYMRZgqS6vTZYkqUS9+SYceSTccgt07546jVRYLMGSJJWgJUugTx+4
   9FI44ojUaaTC40ywJEklpqYGvv996NAB/vKX1Gmk/HMmWJKkMvTb38J778G996ZOIhUuS7AkSSXk
   4Yfh5puzDXFt26ZOIxUuS7AkSSVizhw47TR48EHYbLPUaaTC5kywJEkl4MsvYd99oW9fOPfc1Gmk
   tBozE2wJliSpBFx0Ebz+OjzwAIR6/+iXSp8b4yRJKgOPPgojR8JLL1mApcayBEuSVMTeeSebAx4x
   AjbaKHUaqXh4WYYkSUUqxqwAn346HHhg6jRScbEES5JUpG67LVsJ/vWvUyeRio8b4yRJKkLz58Oe
   e8L48dCtW+o0UmFpzMY4V4IlSSoyMWYjEL/4hQVYai5LsCRJRWbwYPjwQ+jfP3USqXg5DiFJUhFZ
   tAh22w0qK2GnnVKnkQqT4xCSJJWY88+Hn/7UAiytLs8JliSpSIwZA9OmwZ13pk4iFT9LsCRJReDT
   T+Gcc7J54DXXTJ1GKn7OBEuSVAQuvjibB3YVWGpYY2aCLcGSJBW4V1+Fgw6C6dNh001Tp5EKnxvj
   JEkqcjFmm+H++78twFIuWYIlSSpgo0dnVyOfdVbqJFJpcWOcJEkFaulSuOACuOkmaO2f2FJOuRIs
   SVKBuu462Hln6NUrdRKp9LgxTpKkAvT229CtGzz3HHTtmjqNVFw8HUKSpCJ1xhnQrh1cdVXqJFLx
   aUwJdsJIkqQCM3MmPPAAzJ6dOolUupwJliSpwFx6Kfzyl9lKsKSW4TiEJEkF5Lnn4Nhjs1XgtdZK
   nUYqTl6WIUlSEYkxux55wAALsNTSLMGSJBWIsWNh8WI4+eTUSaTSZwmWJKkA1NTAJZfA5Zd7MYaU
   D5ZgSZIKwN13w9prw1FHpU4ilQc3xkmSlNiyZbDTTjBwoLfDSbngxjhJkorAyJGw0UZwyCGpk0jl
   w5VgSZISWrYMdt4Zrr8eDj00dRqpNLgSLElSgbvnnuxSDMcgpPxyJViSpESWrwL/6U9w2GGp00il
   w5VgSZIK2L33ZqvAjkFI+edKsCRJCSxbBt26wbXXwre/nTqNVFpcCZYkqUCNGgXrrecYhJSKJViS
   pDyLEa68MrshLtS7ViWppViCJUnKs/Hj4bPP4HvfS51EKl+WYEmS8uyKK+CXv4Q1/FNYSsaNcZIk
   5dELL8BRR8Ebb0DbtqnTSKXJjXGSJBWYq66CX/zCAiyl5kqwJEl58sYbsPfeMHcufPObqdNIpcuV
   YEmSCsg118BZZ1mApULgSrAkSXmweDFsvz3MnAnt26dOI5U2V4IlSSoQN94Ixx5rAZYKhSvBkiS1
   sKVLoXNnePJJ2HHH1Gmk0udKsCRJBWDkSNhlFwuwVEgswZIktaAY4brr4Oc/T51EUl0NluAQQu8Q
   wswQwushhItX8vWNQwiPhhBeCiG8EkI4pUWSSpJUhCZOzK5I/va3UyeRVFe9JTiE0AoYCPQGdgRO
   DCHssMJj5wBTY4y7ARXAH0IIrVsgqyRJRee66+D8870iWSo0Df0nuRcwJ8Y4L8ZYBdwNHLnCM28D
   69V+vh7wfoyxOrcxJUkqPnPnwlNPQd++qZNIWlFDK7YdgAV1Xi8EeqzwzGBgfAjhLeCbwHG5iydJ
   UvEaOBD69YN11kmdRNKKGirBjTnT7FLgpRhjRQhha+DxEMKuMcaPVz+eJEnF6V//gqFDYerU1Ekk
   rUxDJXgR0KnO605kq8F19QR+BxBjfCOE8CawHTBlxW82YMCArz6vqKigoqKiyYElSSoGt98OBx8M
   W2yROolU+iorK6msrGzS76n3sozaDW6zgEOAt4C/AyfGGGfUeeaPwJIY4/+EEDYFXgB2iTF+sML3
   8rIMSVJZiBF22AEGD4b990+dRio/jbkso96V4BhjdQjhHGAc0AoYEmOcEUI4s/brNwGXA7eFEKaR
   bbTrv2IBliSpnEyYAK1bw377pU4iaVW8NlmSpBz7wQ+yUYizz06dRCpPjVkJtgRLkpRDb70FO+8M
   8+bBeus1+LikFtCYEuzR3ZIk5dDgwXD88RZgqdC5EixJUo5UVUHnzjB2LOyyS+o0UvlyJViSpDx6
   6CHo0sUCLBUDS7AkSTnyl7+4GU4qFo5DSJKUA7NmwQEHwPz58I1vpE4jlTfHISRJypMbb4TTTrMA
   S8XClWBJklbT559Dx44wZUo2EywpLVeCJUnKg/vvh+7dLcBSMbEES5K0mm65BU4/PXUKSU3hOIQk
   Sath9mzYf39YsADatk2dRhI4DiFJUosbMgT69rUAS8XGlWBJkpqpqgo6dYLKSth++9RpJC3nSrAk
   SS3o4Ydhm20swFIxsgRLktRMt9wCZ5yROoWk5nAcQpKkZliwAHbdFRYuhLXXTp1GUl2OQ0iS1EJu
   uw1OOMECLBUrV4IlSWqiZctgq63gr3+FPfZInUbSilwJliSpBTz5JGy8sQVYKmaWYEmSmsgb4qTi
   5ziEJElN8P77sPXWMG8ebLBB6jSSVsZxCEmScmzECDj8cAuwVOwswZIkNcHtt8PJJ6dOIWl1WYIl
   SWqkV16Bd96BQw5JnUTS6rIES5LUSEOHQt++0KpV6iSSVpcb4yRJaoTqaujUCSorYbvtUqeRVB83
   xkmSlCPjxkHnzhZgqVRYgiVJaoShQ+GUU1KnkJQrjkNIktSADz7Irkn2bGCpODgOIUlSDtx9N/Tu
   bQGWSoklWJKkBjgKIZUeS7AkSfV47TVYuBAOPTR1Ekm5ZAmWJKkeQ4fCj3/s2cBSqXFjnCRJq1Bd
   DVtsAU8+CTvskDqNpMZyY5wkSavhiSeyCzIswFLpsQRLkrQKd9yRXZMsqfQ4DiFJ0kp88gl07Aiv
   vw6bbJI6jaSmcBxCkqRmevBB2HdfC7BUqizBkiStxPDhcNJJqVNIaimOQ0iStILFi2HbbWHRIlhn
   ndRpJDWV4xCSJDXDPffAd79rAZZKmSVYkqQVOAohlT7HISRJquONN6Bnz2wUonXr1GkkNYfjEJIk
   NdFdd8Fxx1mApVJnCZYkqVaMjkJI5cISLElSrRdfhOpq6NEjdRJJLc0SLElSreHD4Yc/hFDvJKGk
   UuDGOEmSgGXLoFMnmDABttsudRpJq8ONcZIkNdKECbD55hZgqVxYgiVJwg1xUrlxHEKSVPY+/xw6
   dIBXX4XNNkudRtLqchxCkqRGePhh2HNPC7BUTizBkqSy5yiEVH4ch5AklbUPPoAuXWDBAlhvvdRp
   JOWC4xCSJDXgvvvg29+2AEvlxhIsSSprjkJI5clxCElS2Zo/H/bYA956C9q2TZ1GUq44DiFJUj1G
   jIBjjrEAS+XIEixJKluOQkjlyxIsSSpL06fDRx/BfvulTiIpBUuwJKksDR8OP/whrOGfhFJZcmOc
   JKns1NRA584wZgx065Y6jaRcc2OcJEkrMWkSrL++BVgqZ5ZgSVLZcUOcJMchJEll5csvYfPN4YUX
   YMstU6eR1BIch5AkaQVjx8KOO1qApXJnCZYklRVHISSB4xCSpDLyr39Bp07w5puw4Yap00hqKY5D
   SJJUx6hRUFFhAZZkCZYklRFHISQt5ziEJKksvP12tiHurbdgrbVSp5HUkhyHkCSp1t13w5FHWoAl
   ZSzBkqSy4CiEpLoswZKkkjdrFixaBAcfnDqJpEJhCZYklbzhw+GEE6BVq9RJJBWK1qkDSJLUkmLM
   SvDIkamTSCokrgRLkkra5MnQujXsuWfqJJIKiSVYklTSlm+IC/UeliSp3HhOsCSpZFVVQceO8PTT
   0LVr6jSS8sVzgiVJZe2JJ6BLFwuwpP9kCZYklSzPBpa0Kg2W4BBC7xDCzBDC6yGEi1fxTEUIYWoI
   4ZUQQmXOU0qS1ESffgoPPwzHH586iaRCVO8RaSGEVsBAoBewCHg+hDA6xjijzjMbAH8Gvh1jXBhC
   2LglA0uS1BgPPgj77APt26dOIqkQNbQSvBcwJ8Y4L8ZYBdwNHLnCMz8E7o8xLgSIMb6X+5iSJDWN
   oxCS6tNQCe4ALKjzemHtP6trG2DDEMKEEMKUEMKPcxlQkqSmevfd7ESIo45KnURSoWroxrjGnGnW
   BtgDOARYG3g2hPBcjPH1FR8cMGDAV59XVFRQUVHR6KCSJDXWPfdAnz6w7rqpk0jKh8rKSiorK5v0
   e+o9JziEsDcwIMbYu/b1JUBNjPHKOs9cDKwVYxxQ+/oW4NEY430rfC/PCZYk5UXPnnDZZXD44amT
   SEohF+cETwG2CSF0DiG0BY4HRq/wzIPAfiGEViGEtYEewGvNDS1J0uqYOxfmzIHDDkudRFIhq3cc
   IsZYHUI4BxgHtAKGxBhnhBDOrP36TTHGmSGER4GXgRpgcIzREixJSmL4cDjuOGjTJnUSSYXMa5Ml
   SSUjRthhB7j9dth779RpJKXitcmSpLLywgtQXQ09eqROIqnQWYIlSSVj+dnAod71H0lyHEKSVCKq
   q6FjR3jqKdh229RpJKXkOIQkqWyMHw9bbGEBltQ4lmBJUkm480740Y9Sp5BULByHkCQVvU8/zUYh
   Zs6ETTdNnUZSao5DSJLKwujR2ZFoFmBJjWUJliQVveWnQkhSYzkOIUkqau++C9tsAwsXwrrrpk4j
   qRA4DiFJKnn33AOHH24BltQ0lmBJUlHzVAhJzeE4hCSpaL3xBvTsCYsWQevWqdNIKhSOQ0iSStrw
   4XD88RZgSU1nCZYkFaUYPRVCUvNZgiVJRWnKFKipgb32Sp1EUjGyBEuSitLyVeBQ79SfJK2cG+Mk
   SUWnqgo6dYKJE7MzgiWpLjfGSZJK0mOPwVZbWYAlNZ8lWJJUdIYOhZNPTp1CUjFzHEKSVFQ+/BC6
   dIE334R27VKnkVSIHIeQJJWckSPhsMMswJJWjyVYklRUhg1zFELS6rMES5KKxuzZMHduthIsSavD
   EixJKhrDhsEPfwht2qROIqnYuTFOklQUamqyDXGjR8Ouu6ZOI6mQuTFOklQy/va3bDOcBVhSLliC
   JUlFYehQ6Ns3dQpJpcJxCElSwfvkk+ya5JkzYdNNU6eRVOgch5AklYS//hX23dcCLCl3LMGSpILn
   KISkXHMcQpJU0BYsgN12g0WLYM01U6eRVAwch5AkFb1hw+DYYy3AknKrdeoAkiStSk0N3HorjBiR
   OomkUuNKsCSpYD31FKy9NnTvnjqJpFJjCZYkFawhQ6BfPwj1TvZJUtO5MU6SVJA++gg6d4Y5c2Dj
   jVOnkVRM3BgnSSpaI0bAYYdZgCW1DEuwJKkgLR+FkKSWYAmWJBWcadNg8WLo1St1EkmlyhIsSSo4
   Q4bAKadAq1apk0gqVW6MkyQVlC++gI4d4fnnoUuX1GkkFSM3xkmSis6DD2bXJFuAJbUkS7AkqaC4
   IU5SPjgOIUkqGP/4B+y5JyxcCGuumTqNpGLlOIQkqagMGQInnmgBltTyXAmWJBWEqirYckt47DHY
   eefUaSQVM1eCJUlF46GHYOutLcCS8sMSLEkqCDfeCGedlTqFpHLhOIQkKbk5c6BnT5g/33lgSavP
   cQhJUlG4+ebshjgLsKR8cSVYkpTU0qXQqRM88wx07Zo6jaRS4EqwJKng3X9/dkOcBVhSPlmCJUlJ
   uSFOUgqWYElSMq++mm2K+973UieRVG4swZKkZG66CU4/Hdq0SZ1EUrlxY5wkKYmPP4bOnWHqVNhi
   i9RpJJUSN8ZJkgrWsGFw0EEWYElptE4dQJJUfmpqYODAbBxCklJwJViSlHdPPAFt28L++6dOIqlc
   WYIlSXl3/fVw3nkQ6p3Yk6SW48Y4SVJezZkDPXvCP/4Ba62VOo2kUuTGOElSwfnzn6FfPwuwpLRc
   CZYk5Y3HoknKB1eCJUkFxWPRJBUKV4IlSXlRUwPbbw+33AIHHJA6jaRS5kqwJKlgjB4N7dp5LJqk
   wmAJliTlxTXXwEUXeSyapMJgCZYktbhnn4W33oLvfz91EknKWIIlSS3uD3+AX/wCWrdOnUSSMm6M
   kyS1qDlzYJ994M03Yd11U6eRVA7cGCdJSu7aa+HMMy3AkgqLK8GSpBbz3nuwzTYwYwZ861up00gq
   F64ES5KS+stf4OijLcCSCo8rwZKkFvHxx7DVVjBpEmy3Xeo0ksqJK8GSpGRuvBEOOcQCLKkwuRIs
   Scq5zz/PVoHHjYNddkmdRlK5cSVYkpTELbdAjx4WYEmFy5VgSVJOLV0KXbvCqFHQvXvqNJLKkSvB
   kqS8GzYMdtrJAiypsLkSLEnKmepq2HbbrAjvt1/qNJLKVU5WgkMIvUMIM0MIr4cQLq7nue4hhOoQ
   wtHNCStJKn533QWdOlmAJRW+eleCQwitgFlAL2AR8DxwYoxxxkqeexz4DLgtxnj/Sr6XK8GSVMKq
   qmD77eHWW+HAA1OnkVTOcrESvBcwJ8Y4L8ZYBdwNHLmS584F7gPebVZSSVLRu/VW2HprC7Ck4tC6
   ga93ABbUeb0Q6FH3gRBCB7JifDDQHXC5V5LKzBdfwG9/C/f/x98DSlJhaqgEN6bQXgf8KsYYQwgB
   WOXS84ABA776vKKigoqKikZ8e0lSoRs0CPbcE/baK3USSeWosrKSysrKJv2ehmaC9wYGxBh7176+
   BKiJMV5Z55m5/Lv4bkw2F3xGjHH0Ct/LmWBJKkGffJKdC/z449CtW+o0ktS4meCGVoKnANuEEDoD
   bwHHAyfWfSDGuFWdH3gb8NCKBViSVLr+9Cc4+GALsKTiUm8JjjFWhxDOAcYBrYAhMcYZIYQza79+
   Ux4ySpIK1IcfwnXXwTPPpE4iSU3jZRmSpGbr3z8rwoMHp04iSf/WmHEIS7AkqVnmzcs2w73yCmy2
   Weo0kvRvObkxTpKklbnkEjj/fAuwpOLkSrAkqckmT4ZjjoFZs2CddVKnkaSvcyVYkpRzMcIFF8D/
   /Z8FWFLxsgRLkprk/vvh00+hb9/USSSp+RyHkCQ12uefw447wi23wCGHpE4jSSvnOIQkKaeuuAK6
   d7cASyp+rgRLkhrljTegRw+YOhU6dUqdRpJWzZVgSVLO/PzncNFFFmBJpaHea5MlSQJ4+GGYPTvb
   FCdJpcASLEmq12efZZdiDBoEbdumTiNJueFMsCSpXhdfDPPnw4gRqZNIUuM0ZibYlWBJ0iq9+CLc
   fjtMn546iSTllhvjJEkrVVUF/frB1VdD+/ap00hSblmCJUkr9cc/ZuX3xz9OnUSScs+ZYEnSf5g9
   G3r2hOefhy5dUqeRpKbxnGBJUpNVV0PfvvCb31iAJZUuS7Ak6WuuuAK++U342c9SJ5GkluM4hCTp
   Ky+8AN/5TnYqRMeOqdNIUvM4DiFJarTPP882wV13nQVYUulzJViSBMB558E//wl33w2h3vUTSSps
   XpYhSWqUBx6A0aNh6lQLsKTy4EqwJJW5efOgR4+sBPfokTqNJK0+Z4IlSfX68ks44QTo398CLKm8
   uBIsSWXsootg1qxsFdgxCEmlwplgSdIq3XMP3HdfdiyaBVhSuXElWJLK0LRp0KsXPP447LZb6jSS
   lFvOBEuS/sP778P3vw833GABllS+XAmWpDJSXQ29e8Oee8KVV6ZOI0ktozErwZZgSSoTMcLZZ2dH
   oj38MLRqlTqRJLUMN8ZJkr5y9dXwzDMwcaIFWJIswZJUBu65BwYOzErweuulTiNJ6VmCJanETZoE
   55yTnQTRsWPqNJJUGDwdQpJK2NSpcPTRcOedsOuuqdNIUuGwBEtSiZo5E/r0gUGD4LDDUqeRpMJi
   CZakEjRvXlZ8r7gCjjkmdRpJKjyWYEkqMW+9ld0G178/nHxy6jSSVJgswZJUQhYuhIoKOP30bDOc
   JGnlLMGSVCLmzYMDD4Qzz4Rf/Sp1GkkqbJZgSSoBb7yRrQD//Odw4YWp00hS4bMES1KRmzEjK8CX
   Xgrnnps6jSQVB0uwJBWxZ56Bgw6Cyy+Hn/wkdRpJKh7eGCdJRWr0aOjXD+64A3r3Tp1GkoqLK8GS
