{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*** Perceptron Demo ***\n",
    "\n",
    "Build your own perceptron for the small housing dataset. Show that SLO houses and Paso Robles houses can be distinguished based on their sizes and prices."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from bs4 import BeautifulSoup\n",
    "import urllib.request\n",
    "\n",
    "from pandas import DataFrame\n",
    "from pandas import read_csv\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn\n",
    "from functools import reduce\n",
    "\n",
    "import numpy as np\n",
    "\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.svm import *\n",
    "\n",
    "%matplotlib inline "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "### this function removes extra whitespace from the data that was read from the CSV files\n",
    "### kept here to make your life a bit easier\n",
    "\n",
    "def cleanLabels(frame) :\n",
    "    nf = pd.DataFrame(frame)\n",
    "    vals = nf.values\n",
    "    vals[:,-1] = [x.strip() for x in vals[:,-1]]\n",
    "    corrected = pd.DataFrame(vals, columns = frame.columns)\n",
    "    return corrected"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "## This functions helps build column of +1, -1 class labels for the City column\n",
    "\n",
    "def getCityLabel(city):\n",
    "    if city == 'Paso Robles':\n",
    "        return -1\n",
    "    else:\n",
    "        if city == 'San Luis Obispo':\n",
    "            return 1\n",
    "        else: \n",
    "            return 0\n",
    "        \n",
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "### plotW() takes as input the set of SLO data points, the set of Paso Robles data points, and the vector w representing the\n",
    "###         current separating plane. It draws the two sets of the data points and the separating plane.\n",
    "\n",
    "def plotW(slo,paso, w):\n",
    "    \n",
    "    plt.figure(figsize=(10,8))\n",
    "\n",
    "    plt.plot(slo['Footage'], simpleSlo['Price'], 'ro')\n",
    "    plt.plot(paso['Footage'], simplePaso['Price'], 'bs')\n",
    "    \n",
    "    points = list(slo['Footage'])\n",
    "    points.extend(list(paso['Footage']))\n",
    "    points = np.array(sorted(points))\n",
    "    \n",
    "    plt.plot(points, -1*points*w[0]/w[1] - w[2]/w[1])\n",
    "\n",
    "    plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "### This function takes as  input the dataset of points, the current values w of the separating plane normal (w.x = 0),\n",
    "### and the learning rate (Rate), and produces one round of perceptron training. \n",
    "\n",
    "### One round means the function trains the perceptron on each data point from the dataset exactly once\n",
    "### You can use either the full gradient descent approach or the stochastic gradient descent approach\n",
    "### A version of stochastic approach (adjust w after visting each data point in turn) is recommended\n",
    "\n",
    "def trainPerceptron(data, w, Rate):\n",
    "    \n",
    "   \n",
    "\n",
    "\n",
    "    return w\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "### Given the data frame and the current separating plane normal vector w (w.x = 0) (i.e., the current perceptron)\n",
    "### this function should apply the perceptron to each data point in the data set,\n",
    "### determine if the prediction is correct, and output all predictions and the overall accuracy\n",
    "\n",
    "def getPerceptronAccuracy(data, w):\n",
    "   \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'pd' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-4-c8d360f8cb98>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[0mmasterFileName\u001b[0m\u001b[1;33m=\u001b[0m \u001b[1;34m'HousingSmallSet.csv'\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[0mmasterFile\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmasterFileName\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"r\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 5\u001b[1;33m \u001b[0mdt\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmasterFile\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      6\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      7\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Records:\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdt\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mNameError\u001b[0m: name 'pd' is not defined"
     ]
    }
   ],
   "source": [
    "### Step 1: retrieve the data\n",
    "\n",
    "masterFileName= 'HousingSmallSet.csv'\n",
    "masterFile = open(masterFileName, \"r\")\n",
    "dt = pd.read_csv(masterFile)\n",
    "\n",
    "print(\"Records:\", len(dt))\n",
    "    \n",
    "dt.columns = [s.strip() for s in dt.columns]\n",
    "\n",
    "cleaned = cleanLabels(dt)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'cleaned' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-3-c3d8608f1f94>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[1;31m### We plot the entire dataset\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 5\u001b[1;33m \u001b[0mslo\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcleaned\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"City =='San Luis Obispo'\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      6\u001b[0m \u001b[0mpaso\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcleaned\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"City =='Paso Robles'\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      7\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mNameError\u001b[0m: name 'cleaned' is not defined"
     ]
    }
   ],
   "source": [
