{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Python - Librerías esenciales para el analisis de datos"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*Esta notebook fue creada originalmente como un blog post por [Raúl E. López Briega](http://relopezbriega.com.ar/) en [Mi blog sobre Python](http://relopezbriega.github.io). El contenido esta bajo la licencia BSD.*"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "En mi [artículo anterior](http://relopezbriega.github.io/blog/2014/05/25/mi-python-blog-introduccion-a-python/) hice una breve introducción al mundo de [Python](http://python.org/), hoy voy a detallar algunas de las librerías que son esenciales para trabajar con [Python](http://python.org/) en la comunidad científica o en el análisis de datos. \n",
    "\n",
    "Una de las grandes ventajas que ofrece [Python](http://python.org/) sobre otros lenguajes de programación, además de que es que es mucho más fácil de aprender; es lo grande y prolifera que es la comunidad de desarrolladores que lo rodean; comunidad que ha contribuido con una gran variedad de librerías de primer nivel que extienden la funcionalidades del lenguaje. Vamos a poder encontrar una librería en [Python](http://python.org/) para prácticamente cualquier cosa que se nos ocurra.\n",
    "\n",
    "Algunas de las librerías que se han vuelto esenciales y ya forman casi parte del lenguaje en sí mismo son las siguientes:"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Numpy"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[Numpy](http://www.numpy.org/), abreviatura de Numerical [Python](http://python.org/) , es el paquete fundamental para la computación científica en [Python](http://python.org/). Dispone, entre otras cosas de:\n",
    "\n",
    "* Un objeto <a href='http://es.wikipedia.org/wiki/Matriz_(matem%C3%A1ticas)' target='_blank'>matriz</a> multidimensional *ndarray*,rápido y eficiente.\n",
    "* Funciones para realizar cálculos elemento a elemento u otras operaciones matemáticas con <a href='http://es.wikipedia.org/wiki/Matriz_(matem%C3%A1ticas)' target='_blank'>matrices</a>. \n",
    "* Herramientas para la lectura y escritura de los conjuntos de datos basados <a href='http://es.wikipedia.org/wiki/Matriz_(matem%C3%A1ticas)' target='_blank'>matrices</a>.\n",
    "* Operaciones de [álgebra lineal](http://es.wikipedia.org/wiki/%C3%81lgebra_lineal), [transformaciones de Fourier](http://es.wikipedia.org/wiki/Transformada_de_Fourier), y generación de números aleatorios.\n",
    "* Herramientas de integración para conectar [C](http://es.wikipedia.org/wiki/C_(lenguaje_de_programaci%C3%B3n), [C++](http://es.wikipedia.org/wiki/C%2B%2B) y [Fortran](http://es.wikipedia.org/wiki/Fortran) con [Python](http://python.org/)\n",
    "\n",
    "Más allá de las capacidades de procesamiento rápido de <a href='http://es.wikipedia.org/wiki/Matriz_(matem%C3%A1ticas)' target='_blank'>matrices</a> que [Numpy](http://www.numpy.org/) añade a [Python](http://python.org/), uno de sus\n",
    "propósitos principales con respecto al análisis de datos es la utilización de sus [estructuras de datos](http://es.wikipedia.org/wiki/Estructura_de_datos) como contenedores para transmitir los datos entre diferentes algoritmos. Para datos numéricos , las <a href='http://es.wikipedia.org/wiki/Matriz_(matem%C3%A1ticas)' target='_blank'>matrices</a> de [Numpy](http://www.numpy.org/) son una forma mucho más eficiente de almacenar y manipular datos que cualquier otra de las [estructuras de datos](http://es.wikipedia.org/wiki/Estructura_de_datos) estándar incorporadas en [Python](http://python.org/). Asimismo, librerías escritas en un lenguaje de bajo nivel, como [C](http://es.wikipedia.org/wiki/C_(lenguaje_de_programaci%C3%B3n) o [Fortran](http://es.wikipedia.org/wiki/Fortran), pueden operar en los datos almacenados en <a href='http://es.wikipedia.org/wiki/Matriz_(matem%C3%A1ticas)' target='_blank'>matrices</a> de [Numpy](http://www.numpy.org/) sin necesidad de copiar o modificar ningún dato.\n",
    "\n",
    "Como nomenclatura general, cuando importamos la librería [Numpy](http://www.numpy.org/) en nuestro programa [Python](http://python.org/) se suele utilizar la siguiente:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Creando matrices en Numpy"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Existen varias maneras de crear matrices en Numpy, por ejemplo desde:\n",
    "\n",
    "* Una *lista* o *tuple* de [Python](http://python.org/)\n",
    "* Funciones específicas para crear matrices como `arange`, `linspace`, etc.\n",
    "* Archivos planos con datos, como por ejemplo archivos .csv\n",
    "\n",
    "En [Numpy](http://www.numpy.org/) tanto los vectores como las matrices se crean utilizando el objeto `ndarray`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 2, 3, 4])"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Creando un vector desde una lista de Python\n",
    "vector = np.array([1, 2, 3, 4])\n",
    "\n",
    "vector"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1, 2],\n",
       "       [3, 4]])"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Para crear una matriz, simplemente le pasamos una lista anidada al objeto array de Numpy\n",
    "matriz = np.array([[1, 2],\n",
    "                   [3, 4]])\n",
    "\n",
    "matriz"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(numpy.ndarray, numpy.ndarray)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#El tipo de objeto de tanto de los vectores como de las matrices es ndarray\n",
    "type(vector), type(matriz)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(4,) 4\n",
      "(2, 2) 4\n"
     ]
    }
   ],
   "source": [
    "#Los objetos ndarray de Numpy cuentan con las propiedades shape y size que nos muestran sus dimensiones.\n",
    "print vector.shape, vector.size\n",
    "\n",
    "print matriz.shape, matriz.size"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Utilizando funciones para crear matrices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#arange\n",
    "#La funcion arange nos facilita la creación de matrices\n",
    "x = np.arange(1, 11, 1) # argumentos: start, stop, step\n",
    "\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([  1.,   2.,   3.,   4.,   5.,   6.,   7.,   8.,   9.,  10.,  11.,\n",
       "        12.,  13.,  14.,  15.,  16.,  17.,  18.,  19.,  20.,  21.,  22.,\n",
       "        23.,  24.,  25.])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#linspace\n",
    "#linspace nos devuelve un vector con la cantidad de muestras que le ingresemos y separados uniformamente entre sí.\n",
    "np.linspace(1, 25, 25)  # argumentos: start, stop, samples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 0, 0, 0, 0],\n",
       "       [1, 1, 1, 1, 1],\n",
       "       [2, 2, 2, 2, 2],\n",
       "       [3, 3, 3, 3, 3],\n",
       "       [4, 4, 4, 4, 4]])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#mgrid\n",
    "#Con mgrid podemos crear arrays multimensionales.\n",
    "x, y = np.mgrid[0:5, 0:5] \n",
    "\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 1, 2, 3, 4],\n",
       "       [0, 1, 2, 3, 4],\n",
       "       [0, 1, 2, 3, 4],\n",
       "       [0, 1, 2, 3, 4],\n",
       "       [0, 1, 2, 3, 4]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.,  0.,  0.],\n",
       "       [ 0.,  0.,  0.],\n",
       "       [ 0.,  0.,  0.]])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#zeros y ones\n",
    "#Estas funciones nos permiten crear matrices de ceros o de unos.\n",
    "np.zeros((3,3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1.,  1.,  1.],\n",
       "       [ 1.,  1.,  1.],\n",
       "       [ 1.,  1.,  1.]])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.ones((3,3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1.39342127,  0.27553779,  1.60499887,  0.49998319,  0.70528917],\n",
       "       [ 0.77384386,  0.13082401, -0.94628073,  1.11938778, -0.03671148],\n",
       "       [-1.26643358, -0.49647634,  0.02653584,  1.69748904,  0.83353017],\n",
       "       [ 2.37892618, -1.21239237,  1.12638933,  1.70430737,  0.50932112],\n",
       "       [-0.67529314, -0.48119409, -0.6064923 ,  0.03554073, -0.29703706]])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#random.randn\n",
    "#Esta funcion nos permite generar una matriz con una distribución estándar de números.\n",
    "np.random.randn(5,5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1, 0, 0],\n",
       "       [0, 1, 0],\n",
       "       [0, 0, 1]])"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#diag\n",
    "#Nos permite crear una matriz con la diagonal de números que le ingresemos.\n",
    "np.diag([1,1,1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Matplotlib"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[Matplotlib](http://matplotlib.org/) es la librería más popular en [Python](http://python.org/) para visualizaciones y gráficos. [Matplotlib](http://matplotlib.org/) puede producir gráficos de alta calidad dignos de cualquier publicación científica.\n",
    "\n",
    "Algunas de las muchas ventajas que nos ofrece [Matplotlib](http://matplotlib.org/), incluyen:\n",
    "\n",
    "* Es fácil de aprender.\n",
    "* Soporta texto, títulos y etiquetas en formato $\\LaTeX$.\n",
    "* Proporciona un gran control sobre cada uno de los elementos de las figuras, como ser su tamaño, el trazado de sus líneas, etc.\n",
    "* Nos permite crear gráficos y figuras de gran calidad que pueden ser guardados en varios formatos, como ser: PNG, PDF, SVG, EPS, y PGF.\n",
    "\n",
    "[Matplotlib](http://matplotlib.org/) se integra de maravilla con [IPython](http://ipython.org/) (ver más abajo), lo que nos proporciona un ambiente confortable para las visualizaciones y la exploración de datos interactiva.\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Algunos gráficos con Matplotlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#Generalmente se suele importar matplotlib de la siguiente forma.\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Ahora vamos a graficar la siguiente función.\n",
    "\n",
    "$$f(x) = e^{-x^2}$$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Definimos nuestra función.\n",
    "def f(x):\n",
    "    return np.exp(-x ** 2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#Creamos un vector con los puntos que le pasaremos a la funcion previamente creada.\n",
