Getting Started with Pandas, Numpy.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "\"\"\"\n",
    "Execute any notebook cell with Shift-Enter\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Numpy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# import the numpy package\n",
    "import numpy  # often also imported as np with `import numpy as np`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 0.,  0.,  0.])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create zero vectors\n",
    "numpy.zeros(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.,  0.],\n",
       "       [ 0.,  0.],\n",
       "       [ 0.,  0.]])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create zero matrix\n",
    "numpy.zeros((3,2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.,  0.,  0.],\n",
       "       [ 0.,  0.,  0.]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Transpose a matrix\n",
    "numpy.transpose(numpy.zeros((3,2)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3.0"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# dot product in numpy (multiply every vector element with the corresponding element in the other vector)\n",
    "numpy.dot(numpy.ones(3), numpy.ones(3), )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1.,  0.,  0.],\n",
       "       [ 0.,  1.,  0.],\n",
       "       [ 0.,  0.,  1.]])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# other useful methods\n",
    "numpy.eye(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 1.,  2.,  3.])"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# another application of the dot product: every row of the first matrix is multiplied with the \n",
    "# vector and the sum will be the result for the 1st, 2nd, 3rd result vector element\n",
    "numpy.dot(numpy.array(range(1, 4)), numpy.eye(3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAEPCAYAAABGP2P1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1102b84d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAEPCAYAAABGP2P1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nzKyOE4OZmdVxYjAzszpODGZmVuf/A0Gv5XFthR6WAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x110061f90>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAEPCAYAAABGP2P1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3XmYFPW18PHvYRcBBUQUEERQQBhQRMCIcRT3GI0mMdGo\niXkTTYxLbkxek3tft+zGJOYak+t6vUajXpd4o1GjRplrFNmHfd8UREAQBERZz/vHqZKepmempqer\nq7r7fJ6nn+lpaqrOLPSp33Z+oqo455xzoRZJB+Cccy5dPDE455yrwxODc865OjwxOOecq8MTg3PO\nuTo8MTjnnKsj1sQgIveLyBoRmdnAMXeIyCIRmS4iR8UZj3POucbF3WJ4ADi9vn8UkTOBfqp6OHAF\ncFfM8TjnnGtErIlBVV8HNjRwyLnAn4JjJwL7iUj3OGNyzjnXsKTHGHoCKzI+fyd4zTnnXEKSTgzO\nOedSplXC138HOCTj817Ba3sRES/q5JxzeVBVacrxxWgxSPDI5RngUgARGQ1sVNU19Z1IVVP1uOmm\nmxKPoVTi8pg8pkqIK40x5SPWFoOIPAJUA11F5G3gJqANoKp6j6o+LyJnichi4EPgsjjjcc4517hY\nE4OqXhThmKvijME551zT+OBzM1RXVycdQk5pjMtjisZjii6NcaUxpnxIvn1QxSYiWiqxOudcWogI\nmsLBZ+dcBKqwbVvSUTjnicG51Hj2WfjCF5KOwjlPDM6lxoQJMGVK0lE454nBudSYNg1Wr4Z165KO\nxFU6Twxl5vbb4eOPk47CNZWqJYa+fWHWrKSjcZXOE0MZ+eADuO46mDgx6UhcU61aZR9PP90Tg0ue\nJ4YyMnmy3XlOmJB0JK6pamth+HCoqvLE4JLniaGMTJgAffp4i6EU1dbC0Ud7YnDp4ImhjEyYAFdf\nDW++aS0HVzqmTbMWw5AhMGcO7N6ddESuknliKBNhF9KXv2xvKitWNP41Lj3CFkPnzrD//rB8edIR\nuUrmiaFMLF0K7dtDz54wapR3J5WS9ethwwY47DD73LuTXNI8MZSJCRNg9Gh7Pnq0D0CXkunT4aij\noEXwv9ETg0uaJ4Yy4YmhdE2bZt1IIU8MLmmeGMpEZmIYMcLuQrdvTzYmF004VTXkicElzRNDGfjo\nI5g7d89dZ6dO1l