    "### Step 2: for the sake of clarity and ease of display, we extract SLO and Paso Robles houses into separate data frames\n",
    "###         This is purely for visualization purposes\n",
    "### We plot the entire dataset\n",
    "\n",
    "slo = cleaned.query(\"City =='San Luis Obispo'\")\n",
    "paso = cleaned.query(\"City =='Paso Robles'\")\n",
    "\n",
    "plt.figure(figsize=(20,15))\n",
    "\n",
    "#plt.xkcd()\n",
    "plt.plot(slo['Footage'], slo['Price'], 'ro')\n",
    "plt.plot(paso['Footage'], paso['Price'], 'bs')\n",
    "\n",
    "plt.xlim(1700, 2600 )\n",
    "plt.ylim(0,1500000)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As you can see, the dataset above is not linearly separable: there are  a few data points that prevent linear separability.\n",
    "\n",
    "To make this first example simpler, let us remove the points responible for this from the dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'slo' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-2-047bbb22de7b>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;31m### Let's make a slightly simpler perceptron problem\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[0msimpleSlo\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mslo\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Price > 630000'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      4\u001b[0m \u001b[0msimplePaso\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpaso\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Price < 630000'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mNameError\u001b[0m: name 'slo' is not defined"
     ]
    }
   ],
   "source": [
    "### Let's make a slightly simpler perceptron problem\n",
    "\n",
    "simpleSlo = slo.query('Price > 630000')\n",
    "simplePaso = paso.query('Price < 630000')\n",
    "\n",
    "simpleData = pd.concat([simpleSlo, simplePaso], ignore_index = True)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The dataset as provided in the CSV file uses strings as category labels (\"SLO\", \"Paso Robles\"), while perceptron training requires +1, -1 labels.\n",
    "\n",
    "Additionally, we want to train a perceptron with a non-zero intercepts (potentially), so we need to add a new column to represent it.\n",
    "\n",
    "Finally, the data is currently listed in the SLO houses first - Paso houses second order. This is not a very good order of data points to train perceptron. What we want is a more natural mix of points where SLO and Paso Robles data points are interleaved.\n",
    "You can come up with your own inteleaving strategy, but make sure that to actually physically change the order of points in the final data frame you will be using. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "### NOTE: for simplicity, feel free to split this data frame into three-four separate data frames, one per task.\n",
    "###       I am using one data frame here because the amount of code is not significant\n",
    "\n",
    "\n",
    "### Add +1/-1 class label to the dataset\n",
    "\n",
    "\n",
    "### Add the Theta column to the dataset\n",
    "\n",
    "\n",
    "###  Change the order of the data points in your data frame.\n",
    "\n",
    "\n",
    "### output the final state of the data frame you will be using\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABKQAAANnCAYAAAAP+IBEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xb83c320>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "### Let's draw the dataset\n",
    "\n",
    "### Note: I use simpleSlo and simplePaso data frames here, so we see the linearly separable case\n",
    "\n",
    "plt.figure(figsize=(20,15))\n",
    "\n",
    "#plt.xkcd()\n",
    "plt.plot(simpleSlo['Footage'], simpleSlo['Price'], 'ro')\n",
    "plt.plot(simplePaso['Footage'], simplePaso['Price'], 'bs')\n",
    "\n",
    "plt.xlim(1900, 2600 )\n",
    "plt.ylim(0,1400000)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/wFNTP/F/DLHegAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xba1b860>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "### Use this cell to test the work of plotW() function if you want it.\n",
    "\n",
    "w = [1,1,1]\n",
    "\n",
    "plotW(simpleSlo, simplePaso, w)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 221,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted: -1.0    Actual: -1 Raw:  -2016.0\n",
      "Predicted: -1.0    Actual: 1 Raw:  -2018.0\n",
      "Predicted: -1.0    Actual: -1 Raw:  -1631.07092767\n",
      "Predicted: -1.0    Actual: -1 Raw:  -1625.57090548\n",
      "Predicted: -1.0    Actual: 1 Raw:  -1475.57087521\n",
      "Predicted: -1.0    Actual: -1 Raw:  -1324.64561197\n",
      "Predicted: -1.0    Actual: 1 Raw:  -957.145567286\n",
      "Predicted: -1.0    Actual: 1 Raw:  -471.080165439\n",
      "Predicted: 1.0    Actual: 1 Raw:  456.825371423\n",
      "Predicted: -1.0    Actual: -1 Raw:  -495.242595661\n",
      "Predicted: -1.0    Actual: -1 Raw:  -426.519507646\n",
      "Predicted: 1.0    Actual: 1 Raw:  397.685980369\n",
      "Predicted: -1.0    Actual: -1 Raw:  -788.281896196\n",
      "Predicted: -1.0    Actual: 1 Raw:  -103.833805677\n",
      "Predicted: 1.0    Actual: 1 Raw:  1076.51815593\n",
      "Predicted: -1.0    Actual: -1 Raw:  -109.401760555\n",
      "Predicted: -1.0    Actual: -1 Raw:  -121.769735275\n",
      "Predicted: 1.0    Actual: 1 Raw:  476.282427365\n",
      "Predicted: 1.0    Actual: 1 Raw:  1190.48265705\n",
      "Predicted: -1.0    Actual: -1 Raw:  -11.124161075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -294.199087995\n",
      "Predicted: -1.0    Actual: -1 Raw:  -521.690914915\n",