    "x = np.linspace(-1, 5, num=30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYcAAAEgCAYAAABfB78oAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f8f96aa6ed0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Representeamos la función utilizando el objeto plt de matplotlib\n",
    "plt.xlabel(\"Eje $x$\")\n",
    "plt.ylabel(\"$f(x)$\")\n",
    "plt.legend()\n",
    "plt.title(\"Funcion $f(x)$\")\n",
    "plt.grid(True)\n",
    "fig = plt.plot(x, f(x), label=\"Función f(x)\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWEAAAEACAYAAABiV8coAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzsnXdYFFcXh9+tFBEFUVFBwd7Fjl3E3o01Vuwx9pZoNBpN\nMcZoLMmnRo1GY8Peu2IXG/aOYkFBQDosbJnvjwVsoCu7wCLz+tzHnZ07c347O5y9c+6594KIiIiI\niIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiFliCfgCV4BbwKyslSMiIiKS87BO+l8O\nnAPqZ6EWERERkWyF1ATniEv6XwnIgFcmOKeIiIhIjsAUTliKPhwRDBxDH5YQEREREclk8qAPRzTO\nYh0iIiIi2QZTtISTiQT2ADXefLNw4cICIBaxiEUshpQHGIvM4lPsvRs+dUb/RH8TuAGMSsVCY/T+\nzi+pTDVasxE4AHmTXlsBJwDPd+oIWc306dOzWoIgCOahwxw0CIJ56DAHDYJgHjrMQYMgCMmO0VgE\ny6ojDSqp2HME3JJe2wB3gXLv1GkM7DSBTkCf0WAMhYB/0beopcAa4IixokxNQEBAVksAzEOHOWgA\n89BhDhrAPHSYgwaTIpGk98igpAIQA9wGCif9/5aF9Bp4F2Od8HWgmimEiIiIiJgMiUkirS5AVfRj\nId5EAOoCV4FAYAJGJCQY64SzBV5eXlktATAPHeagAcxDhzloAPPQYQ4aTIpUZuwZbIDNwGj0LeI3\nuYw+dhwHtAK2A6XTa8hkTeoPkBTqEREREfkwEn0YwVi/JFjWmpDqDm3UE3RRT19vPz+bmj0FsBvY\nB8w3wN4joDrpHCNhyuwIs8XHxyerJQDmocMcNIB56DAHDWAeOsxBg0mRSFMtsjwuKJwbpJTUjgRW\noA8vpOWAC/LacddKep3uQWo5IhwhIiKSw0h/x1w9oDdwDX36GcB3QNGk10uBLsAwQIM+JNEj3ToR\nwxEiIiJmhMnCEXUmG1RRdXaWKewZhdgSFhER+fxIf0s40xFjwpmIOegwBw1gHjrMQQOYhw5z0GBS\n0ogJv1fMALElLCIi8vlhfIpapiHGhEVERMwGk8WEG84wqKLqxHRT2DMKsSUsIiLy+SEVY8JmhbnE\nu8xBhzloAPPQYQ4awDx0mIMGkyLGhEVERESykGyUHSHGhEVERMwGk8WEPQ1bc1h1ZLIp7BmF2BIW\nERH5/MhGLWHzCIpkMOYS7zIHHeagAcxDhzloAPPQYQ4aTIpUZlgxA8SWsIiIyOeHmXS6GYIYExYR\nETEbTBYTbjnPoIqq/eNMYc8oxJawiIjI50c2aglnH6VGYC7xLnPQYQ4awDx0mIMGMA8d5qDBpEgk\nhhUzQGwJi4iIfH5ko5awGBMWyZEkJiZy/PhxwsPDcXJyok6dOsnxSJEsxGQx4bZ/GVRRtXu4KewZ\nhdgSFslRCILA7N9+Y968P3B0Kkq+Ao488b+PRNDyy88/0a1bt6yWKGIK0p9+5gysBgqgX1X5b2Bh\nKvUWol/kMw7w4vUqHJ9M9mmzG4G5xLvMQYc5aICs0SEIAsNHjGDtxs3MWrGVvqOm8N28f1i8/QTD\nvp/DmHETWLZsWabrMofvxBw0mJT0x4TVwFigAuAODAfKvVOnNVASKAUMARYbI1VsCYvkGM6dO8eO\nnbv5a6sPUeFhLJk9i9ioOMq5VWbk9zP4edkmxnzZki5dumBnZ5fVckWMIf0x4aCkAvql7m8DhZP+\nT6Y98G/Sa18gL/rFP4PTY1CMCedgBEHAx8eHAwcP4pAvH7169aJQoUJZLSvD6N2nL7kKlaRVl954\ntfIgOuJrdDpPFIrFFC97n4UbtjBn0te0aVKPMWPGZLXcHInJYsKdlhtUUbVt0IfsuQDH0beKY954\nfxcwCziTtH0Y+Ba49OlSxZZwjkUQBHr16cv27QfQaASkMgXTZ8xg7+7dNGrUKKvlZQiX/fwY1ak/\nN/3Oo04sjk73LQBq9d88vJufiFehVK5Vn0uXL2exUhFjSauTVRtyB13IXUNOYQNsBkbztgNOMfHO\ndrpbmmJMOBMxBx3JGg4dOsT2HQdRq2uiTjhNQtwKEhIU9Ozdh8x4csmKayGXy0lMTERpYYmgiwCO\nJu2JRadLRKFQolGrkcszt21iTvfF54JEIkm1yAuUQ1mhY0pJAwWwBfgP2J7K/kD0HXjJOCW9ly5y\nhBMWeZ/de/aSmJCAJnEJUBpohU47kPDwcB4+fJjV8jIETw8PzhzZQ8VqtSlc1AK5fAawGAvLFni2\n64qNbR7OHtlNs6aeWS1VxEgkUolBJbVDgRXALWB+GqffCfRNeu0ORJDOeHCyQWMwJJ1DjAmbIdOm\nT+fX2YtRJ+wA6gAgV/RAKt3B0yePKVCgQNYKzADu379PLXd3/li7j3wFHNm8cgnPAp5RoVoV2nTr\nw+Wzx5k/dRRPHgdgYWGR1XJzJKaKCdt0W2VQxRhvr3ft1QdOANd4HWL4Diia9Hpp0v9/Ai2BWKA/\nkO4YlrEf1jGpXEEfQ7kEdOTtnkTRCZsh/v7+VKrsRqI6F1r110jlD5DL99GwYXUOHdif1fIyjL+X\nLeP7aT/gNWYKDVu0R2lhSXRkBAe2rGXzyj/Zvm0rDRo0yGqZORZTOeHc3f/9eC0gemM/U9gzCmPD\nEUHoHTC8nc5hVphLvMscdCRrKFGiBBvWryV3bjU2eRYil2+hTp3KbFi3NlN1ZDZDBg9m3X+ruXh4\nO13qlKZfs2r0bVaN6Of3OXHcJ0scsDndF58LacWE3y3mgCl7IFyAqujz5kSyAe3bt+dlUBC3b9/G\nzs4OZ2fnjx/0GeDp6Ymnpye7du2iUqVKODg4YGNjk9WyREyJefhXgzCVVBvAB/iJ93sTxXCEiIiI\nQZgqHJGn5xqDKkau62MKe0Zhipbwx9I58PLywsXFBYC8efPi5uZG48aNgdePQeK2uC1u57zt+fPn\nc+XKlRT/YCrMJdRgCMYqlaAfvheGfrx1amR5S9jHxyflS8/pOsxBg7noMAcN5qLDHDSA6VrC9n3W\nGVTx1ZqeprBnFMa2hOsBvdGncyTPIjQZ+Hy710WyBQ8ePGDr1q2EhISSJ48tbdq0oWrVqlktSySz\nyD4NYXHuCJHPi/v37+M1aCh+fn5QuCYaeW5k2nhkQZdwLebMsiV/4u7untUyRdLAVC3hfP3WG1Qx\n7N8vTWHPKMS5I0Q+G27dukXdBo1ROTdF6jkbiUyBImmfrtwX3Ht2Ac/mrdi1fQtNmjTJUq0iGUt2\nignniGHLyZ0BWY056DAHDWB6HTqdjpZt2qMq0QFZyWZIZIq39kukMuRF3dG6DabjF12Jior6bK9F\ndtVgSnJqnrCISJZx4MABIhMkSJ31Q7B18eEkXliPLuIxklwFsajZHaltEWQFyiFxKM3q1aupWLFi\nFqsWyTDMw78ahBgTFvksaNO+E4cD8yB3bYQg6FAd/AUhpjv6hQ/2gHIGVi2nI1FYo315m2JhB7h7\n82pWyxZ5B1PFhAsM9Dao4ssV3UxhzyhyRDhC5PPnYcBjJLZFABDiwhDiY4Gf0Q/kHA664ujCAwCQ\n2hbmReCzLFIqkhlIpVKDijlgHioyGHOJd5mDDnPQAKbXoVAoQKcBQCK3ACEWiEzaqwbhJcgtARB0\nWuQKxWd7LbKrBlOSnWLCOcIJi3z+NKzrjjT0JgASC1tkLvVB1gD4GWSeSPM5ILVzAUAXfI3qNWpk\nnViRjEdiYDEDxJiwyGfB/fv3qVK9NnjOQiJTIggC2mcX0IU/QZo7P7Ji9ZFIZQiCDvnpn9myZinN\nmjXLatki72CqmHDhr7YaVPH5ki9MYc8oxJawyGdBqVKlaNu6FbKr/yDoNPqlbJxroazcBblroyQH\nLCC5tZmSzgXx9BRXz/icMSIc8Q/6VTKup3HqxujjXH5JZaqxWnOEEzaXeJc56DAHDZAxOlavWkHt\nUvmQ+85F89wPQdAB+kVNtSF3kF36C1dlMIf270YqlX7W1yI7ajAlRjjhlehXzPgQx9FP21sV/cyR\nRiHmCYt8NlhaWrJ/z07Wr1/Pr7/P59HBNShy5UWtiqaAvR3fTBjNgAEDsLa2zmqpIhlN+gMMJ9Gn\n1GTM2TP6ZGkgxoRF2LNnD19//S1RUeG0bt2KZcsWZrgzDAwM5NWrV9jY2ODi4mI2veEiaWOqmHDR\nkTsNqvhkUfvU7LkAu4BKqRzSCNgKPEO/wvIE9IuCphuxJSyS4fj5+dG1a3/i49cCpdi6dSJq9dd4\ne6/KULtFihShSJEiGWpDxDzJwB/cy+gXOI4DWqGfQ720MScUY8KZiDnoyAoNBw4cQK3uAzQDXFCp\nFrFzp2G91xmJOXwfYB46zEGDKUkrBqwKvE6E77qUkg6i0TtggH3oF7WwN0ar2BIWyXBsbW1RKC6i\n0SS/E4ClpRiXFclA0mgIWzlXxsq5csp2pK9hU16+QUHgJSAAtZIsvUqPxGTEmLCZoNVqOXDgAAv/\nWsrDgACkUimVK1Zg7KjhuLu7Z+t4ZnR0NFWq1OHFi4okJJTGymo5y5bNpWfPL7NamoiZYaqYsOvY\nPQZVfPRHm3ftrUcf93VAn6o2HVJmRF0KDAeGARr0LeJxwDljxIpO2Ay4ePEi7Tt1IVarIN6xHtI8\nTgiCDkm4P4rAU7g4FWLPzq0ULVo0Xee/ceMGAwaM5smTJ7i71+KffxZhb2/UE9QnExUVxYoVK3j1\nKoIWLZpRv379TLUvkj0wlRMuPm6vQRUfzmttCntGIcaEM5HUdFy8eBEPz+aEFWmNus5k5K4NkdoX\nR5avJNKSLdA0nMEDoQQ1atchMDDwk22GhITQoEFzLl7sRnDwLvbsiaFly85k9g+jra0tY8eO5ccf\nZ1C/fn2z+E7MQQOYhw5z0GBKJBLDijmQI5ywuaLVamnXsTOJ5XogK5L6XAYSiRRJyRZEO9SmV9/+\nn2zj9OnT6HRVEYShQFk0mlFcvXqZV6+MCmPlKARBYO3atYwZM5HFixejVquzWpLIR5BKJQYVcyBH\ndMyZwyqy8L6O/fv3EydYpjhgQRDQPDqJ9uFFkMpRlPdA5piUqliiOb5HJuPv70+JEiUMtmltbY1O\nFwTo0P/mVkGnU2NlZWWSz5RezOE7MVTDV1+NYe3aU8TGdsXaeiubNu3l8OEdJpsKMTtdi+xCdupD\nEVvCWcjCv5YS71gvZVvz6ASa66cRouYhRHxPou8atCF3AJDIlEic67Bs+T+fZMPDw4OyZXNjadkJ\nmIO1tScjR44WR40ZSGhoKKtWrSI29igwibi4vZw/f48LFy5ktTSRDyCGI8wMc4l3vavD/+FDpHmc\nUra1Dy+CdjHQHOgM2mloAy6m7NdYF+buff9PsqlQKDh5cj8//9yY4cOfM25ce+bO/cWIT2EazOE7\nMURDbGwscrkNYJv0jgKZrCAxMTGZqiOjMQcNpkQMR4gYhFQqhaRJZgCQyIA3/7ijQSp7vSnokMk+\n/XfT0tKScePGAvo/tuz0qJbVODs74+zsiL//ZDSaQUgk+1EoAqghzkds1mSnWzxHtITNJd71ro5K\nFSsghL9u2SrKNwbZEOAvYBbIfkdeskHKfouYAKpWSW04e/o1ZBXmoMMQDfrZ1vbg4XEPB4dm1Ky5\nndOnD5EnT55M1ZHRmIMGU5KdVtYQ84SzkFOnTtGq05doGvyQckNoX95CG3AJpDLkpRqmhCuExDg4\n+h2P/O/h6OiYlbJFRDIMU+UJV/r+kEEVr//YzBT2jCJHtITNJd71ro569erh7OiA8OhIynuyAuVR\n1uqDskbP1w5YEJDd20qbtm2NdsDmei1yqgYwDx3moMGUZKeWcI5wwuaKRCJh765t2Dz3QXd/H4L2\n/fxTQR2H7OY6nBRh/LNsSeaLFBHJhmSn7AgxHGEGPHnyhC/7eOHndwWc6qDJVRghMRbh4Vl0sZEU\nLlKAkyf24erqanLbiYmJbN++nb37DwLQsnlTvvjiC5RKpcltibzNq1evuHnzJtbW1ri5uSGTyT5+\n0GeOqcIRbj8c+Xgt4MoPnqawZxSiEzYj7t27x7LlK7h9zx+fI6eIj+uOTtcdhcKb4sVPcv36Of3S\n7ibiwYMHeDZrgSS3A/mrNgEg9KoPmoggjhw8QOnSRk2TaraoVCp27NjBvXv3kMlk1KxZE09PT5MN\nvvgYMTExjBozls2bN+FUvDQxkRGgVTPr55/o1atXpmgwV0zlhKvOMMwJ+03PeidsirvuYwvjZTnm\nEu/6mI7SpUsz57fZ/Dh9ChLs0OnmA3VRq/8gMDCa27dvm0yDRqOhaYtWODbuQfGW/Xh64QJPL1zA\npWlPnJr2oWnzliQmJhpt70M6MvvHWRAEZv06m8JOzsyY+ydbjl/kwPXHDBw+muKlSrNly5YM16DV\namnVpi33gsL5avZyKjZsQbk6HnSZ+DPjv53Mqn//zXANqWEufyOmIjvFhE2RJ7wSWASsNsG5RNAP\nsNDp4tHPlqcANOh0KpOGCHbs2IHOKg+58jtxYsEPaBPnAhJC/cfTYOQUpLb52bZtG927dzeZzWRi\nY2OZOvVHfH1bYmGRi19+mcmoUcNNbudNBEHgq2HDOXjyLH1+X4eDkyuPrvriWqU2woAJBFw7z9Dh\no4iIjGTggAEZpmPv3r0EhUXQqqMX80d/haDrDlzlyonT9Pt+LpMmj6FXz54mfeLJiZiJfzUIU7SE\nTwLhJjhPhmEuOZCG6ihfvjw1a1bAyqozsBIrqy9wd69CmTJlTKbhwOEjFHDz4M7+HWgTZwO9gV5o\nE+dye+8O8ldtwv6Dh422lxrDho3j0iUHNJoQYmPPMHnyXPbt25chtpLZtWsXuw8epucv/+Dg5IpW\nqyFXXntevXgCgGuV2vSatZJx4yfw5MmTDNOxZu063Nt1Z92c31An/IdG/Rca9VnCg8vw5O5NbPPl\n5/Tp0xlmPy3M5W/EVGSnEXNidoQZIpVKOXBgK5Mn16FTp2NMmVKPvXs3m/TxSYK+dahvMrwxag9t\n8s4Mi5QdPHgElWoGkBsoQ1zcEA4ePJoxxpKYO38hdboNxTJXbmLCw/hrUFeWjviaPwf3ZO33Y9Fq\nNTg4F6eSRzsWL1maYTqioqPJbZePuOhwoHzSuxLU6vLERIaT286B6OjoDLOfU8hp4YiP4uXlhYuL\nCwB58+bFzc0t5Zc3ORaVkdtXrlxhzJgxmWYvre03426G1P/++8kp2xYWFibRM3/+fNzc3GjVojl7\nv5tJITcPgm+NRacRAClS+VgKVerPS78jtJn+bYZcDysrJbAR/aIFx1AoDuPo2Nxk50/evnPnDvPm\nzcPKyooLvueYMGEBj676cnjlYl4FNUOnaQeo8b/8Lb7b/6NuZy/yuZRi5b+LmfXLzybXA+Bgb8f5\n/VspX6s+V09NQpPYE/BBabGeklV+xcd7JbGxsSSTWfdn8nuZ/fcxf/58rly5kuIfTIUR/vUfoA36\nJYzSGp66EP0in3GAF+CXbmuYrq3jQtpLRGd5doSPj49ZPG6Zg45kDRqNhjLlK2Jfuz15nEpye982\nBAHKtexATNBjgk9t5v6dWyaPTS5dupTFi5dx/fotlMqeyGQvcHR8yuXLp7C1tf34CQxk5o8/MWPG\n7/rYuiAgt7Bg2m7938q8Ph2ICFqNfs3GxsBiKjc5TpfJPxETHsbSoa2JeBVmMi1v8vTpUypVrsJX\nvy1n3+p/uel7BJlMyZcTphD67BHalwHs27M7Q2x/CHO4N8F02RHuvx43qOK5SY3etdcA/QQuq0nd\nn7UGRiT9XxtYALgboTVnTOBjDjcXmIeOZA1yuZwjB/fj2bwlQRetcKzaBCQS7u9ehiwhmiMH95vc\nAY8ePZaFC9cB44FTaDTrmTt3Dv369SNXrlwmsxMcHMyMGb8jCL1AWAg8R5NQiztnj1C2jicFiroS\nFbIVnfZnQI3cYhcFi+sXf4wJDyFP3rwG2YmNjWXatGk8eBBA584d6Nu370ePcXZ25u+lSxg6bAh1\nWnehaY9lxEZFcn7PJuJeBXH8WMaGZdLCHO5NU2JES/gk+kZlWrQHklNYfIG86Bf/DE6vQVPEhNcD\nZ4DSwFPg05d/EMkS7O3tmTn9e9o2dqdY4hNq2Maz4Kep3L9z65Mmjv8Y9+/f59SpU/z55zLgCPAN\nsBONtiH+/v4mdcAAvr6+CIIOQTcZkAHOwED8DmwFoP3YSeTOtwmldSUUlqVxLptAnS/0DvT64e10\n7dz5ozZUKhXFi1di3ry77NxZk379vmP48NEG6evWrRsXfM9RJn8uzm5YzAOf7YwY0IvLFy9QsGDB\ndH5qkTfJwJhwEfR+LplngFMadQ3CFC1hs18y11wetcxBR7KGP+YvZOq0aVgXLo9gmQf18xsULVyA\n7yZ9g1xumgeka9euMXDIVzzwf4h9ISd0OjVQKFkJUITIyEiT2HqTYsWKIZHIEDgHdAF0SKSneXLz\nGomqeGwdHBm1chtXDmzBuUI1CriURiqVEv7iKVcPbWPVpY9P2L5hwwZevrRDH4WTAL1YvLgEixb9\nYdCgj5IlS/LHvLmAed0Xnwtp+ddIfz8i/Y0K4cL74RKj4q1idkQO5L//1jL9lzlYNxpLjEpJ1PMQ\nBBcPAnNVpEFjTxISElI9zs/Pj86du/DFF525ePFiqnWSCQgIwMOzGTaVm+Bapy2CRSHyFS0Dkt7A\nLeA4sIEhQ4aY/PNVqVKF6jXKI5H2R6roiEReDYnEj2pVKrNx2hAiX75AobTAoWgJHIuXRSqV8vze\nDdZO9uLHmT9QvHjxj9rQr9FXmNd/jwX1y1NpNCb/PCKfjlQqTbXYlaqOS8tBKSUdBKJ/tErGKem9\ndCMOW85hCIJA8dLliHRtR8TxlQiJ3wKVkMhnYl22IBbxT1k0cxw9e/Z867iTJ0/SqFFLBKE/IEUi\nWcGRI7vx8PBI1c7wkaO4GBjLgwsXiAyqjlbTBLlyBdZ5g4l59RILhYKVKxcYNBhEEARUKhUWFhap\ntjJDQ0Px9vbm+fPn2Nvb07lzZwoWLMj06T/gvWUrdnZ2zPppJk2bNmXqtOn89ddfFK9Sm/ylKqHT\nanjid5qol4HMnvULXv36GXQdHz9+TPHiFdHplgA1gR8oXfoOd+9eNuh4kdQxVcdcw3mnDKp4Ylz9\n1Oy5kHaiwZsdc+7AfIzsmBOdcA4jKCiI4qXKoazalcgz8aBdk7TnBchKkbdBP5o5RuK9/r+3jitT\ntjr37nZHH88FmEeJEv/y4MHVVO04FXOhXLtBHP9nB+r48+hvtVik8oI0Hjgem5Bb7Niy6YNab926\nxaJFf7Ju3VpUKhUA7dq3Z8Tw4TRu3Bi1Ws34CRP4999/aezZEmfXEoQGv+Dgnh00bdaUFcuXkzt3\n7vfOGx0djbe3N3fu3EWukFOrZk3atWv3yWGY48eP063bQCIjI3Fzq8SBA9tMOtl7TsRUTrjRH4YN\neDk+tt679tYDjQAH9J1t09EPWwVITiD/E2gJxKLvAzPqlzdHZEeYS7zLHHScOXMGQdAhkUiBN6fO\n1Ojf0+mQpDKSKDo6HnjzMd2V6BhVmna0Wi0SqQQJVry+x5WADIlURvCLFx/UuWbNf4wZM4ahw77G\n7/ptChcuTFRUFOvX/Uf/AQPo1rUrT54+JTAohP2nrpHXPl/KsROn/8rs6d/SslVrjh45nJJjnUzu\n3LkZOHCg0d9Ho0aNCA5+kO7jkzGH+8IcNJgSI7IjDOnjGpHus6eCGBPOYdjZ2eFctBgorEF2BCRT\ngA1I5O3IVak10qdn6Nqpw3vH9ejeBn0r+Cr6uZom0r1bqzTtNGvalJiQFygsnyCRfg/4IFP0oXDZ\najy/dhr3Wmmv0Xby5ElGjx7N4WMnmPbDTAoXLgyAra0tQ7/6mlNnL7B7zx6OHDnKgmXrkUiljB82\njOZ16jG4Zy/CX4UxffZCkMpZu3atMZdLJJuSnUbMieGIHMi4ceP544//AYlILRyR2ztjVbwyksQI\nHKJvceua33s5woIg0LfvADZs2AEIdO7chvXr16R5I9+8eZN6DRpRx+tb7p85RUTQCwqXKYdd4QL4\nH9nE7ZvXUw0VAFSvXp3BQ7/Ga8BAdu/ayajh3xAa+oLChYvy19I/aNLEk2tXr9K6ZTOOXbrPl+3a\ncv9uBdSJg5HK9mGfbyX7Tp3lku8Zli34hYvi8vTZBlOFI5osPGNQxaOj6prCnlGITvgDCILA6dOn\n2b5jJ5FRUTgVKUyf3r0N6j03V/z8/KhXrxXx8fuBCsAk5FbrsVCqcXOrzJaN60yWq3rs2DF69+uP\nzDo3eQsVJejeDQo7FmCL94Y085CfP39O6dKlefL8Jcd9jtG5Y08EYTgwEjgKDMapaAFGjhrNhvXr\n6NJ7MDMnTyNB9ZzkBzub3HVZuHwKVWu4U7tc4TSzPUTMD1M54aaLzhpU8fDIOqawZxQ5Ihzx5vh4\nQ7l69SrlK1WmS69+nAmM54GQn12X/HGrUZO27TsSERGRKTpMzapVqxCEToAb+v6GWmjiY1BKrahU\nrjJ2dnYms+Xh4cGTR/78u3ghk4f0Zv+ubVy5dIESJUqkeS18fX0p4uSMtbU1k76ZgSDIgZ/R5xf3\nQqaoSdVWXZi/6E8CAh5x48pFdDoVEJ90Bi06XRRKCwvU6sQPrlZhDt8HmIcOc9BgSrLTLGo5omPu\nU7lx4wYens2o1Xs8zRu3f+uR273XWM79N48GjT04e+okNjY2Waj007Gzs0MmOwhogfPoW5jbCA93\n5t9/R3L1akvKli9BpQrl8fLyes8pR0ZG4uU1nGPHjpIvXwGWL/8jzTQ1AJlM9sH97yKVSlMyIcJf\nhaN3riHAQWABWvUjDq+9gzqxGprEknj/9x9VqlXn9o3WxMf3xMLiIMVL2lO5ak32bPOmQcOGn3aB\nRD4LzMS/GoQYjkgF93oNsKnSjIotuqHTanlw9gDRoUE4lqpMkQo1EASBw3+Mp1sTd6ZPn5bVcj8J\njUZDkybt8PMLR6VKQKNpB8xM2nsKiaQduWzzoLSQI5fEcub0qbdCBy1afMHx43lISJgBXMXaegB+\nfqdNthSgFus8AAAgAElEQVRSVFQUjo6F8L3oR7s27XjyJA5Bp03auwawAPoCk4AhwEnyOfRj6OgR\nXLl4jRKlXeg/dAQ6QUfPdh78/tuvtGvXzihNKpUKb29v1m7cREREJPkdHPDq05MOHTpkq8nXX7x4\nwa5du5DJZHTo0AEHB4eslvQepgpHtFrsa1DFfcNqm8KeUYhO+B1u3LhBA4+m9F5yCKlUxvaZY3lx\nJwKt2h2pfCt1e3lRtX0vQh7d4fDs4QQ+fWyyYb6ZhUajYdeuXaxevYY9e/KiVv8DJKKf37YT8CUy\n2UasbNbh0bgGO7dvA0Cn06FUWqHVhgPWAFhZDWLu3OoMGzbskzQEBgbyzz//8PBRAKVLlaR///44\nOjoCULdePVxcS7B3z25qtOyOz+bNaDW/8Xpakj3oc+QPASEolSXxexiY8sRy99YNfpoylsoVy7Fi\n+XKjesF9fHzo3LU7eYqWplDt1ljlyUdsWBDPz+xCHRnMnp07qFq1arrPn1msXbuWQYOGIlPYIwG0\nmld4e2+gbdu2WS3tLUzlhFsvMcwJ7/0q652wGBN+hyNHjuBaywOZXMGzG+d5cecZatUpdNoFaBJO\ncmr1XLTqRPK7lkWisODOnTsZoiOj8PHxQS6X06lTJ5Yt+xt7ex+Uyv7AcPSO+DegGlrtr2gSrdm3\nd0/KsRKJBEtLGyB55QkBmezxJ09BuW3bNsqULccJ3ys8fxXL3ytXU7RoMb75Rj8QZOOGDezdswut\nTodH115UbewJkpA3zhCSpDUMGIFWCx2a1GRk/250b92A4f06061zR5YvW/ZBB/yx7+PcuXN0+KIz\nVQf9SN2xf+JatzWOFWpTomEHGkxaTslOo2jSrMUn3QPp0WEsYWFhDBo0BJ1QkNjof4iJXoJWa0uP\nL3sSFxeXKRoyG4mB/8yB7NWEywRUKhVyC/2sXqroCJCU4PWAmWKADLUqDplCidIq1yf1vEdGRnLm\nzBmcnZ1xdnb++AHvEBUVxaZNm3j27Bmurq64ublx8OBBEhISaNCgAQ0aNDCo1adWq7lz5w6CIHDx\n4gnWrPmPadOmgyQfGrUa/aCKRLS6aCwsLFOOk0gkzJkziwkTmhMX1x8rq2sULRpJZwNmHUsmLCyM\n/gMGUtXdgxOHT5GYUBYIAkl95sz5E1tbW6ZOncqlixepWdudC4d20rKfF9dO9yYxPhqwQqaYg9JC\nQaKqKBIUHD26G6VSyYsXL7Czs6NevXomeToZOWYcFbuPx7FCbbQaNfcOexMZ+AyH4iUp0agTRWs1\nIzb0Od9MnsLObRm/SGh6OXjwIAqL/ERHzgOaApCY+DNW1j9w8uRJWrRokbUCM4DsFBPOEU74U0YC\nFStWjMit+vXOHEtXQdD9BOwF6iORziNPQVcsbPKgTognPOgZRYoUMei8e/fupUeP/giCM4LwhNmz\nf2TMGMMH3nh7ezNg0BBsi1dFyOOE6vluogKuU8zNnbxOJVi0bCWF8+dj4R9zkcvl2NnZUbp06bec\nslar5dTpM3Tt/iVKaxuQSFBFR/D1sGF49fdi647DxES1JVHVEaXldmxyW9GtS6e3dAwbNoTSpUtw\n7NhxChZswsCBA7G0tHxXbpqsX78et5p1OXviNIkJV9HPDPgQhOrATH788VemTp1KiRIl2LRxA+07\ndiKPQ0G6j/2Gx3fuABLqtvkX23z5+WNYV1Yt/5sGDRoYbP9NPnRfXL9+nQcPH9FqWAsEnY5jv00k\n1F+BNrE1AWe8Cbp9g/pfT6ekR2f2TGjL8+fPUwaVmFKHKbC0tARBB7w5Y104Op0aKyurTNGQ2ZjL\nQAxDEGPC7xAXF0dhJ2c6zdpAHkdnnl0/z/4/ZhAf9YL8Lm60mfQLuR0cuXFoM1L/sxzct+ej51Sp\nVNjbFyY+fg9QB3iCUlmN69fPGNShdenSJRo3a0n+lmMIPrWLhLBArAq6YlmgAKHnD6G0zoV9MVei\nX9xDKgHHIs5EhL7E3i4vY0aOYPDgwUilUnr16cuFW/40Hvwd1rZ2gIAqNprjK2ZTooAtkRGR3Lh5\nC6tcDsTHhlKpUgX27t6V5qAK0OdSX7p0ibCwMKpXr/7Rzp5JkyZx8+Fzju2/R2z0uTf2VADGIJVO\nQqsNQ6fTUcXNjQcPglDF2yNTWJHLNoIBM37h0fXLnNq2hm+/mcjE8eM/ev3Sw9KlS1ngfYBq/acT\n9ugWh3+eiibhDvqnolikcmc6zN2AtX1BfBeO4fcpY+jQ4f2RhuZAfHw8hQoXIS5Wglo9GUhAofid\nfA7WPHv65INpfJmNqWLCnZZ/eJa/ZLYNqmEKe0aRI1rCnzIu3tramlGjRvHf/6bSasoSnCrVYtA/\nbzva8OcBXNr4Jzu2eBt0zuDgYLRaJZAcuigKVOD+/fsGOeFf58zFtlpHnu5cjCZuDAgdiAlYRcyj\nP4EdJMYWIvh2P9yaNKLPtN+QSCQIgsD9y2f4Y+lC9uzbz9jRozh68jQNvL7h2D9/EXD1HCClSLkq\ndJ46h03f9eXvhfPImzcvt2/fpnz58tSuXfuDLQqdTke3bl7s338KmcwFuMWhQzupVatWmsdUrFiR\noyfPkphwGzgF1EeffvYSWISLSwEAjh49SmBgGFpte2AZWrWEqLCx/Dl2GA0a1uDgvr1Uq1bto9fu\nQ3zovtBoNEhk+jCUNlGFRGrH67CUNRJZLjSJ+lQ6qVxh1BSWGT1vg5WVFQf276NDx47Exf2OIOiw\nt8vD7t27UhywOHdE1pEjOuY+lR+mfU+dymXYMaUX907tRatOBCA+Khy/HSvZOa0fc2b9TEMDc1Ad\nHR2Ry9XAlaR3HgA3DV7C/tTpM8jzFkSnyQ/CBKAUCD8BeQBHoAyC8BcBN26lOE2JRELp6vUYPHcN\nT8KiGTFqDFVa9eTOyUM8viZFqw5Cqw7i+Z18nFy7jMptevO/pcuoU6cOAwYMwN3d/aOPdFu3bmX/\n/tvExt4iKuooUVGL6NHjw3O0dunShedPHlHfswlW1h2QyfMBHVEoE7GweMyFC/rZr/z9/VEocqNO\nbMbrhkprbPPkp0WzZqk64JcvX9K0aVNcXIvj6elJcHC6V5yhdOnSRATcRBAE7IuVQ2YRgkQyC7iB\nRDaRXPZ5sCnghE6nJeThLZOl6GUUtWvXJvDZMw4f2onPsX08evSQSpXSWscy+5Od5o7IEU74U3/h\npVIp/63+lwW//kik707+7uPOyv71Wf1VMwolBHJo3x4GDRpo8PksLCzYsWMj1tY/YmFRBqWyOgsW\nzKJkyZIGHW9paYVE0IEujNet6VggCkgeLPIEuVLBohED+b69B3+NHkLEyxfIFUq+GP8L/v4PyFuo\nKNFh0WgSB6DPt1WgSRxA4K3bFHApw6OAAIM/E8DDhw9JSGgIJMeEmxMY+PAjn8WS/fv28vjedVyK\nO9OkVWNKlXWlePEiXL9+EXt7ewCqVauGShWKpeUqQAWoUVosR6eLw83NDdC3xLVafQ5xdHQ0pUpV\n5vjxYB4H9ObEiVBKlqz8wZU7PnRfNGnSBFQxhPlfR25pRYtpiylQ9hBWeTtQqOJNmk5ZiFQqI/Dy\ncYo6FTbKoWVWC1Qmk1GrVi2qV6/+3rzMn1MrGPQtYUOKOSDGhA0gJiaG2NhY8ubN+960iJ9CZGQk\nDx8+xMnJifz586dZT6vVcuDAAcLDw6lXrx7LVqzgnwN+xEbEEROgQVC3QaLYhKB7CNoOQCHkyr9R\nWloQHzMKQdcJqWwdefNvYPLaHcgVSlZMHoxGosA6TyGuHpCj1einRpXKxlK+UTAla9Um8uI+jh46\nYPDnOXToEB07DiMu7jRQEKn0dypX3oGf38mPHqvVajl69CiPHj2iVKlSNGrU6C3HIAgC7dq156zv\ndaIiwkEiJXduW8qVc2aTtzfjv/mWrZs3o9GoadC4CVUrVWDhwlXodE/R/zDFIpUW5eefJzJp0iSD\nP9ObrFjxD5Nn/EyDb/7GKu/7se7o4KecmD2Y/1Yup02bNumyIfI2pooJd1tl2BS/3l7VTGHPKHJE\nS/jIkSOsWrWKRp7NqFW3Pj/99HPS8jSGYWNjQ8GCBY1ywKCfPKdq1arvOeC7d+/Ss08/bPPmI1fu\nPNjbF6Vt2/H07r2WUqWqUL1qVYTAa+R2Kkphzyo41L5M4Wb1sa9SF4XVZhr3eEXX8ZPQavIj6L4F\nSqPTTicmUkPIswAAilWoyt2zR7h//iDWeY6gtKqO0qoWuR324TloFDf2r2fwAK9P+jzNmjVj/Hgv\nlMqSWFs74eT0D1u2/PvxA9FPV9msWTOGDBmCh4fHey0ziUTCli2bmTBuKCVLOeHiUoARw/uxY/t2\nGjT24Oi5W6jVOgRBxrV7wfxv8RKk0ny8fjLIhUzmQGhoaJoaPpYbO3DgAIYP7s/Rmb25vWcVqqhX\nCIJA3Ktgbm5bis8v/Zk18wejHbA55OiagwZTIjGwpEFL4A5wH/g2lf2N0aea+CWVqcZo/ew75rRa\nLZOnfs/Tl5FopbbodAJL1u9g+cqVnD97hgIFCmSpvkuXLtHYsxkJjnUQnJuji3iE7pka/bwOMjSa\nPQwaNIwrV04xdPgojvtswzpvfkKvBSGVK2jSbQAtB47hxcO7CLpX6MMVFkAcOm0kFpb6kW0J8Sok\n+SoRJ1UgiblD1RYNKVXbA4eiJTm7/k9yy4VPyvdNZubMqYwbN4KIiAicnZ2RyWTodLqkUEUCxYoV\nS/f8GhYWFkyePJnJkyenvLd69Wpi1PDqhRpB9xTIQ1RQX2wcEogKeoZEMg9B6IFEsgmN5vknf6ZL\nly5x/vx5QB8SmTZ1Cq1aNGfegkXsmNCWhAQV1rls6NGjB6t9jmZYXFWlUrFkyRL+Wrqc4KAXFHFy\nZvTwrxg4cGC2GiqdVcjSnygsQ79yRlP0a8ddAHYCt9+pdxxon14jb/LZhyO2bt3KsHGTeBUUhiZh\nKlAAmfI7HMsUoWPjmvy5cEGWaQOoVLUmdzQl0Dw4BeqyoFOA4Iv+uy8BhCGXF0OtjgEgJCSEoKAg\nihQpwqFDh/jht/kMnb8OQRBYPmk09y9HoU5og9JyGxXqOvPFmG9YPmksj2+dBYkCeZG6SHMXQn3P\nm1JVavH49mXKlC7DzBk/0K5dO4NWCk4LnU7HokWLmLdgIbFxKpRWVkS/CqVbt+78OGN6uvNo3+Sr\nr0ew9aAvIf79ga+T3r2EtV0PbK1VvAyKRtCpkUgUzJ49lQkTJhh0Xl9fXwZ/NZzAoGAKVqgNEgkv\nb52ngL0dfy/+k/r16wP6rImMHqauUqlo1KQZD8PVWFdujVSuRJsYT9yVXVQtWYh9u3Zku6HyhmKq\ncESvNVc+XgtY28ftXXt10C9p1DJpOzmW9esbdRoD4wHjJiVJ4vP8Jt9gw6YtyGwKoEnoCYwFQJtY\niMig4WzZujVLnbC/vz8PHz5EZ5cXEjqC8GfSnl+StG4HfqZ8+Sopx+TPnz8lnNGpUydGjBpN4P1b\nFClVnoG//MG5Pd68eHgPp1IdqdmqC/8bM5Snd6sBx0B4gCawIYoStlja2PPszhU8W7Qlr509k6d8\nz4SJ37D2vzUfTDFLC51OR4+evbh4+wENh/9C4bJuSCQSosOC8du5mhq13Dl7+iTFihUz6po5FSmE\nVJKIVH4WnWYYIAHJORSWllSuUpbt97158eIFhQoVShmI8DHOnDlDq7btqPjlRJrXaoZUqk/bEnQ6\nnl06Rpv2Hdm+ZRMeHh6Z4vz+mL+AR5E6LEo14unWeUikRRCEQJzaj8bvyg5WrVrFoEHpWik4x2BE\np1sR4Okb28+A2u/UEYC66JeZCQQmoF9CPF189k5Yq9OREBuJ/ikjGTkIeseRmbybixkWFobSJh+q\n+FgQ3lyw1R2YA1hSsGBRDhxIfeVYpVLJ7F9nMWXacAb9vpp8hZ2p2/7tJbICbp5Dp/VG/1WXBaEh\nBJ+hTNkSzFu6hmuXLxAZGU53r6E8uHOLNm3acurUSYPT55JZs2YNvtdu0/WXNUSFvGDvHzNQxcRS\nvrEHDftPxDJ3XvoNGITPkUOpXgtD8erXj9/mzMUqTwyJsY0Be5CcQqpVMGbEb1hZWRk86b6Pjw8N\nGzakZ59+uPWdilN1DyKePeCBzy4QBEo0bINzTU/kltb06tuPpwGPMmRgw7vX4q8lf2Pl7sXTLfMQ\nNGcQKA+c59nO5ji1H8mCv5aY3Al/fnnCqXvhoFsXCL79wYEchjy2X0a/7H0c0Ap9ayndOYqfvRPu\n3rkTx06cRq6cjybREciP3GIieRzz07ZBkyzVVrJkSVQRQUiKVoSw+aBtDViA9DekxdxRhpzj5Ml9\nKbOLpcaA/v2JiYnh+686Ur1ZR6o274RtvvxEhgZzZudGtGoJcAloBuiAO5AQzoLlZxkzaBB3b0Yg\nUBpB+J55y5bRrd8QfpszhxXLlwP6LIWoqChsbW0/mFc5b8EianYbRmx4CP+O6Y06fgSCUJSAKz8S\nHxVJtfZ9WTZgJffu3TMqp9bJyYkN6/6jZ+8+2DjKkcpDiXyhYuLYCbRqlfaad2lx9OhREpBTpFpj\nXgXc4dDPw9EmjABk+B//Gs9Jf1CoUh3u7bRj3759mTLrWPCLZxSRKZDISiNoyie9WwuJJD8ySxsC\nnz394PEiac8dUbhCTQpXqJmyfW3rknerBKJ3sMk4o28Nv0n0G6/3Af8D7AHDe/vf4LOPCWs0Gpq2\naMW9Z8EkJlqi0wpY28rQRb7gou9Zk8QpjaFXHy+2nb5Pgi4XuifHAQGpY00UuW2oVUTHiaOHDDpP\nQEAAi5csZdOWLURFRqLRaonV2SKxLYH66XmgFUjugyyQdh2b4V6vIT99t5r4OB/0TwmHcSjwFRv3\nHaBdwyrEREdz/PhxWrb6ggRVHAqFBdu3r6d169bv2U5ISMAmd27GbrnK2Y1LOL1eQNAtTNp7Hhv7\nngxfs5eD879l5Jft6d+//3vn+BhqtZq7d+9ibW2Nq6srKpWKI0eOEB8fj4eHR7rnxp06dSo7br6k\n8hdfc2LB9zy75AmMSdq7FMeKW2nyzWxu7lpBE2cL5s39PV12PoXCRV1R1h3Iky3zEDTn0Dey/JDI\nPXDqMJrc93dx86pRq6ybLaaKCXutv2ZQxVVfVn7Xnhy4C3gCz9H3kH/J2x1zBdEP8RSAWoA34JJe\nsZ99ippcLufA3t1MHjEYl4JyCtlp6dWuCX4Xz2e5AwZYuvhPKjvKyBV/D1nZVsjKtsOGUIrJnrN5\ng+ErBbu4uDD711k8vH+P0JfBHD6wH6XmFRJlbpRl2yF3eomiaEFkdoVxci5KaMhL1OrqvA7T1CQy\nPAh7h/yo4uOJioqiefMOJKhWAirU6i20b9+DsLCw92zrwzoSJFIpWq0WQXgzFmuFLmlSdolUlq4Q\n0PPnzylbtjp16nxBxYp16dKlD0qlkrZt29K1a1ejJidXazRI5Ur9a1UC8Ga2TAG0SbPkSeVKEtXq\ndNv5FL4eOpi4mwcp1HwAEnltpBbVkMibUKTdCOKv7WbEV4MzRUd2xogUNQ36Je0PoI/zbkTvgIcm\nFYAu6Jccv4J+Yusexmj97J0wwNmzZxk5ciQXz53h5tXLzJ71i8kWs/wUUsvFtLGx4ezp42xbt4LB\nHs541c/PmiVzuHX9ilHpczVq1GDr5o1YhR7H8tU5UMciU72A8JtcOneKKtVrI5dtQv+jr0Um/4kK\nVepw89plihZz4fHjx6g1eYDkSWmaotUWSXXuXCsrK1yKl+DJNV/KNWyFQrkCWAEcRG7RF7dWHdFp\nNQT4naFGDf1S9/v27WP9+vUsXryYq1evfvCz9O8/kidP2hETc5f4+Efs3/+UZcuWpfvaJOPj40Ol\nihWJfqhvNZVs1BSZ8jvABziJTDmR4o09AYh6eBW3yhmTjvbufTFu7BicLBNRPz6P8xfjcO7cDeeO\no1HdPEh5Z3sGDjR8tGZ6NWR3ZFKJQSUN9gFlgJLArKT3liYVgL+AiugXaqwLnHv3BJ+CKWLCLdH/\nGsiA5cBsE5wzRyGRSPD09MTT09Mk54uKiuLu3bsUKlSI54FP2blzJ9ev38DGJhcODg5MmjQZhULB\nhOmT+W16DTSaBEqVqUmfQcOYPW0irVu1pECBAkgIQ+AZ4AS8RCIJpFChQqnaHD3iaxau/JuOPyyj\nxy+L8Vm1lITYOMo3bk2tL/py/eBmXF2KUaVKFbZv307v3r1xLVcJy1y5+f6HGdRxd8d7w/pUMxpu\n3LiJRjMTfdvFiri4jly+fNMk16pz586MGDWGyEB/irk3R50Qz63dI0EQKNuyByUatCM6+CnBty/R\no8d2k9j8GNbW1pw6fpSFCxexeNkKgl88p5BzUaZ+PZRhw4ahVCozRUd2xlzmhTAEY5XK0Del3kxs\nfjd+ku2HLWcXwsPDmfjNt2zatInCzsWIj4tFq05k4oTxjBw5MuXG3LJlC8O+Hs7Ib3+gQZMWrFwy\nn53ea3Eo6EiePHZEvAoBQYuraymOHD6HINQBzjNkSA+WLl2Uqu3ExESat2pNqFpO/X4TyVtI37eR\nqIrj2n5vLm9bzoljR7G2tqZ6jZoULVebO5evIpMXQSp9hmvZ4rwIeIBEIsUhf34GefWlf//+2Nvb\n4+nZgePHa6LVTgUSsbZuza+/dmTkSMPmY46NjcXb25uYmBjatm2Lq6vrW/v/t3gJ037+lXrj/sIm\n/9vzQ8eGBXHmjxFMGjOCcWPHIJKxmComPGTTDYMq/t21oinsGYWxxg1JbBadcCYQGRlJ3Xr1KVm5\nJl9+NR4b27zI5HL8b1/nrx+/oblHQxYsmJ9S/+TJk/zwwwzO+Z6juntDxnz3E8WK6ycUEgSBq5d8\nmf/TZEoVd6FFi+a4ublRu/a76ZKv8fHxYcZPv3De1xe1OpH