89c2aycbloslsMAwfCsmVeadUlxxNDGZg2DY48EvbZZ89r3p1UGrZssRlkgwbt\nea1tW0vs8+YlF5erbJ4YykBmN1Jo1ChPDKVg5kwYPBhaZW2y691JLkmeGMpArsQwerRPWS0F2d1I\nIU8MLkmeGMpArsQwaBCsXeslnNMue+A55InBJckTQ4l75x0rsx0ujgq1bAnHHuuthrTzFoNLI08M\nJW7iRGstSI6tvn0FdLpt2wYLFlgSyNanD2zaZCuinSs2TwwlLlc3UshnJqXbnDnQr1/d2WShFi1s\nUNpbDS4JnhhKXEOJYdQomDTJK3WmVX3jC6GhQz0xuGR4YihhO3ZYH/Wxx+b+9wMPhC5drLvCpU9Y\nUbU+Ps7gkuKJoYTNmmV7BHfqVP8x3p2UXvUNPIc8MbikeGIoYRMmWHdRQzwxpNOuXfamf9RR9R9T\nVQWzZ/umS674PDGUsIbGF0I+MymdFi6E7t1hv/3qP6ZLF+jQAd5+u3hxOQeeGEpalMRw1FGwaJHV\n5HHp0djAc8i7k1wSPDGUqPXrYc2ausXXcmnb1ma3TJlSnLhcNI2NL4SqqrxKris+TwwlauJEm43U\nsmXjx/o4Q/p4i8GlmSeGEhWueI7CxxnSRbXxqaohTwwuCZ4YSlSU8YVQ2GLw2S3p8NZbttr5wAMb\nP3bQIFiyxHfjc8XliaEE7d5tK5obm6oa6tPHkoLPbkmHqN1IAO3awaGHwvz5sYbkXB2eGErQggXQ\ntSt06xbteBHvTkqTqAPPIe9OcsUWe2IQkTNEZL6ILBSR63P8e1cReUFEpovILBH5Wn3nWrky1lBL\nRlO6kUI+AJ0eTWkxgCcGV3yxJgYRaQHcCZwODAYuFJGBWYddBUxX1aOAk4DfiEjWRofmlVfijLZ0\nRFnxnM0TQ3p4i8GlXdwthpHAIlV9S1V3AI8B52YdsxroGDzvCKxX1Z25TuaJweTTYhgxAmbM8EHM\npK1ebfsw9O4d/Ws8Mbhiizsx9ARWZHy+Mngt073AYBFZBcwArq3vZK+84jNrNm+GxYth2LCmfV3H\njlb7f8aMeOJy0YTTVHNtrFSfvn3h/fdh48b44nIuU84umyL7ETBDVU8SkX7AyyIyVFX3KuKwZcvN\nXH01HHAAVFdXU11dXfRgkzZlipW5aNOm6V8bdifVV6bbxS/q+oVM4aY9s2fDmDHxxOXKR01NDTU1\nNc06R9yJ4R0gs9HcK3gt0/HAzwBUdYmILAMGAnsVcTj//Js58ki48sqYoi0B+XQjhUaPtlbX1VcX\nNiYXXW0tnH9+078u7E7yxOAak33TfMsttzT5HHF3JU0G+otIHxFpA3wZeCbrmHnAKQAi0h04Alia\n62Rjx/o4Q1NWPGfzKavJa+rAc8jHGVwxxZoYVHUXNuvoJWAO8JiqzhORK0Tk8uCwXwAjRGQG8DLw\nf1X1/VznO/lkqKmxWvaVSLV5LYZBg+C99+zhim/jRli7Fg4/vOlf64nBFVPsYwyq+ndgQNZrd2c8\nXwd8Nsq5evSwMgLTp8MxxxQ2zlLw1ltWNK9Xr/y+vkULGDnSWg1nn13Y2Fzjpk+3SrdRCh9mCxOD\natMGrp3LR8mtfK7k7qSwtdCcNwbvTkpOUxe2ZerWzcpj+CJPVwyNJgYR6ScibYPn1SJyjYjsH39o\nuXliaN45fKFbcvIdXwh5d5IrligthqeAXSLSH7gHOAR4JNaoGlBdDePH2yKhSpPPiudso0ZZAb7d\nuwsTk4sun6mqmTwxuGKJkhh2ByuRzwN+r6o/AA6ON6z6de4MAwdW3l3vtm32ptDcsZVu3WwdiFfr\nLK6tW2HpUluPkC9PDK5YoiSGHSJyIfBV4G/Ba63jC6lxldidVFsLAwbAvvs2/1zenVR8s2bZDU0+\nCxNDnhhcsURJDJcBxwE/U9VlItIXeCjesBpWiYmhEOMLIU8MxdecgefQkUfCwoWwY0dhYnKuPg0m\nBhFpCfybql6jqo8CqOoyVb21KNHV4/jjrebP5s1JRlFchU4MPjOpuJo78AzQvj0ccoglB+fi1GBi\nCBaohauWU6N9e6v389prSUdSPIVMDMOGWSG+SkqsSStEiwG8O8kVR5SupKXAGyJyg4h8L3zEHVhj\nKqk7afVqexPPZ8VsLm3aWHKYslc1KheHHTtgzhxb3NZcnhhcMURJDEuwQecW2H4J4SNRlZQYJk60\naaaFXPHq4wzFM2+e7btdiIkDnhhcMTRaEkNVbwEQkfaqujX+kKI59lhYvtxqzxx4YNLRxKuQ3Uih\nUaPg0UcLe06X27RphelGAk8MrjiirHw+TkTmAvODz4eJyB9jj6wRrVrBpz8N48YlHUn84kgMYYuh\n0jc+KobmLmzL1K+f3Qz5+JCLU5SupN9hezavB1DVGcCn4wwqqkroTtq508YCRo4s7Hl797auqbfe\nKux53d4KNfAMVoBv0CDbtMe5uEQqoqeqK7JeSkXh67Fj4dVXk44iXnPmWDXV/QtcnUrEC+oVw+7d\nVlX1qKMKd07vTnJxi5IYVojIpwAVkdYi8n1sc53EDRliTepyvuuNoxsp5APQ8VuyBLp2hS5dCndO\nTwwublESw7eA7wA9gVXAUcHniROxzXvKuTvJE0NpK8TCtmxDh3picPFqNDGo6jpV/YqqdlfVbqp6\nsaquL0ZwUZT7OEOciWHECJg5szIr1RZLIQeeQ5mb9jgXhyizkg4TkWdF5D0RWSsifxWRw4oRXBTh\nOEM5/ifZsME2ZmlORc6GdOgA/ftbeREXj0JOVQ11726D0O++W9jzOheK0pX0CPA4Vmq7B/AEkJoZ\n8H37wj77wNy5SUdSeJMn2119qxg3YPXupPioxtNiAB9ncPGKkhjaq+pDqrozeDwMtIs7sKYo1+6k\nOLuRQl5QLz4rV9qd/cEx7F7iicHFqd7EICJdRKQL8IKI/FBEDhWRPiLyf4Hnixdi48p1ALoYiWHU\nKG8xxCVsLRSylEnIE4OLk2g9nfMisgxQINeftapqUccZRETri3XNGtvEZt26eLtdiknVdlqbMwcO\nOii+6+zebVMpFy4s/9IixXbLLbB9O/zsZ4U/96RJ8K1v2RiGcw0REVS1Sbcn9bYYVLWvqh4WfMx+\npGbwGWww7pBDYOrUpCMpnEWLoGPHeJMCQIsWtqrau5MKL46pqqHBg2171p074zm/q2xRZiW1FJFz\nROSaNJXdzlZu4wzF6EYK+QroeMQ18AxWqbVHD7uBcK7Qogw+Pwt8DehKispuZ/PEkD+fmVR469bB\npk1wWIxtax9ncHGJ0iPfS1ULsMVIvE48ES68ED76