   VIRuvhnOOgseecQCLEnN4UqwJBWRZcuy2d/774ennoKuXVMnkqTiZAmWpCLxr3/BSSfBJ5/A5Mmw
   0UapE0lS8XIcQpKKwNy50LMndOgAjz1mAZak1WUJlqQCV1mZFeCf/hQGDYI2bVInkqTi5ziEJBWo
   mhq4+mq49lq4807o1St1IkkqHZZgSSpAH34IffvC++/D889Dp06pE0lSaXEcQpIKzJQpsMce2ckP
   lZUWYElqCZZgSSoQMcKf/wx9+vx7DKJt29SpJKk0OQ4hSQVg8WI47TR45x2YNAm23TZ1Ikkqba4E
   S1JiY8fCbrtBt27wzDMWYEnKB1eCJSmRzz+Hiy+GBx6Au+6CiorUiSSpfLgSLEkJvPwy7LVXNv4w
   bZoFWJLyzRIsSXlUVQW//S0ccghceCGMHAnt2qVOJUnlx3EIScqT6dPhlFNgk03gxRc9+kySUnIl
   WJJaWHU1/O53cPDB2dXHY8dagCUpNVeCJakFvfJKtvq74YbwwguwxRapE0mSwJVgSWoR1dVw+eVw
   0EFw5pkwbpwFWJIKiSvBkpRjr76arf62a+fqryQVKleCJSlHqqqy2d+KCjjjDFd/JamQuRIsSTkw
   bRqceiq0b+/qryQVA1eCJWk1fPkl/OY3cOihcO652ckPFmBJKnyuBEtSM02Zkq3+du4MU6dChw6p
   E0mSGsuVYElqoi++gEsugcMPh1/9CkaPtgBLUrFxJViSmuDZZ+G002CnneDll2HTTVMnkiQ1hyVY
   khrhs8/g17+Gu+6C66+HY49NnUiStDoch5CkBkycCLvuCm+/DdOnW4AlqRS4EixJq/DFF9nq7/Dh
   MGgQHHlk6kSSpFyxBEvSSrz4IvTtC9tvn83+brxx6kSSpFxyHEKS6qiuht/+Fnr3zk6AuPdeC7Ak
   lSJXgiWp1qxZ2erv+utnK8EdO6ZOJElqKa4ESyp7NTVwww2w775w8skwbpwFWJJKnSvBksraO+9k
   xXfJEnjmGdh229SJJEn54EqwpLI1dizsvjvstRdMmmQBlqRy4kqwpLKzdClceinccw+MGAEVFakT
   SZLyzRIsqazMng0nnABbbgkvvQQbbZQ6kSQpBcchJJWFGOH227PNb2ecAaNGWYAlqZw1aiU4hNAb
   uA5oBdwSY7xyha+fBPQHAvAx8NMY48s5zipJzfLZZ3D22fD88zBhAuy8c+pEkqTUGlwJDiG0AgYC
   vYEdgRMLnhDgAAAPVElEQVRDCDus8Nhc4IAY4y7A/wE35zqoJDXH7Nmw997ZJRh//7sFWJKUacw4
   xF7AnBjjvBhjFXA3cGTdB2KMz8YYl9S+nAx4wqak5O67Lxt/+NnP4I47YJ11UieSJBWKxoxDdAAW
   1Hm9EOhRz/P9gEdWJ5QkrY6qKrj4YnjgAXj0Udhzz9SJJEmFpjElODb2m4UQDgJOA/ZtdiJJWg0L
   F8Lxx8OGG8KUKdmvkiStqDEleBHQqc7rTmSrwV8TQtgFGAz0jjF+uLJvNGDAgK8+r6iooMLDOSXl
   0KRJcNxxcO652UrwGp5/I0llobKyksrKyib9nhBj/Qu9IYTWwCzgEOAt4O/AiTHGGXWe2QIYD/wo
   xvjcKr5PbOhnSVJzDR4M/+//wdCh0Lt36jSSpJRCCMQYQ33PNLgSHGOsDiGcA4wjOyJtSIxxRgjh
   zNqv3wT8N9AOGBRCAKiKMe61uv8DSFJDqqrg5z+H8eNh4kSvPpYkNU6DK8E5+0GuBEvKsXffhR/8
   ANZbD4YPz36VJKkxK8FOzEkqSi+9BN27w/77w4MPWoAlSU3TqBvjJKmQjBoFZ54Jf/5zthFOkqSm
   sgRLKhoxwjXXwPXXw7hxsMceqRNJkoqVJVhSUaiqgnPOgcmT4dlnoaP3UkqSVoMlWFLBW7IkG3to
   3To7AeKb30ydSJJU7NwYJ6mgzZ8P++0HXbtmG+AswJKkXLAESypYU6bAPvtAv34wcGC2EixJUi74
   R4qkgvTII3DyydlNcEcdlTqNJKnUWIIlFZyhQ+Hii+Ghh2DvvVOnkSSVIkuwpIIRI1x1FQwaBJWV
   sP32qRNJkkqVJVhSQaipgQsugCefhKefhg4dUieSJJUyS7Ck5JYuhVNOgbfeyo5A22CD1IkkSaXO
   0yEkJfXxx/Dd72ZFeNw4C7AkKT8swZKSWbwYKipg663h3nthzTVTJ5IklQtLsKQkFi6EAw+Eww/P
   NsK1apU6kSSpnFiCJeXd3LlwwAHZJRj/+78QQupEkqRyYwmWlFczZmQrwP37w0UXpU4jSSpXng4h
   KW+mToU+fbKzgH/849RpJEnlzBIsKS+efTa7/njQIDj66NRpJEnlzhIsqcU9+SSceCIMGwa9e6dO
   I0mSM8GSWthDD2UF+L77LMCSpMJhCZbUYkaOhDPOgDFjstMgJEkqFJZgSS3i1lvhggvg8cehe/fU
   aSRJ+jpngiXl3PXXwx/+ABMmwLbbpk4jSdJ/sgRLyqnLL4fbboOnnoItt0ydRpKklbMES8qJGOHS
   S7ONcE89BZttljqRJEmrZgmWtNpqauC88+C556CyEjbeOHUiSZLqZwmWtFqqq7MTIObMyc4DXn/9
   1IkkSWqYJVhSs335JZx0EixZAo8+CuuskzqRJEmN4xFpkprl88+za5CrqrI5YAuwJKmYWIIlNdnH
   H0OfPtCuHdx7L3zjG6kTSZLUNJZgSU3ywQfQq1d2/u+wYdCmTepEkiQ1nSVYUqO98w5UVMD++8ON
   N0KrVqkTSZLUPJZgSY0yfz4ccAAceyxcfTWEkDqRJEnNZwmW1KDXX89Wf88+G379awuwJKn4eUSa
   pHq9/DJ85zvwv/8L/fqlTiNJUm5YgiWt0uTJcMQRcP31cPzxqdNIkpQ7lmBJK1VZCccdB7fdBocf
   njqNJEm55UywpP8wZkxWgEeOtABLkkqTJVjS1wwbls3+PvQQHHRQ6jSSJLUMxyEkfeWaa+CGG2DC
   BNhhh9RpJElqOZZgSdTUQP/+MHYsPP00dOyYOpEkSS3LEiyVuaqqbPzhjTdg4kTYcMPUiSRJanmW
   YKmMffpptgEuBHj8cVh77dSJJEnKDzfGSWXq/fehVy9o3x7++lcLsCSpvFiCpTL0+uuwzz5QUQG3
   3gpt2qROJElSflmCpTIzaRLsvz/88pfw+99noxCSJJUbZ4KlMjJiBJx/PgwfDocemjqNJEnpWIKl
   MhAj/O53MHgwjB8PO++cOpEkSWlZgqUS9+WXcOaZMH06PPccbLZZ6kSSJKXnTLBUwhYvzsYePvwQ
   /vY3C7AkSctZgqUS9eKL0L07HHAAjBoF66yTOpEkSYXDcQipBN11V7YB7sYb4ZhjUqeRJKnwWIKl
   ErJsGfzqV3D//dkGuG7dUieSJKkwWYKlEvHee3DSSVkRfv552Gij1IkkSSpczgRLJeDpp2GPPWDX
   XeHRRy3AkiQ1xJVgqYjV1MAf/gDXXANDhsB3v5s6kSRJxcESLBWpDz6Ak0/OxiCefx622CJ1IkmS
   iofjEFIR+tvfYPfdYdtts88twJIkNY0rwVIRWboUfv1ruPPO7Arkww9PnUiSpOJkCZaKxPTp8KMf
   wVZbwbRpsMkmqRNJklS8HIeQCtyyZfDHP8LBB2cXYIwaZQGWJGl1uRIsFbBXX4V+/aBtW5g8OVsF
   liRJq8+VYKkALV0KAwZARQWceipUVlqAJUnKJVeCpQIzcSKcdRZ07QovvQQdOqROJElS6bEESwVi
   0SLo3x+eeiqbAf7BDyCE1KkkSSpNjkNIiS1dCldemV153LkzzJwJxx5rAZYkqSW5EiwlUlMD990H
   l10G228Pzz2XjUBIkqSWZwmWEnjySbj44uzzG2+EQw5Jm0eSpHJjCZby6Nln4Te/gTffhN/9Lpv7
   XcOhJEmS8s4/fqUWFiNMmJCt9p54Ihx9NLz2Ghx3nAVYkqRUXAmWWkhNDYwZA1dcAe+9B5dcAied
   BG3apE4mSZIswVKOLVkCt90GAwdCu3Zw4YXZaQ+tWqVOJkmSlrMESzkybRoMHgx33QWHHQZ33AF7
   7+1RZ5IkFSJLsLQaPvgARoyAW2+Fd9+FU06Bl1+Gjh1TJ5MkSfUJMcb8/KAQYr5+ltSSPv4YHn4Y
   7r0Xxo+HPn3g1FPh4IMdeZAkqRCEEIgx1vt3sZZgqRE++ijb5HbffVnx3W+/7Hizo47K5n4lSVLh
   sARLzVRTAy+9BGPHwqOPZp8feGC2we2IIyy+kiQVMkuw1EjLlsH06TBpUvYxYQJsuCH07p19HHAA
   rLVW6pSSJKkxLMHSKrz9NkydCi+8AE8/nd3ktvnm2ZjDfvtlq76dO6dOKUmSmsMSrLL3yScwezbM
   mpWt9E6dmn1UVcHuu2cf++6bfWyySeq0kiQpFxpTghu8tDWE0DuEMDOE8HoI4eJVPHN97denhRB2
   b25gNV5lZWXqCAUhRli8GKZMgVGj4Npr4Wc/g169oFMnaN8+O7Zs1Cho2xbOOgv+/vfsBrcnnoCr
   r4YNNqi0AOeQ/27mlu9n7vhe5pbvZ275fuZfvecEhxBaAQOBXsAi4PkQwugY44w6z/QBusYYtwkh
   9AAGAXu3YGaR/cdSUVGROkaLWbo0O3f3n//MSu7ixV///O23Yf787GPttWHLLWGLLbKPbbaB730P
   ttsue93QsWWl/l7mm+9nbvl+5o7vZW75fuaW72f+NXRZxl7AnBjjPIAQwt3AkcCMOs8cAQwFiDFO
   DiFsEELYNMb4zxbIqwIQY3Z6QnV1NlZQXZ2V1s8/X/nHZ599/fWnn2ZXC3/0Ufbr8o+6r6urs/GE
   TTfNVnPbt//35926ZZ8vL73rrpv6HZEkScWmoRLcAVhQ5/VCoEcjnukIlG0JXrwYTjstK4vLx6Cb
   83l9X//HP+Dxx5v/vVf2+YrFdvmvK/s8BGjTBlq3zn5t0yZbkV1rrVV/LP/6OutkJXbbbWH99bOP
   DTb49+frr58963XDkiSppdS7MS6EcAzQO8Z4Ru3rHwE9Yozn1nnmIeCKGOPTta+fAPrHGF9c4Xu5
   K06SJEl50dDGuIZWghcBneq87kS20lvfMx1r/1mTgkiSJEn50tDpEFOAbUIInUMIbYHjgdErPDMa
   6AsQQtgb+Mh5YEmSJBWyeleCY4zVIYRzgHFAK2BIjHFGCOHM2q/fFGN8JITQJ4QwB/gUOLXFU0uS
   JEmrIW+XZUiSJEmFosHLMnIthHBhCKEmhLBhvn92KQkh/F/t5SQvhRCeDCF0avh3aVVCCFeHEGbU
   vqejQgjrp85UzEIIx4YQXg0hLAsh7JE6TzFqzEVFapwQwq0hhH+GEKanzlIKQgidQggTav8bfyWE
   cF7qTMUqhLBmCGFy7Z/lr4UQfp86UykIIbQKIUytPbxhlfJagmuL2qHAP/L5c0vUVTHGXWOMuwEP
   AL9JHajIPQbsFGPcFZgNXJI4T7GbDnwfeCp1kGJU56Ki3sCOwIkhhB3Spipqt5G9l8qNKuAXMcad
   yC7H+pn/fjZPjPEL4KDaP8t3AQ4KIeyXOFYpOB94Dah33CHfK8F/BPrn+WeWpBjjx3Vergu8lypL
   KYgxPh5jrKl9OZnslBM1U4xxZoxxduocReyri4pijFXA8ouK1AwxxonAh6lzlIoY4zsxxpdqP/+E
   7AKtzdOmKl4xxs9qP21Ltv/qg4Rxil4IoSPQB7gFqPdksryV4BDCkcDCGOPL+fqZpS6E8LsQwnzg
   ZOCK1HlKyGnAI6lDqKyt7BKiDomySKsUQugM7E62eKBmCCGsEUJ4ieySsQkxxtdSZypy1wK/BGoa
   erChc4KbJITwOPCtlXzpMrK/Xj6s7uO5/NmlqJ7389IY40MxxsuAy0IIvyL7X7onc9Sjofez9pnL
   gC9jjHflNVwRasz7qWZzx7IKXghhXeA+4PzaFWE1Q+3fQu5WuxdlXAihIsZYmThWUQohfBdYHGOc
   GkKoaOj5nJbgGOOhqwi1M9AFmBayu3A7Ai+EEPaKMS7OZYZSsqr3cyXuwpXLBjX0foYQTiH7K5RD
   8hKoyDXh3081XWMuKpKSCSG0Ae4H7owxPpA6TymIMS4JIYwB/guoTBynWPUEjggh9AHWBNYLIQyL
   MfZd2cN5GYeIMb4SY9w0xtglxtiF7P+Y72EBbr4QwjZ1Xh4JTE2VpRSEEHqT/fXJkbUbFZQ7/q1P
   0zXmoiIpiZCtZg0BXosxXpc6TzELIWwcQtig9vO1yA4P8M/zZooxXhpj7FTbNU8Axq+qAEOCI9Jq
   +Vd9q+/3IYTptXNEFcCFifMUuxvINhg+Xnusyl9SBypmIYTvhxAWkO0cHxNCGJs6UzGJMVYDyy8q
   eg0YGWOckTZV8QohjACeAbYNISwIITg6tnr2BX5EdpLB1NoPT99ons2A8bV/lk8GHooxPpk4Uymp
   t296WYYkSZLKTqqVYEmSJCkZS7AkSZLKjiVYkiRJZccSLEmSpLJjCZYkSVLZsQRLkiSp7FiCJUmS
   VHb+P0+c/XqDVTs2AAAAAElFTkSuQmCC
   "
   >
   </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">
   <h4 id="Cumulative-Hazard-Function">Cumulative Hazard Function<a class="anchor-link" href="#Cumulative-Hazard-Function">&#182;</a></h4>
   </div>
   </div>
   </div>
   
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[12]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">fig</span> <span class="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">kde3</span><span class="o">.</span><span class="n">support</span><span class="p">,</span> <span class="n">kde3</span><span class="o">.</span><span class="n">cumhazard</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,iVBORw0KGgoAAAANSUhEUgAAAr0AAAHfCAYAAABd8GAUAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzt3XmYnWV9N/DvTUIgyCYim6CRRTYFRYqIIqMsAi4ghYqt
   iGD1rftCcQEtKVrXF6WlWjfgBVkqiwoIFSwyFAiNgiwhgMimASUg+05CnvePZwIxJpNZzpnnLJ/P
   dZ1rzpk5c+abYzDf657fc9+lqqoAAEAvW67pAAAA0G5KLwAAPU/pBQCg5ym9AAD0PKUXAICep/QC
   ANDzhi29pZTjSilzSymzlvC1Q0opC0opa7QvHgAAjN+yVnqPT7L74p8spWyQZNckv2tHKAAAaKVh
   S29VVZckuX8JX/p6kk+2JREAALTYqGd6Syl7Jbmjqqpr25AHAABabvJonlxKWSnJYalHG5759FKe
   63xjAAAmRFVVS+ykC412pXejJNOSXFNKuS3J+kmuLKWstZQf7tai2xFHHNF4hl66eT+9l5168356
   Pzv15r30fnbybSRGtdJbVdWsJGsvfDxUfF9ZVdV9o3kdAACYSMvasuzUJDOSvKSUMqeUctBiTzHC
   AABAxxt2pbeqqncs4+sbtjYOSzMwMNB0hJ7i/Wwd72VreT9by/vZOt7L1vJ+Trwy0jmIUb9wKVW7
   XhsAABYqpaRq8YVsAADQdZReAAB6ntILAEDPU3oBAOh5Si8AAD1P6QUAoOcpvQAA9DylFwCAnqf0
   AgDQ85ReAAB6ntILAMAz5s9Pvv3tpKqaTtJaSi8AAM+YPTs5+uiklKaTtJbSCwDAM2bOTLbfvukU
   raf0AgDwjJkzk1e9qukUraf0AgDwjP/9394svaVq05RyKaVq12sDANB6Dz2UrLdecv/9yfLLN51m