      "Predicted: 1.0    Actual: 1 Raw:  512.523586205\n",
      "Predicted: -1.0    Actual: -1 Raw:  -394.235131915\n",
      "Predicted: 1.0    Actual: 1 Raw:  2303.29995161\n",
      "Predicted: 1.0    Actual: 1 Raw:  657.573993365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -765.487626395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -469.645563755\n",
      "Predicted: 1.0    Actual: 1 Raw:  1033.29468241\n",
      "Predicted: -1.0    Actual: -1 Raw:  -380.209317595\n",
      "Predicted: -1.0    Actual: -1 Raw:  -768.714296715\n",
      "Predicted: -1.0    Actual: -1 Raw:  -551.449067035\n",
      "=== Loop  0  ===\n",
      "Weights: [ -9.99989560e-01   3.68100000e-03  -5.00000000e-09]\n",
      "Accuracy: 100.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xbc4a5c0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted: -1.0    Actual: -1 Raw:  -13.514952955\n",
      "Predicted: 1.0    Actual: 1 Raw:  1018.84606793\n",
      "Predicted: -1.0    Actual: -1 Raw:  -291.589932075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -228.969817235\n",
      "Predicted: 1.0    Actual: 1 Raw:  492.230339365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -264.969441395\n",
      "Predicted: 1.0    Actual: 1 Raw:  644.280673445\n",
      "Predicted: 1.0    Actual: 1 Raw:  555.660830045\n",
      "Predicted: 1.0    Actual: 1 Raw:  1069.40603885\n",
      "Predicted: -1.0    Actual: -1 Raw:  -108.832919395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -15.365653995\n",
      "Predicted: 1.0    Actual: 1 Raw:  1013.81181141\n",
      "Predicted: -1.0    Actual: -1 Raw:  -451.502031995\n",
      "Predicted: 1.0    Actual: 1 Raw:  398.852082845\n",
      "Predicted: 1.0    Actual: 1 Raw:  1076.51815593\n",
      "Predicted: -1.0    Actual: -1 Raw:  -109.401760555\n",
      "Predicted: -1.0    Actual: -1 Raw:  -121.769735275\n",
      "Predicted: 1.0    Actual: 1 Raw:  476.282427365\n",
      "Predicted: 1.0    Actual: 1 Raw:  1190.48265705\n",
      "Predicted: -1.0    Actual: -1 Raw:  -11.124161075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -294.199087995\n",
      "Predicted: -1.0    Actual: -1 Raw:  -521.690914915\n",
      "Predicted: 1.0    Actual: 1 Raw:  512.523586205\n",
      "Predicted: -1.0    Actual: -1 Raw:  -394.235131915\n",
      "Predicted: 1.0    Actual: 1 Raw:  2303.29995161\n",
      "Predicted: 1.0    Actual: 1 Raw:  657.573993365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -765.487626395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -469.645563755\n",
      "Predicted: 1.0    Actual: 1 Raw:  1033.29468241\n",
      "Predicted: -1.0    Actual: -1 Raw:  -380.209317595\n",
      "Predicted: -1.0    Actual: -1 Raw:  -768.714296715\n",
      "Predicted: -1.0    Actual: -1 Raw:  -551.449067035\n",
      "=== Loop  1  ===\n",
      "Weights: [ -9.99989560e-01   3.68100000e-03  -5.00000000e-09]\n",
      "Accuracy: 100.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xbc68be0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted: -1.0    Actual: -1 Raw:  -13.514952955\n",
      "Predicted: 1.0    Actual: 1 Raw:  1018.84606793\n",
      "Predicted: -1.0    Actual: -1 Raw:  -291.589932075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -228.969817235\n",
      "Predicted: 1.0    Actual: 1 Raw:  492.230339365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -264.969441395\n",
      "Predicted: 1.0    Actual: 1 Raw:  644.280673445\n",
      "Predicted: 1.0    Actual: 1 Raw:  555.660830045\n",
      "Predicted: 1.0    Actual: 1 Raw:  1069.40603885\n",
      "Predicted: -1.0    Actual: -1 Raw:  -108.832919395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -15.365653995\n",
      "Predicted: 1.0    Actual: 1 Raw:  1013.81181141\n",
      "Predicted: -1.0    Actual: -1 Raw:  -451.502031995\n",
      "Predicted: 1.0    Actual: 1 Raw:  398.852082845\n",
      "Predicted: 1.0    Actual: 1 Raw:  1076.51815593\n",
      "Predicted: -1.0    Actual: -1 Raw:  -109.401760555\n",
      "Predicted: -1.0    Actual: -1 Raw:  -121.769735275\n",
      "Predicted: 1.0    Actual: 1 Raw:  476.282427365\n",
      "Predicted: 1.0    Actual: 1 Raw:  1190.48265705\n",
      "Predicted: -1.0    Actual: -1 Raw:  -11.124161075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -294.199087995\n",
      "Predicted: -1.0    Actual: -1 Raw:  -521.690914915\n",
      "Predicted: 1.0    Actual: 1 Raw:  512.523586205\n",
      "Predicted: -1.0    Actual: -1 Raw:  -394.235131915\n",
      "Predicted: 1.0    Actual: 1 Raw:  2303.29995161\n",
      "Predicted: 1.0    Actual: 1 Raw:  657.573993365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -765.487626395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -469.645563755\n",
      "Predicted: 1.0    Actual: 1 Raw:  1033.29468241\n",
      "Predicted: -1.0    Actual: -1 Raw:  -380.209317595\n",
      "Predicted: -1.0    Actual: -1 Raw:  -768.714296715\n",
      "Predicted: -1.0    Actual: -1 Raw:  -551.449067035\n",
      "=== Loop  2  ===\n",
      "Weights: [ -9.99989560e-01   3.68100000e-03  -5.00000000e-09]\n",
      "Accuracy: 100.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xc02c320>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted: -1.0    Actual: -1 Raw:  -13.514952955\n",
      "Predicted: 1.0    Actual: 1 Raw:  1018.84606793\n",
      "Predicted: -1.0    Actual: -1 Raw:  -291.589932075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -228.969817235\n",
      "Predicted: 1.0    Actual: 1 Raw:  492.230339365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -264.969441395\n",
      "Predicted: 1.0    Actual: 1 Raw:  644.280673445\n",
      "Predicted: 1.0    Actual: 1 Raw:  555.660830045\n",