yKavlroJE+DSS4tzrVGjbGrsrl02i8Y1X22t\n1UeKY+A5FCaGCy6I7xquMkVpMbwoIqfFHkkzdepk/1HGj086kub78ENYsCC+bohsBxwA3bpZn7Ur\njDgWtmXzFoOLS5TE8CbwPyLykYhsEpHNIrIp7sDyUS7dSVOn2n/6tm2Ld03vTiqsOMcXQp4YXFyi\nJIbfAKOxhW6dVLWjqnaKOa68lEtimDixeOMLIU8MhVXIPRjq07+/lcXYsiXe67jKE6nsNjC73kUE\nKXLccVYaY+PGpCNpnmIOPId8BXThbN5sq54HDIj3Oq1awcCBttbFuUKKkhiWAjUi8qM0T1cFaNfO\n3uD+93+TjiR/qvDmm8VPDEOH2t4BvmVk882YYXuFFGOxpXcnuThESQzLgFeANqR4umqo1Hd1W7nS\nViP36VPc67ZpY7NoJk8u7nXLUTEGnkOeGFwcGr2nUdVbihFIoYwdC5ddlnQU+ZswwaaPxjnNsT5h\nd9LJJxf/2uWktta6NYuhqgqeT1XlMlcOGk0MIjIOq5lUh6qm8u1j+HBYtQpWr46/nEQckhhfCI0a\nBX/+czLXLifTpsF3irTHYeamPUncTLjyFKUr6fvAD4LHDcB0YEqcQTVHy5a22K1Uu5OSTAzhzKT0\nTzNIr48/tjIVQ4YU53oHH2xdj2vWFOd6rjJE2dpzasbjDVX9HlAd9QIicoaIzBeRhSJyfT3HVItI\nrYjMDloozVKq01a3b4fp021zniQccogl1uXLk7l+OZg9Gw4/3CZCFIOIjzO4wotSRK9LxuMAETkd\n2C/KyUWkBXAncDowGLhQRAZmHbMf8AfgbFUdAnyxqd9EtjAxlNqd74wZNje9Y0JD+yJeUK+5irGw\nLZsnBldoUbqSpmJdR1OxVdDXAf8n4vlHAotU9S1V3QE8BpybdcxFwFOq+g6Aqq6LeO56DRxod99L\nlzb3TMWVZDdSyBe6NY8nBlcOonQlZe7LcLiqnqaqr0c8f09sgVxoZfBapiOALiIyTkQmi8glEc9d\nL5HS7E5KYsVzNk8MzVPMqaohTwyu0KK0GBCRT4nIRSJyafgoYAytgOHAmcAZwA0i0r+5Jy3FxJCG\nFsOIEfYms21bsnGUop077Wc3bFhxrztkCMybZ9VxnSuEKNNVHwL6YbORwj89Bf4U4fzvAL0zPu8V\nvJZpJbBOVT8GPhaR14BhwOLsk918882fPK+urqa6urreC598MvzgBzZjo0Wk9Jes996D9evjL6PQ\nmH33tcHT6dNtvMFFt2AB9OxplX6LqWNH25Z1yRI44ojiXtulT01NDTU1Nc06R5RF+yOAI/OslTQZ\n6C8ifYB3gS8DF2Yd81fg9yLSEmgLjAJ+m+tkmYmhMb17w/77J3MHl4+JE22LzTQksbA7yRND0yQx\nvhAKu5M8Mbjsm+Zbbmn6GuUob0OzgbyWiqnqLuAq4CVgDvCYqs4TkStE5PLgmPnAi8BMYAJwj6rO\nzed62UqpOylNb8ReUC8/SYwvhHycwRVSlMRwADBXRF4UkWfCR9QLqOrfVXVAMHD9y+C1u1X1noxj\nfq2qg1V1qKr+vunfRm6llhiSHl8IjRrlA9D5SEOLwblCkMZ6iETkxFyvq2pRa5iKSJN7s9atg379\n7GPr1jEFVgC7dkGXLja9tmvXpKOxcZkuXazPvHv3pKMpDarQubOteu7WrfjXnzMHzjsPFi4s/rVd\nuokIqtqkgilRiuiVbBHrAw6wzdgnTYLjj086mvrNm2dvwGlICmDjHOFCt3POSTqa0rBsmQ0CJ5EU\nwMYWVqyArVuhfftkYnDlIwVDnfEqhe6kNHUjhXwFdNMk2Y0E1iI+4gjbqMq55vLEkAJpTAy+0K1p\nkhx4Dvk4gyuUKLWSPhvUPCpJJ5wAU6fChx8mHUn90rDiOduoUbZpjy+aiibpFgN4YnCFE+UN/0vA\nIhH5VXYBvFLQoYP9h309ahGPItu0yfqnq6qSjqSurl1tP4t585KOpDR4i8GVkyi1ki4GjgaWAP8l\nIm+KyOUiktrtPbOlebvPyZPtDSWNs6Z82mo0775r5TB69Uo2Dk8MrlAidRGp6ibgSaw66sHAecA0\nEbk6xtgKJs3jDGkcXwj5OEM0YWsh6R3UevWyjYLeey/ZOFzpizLGcI6IPA3UAK2Bkap6JlbP6Lp4\nwyuMUaNsfvf77ycdyd7StOI5m6+AjiYN4wtgiWnoUG81uOaL0mL4PHC7qlap6m2quhZAVbcSfV+G\nRLVpY+sYmllXquBU091iGDrUFt1t2pR0JOmWlsQA3p3kCiPKGMNXVfW1ev4tpR00e0tjd9LSpbYF\nZM/sHSpSonVre8ObPDnpSNItDQPPIU8MrhBKdhpqU6UxMaS5tRDy7qSGbdhg5dL7N3sHkcLwxOAK\noWISw7BhVjPpnezdIBJUConBZyY1rLbW/rbSUC4dbNOeOXOs3pVz+UrJn3P8WrSAk05KV6uhFBJD\nODMpr904KkCaxhcA9tvP1qAsW5Z0JK6URZmVdLaI1IrI+yKySUQ2i0hJDkemqTvpo4+srk1a+qbr\n06uXjTX4G01uaRpfCFVVwcyZSUfhSlmUFsPvgK8CXVW1k6p2VNUib15YGGFiSMPdb20tHHkk7LNP\n0pE0TMTHGRqSthYD+DiDa74oiWElMDvPrT1TpX9/61JKQ836UuhGCvk4Q24ffgjLl1uCTxNPDK65\noiSG64EXRORHIvK98BF3YHEQSU93UpoXtmXzFdC5zZxpSSFt5Uw8MbjmipIYfgJ8CLQDOmY8StLJ\nJ6cnMZRKi+GYY2D2bNi2LelI0iWN3UgAAwbAW2/ZOJZz+Wh0Bzegh6oOiT2SIhk7Fr77XSsn3bJl\nMjG8847ttNWvXzLXb6p997VNYGprSyeZFcO0aZY006ZNG+s2nTcvfQPjrjREaTE8LyKnxR5JkfTo\nAQceCNOnJxdDuP9C0kXXmsK7k/aW1hYDeHeSa54oieHbwN9F5ONgqmrJTlcNJT3OUErdSCGfmVTX\n9u12Rz50aNKR5OaJwTVHlFpJHVW1haq2C56X7HTVkCeGpvOZSXXNnQt9+0L79klHkpsnBtcckVY+\nB6W3fx08zo47qLhVV8P48ckMpu7YYX3Txx5b/Gs3xxFHwMaNsGZN0pGkw7Rp6e1GAk8MrnmirHz+\nJXAtMDd4XCsiv4g7sDh17gwDBybTNTJ7Nhx6qJUuKCUtWlirwbuTTG1tugd2e/e2dRbr1ycdiStF\nUVoMZwGnqup/qup/AmcAn4k3rPgl1Z1Uit1IIR+A3iPNA89gExuGDPFWg8tP1CJ6+