   5Eopqapq2ClkK70AACRJfvWr5BWv6K7CO1JKLwAASXp3njdRegEAGNKr87yJmV4AAFIfRrHWWslV
   VyXrr990mtEx0wsAwIjcckuy4ordV3hHSukFACCXX568+tVNp2gfpRcAAKUXAIDeN2NGssMOTado
   HxeyAQD0uYcfTtZZpz6UYsqUptOMngvZAABYpl/9Knn5y7uz8I6U0gsA0Ocuv7y3RxsSpRcAoO/N
   mNHbF7ElZnoBAPpaVSVrrplcd12y7rpNpxkbM70AAAzrppuSVVft3sI7UkovAEAf6/X9eRdSegEA
   +lg/zPMmSi8AQF/rl5VeF7IBAPSpBx9M1l8/ue++ZPnlm04zdi5kAwBgqWbOTLbZprsL70gpvQAA
   fapfRhsSpRcAoG/1w0lsC5npBQDoQwsWJM97XvKb3yRrrdV0mvEx0wsAwBLdcENderu98I6U0gsA
   0IcuvTR57WubTjFxlF4AgD50ySXJjjs2nWLiKL0AAH3okkus9AIA0MN+//vkiSeSl7yk6SQTR+kF
   AOgzC+d5y7D7HfQWpRcAoM/020VsidILANB3+u0itsThFAAAfeW++5Jp0+qPkyc3naY1HE4BAMCf
   mTEjedWreqfwjpTSCwDQR/ptq7KFlF4AgD5y6aX9N8+bmOkFAOgbjz+ePP/5ydy5yXOe03Sa1jHT
   CwDAM375y2TLLXur8I6U0gsA0Cf6dbQhUXoBAPpGv17Eloyg9JZSjiulzC2lzFrkc18rpdxQSrmm
   lPKjUspq7Y0JAMB4PP10cvnlyWte03SSZoxkpff4JLsv9rkLkmxZVdXWSW5K8plWBwMAoHWuvTZZ
   b736QrZ+tMzSW1XVJUnuX+xzP6+qasHQw5lJ1m9DNgAAWqQfjx5eVCtmeg9Ocl4LXgcAgDbp99I7
   rgPoSimHJ3mqqqpTlvT16dOnP3N/YGAgAwMD4/lxAACMQVUlF1+cHHVU00laY3BwMIODg6P6nhEd
   TlFKmZbknKqqXrbI596d5L1Jdq6q6oklfI/DKQAAOsDs2clb35rcckvTSdpjJIdTjGmlt5Sye5JD
   k+y0pMILAEDnGBxM+v0X7iPZsuzUJDOSbFpKmVNKOTjJMUlWTvLzUspVpZRvtTknAABjpPSOcLxh
   TC9svAEAoHFVlay9dnLFFckLX9h0mvYYyXiDE9kAAHrY9dcnq6zSu4V3pJReAIAedvHFyU47NZ2i
   eUovAEAPM89bM9MLANCjFs7z/upXyYte1HSa9jHTCwDQx264IVl55d4uvCOl9AIA9CijDc9SegEA
   epTS+ywzvQAAPahf5nkTM70AAH3LPO+fU3oBAHrQ4KD9eRel9AIA9KALL0ze8IamU3QOM70AAD3m
   6aeTtdZKZs1K1luv6TTtZ6YXAKAPXX11fRFbPxTekVJ6AQB6zH//d7Lzzk2n6CxKLwBAj7nwwmSX
   XZpO0VnM9AIA9JAnnkie//xkzpxk9dWbTjMxzPQCAPSZyy9PttiifwrvSCm9AAA9xGjDkim9AAA9
   xEVsS2amFwCgRzz4YLL++sk99yQrrth0moljphcAoI9cfHGy/fb9VXhHSukFAOgRRhuWTukFAOgR
   LmJbOqUXAKAH/PGP9e0Vr2g6SWdSegEAesCFFyYDA8mkSU0n6UxKLwBADzj//OSNb2w6ReeyZRkA
   QJdbsCBZd91k5sxk2rSm00w8W5YBAPSBa66pjx3ux8I7UkovAECX+9nPjDYsi9ILANDlzPMum5le
   AIAu9vDDyXrrJXfdlTznOU2naYaZXgCAHnfRRcl22/Vv4R0ppRcAoIsZbRgZpRcAoIspvSOj9AIA
   dKlbbkkefTTZaqumk3Q+pRcAoEudf36y225JGfYSLhKlFwCgaxltGDlblgEAdKGnnkqe//zk5pvr
   j/3MlmUAAD1qxoxkk00U3pFSegEAutC55yZvelPTKbqH0gsA0IWU3tFRegEAusxttyX33ptsu23T
   SbqH0gsA0GXOOy/ZY49kOU1uxLxVAABdxmjD6NmyDACgizz2WLLOOsmcOclqqzWdpjPYsgwAoMf8
   4hfJK1+p8I6W0gsA0EWMNozN5KYDAAAwMlVVl97zz286Sfex0gsA0CWuuy6ZPDnZbLOmk3QfpRcA
   oEuce26y555JGfaSLZZE6QUA6BLmecfOlmUAAF3gvvuSadOSuXOTqVObTtNZbFkGANAjzj03ecMb
   FN6xUnoBALrAWWcle+/ddIruZbwBAKDDPfFEfQrbzTcna67ZdJrOM+7xhlLKcaWUuaWUWYt8bo1S
   ys9LKTeVUi4opazeqsAAAPylCy9MttpK4R2PZY03HJ9k98U+9+kkP6+q6iVJLhx6DABAm5x1VrLX
   Xk2n6G7LHG8opUxLck5VVS8benxjkp2qqppbSlknyWBVVX+xRbLxBgCA8VuwIFlvveTSS5ONN246
   TWdq1+4Na1dVNXfo/twka4/hNQAAGIGZM+uxBoV3fCaP55urqqpKKUtdzp0+ffoz9wcGBjIwMDCe
   HwcA0HeMNvylwcHBDA4Ojup7xjreMFBV1V2llHWTXGS8AQCgPTbfPDnhhGS77ZpO0rnaNd5wdpID
   h+4fmOQnY3gNAACW4Te/SR56KNl226aTdL9lbVl2apIZSTYtpcwppRyU5MtJdi2l3JTkDUOPAQBo
   sbPOSt761mQ5x4mNm8MpAAA61Gtek3zuc8nui28gy58ZyXiD0gsA0IH++Mdkiy2Su+5KVlih6TSd
   rV0zvQAAtNmPf5y86U0Kb6sovQAAHeiMM5J99206Re8w3gAA0GHuuSfZZJN6xGHq1KbTdD7jDQAA
   XegnP6kvXlN4W0fpBQDoMGeckfz1XzedorcYbwAA6CD33Ze8+MXJnXcmK6/cdJruYLwBAKDLnH12
   sssuCm+rKb0AAB3Erg3tYbwBAKBDPPhg8sIXJnPmJKuu2nSa7mG8AQCgi/z0p8lOOym87aD0AgB0
   CKMN7WO8AQCgAywcbfjd75LVV286TXcx3gAA0CXOOit5/esV3nZRegEAOsCppyb77990it5lvAEA
   oGH33JNsskl9IMVzntN0mu5jvAEAoAuceWayxx4KbzspvQAADTv11OQd72g6RW8z3gAA0KA77ki2
   3jr5wx+SFVZoOk13Mt4AANDhTjst2XtvhbfdlF4AgAb953/atWEiKL0AAA25+eb6MIrXv77pJL1P
   6QUAaMgPf5jst18yeXLTSXqf0gsA0ICqSk4+2a4NE0XpBQBowJVXJk8+meywQ9NJ+oPSCwDQgB/8
   IDnggKQMu9EWrWKfXgCACTZvXrL++slllyUbb9x0mu5nn14AgA50/vnJRhspvBNJ6QUAmGA/+EHy
   rnc1naK/GG8AAJhADzyQvOhFyW23JWus0XSa3mC8AQCgw5xxRrLzzgrvRFN6AQAmkNGGZhhvAACY
   ILffnmy7bfKHPyRTpjSdpncYbwAA6CAnnZT8zd8ovE1w0jMAwARYsCA5/vjk1FObTtKfrPQCAEyA
   iy9OVlop+au/ajpJf1J6AQAmwHHHJe95j2OHm+JCNgCANnvggWTatOTmm5M112w6Te9xIRsAQAc4
   9dRk110V3iYpvQAAbbZwtIHmKL0AAG107bXJ3Ln1Si/NUXoBANro2GOTd787mTSp6ST9zYVsAABt
   8uSTyfrrJzNnJhtu2HSa3uVCNgCABp11VrLVVgpvJ1B6AQDa5NhjXcDWKYw3AAC0wW231aevzZmT
   TJ3adJreZrwBAKAh3/tecsABCm+nsNILANBiTz2VvPCFycUXJ5tu2nSa3melFwCgAT/5SbLFFgpv
   J1F6AQBa7D/+I/mHf2g6BYsy3gAA0EI33pgMDCS//30yZUrTafqD8QYAgAn2ne8kBx+s8HYaK70A
   AC3y+OPJBhskV1yRTJvWdJr+YaUXAGACnXZa8qpXKbydSOkFAGgRF7B1rjGX3lLKZ0ops0sps0op
   p5RSVmhlMACAbnL11ckf/pDsuWfTSViSMZXeUsq0JO9Nsk1VVS9LMinJ/q2LBQDQXb75zeR970sm
   TWo6CUsyeYzf91CSeUlWKqU8nWSlJHe2LBUAQBe5997kjDOS3/ym6SQszZhWeququi/JUUl+n+QP
   SR6oquq/WxkMAKBbHHtsstdeyVprNZ2EpRnTSm8pZaMkH0syLcmDSU4vpfxdVVUnL/q86dOnP3N/
   YGAgAwMDY80JANCR5s+vRxt+9KOmk/SPwcHBDA4Ojup7xrRPbynl7Ul2rarq74ceH5Bk+6qqPrjI
   c+zTCwD0vB/9KDnqqOSyy5pO0r/auU/vjUm2L6VMLaWUJLskuX6MrwUA0LWOOSb5yEeaTsGyjHWm
   95okJya5Ism1Q5/+bqtCAQB0g2uvTX7722SffZpOwrI4hhgAYIze+97kRS9KPvvZppP0t5GMNyi9
   AABjcO+9ycYb19uU2bWhWe2c6QUA6Gu2KesuVnoBAEZp/vx6lffMM5NXvrLpNFjpBQBog7PPTtZb
   T+HtJkovAMAoff3rycc/3nQKRkPpBQAYhZkzkzvvTN72tqaTMBpKLwDAKHz968nHPpZMntx0EkbD
   hWwAACN0++3Jttsmt92WrLJK02lYyIVsAAAt9K//mrznPQpvN7LSCwAwAg88kGy4YX308PrrN52G
   RVnpBQBoke99L9lzT4W3W1npBQBYhnnz6lXes89OXvGKptOwOCu9AAAtcNppySabKLzdTOkFABhG
   VdXblB1ySNNJGA+lFwBgGBdfnDz2WLLHHk0nYTyUXgCAYRx1VPKJTyTLaU1dzYVsAABLMXt2svPO
   9WEUU6c2nYalcSEbAMA4fO1ryUc+ovD2Aiu9AABL8Pvf17s13Hxz8tznNp2G4VjpBQAYo298Izn4
   YIW3V1jpBQBYzL331vvyzpqVvOAFTadhWaz0AgCMwTe/meyzj8LbS6z0AgAs4tFHkxe/OLnkkmTT
   TZtOw0hY6QUAGKXjjkt23FHh7TVWegEAhsybl2y8cXL66cl22zWdhpGy0gsAMAo//GGy4YYKby+a
   3HQAAIBOUFXJV76S/N//23QS2sFKLwBAkvPOSyZPTnbbrekktIPSCwCQepX3U59KyrCToXQrpRcA
   6HszZiR33JHsu2/TSWgXpRcA6Htf+Upy6KH1eAO9yZZlAEBfmz072Xnn5LbbkqlTm07DWNiyDABg
   Gb74xeRjH1N4e52VXgCgb918c/LqVye33JKsumrTaRgrK70AAMP48peTD3xA4e0HVnoBgL40Z06y
   9dbJb3+bPO95TadhPKz0AgAsxde+lrznPQpvv7DSCwD0nblzk803T66/PllnnabTMF5WegEAluDr
   X0/+9m8V3n5ipRcA6Cv33Zdsskly1VXJC1/YdBpawUovAMBijjkm2WsvhbffWOkFAPrGww8nG26Y
   XHZZ8pKXNJ2GVrHSCwCwiG9/O9llF4W3H1npBQD6wuOP16u8F1yQvOxlTaehlaz0AgAMOfbYZLvt
   FN5+ZaUXAOh5Tz1V79hw+ul18aW3WOkFAEhy0knJppsqvP3MSi8A0NPmz69PX/v+95Oddmo6De1g
   pRcA6Hunn56svXbyutc1nYQmTW46AABAuyxYkHzxi8lXv5qUYdcB6XVWegGAnnXOOcmUKcnuuzed
   hKYpvQBAT6qq5AtfSA4/3CovSi8A0KMuuCB57LFk772bTkInUHoBgJ5TVck//3Pyuc8ly2k7ZByl
   t5SyeinljFLKDaWU60sp27cyGADAWF14YXLffcl++zWdhE4xnt0b/jXJeVVV7VtKmZzkOS3KBAAw
   ZgtXeT/72WTSpKbT0CnGdDhFKWW1JFdVVbXhMM9xOAUAMOEGB5P3vS+5/vpkss1Z+0I7D6d4cZJ7
   SinHl1J+XUr5XillpTG+FgBAyxx5ZL1jg8LLosb612Fykm2SfKiqql+VUo5O8ukk/7Tok6ZPn/7M
   /YGBgQwMDIzxxwEALNsllyS/+13yt3/bdBLaaXBwMIODg6P6nrGON6yT5PKqql489Pi1ST5dVdWb
   F3mO8QYAYELtumuy//7Je97TdBImUtvGG6qquivJnFLKS4Y+tUuS2WN5LQCAVpgxI/ntb5MDDmg6
   CZ1oTCu9SVJK2TrJ95NMSXJLkoOqqnpwka9b6QUAJsweeyRve1t9ERv9ZSQrvWMuvSP44UovADAh
   fvnLZN9965XeFVZoOg0TrZ27NwAAdIwjj0w+/WmFl6Wz0gsAdLUrr0z22iu5+eZkxRWbTkMTrPQC
   AD3v859PPvUphZfhWekFALrW1Vcne+6Z3HJLMnVq02loipVeAKCnff7zyaGHKrwsm5VeAKArzZpV
   H0Zx663JSis1nYYmWekFAHrWF76QHHKIwsvIWOkFALrOrFnJLrvUs7wrr9x0GppmpRcA6En//M/1
   LK/Cy0hZ6QUAusrVV9dHDt9yi9EGalZ6AYCeM316vS+vwstoWOkFALrGlVcmb31rffqabcpYyEov
   ANBTpk9PPvMZhZfRm9x0AACAkfjlL+t53tNPbzoJ3chKLwDQFY44Ijn88GTFFZtOQjey0gsAdLwZ
   M5IbbkjOOqvpJHQrK70AQMc74ojks59NpkxpOgndSukFADra//xPvSfvgQc2nYRupvQCAB3tiCOS
   f/qnZPnlm05CN1N6AYCOddFFyR13JO98Z9NJ6HZKLwDQkaqqXuE94ohkskvvGSelFwDoSBdckPzp
   T8k73tF0EnqB0gsAdJwFC5LDDku+8IVk0qSm09ALlF4AoOOceWZSSrLPPk0noVeUqqra88KlVO16
   bQCgd82fn7z0pcm//Vuy225Np6EblFJSVVUZ7jlWegGAjnLiicm66ya77tp0EnqJlV4AoGM88USy
   6abJf/5n8upXN52GbmGlFwDoKt/+drL11govrWelFwDoCA8/nGyySfLznycve1nTaegmVnoBgK5x
   9NHJLrsovLSHlV4AoHH33lvP8s6cmWy0UdNp6DZWegGArvDlLyf77afw0j5WegGARt15Z7LVVsms
   Wcl66zWdhm40kpVepRcAaNR73pOstVbypS81nYRuNZLSO3miwgAALG7WrOSnP01uuqnpJPQ6M70A
   QGM+9ank8MOT1VZrOgm9zkovANCICy+sV3h/8pOmk9APrPQCABNuwYLk0EPrOd4pU5pOQz9QegGA
   CXfKKXXZ3XffppPQL+zeAABMqCeeqA+iOPnk5LWvbToNvcDhFABAxznmmGSbbRReJpaVXgBgwtx7
   b7LZZsmll9arvdAKDqcAADrKJz5Rjzd861tNJ6GXKL0AQMe46aZkhx2S2bOTtdduOg29xEwvANAx
   Djkk+fSnFV6a4XAKAKDtzj8/ufHG5Mwzm05Cv7LSCwC01bx5ycc/nhx1lIMoaI7SCwC01be/nbzg
   Bclb3tJ0EvqZC9kAgLa5995k882TX/wieelLm05Dr7J7AwDQqA99KKmq5JvfbDoJvWwkpdeFbABA
   W8yenfzwh8kNNzSdBMz0AgBtUFX1xWuf+1yy5ppNpwGlFwBog7PPTubMSd7//qaTQM14AwDQUo89
   lnz0o8mxxybLL990GqhZ6QUAWuqLX0y23z7Zeeemk8CzxrV7QyllUpIrktxRVdVbFvua3RsAoM/c
   dFOyww7JNdfUe/PCRBjJ7g3jXen9aJLrk2i3ANDnqqreouywwxReOs+YS28pZf0keyb5fpJhmzUA
   0PvOPDP5wx+SD3+46STwl8ZzIds3khyaZNUWZQEAutQjj9RblJ18sovX6ExjKr2llDcnubuqqqtK
   KQNLe9706dOfuT8wMJCBgaU+FQDoYkcembz+9cnrXtd0EvrB4OBgBgcHR/U9Y7qQrZTyxSQHJJmf
   ZMXUq71nVlX1rkWe40I2AOgDs2cnAwPJddcla6/ddBr60UguZBvX7g1DP2SnJP9o9wYA6D8LFiQ7
   7pj83d8lH/hA02noVxOxe8NC2i0A9KHvfKf++A//0GwOWJZxr/Qu9YWt9AJAT7vzzuTlL08GB5Mt