      "Predicted: 1.0    Actual: 1 Raw:  1069.40603885\n",
      "Predicted: -1.0    Actual: -1 Raw:  -108.832919395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -15.365653995\n",
      "Predicted: 1.0    Actual: 1 Raw:  1013.81181141\n",
      "Predicted: -1.0    Actual: -1 Raw:  -451.502031995\n",
      "Predicted: 1.0    Actual: 1 Raw:  398.852082845\n",
      "Predicted: 1.0    Actual: 1 Raw:  1076.51815593\n",
      "Predicted: -1.0    Actual: -1 Raw:  -109.401760555\n",
      "Predicted: -1.0    Actual: -1 Raw:  -121.769735275\n",
      "Predicted: 1.0    Actual: 1 Raw:  476.282427365\n",
      "Predicted: 1.0    Actual: 1 Raw:  1190.48265705\n",
      "Predicted: -1.0    Actual: -1 Raw:  -11.124161075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -294.199087995\n",
      "Predicted: -1.0    Actual: -1 Raw:  -521.690914915\n",
      "Predicted: 1.0    Actual: 1 Raw:  512.523586205\n",
      "Predicted: -1.0    Actual: -1 Raw:  -394.235131915\n",
      "Predicted: 1.0    Actual: 1 Raw:  2303.29995161\n",
      "Predicted: 1.0    Actual: 1 Raw:  657.573993365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -765.487626395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -469.645563755\n",
      "Predicted: 1.0    Actual: 1 Raw:  1033.29468241\n",
      "Predicted: -1.0    Actual: -1 Raw:  -380.209317595\n",
      "Predicted: -1.0    Actual: -1 Raw:  -768.714296715\n",
      "Predicted: -1.0    Actual: -1 Raw:  -551.449067035\n",
      "=== Loop  3  ===\n",
      "Weights: [ -9.99989560e-01   3.68100000e-03  -5.00000000e-09]\n",
      "Accuracy: 100.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xc083470>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted: -1.0    Actual: -1 Raw:  -13.514952955\n",
      "Predicted: 1.0    Actual: 1 Raw:  1018.84606793\n",
      "Predicted: -1.0    Actual: -1 Raw:  -291.589932075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -228.969817235\n",
      "Predicted: 1.0    Actual: 1 Raw:  492.230339365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -264.969441395\n",
      "Predicted: 1.0    Actual: 1 Raw:  644.280673445\n",
      "Predicted: 1.0    Actual: 1 Raw:  555.660830045\n",
      "Predicted: 1.0    Actual: 1 Raw:  1069.40603885\n",
      "Predicted: -1.0    Actual: -1 Raw:  -108.832919395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -15.365653995\n",
      "Predicted: 1.0    Actual: 1 Raw:  1013.81181141\n",
      "Predicted: -1.0    Actual: -1 Raw:  -451.502031995\n",
      "Predicted: 1.0    Actual: 1 Raw:  398.852082845\n",
      "Predicted: 1.0    Actual: 1 Raw:  1076.51815593\n",
      "Predicted: -1.0    Actual: -1 Raw:  -109.401760555\n",
      "Predicted: -1.0    Actual: -1 Raw:  -121.769735275\n",
      "Predicted: 1.0    Actual: 1 Raw:  476.282427365\n",
      "Predicted: 1.0    Actual: 1 Raw:  1190.48265705\n",
      "Predicted: -1.0    Actual: -1 Raw:  -11.124161075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -294.199087995\n",
      "Predicted: -1.0    Actual: -1 Raw:  -521.690914915\n",
      "Predicted: 1.0    Actual: 1 Raw:  512.523586205\n",
      "Predicted: -1.0    Actual: -1 Raw:  -394.235131915\n",
      "Predicted: 1.0    Actual: 1 Raw:  2303.29995161\n",
      "Predicted: 1.0    Actual: 1 Raw:  657.573993365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -765.487626395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -469.645563755\n",
      "Predicted: 1.0    Actual: 1 Raw:  1033.29468241\n",
      "Predicted: -1.0    Actual: -1 Raw:  -380.209317595\n",
      "Predicted: -1.0    Actual: -1 Raw:  -768.714296715\n",
      "Predicted: -1.0    Actual: -1 Raw:  -551.449067035\n",
      "=== Loop  4  ===\n",
      "Weights: [ -9.99989560e-01   3.68100000e-03  -5.00000000e-09]\n",
      "Accuracy: 100.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3X+U3fV93/nnSKOZ0Y87Qj9GGDs4xml4K1q61M4uQlmQ\n6lAWA3G9ytHZYJ9siUn44aO6NjhpE1KoQ6I6Pi0E07pa4pQa/2p2oz1Kd5cCIvHWloxzIpy4Li68\nwacrhx5vbCEJ3ZElzWhm7v5xvyOuRnc00mh+3O93no9zOKP7uZ/56Hv5zB297uf7/by/XY1GA0mS\nJJXfovk+AEmSJM0Mg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVUT3+XSKiI3A72bmeyJi\nA/B48dSrwK9k5lhE3AncBZwCdmTmUxHRB3wRWAfUgdsz81BEXAs8WvR9LjMfKv6eB4Fbi/Z7M3N/\nRKwBvgz0Ad8HPpSZJ2fk1UuSJFXIlCt2EfFrwGeB3qJpB/DrmXk90AW8LyIuBT4CbALeC3wyIpYA\nHwa+nZmbgS8ADxRj7ARuK8bYGBFXR8S7gM2ZuRH4APCZou+DwJcycwvwLeCei33RkiRJVXQ+p2K/\nC2xtefzzmfn1iOgB3gIcBa4B9mXmSGbWaa7kXQ1cBzxTfN/TwA0RUQN6MvNA0f4scGPRdw9AZr4G\nLI6Ite3GmM4LlSRJqropg11m7gZGWh43IuLtwIvAGuA/Av00A964Y8BKoNbSPtjSVm/pO9im72Tt\n422SJEma4LyusZsoM/8KuDIifhn4PWAXzXA3rgYcoRngai1tb9AMZ+36Drf0pejTOsZQyxhTajQa\nja6urgt6XZIkSfNkRkLLBQe7iPh3wMcz87s0Q9oosB/YUZyeXQqsp7mi9zxwC/BC8XVvZg5GxFBE\nXAEcAG4CPlGM86mIeBi4HOjKzMMR8fXiez8P3AzsPZ/j7Orq4uDBwQt9eeoAAwM1567EnL/ycu7K\nzfkrt4GB2tSdzsN0Vux+F/hcRAwBx2nuiv1BRDwG7KOZOO/PzOGI2Ak8GRF7aa64fbAY4x6aO10X\nAXsycz9A0e8bxRjbi747ijHuBF5vGUOSJEktuhqNxnwfw2xp+MmlnPzUWW7OX3k5d+Xm/JXbwEBt\nRk7FWqBYkiSpIgx2kiRJFWGwkyRJqgiDnSRJUkUY7CRJkirCYCdJklQRBjtJkjpM7+5drNqyibWX\nrWLVlk307t4134ekkpjWLcUkSdLs6N29i/677zj9uPul79B/9x3UgaGt2+bvwFQKrthJktRBlj36\ncPv2Tz8yx0eiMjLYSZLUQRa/8vIFtUutDHaSJHWQ0SvXX1C71MpgJ0lSBzn+sY+3b//ofXN8JCoj\ng50kSR1kaOs26o8/wciGq2h0dzOy4Srqjz/hxgmdF3fFSpLUYYa2bjPIaVpcsZMkSaoIg50kSVJF\nGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIq\nwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJU\nEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEd3n0yki\nNgK/m5nviYi/BTwGjABDwN/LzIMRcSdwF3AK2JGZT0VEH/BFYB1QB27PzEMRcS3waNH3ucx8qPh7\nHgRuLdrvzcz9EbEG+DLQB3wf+FBmnpyp/wGSJElVMeWKXUT8GvBZoLdoehTYnpk/C+wG/lFEXAp8\nBNgEvBf4ZEQsAT4MfDszNwNfAB4oxtgJ3JaZ1wMbI+LqiHgXsDkzNwIfAD5T9H0Q+FJmbgG+Bdxz\nsS9akiSpis7nVOx3ga0tj38hM/9T8edu4CRwDbAvM0