2c8L7F73dw8\nMTSdjzOYXbtgxox0Jwbw7iSXvyiJ4RdArYj8l4g8CEwFfhZvWPE7/nj7z71lS3GvW0ornrONHAlT\nptgbYyVbvBi6dYP992/82CR5YnD5ijIr6VFgNPAX4CngOFX977gDi1v79jBiBLyWc2+6eKxfD+++\nm77aOlF17QoHH2wzcipZGiuq5uKJweWr3sQgIsPDB3AwVkxvJdAjeK3kFbs7adIkm42U1IrrQvDu\npPSPL4SqqnzTHpefhloMvwkefwAmAvcA9wbP/xB/aPErdmIo5fGFkA9Ap3+qaqhzZ+jUyeomOdcU\n9SYGVT1JVU8C3gWGq+oIVT0GOBpI0QaZ+Tv2WCub/N57xbleuSSGSp6yqpr+qaqZvDvJ5SPK4PMA\nVf3kT0tVZwOD4gupeFq1ghNOgHHj4r/W7t32hlqqA8+hqipLph98kHQkyVixworUHXRQ0pFE44nB\n5SNKYpgpIveJSHXwuBcom40Di9WdtGCBDd4eeGD814pT69bWjTJ5ctKRJKNUBp5DnhhcPqIkhsuA\nOdjq53AF9GVxBlVMxUoM5dCNFKrk7qRSGXgOeWJw+YgyXfVjVb1dVc8LHrer6sfFCK4YhgyBzZvj\nH6ALS22Xg0oegC61FsOgQbB0qW+y5JomSq2k40XkZRFZKCJLw0fUC4jIGSIyP/j66xs47lgR2SEi\n50c9dyGIFGdXt3JqMYRTVkt/F/CmK7UWQ9u2VgV2/vykI3GlJEpX0v3Ab4ExwLEZj0aJSAvgTuB0\nYDBwoYgMrOe4XwIvRgu7sOLuTtqyBRYtgmHD4rtGMfXqZW84SyPfHpSHtWutMN2hhyYdSdN4d5Jr\nqiiJ4QNVfUFV16rq+vAR8fwjgUWq+paq7gAeA87NcdzVwJPA2ojnLaixY+HVV+O7A54yxZJCmzbx\nnD8JlTjOELYWSmnnPfDE4JouSmIYJyK3ichxWauho+gJrMj4fGXw2idEpAfwOVX9DyCR/3J9+0K7\ndvGVeiinbqRQJa6ALpWFbdk8MbimahXhmHDm/YiM1xQ4uUAx/A7IHHtIJDmE3UmDBxf+3BMmwEUX\nFf68SRo9Gp54Iukoiqu2Fs7N1d5NOU8MrqkaTQzB6ud8vQP0zvi8F3uvmh4BPCYiAhwAnCkiO1T1\nmeyT3XzzzZ88r66uprq6uhmh1TV2LDz2GFxzTcFOCVj31IQJcMcdhT1v0o45xurwfPyxtbYqQW0t\nZPwJloxDD7Xd9zZssDIZrrzV1NRQU1PTrHOIRuhYF5HPYIPHn7wFqOqPI3xdS2ABMBYrrTEJuFBV\n59Vz/APAs6r6lxz/plFizdeaNTBgAKxbZyuiC2X5cvjUp+Cdd0qvb7oxw4fDH/4Axx2XdCTx++AD\n6NnTPpZiEcTRo+G222ylv6ssIoKqNundJ8p01buAL2EDxAJ8EegT5eSqugu4CngJWyT3mKrOE5Er\nROTyXF8SNfBC694dDjnE+pELKRxfKLekAJW1nmHGDOuSKcWkAN6d5Jomyr3xp1R1qIjMVNVbROQ3\nwAtRL6CqfwcGZL12dz3Hfj3qeeMQjjOMHFm4c5bjwHNo9Gh4/vmkoyiOUh14Dg0d6onBRRdlVlK4\nynlrMINoB7Y/Q9mJYz1DOa14zlZJLYZSqqiai7cYXFNESQzPisj+wG3ANGA58EicQSXlxBPtjfzj\nAhX82LYNZs60gdpydPjhsGkTrF6ddCTxK/UWQ1UVzJ5dmavVXdM1mBiCFcmvqOpGVX0KG1sYqKo3\nFiW6IuvUyWonjR9fmPNNnw5HHAH77luY86WNiK1nKPeFbh99BEuW2N9Gqera1bazXbGi8WOdazAx\nqOpuMnZrU9VtqlrWlfgL2Z1UzuMLoUroTpo92xJ827ZJR9I83p3koorSlfSKiHw+WGdQ9jwxNE0l\nrIAutYqq9fHE4KKKkhiuAJ4AtonIJhHZLCKbYo4rMccdZwu3CrFDWSUkhpEjrRbUrl1JRxKfUquo\nWh9PDC6qKPsxdFTVFqraRlU7BZ93KkZwSWjXzt7M//d/m3ee1astuRx+eGHiSqsuXWzh15w5SUcS\nn1IfeA5VVdlkCOcaE6XFUHEK0Z0U7u/cogJ+wuXcnbRjhyW9ciiZPmgQLF4M27cnHYlLuwp422q6\nQiSGSuhGCpXzAPT8+bb/RMeOSUfSfPvsA3362P7jzjXEE0MOw4fDqlXNm59faYmhXKeslvrCtmw+\nzuCiiJQYRGSMiFwWPO8mIn3jDStZLVvaYrdXX83v63ftgqlTC1taI82qqmzP7I0bk46k8MplfCHk\nicFFEaWI3k3Yfgk/Cl5qDTwcZ1Bp0JzupDlzbEC2Ukoct2pld9WTJycdSeF5i8GVsnxnC0ZpMZwH\nnAN8CKCqq4Ay6HFtWJgY8ikhMGGCDchWknLsTtq921ave4vBlZrly+GGG2xMKR9REsP2YCMEBRCR\nMi3wUNfAgTZ7I58N7ytpfCFUjgPQS5fCfvtZOYlycdhhsH59YdbpuHTZtg0efxxOOw1GjLA6ZvlW\nP46SGB4XkbuB/UXkm8A/gHvzu1zpEMm/O6kSE0M4ZbWcirSVWzcS2PTpI4+0Mh+uPMydC9ddZ/vJ\n3H03XHYZrFwJ//7vVm49H1EWuP0aeBJ4CttX4UZV/X1+lystJ5/c9MSwcaMVKivlgmv56NnTpkPm\n08JKq3IbeA55d1Lp+/BDeOABOP54OOUUq+M1fry9X114YfO32420iaWqviwiE8PjRaSLqr7fvEun\n39ixcP311tccdaHapElWZruQ24OWirA7qV+/pCMpjNpa+M53ko6i8DwxlCZVm+14333WZTRmjL0/\nnXVW4d9vosxKukJEVgMzgSnA1OBj2evd2/qYm9LsrsRupFA5rYBW9RaDS4cNG2xv9eHD4YILrMto\n1ix45hk455x4bkKj3Ad/Hxiiqoeq6mGq2ldVDyt8KOnU1HGGSk4M5TQAvWqVfezZM9k44hAmhnIa\nDyo3qvDaa3DJJdC3L/zzn3DbbVbS5N/+Lf6/yyiJYSmwNd4w0qspiUF1T42kSjR8uA2EffRR0pE0\nX1hRtRyLzR94ILRpA++8k3QkLtuaNfCrX8GAAfDtb1u39OLF8NhjNpZQrNprURohPwLeFJEJwLbw\nRVW9JraoUuSkk+Ab37Biaq1bN3zs4sVWU+fgstwRu3Ht21uhttpa+NSnko6mecq1GykUthp69Uo6\nErdrF7z0Etx7L4wbB+efDw8+aC3wpG5MouSfu4FXgAnY+EL4qAgHHGBzv6Os6q3kbqRQuYwzlONU\n1Uw+zpD+HvkpAAAXFElEQVS8t96Cm26yrqKbboIzz7TX7r/f9oVJsrUapcXQSlW/F3skKRZ2JzV2\nF1yJK56zjR4Nf/tb0lE037Rp1qQvV1VVdnfqimv7dhs0vu8+2+Dqoovg2WfTV9Y9SovhBRG5XEQO\nFpEu4SP2yFIk6jiDtxjKYwB6/XqbCVIu025z8RZDcc2fD9//vs0o+sMf4NJLbb3THXekLykAiDYy\nNUFEluV4WYs9M0lEtLFY47JlCxx0EKxda/3ouWzdCt262ZtKcxeXlDJV636bPbt0x1r+8Q/48Y9t\nVki52rrVSn1s2tT42JnLz9at8MQT1jpYvBi+9jX4+teLv6ujiKCqTeqYirLyuW+OR8VMVwXo0MEG\nIl9/vf5jpk611c6VnBTA+kVHjSrtgnrlPr4AdoPTqxcsWpR0JOVn2jS48kprHTzxhJWrePtt+MUv\nSmer3ygL3FqLyDUi8mTwuEpEKu4eo7HuJO9G2qPUu5PKfUZSyLuTCmflSvj97+2G4vOfhx49YMYM\nG2/73OdKr1UWZYzhP4BjgD8Gj2OC1yqKJ4boSn1mUriGodx5Ymie+fOtFTBypI0TTJkCt94KS5bA\n//t/pT0VOMoYwwxVHdbYa3FLcowBbDbBAQdYnfMuWUPvqrYS8Y03bOpZpduwwcqJbNhQejWjtmyx\nBWAffFB6d3lN9eST8NBD8Ne/Jh1JaVC1N/+nn7bH5s3WGjj/fDjhhPT+vcQyxgDsEpFP5meIyGFA\nnvsCla42baySYU3N3v+2cqUtUjn00GJHlU6dO9vd0pw5SUfSdDNmwODB6f1PXkjeYmjczp22xe/V\nV9vNziWXWIJ48EEbN7jzTqvCXG5/L1Hu534AjBORpYAAfYDLYo0qpcLupPPPr/v6xInJrlJMo3Cc\nIY1T8RpSCQPPof79YfVqu/PtWPZ7Mkb30Ue2Evnpp22MoG9fOO88e23QoKSjK45GE4OqviIih2N7\nMQAsUNVtDX1NuRo71mqdZ/Pxhb2F4wxXXJF0JE0zbZr1GVeCli3tjW7OHP/73bjRksDTT9t05WOO\nsWTwk5/Y7KJKE2VW0heBNqo6E9v7+VERqZB7qrqGDYN16/YuPuYrnvdWqntAV1KLASq7O+ndd+E/\n/sO2wuzd26aWfvazttlU2H1UiUkBoo0x3KCqm0VkDDAWuJ8KnJUEVtnwpJPqzk7avt02jD/22OTi\nSqMhQ2xl58aNSUcS3bZtNtOkqirpSIqn0hLDokVW6uS442ws6Y03rFW7apUNwn/ta+W1x3e+Ig0+\nBx8/A9yrqs8BbeILKd2yp63OnGlF9ryPtq5WrezOe9KkpCOJbs4c63ffZ5+kIymeck8M4YZLN9xg\nNyuf/jQsWwa33GLjKw8/bOsOOnRIOtJ0iTL4/I6I3A2cCtwqIm2JllDK0tix8LOf2R+ciI8vNCTs\nTjrttKQjiaZS1i9kyty0p1wmT+zaZS2Bv/wF/ud/7Cbl/POtrPWoUcXb06CURfkRXQC8CJyuqhuB\nLthMpUhE5AwRmS8iC0Xk+hz/fpGIzAger4tIqhvy/fvbx7CUgCeG+pXaCuhKWfGc6aCDLCGsXp10\nJM3z8cfw3HO2d8rBB8O119p6o2efrdt95Ekhmii1kraq6l9UdVHw+buq+lKUk4tIC+BO4HRgMHCh\niAzMOmwp8OlgwdxPgXub8g0Um0jd7iRPDPULayaVyhaSlTbwDPb3XKrdSZs22c5mX/qSJbhbb7Vx\ng4kT7Xd54432vZVLS6iY4s6fI4FFqvqWqu4AHgPOzTxAVSeo6gfBpxOA1O+yGyaG996zWUoDs1Od\nA6xeTPv2ViIg7XbtsvGio45KOpLiK7XEsHUrXHCBLaJ86CE49VRYuNCq4f7Lv3j1gUKIu2BBT2BF\nxucrsWRRn28AL8QaUQGMHQvf/S68+abNeffmaf3C7qSwCy6tFi60u8799ks6kuKrqmq4cnCa7Npl\na4k6dbKKA506JR1ReUpNJRsROQlbUT2mvmNuvvnmT55XV1dTXV0de1y59Ohh9XTuvtu7kRoTLnS7\n+OKkI2lYJY4vhKqqbD5/2qna2oJwn4M2FTs3smE1NTXU5Krd0wSNFtFr1slFRgM3q+oZwec/xDb5\nuTXruKHAU8AZqpqz4yHpInrZrrrKdmJ67jk466yko0mvN96wgcApU5KOpGHf/77NX//Rj5KOpPi2\nbIHu3a3PvmXLpKOp3y9/aWMKr73mLYWmiKuIXnNMBvqLSB8RaQN8GXgm8wAR6Y0lhUvqSwppNHas\nfayU8gn5Gj4c5s2z+jNpVskthg4drBtt8eKkI6nfww/DXXfB8897UiiGWBODqu4CrgJeAuYAj6nq\nPBG5QkQuDw67AZsC+0cRqRWRklgSNXastRoOOCDpSNJtn33gyCNte8NdKa3Jq2qr1ys1MYB1J82c\nmXQUub3yiu2C9txz1o3r4hdrV1Ihpa0ryUU3YYL9x16/Hv71X+Gii9K1T8Py5VZSPbsGViW54Qab\n1vnjHycdSV0zZ8Ipp9iYwoknJh1NaUpjV5JzjB5ts17++Ed44AEYMMBaENu3Jx2ZqeRupFAap6yu\nWAGf+YxtmelJobg8MbiiELENTcaNs01OnnjCNkb/4x9t1WqSKnFhW7a0JYaNG+HMM21a+Je+lHQ0\nlccTgyu6MWPgxRfh8cfhhRegXz/43e9sGmISvMVgSXrVKvjww6QjsSq3551nXUjf+17S0VQmTwwu\nMaNGWS2bv/0N/vlPq1L7q1/ZjmLF5C0GG/MZMCD57Vh3795T+vo3v/FyFknxxOASd/TR8NRTtnNW\nba21IH7yk+Ls5bB6tXVl9e4d/7XSLg3dST/8oY0tPPRQutdUlDtPDC41hgyBRx+11sPixVZG48Yb\n4f3347tmWGrb70yTTwy//z0884xtmFNJe2KkkScGlzoDBtgA9aRJtv3i4YfbneTatYW/lncj7ZFk\nYnj6aVvZ/MILvoNaGnhicKl12GG2uUptrY07DBxo1TNXrSrcNXzgeY+kEsP48ba95jPPeGXUtPDE\n4FKvd2+rSzV7tn0+ZAh85zvw9tvNP7e3GPbo0QN27oQ1a4p3zQULbHe1P/0JjjmmeNd1DfPE4EpG\njx5w++1We6lDB7vT/+Y3YenS/M63caO9CR5+eGHjLFXF3rRn9Wpbq/Dzn8MZZxTnmi4aTwyu5HTv\nbrt1hXsojBwJX/2q3X02xfTpMGyYz37JVKzEsGULnH22/d6+/vX4r+eaxhODK1ldu9q01nAG05gx\ntolL2OXUGB9f2FsxEsPOnbYD27BhNuvMpY8nBlfy9t/fisAtXWpbc55yCnz+8zZ+0JBwqqrbI+7E\noArf/rZ9vOsunyacVp4YXNno2BGuv972mB4zxroqPvtZm/aay7RpPvCcbcgQmDs3vhLpP/2p/dyf\neAJat47nGq75PDG4srPvvjatdckSG9T8whfg9NPr7mu8dSssWwaDBycXZxp16gTduuU/oN+QBx6w\nx3PP2eQBl16eGFzZatfOprUuXmzJ4dJL4aST4NVXrc7/wIG+b3AucXQnvfiibZv6wgs2YcClmycG\nV/batLFprQsWWIG2b3/bqnf6+EJuhU4M06bBxRdbPawBAwp3XhefFO2j5Vy8Wre26ZHhm5SvX8it\nqsp+PoWwfLmN89x9t+2S50qDb+3pnKtj9myb1dXUdSHZ3n/fksGVV8LVVxcmNtd0+Wzt6YnBOVfH\njh02CP3++/lXOf34Yzj1VNvW9bbbChufaxrf89k512ytW1s329y5+X397t3WXdezp61Qd6XHE4Nz\nbi/NGYC+7jpYt85Kp7fwd5iS5IPPzrm95JsYbr8dXn7ZNltq27bwcbni8HzunNtLPonh8cfht7+F\n55+Hzp3jicsVh7cYnHN7aWpieO01uOoqay34/tmlz1sMzrm9HHIIfPSRjRU0Zu5c+OIX4ZFHrGKq\nK32eGJxzexGxgnqNtRpWrYKzzoJf/9qq2rry4InBOZfT0KENJ4ZNmywpXH45XHJJ8eJy8fPE4JzL\nqaFxhu3brTDh6NFWHM+VF08Mzrmc6ksMqlaUsF07uPNO32ynHPmsJOdcTkOGwJw5tpI5c6HajTfC\n/PlWvryVv4OUJW8xOOdy2n9/W4+wfPme1+65Bx59FJ591jZEcuXJE4Nzrl6Z3Ul/+xvcdBP8/e9w\n4IHJxuXi5Q1B51y9wsTQowdcdpklh/79k47Kxc1bDM65elVV2Xac55wD998Po0YlHZErhtgTg4ic\nISLzRWShiFxfzzF3iMgiEZkuIkfFHZNzLpqqKhg/3rqQzjkn6WhcscSaGESkBXAncDowGLhQRAZm\nHXMm0E9VDweuAO6KM6ZCqqmpSTqEnNIYl8cUTdpiqqqCO+6o4VvfSjqSvaXtZwXpjCkfcbcYRgKL\nVPUtVd0BPAacm3XMucCfAFR1IrCfiHSPOa6CSOsfQRrj8piiSVtMIrB+fU3SYeSUtp8VpDOmfMSd\nGHoCKzI+Xxm81tAx7+Q4xjnnXJH44LNzzrk6RFXjO7nIaOBmVT0j+PyHgKrqrRnH3AWMU9X/Dj6f\nD5yoqmuyzhVfoM45V8ZUtUmFS+JexzAZ6C8ifYB3gS8DF2Yd8wzwHeC/g0SyMTspQNO/Meecc/mJ\nNTGo6i4RuQp4Ceu2ul9V54nIFfbPeo+qPi8iZ4nIYuBD4LI4Y3LOOdewWLuSnHPOlZ7UDz6LyP0i\nskZEZiYdS0hEeonIqyIyR0Rmicg1KYiprYhMFJHaIK6fJx1TSERaiMg0EXkm6VhCIrJcRGYEP69J\nSccDICL7icgTIjIv+B0mus5YRI4Ifj7Tgo8fpORv/UfBz2emiPxZRNqkIKZrg/eCRN8Pcr1fikhn\nEXlJRBaIyIsisl9j50l9YgAewBbIpclO4HuqOhg4DvhO9sK9YlPVbcBJqno0MBQ4WUSOTzKmDNcC\nc5MOIstuoFpVj1bVkUkHE/h34HlVHQQMA+YlGYyqLgx+PsOBY7Cu3qeTjCkYr/wmcLSqDsW6w7+c\ncEyDgf8DjACOAs4WkcMSCifX++UPgX+o6gDgVaDRrZVSnxhU9XVgQ9JxZFLV1ao6PXi+BfsPnPja\nC1XdGjxti/1uE/+5iUgv4CzgvqRjySKk6O9fRDoBJ6jqAwCqulNVNyUcVqZTgCWquqLRI+O1CdgO\n7CsirYD2wKpkQ2IQMFFVt6nqLuA14PwkAqnn/fJc4MHg+YPA5xo7T2r+Y5QqETkUu0uYmGwkn3TZ\n1AKrgRpVTcNd+u3AD4C0DWYp8LKITBaRbyYdDNAXWCciDwRdN/eIyD5JB5XhS8CjSQehqhuA3wBv\nY4thN6rqP5KNitnACUGXTXvsRuiQhGPKdGA401NVVwONFk33xNAMItIBeBK4Nmg5JEpVdwddSb2A\nT4vIiUnGIyKfAdYErSsJHmlxfNBFchbWFTgm4XhaAcOBPwRxbcW6ABInIq2Bc4AnUhDLYcC/AH2A\nHkAHEbkoyZhUdT5wK/Ay8DxQC+xKMqZGNHqT5okhT0Ez9kngIVX9a9LxZAq6IJ7D+jyTdDxwjogs\nxe42TxKRPyUcEwCq+m7w8T2s3zzpcYaVwApVnRJ8/iSWKNLgTGBq8LNK2gjgDVV9P+i2+QvwqYRj\nQlUfUNURqloNbAQWJhxSpjVh/TkROQhY29gXlEpiSNvdJsB/AnNV9d+TDgRARA4IZxsEXRCnAtOT\njElV/1VVe6vqYdgA4auqemmSMQGISPugtYeI7AuchnUHJCZo6q8QkSOCl8aSngH7C0lBN1JgATBa\nRNqJiGA/p0QH6QFEpFvwsTdwHvBIkuFQ9/3yGeBrwfOvAo3eyKZ+BzcReQSoBrqKyNvATeEAXYIx\nHQ98BZgV9Okr8K+q+vcEwzoYeDD4z9ICa8m8kmA8adYdeDoos9IK+LOqvpRwTADXAH8Oum6WkoLF\nnkGf+SnA5UnHAqCqM4JW51Ssu6YWuCfZqAB4SkS6ADuAK5OaOJDr/RL4JfCEiHwdeAu4oNHz+AI3\n55xzmUqlK8k551yReGJwzjlXhycG55xzdXhicM45V4cnBuecc3V4YnDOOVeHJwZXckTk3KSr2UYh\nIpuTjqGQRKSPiMxKOg4XP08MrhR9Dhgc18lFpGWBTlWOi4Ty/p4K+HN1MfPE4IBPykT8LdiQZaaI\nfDF4fWxQ7XOGiNwXrMpFRJaJyM+D4yeLyPBgE5BFYlu3huf9vohMEpHpInJTPdfeLCI/DY4Zn1Fe\noI+IvBJc+2WxDZKOwwq6/SqIq2/Wub4YbJZSKyI1wWttReQ/g+9rqohU54jhRBF5TUT+CswJXns6\n+N5micg3IsR7aPD5DBH5Sdb5bwvOM0NELsi4Zo2I/I+ILBaRX4rIxcHPa0b29xZ8ze9E5Ibg+enh\n95h1zE1iG7aMC857dcbPc1bGcdeJyI3B83Ei8tvg+50rIseKyF/ENnfJ/F5ai8jDwTGPi0i74OuH\nB9/LZBF5QfbU5hknIreLbYZ0jYh8Ifv341JIVf3hD7D68XdnfN4R29fhbaBf8NqDwDXB82XA5cHz\n3wIzsNr4BwCrg9dPDc+J1W55FhiT49q7gbOC57di5UXAarxcHDy/DHg6eP4AcH4