   t2w6Df1sIld6AYA+8+EPJ+9/v8JLdxjPlmUAQJ/68Y+T669PTjml6SQwMsYbAIBReeihenX35JNt
   UUZnmJDdG4b54UovAPSgD34wmTcv+e53m04CtZGUXuMNAMCIXXZZPdowe3bTSWB0XMgGAIzIY48l
   73538q1vJc99btNpYHSMNwAAI/Lxjyd3313P8kInMd4AALTEJZckp52WXHtt00lgbIw3AADDeuyx
   5OCD67GG5z2v6TQwNsYbAIBhfexjyZ/+lJx0UtNJYMmMNwAA43LJJcnppyezZjWdBMbHeAMAsESP
   PpocdFDyH/+RrLFG02lgfIw3AABL9P731/O8J5zQdBIYnvEGAGBMfvrT5Gc/S665pukk0BpKLwDw
   Z+bOTd773nqLslVXbToNtIbxBgDgGVWVvOUtydZbJ//yL02ngZEx3gAAjMp3vpPcdVfyox81nQRa
   y0ovAJAk+c1vkte+tt6mbLPNmk4DIzeSlV5blgEAmTcv+bu/S448UuGlN1npBQDyyU8m11+fnHNO
   UoZdL4POY6YXAFim//qv5NRTk6uuUnjpXUovAPSxO++sT1077bRkzTWbTgPtY6YXAPrU00/Xc7wf
   /GDyutc1nQbaS+kFgD71+c8nkyYlhx3WdBJoP+MNANCHLrqo3pP317+uiy/0Oiu9ANBn7r47OeCA
   5IQTknXXbToNTAylFwD6yPz5ydvfnrz73cluuzWdBiaOfXoBoI988pPJNdck551nrIHeYZ9eAOAZ
   Z55Zb012xRUKL/3HSi8A9IEbb0x23LE+iGLbbZtOA601kpVeM70A0OMeeSTZZ5/kS19SeOlfVnoB
   oIdVVbL//skqqyTf/37TaaA9zPQCQJ87+ujk5puTyy5rOgk0S+kFgB51wQXJV7+aXH55suKKTaeB
   Zim9ANCDbrqpPoDi9NOTadOaTgPNcyEbAPSY++9P3vKW5AtfSF73uqbTQGdwIRsA9JD585M3vSnZ
   dNPk3/6t6TQwMWxZBgB95tBDkwULkq9/vekk0FnM9AJAjzjuuOSnP01mzkwm+xce/ozxBgDoAf/z
   P8m++9YfN9us6TQwsYw3AEAfuPHGZL/9kpNPVnhhaZReAOhic+cme+6ZfPnLya67Np0GOpfSCwBd
   6tFH663J3vnO5KCDmk4Dnc1MLwB0oaefTvbZJ1ltteSEE5Iy7DQj9LaRzPS6thMAutAnPpE8/HB9
   4prCC8um9AJAl/nGN5L//u/kssuSKVOaTgPdQekFgC5y8sn1wROXXpqsvnrTaaB7KL0A0CXOO68e
   a/jFL5IXvajpNNBdlF4A6AKXXZYceGByzjnJlls2nQa6jy3LAKDDzZpV79Rw0knJ9ts3nQa6k9IL
   AB3s1luTPfZI/vVfkze+sek00L2UXgDoUHfdley2W3LYYcn++zedBrqb0gsAHeiee5Kdd07e/e7k
   Ax9oOg10P6UXADrMvfcmu+xSz/F+9rNNp4He4BhiAOggDzxQr/DuvHPyla84bQ1GYiTHEI95pbeU
   skEp5aJSyuxSynWllI+M9bUAgOShh5Ldd0923FHhhVYb80pvKWWdJOtUVXV1KWXlJFcm2buqqhuG
   vm6lFwBG6JFH6sK71VbJN7+p8MJotHWlt6qqu6qqunro/iNJbkiy3lhfDwD61SOPJG9+c7LZZsm/
   /7vCC+3QkgvZSinTkrwiycxWvB4A9IsHH6z339144+Q730mWc4k5tMW4jyEeGm04I8lHh1Z8nzF9
   +vRn7g8MDGRgYGC8Pw4AesZ999WFd7vtkmOOUXhhpAYHBzM4ODiq7xnX7g2llOWT/DTJf1VVdfRi
   XzPTCwBLcc89ya671luTfe1rRhpgPNq9e0NJcmyS6xcvvADA0t11VzIwUM/xKrwwMcbzi5TXJHln
   kteXUq4auu3eolwA0JPmzEl22il5xzuSL3xB4YWJ4nAKAJggN9xQb0v20Y8mn/hE02mgd4xkvGHc
   F7IBAMt2+eXJ295WjzMccEDTaaD/KL0A0GbnnZcceGBy4onJHns0nQb6k81RAKCNTjwxOfjg5Jxz
   FF5okpVeAGiDqkqOOqref/eii5LNN286EfQ3pRcAWmz+/OTDH04uvbS+bbBB04kApRcAWujBB5O/
   +Zv6dLXIiaujAAALvElEQVTLLktWXbXpREBiphcAWub225PXvCbZeON6hlfhhc6h9AJAC8ycWRfe
   970v+fd/Tyb7XSp0FP9JAsA4nXBC8o//mBx/fH20MNB5lF4AGKN585JDDkl+9rPk4ouTLbZoOhGw
   NEovAIzB3Xcn++2XrLJK8stfJquv3nQiYDhmegFglK64Ivmrv0p22ik5+2yFF7qBlV4AGKGqSr75
   zeTII5PvfjfZe++mEwEjpfQCwAg88EDy93+f3HZbMmNGvS0Z0D2MNwDAMvzqV8k22yTrrqvwQrdS
   egFgKRYsSI4+OnnTm5KvfjU55phkhRWaTgWMhfEGAFiCO+5IDjooefjh5PLLk402ajoRMB5WegFg
   MT/8YT3O8LrXJZdeqvBCL7DSCwBD7r8/+dCHkiuvTM49t96WDOgNVnoBIPV+u1ttlTz3ucmvf63w
   Qq+x0gtAX5s7N/nIR+qi+4MfJAMDTScC2sFKLwB9qaqSE0+sV3enTUuuvVbhhV5mpReAvnPTTfXs
   7t13J+edl7zylU0nAtrNSi8AfeORR5LPfCbZYYfkjW+sD51QeKE/KL0A9LyqSk47Ldl883r/3Vmz
   kkMOSZZfvulkwEQx3gBAT7vyyuTQQ5N7701OOSXZccemEwFNsNILQE+6/fbkne9M3vKW5O1vr8uv
   wgv9S+kFoKfcf3+9svvKVyYbb5z85jfJ//k/yWS/24S+pvQC0BMefDA58shkk03q+9ddl0yfnqyy
   StPJgE6g9ALQ1RaW3Y03Tm69Nbn88uS7303WXbfpZEAnUXoB6EoPPJB8/vN12b3llmTGjOT//b96
   pRdgcUovAF3l9tuTj3882XDD5Oabk8suS044QdkFhqf0AtAVrrgi2X//ZNtt6/11r722LrsveUnT
   yYBu4FpWADrWk08mP/5x8q1vJb/7XfKxj9Xzuquu2nQyoNsovQB0nFtvrcvt8ccnL3tZ8uEPJ3vv
   7QQ1YOyUXgA6wuOPJ2efnRx3XPLrXycHHphcconxBaA1lF4AGrNgQXLxxclJJ9VjDNtum7zrXclZ
   ZyUrrth0OqCXlKqq2vPCpVTtem0AuldV1RelnXlmcsopyRprJAcckLzjHcl66zWdDuhGpZRUVVWG
   e46VXgDabv785NJLkx/9qF7Rfc5zkn32Sc49t57ZBWg3pReAtrjnnuSCC5Lzz09+9rNkgw3qonvB
   BcnmmzedDug3xhsAaIl585L//d9nS+5vf5sMDCS7757ssUcybVrTCYFeNZLxBqUXgDF59NG65F5y
   SX375S/rU9F23z154xuTV786mTKl6ZRAP1B6AWiJBQvqldsrrkiuvDKZMSOZNSt5+cuTHXesbzvs
   kDz3uU0nBfqR0gvAqM2bl9x0U11qr7yyLrq//nW9y8K229a3V72qvk2d2nRaAKUXgGE89VRyyy3J
   7Nl/frv11vqis5e+9NmSu802yZprNp0YYMmUXoA+9+CDdbFdeLv11mfv//GPyQtfmGy5ZbLFFvXH
   LbdMNtvMwRBAd1F6AXrUggXJ/fcnd96Z3HHH0m8LFiQbbVTfNtzw2fsbbVQX3uWXb/pPAjB+Si9A
   l6iq5KGH6iJ7zz3J3LnJ3Xcv/XbPPcnKKycveEGy/vpLv622WlKG/WcAoPspvQATaMGCepzg/vuf
   vT3wwJ8/XtrtwQfri8LWWCNZa61l357/fNuBASyk9AKM0rx5zxbXRQvrSMrrww/Xq6/PfW6y+ur1
   x5HeVl89meyMTIAxUXqBvlNVyWOPPVtSl1Rch/vc44/XBXRhaV3843C31VZLJk1q+h0A6D9KL9DV
   5s9P7rsv+dOfknvvrW8L7y/pcwuL7OTJf15Sl1Rcl/a5VVYxAwvQbZReoGM8+eRfltRlldiHH67L
   6POeV+8Ru6SPi95fY426uK6wQtN/WgAmktILtMXjj/9lWV3Wxyef/MuSuqwSu/rqyXLLNf2nBaDT
   Kb3AsKoqefTR0ZXXP/2p3qVgaSuvSyuxxgYAaJe2lt5Syu5Jjk4yKcn3q6r6ymJfV3pbaHBwMAMD
   A03H6Bm99H5WVb3yOpqLtu6//9lRgkmTRlZeF/240krPFtheei87gfeztbyfreO9bC3vZ2uNpPSO
   aYOcUsqkJP+eZJckdyb5VSnl7KqqbhjL67Fs/uNorabfz6pKnnoqeeSRem51WbclPW/RUjtp0vAX
   a22wQbLVVn/+nIUldurU8f1Zmn4ve433s7W8n63jvWwt7+fEG+uukNslubmqqtuTpJTyn0n2SqL0
   0jGqqv41/IIFydNPP3tbsKDe0uqPf6z3ZH3qqfq26P3FHy/ta08+Wa+yPvZY/XG4+4s/Xm65+lf+
   y7qttlp9stbin190Wy0XbgHA8MZael+QZM4ij+9I8qrxx+leBx1UHwua1GVrobHeX/xzt96aXHpp
   a167G+4vWlSXdn+4ry0su6XUq6DLLVd/XHh78snkxBPrE62mTEmWX37J94f72vLL12Vz6tS6eE6d
   Wt9WWunZ+4s/XvS+gwgAYOKMaaa3lPLXSXavquq9Q4/fmeRVVVV9eJHnGOgFAGBCtGWmN/Uc7waL
   PN4g9WrviH8wAABMlLHugHlFkk1KKdNKKVOSvD3J2a2LBQAArTOmld6qquaXUj6U5PzUW5Yda+cG
   AAA6VdsOpwAAgE4xIQd8llIOKaUsKKWsMRE/r1eVUj5fSrmmlHJ1KeXCUsoGy/4ulqSU8rVSyg1D
   7+ePSimrNZ2pm5VS9iulzC6lPF1K2abpPN2olLJ7KeXGUspvSymfajpPtyulHFdKmVtKmdV0lm5X
   StmglHLR0H/j15VSPtJ0pm5WSlmxlDJz6N/y60spX2o6U7crpUwqpVxVSjlnuOe1vfQOFbNdk/yu
   3T+rD3y1qqqtq6p6eZKfJDmi6UBd7IIkW1ZVtXWSm5J8puE83W5Wkrcl+Z+mg3SjRQ782T3JFkne
   UUrZvNlUXe/41O8n4zcvycerqtoyyfZJPujv59hVVfVEktcP/Vu+VZLXl1Je23CsbvfRJNcnGXZ8
   YSJWer+e5JMT8HN6XlVVDy/ycOUkf2oqS7erqurnVVUtGHo4M8n6TebpdlVV3VhV1U1N5+hizxz4
   U1XVvCQLD/xhjKqquiTJ/U3n6AVVVd1VVdXVQ/cfSX0Q1XrNpupuVVU9NnR3Supro+5rME5XK6Ws
   n2TPJN9PMuzOYW0tvaWUvZLcUVXVte38Of2klPIvpZTfJzkwyZebztMjDk5yXtMh6GtLOvDnBQ1l
   gaUqpUxL8orUiwWMUSlluVLK1UnmJrmoqqrrm87Uxb6R5NAkC5b1xHGfCVVK+XmSdZbwpcNT/8p4
   t0WfPt6f1+uGeT8Pq6rqnKqqDk9yeCnl06n/hz5oQgN2kWW9l0PPOTzJU1VVnTKh4brQSN5PxswV
   xXS8UsrKSc5I8tGhFV/GaOg3jS8fup7k/FLKQFVVgw3H6jqllDcnubuqqqtKKQPLev64S29VVbsu
   JchLk7w4yTWllKT+9fGVpZTtqqq6e7w/t1ct7f1cglNidXJYy3ovSynvTv0rkZ0nJFCXG8XfTUZv
   mQf+QJNKKcsnOTPJSVVV/aTpPL2iqqoHSynnJtk2yWDDcbrRDkneWkrZM8mKSVYtpZxYVdW7lvTk
   to03VFV1XVVVa1dV9eKqql6c+v/At1F4x66UsskiD/dKclVTWbpdKWX31L8O2WvoogJax290Rs+B
   P3SsUq9cHZvk+qqqjm46T7crpaxZSll96P7U1Bf7+/d8DKqqOqyqqg2Geub+SX6xtMKbTNCWZUP8
   +m78vlRKmTU0BzSQ5JCG83SzY1JfDPjzoW1OvtV0oG5WSnlbKWVO6iu7zy2l/FfTmbpJVVXzkyw8
   8Of6JD904M/4lFJOTTIjyUtKKXNKKUbBxu41Sd6ZepeBq4ZudsYYu3WT/GLo3/KZSc6pqurChjP1
   imG7psMpAADoeRO50gsAAI1QegEA6HlKLwAAPU/pBQCg5ym9AAD0PKUXAICep/QCANDz/j97i0PJ
   jibf5AAAAABJRU5ErkJggg==
   "
   >
   </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">
   <h4 id="Inverse-CDF">Inverse CDF<a class="anchor-link" href="#Inverse-CDF">&#182;</a></h4>
   </div>
   </div>
   </div>
   
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[13]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="n">fig</span> <span class="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">kde3</span><span class="o">.</span><span class="n">support</span><span class="p">,</span> <span class="n">kde3</span><span class="o">.</span><span class="n">icdf</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,iVBORw0KGgoAAAANSUhEUgAAAr8AAAHfCAYAAABZBbApAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xm41WW9///njSMJOAAODCoikhKOqYjTFlPJ2bpwaFKz
   Otoxh2Pn1FEz6lv5M4+nHI7GlWZqmoc0cU4N2IITCDKDggiKAgI5MMuw798fNxoeETfstfa91vo8
   H9e1Ljay2ft1rSvj5c37875DjBFJkiSpCFrkDiBJkiQ1F8uvJEmSCsPyK0mSpMKw/EqSJKkwLL+S
   JEkqDMuvJEmSCqNJ5TeEsGUIYUQIYWwIYXII4epSBZMkSZJKLTR1z28I4XMxxqUhhE2BZ4Afxhif
   KUk6SZIkqYSaPPYQY1y65sPNgU2Ad5r6NSVJkqRyaHL5DSG0CCGMBd4GhsYYJzc9liRJklR6mzb1
   C8QYG4B9QwhbA0+EEOpijPUf/noIwfuTJUmS1CxijGF9v16ybQ8xxveBR4EvruPXfJXo9dOf/jR7
   hlp5+V76flbyy/fT97JSX76fvp+V/GqMpm57aBdC2GbNxy2BY4AxTfmakiRJUrk0dexhJ+COEEIL
   UpG+K8Y4uOmxJEmSpNJrUvmNMU4A9i9RFjVCXV1d7gg1w/eytHw/S8v3s3R8L0vL97O0fD+bX5P3
   /H7mNwghlvt7SJIkSSEEYnM98CZJkiRVOsuvJEmSCsPyK0mSpMKw/EqSJKkwLL+SJEkqDMuvJEmS
   CsPyK0mSpMKw/EqSJKkwLL+SJEkqDMuvJEmSCsPyK0mSpMKw/EqSJKkwLL+SJEkqDMuvJEmSCsPy
   K0mSpMKw/EqSJKkwLL+SJEkqDMuvJEmSCsPyK0mSpE8YORJ+9rPcKUrP8itJkqRPmDYNXnkld4rS
   s/xKkiTpE+bPh/btc6coPcuvJEmSPsHyK0mSpMJYsADatcudovQsv5IkSfoET34lSZJUGJZfSZIk
   FcaCBdC2be4UpWf5lSRJ0icsWQKtWuVOUXqWX0mSJH3CsmXQsmXuFKVn+ZUkSdInLF9u+ZUkSVJB
   ePIrSZKkQli5Mv246aZ5c5SD5VeSJEkfU6unvmD5lSRJ0v9h+ZUkSVJhWH4lSZJUGLW66QEsv5Ik
   Sfo/li2DLbfMnaI8LL+SJEn6GMceJEmSVBiWX0mSJBWG5VeSJEmF4cyvJEmSCsNtD5IkSSoMxx4k