8zsWxyZOXFw9uU6duXebPnUO5cuWY\n/N13HDx9gZsXwkiIPwnkAlZS0HkeEa8C6Dx7E3HhITw4tpngmxc4dGBf0moZzYiKskKjCadhwxrs\n2rUxJWc3NDSUAwcOEBMTg6urK56enimpZJGRkZQq5UZIiDNQCLl8H8eP76du3bpv6Z+/cCFTp07D\nqWpD8pWvAxJ4dduXp5d8+H7qFL6ZOCFbta6yK6Zywl9tNuxJaUmXCqawZxTGxoRTS2w2bKmJTMRc\n4l0ZqWPO779TpGR5+o6ewuxvxtOhuivtqrpy8dQJfvrbmw3em7hy5UqKhgYNGlCmbBk8mrdl3rL1\nFCtekrCQl9y5cYXYmGjcarjzv7W7uHPfHysrqw864I0bN9Kpa3fCsKVg6bq4VPVEKpWjSIzhyuWL\nHNi7m3LlygHwwP8RCqUliapS6B0wQAdeBT/GwtKaqJdPcXAtS8MRv+LWawLNWrQid+7c3Lt3hcOH\nl3H+/F727NmEn58fq1atomWrVpQsWYrV67w5fOIcEyd9h4trcVavXg3ArFm/EhJSEzgBbESjWUKP\nHvqOrTe/jzGjRvH4kT8D2zXE4eVlHIIv07eFO4/87/PtNxMz1AGbw/1pDhpMSXaaRc3YmLBBTVwv\nLy9cXFwAyJs3L25ubimJ4clffkZuX7lyJVPtZfa2IAgsW7acH//exIyRg7nlp0SniwFdMOuWuAMa\nWnXry+IlSylXVj8Io2rVqqxbu47vfl3EJd9T3L99h0Wzf0IqsUPgFQv++Y8adRri2aYTM2f+SJ8+\nfZBIJO/ZP3z4MEO+GkbR6s24ffIWmsQWwF0scgUjdS7IqlWraNKkSUp9aysLXgXfQ64IRZ0Yjn7Q\n0WZs8hQkPOQZ+2b9iEA4rb6ZQ6n6rbh/dAtTpkzhf//7HzVr1mTBggW0btueOLUGbWIipUqX4cd5\ni/Fors/fvXD2JA/v3+X76T8QHR3NuXMX0fevJJNAaOjreYbf/Dz58uWjZo0a1KxRI8fdn6ldj8zY\nnj9/PleuXEnxD6YiOz21GKvUHfiB1+GIyehHBLzZOWcW4YiAgACW/v039+4/oFLFCgwdMiTNTqbs\nRkxMDAUKFGTbxQB6NKhFxKsDvB7A8ysd+zylRv2GHNm4nKNJI9bWrVvHitXr+G3JOh49uEvvdm1J\nUPmiT3c8Qi6bnhzxu41UKqVdvfKcOnki1fmPT58+zZcDhhLo/widdhj6vHU5YIO9kzX1a7qxY+vm\nlPrPnj2jUuUqlHRryJVTPsgVDigtEoiKCE2aM6MScAa5RVu8/jlIyMNb3POex61rVzhx4gTtO31B\nnUHTiQ55jvrBef5es5Xnz54wZ+ZPBAe9pF6jegwbO57gF4H0aN2AuXN/Z/Dg6QjCcfQT4PekTRsL\ndu82bFUUkczFVOGIEVsNG0X85xflTWHPKIwNR1wESqH/y1UC3dHPOGRWHD16lKrVquO9/SAXrjxm\nzcadVKxcmUuXLmW1NJNgaWmJTtARExVJ3nwF0H8tAAJKiwvkdyxARFgItnleL00fFhZG/oL6POnH\nD+8jl9fkdb65JxoNhIeFIJVKyV+wUKr5wZA0oY1CiU6rAnYDj4AIoBOvAl8SGRHxVn0nJye2btnM\n0zu+OBSyx7WiIyrVK6TSMugdMEBdJFIHol8+x7ZAEUJDQhAEga+Gj8R90DTylyjPuf+WcuHUCdzL\nudC5eROOH67CrWuTWLPsHNMmjMOpqAueLdsRGhrKlCmDkckqIZHkpV49FRs3rjTBVRcxZ4xMUctU\njHXCaSU2mw1arZYeX/ZEmcuRp/5lefpgLM8eFsE6jxODhgz9+AlMSEbF3eRyOe3atefQ9g2MnTkT\nS+vRWFr3wMq6EY5OAbTu2pdD29bR68seKRrs7OwICX4BgLNLCbSaS7wenXkCmUyHnb0DOp2O0JdB\nKStevEvNmjUJCwxA3/rtg34wkRTQd2QVdyn63jEeHh78t3o18dER2FeoR9vv/0YifQz4J9W4hk77\nkv+3d95hUVxdHH630VVAAStgx9iwYVcsWGLBEhtq1PjFxMRYYozGFluaPcZeE41ijFijYu8NG4pd\nRJF1DPkAACAASURBVOwiilIEZNmd74/BkkhZYGEHd16fedyZvXPvb3eGs3fOvfccu0IuxD2NwMHR\nkbNnz/Lk2XNKeTVj2w8j0GkHIQgvSUz4moT4muj1o4GWJCZuYPvmNeh0Ouo2asbJoFNMnvw9Wu0L\nkpNfcuTITmxtRV+0VPygUtAhBQ3GRKkwbJMCxliskdrEZslw7tw5kvV6YqL0aJNWAt1JermeiHsP\nCAsL486dO6aWaBRGfzeKv5f+ilabxOLNu/hyTH2G/9CX39ZtZMMfC9DGx9KhQ4fX5du0acOZE0eI\nehJJ6XIVGDBsCBaWVbHNVxNrm85MXbAEtUZD0JH9ODk5pZmKycbGhvHjxqFQC6DYB+hS3jkEKOnZ\ns2eq56nVavr27cPL6KcU9qhGvb5DUGlqYWFTB7VFE5oOGo+lbX5u7t9An15+hIaG4lzqA/R6HVF3\nLyBOylECpRA9YK/Qokh5utTr9SjfyrmXnTCdMnmLvJRj7r0P4KPT6bCxtSMhwYI3rh8VCoUalfJN\njrLcICejVFWrVg3/Navx69mLMh9UoUrtRjx+cI9Vc3/GydGBPbt3odFoXmtwcHCga7euzJs6gbG/\nzOXjAV/Qom17IiMeUsK9NPYOjiQmxLNw5hSGDv4q3Rt2+NfDOHvuHP7+W0DhiUJRDEF3FI8KpcRc\nbang7e2Nq6srv9f0okQNbyq37op7rYbERtynQBE3bB2duH32EPfOHebT1Qs4ffo0CTFRKFVqNJYF\n0CaeA2oCLYAvUCq/Qa+vhZX1LHy7/A+VSsXhfYE0bVgv1fZfaZACUtAhBQ3GRCq9XEMwiwA+xYqX\nIFmwIzrqQ3TJ7VBb/ElBl9M45IPLF0Mk84uYXW7cuMH27ds5c+YMAmKW5/bt2tGgQYNUP2NsbCxN\nmzXDpXgpPvt6DEWLv4n1e/nCWWZOGknVyh+wYvlyg76jtWvXMn7SFOJiY+nSqSM//DAlw6waO3fu\npJtfL8o0bk+5Jp2wK+hCzOP7XN/7N+HHd7Ft62bq1q1LQkICRYqXoO2U1USGXWXPrAkIQgusrK5T\nqaozxV3dePTgMQ2bNqDnJwO4FXqdPp19uBUWhoODQ6a/SxnTYKyBuRH/vLu8PjWmtfUwRnuSRzA1\nkyZNEuwdCwpu5WoKzsWqCO4eNQV7BwfhwIEDuapj//79OVJvXFyc0LHzR4K9YyGhYftuQkPf7oJ9\nwUJCO98OQkxMTLoaYmNjhaHDhgmOjgWFmnXqC81btxcqVKoilHB1E2bOnCnodLoc0fy2jrCwMGHY\n18MF5yJFBUsra6FoCVdh9Jixwr179/51zsRJkwXXitWF/qtOCl1nbhAKuZUVKlWrJQQeuyiE3I0V\nQu7GChfuxAiL/twkFC5SVPjjjz8M1mBKpKBDChoEQRAwcNprRjZn5LZrBm1Gai9bvPfuCBAXJrRv\n357f5s7jRmgolSpWZMjg1dmKaysl/Hr1JiJRoNeEORzZuBEEAb+xMwneu5Wu3XuwY9s/aZ5rZ2fH\nrJkz+WHKFA4fPkxsbCwuLi7Uq1cvRwKYp0bJkiWZOWN6hmEix44Zzf0HD/n7a1/KNe1MjW6DuL5v\nAx2aeVG6nAdFixbn5vUrWFtbsnDBfHx9fdOtT6/Xk5CQgJWV1XvzNCQjkpe8/++9O+J958qVKzRo\n7I3f2Jks+nYo2pfjASUay4l8+tN01k39jj2B26latWqGdYG4ZDkxMdHg1ECmICQkhAULF3Pl+nXy\n589Pl46+5MuXj5cvX+Lu7k6tWrXSNKp6vZ7AwEDmzJ3H3t27UKpUKJVKmjVrTjXPqpQvX57GjRtT\nokSJVM+XyVmM5Y4Yu+O6QQWntC5njPayhWyE8zgzZ85k67HzPH7wjMvH2wIDUt75nXI11lK8TDF8\nPMsyatSo9KoBICBgA336fEpCQixly1Zm+/a/DU4VlB20Wi2qFGOYk8THx9Olazeu3bzFh37/o0HL\n9lha2xDzPIq9G/3ZsmoRjg4FeRoZQWPvxixauNAkIU/NGWMZ4XGBhhnhya1Mb4TzUq89y0hlDmRO\n6NDr9ShUKvQ6PWD11jvW6HR6lCr1v2aApKXh6tWrfPzx57x4sQu9/iU3bvSgVavMpYtPjbi4OOLi\n4t457u/vz4hvv8XZ2QVra2ssLCyo5VWblStXkpiYmO12/4sgCPTw68kLvYqfV2+nWYfuXL8oZuTN\nb+9Ix35f8tumQ2isbejSqx9F3crSsGGjNBepGBMp3J9S0GBMsjlPuBVwFbgBjEyjzJyU988D1bKl\nNTsny5ieJk2acOnIHhp28kVjOQoIADaisfyGxh915NLhXTRp0iTDek6dOoVS2RyoASjQ64dz69bV\nVA2oIWi1Wrp0+RgHB2ccHJzp3LkXSUlJAPz+++8M+OxzIp4nsGjtDk7eeMrRKxH4fTqMRcv+oHqN\nmty9a9w8akePHuXchRAGTZmDRmOBIAjcuhLCno3+3Lh0nlW/TmeQbxseP4zlj6UL6f2/L6heuz6/\n/CKHx86LKBUKg7ZUUAFzEQ3xB4iheSv8p8yHiOsiyiI+ei7IjlbZHfEe0LhJUzSFS+FWuSZ7V68F\nQaBJj648uH6R6JsXOH70SIYDT7t376ZTp2HExZ1G7FGHYG3dkLi4qHfcBAkJCezdu5ekpCS8vb1T\nXU33/fdTmDbtCAkJGwAF1tadGTasNjVqVObLQV8xd9VmSpZ+d2BUEARWLvqVHRvXcCroJAUKFMjG\nN/OGrt17kN+1Au16i+6aeRPGcnjHIQTqkKzdAeRHl7wZeI5S1YV2HZvy5dej8GvfjAcP7qPRaIyi\nQyZ9jOWOmLT7hkEFx/uU/W97hoTnXQjsR1whDGKvuTEQQRaQe8LvARvW/82LO1fZuWQ6HrUqU6F2\nVfb8Ppuo68Fs2bTRoJH/5s2b4+PjiZ2dF7a2H2Nj05ylSxe+Y4Cjo6Px9KyPn98v9O27jHLlqhIa\nGvpOffv2nSAh4XPABrAmIWEg+/ef4Ovh3zBl9rLXBjjy8SP2bN/E0QO7ObB7O6uW/EZ+ewdcS5Vj\n4cJ3MuFmmf3791HHpw0AYVdCOLR9J4kJZ3iZsBJdchC65AjE2BkN0OvGcuTgMdxLlUGt0fDo0SOD\n21m/PgBnZ3esrQvQtm03oqOjjfYZZAwnG+4IQ8LzplameJa1ZvXEvIRU/F05paNgwYIcO3KYtat+\np2bxAtQolp/VK5YRdOLYO3nq0tKgUCgICFjF+vXT+O23Jpw8uRc/v3fzF/7003TCw6sSG3uI2Nht\nPHs2hC+++Padcm5uhVEo9r/eVyoPYmWlxC6/PZ616nL6xGFCzp2mU9MGfP/NOgZ/8h3fDRnMvuBr\n/L0tkKOH9vPz1OlojZRcMzEhEWsbceHIsyePUanLA68COJUE8gFPU76LO0Ayer2exIQELC0tDWrj\n9OnT9OnzJZGRa0hMDGP3bht69hyQ4XlSuD+loMGYKAz8lwqGPrb/9+QsP+6bxTxhc0ChUNCgQQMa\nNGiQrTpatmyZbpmbN++SlNSAV/egXl+f27ffDQv55EkUgrAZcdwCBOEMtnZNaFKr/eue+fjh3xD/\n4jfE4Hs6dMm1iH36CNea3lT3+5qdP3/BkKHDmD9vbpY/0yucnJ15fP8OdvkrU7J8RXS6YMRkuY2B\n5UAssAilKgaNxp9yFTw5enAvbu7uODk5GdTGvn37SEryQ8z9CElJ09i3L/WYGzI5izqN7uXN4BOE\nBZ9M79T7wNvzE0vwJrJVWmWKpxzLEmbRE5bKungp6MiuhqZN62JjsxQxXGUSVlZzaNSozjvljh07\nAhwDhgNfAwN4cP8BdvnEcJo16zTkyeN7QMOUM1ag094n/FQlji3bzZ5Z4/AZMYc/Vq0iJiYmW5oB\nevX0Y+/GNQA4Ohfmu9nzsM33MwqFBU5FpvLt9Fl07h9P1wE2uJcrSccufsz+eSKDvxpk8EIOR0dH\nLCyu8aZTdI18+VKPPvc278N9ITXSCthTplpdWvQb+npLBUPC824BPk55XQfxjyFL/mAwEyP8vhEf\nH8+06dOp19Cb7n69OHfuXJplw8PDGfTVYIoWL0HBQk582LYd+/fvT7N8Rnz22af06lUblaowarU9\nDRrEM3v2u8Hz7O0LAeFAO6AdVlahFCpUkIiHbzoMH1SpCUxFjLz2NXAIhFkkv9zHs7s6noZfpUh5\nT3bt2pVlva91DxjAkcBN3L8l+q896zbmzyPn+CvoBkt2HqRei3b0HjIKD88aRNwLZ8XCX6ntVYN+\n/foZ3EbPnj1xd4/ExqYNGs0wrK07MX9++qsAZXKGbPiE0wrP+1nKBrAdCANCgUXAF9nRahazIw4c\nOCCJX3pj6NBqtVSv6cWVK+EIgi2C/hkaCw1bN6+jRYsW/yp7/vx5mjX3wevDj6hQpzEKhYpzB3cQ\ncnAn40aP4qtBhmUrTo3ExES0Wi358uVL9f3AwEA6d/4Yna4LavVNXF2fsnz5b3Ts1JnNh0IIPn0c\n15JlaF2nBgolCPoE4CWvPGRqy97U7VuWqOtnGdGnI3369Mmy1lcsWrSIsd9PZPScPyhVoTIhp45R\nuZboOhAEgTOH9zJtxGeUKVWKcePG0rVr10wvZ05ISGDNmjVERUXRrFkzqlevnuE5Urg/paABjDc7\nYsbBmxmXAoY3Lm2M9rKF7BPOY2zatImrV++iS54MwiAgguTkWnz6+UBuh7258QRBoHeffrT5fARX\ngs4yZ+hAlMr8WNvB5z/PZew3n9DB1zfLy3OtrKywsrJK8/1WrVpx8uQ+9u7dS4ECtejWrRvW1taU\nLFmSzetW4laqLM4uRShRujgenQZxbsOfRIV/g173PXAahO04l1/Bpc1LqFx5vMG6wsLC2LFjBxYW\nFvj6+r4emIyPj2fpipVExyUxvEc3bGxtqN20AbHPo4h6/IhD//zNyxexBG7fli1jZG1tTf/+/bN8\nvoxxSGMOsCQxC3eEFH7hwTg6Tp85Q7I2GoRPUo64AO25cyuMt584goODiXz6FL1O4PyhWyQn3SEp\n8Raxz/zYsmgRtXzas2z58mzrSY9KlSoxZMgQ+vbt+zoWxbKlS1g8+yceP3yAIAj4ffwpV3esxOeb\nH3Eufx6VxhUbh89o/s1PRFw+TYliRQzqTQKMHTeOatVrsGDxcmbOmUuZMmVZsUJMZfTrnN+4eP0B\nyUllEPSreRE7hH1btzFvwje8fBjKnBlTCbsZapJ7RQr3pxQ0GBNzy6whk4tU8PBApc6PmNAE4AUo\n9uFcuOi/Hp3Dw8MpXsaDO9eukZT4EWAHKNDr+nAv9CqFS3twM+xWptreu3cvdeq0oFKlBsyY8StZ\ncTNVqFCBfXv3sHLhDHq3bwQIFLSxZP/MoVRp+xE9Fuyg9ZiZPAg+xLWtS/lr9SqD6g0MDGTF8t9J\nSlJx9VJDbl6riaCwYdjXwwkNDWX1X+t5GfMUQRsAtAZGoFB8hMLSll49/WjZsqWceeM9QqVQGLRJ\nAbO466QyB9IYOrp27Yqziy1K1SeoLOuiVJdBrYpgxvSp/ypXtGhRHt0Oo0hJNzSWOwBxyTCKWTiX\ncOfJ3VuUKPbfOejvEhcXx/r16xk/fjwfftiVkyc/4dKlSYwevYSpU2dm6TNUrlyZhQvmM3vGNG5d\nPoO1WsBelUyI/zQ2DmvD0VmDaVGpOMFnT1O+fHmD6ly+YgUKtQOJCdPQ6Waj1S4jPu5jChctxcqV\nK1G9NrBv5h0Lwl0QMLnxlcL9KQUNxkShMGyTArJPOI9hY2PD+bNn+G7MWAJ37sKlsBuTxo+jTZs2\n/yrn5eWFtaWG/A5OlK6iJiykPEpVIZTKO3QevIjF337K3JPH021ryZIljBw5isrVanDn9j2SkoYD\n4gKOpKSlLFgwgJEjh2fpcyiVSnx8fKhfvz42NjbZjucbFfWMiIePgdKvj+n1ZRCEAzx//pw+vboz\nJnw2L2N9EbSjQXEZhTIIpd6CRo0aZattGekhFVeDIZiFEZaKv8tYOpycnFi6eFG6ZRQKBcuXLKad\nbwea9fyc1n0+AQRioiJZ8+MIBn81KM3knQA7duxgwsRJ/G/QCJYvWEz080jg7SW4sVhYZLySLDY2\nFltb23d6m3FxcdjbFyEmJhEraw2zZ03hs8+ynv26cqWK7Nt7GhgD/IG4+GIiMdEKmjRpwocffsjm\nrds5dTaEZMX3KBValFpY578aCwuLLLdrDKRwf0pBgzHJSwNzZjFFzZy5cOECk3/4iS2bN5Ks1VKt\nRk1GjviGLl26pHued5MmVK5Rn6Xzl5OYEICY0bg1MAwojIXFJH7/fRY9ery7tBnEfHctW3bi7t2b\naDQWrFixmG7dugIQGRlJkSJlQNEVXXJ/lMptCMJszpw5RLVqWYsKeOLECerWbQf0BVYDFigUcXh6\nuhIUFIRarUav17N792727z+Ai4szfn5+crxgiWGsKWqLT4QbVHBAHXdjtCd5cjlL1btIJX+WKXXo\n9XpBp9MZrMHa2lr4ZOAwQaEYK4CQsu0RNBoHoXDRcsLIkSPTPb9kyUqCQvGrAHoBzgnW1k7C1atX\nBUEQhJEjRwpgJ4Dudd1qTRWhX79+Wf58Op1O8PSsL6hUXQXYLCgUfoKLSykhOjo6zXPk+0JaGgTB\neDnmlp68bdBmpPayhVkMzMmIPYzMDEDly5cftVqNxuLtkIB6nFyK4urmnK4fNTY2lrt3byIIXyF2\nMjxRqZpy6tQpDh06xNSpcxBXyb1MOUOHIMRiY2OT+Q+WglKp5PDhQL780o169Rby+ecuXL9+jvz5\n82e5Tpm8S14amJPdEe8pjx8/ZsqUqdy9G0GbNk3o379fpga/hgwdyqOnMRw5cIKnTz4gWeuGxuJP\nho76hmVzp3P37p00o4vp9Xrs7BxJSDgIVAUSsLWtztat8+nZ83MePpwAbAMeAj1QKLegVB4i7OYF\nXF1ds//hZfIsxnJH/H7qjkEF+9ZyNUZ72cIsBubMjejoaKpVq09kZGu02qbs2vUb16+HMXXqFIPr\nGDN6NPXq1ad+w/oUdHZBL+hRqT5hxYJZ/Prr7HTDOyqVSlasWEy/fj6oVM0QhGDatq2Lt7d3Snxd\nT6ALYgKDZdhYX2P37h2yAZYxGhLp5BqEWbgjpDIHMrd0bNmyhejoCmi1c4B+xMdv49dfZyEIgsEa\nnJ2dOX78GO7Fnflnw1r+/nM5t6+FsO6vtfTo0SPD87t168rZs4dYsKANW7bMw99/GQqFgvr1awPf\nAbuBdqC4w9Kl86lbt242PnHWyM71SE5OloSO90mDMclGeqNcxyyMsLkhBkK3e+uILXq9LtMr3Jyc\nnJg6dSp379wm6ulTtm37J1Nzaj08POjVqxdNmzZ97QrZuHENXl7RQFtUqsqM/LYv3bunPsNCiixf\nvhyNJj8ajSUFC7px9epVU0uSSQWFgZsUyI6OLsAEwAOoBZxNo5zsE85lHj58SIUK1YmJGYUgVMfa\n+md8fV3w98/ZWBGZQa/Xv47xmle4cuUKFSt6IQg7gdrANAoUmMvz5/+N+S2TVYzlE159xrBEsT1r\nlDBGe9kiOz3hEKAjcMhIWmSMRJEiRTh+fB/Nmh3ggw9GMnBgVf74w/B8bVeuXCEwMJA7dwwb3MgK\nSqUyTxlgEBewCDRCzJyhAkYSHR0p55GTIGkFdf/vJgWyY4SvAteNJSQnkYq/Kzd1VKhQgd27N3Lp\n0jFmzPjx9aqwjDRMmPAj1at789FHv+DhUYN169bniD4pXJPMaihdujQIl3gzte4aCoUCOzu79E4z\nuo6cQAoajInSwE0KyLMjZF5z6dIlfvllDomJFxBDZAbTt28T2rVr8zoUpRRITk5Gp9MZnIAzs0RH\nR7Ny5Up27N6LVqulSsUPGPj5Z7Rv3x5Pz6kEB1cCRS0QtjN58nhUKlWO6JDJOjk06OaImGnDDTFt\nTFfE1Eb/JRyIQZwMrwW80qs0IyO8GyicyvHRwNYMzn1N3759cXd3B8De3h5PT8/Xa9Vf/QLn9P4r\ncqu91Pa9vb1N2v7b30Fq79+6dQsxm/cVRCPsiU6nYvPmza8Hz9Kq393dnXXr1hEWFoa3t3eG5bOy\nHxgYyKjRYwg5H4xCqcStZClat/DB19cXHx+fTNeX2vUYP34802bOxM2zIS7VmxDz6A6bT1xiybLa\ndPmoM1OnTuDAgQMolUpat95OUlJSmt9nZvZfYer7I7f3Z8+eTXBw8Gv7YCxyyNUwCtEmTgVGpuyP\nSqWcAHgDUYZUagyl+xGzOcoDc3mcW7duUbGiFwkJ+4FKwDbs7T8lIiI83SA3ly9fpk6dJiQmfgQI\nWFtvICjooMFhKA3hl6nTmPHrb9Tv+RWuFWtw9dgeIsKuEHnrKmVKFGFX4I5s94y3bdtGz76f0Pib\neTi6/Vu7NuEFR+cMp2nNiixbsjhb7cikjbEG5gKCHxhUsLNn0cy0dxUxPXcEYuf0AOLEhP9yC6gJ\nPDWkUmO5RaTh4U4Dqfi7pKAjPQ0lS5Zk8eJfsbJqgI2NKwUK/I9t29ZnGGVs9OgfiIsbiVY7D612\nPrGxwxg37t3kn4bq+C9nzpxh6oyZ9J6+hoibV5jXvzOnA9ZRWK2lqFNBzp09y7CvMx9S820NgiAw\nZPgIavWfgKNbee6c3k/AUD/+GtiBoFVzUFlYUn/wDP4O2MCNGzfSrjQLSP2+yIvk0MCcC2+yKkek\n7KeGAOxBzNz8aUaVZscn3BGYAxRCXIN6DjHMlkweplcvPzp29CUiIoJixYoZ1Lt88uQ5glDq9b4g\nlObJk/RjFWeG2XN+o3q7Xlw/uZ8TG9chCN2IerqOnYG3cXZ2Y+R3o/nph8nMmD4ty77r48ePE5vw\nkmJV6xNx7RwHf/sBXdJKoCjX9gwC5uHVewilG/mycNFiZkyfZrTPJ2N80jKvF08d4+LpY+mdmpYL\ndsx/9tML/lMfcU2+U0p9V4HDmdVqTGR3xHvOb7/NZ9SopcTH+wN6bGy6M336lwwcOMAo9ZcsU5YP\nR87hrwlf8vRBM8ThiN2ILpPJVKoUCIoXfDHwcwYOHJilNpYtW8asNduo9elEglbN4vL2UsDYlHcv\nYm3vS7cFm7hzej+Ki4HsCdxulM8m82+M5Y7YdOGhQQU7VCmSmfauIvp6HwFFEF2xqbkj3uZ7IA6Y\nkVYBqczSkMmjPH36lDJlStK27Qfkz++No2MLRo3qzuefZ/gUlgkUCIKe+Ogo4B7QBqiM+LczhkuX\ngvDxacH161mfManRaNAli1PPNNbWKJT333r3AWpLsYet0740eRB4mYxRojBoyyRbgD4pr/sAm1Ip\nYwPkS3ltC7RAXFORjlYzQCr+LinoMJaG+/fv49e7D67upRg4ahKnbt5DYSHgXqY4tWvXyNDflhkd\nTbwbc+3YHhydXdBYHAGCeJ0zjzPky1eQmzdD080UkpGGRo0ace/8MbSJ8ZRv1hkL2y0olF8AP6Cy\n6E3NnuKPyqMz+2jVvGmm2smMDlMhBQ3GJIdiR/wM+CCuj2iasg9QFNElC6Ir4zAQDJwE/gF2pVep\nPE/YzNDpdGzatIkrV65QtGhROnXqRL58+TI+8S1u375NnXoNsK/mQ6NJ67HM5wCAXpfMo+BDdPHr\nza8zptK3T58MajKMoYO/onHT5lRt1ZUioWe4e/spTyIro1ZXQ6ncy6QpExk7eiTLly3Nchvu7u7U\nqVuPazv9qeTbH99fVnFtbwDahJu4eU3DpXw1om5f537IcfpsW2uUzyWTc+TQYrgooHkqxx8gPp4B\nhCGGCTQY2SdsRly8eJE2bdti71SYshWrE3EvnItnT/L7iuX4+voaXE+tOvV46VabUj49EfR6nt++\nQnLiC+zdPkBjY0fsw3CCZgzg/NnTlCpVKsP6DGHuvPl8P3EyVnb5KeVanObNmqJUqoh7EcvSxYv4\n8ccf+WxA9nzQt2/fxqtuPVy9u+DR0u+1C0IQBB5cOEbQ0u9ZMGe2QVHkZLKGsXzCOy4+Nqhg60rO\nxmgvW8hG2ExITEykTNmytOr6Cf+sXUfko5tYWRegz+BhrF08k+NHjxo0r/fcuXM0bdWGhpM2AHDi\n19FEhd1BoXRBoQyj4cg55CtSkqvrf6VNpcJGnUVw5MgRfp42nZ07tmNjbY1KpcbDozw//fQTjRs3\nNkobt2/f5tOBX3L82FGKV62HSm1JZOgF8ttYMnv61HeyWssYF2MZ4cBLhhnhVhVNb4Rln3AuYkod\nAQEBFHUvw9/LlxDxYCh6/UviX2xk+ayZNGrpy7z584mJiWH27Nk0atYCb59WLFy4kBcvXvyrnvUB\nAbjUbIlSpebO0S1E3dSje3mF5ISjaF+M48wy0egWrdOGv/4OSFNPVr6LBg0a8M/mTWiTkoiOjiYq\n6inHjh3LsgFOTYObmxu7tv9DSPA5Rv+vO8P82rDRfyXXL1/MMQMshftTChqMSV5KbyT7hM2Ec8HB\nlK5QlXMng4FXqeUboFLXpoCjEydPHqRiFU8UhdzROLkDAlMW/snMOXM5dugAhQoVAiDq2XM0KT7g\nFxEP0CX5AJqU+loT/0TM3mGZ35HY2Jhc/ITGxd3d3ehLaWVyD4W014/9C7PoCb8dN8GUmFKHs5MT\nMVFPUJAMvFrxFYdedxltUiJ3HzzEomwdHofe5PaBG9zef5mo+4/ROpVl2Dffvq6nSGEXXkY9AqCA\nWzlUFusQY5gIoFxCgRKiS+PFkwc4FiyYph4pXBMpaABp6JCCBmOiVBi2SQGzMMIy4Ofnx9G92+n1\nxTAsrRpiZdMLK+sa1G/ekGN7thP19AlxkdG8jO2BLvEwupcnSHzWBK1WRUDAehITE8V6evTg4amd\n6JISKVbLhxJ1K6NUu6KyKIat0yaq9xcN9sPjW+j3cW9TfmQZM0ZObyQxpOLvMqWO4sWLM3nSRP5a\nOouCLi4Uc7tGc98G3L0ZjGeVitg5OJEY9QT0zVLOUCDompL4LBqVSvM6cHmZMmWoX78e1zfPdip8\nAAAAEflJREFUB6Bqr6G0mLqBphMX0mzSCqztnXhy/SyPzx/kswFpL9iQwjWRggaQhg4paDAmCgP/\nSQGzMMLvA7Gxsfz111/8+eefREZGZqkOhUKNNikfD24P4eaVlgSu/5uhgway8o8/SIx5Rr4Srig1\n8xEXQsSj1CzGtogzGrWKgm+5FvxXrUT98DIXlo8j+s41LPPZY1OoKNr4WG4GruTCku8IWPcXLi5p\nxTeRkclZ8pI7Qp6ilgeIjIykatV6REYWRxBssLU9w5kzRzJcIbZkyTJmzVqKUqlk9OhBDB8+nkeP\n1gI1AFCrBzFhQlHGjBnNwC+/4p+Tl0h4IRB14zSgx6lSI9S6aD7p6MPkSRP/VXdsbCwzZ81m/sJF\nJKNErbEgLiqS9r6+jBn1LZUqVcqhb0PmfcZYU9QOXTMolC+Nyjsao71sIRvhPMBXXw1n7twXwKs8\ncT/TsuUpAgPTngL2xx+r+OKLScTHLwK02Nh8ikqVSGzsAeADAJTKbxk/3o7vvx9PQkICvp26cDr4\nPAUq1EcQdDy7eBifpk3w/3MlGo0m1XaSk5MJCwsjKSmJEiVKUKBAAWN+dBkzw1hG+PB1w4xww3Km\nN8Jm4Y6Qir8rqzru3HmEmFzyFXW4fTv9oNWLFq0hPn4a4hL3lsTHT8HZuQSWlp0QQ50uw9p6BV27\ndgHA2tqandu3Erg5gD6NPOjftAqH9uxk/V/+aRpgALVaTbly5ahUqVKmDLAUrokUNIA0dEhBgzHJ\nSynv5XnCeQAfnwZs3z6T5OQ2gBVK5Y+0apX+AgVrayvg2VtHoqhatSJNm9py6tQUChTIxy+//EOF\nChVel1AoFHh5eeHllW5KLBkZyaOSyMwHQ5DdEXkAvV7P4MEjWLBgLiDg69sFf//l6QZcP3ToEK1a\ndSYhYQSgxdZ2NgcPBlKjRo1c0y0jk1mM5Y44Hvos41JA3TIOxmgvW8hGOA+RnJyMXq83OJ5tUFAQ\nixevRKVS8sUX/alatWoOK5SRyR7GMsInQlNLgvwudcrYG6O9bCH7hHOR7OpQq9WZCiju5eXF0qVz\nWbRozmsD/L58F++LBpCGDiloMCZ5KXaEWRhhGRkZ8yKHBua6AJcAHVA9nXKtEFMh3QBGGqI1p5Hd\nETJ5nq1btzJgwDCio5/QuHFz/P2XYm9vb2pZ7x3GckcEhRnmjvAqlSl3hAegBxYBw4GzqZRRAdcQ\ng7/fB04BPYAraVUq94RlZDIgJCSE7t378+jRUhISQtm3z5EuXfqaWpZMOuTQsuWriKmN0sMLCAXC\nAS2wFkg3Y4JZGGGp+LukoEMKGkAaOgzVsG/fPnS6LoiJdguRlDSTAwcCc11HTiIFDcbEhMuWiwF3\n39q/l3IsTeR5wmZEUlISDx8+5MmTJ6/jA8tkjIODA2r1dV6+FBCfXK9jZ+doalky6ZGGgT19/DBn\nThxJ78zdiMk6/8toYKsBLWfa9yr7hM2A5ORkvp84iXnzF4BKw8v4OLxq12Hu7BlUrlzZ1PIkT2Ji\nIl5eTbh5056kpIpoNKtZvHgGvXr5mVrae4exfMJnww1LKFDdPX9W2ttP2j7hOsAExME5gO8Q/ci/\npFWZ3BM2A/x69+FgcCj56/ck4eE9rG1tCdPY0NC7KSePHTEot5w5Y2VlRVDQflavXs2TJ0/w9t5E\n7dq1TS1LJh1yYfpZWi2cBsoC7ohZmLshDsyliewTzkVMoeP8+fME7t6LukR17gdu5slpZyKOwOOT\nO7H1/JBxEybluiaQxjXJjAYrKyv69+/PyJEjjW6A89p3kRfIoSlqHRH9vXWAbcCOlONFU/YBkoFB\nwE7gMvAX6cyMALkn/N6zPiCAfBWb8uiAP3rtKeA+gs6b5BdtUFrlZ8umZaaWKCNjfHKmJ7wxZfsv\nD4C3s8Du4I2BzhCzMMJSyZ9lCh2JiS8R1FYIupeAM+KTEgiCCwgCWm0SgiC88sXlGlK4JlLQANLQ\nIQUNxkQqWTMMITvuiGmI3ezzwAZADiQrQbwbN0J76yQFPBqjUPcBQoA1KBSbQAE1a9fLdQMsI5PT\n5KXMGtkxwruAikBVxAnM3xlFUQ4gFX+XKXS0atUKBysFti4uOFZRorJpiXXh6bh1+JKYoAAmjhud\n65pAGtdEChpAGjqkoMGo5KGAwtkxwrsRp14AnASKZ1+OjLFRqVTs370T59hrJN8LwsHNHftCVkTu\nnMuMn6bQqlWrjCuRkclj5KVEn8ZSsRXwB9ak8p48T1gCCILA6dOnOXfuHPb29rRp0wZbW1tTy5KR\n+RfGmid86X6cQQUrFrMzRnvZIqPGDVk9MgYxolDnNOqQjbCMjIxBGMsIXzbQCH8gASOc0ewInwze\n7wt8CDRLt1Dfvri7uwNgb2+Pp6fn69HYV76onNwPDg5m6NChudZeWvtv+91M0T7A7Nmzc/37T23/\n1TFzvx5SuT9fHTPF/RgcHPzaPhgNaXgaDCI7UlsBM4DGwJN0ypm8J3zgwAFJTMExhQ69Xs+dO3co\nUKAADg4OZv1dSFGDVHRIQQMYryd85cELgwpWKGprjPayRXYavwFYAK9ySx8HvkilnMmNsLmyb98+\n/Hp/zLOoaAS9ltZt2rJ65e/Y2dmZWpqMTKoYywhfe2iYES5fJG8bYUORjbAJuHfvHmXKeaDV2qBP\n/hyl+gZK1W7at29OwLq1ppYnI5MqRjPCjww0woVNb4Tl2BG5SG7q+PPPP0nWWaFP3gxMQp/sj6D3\nZvPGAOLiDBu0yEmkcE2koAGkoUMKGoxJXpqiZhZG2Bx59uw5gl4LuL4+pte5g0LBixeG9RLeFx49\nesSkyZNxK1kaC0tL8uUvQOs2bQkKCkKv12dcgUyeIy8l+pTdEe8pBw8epGXrj9Am10OvnQWEolR3\nx9WtEGE3rpnNUuXAwEB69OxFlUYtqN2uBy7uZdAmJnDh8C6ObViFR2l3Nqz/GxsbG1NLlcF47ojQ\niHiDCpZxsTFGe9lCNsLvKYIg0O9/n+K/ZhM6nYBCqcZSk8jePbvMJhZuUFAQLVt/SN8fFlKqco13\n3tcla/H/cQTOlrBl8yaz+WGSMkYzwo8NNMLOshHOFaQy/Sa3dQiCwIkTJ9i5cydOTk50796dkJAQ\ns/guBEGgVu06xCQJJMTFoFQqye9cBEsbB1zc3GnUqRf3Q69QsnJ1pvVpTcDa1dStWzfH9KSHFO5P\nKWgA4xnhm48TDCpY2tnaGO1lC7MIZWmuKBQK6tatazLjYip0Oh09e/YiPDyc/gOHUr9RE7Zv2ciy\n+X+SnDwYhfIix7Z8RNfho1BrLKjdrgdzfptrdt/T+0wORUjrgpi6yAOoRerpjUDMtBwD6BAzLnul\nV6lZ9IRlzIuxY8cSuGsvS/w3Y21tw7074XRs0Yy42F2IQf9ApW7PR0NrU7+DH4/CQ1kzfiC3boaa\nVriM0XrCt54Y1hMuWShTPWEPxKBli0g7xxzALaAGb9ZQpIvcE5Z5r4iNjWXuvHls2RuELjmZzq1a\nERYaTmJCAjAeWA9o0CUXJjFBnCWi0mjQapNNKVvGyOTQ9LOrmZJgIGYxRU0qcyCloEMKGiDndGzZ\nsoWatetRuGgxfhz/PaHXPEhMuANEArHASCAAhWINCTHRANy7folSpUvliB5DkMI1kYIGY2LiKWoC\nsAcx6eenGRWWe8Iy7xWPHj2ihFtJAEKCL5KU9AtiX8MS6IuFxbe4uh/FLn9l1BYWAARt9WfssEEm\n0yxjfLJhXw2JHJkR9YGHgFNKfVeBw2kVNgsjLIVRX5CGDilogJzTUbBgQSIeHgWgdNnShIdtJTm5\nISBgabmdfp/1Z9h3Y/Bt0YDSVb04ue1vYh8/oFOnTjmixxCkcE2koMGYpNXLPX7kIMePHErv1Iwi\nRxrCw5T/IxETg3qRjhGWB+bS4cqVK4SEhFCnTh1cXV0zPkHG5ERFRVGyVCl2HjmPTq+jW9t2PH9m\niSAkULJ0IVZv3MjtW6H069ERz+ZtuXRgOwf27cXDw8PU0mUw3sDc3aiXBhUs4WiZlfb2A98AZ1J5\nzwZQIfq+bBHTwE1M+T9VZJ9wGnTt1oMPPqhG9+5f4OZegYkTJ5pEh7GRggbIOR2Ojo583Ls340YM\nooC9IzsOHWbpmun88fci1m3bhk6XzLeDPyUxPg7b+CecDjppcgMshWsiBQ3GJIcSfXYE7gJ1gG28\nSWtfNGUfRFfGYSAYMe3bP6RjgMFMjHBmCQgI4O91W4GTCMITENYyYeJUbt++bWppMgYwY8YMrC2U\n9GjXlMB/NuLqXhKXwkVZ9+dyOvjU5YPy5Xj44D5fDx1C8eJyasT3kRwamNsIlACsEY1t65TjD4A2\nKa/DAM+UrRLwU4ZaMy0j8+Q5d8SgQYNYuOg8uuQ3bhyFwonVq+fQo0cPEyqTMRSdTsfWrVuZO28e\nwcHBKBVK6jeoz1eDBtGkSRN5ibJEMZY74uHzJIMKFrG3MEZ72cIsBuYyS6VKldDrVgMRgAsQgiDE\nUqVKFRMrkzEUlUpFhw4d6NChg6mlyJiCPPQbaxbuiMz6uz777DMqVCiJQuGBSt0IqEvHTu2oWLFi\nrurICaSgAaShQwoaQBo6pKDBmCgM3KSA3BNOBYVCwcWLZ1iwYAEXL16kSZOv6NKli6llycjIGEhe\n8jbJPmEZGRnJYCyf8ONYrUEFnfNpjNFetpB7wjIyMu8deagjLPuEcxMp6JCCBpCGDiloAGnokIIG\nY5KX0hvJPWEZGZn3Dqkk8TQE2ScsIyMjGYzlE456YVhoUkdbtTHayxZm4Y6QkZGRkSpmYYSl4u+S\ngg4paABp6JCCBpCGDiloMCayT1hGRkbGhCilYmENQPYJy8jISAZj+YRjEnQGFcxvrTJGe9lC7gnL\nyMi8f+SdjnC2fMKTgfOIcTP3IoZ4kyRS8XdJQYcUNIA0dEhBA0hDhxQ0GBOFgf+kQHaM8FTE/OGe\nwCbge6MoygGCg4NNLQGQhg4paABp6JCCBpCGDiloMCbmMjAX+9ZrO+BJNrXkGM+fPze1BEAaOqSg\nAaShQwoaQBo6pKDBmEjEvhpEdn3CPwC9gXjElB8yMjIypicPWeGM3BG7gZBUtnYp748BXIHfgVk5\nIzH7hIeHm1oCIA0dUtAA0tAhBQ0gDR1S0GBMlAqFQZsUMJYKV2A7Yk6l/xIKlDZSOzIyMu83N4Ey\n2awjM3NinwGO2WzPZJR96/VXwCpTCZGRkZExR9YjuiaCgQDA2bRyZGRkZGRkZGRkZCTKcECP6fwv\nUllcMg24kqJlA1DABBq6AJcAHVA9l9tuBVwFbgAjc7ntVyxHTKUdYqL2X1EC2I94LS4Cg02gwQo4\nifh3cRn4yQQaXqECzgFbTajhvaUEEAjcwnRGON9br78ClppIhw9vZqX8nLLlNh5AOUQDkJtGWIU4\nUOsOaBD/8CvkYvuvaAhUw/RGuDDiYicQ59pfwzTfh03K/2rgBNDABBoAvgZWA1tM1L5JyK1QljOB\nb3OprbSQyuKS3YhPBCD2QIqbQMNV4LoJ2vVCNMLhgBZYC/iaQMdhxFFxU/MI8YcIIA7xCamoCXTE\np/xvgfhDGWUCDcWBDxE7R9KYO5ZL5IYR9gXuARdyoa2M+AG4A/TBND3Q//IJ4tQ+c6EYcPet/Xsp\nx2TEp4NqiD/MuY0S8ccgAvHp6LIJNMwCRvCmg2I2GCuK2m7ER6v/Mgb4Dmjx1rGc/JVLS8doRD/T\nmJRtFOJF72ciHaToSALWmFBDbiPHNE0dO8TZRkMQe8S5jR7RLVIA2Al4Awdysf22wGNEf7B3LrZr\nFlRC/HW9lbJpER9FTT2dzRVxIMRU9AWOIg6KmJLc9gnXQRwbeMV3mG5wzh3T+4RB9I3vBIaaWkgK\n44BvcrnNHxGfkG4BD4EXwMpc1mA2mHJgTiqLS1ohjoYXMlH7b7MfqJGL7akRV0S5I/ofTTUwB9Iw\nwgpEY2PKJf+FAPuU19bAIaCZ6eTQGHl2RI4ShumMsFQWl9wAbiM+ep0D5ptAQ0fEnkcC4uDQjlxs\nuzXiLIBQxJ6wKfAHHgAvEb+HnHJLZUQDRFdAMG/uh1a5rKEycDZFwwVEv6wpaYyZzY6QkZGRkZGR\nkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRMSL/B77Ns1I+jtr1AAAA\nAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f8f961f8f10>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Grafico de puntos con matplotlib\n",
    "N = 100\n",
    "x1 = np.random.randn(N) #creando vector x\n",
    "y1 = np.random.randn(N) #creando vector x\n",
    "\n",
    "s = 50 + 50 * np.random.randn(N) #variable para modificar el tamaño(size)\n",
    "c = np.random.randn(N) #variable para modificar el color(color)\n",
    "\n",
    "plt.scatter(x1, y1, s=s, c=c, cmap=plt.cm.Blues) \n",
    "plt.grid(True)\n",
    "plt.colorbar()\n",
    "\n",
    "fig = plt.scatter(x1, y1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Interfase orientada a objetos de matplotlib"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "La idea principal con la [programación orientada a objetos](http://es.wikipedia.org/wiki/Programaci%C3%B3n_orientada_a_objetos) es que a los objetos que se pueden aplicar funciones y acciones, y ningún objeto debería tener un estado global (como en el caso de la interfase con plt que acabamos de utilizar). La verdadera ventaja de este enfoque se hace evidente cuando se crean más de una figura, o cuando una figura contiene más de una trama secundaria. \n",
    "\n",