938dM4ODgeafg\n4/eA+4LnA7CyAG2yvu5EYDPQO+O1/YOP7YBZQOdG4v0r8JXg+ZXApuD554EXg+cHBtfvHlzz/eC1\nNlgZ6ZuD464Bfpvj+9sniKUamA8cmuOYm4DXsXIfXYF1QEusIunMjOOuA24Mno8DfpFx7VUZca0A\nOgdfvxsYHRx3f/CzbQW8AXQNXr8A2989PO+dDf1+/JG+h7cYXGgWcKqI/EJExqjqZuxNdKmqLgmO\neRD4dMbXPJvxtRNUdauqrgM+Ftt45rTgnNOAacH5Ds9x7W2q+nzwfCpwaPD8OPYUb3sIq9bamNex\nmlHfYE8tsDHAwwCqugBYDhyR42snqerbGZ9/V0SmAxOwUuZh7PXFezzwWEa8ZLz+aHD9tUANcGzw\nb5NVda2qbgcWAy8Gr8/KOO8nVPUjrG7Ry8Adqro8x/cB8JzaZj/rgTVYImpMuPXqLGBWRlxL2LO/\nwNuqOiF4/jD2sx0ADMH2t6gF/g0riR3674znuX4/LmX8F+MAUNVFIhLuT/ATEXkFe6NoqKrttuDj\n7ozn4eetgq/9hare28jld2Q838Wev8sm92er6pUicixwNjBVRI7JcVh939OHnxxge1mcDIxS1W0i\nMg5rOTQWbxhzQz+3zH/L/rll/kzr+/85FGsFNLRrYK7fx06s5RBqR131/T7DYoO5KPb9zFbV+hL3\nJz/XHL+f4Wqb77gU8RaDA0BEDgY+UtVHgF9jewEsAPrInv1rL8Hudhs9XfDxReDrYqWtEZEeYX98\nPcdnG4+VfAa4GPhn8Hwz0Kme7+MwVZ2sqjdhded7BV93cfDvR2B3vwsa+R72AzYESWEgMDpCvG9k\nxPuVjNf/CXxJbIe9bsAJwKRGrp+T2J7H/wIcDZwpIk3ZR2IN0E1sp7G22JtzU/UWkVHB84uw721B\ncN7RQYytROTIeuLP/v2kaaczF/DE4EJVwKSgK+BG4Kequg3r239SRGZgd8d3B8c3dDevAKr6MlaX\n/k0RmYntANahvuNzuAa4LOjO+QpwbfD6Y8APgoHk7AHa24JB5pnAeFWdCfwRaBG89ijwVVXdQcP+\njg20zgF+DrwZId7vYrvBzcDKoNvBqk9jfeszgH8APwi6lLJFaSHdB1yntkXjN4B7RaRNI18T/j52\nAj8GJmNJe172MQ19fWA+9j3OBfYH7gp+ll8Abg1+V7VYN2Cu82b+ft4Ifj8uZbzstnPOuTq8xeCc\nc64OTwzOOefq8MTgnHOuDk8Mzjnn6vDE4Jxzrg5PDM455+rwxOCcc64OTwzOOefq+P97xT3Ul+n3\nKwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x110402690>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot data with matplotlib\n",
    "# line below is only needed in iPython notebooks\n",
    "%matplotlib inline  \n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "print numpy.ones(10)\n",
    "# random data\n",
    "for symbol in ['rx', 'bo', '']:\n",
    "    y = numpy.random.rand(10,1)\n",
    "    x = numpy.ones(10) * numpy.array(range(1, 11))\n",
    "    plt.plot(x, y, symbol)\n",
    "    plt.ylabel('some random y numbers')\n",
    "    plt.xlabel('some not so random x numbers')\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([  4.,   5.,   6.,   7.,   8.,   9.,  10.])"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# use the numpy where method\n",
    "x = numpy.ones(10) * numpy.array(range(1, 11))\n",
    "x[numpy.where( x > 3.0 )]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Import package \n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Read data from csv (could also be excel, etc.)\n",
    "df = pd.read_csv('https://archive.ics.uci.edu/ml/'\n",
    "        'machine-learning-databases/iris/iris.data', header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     0    1    2    3            4\n",
       "0  5.1  3.5  1.4  0.2  Iris-setosa\n",
       "1  4.9  3.0  1.4  0.2  Iris-setosa\n",
       "2  4.7  3.2  1.3  0.2  Iris-setosa\n",
       "3  4.6  3.1  1.5  0.2  Iris-setosa\n",
       "4  5.0  3.6  1.4  0.2  Iris-setosa"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the first 5 rows\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>6.7</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.3</td>\n",
       "      <td>Iris-virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>6.3</td>\n",
       "      <td>2.5</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>Iris-virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>6.5</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>Iris-virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>6.2</td>\n",