   SZJUGIsWQevWuVOUh+VXkiRJH7NwIbRpkztFeVh+JUmS9DGWX0mSJBXGokWWX0mSJBWEJ7+SJEkq
   DMuvJEmSCsPyK0mSpMKw/EqSJKkwFi50z68kSZIKwpNfSZIkFcI770CMsM02uZOUh+VXkiRJH5kw
   AXr0gBByJykPy68kSZI+MnEi9OyZO0X5WH4lSZL0kQcfhCOOyJ2ifEKMsbzfIIRY7u8hSZKkpps7
   F/bcM/24xRa502y4EAIxxvUObHjyK0mSJABGjICDD67O4ttYll9JkiQB8MILqfzWsk1zB5AkSVJ+
   s2fDH/4Af/977iTl5cmvJElSwb3/Pnz5y3DppbW96QEsv5IkSYUVI/zsZ3DYYXDoofCjH+VOVH6O
   PUiSJBXUwIFw//1wzTVw3HG1e7HF2lx1JkmSVEDLl8PnPw933AFHHpk7TWm46kySJEnrdPPNsO++
   tVN8G6tJ5TeE0DmEMDSEMCmEMDGEcFGpgkmSJKl8hg2Db3wjd4rm19SZ35XApTHGsSGEVsDoEMJT
   McYpJcgmSZKkMpk+HXbfPXeK5tekk98Y49wY49g1Hy8GpgAdShFMkiRJ5REjvPYadO2aO0nzK9nM
   bwhhV2A/YESpvqYkSZJKb9gw2GoraN06d5LmV5JVZ2tGHu4DLl5zAvwx/fv3/+jjuro66urqSvFt
   JUmStIFihO9+F37969xJmq6+vp76+voN+j1NXnUWQtgMeAR4PMb423X8uqvOJEmSKsSECXDSSTBj
   Ru3t9S37qrMQQgBuAyavq/hKkiSpstx3H3z1q7VXfBurqTO/hwLfAI4KIYxZ8+pbglySJEkqsQED
   4JZb4MwzcyfJxxveJEmSCmDMGDjxxHTye8ghudOUR2PGHiy/kiRJNW7pUjj0UDj/fPiXf8mdpnws
   v5IkSeJ730sF+K67anvWtzHltySrziRJklR5li6Fa6+Fv/0tbXmo5eLbWCW75EKSJEmVY9IkOPxw
   eOklePpp2Hrr3Ikqg+VXkiSpxowfD3V1adxh0CDo0iV3osrh2IMkSVKNmDUL7rgDbrgB/ud/4PTT
   cyeqPJ78SpIkVbn33oO774YDDoA5c2DwYIvvp/HkV5IkqUrNnQs33ww33gg9esCjj8KBB+ZOVdks
   v5IkSVVm5Up4/nk44ww44QQYNw523jl3qupg+ZUkSaoSS5bAJZfAPfdAp05w003w1a/mTlVdLL+S
   JElVYM4cOOccaNs2Pdi23Xa5E1UnH3iTJEmqcNOnQ8+e6XXHHRbfpvB6Y0mSpAq2ZAn06we9e8OV
   V+ZOU9kac72xJ7+SJEkVaNIkOPhg2GknaN0afvSj3IlqgzO/kiRJFejGG6FPH3jqKWjTJnea2mH5
   lSRJqjAzZ8Jf/wrPPWfxLTXHHiRJkirIiBGw335pzGH33XOnqT0+8CZJklQhFi1Kxfeaa9zfuzEa
   88Cb5VeSJKlCfPvb0KIF3Hpr7iTVqTHl15lfSZKkjBYsgL/8Be67D958E0aPzp2otjnzK0mSlMGz
   z6aT3m7dYPhwuPBCGDMGWrXKnay2OfYgSZLUzCZNgrq69FDb2WdD+/a5E9UGZ34lSZIqzMqV0KsX
   nH8+fPe7udPUFsuvJElSBVi1CqZMgZdegltugR12gEGDIKy3pmlDWX4lSZIy+9//hX/7tzTLe8AB
   cMIJcNZZaauDSsttD5IkSRl88AHcdhs88gjMmAH3359GHZSf5VeSJKlEnn0WnngirS7r2hX69YMz
   z4SWLXMn04cce5AkSWqCFStg6FC49154+mn42tegTx846ihnepubYw+SJEllMncu/PKX8PjjaVXZ
   0UfDqFGw3Xa5k2l9PPmVJElqpCVLYPDgVHgHDoRvfSuNNvTunTuZwJNfSZKkJosxnej+/OcwZEja
   2NC3b7qNbeedc6fThrL8SpIk/R+rVsG4cfD88/DYY+njH/8Y7roLttkmdzo1hWMPkiRJa8ycmTY2
   /OY3acThsMPSSIMbG6qDl1xIkiQ1wrx5cPLJaSfvEUeksYZvf9ttDdXGmV9JkqS1xAhvvw1z5sD8
   +bBgAUyalC6kuOAC+MlPvHmt1ll+JUlSzVq9Gl5/HR58MO3iffFFWLkSOnWCdu3SirKdd04bHHr0
   yJ1WzcGxB0mSVDNmzIBrrkmbGN56K40ztGsHxx8Pxx4LBx0Eu+ziOEOtcuZXkiTVvLffhpEj4Zln
   4NZb4V//Fb78ZejYEXbaCTbbLHdCNRdnfiVJUk177DE491zYf3/o0gUmTIAOHXKnUiWz/EqSpKqy
   eDE88gg8/TQ8/DDcf39aSSY1huVXkiRVvPffh6uuSpdOvPxyKrsHHwyjR8MOO+ROp2rizK8kSapY
   U6akNWR33gmnnpp27+61F7RpkzuZKpEzv5IkqSrNnp327r74IpxzDjz3HOy+e+5UqgWWX0mSlF1D
   A7zzTnpNnQrf+x585zvwl7/A5pvnTqdaYvmVJEnNbvVqmD4dRo1Kow133AFLlsB220HbtjBgAJx0
   Uu6UqkWWX0mS1Czeew+GDIG77oLHH4ftt08PrXXpkrY27LNP7oQqAsuvJElqsoYGWLAA/vGP9Jo3
   D4YPhzfeSDetvfVWKr+HHZYuoPjTn2CrrXKnVhG57UGSJG2w8eNh2LB/Ft2HHoJly9JVwm3bplev
   XtCtW7pprWPHdPmEt62pnLzeWJIklcySJTB4MPz2t/DKK2kmt337VHjr6hxbUH6uOpMkSU3y7rvp
   yuBnn4Vrr007di+4APr1cwuDqpPlV5IkATB3biq548enk90pU2DGDPjCF9L4wogR6Uepmjn2IElS
   gcydm/bozpjxz9drr8Grr8KKFfDFL8JBB0H37unVsydsuWXu1FLjOPMrSVJBxZg2LYwbl16DBsHM
   memf77lnWi+2667px65dYbfdoFMnaNEid3Jp41l+JUkqiOnTob4enn4aXnghrRbbemvYe+/0INox
   x6SP27eHsN5qIFUvy68kSTUqRnjyyTSH+8ADaZyhTx848kjo3Rt22QVat86dUmpell9JkmrI4sXw
   97+nMYZ774VNNoETToDjjkurxhxZUNFZfiVJqlJLlqQb0554Il0FPH58GmU44gjYbz848UQ45BDY
   1L1N0kcsv5IkVYGGBpg2LY0wPPdcer36Kmy7LRx6KJx2WprX7dbN3brS+lh+JUmqUG+/DX/8Y3pA
   7bnnUtE9+OB0mnvIIbDvvhZdaUNZfiVJqiANDfDXv6bX44+nW9KOPz49oLb99rnTSdXP8itJUgVY
   uDDN7F53Xdq9+y//kkYZ2rfPnUyqLY0pv47JS5JUQjNmwEsvpY0M48enH+fNS1cE9+2btjRssUXu
   lFJxefIrSVITfPBBuj3t5Zdh1Kh0wcQhh6SLJT68YKJr17SWTFJ5OfYgSVIJrV4NEyfC7Nnw7rsw
   aRI8+GAaXzjkEOjZE449Ftq2zZ1UKibLryRJG2n5chgyJJ3mjhoFc+akK4S33x523TVtZ+jWDQ47
   LF0d7JXBUn7NUn5DCH8ATgDmxRh7ruPXLb+SpIq3ejVMnZrmdV96KV0Z3LFjKrcHHJCuC955Z9hh
   h9xJJX2a5iq/hwOLgTstv5KkarBwIVx7bSq5c+emnbvz5qWCu//+6Qa1ujro1St3Ukkbolm2PcQY
   h4cQdm3q15EkqRzmzIHJk2HWLLj77nST2ty5cNZZcP75sOOO6TR3hx3cwiAVgavOJEk1YeVKGDs2
   7dF94430MNqwYbBgQdq40KEDnH12ulBip52gZcvciSXl0Czlt3///h99XFdXR11dXXN8W0lSjYox
   nejW16eSO3kyPPkk7L57WivWuXPaq3vppenhtK22yp1YUjnU19dTX1+/Qb+nJNse1ow9POzMrySp
   1FavhtGj4e9/h9deS6+JE9M/P+KINKO7885w0kmw3Xa500rKyRveJElVKUaYMiVdHjFgALRunfbn
   HnQQ9OuXTnU7dHC9mKQN1+TyG0L4M3Ak0DaEMAu4KsZ4e5OTSZIK6cUX4ZJL0tzuqaem64APOSR3
   Kkm1wksuJElZrVgB48fD88+nSyVGjIBf/ALOOQdatMidTlI18YY3SVJFWLECZs6EGTPg5ZfTZRKv
   vZZuTJs1K92UdvDBcOih8JWvQJs2uRNLqkaWX0lSFnPnwnPPwbhx8MoraStDq1Zp88LnP5/Kbteu
   6bXrrq4dk1Qall9JUtk1NKT53MmTYcIEeOSRtI3hsMNg331T2f3iF6F799xJJdU6y68kqWzmzoWr
   r4b77ks/79ED9toLjjkGvvQlb0uT1PxcdSZJKol33kljDC++CK++muZ1J0+G886DwYPT6a4kVQNP
   fiVJH4kR3nwzvd59N71uuSVtYzjoIOjVK40v7LYb7Lmnl0pIqiyOPUiSPmbZsvQA2muvpe0Lb70F
   s2enq4Jnz4Z589K4QpcusM02sO22UFeXTng39e8KJVU4y68kFdjy5TBsGDz7bHoAbeLE9GDa2lsW
   OneGnXZKrw4doH37dJrrzWmSqpHlV5IK5B//gJEj4YknUuGdNCltW+jTB/beO10J3K0bbLZZ7qSS
   VB6WX0kqgLlzYdAguPLKVHL79EmvffeFz30udzpJaj5ue5CkGvP++zB6dLo0YsyYNKv72mtw3HGp
   AB92WO6EklTZPPmVpAr3wQdw8cVwzz3pQomePdNDaAcfnOZ0d9sN2rXLnVKS8vPkV5Kq1KxZMHAg
   PPwwjBoFxx8P06enkuvDaJK08Tz5laSMZs6EoUNhypT08euvpx9XroTTToOvfAUOPxzatMkcVJKq
   gA+8SVIFiRHGjYPhw9Os7uOPpz27X/pSelBtl13Sa9ddYccdoUWL3IklqbpYfiUpk1Wr0jXA48fD
   hAnp41dfhfnz08NpO+2UNjIceihssknutJJUGyy/ktQM3n47nei+/DKMHZs+njIlPYzWs2d67bEH
   dOwIvXunG9QkSaVn+ZWkMmloSLelDR8Ol12WLpDo3h322w/22Sf9fKutcqeUpGJx24MklUiMMG8e
   DB4MDzwATz4JrVvDXnul/bq9e+dOKElqDE9+JWkdli9PK8aee+6fr1Wr0ozuaafBiSfC9tvnTilJ
   WptjD5LUCO+8k9aNzZqV1oyNGJEeVNtrr3Si++Grc+fcSSVJ62P5laR1mDMnnepOmwaPPpo+Pvzw
   dFNa585w4IHp5cyuJFUXy68krWXmTLj1Vrj5ZjjkEOjaNZXevn3T/K4kqbr5wJukwlu+HGbPhuuv
   h7vvhtNPhzFj0mUSkqTisfxKqknDh8Mtt6TNDNtvD0cemcYctt02dzJJUk6OPUiqejGmCyYeeghG
   jkwXTCxbBpdcAmefDdtskzuhJKk5OPMrqaYtWQJ/+AP89rewcmVaP1ZXly6b6NEDNvXvtiSpUJz5
   lVST5s2Dm26C3/0uPbB2991w8MEQ1vt/d5IkQYvcASSpMT74ACZMgO9/P53szpsHzzwD998PvXpZ
   fCVJjePJr6SKd9ddcOGF0LYtfO1rab53hx1yp5IkVSPLr6SKtXIlDBoEP/whvPAC7Lln7kSSpGpn
   +ZVUcd57L11Ecf310KFDWldm8ZUklYLlV1J2S5fCn/+cSu7UqfDmm9CvHwwdCnvtlTudJKmWWH4l
   ZTFhAgwYkB5amzYN+vRJO3n33BN23x223DJ3QklSLXLPr6RmtWABXH55OuW9+GI49th0utuqVe5k
   kqRq555fSRVh1SoYMiQ9vHbvvfCtb6Vb2Nq1y51MklQ0ll9JJRcjvPJKGmeYNCk9vNaxIxx3XBp3
   6Ngxd0JJUlFZfiWV1OrV6WR32DDYe2/o1CmNOBxwQO5kkiRZfiWV0L33wv/8D2y2Wdra0LJl7kSS
   JH2c5VdSkyxbBrffDk8/DWPGwNVXw0knweab504mSdInue1B0kZbuTLt4/3gg1R4zzoLtt02dypJ
   UlG57UFS2bz7biq+W2yRtjhssUXuRJIkfbYWuQNIqk7nnAPdusGDD1p8JUnVw5NfSRtkxAi47TZ4
   8UWYPh029f9FJElVxD+2JK1XQwO89BI8/zzcdRe8/TZ8/evp4Ta3OUiSqo0PvElap4UL4aKL0jzv
   1ltD377pobZjjnHMQZJUmXzgTdIGW7gwnepecQV0755uatthh9ypJEkqDcuvJABGj07jDLNmpZvZ
   TjkF/v3fYZNNcieTJKl0HHuQxD/+AYccAj/+cbqa2IfYJEnVqDFjD646kwrurbfg5JPTSe+3v23x
   lSTVNsuvVGBPP51GHPr0gWuuyZ1GkqTy84xHKpgYob4eHnkkrS4bOBCOPjp3KkmSmocnv1LBDBgA
   3/lOWl82eLDFV5JULD7wJhVMt25w553pATdJkmqJD7xJ+pg33kh7fHv1yp1EkqQ8LL9SgQwdCkcc
   AWG9/00sSVLtsvxKBXLffWmtmSRJRWX5lQogRvj1r9MtbqeckjuNJEn5uOpMqnENDenyismT4YUX
   oE2b3IkkScrH8ivVoIYGGDsWnngCHngAttoq7fb93OdyJ5MkKS9XnUk1ZsUKOOMMmDABTjgBjj0W
   jjvOa4slSbWvMavO/ONQqiEjR8I3vwl77ZXGHDbfPHciSZIqi+VXqgGLF0O/fumBthtvhNNPd52Z
   JEnrYvmVqlyM8B//AW3bwltvwWab5U4kSVLlsvxKVe6GG2DIEHjmGYuvJEmfpcl7fkMIfUMIL4cQ
   poUQflSKUJIa76GH4L/+C9q1y51EkqTK16TyG0LYBLgJ6AvsBZwVQtizFMEkfbYHH0wPuR1+eO4k
   kiRVh6aOPRwEvBpjnAkQQrgXOAWY0sSvK2k9hg+Hm26CYcPgkUdg661zJ5IkqTo0deyhIzBrrZ+/
   ueafSSqTgQPha1+DI4+EKVPSj5IkqXGaevLr7RVSM1q1Cq64Au68E446KncaSZKqT1PL71tA57V+
   3pl0+vsx/fv3/+jjuro66urqmvhtpeKJEa68Ejp0AP8VkiQJ6uvrqa+v36Df06TrjUMImwKvAEcD
   s4GRwFkxxilrfY7XG0tN9MEHcNVV8NRTMGgQ7Lxz7kSSJFWexlxv3KSZ3xjjKuBC4AlgMvC/axdf
   SU03fTrss0+a7334YYuvJElN0aST30Z9A09+pY02eDBcdBF85ztw6aW500iSVNkac/Jr+ZUq1MSJ
   cOihcN11cN55ENb7r7IkSbL8SlWqoQG+/GU4/ni4+OLcaSRJqg5ln/mVVB4/+AEsXw4XXJA7iSRJ
   taWpq84kldhLL8FDD8GkSbD55rnTSJJUWzz5lSrMjTemE982bXInkSSp9njyK1WQadPgkUdg6tTc
   SSRJqk2e/EoV5Oc/h0sugW23zZ1EkqTa5LYHqUK89x7ssgvMmAHbbZc7jSRJ1cdtD1IV+dWv4IQT
   LL6SJJWTJ79SBYgxjTpMngwdOuROI0lSdfLkV6oSr78OrVpZfCVJKjfLr1QBxo6FffbJnUKSpNpn
   +ZUqwLhxsO++uVNIklT7LL9SBfDkV5Kk5mH5lTJbtAhGj/bkV5Kk5mD5lTKaMwd69YK6Oth999xp
   JEmqfZZfKZOZM+Goo+BrX4M774QW/tsoSVLZ+cet1MxefRX69IG994bzz4crrsidSJKk4tg0dwCp
   SD74AM49F445Bh57DLbcMnciSZKKxZNfqZlcey106gQdO8Lll1t8JUnKwZNfqRncfTfccgu88AJ0
   7Zo7jSRJxRVijOX9BiHEcn8PqZKNHAknnABDhkDPnrnTSJJUu0IIxBjD+j7HsQepjIYPh69+FX7/
   e4uvJEmVwLEHqYRihMGDYdgwmDgxnfpedRWcemruZJIkCRx7kErqllvguuvgjDOgR490eUWHDrlT
   SZJUDI0Ze7D8SiWyeDF06waPPgr77587jSRJxePMr9SMfvObdGObxVeSpMrlzK9UAiNHwg03pFVm
   kiSpcnnyKzXR8uVwyilw++3u8JUkqdJZfqUmqq9PpffEE3MnkSRJn8XyKzXRHXfAySfnTiFJkhrD