cysw68ClwNXAc8U/R9GrghImpAT2YeKNqf\nBW4s+u4ByMzXgMURsbbdGBf6IiVJkhaCKYNdZu6medp1/PEPACLiZ4DtwO8B/cDRlm87BqwEai3t\ngy1t9Za+g236TtY+3iZJkqQJzusau4ki4heA3wBuKa6Zq9MMd+NqwBGaAa7W0vYGzXDWru9wS1+K\nPq1jDLWMcV4GBmpTd1JHcu7KzfkrL+eu3Jw/XXCwi4hfpLlJ4m9n5njI+nPgdyKiB1gKrAdeBJ4H\nbgFeKL7uzczBiBiKiCuAA8BNwCeAUeBTEfEwcDnQlZmHI+Lrxfd+HrgZ2Hu+x3rw4OCFvjx1gIGB\nmnNXYs5feTl35eb8ldtMhfILCnYRsQj4NPA9YHdENICvZuZvRcRjwD6gC7g/M4cjYifwZETspbni\n9sFiqHto7nRdBOzJzP3F+HuBbxRjbC/67ijGuBN4vWUMSZIktehqNBrzfQyzpeEnl3LyU2e5OX/l\n5dyVm/NXbgMDta6ZGMcCxZIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIk\nVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIk\nqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIk\nSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMk\nSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRXRfT6dImIj8LuZ\n+Z6WtkeAlzPz94vHdwJ3AaeAHZn5VET0AV8E1gF14PbMPBQR1wKPFn2fy8yHijEeBG4t2u/NzP0R\nsQb4MtAHfB/4UGaenIHXLkmSVClTrthFxK8BnwV6i8drI+LfA+9r6XMp8BFgE/Be4JMRsQT4MPDt\nzNwMfAF4oPiWncBtmXk9sDEiro6IdwGbM3Mj8AHgM0XfB4EvZeYW4FvAPRf5miVJkirpfE7FfhfY\n2vJ4BfBPaAa1cdcA+zJzJDPrwKvA1cB1wDNFn6eBGyKiBvRk5oGi/VngxqLvHoDMfA1YHBFr241x\nIS9QkiRpoZgy2GXmbmCk5fGBzNwPdLV06weOtjw+BqwEai3tgy1t9Za+g236TtY+3iZJkqQJzusa\nu/NQpxnuxtWAI0V7raXtDZrhrF3f4Za+FH1axxhqGUOSJEkTXEiw6zrHc38O/E5E9ABLgfXAi8Dz\nwC3AC8XXvZk5GBFDEXEFcAC4CfgEMAp8KiIeBi4HujLzcER8vfjezwM3A3vP94AHBmpTd1JHcu7K\nzfkrL+eu3Jw/XUiwa0z2ODN/EBGPAftoBsD7M3M4InYCT0bEXporbh8svuUemjtdFwF7ilO7FP2+\nUYyxvei7oxjjTuD1ljGmdPDg4AW8PHWKgYGac1dizl95OXfl5vyV20yF8q5GY2Jeq4yGP+Dl5C+n\ncnP+ysu5Kzfnr9wGBmrnOjN63ixQLEmSVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmq\nCIOdJElSRRjsJEmSKsJgJ0mSVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmqCIOdJElS\nRRjsJEmSKsJgJ0mSVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmqCIOdJElSRRjsJEmS\nKsJgJ0mSVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmqCIOdJElSRRjsJEmSKsJgJ0mS\nVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmqCIOdJElSRRjsJEmSKsJgJ0mSVBEGO0mS\npIroPp9OEbER+N3MfE9E/ATwOWAMeDEztxd97gTuAk4BOzLzqYjoA74IrAPqwO2ZeSgirgUeLfo+\nl5kPFWM8CNxatN+bmfsjYg3wZaAP+D7wocw8OTMvX5IkqTqmXLGLiF8DPgv0Fk2PAPdn5hZgUUS8\nPyIuBT4CbALeC3wyIpYAHwa+nZmbgS8ADxRj7ARuy8zrgY0RcXVEvAvYnJkbgQ8Anyn6Pgh8qfj7\nvgXcc9GvWpIkqYLO51Tsd4GtLY9/OjP3Fn9+GrgRuAbYl5kjmVkHXgWuBq4Dnmnpe0NE1ICezDxQ\ntD9bjHEdsAcgM18DFkfE2nZjXOiLlCRJWgimDHaZuRsYaWnqavnzINAP1ICjLe3HgJUT2gdb2uoT\nxpjYd7L28TZJkiRNcF7X2E0w1vLnGvAGzaDWP6H9SNFem9B3cJK+wy19Kfq0jjHUMsZ5GRioTd1J\nHcm5Kzfnr7ycu3Jz/jSdYPcXEbE5M78G3Ax8BdgP7IiIHmApsB54EXgeuAV4ofi6NzMHI2IoIq4A\nDgA3AZ8ARoFPRcTDwOVAV2YejoivF9/7+eLv28t5OnhwcBovT/NtYKDm3JWY81dezl25OX/lNlOh\nfDrB7leBzxabI14CdmVmIyIeA/bRPFV7f2YOR8RO4MmI2Etzxe2DxRj30NzpugjYk5n7AYp+3yjG\n2F703VGMcSfwessYkiRJatHVaDTm+xhmS8NPLuXkp85yc/7Ky7krN+ev3AYGal1T95qaBYolSZIq\nwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJU\nEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZJU\nCb27d7FqyybWXraKVVs20bt713wf0pzrnu8DkCRJuli9u3fRf/cdpx93v/Qd+u++gzowtHXb/B3Y\nHHPFTpIkld6yRx9u3/7pR+b4SOaXwU6SJJXe4ldevqD2qjLYSZKk0hu9cv0FtVeVwU6S5ogXdkuz\n5/jHPt6+/aP3zfGRzC83T0jSHPDCbml2DW3dRp3mNXWLX3mZ0SvXc/yj9y2495fBTpLmwLku7F5o\n//BIs2Vo67YF/37yVKwkzQEv7JY0Fwx2kjQHvLBb0lww2EnSHPDCbklzwWAnSXNgaOs26o8/wciG\nq2h0dzOy4Srqjz+x4K8HkjSz3DwhSXPEC7slzTZX7CRJkirCYCdJklQRBjtJkqSKMNhJkiRVhMFO\nkiSpIgx2kiRJFWGwkyRJqgiDnSRJUkUY7CRJkirCYCdJklQRBjtJkqSKmNa9YiOiB/g3wDuBo8D2\n4qnPAWPAi5m5veh7J3AXcArYkZlPRUQf8EVgHVAHbs/MQxFxLfBo0fe5zHyoGONB4Nai/d7M3D+d\n45YkSaqy6a7Y3QkMZuYm4CPAZ4BHgPszcwuwKCLeHxGXFs9vAt4LfDIilgAfBr6dmZuBLwAPFOPu\nBG7LzOuBjRFxdUS8C9icmRuBDxR/lyRJkiaYbrDbADwNkJmvAj8FvDsz9xbPPw3cCFwD7MvMkcys\nA68CVwPXAc+09L0hImpAT2YeKNqfLca4DthT/F2vAYsjYs00j1uSJKmyphvsvgX8HEBx+vRtE8Ya\nBPqBGs1TteOOASsntA+2tNUnjDGxb+sYkiqsd/cuVm3ZxNrLVrFqyyZ6d++a70OSpI43rWvsgCeA\nn4qIrwFfB74JXNbyfA14g2ZQ65/QfqRor03oOzhJ3+GWvq39pzQwUJu6kzqSc1duFz1/f/iHcPcd\npx92v/Qd+u++A/qXwm23XeTR6Vx875Wb86fpBrv/HvjTzLwvIn4a+HHgryNiS2Z+FbgZ+AqwH9hR\nbLZYCqwHXgSeB24BXii+7s3MwYgYiogrgAPATcAngFHgUxHxMHA50JWZh8/nIA8eHJzmy9N8Ghio\nOXclNhPzt+qh32n7y2nkt3dw5IZbL2psTc73Xrk5f+U2U6F8usHuVeC3I+I3aa6q/TLNlbTPFpsj\nXgJ2ZWYjIh4D9gFdNDdXDEfETuDJiNgLDAEfLMa9B/gyzdO6e8Z3vxb9vlGMMb4DV1JFLX7l5Qtq\nlyQ1dTUajfk+htnS8JNLOfmps9xmZMVuyya6X/rOWe0jG67iyH94/qLG1uR875Wb81duAwO1rpkY\nxwLFkjrO8Y99vH37R++b4yORpHIx2EnqOENbt1F//AlGNlxFo7ubkQ1XUX/8CYa2bpvvQ5Okjjbd\na+wkaVYNbd1mkJOkC+SKnSRJUkUY7CRJkirCYCdJklQRBjtJkqSKMNhJkiRVhMFOEr27d7FqyybW\nXraKVVs20bt713wfkiRpGix3Ii1wvbt30X/3Hacfd7/0HfrvvoM6WG5EkkrGFTtpgVv26MPt2z/9\nyBwfiSTpYhnsVFqePpwZi195+YLaJUmdy2CnUho/fdj90nfoGh09ffrQcHfhRq9cf0HtkqTOZbBT\nKXn6cOYc/9jH27d/9L45PhJJ0sUy2KmUPH04c4a2bqP++BOMbLiKRnc3Ixuuov74E26ckKQScles\nSmn0yvV0v/Sdtu26cENbtxnkJKkCXLFTKXn6UJKksxnsVEqePpQk6WyeilVpefpQkqQzuWInSZJU\nEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZI6\nXO/uXazasom1l61i1ZZN9O7eNd+HpA7lLcUkSepgvbt30X/3Hacfd7/0HfrvvoM6eFtFncUVuyn4\nKUmSNJ+WPfpw+/ZPPzLHR6IycMXuHPyUJEmab4tfefmC2rWwuWJ3Dn5KkiTNt9Er119QuxY2g905\n+ClJkjTfjn/s4+3bP3rfHB+JysBgdw5+SpIkzbehrduoP/4EIxuuotHdzciGq6g//oSXBKktr7E7\nh+Mf+/gZ19idbvdTkiRpDg1t3WaQ03lxxe4c/JQkSZLKxBW7KfgpSZIklYUrdpIkSRVhsJMkSaoI\ng50kSVJFTOsau4joBp4E3gGMAHcCo8DngDHgxczcXvS9E7gLOAXsyMynIqIP+CKwDqgDt2fmoYi4\nFni06PtcZj5UjPEgcGvRfm9m7p/Wq5UkSaqw6a7Y3QIszsz/Afht4J8CjwD3Z+YWYFFEvD8iLgU+\nAmwC3gt8MiKWAB8Gvp2Zm4EvAA8U4+4EbsvM64GNEXF1RLwL2JyZG4EPAJ+Z5jFLkiRV2nSD3StA\nd0R0AStprqS9OzP3Fs8/DdwIXAPsy8yRzKwDrwJXA9cBz7T0vSEiakBPZh4o2p8txrgO2AOQma8B\niyNizTSPW5IkqbKmW+7kGHAF8DKwBngfcH3L84NAP1ADjk74vpUT2gdb2uoTxngncAI41GaM1jZJ\nkqQFb7rB7l7gmcz8zYh4G/AfgJ6W52vAGzSDWv+E9iNFe21C38FJ+g639G3tP6WBgdrUndSRnLty\nc/7Ky7krN+dP0w12h2mefoVmyOoG/jIitmTmV4Gbga8A+4EdEdEDLAXWAy8Cz9O8Tu+F4uvezByM\niKGIuAI4ANwEfILmpoxPRcTDwOVAV2YePp+DPHhwcJovT/NpYKDm3JWY81dezl25OX/lNlOhfLrB\n7lHgiYj4GrAE+HXgm8AfFJsjXgJ2ZWYjIh4D