       "      <td>3.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.3</td>\n",
       "      <td>Iris-virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>5.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "      <td>Iris-virginica</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       0    1    2    3               4\n",
       "145  6.7  3.0  5.2  2.3  Iris-virginica\n",
       "146  6.3  2.5  5.0  1.9  Iris-virginica\n",
       "147  6.5  3.0  5.2  2.0  Iris-virginica\n",
       "148  6.2  3.4  5.4  2.3  Iris-virginica\n",
       "149  5.9  3.0  5.1  1.8  Iris-virginica"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the last 5 rows\n",
    "df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# extract sepal length and petal length\n",
    "X = df.iloc[0:100, [0, 2]].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 5.1  1.4]\n",
      " [ 4.9  1.4]\n",
      " [ 4.7  1.3]\n",
      " [ 4.6  1.5]\n",
      " [ 5.   1.4]\n",
      " [ 5.4  1.7]\n",
      " [ 4.6  1.4]\n",
      " [ 5.   1.5]\n",
      " [ 4.4  1.4]\n",
      " [ 4.9  1.5]\n",
      " [ 5.4  1.5]\n",
      " [ 4.8  1.6]\n",
      " [ 4.8  1.4]\n",
      " [ 4.3  1.1]\n",
      " [ 5.8  1.2]\n",
      " [ 5.7  1.5]\n",
      " [ 5.4  1.3]\n",
      " [ 5.1  1.4]\n",
      " [ 5.7  1.7]\n",
      " [ 5.1  1.5]\n",
      " [ 5.4  1.7]\n",
      " [ 5.1  1.5]\n",
      " [ 4.6  1. ]\n",
      " [ 5.1  1.7]\n",
      " [ 4.8  1.9]\n",
      " [ 5.   1.6]\n",
      " [ 5.   1.6]\n",
      " [ 5.2  1.5]\n",
      " [ 5.2  1.4]\n",
      " [ 4.7  1.6]\n",
      " [ 4.8  1.6]\n",
      " [ 5.4  1.5]\n",
      " [ 5.2  1.5]\n",
      " [ 5.5  1.4]\n",
      " [ 4.9  1.5]\n",
      " [ 5.   1.2]\n",
      " [ 5.5  1.3]\n",
      " [ 4.9  1.5]\n",
      " [ 4.4  1.3]\n",
      " [ 5.1  1.5]\n",
      " [ 5.   1.3]\n",
      " [ 4.5  1.3]\n",
      " [ 4.4  1.3]\n",
      " [ 5.   1.6]\n",
      " [ 5.1  1.9]\n",
      " [ 4.8  1.4]\n",
      " [ 5.1  1.6]\n",
      " [ 4.6  1.4]\n",
      " [ 5.3  1.5]\n",
      " [ 5.   1.4]\n",
      " [ 7.   4.7]\n",
      " [ 6.4  4.5]\n",
      " [ 6.9  4.9]\n",
      " [ 5.5  4. ]\n",
      " [ 6.5  4.6]\n",
      " [ 5.7  4.5]\n",
      " [ 6.3  4.7]\n",
      " [ 4.9  3.3]\n",
      " [ 6.6  4.6]\n",
      " [ 5.2  3.9]\n",
      " [ 5.   3.5]\n",
      " [ 5.9  4.2]\n",
      " [ 6.   4. ]\n",
      " [ 6.1  4.7]\n",
      " [ 5.6  3.6]\n",
      " [ 6.7  4.4]\n",
      " [ 5.6  4.5]\n",
      " [ 5.8  4.1]\n",
      " [ 6.2  4.5]\n",
      " [ 5.6  3.9]\n",
      " [ 5.9  4.8]\n",
      " [ 6.1  4. ]\n",
      " [ 6.3  4.9]\n",
      " [ 6.1  4.7]\n",
      " [ 6.4  4.3]\n",
      " [ 6.6  4.4]\n",
      " [ 6.8  4.8]\n",
      " [ 6.7  5. ]\n",
      " [ 6.   4.5]\n",
      " [ 5.7  3.5]\n",
      " [ 5.5  3.8]\n",
      " [ 5.5  3.7]\n",
      " [ 5.8  3.9]\n",
      " [ 6.   5.1]\n",
      " [ 5.4  4.5]\n",
      " [ 6.   4.5]\n",
      " [ 6.7  4.7]\n",
      " [ 6.3  4.4]\n",
      " [ 5.6  4.1]\n",
      " [ 5.5  4. ]\n",
      " [ 5.5  4.4]\n",
      " [ 6.1  4.6]\n",
      " [ 5.8  4. ]\n",
      " [ 5.   3.3]\n",
      " [ 5.6  4.2]\n",
      " [ 5.7  4.2]\n",
      " [ 5.7  4.2]\n",
      " [ 6.2  4.3]\n",
      " [ 5.1  3. ]\n",
      " [ 5.7  4.1]]\n"
     ]
    }
   ],
   "source": [
    "print X\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}