   bQ9SE1x0ETz1FIwaBVttlTuNJEnF1phtDz7wJm2koUNh4ECYNs3iK0lStXDsQdoIt90Gp58O99wD
   rVvnTiNJkhrLk19pAzQ0wE9/CnfdBc89ly61kCRJ1cPyKzXSqlXwzW/CW2+lvb7bb587kSRJ2lCW
   X6kRFi6ECy6Ad96BJ5+ELbfMnUiSJG0MZ36lz3D99bDbbmnkYdAgi68kSdXMk1/pUyxdCn/6E1x3
   Xbq2ePfdcyeSJElNZfmV1mHVKvjSl2DTTdNpr8VXkqTaYPmV1mHIEFixAp59FsJ6V2VLkqRqYvmV
   1jJ8eDrpvf9++OEPLb6SJNUarzeWSGMORx8Ns2bBuefCccfBF78ILXwkVJKkquH1xlIjrFwJAwbA
   8uUwdWqa85UkSbXJP+ZVaBMmwHnnpRPe//ovi68kSbXOv9RVYT3xBPTpA2ecAc8/D4cfnjuRJEkq
   N2d+VUgrVkDnzvCXv8ARR+ROI0mSSsGZX2kdFi+GX/0Kune3+EqSVDSOPahQBgyAXXZJD7bddVfu
   NJIkqbk59qDCmDEDDjooXVyxxx6500iSpFJrzNiDJ78qjAcfhJNPtvhKklRkzvyq5s2fn0YcbrgB
   fv/73GkkSVJOjj2opjU0QO/e0KULnH46nHZa7kSSJKlc3PagwvvznyEEuOee9KMkSSo2T35Vs959
   F/bfH/74RzjyyNxpJElSufnAmwrrqqvSqEO/fhZfSZL0T449qKbMmQM33gj33QdTpsBOO+VOJEmS
   Koknv6p6q1fDr38NRx0Fe+0Fs2fDkCEWX0mS9Eme/KrqXX01PPooXHkl9OkDLVvmTiRJkiqV5VdV
   a+lS+PGPYeBAGD0aOnbMnUiSJFU6xx5UlaZMgf32Sxsdxo61+EqSpMax/KqqrFoFf/87nHkmfP/7
   6ea2HXfMnUqSJFULxx5UFebPh/794cEH0ynvt74FF12UO5UkSao2nvyq4j3wAOy7L2y+OTz1FIwY
   AZdd5o1tkiRpw3nyq4q0ahXcfjvcdhvMnQt/+Qv07p07lSRJqnaWX1WUd9+F66+HW2+F3XeHX/wC
   Dj4YWrfOnUySJNWCjR57CCH0CyFMCiGsDiHsX8pQKp758+GSS2DvveH11+Hxx6G+Hr70JYuvJEkq
   nabM/E4ATgOGlSiLCmjZsnTKu88+6ecPPpjGHXr2zJtLkiTVpo0ee4gxvgwQfOpIG+nVV+HUU6FT
   J7j3XjjiiNyJJElSrXPbg7K49940y3vhhfC3v1l8JUlS81jvyW8I4SlgXVcIXB5jfLix36R///4f
   fVxXV0ddXV1jf6tq0JQp8IMfwJAh/xx3kCRJ2lD19fXU19dv0O8JMcYmfdMQwlDgshjjS5/y67Gp
   30O1YepU+OUv4dFH4b//O11UIUmSVCohBGKM653JLdXYg4O/Wq/Bg9Oe3j33hLFjLb6SJCmPjT75
   DSGcBtwAtAPeB8bEGL+8js/z5Lfg5s9PN7TdcUdaXSZJklQOZT35jTE+EGPsHGNsGWPccV3FV8W2
   cGG6oW3//eH88y2+kiQpP294U8k1NMBll6V9vUceCXff7TYHSZJUGSy/KrkbboAXXoBp06B9+9xp
   JEmS/snyq5J57710yvvLX8Kzz1p8JUlS5bH8qiQWLEgPtfXuDY88AnvskTuRJEnSJzV5z+9nfgO3
   PdS8t9+Gn/wkzfreemvuNJIkqaiac8+vCiRGuP9++OpXoUsX+Pzn08jDr36VO5kkSdL6efKrRnv/
   fRg4EK69Flavhp/+FA48ELp3hxb+Z5QkScqsMSe/zvxqvaZNg9//HoYNg5dfhj59YMAAqKuD4L1+
   kiSpyng/BHROAAANNUlEQVTyq3WaORO+8x0YPx7OOQdOPhm+8AXYZpvcySRJktbNk19tlDFjoF+/
   VHoffRS22CJ3IkmSpNKw/Ooj772XriEePDhdVHHWWbkTSZIklZblVwDMmQN9+6ZriGfMgFatcieS
   JEkqPZ/RF0uWwLHHptVlN9xg8ZUkSbXLB97EZZfB7Nlwzz1ucJAkSdXLB960XjHCddelCytGjrT4
   SpKk2mf5LajVq+EHP0il9+mnYfvtcyeSJEkqP8tvAU2cCOedB61bw5Ah0KZN7kSSJEnNwwfeCmbR
   IjjpJDj7bHjySYuvJEkqFh94K5CGBjj66HRT24035k4jSZJUWo154M2T3wK58UZYtQquvz53EkmS
   pDyc+S2I4cPhV7+CZ56BFv4njyRJKijHHgriK19JN7h973u5k0iSJJWHYw/igw/g+9+H8ePh9NNz
   p5EkScrLsYcad+GFMHUqvPSSmx0kSZIce6hhMULHjmnet2vX3GkkSZLKy7GHglq9Gv70J9h7b2jZ
   EnbbLXciSZKkyuDYQw2ZPx8eeAAGDoQlS+AXv4Djj4ew3v/+kSRJKg7HHmrEu++mCyy6dEk/nnce
   bLFF7lSSJEnNpzFjD5bfGrBiBRxwABxxBNx0kye9kiSpmJz5LYBx46B3b+jRw+IrSZL0WSy/VWrJ
   ErjtNjjlFPjGN9IDbhZfSZKk9fOBtypTX59K78MPw5FHwu9+l25ukyRJ0mdz5rcKNDTA1VfD3Xen
   NWYXXghnnAHbb587mSRJUuVozMyvJ79V4He/g7/+FW6/HQ48EFo4rCJJkrRRPPmtcOPHp9VlzzwD
   3bvnTiNJklS53PZQ5ZYsSeMN111n8ZUkSSoFT34r2LnnQozwxz/mTiJJklT5nPmtYnfeCS+8AC++
   mDuJJElS7fDktwK9/z507QqDB8M+++ROI0mSVB2c+a1Ckyen29r69bP4SpIklZonvxXmK1+Bww6D
   f/u33EkkSZKqizO/Veamm9INbrffnjuJJElSbfLkt0K8+CKceioMHQp77JE7jSRJUvVpzMmv5bdC
   fOMbcMABcOmluZNIkiRVJ8tvlYgRdtgBRo+Gzp1zp5EkSapObnuoEi+/DFttZfGVJEkqN8tvBbjz
   Tjj55NwpJEmSap9jD5ktWgRdusDIkbDbbrnTSJIkVS/HHqrAn/8MdXUWX0mSpOZg+c1oxYo08nDG
   GbmTSJIkFYPlN5OlS6FrV1i+HI47LncaSZKkYvCGt0wmToT27WHUqNxJJEmSisOT30zGj4e9986d
   QpIkqVgsvxksWAA33wz77587iSRJUrG46qyZNTTAmWfCNtvATTfB5pvnTiRJklQbGrPqzJnfZnb7
   7TBjBjz9tMVXkiSpuXny24zmzYP99oP774devXKnkSRJqi1eclFBVq+Gr38dzjnH4itJkpSL5beZ
   DBiQLrX42c9yJ5EkSSouy28zuftu+M//hE2dspYkScrG8tsMrrkG5s6FPn1yJ5EkSSo2H3grs+nT
   04zv+PGw006500iSJNUuH3irALfcAueea/GVJEmqBJ78ltGyZbDzzvDCC9C1a+40kiRJtc2T38xG
   jYIuXSy+kiRJlWKjy28I4doQwpQQwrgQwl9DCFuXMlgtWLQI2rbNnUKSJEkfasrJ75NAjxjjPsBU
   4D9LE6l2LF4MrVrlTiFJkqQPbXT5jTE+FWNsWPPTEUCn0kSqHUuWwFZb5U4hSZKkD5Vq5vfbwGMl
   +lo1w5NfSZKkyrLe+8ZCCE8BO67jly6PMT685nOuAFbEGO/5tK/Tv3//jz6uq6ujrq5uY7JWnSVL
   LL+SJEnlUl9fT319/Qb9niatOgshnAN8Fzg6xrj8Uz6nsKvOrrwSttgCfvKT3EkkSZJqX2NWna33
   5Pczvnhf4N+BIz+t+BbdkiVue5AkSaokTZn5vRFoBTwVQhgTQri5RJlqxuLFPvAmSZJUSTb65DfG
   2K2UQWqRD7xJkiRVFm94KyMfeJMkSaoslt8ycuxBkiSpslh+y2jhQmjdOncKSZIkfcjyW0azZkHn
   zrlTSJIk6UNN2vPbqG9Q0D2/y5bBNtukH1v4nxiSJEll15g9v9ayMpk1Czp1svhKkiRVEqtZmbz+
   OuyyS+4UkiRJWpvlt0wuvxxOPDF3CkmSJK3Nmd8ymDcPuneHf/zDsQdJkqTm4sxvJiNGwIEHWnwl
   SZIqjfWsDAYNgj59cqeQJEnS/+XYQ4k1NKRb3d54A9q3z51GkiSpOBx7yGDp0jTuYPGVJEmqPJbf
   Elu82CuNJUmSKpXlt8QWL4ZWrXKnkCRJ0rpYfkvM8itJklS5LL8lZvmVJEmqXJbfElu0yPIrSZJU
   qSy/JebJryRJUuWy/JaY2x4kSZIql+W3xDz5lSRJqlyW3xKz/EqSJFUuy2+JWX4lSZIql+W3xN5/
   H9q0yZ1CkiRJ62L5LbEFC6B9+9wpJEmStC6W3xJbsADatcudQpIkSeti+S0xy68kSVLlsvyW2Pz5
   ll9JkqRKZfktoRjTyW/btrmTSJIkaV0svyW0eDFsthm0bJk7iSRJktbF8ltCy5fDKafkTiFJkqRP
   E2KM5f0GIcRyfw9JkiQphECMMazvczz5lSRJUmFYfiVJklQYll9JkiQVhuVXkiRJhWH5lSRJUmFY
   fiVJklQYll9JkiQVhuVXkiRJhWH5lSRJUmFYfiVJklQYll9JkiQVhuVXkiRJhWH5lSRJUmFYfiVJ
   klQYll9JkiQVhuVXkiRJhWH5lSRJUmFYfiVJklQYll9JkiQVhuVXkiRJhWH5lSRJUmFYfiVJklQY
   ll9JkiQVhuVXkiRJhWH5lSRJUmFYfiVJklQYll9JkiQVhuVXkiRJhWH5lSRJUmFYfiVJklQYll9J
   kiQVhuVXkiRJhWH5lSRJUmFYfiVJklQYG11+Qwj/L4QwLoQwNoQwOITQuZTBtG719fW5I9QM38vS
   8v0sLd/P0vG9LC3fz9Ly/Wx+TTn5/XWMcZ8Y477AIOCnJcqk9fBfktLxvSwt38/S8v0sHd/L0vL9
   LC3fz+a30eU3xrhorZ+2AhY0PY4kSZJUPps25TeHEH4JfBNYCvQqSSJJkiSpTEKM8dN/MYSngB3X
   8UuXxxgfXuvzfgx0jzGeu46v8enfQJIkSSqhGGNY36+vt/w2VghhZ+CxGOMXmvzFJEmSpDJpyraH
   bmv99BRgTNPjSJIkSeWz0Se/IYT7gO7AamA6cEGMcV4Js0mSJEklVZKxB0mSJKkaNNsNbyGEy0II
   DSGE7Zrre9YiLxcprRDCtSGEKWve07+GELbOnamahRD6hRAmhRBWhxD2z52nGoUQ+oYQXg4hTAsh
   /Ch3nmoWQvhDCOHtEMKE3FlqQQihcwhh6Jp/xyeGEC7KnalahRC2DCGMWPNn+eQQwtW5M9WCEMIm
   IYQxIYSH1/d5zVJ+1xS0Y4DXm+P71TgvFymtJ4EeMcZ9gKnAf2bOU+0mAKcBw3IHqUYhhE2Am4C+
   wF7AWSGEPfOmqmq3k95LlcZK4NIYYw/SetN/9X+fGyfGuBw4as2f5XsDR4UQDsscqxZcDEwG1jvW
   0Fwnv/8N/Eczfa+a5uUipRVjfCrG2LDmpyOATjnzVLsY48sxxqm5c1Sxg4BXY4wzY4wrgXtJDxRr
   I8QYhwPv5s5RK2KMc2OMY9d8vBiYAnTIm6p6xRiXrvlwc2AT4J2McapeCKETcDxwK7DeVWdlL78h
   hFOAN2OM48v9vYoihPDLEMIbwNnA/5c7Tw35NvBY7hAqtI7ArLV+/uaafyZVlBDCrsB+pEMDbYQQ
   QosQwljgbWBojHFy7kxV7jfAvwMNn/WJTbrh7UPruQzjCtJfIx+79qeX4nvWss+6XCTGeAVwxZrL
   RX4DfOJyEf1TYy5rCSFcAayIMd7TrOGqUGMvv9FG8QlkVbwQQivgPuDiNSfA2ghr/tZx3zXPmjwR
   QqiLMdZnjlWVQggnAvNijGNCCHWf9fklKb8xxmM+JcwXgC7AuBACpL9SHh1COMi1aJ/u097PdbgH
   Tyo/02e9nyGEc0h/VXJ0swSqchvwv09tuLeAtR9i7Uw6/ZUqQghhM+B+4E8xxkG589SCGOP7IYRH
   gS8C9ZnjVKvewMkhhOOBLYE2IYQ7Y4zfWtcnl3XsIcY4Mca4Q4yxS4yxC+n/xPe3+G48LxcprRBC
   X9Jfk5yy5gEElY5/y7PhRgHdQgi7hhA2B84AHsqcSQIgpFOs24DJMcbf5s5TzUII7UII26z5uCVp
   KYB/nm+kGOPlMcbOa7rmmcCQTyu+0Iyrztbwr/Sa7uoQwoQ1c0J1wGWZ81S7G0kPDj61Zj3KzbkD
   VbMQwmkhhFmkJ8EfDSE8njtTNYkxrgIuBJ4gPbH8vzHGKXlTVa8Qwp+B54A9QgizQgiOiDXNocA3
   SJsJxqx5uU1j4+wEDFnzZ/kI4OEY4+DMmWrJevuml1xIkiSpMJr75FeSJEnKxvIrSZKkwrD8SpIk
   qTAsv5IkSSoMy68kSZIKw/IrSZKkwrD8SpIkqTD+fz6HoczWyyCgAAAAAElFTkSuQmCC
   "
   >
   </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">
   <h4 id="Survival-Function">Survival Function<a class="anchor-link" href="#Survival-Function">&#182;</a></h4>
   </div>
   </div>
   </div>
   
   <div class="cell border-box-sizing code_cell rendered">
   <div class="input">
   <div class="prompt input_prompt">
   In&nbsp;[14]:
   </div>
   <div class="inner_cell">
       <div class="input_area">
   <div class="highlight"><pre><span class="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">kde3</span><span class="o">.</span><span class="n">support</span><span class="p">,</span> <span class="n">kde3</span><span class="o">.</span><span class="n">sf</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,iVBORw0KGgoAAAANSUhEUgAAAsEAAAHfCAYAAACxhQUCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz
   AAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xm81nP+//HHu442oUJRKWQZoWzTYslBTJJtbC1kp8GY
   +d2Mr2Vm6Dvf78zwHd9ZDIOxi4RkG741RMMgWVKYSlmSIssIyRK9f398Thyps17nel/L4367Xbdz
   Xed8us7z9nHo5XVe7/c7xBiRJEmSykmz1AEkSZKkfLMIliRJUtmxCJYkSVLZsQiWJElS2bEIliRJ
   UtmxCJYkSVLZqbUIDiFcF0JYHEJ4oYZrLg0hzA0hzAgh7JjbiJIkSVJu1aUTfD0waE1fDCEMBraI
   MW4JnAJckaNskiRJUpOotQiOMT4GfFDDJQcBN1Zd+xTQLoTQKTfxJEmSpNzLxUxwF2BBtddvAl1z
   8L6SJElSk6jI0fuEVV5/5yzmEILnM0uSJCkvYoyr1qffkosieCGwSbXXXas+t7owOfh2Ahg9ejSj
   R49u8J9f+Y8ixm+ef/VV9li+HL788puPdXn++efw6aerfyxb9u3Xn3wCH34IS5ZkH1c+1loL1lsv
   e7RrBxtuCB07QqdO2cfqzzfaCDbYAEKNP975uZf6Nu9nbnk/c8d7mVvez9zyfuZWqEOBkIsi+F7g
   DGBcCKEfsCTGuDgH76smtPJno/rPSPPm2cfWrfOfJ8asWF5ZEC9ZAu++C4sXwzvvwGuvwdSp2fN3
   3oFFi7KCulu37NG9+zfPe/SArbfOiuhcFMmSJKn01FoEhxBuBfYENgghLAAuBNYCiDFeFWN8IIQw
   OIQwD/gEOL4pA6s0hQBrr509Oneu259ZuhQWLID58+GNN7LH5Mlw1VUwZ05WWH/ve1lBvPXWsO22