    "Para utilizar la [API](http://es.wikipedia.org/wiki/API) [orientada a objetos](http://es.wikipedia.org/wiki/Programaci%C3%B3n_orientada_a_objetos) comenzamos de forma similar al ejemplo anterior, pero en lugar de crear una nueva instancia global de `plt`, almacenamos una referencia a la recientemente creada figura en la variable `fig`, y a partir de ella creamos un nuevo eje `ejes` usando el método `add_axes` de la instancia `Figure`:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEgCAYAAACuDOSlAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xd4VGXax/FvaNKlQyBIJICAiIBIEyRCKCpVapQmuLq8\n69pWVxcWicuugqwFXBVBUZCVoiJNQJqhSReUphQDGyEUAYEAIZCc948nhECADGFmnjOZ3+e65iJT\nz825Zuae+6kgIiIiIiIiIiIiIiIiIiIiIiIiIiIiIgHiEeAb20GIiIgde4DTwMkMl9EePvcm4DVg\nb9pr7ACev8Lj2gFrgUTgN2ASUCHD/f2AlLRjHwc2Ag9e1/9CRES8Lg5okc3nzgJWAzWBXEBDTJIY\nleExXTFf+j0xCaUs8FHacYulPaYfsCzt7xDgSeAUcHM24xIRES+4VoLoByy/yn0tgTNcWgkANADO\nA5UxX/Z7yVxVhACbgVeucpxCQCpQL6vgRXwtl+0ARCwLycZzWmGqh32X3b4W+BWTQG4DKgKfX/YY\nB/gy7TUulwd4DNPctDMbcYl4VR7bAYhYFALMwPzqv+B5TDPQtZQCDlzlvoS0+0tluH65AxnuB2gE\nHEuLYyfQGZMkRKxSgpBg5gAdgSXX+bzDQJWr3BeK6Yw+nOH63is85nCG66uBZtcZg4jPqYlJ5Pot\nwnRKh112e0NMs9ISTIf1r0D3yx6TC+gCLPZxjCI3TAlCgl12+iAWp12+xIxiyo1pJvoUeA/YjalO\nngf+DkQD+YFywIdAYeCtGw1cRER8J47M8yC+TLuvH1cfxQRm2Opw4H9pr7ET+OsVHteBi/MgjgD/\n5dLRT325OMxVJGhUBL4FtgJbgKfSbo/BlN4b0y5tbQQnkoX+qBlIgpwvO6nPAc8CmzAl9QZgIab0\nfjPtIuJWtwO/2A5CxCZfJogDXBwKmAhs52JpnZ12XxF/mQFEAN1sByISDMIxQ/0KA0Mxa+D8gBlv\nXuyqzxIREWv88Uu+MBAL/BPzy6wMF8eAD8OMCR+Q8QkRERHO7t27/RCaiEjQ2s3V5/MAvh/mmhcz\nKmQSJjkAHML0QziYIX8NLn/S7t27cRxHl8suQ4cOtR6D2y46JzonOifXeRk+HKdBAzDNqNfkywQR\ngmlC2ga8neH20Ax/d8YsXCYiIr62cCGMGgVffpn1Y/FtJ/U9QC/gR8xwVoBBmElDdTAVRBzwhA9j\nEBERgLg46N0bpk6FsMsXAbgyXyaIFVy5Qpnnw2PmaJGRkbZDcB2dk8x0TjIL+nNy+jR07gyDBkHz\n5h4/za3DTR3HcWzHICIS+BzHVA4hITBxovkXCDH/XjMHaDVXEZGcbPRo2LoVVq5MTw6eUgUhIpJT\nxcZCz56wejWEh19ylycVhFZzFRHJieLj4eGHYdKkTMnBU0oQIiI5TVISdOkCzzwDUVHZfhk1MYmI\n5CSOA489BidPmiGtV+l3UCe1iEiw+eADWLPG9DtcZ6f05VRBiIjkFKtWQadOZsRSlWsus6ROahGR\noJGQAN26wfjxWSYHTylBiIgEuuRk6NoVnngCHnzQay+rBCEeq1WrFsuWBdb2yf369WPIkCG2wxDx\nrWefhVKlYPBgr76sOqnFY1u2bPHr8fbs2UPlypU5f/48uXJl77dMSEjIhbZWkZzpk09g8WLTMZ3N\nz8nVKEGIK50/fz797xsdsKABD5JjrV8Pf/0rLF0KN9/s9ZdXE5N4LDw8nMWLFxMTE0P37t3p27cv\nRYsWpVatWmzYsCH9cSNGjCAsLIyiRYtSvXp1lixZApgv6uHDh1OlShVKlSpFjx49OHbsGGCqhVy5\ncjF+/HgqVapEy5YtaZ626mSxYsUoUqQIa9asYffu3bRo0YJSpUpRunRpevXqxfHjx9OPvXHjRurV\nq0fRokXp2bMnSUlJl/wfxo0bR9WqVSlZsiQdO3YkISHB16dNxDcOHTKT4caMgRo1fHIIJQjxWMam\nmtmzZxMdHc3x48fp0KEDTz75JAA///wz7777LuvXr+fEiRMsWLCA8LRp/qNHj2bWrFksW7aMhIQE\nihcvzp/+9KdLjrFs2TJ++uknFixYkN7fcfz4cU6ePEnDhg0BGDx4MAkJCWzfvp34+HhiYmIASE5O\nplOnTvTt25djx47RrVs3vvzyy/S4lyxZwqBBg/j8889JSEigUqVK9OzZ05enTMQ3zp+HHj2gVy94\n6CHb0fidI+4THh7uLFq0yImJiXFatWqVfvvWrVudAgUKOI7jODt37nTKlCnjLFq0yElOTr7k+TVq\n1HAWL16cfn3//v1O3rx5nZSUFCcuLs4JCQlx4uLi0u+/cFtKSspVY/rqq6+cunXrOo7jOEuXLnXK\nly9/yf1NmjRxhgwZ4jiO4/Tv39958cUX0+9LTEx08ubN6+zdu/c6z4SIZc895zht2jjO+fPZfgnM\npm3XpApCsqVs2bLpfxcsWJCkpCRSU1OpUqUKb7/9NjExMZQtW5bo6Oj0Zpw9e/bQuXNnihcvTvHi\nxalZsyZ58uTh4MGD6a9VsWLFax734MGD9OzZk7CwMG6++WZ69+7NkSNHANi/fz8VKlS45PGVKlVK\n//tC1XBBoUKFKFmyJPv27cv+iRDxt88+gxkzzL+5c/v0UEoQ4nXR0dEsX76cvXv3EhISwosvvgjA\nLbfcwvz58zl27Fj65fTp04SGXtymPGMz1pVGHw0aNIjcuXOzZcsWjh8/zqeffkpqaioAoaGhmb7s\n9+7dm/53+fLl2bNnT/r1U6dOceTIkUxJRcS1fvgBnn4avvoKSpTw+eGUIOS6OdcYFbRjxw6WLFnC\n2bNnuemmm8ifPz+5037l/PGPf2TQoEH873//A+Dw4cPMmjXrqq9VunRpcuXKxe7du9NvS0xMpFCh\nQhQtWpR9+/YxcuTI9PsaN25Mnjx5GD16NOfOnWP69OmsW7cu/f7o6Gg+/vhjfvjhB86ePcugQYNo\n1KgRt9xyS7bPhYjfHD1q+hveeQdq1/bLIZUg5LpcmFdw+a/7C9fPnj3L3/72N0qXLk1oaCi//fYb\nr732GgBPP/00HTp0oHXr1hQtWpTGjRuzdu3aTK9xQcGCBRk8eDD33HMPJUqUYO3atQwdOpTvv/+e\nm2++mfbt29OlS5f05+XLl4/p06fzySefULJkSaZNm0aXLl3SX69ly5YMGzaMLl26UL58eeLi4pgy\nZYpPzpOIV6WkmL0dOnc2GwD5iVtnEDnX+pXqb+Hh4RQtWpTcuXOTN2/eS77URER8btAgMxHum28g\nj3emr2m5by8JCQkhNjaWEn5o8xMRucT06aZDet06ryUHTylBeMhNFY2IBIlt28wCfPPnQ+nSfj+8\n+iA8EBISQlRUFPXr12fcuHG2wxGRYHD8uOlzGDkS7rrLSgiqIDywcuVKQkNDOXz4MK1ataJ69eo0\na9Ys/f4qVapcMtJGxM0iIiLYtWuX7TDkWlJToXdvaNUK+vWzFoYqCA9cGKdfunRpOnfunKmTevfu\n3TiOY/0ydOhQ6zG4LRa3xOGvWM6lnGN1/Gr+ufSfRH4SSeFXC9N0fFNivo1hxd4VJJ9P1o+ZQPDP\nf5phrW++aTUMVRBZOH36NCkpKRQpUoRTp06xYMEChg4dajssEcD0jf185GcW/bKIRb8sYunepVQs\nWpGoylG80OQFmt3SjCI3FbEdplyPOXNg3DjTKZ0vn9VQlCCycPDgQTp37gyYJagfeeQRWrdubTkq\nCWb7T+5n8S+LWRS3iMW/LCZXSC5aVW5Fj9t78EG7DyhbuGzWLyLutHMn9O8PM2dCuXK2o1GCyMqt\nt97Kpk2bbIfhkcjISNshpHNLLG6JA7Ify/Gk4yzduzQ9KSScTKDFrS2IqhzF35v9nSolqmhTpJwg\nMRE6dYJhw6BxY9vRAJoo5xUhISEEUrzibmfPn2X1r6tZHLeYRb8sYvOhzTQKa0TLW1sSVTmKuuXq\nkjtX9hdp0/vVhRwHunc3m/6MGwd+SPieTJRTgvACfeDkRqQ6qWw+uNn0I8QtYuX/VlK9VPX0hNCk\nYhMK5C3gtePp/epCI0aYCXFLl0L+/H45pBKEn+gDJ9drz+970juWF8ctpkSBEukJITI8khIFfDdr\nX+9Xl1m4EPr2hbVrISzMb4dVgvATfeAkK7+d/o1v475NrxISkxOJqhxF1K1RtKzckltu9t+Ksnq/\nukhcnOlvmDoV0rbY9RclCD/RB04ul+qksnbfWmb/PJv5u+ez6+gumt3SzCSFylHcXvp2ax3Ler+6\nxOnTcM898Oij8NRTfj+8EoSf6AMnAInJiSzYvYDZO2Yzd+dcShcsTftq7Xmw2oM0rNCQvLnz2g4R\n0PvVFRzHzJQOCYGJE/3SKX05reYq4mN7f9/LnB1zmL1jNt/Ff0ejsEa0r9ael+99mVuL32o7PHGr\n0aNh61ZYudJKcvCUWyNTBSGulLHpaPaO2RxIPMADVR+gXbV2tI5oTdGbitoOMUt6v1q2dCn06AGr\nV0N4uLUwbDcxVQQmAmUABxgLjAZKAFOBSsAeoDvw+2XPdVWCSElJoX79+oSFhTF79uxM9+sDl7Nd\n3nRUplAZ2lVtR/vb2tOwQsMbmpNgg96vFsXHQ8OGplkpKspqKLYTRLm0yyagMLAB6AQ8CvwGvA68\nCBQHXrrsua5KEG+++SYbNmzg5MmTV9xDWR+4nOdqTUftqrUL+KYjvV8tSUqCe++Frl3hr3+1HY31\nPogDaReARGA7UAHoAFwYzzUBiCVzgnCNX3/9lblz5zJ48GDetLyyovjO1ZqO/lDvD0zrNi0gmo7E\nxRwHnnzSNCm98ILtaDzmr07qcKAusAYoCxxMu/1g2nXXevbZZxk5ciQnTpywHYp42YWmozk75vD1\nzq8pU6gM7au1Z0y7MQHZdCQuNnas6XNYvdrVndKX80eCKAx8CTwNnLzsPiftkklMTEz635GRkVYW\nXZszZw5lypShbt26xMbGXvOxbohXsna1pqMh9w4J+Kajq4mNjc3y/Ss+tGoVvPyyGbFUuLC1MLLz\nPvB1KssLzAHmAW+n3fYTEIlpfgoFvgWqX/Y8V/RBDBo0iE8//ZQ8efKQlJTEiRMn6NKlCxMnTrzk\ncWrTda+rNR21r9ae1hGtg3KvBL1f/SghAe6+Gz74AB580HY0l7DdSR2C6WM4Ajyb4fbX024bgel7\nKIbLO6kBli5dyr///W+NYgoAjuOwIWEDU7ZMYerWqdx80810uK0D7aq1U9MRer/6zZkzZqRS27Yw\nZIjtaDKx3Ul9D9AL+BHYmHbb34DhwDRgABeHuQYErbnvbtsOb2Py5slM2ToFgOha0XzT6xtqlq5p\nOTIJOikp8PDDplN68GDb0WSbW7/xXFdBXIt+kdkTdyyOKVumMGXrFI6eOUqP23vQs1ZP7gq9Swn9\nKvR+9THHgYEDYfdu+Ppr69uGXo3tCkLEJxJOJjBt6zQmb5nML8d+oWvNrrxz/zs0vaUpuUJy2Q5P\ngt2wYWY/6dhY1yYHT7n1J5YqCLnEkdNHmL59OpO3TGbjgY10vK0j0bWiaXFrC9csghco9H71obFj\n4fXXzYilsq4ewW+9k/pGKEEIJ8+eZNbPs5i8ZTLL/7ecNhFtiK4Vzf1V7yd/Hv/supUT6f3qIzNn\nmqalZcugShXb0WRJCcJP9IHznqTzSczdOZcpW6bwze5vaHZLM6JrRdPhtg5BOSTVF/R+9YGVK6Fz\nZ5g7F+rXtx2NR5Qg/EQfuBtzLuUci+MWM3nLZGb9PIu65eoSXSuaLjW7+HTrzWCl96uXbd0KLVrA\np59C69a2o/GYEoSf6AN3/VKdVFb8bwWTN0/my+1fUrl4ZaJrRdP99u6EFgm1HV6OpverF/36q9kV\n7tVX4ZFHbEdzXTSKSVxn++HtfLTxI6ZsmULJgiXpeXtP1jy2JscucyE52LFjZhLcU08FXHLwlCoI\nL9AvsmtLTknmq+1fMWbDGLYf3k7/uv3pVbuXJrBZoverF5w5Y5qTGjSAN96wHU22qInJT/SBu7K9\nv+9l7IaxjN80nuqlqjOw/kA6Ve9EvtyBPTY80On9eoPOn4du3aBgQdPvkCsw596oickLkpKSaN68\nOWfPniU5OZmOHTvy2muv2Q7LtVJSU5i/az7vr3+fVb+uonft3izps4QapWvYDk3kxjkO/OlPkJgI\nU6cGbHLwlBJEFvLnz8+3335LwYIFOX/+PE2bNmXFihU0bdrUdmiucjDxIOM3jueDDR9QulBpBtYf\nyLRu0yiYt6Dt0ES8Z9gwWL8+R8yS9oQShAcKFjRfcsnJyaSkpFCihIZeglk1ddneZby//n2+2f0N\nXWp04YvuX1C/fGCMAxe5LmPHmr2kV66EIsExJ0cJwgOpqanUq1eP3bt3M3DgQGrWDO7O1d+Tfmfi\nDxMZs34MAAPrD2RMuzEUy1/McmQiPjJzJsTEmFnSLl9Cw5uUIDyQK1cuNm3axPHjx2nTpg2xsbGZ\ndowLhh3l1u9fz5j1Y/hy+5e0iWjD+w++z72V7tWqqS6nHeVu0MqV8Ic/mFnSAbCEhje59ZPt2lFM\nw4YNo0CBAjz//PPpt+XkUSGnz51mypYpvL/+fQ6fOswTdz1B/7r9KVs4eH5F5TQ5+f3qdQE6S9oT\nGsXkBb/99ht58uShWLFinDlzhoULFzJ06FDbYfnc9sPb+WDDB0z6cRKNKzbmlchXaBPRJuh3Y5Mg\n8uuv8MAD8OabOS45eEoJIgsJCQn07duX1NRUUlNT6d27Ny1btrQdls+sil/FK0tfYdOBTQyoO4AN\nj2+gUrFKtsMS8a8gmCXtCTUxeUFOKNkvJIbtv21ncLPB9KvTTxPacqic8H71qRwwS9oTmkntJ4H8\ngVNiCD6B/H71uRwyS9oT6oOQq1JiELlMkM2S9kRQnIFt27Zlui1Yh/2til9F20lt6fllTx6q8RA7\n/7yTx+96XMlB5B//MLOkp08PilnSngiKBNG9e3dGjBiB4zicPn2aP//5z7z00ku2w/IrJQaRaxg7\n1jQpzZ0bNLOkPREUCWLNmjXEx8fTuHFjGjRoQGhoKN99953tsPxCiUEkCxdmSc+fH1SzpD0RFH0Q\nefLkoUCBApw5c4akpCQqV65Mrhzevqg+BhEPBPEsaU/k7G/JNA0aNCB//vysX7+e5cuX89lnn9Gt\nWzfbYfmEKgYRD23dCg89BJMmQX0tMHklQTHMdd26ddx9992X3DZx4kT69Onjldd3w7DBdfvWMeTb\nIaoYJEtueL9aFx9v9pJ+7bWgnQineRBeEB8fT58+fTh06BAhISE8/vjjPPXUU5c8xuYH7uTZkwxa\nPIgvtn9BTPMYHq37qBKDXFPQJ4hjx6BpU+jfH/7yF9vRWKME4QUHDhzgwIED1KlTh8TERO666y5m\nzJhBjRoXd0iz9YGbu3MuA78eSItbW/BG6zcoUUD7VEjWgjpBBMksaU9oopwXlCtXjnLlygFQuHBh\natSowf79+y9JEP52+NRhnvnmGVbFr+KjDh8RVTnKWiwiAeP8eXj4YbjlFhg50nY0ASEoOqm9Zc+e\nPWzcuJGGDRtaOb7jOEz6cRK13q9FaOFQNg/crOQg4omMs6Q//lizpD2kCsJDiYmJdO3alVGjRlG4\ncOFM9/t6w6C9v+/lj1//kf0n9zMneg53V7g76yeJoA2DgIuzpINkL2lvUR+EB86dO0e7du24//77\neeaZZzLd78s23ZTUFN5d9y7/WPoPnmv8HC80eYG8ufP65FgSHIKuD2LsWHj9dTPnQRPh0qmT2gsc\nx6Fv376ULFmSt95664qP8dUHbuuhrQyYNYB8ufMxrv04bit1m9ePIcEnqBLEjBnwf/9n9pLWRLhL\nKEF4wYoVK7j33nupXbt2+t7Lr732Gm3btk1/jLc/cGfPn+XV5a/y3vr3GHbfMB6/63FyhajNVLwj\naBLEihVmItzcuZoIdwVKEH7izQ/cd/Hf8disx6hasirvPfAeFYpW8MrrilwQFAkiB+8l7S0a5hpA\nUp1U/rbob3z646eMajuKrjW7plcsInId4uPh/vuDei9pb1GCcIGz58/Sd0Zf9p/cz+aBmylZsKTt\nkEQC04W9pJ9+OmiX0PAmXzdsjwcOApsz3BYD/ApsTLu0zfy04HHi7Ake+OwBklOS+abXN0oOItl1\n5gx06GASRBAvoeFNvk4QH5M5ATjAm0DdtMt8H8fgWgcSD9D8k+ZUK1GNz7t9ToG8BWyHJBKYzp+H\n6GjNkvYyXyeI5cCxK9we9I3rO47soMlHTehSowvvPfgeuXPlth2SSGC6MEv61CnNkvYyW2fyz8AP\nwEdAMUsxWLN231qaf9KcQc0G8fd7/67OaJHschzTnLRhg/aS9gEbCeJ94FagDpAABNWSivN2zuPB\nzx7kg3Yf8Fi9x2yHIxK4UlPNJLiVK2HhQu0l7QM2RjEdyvD3h8DsKz3I12sb2TDxh4m8sPAFZvac\nSZOKTWyHIxK4UlLgscdg1y6THIoWtR2R62VnTS5/tG2EY5LAHWnXQzGVA8CzwN3Aw5c9xzUT5fr3\n78/XX39NmTJl2Lx58xUfk9XEI8dxeH3l67y3/j3mPzKfGqXtLRUuEvAT5c6dg9694bffYOZMKFTI\ndkQByQ0zqScDzYFSmOGuQ4FITPOSA8QBT6Tdl5FrEsTy5cspXLgwffr0yVaCSHVSee6b51gct5h5\nj8wjrGiYL8MVyVJAJ4izZ6FnT5MkvvgC8ue3HVHAcsNM6ugr3Dbex8f0qmbNmrFnz55sP/9fy/7F\n2n1rWdZvGcULFPdeYCLB5swZs7ZSoUIwdao6pP1AM6l96MeDPzJ67Wi+f/x7JQeRG5GYaCbBhYbC\nhAmQR19d/qCz7CWXd6rf0+we+s3ox/CWw6l4c0V7gUnQC/gNg44fhwcegBo14IMPILfmDPmLWwfg\nu6YPAsxWo+3bt7+uPohhS4fx3a/fMffhuZrnIK4SUH0QR49CmzbQsCGMHq1JcF7khj6IoHShaWnj\nExuVHESy69AhaNXKrMj6+uugz5LfKR1nITo6miZNmrBjxw4qVqzIxx9/fM3Hn0s5R78Z/RgRNUIj\nlkSya/9+aN4cOnVScrDIrWfdVU1MWclYsqtpSdzO9U1Me/dCy5ZmItxLL9mOJsdSE5OfqWlJ5Abt\n2gVRUfDcc/DUU7ajCXpqYvISNS2J3KDt2+G++2DQICUHl1AF4SUjvxtJ2cJlebTOo7ZDEQk8P/xg\ntgkdMcIsoyGuoAThJRN/mMjkLpPVtCRyvdavh3bt4J13oFs329FIBkoQXrL/5H5ql61tOwyRwLJy\nJXTuDB9+aGZKi6soQXjJ3RXu1q5wItdjyRLo0QP++18z10FcRwnCSxqHNbYdgkjgmD8f+vQxK7I2\nb247GrkKjWLyEiUIEQ/NmAF9+5q9HJQcXE0JwgPz58+nevXqVK1alREjRlzxMQ3DGvo5KpEANHUq\n/PGPMG8eNNaPKrdTgshCSkoKTz75JPPnz2fbtm1MnjyZ7du3Z3pcqYKlLER3KTet2OmWWNwSB7gr\nFis++QSefRYWLYJ69WxHIx5QgsjC2rVrqVKlCuHh4eTNm5eePXsyc+ZM22FdkZu+gNwSi1viAHfF\n4nfvvw9DhsC330KtWrajEQ95kiCeAoJ2t5t9+/ZRseLF/RzCwsLYt2+fxYhEAsxbb5kF95Yuhdtu\nsx2NXAdPEkRZYB0wDWiLexf48wlNfBO5Af/6l6keli2DypVtRyM+kguTHKYAu4BXgQgfHs9xi1Wr\nVjlt2rRJv/7qq686w4cPv+QxERERDqCLLgFxiYiI8P0HJzXVcQYPdpyaNR1n/37fH0+uW9r74Zo8\nnQeRChwADgIpmCanL4BFwAsevkZAql+/Pjt37mTPnj2UL1+eqVOnMnny5Eses2vXLkvRibiQ48Dz\nz5uJcLGxULq07YgkmzxJEE8DfYAjwIfA88A5TFWxkxyeIPLkycN//vMf2rRpQ0pKCgMGDKBGjRq2\nwxJxp9RUePJJ2LDBJIjiQdt9mSN40sD+CjAe2HuF+2oC27wakZFWAYlIwEhJMZv87NoFX38NRYva\njkiuwZMNgzzppB7KlZMD+CY5BAxPJtD5S3h4OLVr16Zu3bo0aNDAb8ft378/ZcuW5Y477ki/7ejR\no7Rq1Ypq1arRunVrfv/9d2uxxMTEEBYWRt26dalbty7z58/3eRzx8fHcd9993H777dSqVYvRo0cD\nds7L1WLx+nk5dw569YL4eLOMhpKD+JDt/pssnT9/3omIiHDi4uKc5ORk584773S2bdtmLZ7w8HDn\nyJEjfj/usmXLnO+//96pVatW+m0vvPCCM2LECMdxHGf48OHOiy++aC2WmJgY54033vDL8S9ISEhw\nNm7c6DiO45w8edKpVq2as23bNivn5WqxePW8JCU5TufOjvPgg45z5ox3XlN8Dg86qTVRLpvcOIHO\nsdAs16xZM4pf1s48a9Ys+vbtC0Dfvn2ZMWOGtVjA/+elXLly1KlTB4DChQtTo0YN9u3bZ+W8XC0W\n8NJ5OXPGLNedKxdMnw7589/4a4prKEFkk9sm0IWEhBAVFUX9+vUZN26ctTgADh48SNmyZQEoW7Ys\nBw8etBrPO++8w5133smAAQP81tx1wZ49e9i4cSMNGza0fl4uxNKoUSPAC+clMREefNB0RE+ZAvny\neTlisU0JIpvcNoFu5cqVbNy4kXnz5vHuu++yfPly2yEB5jzZPFcDBw4kLi6OTZs2ERoayl/+8he/\nHTsxMZEuXbowatQoihQpcsl9/j4viYmJdO3alVGjRlG4cOEbPy/Hj0Pbtmby28SJkEc7B+REShDZ\nVKFCBeLj49Ovx8fHExYWZi2e0NBQAEqXLk3nzp1Zu3attVjKli3LgQMHAEhISKBMmTLWYilTpkz6\nl/Fjjz3mt/Ny7tw5unTpQu/evenUqRNg77xciKVXr17psdzQeTl6FKKioE4dGDsWcmujrJxKCSKb\nMk6gS05OZurUqXSwtGXi6dOnOXnyJACnTp1iwYIFl4zk8bcOHTowYcIEACZMmJD+pWRDQkJC+t9f\nffWVX86K4zuyAAANf0lEQVSL4zgMGDCAmjVr8swzz6TfbuO8XC2WbJ+XQ4fgvvsgMtLsIZ1LXyHi\nf1Z79z01d+5cp1q1ak5ERITz6quvWovjl19+ce68807nzjvvdG6//Xa/xtKzZ08nNDTUyZs3rxMW\nFuaMHz/eOXLkiNOyZUunatWqTqtWrZxjx45ZieWjjz5yevfu7dxxxx1O7dq1nY4dOzoHDhzweRzL\nly93QkJCnDvvvNOpU6eOU6dOHWfevHlWzsuVYpk7d272zsu+fY5To4bjvPyyWUpDAhoejGJyV0P6\nRWnxi4grbNoEnTqZzX5eesl2NOIFnkyUU8+SiFzbtGnwpz/Be+9Bt262oxE/UoIQkStLTYWXX4ZJ\nk2DhQtMpLUFFCUJEMjtxwiydcfw4rFunFVmDlIYgiMildu6ERo2gQgVTOSg5BC0lCBG5aMECaNoU\nnnrK7ASn2dFBzdcJYjxmk6HNGW4rASwEdgALgGI+jkFEsuI4Zu/ofv3giy/MaCUJer5OEB9jtirN\n6CVMgqgGLE67LiK2JCWZxDBxIqxaBc2a2Y5IXMLXCWI5cOyy2zoAE9L+ngDYm2YrEuz274fmzU2S\nWLECKlWyHZG4iI0+iLKYZifS/i1rIQZxqaFDhzJq1Kj064MHD07f5Ea8bM0aaNAAOnY0q7EWKmQ7\nInEZf8ykDgdmAxcWezkGZFy0/yimXyIjzaQOUnv37uWhhx5iw4YNpKamUq1aNdatW3fFfR7kBkyY\nAC+8AB99BO3b245GLHDrTOqDQDngABAKHLrSg2JiYtL/joyMJDIy0g+hiW2VKlWiZMmSbNq0iQMH\nDlCvXj0lB286fx7++leYPRtiY6FmTdsRiZ/ExsYSGxt7Xc+xUUG8DhwBRmA6qIuRuaNaFUQQmzZt\nGitXruTgwYP069ePtm0vH+cg2XL0KPTsCSEhpklJiTeoeVJB+DpBTAaaA6UwlcPLwExgGnALsAfo\nDly+nZUSRBA7d+4ctWrVIiUlhZ07d7puc6aAtHWr6Wvo2BFGjNAGP+KKJqboq9we5ePjSgDLmzcv\nLVq0oHjx4koO3jBrFgwYAG+8AX362I5GAoh+RojrpKamsnr1ar744gvboQQ2x4FXXzUzoufMgYYN\nbUckAUZLbYirbNu2japVqxIVFUVERITtcALXqVPQo4epHtauVXKQbHFr/a4+CJHs2rvX9DXUqQNj\nxkD+/LYjEhfypA9CFYRITrJsmVmJtV8/+PhjJQe5IeqDEMkpxoyBoUPNBj+tWtmORnIAJQiRQJec\nbJbnXrYMVq6EKlVsRyQ5hBKESCA7dAi6doVixWD1aiha1HZEkoOoD0IkUG3caBbbu/demDFDyUG8\nThWESCCaOhWefBLefRe6d7cdjeRQShAigSQ1FYYMgf/+1+wXXaeO7YgkB1OCEAkUJ07AI4+Yf9et\ng9KlbUckOZz6IEQCwc6dZn5DWJipHJQcxA+UIETcbsECaNrUDGV9/33Il892RBIk1MQk4laOA2+9\nBSNHwuefm9FKIn6kBCHiRklJ8MQT8OOPZn5DpUq2I5IgpCYmEbfZt89UC0lJsGKFkoNYowQh4ibz\n5pnJb506mW1BCxWyHZEEMTUxibjB77/Dc8/Bt9/CxInQsqXtiERUQYhYN28e3HEH3HST6XNQchCX\nUAUhYkvGquGTT5QYxHVUQYjYoKpBAoAqCBF/UtUgAUQVhIi/qGqQAKMKQsTXVDVIgFIFIeJLqhok\ngKmCEPGF33+Hv/wFlixR1SABSxWEiLddqBry5VPVIAFNFYSIt6hqkBxGFYSIN6hqkBxIFYTIjVDV\nIDmYKgiR7FLVIDmcKgiR66WqQYKEKgiR66GqQYKIKggRT6hqkCCkCkIkK6oaJEipghC5GlUNEuRU\nQYhciaoGEVUQIpdQ1SCSzmYFsQf4EdgIrLUYh4ihqkHkEjYrCAeIBI5ajEFEVYPIVdjugwixfHwJ\ndqoaRK7K5hf0L8BxIAX4ABiX4T7HcRwrQUmQyFg1fPihEoMEnZCQEMgiB9hsYroHSABKAwuBn4Dl\nF+6MiYlJf2BkZCSRkZH+jU5yplOnYPRoePNN6NbNVA1FitiOSsTnYmNjiY2Nva7nuKWJZyiQCLyR\ndl0VhHhXUhKMGQPDh0NkJLzyCtx2m+2oRKzxpIKw1QdRELjws60Q0BrYbCkWycnOnYOxY6FqVdOc\n9M03MGWKkoOIB2w1MZUFvsoQw3+BBZZikZwoJQU++wxiYqByZfjiC2jY0HZUIgHFLU1Ml1MTk2RP\naip89RW8/DIUKwb/+pdpUhKRS7i9k1rEexzHDFn9+98hJAT+/W9o29b8LSLZogQhgS821iSGY8fg\nH/+Ahx5SYhDxAiUICVxr1pjEEBdn+hqioyF3bttRieQYtmdSi1y/H36ADh3MPIbu3WH7dujVS8lB\nxMuUICRw/Pwz9Ohh+hZatoQdO+APf4C8eW1HJpIjKUGI++3ZA48+Ck2bQt26sGsXPP005M9vOzKR\nHE0JQtxr/374v/+Du+6CihVh50546SUoVMh2ZCJBQQlC3OfwYXj+ebPKaqFC8NNPZnRSsWK2IxMJ\nKkoQ4h6//w5DhkD16nDmDGzeDCNHQunStiMTCUpKEGLfqVPw2mtmvaR9+2DDBnj3XShf3nZkIkFN\nCULsSUqCt9+GiAgzdHXFChg/HsLDbUcmImiinNhw7hx8/DEMGwb16sGCBVC7tu2oROQyShDiPxlX\nWI2I0AqrIi6nBCG+l3GF1eLFTTNS8+a2oxKRLChBiO+kpMDcuTB0qFZYFQlAbv2kaj+IQLZlC0yc\nCJMmmQluL74InTsrMYi4iPaDEP85fBgmT4YJE+DgQejdGxYvhho1bEcmItnk1p90qiACQXIyfP21\nSQqxsdCuHfTtCy1aaGVVEZfzpIJQgpDr4ziwfr1JClOnwu23m6TQtSsUKWI7OhHxkJqYxHv27TN9\nChMmmMqhTx9YuxZuvdV2ZCLiI6og5OpOnzbDUydMMFVD166mWmjSRB3OIgFOFYRcv9RUs+TFhAkw\nfTo0agT9+8PMmVCggO3oRMSPlCDE2L3bDE399FOzxHbfvrBtG4SG2o5MRCxRgghmx4/DtGkmMezY\nAdHRZvmLunXVhCQi6oMIOikpsHChaUKaN8/s7dy3L9x/v/Z2FgkiGuYqF10+u7lPH+jZE0qWtB2Z\niFigTupgp9nNInIDVEHkNMnJMGeOSQpLl0L79qZa0OxmEclATUzBQrObReQ6qYkppzp50sxiXrUK\nVq82lxIloFcvzW4WEa9RBeF2jgM7d5pkcOGyezfUqWMmsTVubC7ly9uOVEQCiJqYAtGVqoNChS4m\ngsaNTXLIl892pCISwJQg3O5K1cGuXSYBZEwIqg5ExMuUINzm5ElYt+5iMlB1ICKWKEHYpOpARFxM\nCcKfVB2ISABRgvAVVQciEuDcnCDaAm8DuYEPgRGX3W8vQaSkwLFjcORI5stvv8Hmzdaqg9jYWCIj\nI316jECjc5KZzklmOieZuXWiXG7gP0AUsA9YB8wCtnv1KI5jdkTL+AV/9OiVv/gzXk6cgJtvNovY\nXeny6KMwdqyV6kBv8sx0TjLTOclM5yR7bCSIBsAuYE/a9SlAR66VIK71q/5al5CQq3/RV6xofvVf\nfnuxYlqzSEQEOwmiAhCf4fqvQMNMj2rUKOtf9SVKXPyyv1ISKFjQX/8nEZEcx0YfRBdMH8Qf0q73\nwiSIP2d4zC4gws9xiYgEk91AlWs9wEYFsQ+omOF6RUwVkdE1gxYRkZwpDyZzhQP5gE2AdrAREREA\n7gd+xjQl/c1yLCIiIiIiEsjaAj8BO4EXLcfiBuOBg8Bm24G4SEXgW2ArsAV4ym44rpAfWINpst0G\nvGY3HFfJDWwEZtsOxEX2AD9izstau6F4Ljem2SkcyIv6JwCaAXVRgsioHFAn7e/CmObKYH+fAFwY\n150HWA00tRiLmzwH/BczIVeMOKBEVg/K5YdArkfGSXTnuDiJLpgtB47ZDsJlDmB+PAAkYiZZauEr\nOJ32bz7Mj62jFmNxizDgAcySPm5de86WLM+H2xLElSbRVbAUiwSGcEyFtcZyHG6QC5M4D2Ka4LbZ\nDccV3gJeAFJtB+IyDrAIWM/FOWmZuC1BuHgJV3GhwsAXwNOYSiLYpWKa3sKAe4FIq9HY1w44hGln\nV/VwqXswP6zuB/6EacrOxG0JwpNJdCJg+qi+BCYBMyzH4jbHga+B+rYDsawJ0AHT3j4ZaAFMtBqR\neySk/XsY+ArTvO96mkR3ZeGokzqjEMwH/S3bgbhIKaBY2t8FgGVAS3vhuE5zNIrpgoJAkbS/CwEr\ngdb2wrk+mkR3qcnAfuAspn/mUbvhuEJTTHPKJkzzwUbM8OhgdgfwPeac/Ihpd5eLmqNRTBfcinmf\nbMIME9f3rIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhkdjfwA3ATZtmCLUBNqxGJeIlWOBS5\nccMwO7oVwCyHMsJuOCIi4hZ5MVXEavSjS3IQty33LRKISmGalwpjqgiRHEG/dkRu3CzgM6AyEAr8\n2W44IiLiBn2Az9P+zoVpZoq0Fo2IiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhIEPp/hpEYZaXwUSoA\nAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f8f960ba310>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "x = linspace(0, 5, 10) # Conjunto de puntos\n",
    "y = x ** 2 # Funcion\n",
    "\n",
    "fig = plt.figure()\n",
    "\n",
    "axes1 = fig.add_axes([0.1, 0.1, 0.8, 0.8]) # Eje principal\n",
    "axes2 = fig.add_axes([0.2, 0.5, 0.4, 0.3]) # Eje secundario\n",
    "\n",
    "# Figura principal\n",
    "axes1.plot(x, y, 'r')\n",
    "axes1.set_xlabel('x')\n",
    "axes1.set_ylabel('y')\n",
    "axes1.set_title('Ej OOP')\n",
    "\n",
    "# Insertada\n",
    "axes2.plot(y, x, 'g')\n",
    "axes2.set_xlabel('y')\n",
    "axes2.set_ylabel('x')\n",
    "axes2.set_title('insertado');"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAakAAAEaCAYAAACrcqiAAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRERERERERBL2/+8+peDjQeJcAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f8f961eb510>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Ejemplo con más de una figura.\n",
    "fig, axes = plt.subplots(nrows=1, ncols=2)\n",
    "\n",
    "for ax in axes:\n",
    "    ax.plot(x, y, 'r')\n",
    "    ax.set_xlabel('x')\n",
    "    ax.set_ylabel('y')\n",
    "    ax.set_title('titulo')\n",
    "    \n",
    "fig.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## IPython"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[IPython](http://ipython.org/) promueve un ambiente de trabajo de *ejecutar-explorar* en contraposición al tradicional modelo de desarrollo de software de *editar-compilar-ejecutar*. Es decir, que el problema computacional a resolver es más visto como todo un proceso de ejecucion de tareas, en lugar del tradicional modelo de producir una respuesta(`output`) a una pregunta(`input`).  [IPython](http://ipython.org/) también provee una estrecha integración con nuestro sistema operativo, permitiendo acceder fácilmente a todos nuestros archivos desde la misma herramienta.\n",
    "\n",
    "Algunas de las características sobresalientes de [IPython](http://ipython.org/) son:\n",
    "\n",
    "* Su poderoso <a href='http://es.wikipedia.org/wiki/Shell_(inform%C3%A1tica)' target='_blank'>shell</a> interactivo.\n",
    "* [Notebook](http://ipython.org/notebook.html), su interfase web con soporte para código, texto, expresiones matemáticas, gráficos en línea y multimedia.\n",
    "* Su soporte para poder realizar visualizaciones de datos en forma interactiva. [IPython](http://ipython.org/) esta totalmente integrado con [matplotlib](http://matplotlib.org/).\n",
    "* Su simple y flexible interfase para trabajar con la [computación paralela](http://es.wikipedia.org/wiki/Computaci%C3%B3n_paralela).\n",
    "\n",
    "[IPython](http://ipython.org/) es mucho más que una librería, es todo un ambiente de trabajo que nos facilita enormemente trabajar con  [Python](http://python.org/); las mismas páginas de este blog están desarrolladas con la ayuda del fantástico [Notebook](http://ipython.org/notebook.html) de [IPython](http://ipython.org/). (para ver el [Notebook](http://ipython.org/notebook.html) en el que se basa este artículo, visiten el siguiente [enlace](http://nbviewer.ipython.org/github/relopezbriega/relopezbriega.github.io/blob/master/downloads/Python-Librerias-esenciales.ipynb).)\n",
    "\n",
    "Para más información sobre [IPython](http://ipython.org/) y algunas de sus funciones los invito también a visitar el [artículo](http://relopezbriega.com.ar/2014/python/ipython-y-la-computacion-interactiva/) que escribí en mi otro [blog](http://relopezbriega.com.ar/)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[Pandas](http://pandas.pydata.org/) es una librería [open source](http://es.wikipedia.org/wiki/C%C3%B3digo_abierto) que aporta a [Python](http://python.org/) unas estructuras de datos fáciles de user y de alta performance, junto con un gran número de funciones esenciales para el análisis de datos. Con la ayuda de [Pandas](http://pandas.pydata.org/) podemos trabajar con *datos estructurados* de una forma más rápida y expresiva.\n",
    "\n",
    "Algunas de las cosas sobresalientes que nos aporta [Pandas](http://pandas.pydata.org/) son:\n",
    "\n",
    "* Un rápido y eficiente objeto **`DataFrame`** para manipular datos con indexación integrada;\n",