9gFdNDdXDEfETuDJiNgLDAEfLMa9B/gyzWv/9ozv\nfi36faMYY/s0j1mSJKnSuhqNxnwfw2xp+MmlnPzUWW7OX3k5d+Xm/JXbwECtaybGsUCxJElSRRjs\nJEmSKsJgJ0mSVBEGO0mSpIow2EmSFqTe3btYtWUTay9bxaotm+jdvWu+D0m6aNMtdyJJUmn17t5F\n/913nH7c/dJ36L/7DurA0NZt83dg0kVyxU6StOAse/Th9u2ffmSOj0SaWQY7SdKCs/iVly+oXSoL\ng50kacEZvXL9BbVLZWGwkyQtOMc/9vH27R+9b46PRJpZBjtJ0oIztHUb9cefYGTDVTS6uxnZcBX1\nx59w44RKz12xkqQFaWjrNoOcKscVO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmqCIOdJElS\nRRjsJEmSKsJgJ0mSVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbDTOfXu3sWqLZtYe9kqVm3Z\nRO/uXfN9SNKs8eddUtl1z/cBqHP17t5F/913nH7c/dJ36L/7DurA0NZt83dg0izw511SFbhip0kt\ne/Th9u2ffmSOj0Saff68S6oCg50mtfiVly+oXSozf94lVYHBTpMavXL9BbVLZebPu6QqMNhpUsc/\n9vH27R+9b46PRJp9/rxLqgKDnSY1tHUb9cefYGTDVTS6uxnZcBX1x5/wQnJVkj/vkqqgq9FozPcx\nzJbGwYOD830MmoaBgRrOXXk5f+Xl3JWb81duAwO1rpkYxxU7SZKkijDYSZIkVYTBTrPOav6SJM0N\n7zyhWWU1f0mS5o4rdppVVvOXJGnuGOw0q6zmL0nS3DHYaVZZzV+SpLljsNOsspq/JuOmGkmaeW6e\n0Kwa2rqNOs1r6ha/8jKjV67n+Efvc+PEAuemGkmaHQY7zbqhrdv8x1pnONemGn9WJGn6phXsIuJ2\n4JeABrAUuBq4HngUGANezMztRd87gbuAU8COzHwqIvqALwLrgDpwe2YeiohrizFOAc9l5kPFGA8C\ntxbt92bm/um9XEmdwE01kjQ7pnWNXWY+mZnvycyfBb4J/APgQeD+zNwCLIqI90fEpcBHgE3Ae4FP\nRsQS4MPAtzNzM/AF4IFi6J3AbZl5PbAxIq6OiHcBmzNzI/AB4DPTfrWSOoKbaiRpdlzU5omI+O+A\nDZn5B8BPZ+be4qmngRuBa4B9mTmSmXXgVZqre9cBz7T0vSEiakBPZh4o2p8txrgO2AOQma8BiyNi\nzcUct6T55aYaSZodF7sr9jeAT7RpHwT6gRpwtKX9GLByQvtgS1t9whgT+7aOIamkhrZuo/74E4xs\nuIpGdzcjG66i/vgTXl8nSRdp2psnImIlcGVmfq1oGmt5uga8QTOo9U9oP1K01yb0HZyk73BL39b+\nUxoYqE3dSR3JuSu385q/uz7U/I/mL6L+c/fWHPG9V27Ony5mV+xm4E9bHv9lRGwugt7NwFeA/cCO\niOihucliPfAi8DxwC/BC8XVvZg5GxFBEXAEcAG6iuRo4CnwqIh4GLge6MvPw+RzgwYODF/HyNF8G\nBmrOXYk5f+Xl3JWb81duMxXKL+ZUbAD/peXxrwIPRcTXgSXArsz8AfAYsA/4E5qbK4ZpbpK4KiL2\nAr8C/FYxxj3Al4E/A/4iM/dn5l8Ae4FvAH8EbL+IYy4FC7dKkqTp6Go0GvN9DLOlUcZPLhMLt45b\nSNcf+amz3Jy/8nLuys35K7eBgVrXTIzjLcU6zLkKt0qSJJ2Lwa7DWLhVkiRNl8Guw1i4VZIkTZfB\nrsNYuFWSJE2Xwa7DWLhVkiRN18XUsdMsGdq6zSAnSZIumCt2kiRJFeGKnSRJ0nkaHRvjSH2IQ/WT\nHP3RMBvesZoVS5fM92GdZrCTJEkqDJ0a5XD9JIeOnuT14uuhlq9HBodovbfD/3TdFfzd666YvwOe\nwGAnSZIWhEajwY9OjpwV1sZD3OH6SQaPn2r7vV1dcMmKXn7ibStZ29/HmpXN/65Zv26OX8W5Gewk\nSVIljDUaHD02XAS1ExyuD50V3oaGR9t+b/fiRazp7+XydStYMx7c+vtYW3y9pNZL9+LO35pgsJMk\nSaVwamSMI4OTnyY9XB9idKzR9nuX9nYzsHLp6aC2ZmUfq/t7WbOyj7X9fdSW97Coa0Zu1zqvDHaS\nJKkjnBgaOesUaetqW/3YMO1jG6xc3sOPv6XG6v6+N0+Vtnxd1rcwIs/CeJWSJGleNRoNBo+fejOo\nnV5lezPA/ejkSNvvXbyoi1W1Xq68/JIzA1ux2ra6v5cl3Yvn+BV1JoOdJEm6aKNjYxwZHDp9XdvE\nU6WH6ycZHhlr+709Sxaxpr+PK97a33a17ZIVvSxaVP7TpHPBYCdJkqY0fGq0GdImnio9XQZkmLFG\n+xOlK5Yu4bI1y98MbMW1beOPVyxdQlcFrm/rBAY7SZIWuEajwfGhkdNB7fUzNiQ0/1yfogzIO9/W\nX5wWnbji1ktfj3Fjrvh/WpKkijtdBqTltOjEU6UnpygD8raBFaevaWsNbqtKUgZkoTDYSZJUciOj\nY/z1oR/xyveOtN1RenjwJCOjk5UBWXxGCZDW0FalMiALhcFOkqQOd3J45KzSH62Pj56jDEj/8h4u\nX1dru9q2kMqALBTOpiRJ86jRaDB44tQZGxFOfy3+fD5lQN52aY3lPYstA7LAGewkSZpFo2NjvDE4\n3H5HadE2fOrCyoCsLm511VoGZGCgxsGDg3P50tSBDHaSJF2E8TIgh+tDHKoXhXdbwtuRwaFzlwFZ\nvfz07a3WTrjOzTIgulAGO0mSJnFGGZBJbnU1aRkQ4JJaL+98a/9Z17VZBkSzxZ8oSdKCNdZoUP/R\n8Dk3JkxeBqSL1f19bcuArF7Zx2rLgGgeGOwkSZU1MjrG4cGhSTcmHK5PXgakb3wjQkvpj9bH/ZYB\nUQcy2EmSSmtiGZBDxXVu421vDA5NXgZk2RIuX7eizSnS5saEZX1L5vS1SDPBYCdJ6kjjZUDGb2nV\n7jTpZGVAFnU1y4D85OWXnHFN25v3Ku2jZ4llQFQ9BjtJ0rwYG2vwxrGh5i7SCy0D0r2I1f19vOOy\n/ranSi+p9bB4kde3aeEx2EmSZsWpkdHmqdEiqL1+9M0byh+qN8uAjI61P1G6vK+bt6xa1n436co+\napYBkdoy2EmSpuX4yVNnBLeJp0rrPxpu+31dwMoVPbzjstoZq22rWwLc0l7/eZKmw3eOJOksp8uA\nTDxF2nKa9MRQ+zIgixd1saa/j7e+/ZK2u0pX1fpY0u1pUmk2GOwkaQEaGR3jyOCZq20/Gh7lv/5g\n8PRdFEZG21/f1tuzuBnSfqxd0d0+Vq6wDIg0Xwx2klRBQ8Ojp0+L3nEXLO0/zrL+EyztP87S/uP0\nLT9J1ySLZrVlS/ixgeVnrbaNnypd3tft9W1ShzLYSVLJNBoNjp04Vay0DbXdUXrsxJu3ufpvb3zz\ne8fGujjiCsQlAAASIUlEQVQ52Mfh76/hRH0p9/zK4tPh7SffsYaukVHLgEglZrCTpA4zXgZkYmAb\nX4E7XB9i6FT769vGy4D8+Fve3Jjw4G9cwon6Mo7XlzJ0rI9G482lup///ODpPw8M1Dh4cLDdsJJK\nwmAnSXPs1Mgoh+tDb+4gnbDaNlUZkEtXLZ3kpvJ91JadXQbkl1+qzcXLktQBDHaSNMOOnxw5x2rb\nSY5OUgYEijIgb6lNGtwsAyLpXPwNIUkXoFGUAWmt13a4uM5t/A4KJ4ba3+Zq8aIuVvf3st4yIJJm\nicFOklqMjI7xxuCZQW3iTeanLgOykjX9fawu7k26tr956nTl8h4WLXI3qaTZY7CTtKAMDY+eLrDb\n7lTpG8eGaLS/vI3asiW8bWD5Gfckbf3aqWVAfvhDN0RIC8W0g11E/Drwd4ElwL8CvgZ8DhgDXszM\n7UW/O4G7gFPAjsx8KiL6gC8C64A6cHtmHoqIa4FHi77PZeZDxRgPArcW7fdm5v7pHrek6mo0Gvzo\n5EgzqLWEtsP1N4NbaxmQVl1dsKrWy99428q2p0lX9/fRaxkQSR1uWsEuIrYAmzLzZyJiOfCrwCPA\n/Zm5NyJ2RsT7gT8DPgK8G1gG7IuIPcCHgW9n5kMR8QvAA8DHgJ3A1sw8EBFPRcTVwCJgc2ZujIjL\ngf8DuOaiXrWkUhovA9LcUXri9KnR1pW3ycqALBkvA3LpitNBbU1/H2uLEHdJrZfuxV7fJqncprti\ndxPwYkT8MVAD/iHwK5m5t3j+aeB/pLl6ty8zR4B6RLwKXA1cB3yqpe8/joga0JOZB4r2Z4EbgSFg\nD0BmvhYRiyNiTWYemuaxS+pQp0bGODzYvgTI60fPXQZkWW8361Ytba60jZ8ibVl5629TBkSSqma6\nwW4t8Hbg54B3Av8nzZW1cYNAP83Qd7Sl/RiwckL7YEtbfcIY7wROAIfajGGwk0rmxNDIGdezTbzO\n7ZxlQJb3nFF0d+KpUsuASNL0g90h4KViJe6ViDgJ/FjL8zXgDZpBrX9C+5GivTah7+AkfYdb+rb2\nl9RBGo0G9eOnOHLiCN/93uEzV92K4Hb8HGVAVtWKMiAtwW316XuU9rKk2+vbJGkq0w12+4B/APxe\nRLwVWA78aURsycyvAjcDXwH2AzsiogdYCqwHXgSeB24BXii+7s3MwYgYiogrgAM0T/d+AhgFPhUR\nDwOXA12Zefh8DnJgwGrrZeXcdZ7R0TFeP3qSHx45zsEjJzh45Dg/PHKieNxsGx5pXwakr2cxA6uW\n8VOrlrJu1TIGiq/rVi1j3eqlXFLrY7FlQDqC771yc/40rWBX7Gy9PiL+HOiiuRniAPAHEbEEeAnY\nlZmNiHiMZhDsorm5YjgidgJPRsRemtfQfbAY+h7gyzRP6+4Z3/1a9PtGMcb28z1O73lYTt6vcn4M\nnRo9awfpxNtcTVYGZMXSJVy2tlkG5Mfe0s+yJYvOuwzI2PAIhw8dm8VXpvPle6/cnL9ym6lQ3tWY\n7Dd1+TX8AS8nfznNvNYyIJPVb5uqDMhk17atrvXR2/PmaVLnr7ycu3Jz/sptYKA2I6ctvNpYqoCx\nRoOjx4aLoNamDEj9JEPD7cuAdC9exJr+Xt5+6YozwptlQCSpfAx2UgmcqwzIofpJDtcnLwOytLeb\ngZVLTwc1y4BIUnUZ7KQO0K4MyOGWU6VHj02vDMjq/j6W9fk2l6SFwt/40iwbLwNyemNCm+vcLAMi\nSZoJBjvpIo2OjXFkcGiSjQlDHK6f5NQkZUBGhhfz9rf28ROn70965iaFS1b0ssgyIJKk82Swk6Yw\ndGr0jNOircHtcP0kRwaHGZtkd/mKpUt469rl/NneFZyoL+VEfRknBpdyvL6ME/VlnDq5hB/+0FIf\nkqSZYbDTgtZaBmSy+m2DxycvA3LJil7e+bb+06U/zrjOrf/NMiDr/qFFQ2faunWT/z/94Q/bl3yY\nzvdIUpkY7FRpp8uATHJv0tfPowzI5essAyJJKgeDnUptZHTsjNOkh+tnXut2ePAkI6MXVgZkdX8v\na/v7qC3vYZFlQCRJJWKwU0c7MTTSDG6TXON29Ngwk907ZeXyHt5+ae2s06Pjf7YMiCSpavyXTfOm\n0WgweOLUWUV3B0+O8P8dPMah+kl+dPLcZUCuvPySM69tswyIJGkBM9hp1oyOjfHG4PBZq22tK3DD\nk5QB6VmyiDX9fVzx1vYbE8pWBsQL8yVpdrk5qslgp2kbPjV6+pZWb664DZ1+fGRw6JxlQC5bs/ys\nwLZ2ZR8/ecUaho4PeZsrSZIukMFObTUaDY4Xt7l6c2PCmadM65OVAQEuqfXyzrf2n10CpCjC29cz\n+Y/eyhW9HDwx+S20JJjeJ/CF9Kld0sJksFug2pYBmRDcTk5aBqSL1f19vG1gxelr2lqD2yrLgEiS\nNC8MdhV1ugxIvf2trs5dBmTx6RIgq9sEt37LgEiS1JEMdiV1cnjkrEK751sGpH95D5evq52xg7T1\nGrdlfUvm9LVIkqSZYbDrQG3LgEwIbpOVAVnU1SwD8pOXX3J6ha21AO/qWi89SywDIklSFRns5sEZ\nZUDa3eqqfpLhU5OUAelexJqVfVxxWZuNCf19XFLrYfEir2+TJC0sbo5qMtjNglMjo2dc2/b6hAK8\n5yoDsryvm7esWtZ+N+nKPmpLl1gGRJIktWWwm4bjJ081w9okN5afqgzIFW998zZXrRsTVvf3sbTX\nKZEkSdNjiphgvHJ1V9cY6975A5avOsay/hMsrR3np69t3ubqxNA5yoDUijIgbVbbVlsGZFZZdVy6\ncGe/b9587PtGKh+D3SQuu/L7vPvWb57R9vrRxWeENcuASJKkTmKwm8QP/stb+NYz7+LUySUcry/j\nxOAyvv/ayfk+LElSiXlmQbPNYDeJ0VPd/Nf//PYJrQY7SZLUuQx2kiRp3rmaOTO8kl+SJKkiDHaS\nJEkV4anYCVzuLS/nTrpwre+bgYEaBw/6PpLKzBU7SZKkinDFTpKkOeKZBc02g50kSdIF6OQdvAY7\nSZI07+Y7EFWF19hJkiRVhMFOkiSpIgx2kiRJFWGwkyRJqgiDnSRJUkW4K1aSJOkCdPIOXlfsJEmS\nKsJgJ0mSVBEGO0mSpIqY9jV2EfFN4Gjx8P8F/inwOWAMeDEztxf97gTuAk4BOzLzqYjoA74IrAPq\nwO2ZeSgirgUeLfo+l5kPFWM8CNxatN+bmfune9ySJElVNa0Vu4joBcjMny3++2XgEeD+zNwCLIqI\n90fEpcBHgE3Ae4FPRsQS4MPAtzNzM/AF4IFi6J3AbZl5PbAxIq6OiHcBmzNzI/AB4DPTfrWSJEkV\nNt1TsVcDyyPi2Yj4k4jYCLw7M/cWzz8N3AhcA+zLzJHMrAOvFt97HfBMS98bIqIG9GTmgaL92WKM\n64A9AJn5GrA4ItZM87glSZIqa7rB7jjwzzLzJpqrb18CulqeHwT6gRpvnq4FOAasnNA+2NJWnzDG\nxL6tY0iSJKnFdK+xewX4LkBmvhoRh4B3tzxfA96gGdT6J7QfKdprE/oOTtJ3uKVva/8pDQzUpu6k\njuTclZvzV17OXbk5f5pusLsD+JvA9oh4K81AticitmTmV4Gbga8A+4EdEdEDLAXWAy8CzwO3AC8U\nX/dm5mBEDEXEFcAB4CbgE8Ao8KmIeBi4HOjKzMPnc5AHD3ZuAUFNbmCg5tyVmPNXXs5duTl/5TZT\noXy6we5fA/8mIvbS3AX7S8Ah4A+KzREvAbsysxERjwH7aJ6qvT8zhyNiJ/Bk8f1DwAeLce8Bvkzz\nFPGe8d2vRb9vFGNsn+YxS5IkVVpXo9GY72OYLY25/uSybt3kabsTbj/S6cc3zk+d5eb8lZdzV27O\nX7kNDNS6pu41NQsUS5IkVcS0CxRLkqqvLCv9kppcsZMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEW6e\nmEGdfiFxpx+fyuvsC+zffOzPnSTNHVfsJEmSKsIVO0nSpFxxlcrFYHcO1m+SJEll4qlYSZKkijDY\nSZIkVYTBTpIkqSK8xk7SRWu95nRgoMbBg16DKml+LPTr412xkyRJqgiDnSRJUkV4KvYcFsKSrSRJ\nc2mhnyqdba7YSZIkVYTBTpIkqSIMdpIkSRXhNXaSJKkyFvp1eq7YSZIkVYTBTpIkqSI8FStJkubM\nQj9VOttcsZMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVh\nsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoI\ng50kSVJFdF/MN0fEOuAF4O8Ao8DngDHgxczcXvS5E7gLOAXsyMynIqIP+CKwDqgDt2fmoYi4Fni0\n6PtcZj5UjPEgcGvRfm9m7r+Y45YkSaqiaa/YRUQ38L8Cx4umR4D7M3MLsCgi3h8RlwIfATYB7wU+\nGRFLgA8D387MzcAXgAeKMXYCt2Xm9cDGiLg6It4FbM7MjcAHgM9M95glSZKq7GJOxf5zmkHs+0AX\n8O7M3Fs89zRwI3ANsC8zRzKzDrwKXA1cBzzT0veGiKgBPZl5oGh/thjjOmAPQGa+BiyOiDUXcdyS\nJEmVNK1gFxG/BPwwM5+jGeomjjUI9AM14GhL+zFg5YT2wZa2+oQxJvZtHUOSJEktpnuN3YeAsYi4\nkeYK3OeBgZbna8AbNINa/4T2I0V7bULfwUn6Drf0be0/la6BgdrUvdSRnLtyc/7Ky7krN+dP01qx\ny8wtmfmezHwP8C3gfwGejojNRZebgb3AfuC6iOiJiJXAeuBF4HnglqLvLcDezBwEhiLiiojoAm4q\nxngeuCkiuiLi7UBXZh6e1quVJEmqsIvaFTvBrwKfLTZHvATsysxGRDwG7KN5yvb+zByOiJ3AkxGx\nFxgCPliMcQ/wZZqBc8/47tei3zeKMbbP4DFLkiRVRlej0ZjvY5AkSdIMsECxJElSRRjsJEmSKsJg\nJ0mSVBEzuXli1hV3u3gCeAfQA+wA/jMXeSuzOX4ZC1K7ucvM/6t47hHg5cz8/eKxc9dhJnnv/RXw\nL4ARmpug/l5mHnT+Osskc/dd4PeLLq8Cv5KZY85d55nid+cHgb+fmT9TPHb+Oswk77/XgP8beKXo\ntjMz/2im5q9sK3a/CLxe3IrsvcC/ZGZuZabZ1zp3NwP/MiLWRMS/B9433sm561jt3nuPAtsz82eB\n3cA/cv46Uru52wH8enH7xi7gfc5dxzrrdydAcbvNO8Y7OX8dq938vRt4ODN/tvjvj2Zy/soW7P53\n3nxRi2muFFzMrcz+zlwduM6Yu0U0P5GsAP4JzR/Wcc5dZ5r43jsF/EJm/qeirRs4ifPXic6au8z8\n+cz8ekT0AG+heXcf564znfW7MyJWA78DfLSln/PXmdr92/fTwM9FxFcj4rMRsYIZnL9SnYrNzOMA\nxX1l/wj4TZr3rB13obcya73ThWZRu7nLzO8B34uIW1q69uPcdZxJ5u+HRdvP0KwvOb4i5Px1kEl+\nb1IUfP8Tmnfy+Y80i8U7dx2mzfw9APxr4D6al0CM83dnB2ozf/8Y6AX+IDP/MiJ+g+YCx7eYofkr\n24odEXE58BXgycz8Q5rX1o2bzq3MNEcmzN3/Nkk3565DtZu/iPgF4F8BtxTXfTh/Hajd3GXmX2Xm\nlcDjwO/R/MfDuetArfNH8/rIvwHsBP4tsKG4Ttn3Xodqk1v+ODP/snj6j4G/xQy+/0q1Ylecg36W\n5nU9/0/R/JcRsTkzv0bz/PVXaN7KbEdxmmEpZ9/K7IXi6140JyaZu3b+HPgd566ztJu/iPhFmhf6\n/u3MHP9l4/x1mEnm7t8BH8/M79JcBRjF35sdaZLfnX+zeO7HgX+bmfcV/XzvdZhJ5u/ZiPj7mfkC\ncAPwTWbw/VeqO09ExKPA/wy8TPOC3wbNawz+BTB+K7M7i1uZ/TJwd9FvR2b+cUQspfmJ5zKKW5mN\nn07S7Jpk7m7OzKGIeBD465Zdsc5dh2kzf4uB/wb4Hs1Pmg3gq5n5W85fZ5nkvfebwD+jORfHae6K\n/YFz13mm+N05HuzGd8U6fx1mivffMPDXwF2ZeWym5q9UwU6SJEmTK901dpIkSWrPYCdJklQRBjtJ\nkqSKMNhJkiRVhMFOkiSpIgx2kiRJFWGwkyRJqgiDnSRJUkX8//Fc+U9EWZJdAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xb724278>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted: -1.0    Actual: -1 Raw:  -13.514952955\n",
      "Predicted: 1.0    Actual: 1 Raw:  1018.84606793\n",
      "Predicted: -1.0    Actual: -1 Raw:  -291.589932075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -228.969817235\n",
      "Predicted: 1.0    Actual: 1 Raw:  492.230339365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -264.969441395\n",
      "Predicted: 1.0    Actual: 1 Raw:  644.280673445\n",
      "Predicted: 1.0    Actual: 1 Raw:  555.660830045\n",
      "Predicted: 1.0    Actual: 1 Raw:  1069.40603885\n",
      "Predicted: -1.0    Actual: -1 Raw:  -108.832919395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -15.365653995\n",
      "Predicted: 1.0    Actual: 1 Raw:  1013.81181141\n",
      "Predicted: -1.0    Actual: -1 Raw:  -451.502031995\n",
      "Predicted: 1.0    Actual: 1 Raw:  398.852082845\n",
      "Predicted: 1.0    Actual: 1 Raw:  1076.51815593\n",
      "Predicted: -1.0    Actual: -1 Raw:  -109.401760555\n",
      "Predicted: -1.0    Actual: -1 Raw:  -121.769735275\n",
      "Predicted: 1.0    Actual: 1 Raw:  476.282427365\n",
      "Predicted: 1.0    Actual: 1 Raw:  1190.48265705\n",
      "Predicted: -1.0    Actual: -1 Raw:  -11.124161075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -294.199087995\n",
      "Predicted: -1.0    Actual: -1 Raw:  -521.690914915\n",