   sNNO0KWLxbEkSeWu1iI4xjisDteckZs4qqvKysrUEZJr2xa22SZ7rCpGeO89mD07K4jnzIG//AWm
   T4cVK2DHHbPHTjtBz56Vec9eyvzZzC3vZ+54L3PL+5lb3s/8C/ma0w0hRGeClVqM8NZbWTE8fTo8
   +yw8/ng2ArL77tljjz2gZ09o5nmKkiQVpRBCrQvjLIJV9mKEuXPhn//MHo89ls0k77cfDBqUfezk
   zteSJBUNi2Cpgd54AyZNgokTsznjHj1gyBA4/HDYbjtniiVJKmQWwVIOLF8OTz4J99wD48dnoxNH
   HJE9tt/egliSpEJjESzlWIzw9NNwxx3Zo00bOOEEOOYYRyYkSSoUFsFSE4oxW1R33XVw110wYEBW
   EA8Z8s2ey5IkKf8sgqU8Wbo06wxffXV2kMfpp8OJJ0KHDqmTSZJUfupSBLsJlJQDbdvC8cfDE09k
   c8MvvJAtphs1KtujWJIkFRaLYCnHdtkFbroJZs2CjTfO9h0+6iiYMSN1MkmStJJFsNRENtoILrwQ
   Xn0V+vSB/feHgw6CadNSJ5MkSRbBUhNr2xbOOisrhgcNgsMOyx6zZ6dOJklS+bIIlvKkVSs47TR4
   +WXo1y8bkzjlFFi4MHUySZLKj0WwlGetW8PZZ2fFcIcO0KtXNjaxbFnqZJIklQ+LYCmR9u3hoovg
   +eez0YiePWHChGz/YUmS1LTcJ1gqEI88AmeemS2ou/RS2Gab1IkkSSpO7hMsFZG99oLp0+HAA7PT
   5/7zP+GLL1KnkiSpNFkESwWkoiLrBk+fDs88AzvtBFOnpk4lSVLpcRxCKlAxwu23w09/mh228Zvf
   QJs2qVNJklT4HIeQilgIWfH74ovw3nuw447w9NOpU0mSVBrsBEtF4rbbslGJM86A887LRickSdJ3
   1aUTbBEsFZGFC+G44+CTT2DMGOjRI3UiSZIKj+MQUonp0gUmTcrGJPr1g1tuSZ1IkqTiZCdYKlIz
   ZsARR2Rbq/3xj9lJdJIkyU6wVNJ694Znn4WPPoL+/WHu3NSJJEkqHhbBUhFbZx0YOxZGjYJdd80W
   z0mSpNo5DiGViOnTs/GIgw+Giy929whJUvlydwipzPz73zB0aPZ83Djo0CFtHkmSUnAmWCozHTrA
   Aw9Ar17Qp0920IYkSfoui2CpxFRUwCWXwOjR2c4REyakTiRJUuFxHEIqYc88Az/8IZxwAlx4YXYU
   syRJpc6ZYEksXgwHHQRbbQXXXAMtW6ZOJElS03ImWBKdOsEjj8CyZbDfftniOUmSyp1FsFQG2rSB
   O+7IFsv17w/z5qVOJElSWhbBUplo1gx+9zv4f/8P9tgDHn88dSJJktKxCJbKzKhRcP31cMghnjAn
   SSpfnikllaFBg+Chh+CAA7KFc2eemTqRJEn55e4QUhl7/XX4wQ/g8MPhv//bLdQkSaXBLdIk1erd
   d2HwYOjdG668MjtsQ5KkYuYWaZJqteGG2RZqCxZkHeFPP02dSJKkpmcRLIm2beG++7Kt1PbbDz74
   IHUiSZKalkWwJABatICbb4add4YBA2DRotSJJElqOhbBkr7WrBn84Q8wfHi2l/Brr6VOJElS03AJ
   jKRvCQHOOw/WWy/rCP/977DNNqlTSZKUWxbBklbrtNOyWeG994YHHoAdd0ydSJKk3LEIlrRGI0fC
   2mtnewnfdRfstlvqRJIk5YYzwZJqdNhhMGZMdszygw+mTiNJUm5YBEuq1Q9+ABMmwIgRcPfdqdNI
   ktR4jkNIqpM99oD/+z844ABYuhSOPjp1IkmSGs4iWFKd7bwzPPxwdqDG0qUwalTqRJIkNYxFsKR6
   6dkTHn0UBg6Ejz+Gs89OnUiSpPqzCJZUb5tv/k0hvHQpjB6d7S8sSVKxCDHG/HyjEGK+vpek/Hjn
   nWw0Yu+94X//10JYklQYQgjEGGv8W8ndISQ1WMeO8Mgj8MQTcOqp8NVXqRNJklQ3FsGSGqV9+2z/
   4Llzs8M1li9PnUiSpNpZBEtqtHXWyY5WXrIEjjgCPvssdSJJkmpmESwpJ1q3zo5WbtECDjoIPvkk
   dSJJktbMIlhSzrRoAWPHQpcu2SlzH36YOpEkSatnESwppyoq4NprYccdYZ994L33UieSJOm7LIIl
   5VyzZnDppbDvvrDnnvDWW6kTSZL0bR6WIalJhAC//W22aG6PPWDyZOjePXUqSZIyFsGSmtT550Pb
   tjBgQLaV2lZbpU4kSZJFsKQ8OPPMrBCurISJE6FXr9SJJEnlziJYUl6ccAKsvXY2J3zffdCnT+pE
   kqRyZhEsKW+OOiorhA84AMaPzxbNSZKUgrtDSMqrIUNg3LjsZLmJE1OnkSSVK4tgSXm3zz5wzz0w
   ciTceWfqNJKkcuQ4hKQk+veHSZNg8GB4/3045ZTUiSRJ5cQiWFIyO+4Ijz4KgwbB22/DL3+Z7S8s
   SVJTCzHG/HyjEGK+vpek4vL227D//tCvH1x2GTRvnjqRJKmYhRCIMdbYVrEIllQQPvoIDj0U2rWD
   W26BVq1SJ5IkFau6FMEujJNUENZdFx54ACoq4Ac/gCVLUieSJJUyi2BJBaNlS7j1Vthhh+yY5UWL
   UieSJJUqi2BJBaVZM/jjH2H4cNh1V3jppdSJJEmlyN0hJBWcEODcc6FLF9hrLxg7FgYOTJ1KklRK
   7ARLKljHHAN33AEjRsC116ZOI0kqJe4OIangzZkDBxyQHbX8619nIxOSJK2JW6RJKhnvvQeHHAKd
   O8ONN0Lr1qkTSZIKlVukSSoZG2wADz2UbaG2997wzjupE0mSiplFsKSi0apVdpDGwIHQty/MmJE6
   kSSpWDkOIakojRsHP/4xXHEFHH546jSSpEKSk3GIEMKgEMLsEMLcEMI5q/n6BiGEiSGE50MIL4YQ
   jmtEZkmqk6FDYdIkOOssuOACWLEidSJJUjGpsRMcQmgOzAEGAguBp4FhMcZZ1a4ZDbSMMZ4XQtig
   6vpOMcYvV3kvO8GScu6dd+Cww6BDBxgzJjt+WZJU3nLRCe4DzIsxvh5jXA6MAw5e5Zq3gJV/7awL
   vL9qASxJTaVjR5g8GTbeGPr3h3nzUieSJBWD2orgLsCCaq/frPpcdVcD24YQFgEzgJ/kLp4k1a5F
   C7jyymxGeLfdYOLE1IkkSYWutiK4LvML5wPPxxg7AzsAl4cQ1ml0Mkmqp1GjYPx4OOkkuPBC+Oqr
   1IkkSYWqopavLwQ2qfZ6E7JucHW7Ar8GiDG+EkJ4DdgaeGbVNxs9evTXzysrK6msrKx3YEmqyR57
   wDPPwPDhMGgQjB0LG26YOpUkqSlNmTKFKVOm1OvP1LYwroJsods+wCJgGt9dGPd74MMY43+GEDoB
   zwK9Yoz/XuW9XBgnKW++/DLrBt90E9x2G+y6a+pEkqR8ycmxySGE/YE/As2Ba2OMvw0hnAoQY7yq
   akeI64FuZOMVv40xjl3N+1gES8q7+++HE06Ac8+Fn/4UQo3/SZQklYKcFME5DGMRLCmJ11+HI46A
   7t3hmmugXbvUiSRJTSknh2VIUrHbdFP45z+zbdR22AGeeCJ1IklSanaCJZWVe++FU06B00+H88+H
   5s1TJ5Ik5ZrjEJK0GgsXwjHHZFuo3XwzbLJJ7X9GklQ8HIeQpNXo0gUefDDbQm2XXeCuu1InkiTl
   m51gSWVt6tRsT+F994X//V9o2zZ1IklSY9kJlqRa9OsH06fDF19ki+Yefzx1IklSPtgJlqQqd98N
   P/oRjBwJv/oVtGyZOpEkqSHsBEtSPRxyCMyYAS+/DN//Pjz/fOpEkqSmYhEsSdV07AgTJsBZZ2Vz
   wr/9bXYEsySptDgOIUlr8MYbcPzx8OmncMMNsNVWqRNJkurCcQhJaoRu3bKt1IYOhV13hUsuyfYW
   liQVPzvBklQHr7wCJ52UdYWvuw569kydSJK0JnaCJSlHevSAyZPh2GNhwAD4zW9g+fLUqSRJDWUn
   WJLqaf58OPlkeP/9rCvcu3fqRJKk6uwES1IT6N4dJk2C006DgQNh9OjssA1JUvGwCJakBggBTjwx
   O23u6adhl13g2WdTp5Ik1ZVFsCQ1Qteu8Le/wdlnw/77w/nnw2efpU4lSaqNRbAkNVIIcMwxMHMm
   zJ4NO+0ETz2VOpUkqSYujJOkHIoRbr8dfvITOO64bF64VavUqSSpvLgwTpLyLAQ46iiYMQPmzs26
   wtOmpU4lSVqVRbAkNYFOnWD8eLjgAjjwQDjvPPj889SpJEkrWQRLUhMJITtyeeZMmDMn6wo//XTq
   VJIksAiWpCbXqRPceSf84hcwZEi2g4RdYUlKyyJYkvIgBBg27JsdJHbeGZ57LnUqSSpfFsGSlEcr
   u8Lnnw+DBsH//A+sWJE6lSSVH7dIk6RE5s/P9heuqICbbsoO3pAkNZ5bpElSAeveHR55BAYOzMYj
   7rgjdSJJKh92giWpAEybBiNGwO67w6WXwjrrpE4kScXLTrAkFYk+fWD6dGjWDL7/fXjxxdSJJKm0
   WQRLUoFo2xauvTZbNLfXXjBmTOpEklS6HIeQpAL0wgtw+OFQWQl/+hO0apU6kSQVD8chJKlIbb99
   drrckiWw667w2mupE0lSabEIlqQCte66MG4cHHss9O8P//hH6kSSVDosgiWpgIUAP/kJ3HwzHHkk
   /PWvqRNJUmlwJliSisTcuXDggbDffvD732eHbEiSvqsuM8EWwZJURJYsgaFDIcbscI11102dSJIK
   jwvjJKnEtGsHf/sbbLZZtnPE22+nTiRJxckiWJKKTEUFXHEFHHpotnPEyy+nTiRJxceJMkkqQiHA
   L38JG28Me+4J99yTnTonSaobZ4Ilqcjddx+ceCKMHw8DBqROI0npORMsSWXgwAPh1lvhsMNg8uTU
   aSSpOFgES1IJ2GefrBM8dChMnJg6jSQVPotgSSoRK2eDR47MdpCQJK2ZM8GSVGKmTYMhQ2DsWBg4
   MHUaSco/Z4IlqQz16ZONRgwbBk88kTqNJBUmi2BJKkEDBsCYMdlews8/nzqNJBUei2BJKlGDBsHl
   l8P++8OcOanTSFJh8bAMSSphhx8OH32UFcJPPgmdOqVOJEmFwU6wJJW4E06AY47J9hNetix1Gkkq
   DO4OIUllIEY47risKzx+PDRvnjqRJDUdd4eQJAEQAlx9NXz4IfzsZ6nTSFJ6FsGSVCZatIAJE+CB
   B+D661OnkaS0HIeQpDIza1Z2utx990HfvqnTSFLuOQ4hSfqObbaBa67Jdo54663UaSQpDYtgSSpD
   Bx0EJ58Mhx0GX3yROo0k5Z/jEJJUplasyE6U69EDfv/71GkkKXcch5AkrVGzZtkCuQkT4N57U6eR
   pPyyEyxJZe7JJ+GQQ2DaNOjePXUaSWo8O8GSpFr175/tHTx0KCxfnjqNJOWHnWBJEitWwJAhsMMO
   8JvfpE4jSY1Tl06wRbAkCYDFi6F372xGeNddU6eRpIZzHEKSVGedOsEVV8DIkbB0aeo0ktS07ARL
   kr7luOOgZUu46qrUSSSpYRyHkCTV24cfZmMRl18OBxyQOo0k1Z9FsCSpQaZMgaOPhhdfhHbtUqeR
   pPqxCJYkNdioURCjYxGSio9FsCSpwT78ELbdFm65BfbcM3UaSao7d4eQJDXYeutlc8EnnwyffZY6
   jSTllp1gSVKNjjwSttjCQzQkFQ/HISRJjbZ4MWy/PTz8MGy3Xeo0klQ7xyEkSY3WqROMHg1nnJEt
   lJOkUmARLEmq1amnwkcfwbhxqZNIUm44DiFJqpMnn4QjjoBZs2CddVKnkaQ1cyZYkpRTxx8PG2wA
   v/td6iSStGYWwZKknFq8OFsc949/QM+eqdNI0uq5ME6SlFOdOsHPfw4/+1nqJJLUOBbBkqR6Oe00
   mDsXHnwwdRJJajiLYElSvbRoARdfnHWDv/oqdRpJahiLYElSvR16KKy7Ltx4Y+okktQwLoyTJDXI
   tGlZMTxnDrRtmzqNJH3DhXGSpCbTpw/suSdccknqJJJUf7V2gkMIg4A/As2Ba2KMF6/mmkrgD8Ba
   wHsxxsrVXGMnWJJKzOuvw847w+zZsOGGqdNIUqbR+wSHEJoDc4CBwELgaWBYjHFWtWvaAY8DP4gx
   vhlC2CDG+N5q3ssiWJJK0OmnQ+vWdoQlFY5cjEP0AebFGF+PMS4HxgEHr3LNcODOGOObAKsrgCVJ
   pevnP4frr4dFi1InkaS6q60I7gIsqPb6zarPVbcl0CGE8EgI4ZkQwjG5DChJKmydO8MJJ8B//3fq
   JJJUdxW1fL0u8wtrATsB+wBtgCdDCFNjjHNXvXD06NFfP6+srKSysrLOQSVJheucc2DrreHss2Gz
   zVKnkVRupkyZwpQpU+r1Z2qbCe4HjI4xDqp6fR6wovriuBDCOUDrGOPoqtfXABNjjONXeS9ngiWp
   hF1wAbzxBtxwQ+okkspdLmaCnwG2DCFsGkJoARwF3LvKNfcAu4cQmocQ2gB9gX81NLQkqTiddRbc
   fz/MmlX7tZKUWo1FcIzxS+AMYBJZYXtbjHFWCOHUEMKpVdfMBiYCM4GngKtjjBbBklRm1lsvK4R/
   9avUSSSpdp4YJ0nKmY8/hs03h3/+M5sRlqQUPDFOkpRX66wDP/4xXHRR6iSSVDM7wZKknPrgA9hi
   C3j2Wdh009RpJJUjO8GSpLxr3x5OPRUuvrj2ayUpFTvBkqSce/fdbCb4hRegy6pHLElSE7MTLElK
   YsMN4bjj4JJLUieRpNWzEyxJahKLFsF228Hs2dCxY+o0ksqJnWBJUjKdO8NRR8Gf/pQ6iSR9l51g
   SVKTmTcP+veH116Dtm1Tp5FULuwES5KS2mIL2HNPuP761Ekk6dvsBEuSmtTUqTB8OLz8MlRUpE4j
   qRzYCZYkJdevXzYfPGFC6iSS9A2LYElSk/vZz7Lt0vyFoKRCYREsSWpyBx0ES5bAY4+lTiJJGYtg
   SVKTa9YMzjrLwzMkFQ4XxkmS8uLTT2HTTWHKFNhmm9RpJJUyF8ZJkgpG69YwahT8+c+pk0iSnWBJ
   Uh699Rb07JkdntGuXeo0kkqVnWBJUkHZeGMYPNjDMySlZydYkpRXU6fCiBHZ4RnNm6dOI6kU2QmW
   JBWcvn1h/fXhgQdSJ5FUziyCJUl5FQKceSZcemnqJJLKmeMQkqS8+/zzbLu0yZOzhXKSlEuOQ0iS
   ClLLlnDKKXDZZamTSCpXdoIlSUm4XZqkpmInWJJUsDbeGAYNgptuSp1EUjmyCJYkJTNqFFx5JfiL
   Qkn5ZhEsSUpmwICsAH7ssdRJJJUbi2BJUjIhfNMNlqR8cmGcJCmpDz6AzTbLTpDr2DF1GkmlwIVx
   kqSC1749HHoo3HBD6iSSyomdYElSctOmwbBhMHcuNLM9I6mR7ARLkorC978P660HDz2UOomkcmER
   LElKzgVykvLNcQhJUkH4+GPo3h1eeAG6dEmdRlIxcxxCklQ01lkHhg6Fa69NnURSObATLEkqGNOn
   ZztFvPqqC+QkNZydYElSUdlxR+jQASZPTp1EUqmzCJYkFZQTT3QkQlLTcxxCklRQVp4g98orsP76
   qdNIKkaOQ0iSik779jB4MNxyS+okkkqZRbAkqeCsHInwF4iSmopFsCSp4Oy1V7Zv8LPPpk4iqVRZ
   BEuSCk6zZnD88S6Qk9R0XBgnSSpICxZA797w5pvQpk3qNJKKiQvjJElFa5NNoG9fuPPO1EkklSKL
   YElSwTrxRLjuutQpJJUixyEkSQXr88+zjvCTT0KPHqnTSCoWjkNIkopay5YwYoTdYEm5ZydYklTQ
   Zs6EIUPg9dezXSMkqTZ2giVJRa9Xr+z45EceSZ1EUimxCJYkFbyRI+Gmm1KnkFRKHIeQJBW8xYth
   662zPYPbtk2dRlKhcxxCklQSOnWCPfZwz2BJuWMRLEkqCsce60iEpNxxHEKSVBQ++wy6dIHp06Fb
   t9RpJBUyxyEkSSWjVSs48kgYMyZ1EkmlwCJYklQ0Vo5E+ItFSY1lESxJKhp9+2Yfn3oqbQ5Jxc8i