    "* herramientas para la **lectura y escritura de datos** entre estructuras de datos rápidas y eficientes manejadas en memoria, como el `DataFrame`, con la mayoría de los formatos conocidos para el manejo de datos, como ser: CSV y archivos de texto, archivos Microsoft Excel, bases de datos [SQL](http://es.wikipedia.org/wiki/SQL), y el formato científico HDF5.\n",
    "* Proporciona una **alineación inteligente de datos** y un manejo integrado de los datos faltantes; con estas funciones podemos obtener una ganancia de performace en los cálculos entre `DataFrames` y una fácil manipulación y ordenamiento de los datos de nuestro `data set`;\n",
    "* Flexibilidad para **manipular y redimensionar** nuestro `data set`, facilidad para construir [tablas pivote](http://es.wikipedia.org/wiki/Tabla_pivote);\n",
    "* La posibilidad de **filtrar los datos, agregar o eliminar columnas** de una forma sumamente expresiva;\n",
    "* Operaciones de ***merge* y *join*** altamente eficientes sobre nuestros conjuntos de datos;\n",
    "* **Indexación jerárquica** que proporciona una forma intuitiva de trabajar con datos de alta dimensión en una estructura de datos de menor dimensión ;\n",
    "* Posibilidad de realizar cálculos agregados o transformaciones de datos con el poderoso motor **`group by`** que nos permite dividir-aplicar-combinar nuestros conjuntos de datos;\n",
    "* combina las **características de las matrices de alto rendimiento de [Numpy](http://www.numpy.org/) con las flexibles capacidades de manipulación de datos de las hojas de cálculo** y bases de datos relacionales (tales como [SQL](http://es.wikipedia.org/wiki/SQL));\n",
    "* Gran número de funcionalidades para el manejo de **[series de tiempo](http://es.wikipedia.org/wiki/Serie_temporal)** ideales para el análisis financiero;\n",
    "* Todas sus funciones y estructuras de datos están **optimizadas para el alto rendimiento**, con las partes críticas del código escritas en [Cython](http://www.cython.org/) o [C](http://es.wikipedia.org/wiki/C_(lenguaje_de_programaci%C3%B3n);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Estructuras de datos de Pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Importando pandas\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    2\n",
       "1    4\n",
       "2   -8\n",
       "3    3\n",
       "dtype: int64"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Las series son matrices de una sola dimension similares a los vectores, pero con su propio indice.\n",
    "# Creando una Serie\n",
    "serie = pd.Series([2, 4, -8, 3])\n",
    "serie"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[ 2  4 -8  3]\n",
      "Int64Index([0, 1, 2, 3], dtype='int64')\n"
     ]
    }
   ],
   "source": [
    "# podemos ver tantos los índices como los valores de las Series.\n",
    "print serie.values\n",
    "print serie.index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "d    2\n",
       "b    4\n",
       "a   -8\n",
       "c    3\n",
       "dtype: int64"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Creando Series con nuestros propios índices.\n",
    "serie2 = pd.Series([2, 4, -8, 3], index=['d', 'b', 'a', 'c'])\n",
    "serie2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-8\n",
      "b    4\n",
      "c    3\n",
      "d    2\n",
      "dtype: int64\n",
      "d    2\n",
      "b    4\n",
      "c    3\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# Accediendo a los datos a través de los índices\n",
    "print serie2['a']\n",
    "print serie2[['b', 'c', 'd']]\n",
    "print serie2[serie2 > 0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>pop</th>\n",
       "      <th>state</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td> 1.5</td>\n",
       "      <td>   Ohio</td>\n",
       "      <td> 2000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td> 1.7</td>\n",
       "      <td>   Ohio</td>\n",
       "      <td> 2001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td> 3.6</td>\n",
       "      <td>   Ohio</td>\n",
       "      <td> 2002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td> 2.4</td>\n",
       "      <td> Nevada</td>\n",
       "      <td> 2001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td> 2.9</td>\n",
       "      <td> Nevada</td>\n",
       "      <td> 2002</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   pop   state  year\n",
       "0  1.5    Ohio  2000\n",
       "1  1.7    Ohio  2001\n",
       "2  3.6    Ohio  2002\n",
       "3  2.4  Nevada  2001\n",
       "4  2.9  Nevada  2002\n",
       "\n",
       "[5 rows x 3 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# El DataFrame es una estructura de datos tabular similar a las hojas de cálculo de Excel.\n",
    "# Posee tanto indices de columnas como de filas.\n",
    "\n",
    "# Creando un DataFrame.\n",
    "data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],\n",
    "        'year' : [2000, 2001, 2002, 2001, 2002],\n",
    "        'pop'  : [1.5, 1.7, 3.6, 2.4, 2.9]}\n",
    "frame = pd.DataFrame(data) # Creando un DataFrame desde un diccionario\n",
    "frame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pop,state,year\r\n",
      "1.5,Ohio,2000\r\n",
      "1.7,Ohio,2001\r\n",
      "3.6,Ohio,2002\r\n",
      "2.4,Nevada,2001\r\n",
      "2.9,Nevada,2002\r\n"
     ]
    }
   ],
   "source": [
    "# Creando un DataFrame desde un archivo.\n",
    "!cat 'dataset.csv' # ejemplo archivo csv."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>pop</th>\n",
       "      <th>state</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td> 1.5</td>\n",
       "      <td>   Ohio</td>\n",
       "      <td> 2000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td> 1.7</td>\n",
       "      <td>   Ohio</td>\n",
       "      <td> 2001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td> 3.6</td>\n",
       "      <td>   Ohio</td>\n",
       "      <td> 2002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td> 2.4</td>\n",
       "      <td> Nevada</td>\n",
       "      <td> 2001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td> 2.9</td>\n",
       "      <td> Nevada</td>\n",
       "      <td> 2002</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   pop   state  year\n",
       "0  1.5    Ohio  2000\n",
       "1  1.7    Ohio  2001\n",
       "2  3.6    Ohio  2002\n",
       "3  2.4  Nevada  2001\n",
       "4  2.9  Nevada  2002\n",
       "\n",
       "[5 rows x 3 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Leyendo el archivo dataset.csv para crear el DataFrame\n",
    "frame2 = pd.read_csv('dataset.csv', header=0) \n",
    "frame2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0      Ohio\n",
       "1      Ohio\n",
       "2      Ohio\n",
       "3    Nevada\n",
       "4    Nevada\n",
       "Name: state, dtype: object"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Seleccionando una columna como una Serie\n",
    "frame['state']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pop       1.7\n",
       "state    Ohio\n",
       "year     2001\n",
       "Name: 1, dtype: object"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Seleccionando una línea como una Serie.\n",
    "frame.ix[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index([u'pop', u'state', u'year'], dtype='object')"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Verificando las columnas\n",
    "frame.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Int64Index([0, 1, 2, 3, 4], dtype='int64')"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Verificando los índices.\n",
    "frame.index"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Otras librerías dignas de mencion"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Otras librerías que también son muy importantes para el análisis de datos con [Python](http://python.org/) son:"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### SciPy"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[SciPy](http://www.scipy.org/) es un conjunto de paquetes donde cada uno ellos ataca un problema distinto dentro de la computación científica y el análisis numérico. Algunos de los paquetes que incluye, son:\n",
    "\n",
    "* **`scipy.integrate`**: que proporciona diferentes funciones para resolver problemas de integración numérica.\n",
    "* **`scipy.linalg`**: que proporciona funciones para resolver problemas de álgebra lineal.\n",
    "* **`scipy.optimize`**: para los problemas de optimización y minimización.\n",
    "* **`scipy.signal`**: para el análisis y procesamiento de señales.\n",
    "* **`scipy.sparse`**: para matrices dispersas y solucionar sistemas lineales dispersos\n",
    "* **`scipy.stats`**: para el análisis de estadística y probabilidades.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Scikit-learn"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[Scikit-learn](http://scikit-learn.org/stable/) es una librería especializada en algoritmos para [data mining](http://es.wikipedia.org/wiki/Miner%C3%ADa_de_datos) y [machine learning](http://es.wikipedia.org/wiki/Machine_learning).  \n",
    "\n",
    "Algunos de los problemas que podemos resolver utilizando las herramientas de [Scikit-learn](http://scikit-learn.org/stable/), son:\n",
    "\n",
    "* <a href='http://scikit-learn.org/stable/supervised_learning.html#supervised-learning' target='_blank'>Clasificaciones</a>: Identificar las categorías a que cada observación del conjunto de datos pertenece.\n",
    "* <a href='http://scikit-learn.org/stable/supervised_learning.html#supervised-learning' target='_blank'>Regresiones</a>: Predecire el valor continuo para cada nuevo ejemplo.\n",
    "* <a href='http://scikit-learn.org/stable/modules/clustering.html#clustering' target='_blank'>Agrupaciones</a>: Agrupación automática de objetos similares en un conjunto.\n",
    "* <a href='http://scikit-learn.org/stable/modules/decomposition.html#decompositions' target='_blank'>Reducción de dimensiones</a>: Reducir el número de variables aleatorias a considerar.\n",
    "* <a href='http://scikit-learn.org/stable/model_selection.html#model-selection' target='_blank'>Selección de Modelos</a>: Comparar, validar y elegir parámetros y modelos.\n",
    "* <a href='http://scikit-learn.org/stable/modules/preprocessing.html#preprocessing' target='_blank'>Preprocesamiento</a>: Extracción de características a analizar y normalización de datos."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.4.3+"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}