   WJJUNELI9gy+8cbUSSQVOxfGSZKKyhtvwI47wqJF0LJl6jSSCpEL4yRJJadbN9hhB7jvvtRJJBUz
   i2BJUtE59lhHIiQ1juMQkqSis3QpbLIJzJkDHTumTiOp0DgOIUkqSW3bwpAhcNttqZNIKlYWwZKk
   onT00XDzzalTSCpWFsGSpKK0zz4wfz7MnZs6iaRiZBEsSSpKFRUwdCjcckvqJJKKkUWwJKloHX10
   VgS77lpSfVkES5KK1s47Q7NmMG1a6iSSio1FsCSpaIXwTTdYkurDfYIlSUXtlVdg113hzTdhrbVS
   p5FUCNwnWJJU8nr0yB4PPZQ6iaRiYhEsSSp6I0a4Z7Ck+nEcQpJU9N59F7bcMhuJaNs2dRpJqTkO
   IUkqCxtuCLvvDnffnTqJpGJhESxJKgkeoyypPhyHkCSVhGXLoEsXmD0bOnVKnUZSSo5DSJLKRps2
   cNBBMG5c6iSSioFFsCSpZIwY4cEZkurGIliSVDL23hsWLICXX06dRFKhq7UIDiEMCiHMDiHMDSGc
   U8N13w8hfBlC+GFuI0qSVDcVFTB0qN1gSbWrsQgOITQHLgMGAT2BYSGEbdZw3cXARKDGIWRJkprS
   yl0iXIstqSa1dYL7APNijK/HGJcD44CDV3Pdj4HxwLs5zidJUr3stBO0aAFTp6ZOIqmQ1VYEdwEW
   VHv9ZtXnvhZC6EJWGF9R9Sn/31uSlEwIMHy4IxGSalZRy9frUtD+ETg3xhhDCIEaxiFGjx799fPK
   ykoqKyvr8PaSJNXP8OHQvz/84Q+w1lqp00hqalOmTGHKlCn1+jM1HpYRQugHjI4xDqp6fR6wIsZ4
   cbVrXuWbwncDYBlwcozx3lXey8MyJEl5078//PKXMHhw6iSS8i0Xh2U8A2wZQtg0hNACOAr4VnEb
   Y9w8xrhZjHEzsrngH61aAEuSlG/uGSypJjUWwTHGL4EzgEnAv4DbYoyzQginhhBOzUdASZIa4sgj
   4f77YenS1EkkFaIaxyFy+o0ch5Ak5dngwVlHeMSI1Ekk5VMuxiEkSSpajkRIWhM7wZKkkrV0KXTt
   mh2j3LFj6jSS8sVOsCSprLVtCwccALffnjqJpEJjESxJKmmOREhaHcchJEklbfly6NIFnnwSevRI
   nUZSPjgOIUkqe2utlW2XNnZs6iSSColFsCSp5K0cifAXkpJWsgiWJJW8fv2ysYjnnkudRFKhsAiW
   JJW8EGD4cBfISfqGC+MkSWVh9mzYe29YsACaN0+dRlJTcmGcJElVvvc92HhjeOSR1EkkFQKLYElS
   2Rgxwl0iJGUch5AklY1Fi2C77bKPrVqlTiOpqTgOIUlSNZ07w047wd/+ljqJpNQsgiVJZcVjlCWB
   4xCSpDLz4YfQrRu8/jq0b586jaSm4DiEJEmrWG892G8/GD8+dRJJKVkES5LKjiMRkhyHkCSVnc8/
   zxbJPf88bLJJ6jSScs1xCEmSVqNlSzjsMLj11tRJJKViESxJKkuOREjlzSJYklSW9tgDPvgAXnwx
   dRJJKVgES5LKUrNmMGyY3WCpXLkwTpJUtmbOhAMPhNdey4piSaXBhXGSJNWgVy9Yd114/PHUSSTl
   m0WwJKmsuUBOKk+OQ0iSytr8+bDzzrBoEbRokTqNpFxwHEKSpFp07w49e8LEiamTSMoni2BJUtlz
   JEIqP45DSJLK3r//DZtvDm+8kS2Uk1TcHIeQJKkOOnSAPfeEu+5KnURSvlgES5KEIxFSuXEcQpIk
   4NNPoXNnmDULNtoodRpJjeE4hCRJddS6NRx8MIwblzqJpHywCJYkqYojEVL5sAiWJKnK3nvDm2/C
   yy+nTiKpqVkES5JUpXlzGDrUbrBUDiyCJUmqZuVIhGu5pdJmESxJUjU775x1hKdNS51EUlOyCJYk
   qZoQXCAnlQP3CZYkaRXz5sFuu8HChVBRkTqNpPpyn2BJkhpgiy1gs83goYdSJ5HUVCyCJUlaDUci
   pNLmOIQkSavxzjuw1VbZSMTaa6dOI6k+HIeQJKmBOnaE/v3h3ntTJ5HUFCyCJUlag6OPhjFjUqeQ
   1BQch5AkaQ2WLYMuXeCll6Bz59RpJNWV4xCSJDVCmzZw2GEukJNKkUWwJEk1OO44uOEGj1GWSo1F
   sCRJNdgGqAC+AAAQ00lEQVRtN/j8c3jmmdRJJOWSRbAkSTUIAY49NusGSyodLoyTJKkW8+fDzjtn
   ewa3bJk6jaTauDBOkqQc6N4deveG++5LnURSrlgES5JUB45ESKXFcQhJkurgk0+ga1eYNQs22ih1
   Gkk1cRxCkqQcWXttOPRQ9wyWSoVFsCRJdbRyJMJfbErFzyJYkqQ62mOPbCziuedSJ5HUWBbBkiTV
   UbNmWTf4xhtTJ5HUWC6MkySpHl57Dfr0gTffdM9gqVC5ME6SpBzbbDPYfnu4997USSQ1hkWwJEn1
   dNJJcM01qVNIagzHISRJqqfPPsv2DH7mGdh009RpJK3KcQhJkppAq1YwfDhcd13qJJIayk6wJEkN
   MHMmDB4M8+dD8+ap00iqzk6wJElNpFcv6NIFJk1KnURSQ1gES5LUQCedBFdfnTqFpIZwHEKSpAb6
   +GPo1g1mzYKNNkqdRtJKjkNIktSE1lkHDjvME+SkYmQnWJKkRpg6FY45Bl5+GUKNfSdJ+WInWJKk
   Jta3b3Z88j/+kTqJpPqwCJYkqRFC8AQ5qRg5DiFJUiO9/z706AGvvgodOqROI8lxCEmS8mD99WHI
   ELjhhtRJJNWVnWBJknLgiSfg2GNhzhxoZotJSspOsCRJedK/P7RpA5Mnp04iqS4sgiVJyoEQ4LTT
   4C9/SZ1EUl04DiFJUo4sXZqdIDdzJnTtmjqNVL4ch5AkKY/atoXhw+Gvf02dRFJt7ARLkpRDL70E
   ++4L8+fDWmulTiOVp5x1gkMIg0IIs0MIc0MI56zm6yNCCDNCCDNDCI+HEHo1NLQkScVs221hyy3h
   7rtTJ5FUk1qL4BBCc+AyYBDQExgWQthmlcteBQbEGHsB/wX4iyBJUtlygZxU+OrSCe4DzIsxvh5j
   XA6MAw6ufkGM8ckY44dVL58CXA4gSSpbhx4Ks2ZlD0mFqS5FcBdgQbXXb1Z9bk1OBB5oTChJkopZ
   ixZw0klw+eWpk0hak7oUwXVezRZC2As4AfjO3LAkSeXktNNg7FhYsiR1EkmrU1GHaxYCm1R7vQlZ
   N/hbqhbDXQ0MijF+sLo3Gj169NfPKysrqaysrEdUSZKKR+fOMHgwXHstnHVW6jRSaZsyZQpTpkyp
   15+pdYu0EEIFMAfYB1gETAOGxRhnVbumG/AwcHSMceoa3sct0iRJZeWZZ+Dww2HePKioS9tJUk7k
   ZIu0GOOXwBnAJOBfwG0xxlkhhFNDCKdWXXYB0B64IoQwPYQwrZHZJUkqervskp0cd889qZNIWpWH
   ZUiS1ITGj4c//Qkeeyx1Eql8eGyyJEmJHXIIvPFGNhohqXBYBEuS1IQqKuDHP866wZIKh+MQkiQ1
   sQ8+gB494MUXs10jJDUtxyEkSSoA7dvD8OFwxRWpk0hayU6wJEl58PLLsPvu8Prr0KZN6jRSabMT
   LElSgdhqK9htN7juutRJJIGdYEmS8mbqVBg2DObO9fAMqSnZCZYkqYD06wfdusHtt6dOIskiWJKk
   PDrnHLj4YvCXo1JaFsGSJOXR/vtnBfDEiamTSOXNIliSpDwK4ZtusKR0LIIlScqzo47KtkqbOjV1
   Eql8WQRLkpRnFRVw1llw0UWpk0jlyy3SJElKYNmy7CjliROhd+/UaaTS4hZpkiQVqDZt4Oyz4Ve/
   Sp1EKk92giVJSmRlN3jSJOjVK3UaqXTYCZYkqYC1aQM/+5ndYCkFO8GSJCX0ySdZN/jvf7cbLOWK
   nWBJkgrc2mtn3eD/+q/USaTyYidYkqTEVnaDH3wQtt8+dRqp+NkJliSpCKzsBo8enTqJVD7sBEuS
   VACWLYMtt4QJE6Bv39RppOJmJ1iSpCLRpk3WCT73XLBnJDU9i2BJkgrE8cfDW29l+wZLaloWwZIk
   FYiKCvj1r7Nu8IoVqdNIpc0iWJKkAvLDH0LLljBuXOokUmlzYZwkSQVmyhQ44QSYPRtatEidRio+
   LoyTJKkIVVbC1lvDlVemTiKVLjvBkiQVoBdfhL33hlmzYP31U6eRiktdOsEWwZIkFagzzoAQ4M9/
   Tp1EKi4WwZIkFbH334dttoGHH4bttkudRioezgRLklTE1l8fLrgAfvpTD9CQcs0iWJKkAjZqFLz9
   Ntx7b+okUmlxHEKSpAL30ENw6qnZYrnWrVOnkQqf4xCSJJWAgQNhl12y0+Qk5YadYEmSisBbb0Gv
   XvCPf0DPnqnTSIXNTrAkSSVi441h9OhsRnjFitRppOJnESxJUpEYNQo+/xxuuCF1Eqn4OQ4hSVIR
   ef552G+/bJFcx46p00iFycMyJEkqQeeeC/PmwR13ZCfKSfo2Z4IlSSpBo0fDrFlw222pk0jFy06w
   JElF6OmnYcgQmDEDNtoodRqpsDgOIUlSCfvFL7LZ4LvucixCqs5xCEmSStgvfwmvvgpjxqROIhUf
   O8GSJBWxGTOyE+WefBK22CJ1Gqkw2AmWJKnE9e4NF14Iw4bBF1+kTiMVDzvBkiQVuRjh0EOzTvAl
   l6ROI6XnwjhJksrE++/DDjvAX/8K+++fOo2UluMQkiSVifXXh5tvhuOPh/nzU6eRCp9FsCRJJWLP
   PeE//gN++EP49NPUaaTC5jiEJEklJEYYMQLWWgtuuMH9g1WeHIeQJKnMhADXXAPPPw+XXZY6jVS4
   KlIHkCRJudWmTXaKXP/+8L3vwb77pk4kFR47wZIklaDNN4c77shGI154IXUaqfBYBEuSVKIGDIA/
   /QkOOAAWLkydRiosjkNIklTChg3Ltkw74AB49FFYd93UiaTC4O4QkiSVuBjhtNNgzhy4/35o3Tp1
   IqlpeWKcJEkC4KuvYORI+Pe/4e67oWXL1ImkpmMRLEmSvvbll3DUUVln+PbbocKhSJUo9wmWJElf
   q6iAW2+Fzz6DY46B5ctTJ5LSsQiWJKmMtGgBd94JH30ERxyRFcRSObIIliSpzLRunR2m0aIFHHgg
   fPJJ6kRS/lkES5JUhlq0yEYjunXLTpR7//3UiaT8sgiWJKlMNW8OV18Ne+yRHbE8d27qRFL+WARL
   klTGmjWDiy+Gs8/OiuFHH02dSMoPi2BJksTJJ8PNN8Phh2fdYXc1Valzn2BJkvS12bOzQniXXeAv
   f4E2bVInkurPfYIlSVK9fO978NRT2cEafftmRy1LpcgiWJIkfcvaa8OYMXDGGbDbbnDFFY5HqPQ4
   DiFJktZo1iwYORI6dIBrr4WuXVMnkmrnOIQkSWqUbbaBJ56A3XeHnXaCK6+Er75KnUpqPDvBkiSp
   Tl54AX70I/jii2xEYuedUyeSVs9OsCRJypntt8/2ET7tNDjggGxbtYULU6eSGsYiWJIk1VmzZnDc
   cdms8PrrQ69ecN55sGRJ6mRS/VgES5KkemvfHi66CGbMgHfegR494PzzYfHi1MmkurEIliRJDda1
   a7ZrxNNPw4cfZgvpTj8d5s1LnUyqmUWwJElqtM03h8svz8Yk2rWDXXeFffeFO+7IFtJJhcbdISRJ
   Us59/jlMmABXXZUdxTx8OBx1FPTpA6HGNftS49VldwiLYEmS1KTmzIGxY+G227Li+Mgj4eCDs4K4
   oiJ1OpUii2BJklQwYoSZM7Ni+IEH4I03YOBAGDQoG53YZJPUCVUqLIIlSVLBWrQI/v53mDgRHn4Y
   WraE3XbL5on798/2JW7VKnVKFaOcHJYRQhgUQpgdQpgbQjhnDddcWvX1GSGEHRsaWHU3ZcqU1BFK
   hvcyt7yfueX9zB3vZW7l4n527pztOTxuXLa12iOPwODB8NJLcOKJ2TZsPXvC0KHw61/DvfdmC+8+
   +6zR37rg+POZfzUWwSGE5sBlwCCgJzAshLDNKtcMBraIMW4JnAJc0URZVY3/suSO9zK3vJ+55f3M
   He9lbuX6foYAW2wBI0dmi+lmzswO4Lj1VhgyJNt+7Yorslnidu2yrdkGDMiK6AsvhCuvhHvugaee
   ysYsPv88p/GanD+f+VfbOHofYF6M8XWAEMI44GBgVrVrDgJuBIgxPhVCaBdC6BRjdLtsSZLUYC1b
   Qu/e2aO6r77Kjmt+9VV45ZWs6H3uOXj7bXjrrezj4sWw9tpZwdy+ffax+vP11su+3qbNtx+tW3/7
   dYsWsNZa3zxWvm7e3F0uil1tRXAXYEG1128CfetwTVfAIliSJOVc8+bQrVv2qKxc/TUrVmSd5CVL
   4IMPVv98yRL49FNYtmzNjy++gOXLv/v46qtvF8fVH82affsRQu2fW7gwm49e3XWrFts1va7PtfV5
   r3794Be/WP29LlY1LowLIRwGDIoxnlz1+migb4zxx9WuuQ+4KMb4eNXrh4D/iDE+t8p7uSpOkiRJ
   eVHbwrjaOsELgeoblmxC1umt6ZquVZ+rVxBJkiQpX2rbHeIZYMsQwqYhhBbAUcC9q1xzLzASIITQ
   D1jiPLAkSZIKWY2d4BjjlyGEM4BJQHPg2hjjrBDCqVVfvyrG+EAIYXAIYR7wCXB8k6eWJEmSGiFv
   h2VIkiRJhaLWwzJyLYRwVghhRQihQ76/dykJIfxX1eEkz4cQJocQPGyyEUIIvwshzKq6pxNCCOul
   zlTMQghHhBBeCiF8FULYKXWeYlSXg4pUNyGE60IIi0MIL6TOUgpCCJuEEB6p+nf8xRDCmakzFasQ
   QqsQwlNVf5f/K4Tw29SZSkEIoXkIYXrV5g1rlNciuKpQ2xeYn8/vW6L+J8bYO8a4A3A3cGHqQEXu
   78C2McbewMvAeYnzFLsXgEOBR1MHKUZ1OahI9XI92b1UbiwH/l+McVugH3C6P58NE2P8DNir6u/y
   XsBeIYTdE8cqBT8B/gXUOO6Q707w74H/yPP3LEkxxo+rvWwLvJcqSymIMT4YY1xR9fIpsl1O1EAx
   xtkxxpdT5yhiXx9UFGNcDqw8qEgNEGN8DPggdY5SEWN8O8b4fNXzpWQHaHVOm6p4xRiXVT1tQbb+
   6t8J4xS9EEJXYDBwDVDjzmR5K4JDCAcDb8YYZ+bre5a6EMKvQwhvAMcCF6XOU0JOAB5IHUJlbXWH
   EHVJlEVaoxDCpsCOZM0DNUAIoVkI4XmyQ8YeiTH+K3WmIvcH4GxgRW0X1rZPcL2EEB4ENlrNl35O
   9uvl/apfnsvvXYpquJ/nxxjvizH+HPh5COFcsn/o7sxRg9ruZ9U1Pwe+iDGOzWu4IlSX+6kGc8Wy
   Cl4IoS0wHvhJVUdYDVD1W8gdqtaiTAohVMYYpySOVZRCCEOAd2KM00MIlbVdn9MiOMa47xpCbQds
   BswI2Rl8XYFnQwh9Yozv5DJDKVnT/VyNsdi5rFVt9zOEcBzZr1D2yUugIlePn0/VX10OKpKSCSGs
   BdwJ3BxjvDt1nlIQY/wwhHA/sAswJXGcYrUrcFAIYTDQClg3hHBTjHHk6i7OyzhEjPHFGGOnGONm
   McbNyP5jvpMFcMOFELas9vJgYHqqLKUghDCI7NcnB1ctVFDu+Fuf+qvLQUVSEiHrZl0L/CvG+MfU
   eYpZCGGDEEK7quetyTYP8O/zBooxnh9j3KSq1hwKPLymAhgSbJFWxV/1Nd5vQwgvVM0RVQJnJc5T
   7P5MtsDwwaptVf6SOlAxCyEcGkJYQLZy/P4Qwv+lzlRMYoxfAisPKvoXcFuMcVbaVMUrhHAr8ASw
   VQhhQQjB0bHG2Q04mmwng+lVD3ffaJiNgYer/i5/Crgvxjg5caZSUmO96WEZkiRJKjupOsGSJElS
   MhbBkiRJKjsWwZIkSSo7FsGSJEkqOxbBkiRJKjsWwZIkSSo7FsGSJEkqO/8f7jvEAmMRHcoAAAAA
   SUVORK5CYII=
   "
   >
   </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>