      "Predicted: 1.0    Actual: 1 Raw:  512.523586205\n",
      "Predicted: -1.0    Actual: -1 Raw:  -394.235131915\n",
      "Predicted: 1.0    Actual: 1 Raw:  2303.29995161\n",
      "Predicted: 1.0    Actual: 1 Raw:  657.573993365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -765.487626395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -469.645563755\n",
      "Predicted: 1.0    Actual: 1 Raw:  1033.29468241\n",
      "Predicted: -1.0    Actual: -1 Raw:  -380.209317595\n",
      "Predicted: -1.0    Actual: -1 Raw:  -768.714296715\n",
      "Predicted: -1.0    Actual: -1 Raw:  -551.449067035\n",
      "=== Loop  5  ===\n",
      "Weights: [ -9.99989560e-01   3.68100000e-03  -5.00000000e-09]\n",
      "Accuracy: 100.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xdb2bef0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted: -1.0    Actual: -1 Raw:  -13.514952955\n",
      "Predicted: 1.0    Actual: 1 Raw:  1018.84606793\n",
      "Predicted: -1.0    Actual: -1 Raw:  -291.589932075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -228.969817235\n",
      "Predicted: 1.0    Actual: 1 Raw:  492.230339365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -264.969441395\n",
      "Predicted: 1.0    Actual: 1 Raw:  644.280673445\n",
      "Predicted: 1.0    Actual: 1 Raw:  555.660830045\n",
      "Predicted: 1.0    Actual: 1 Raw:  1069.40603885\n",
      "Predicted: -1.0    Actual: -1 Raw:  -108.832919395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -15.365653995\n",
      "Predicted: 1.0    Actual: 1 Raw:  1013.81181141\n",
      "Predicted: -1.0    Actual: -1 Raw:  -451.502031995\n",
      "Predicted: 1.0    Actual: 1 Raw:  398.852082845\n",
      "Predicted: 1.0    Actual: 1 Raw:  1076.51815593\n",
      "Predicted: -1.0    Actual: -1 Raw:  -109.401760555\n",
      "Predicted: -1.0    Actual: -1 Raw:  -121.769735275\n",
      "Predicted: 1.0    Actual: 1 Raw:  476.282427365\n",
      "Predicted: 1.0    Actual: 1 Raw:  1190.48265705\n",
      "Predicted: -1.0    Actual: -1 Raw:  -11.124161075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -294.199087995\n",
      "Predicted: -1.0    Actual: -1 Raw:  -521.690914915\n",
      "Predicted: 1.0    Actual: 1 Raw:  512.523586205\n",
      "Predicted: -1.0    Actual: -1 Raw:  -394.235131915\n",
      "Predicted: 1.0    Actual: 1 Raw:  2303.29995161\n",
      "Predicted: 1.0    Actual: 1 Raw:  657.573993365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -765.487626395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -469.645563755\n",
      "Predicted: 1.0    Actual: 1 Raw:  1033.29468241\n",
      "Predicted: -1.0    Actual: -1 Raw:  -380.209317595\n",
      "Predicted: -1.0    Actual: -1 Raw:  -768.714296715\n",
      "Predicted: -1.0    Actual: -1 Raw:  -551.449067035\n",
      "=== Loop  6  ===\n",
      "Weights: [ -9.99989560e-01   3.68100000e-03  -5.00000000e-09]\n",
      "Accuracy: 100.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xb744828>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted: -1.0    Actual: -1 Raw:  -13.514952955\n",
      "Predicted: 1.0    Actual: 1 Raw:  1018.84606793\n",
      "Predicted: -1.0    Actual: -1 Raw:  -291.589932075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -228.969817235\n",
      "Predicted: 1.0    Actual: 1 Raw:  492.230339365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -264.969441395\n",
      "Predicted: 1.0    Actual: 1 Raw:  644.280673445\n",
      "Predicted: 1.0    Actual: 1 Raw:  555.660830045\n",
      "Predicted: 1.0    Actual: 1 Raw:  1069.40603885\n",
      "Predicted: -1.0    Actual: -1 Raw:  -108.832919395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -15.365653995\n",
      "Predicted: 1.0    Actual: 1 Raw:  1013.81181141\n",
      "Predicted: -1.0    Actual: -1 Raw:  -451.502031995\n",
      "Predicted: 1.0    Actual: 1 Raw:  398.852082845\n",
      "Predicted: 1.0    Actual: 1 Raw:  1076.51815593\n",
      "Predicted: -1.0    Actual: -1 Raw:  -109.401760555\n",
      "Predicted: -1.0    Actual: -1 Raw:  -121.769735275\n",
      "Predicted: 1.0    Actual: 1 Raw:  476.282427365\n",
      "Predicted: 1.0    Actual: 1 Raw:  1190.48265705\n",
      "Predicted: -1.0    Actual: -1 Raw:  -11.124161075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -294.199087995\n",
      "Predicted: -1.0    Actual: -1 Raw:  -521.690914915\n",
      "Predicted: 1.0    Actual: 1 Raw:  512.523586205\n",
      "Predicted: -1.0    Actual: -1 Raw:  -394.235131915\n",
      "Predicted: 1.0    Actual: 1 Raw:  2303.29995161\n",
      "Predicted: 1.0    Actual: 1 Raw:  657.573993365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -765.487626395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -469.645563755\n",
      "Predicted: 1.0    Actual: 1 Raw:  1033.29468241\n",
      "Predicted: -1.0    Actual: -1 Raw:  -380.209317595\n",
      "Predicted: -1.0    Actual: -1 Raw:  -768.714296715\n",
      "Predicted: -1.0    Actual: -1 Raw:  -551.449067035\n",
      "=== Loop  7  ===\n",
      "Weights: [ -9.99989560e-01   3.68100000e-03  -5.00000000e-09]\n",
      "Accuracy: 100.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xc094390>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted: -1.0    Actual: -1 Raw:  -13.514952955\n",
      "Predicted: 1.0    Actual: 1 Raw:  1018.84606793\n",
      "Predicted: -1.0    Actual: -1 Raw:  -291.589932075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -228.969817235\n",
      "Predicted: 1.0    Actual: 1 Raw:  492.230339365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -264.969441395\n",
      "Predicted: 1.0    Actual: 1 Raw:  644.280673445\n",
      "Predicted: 1.0    Actual: 1 Raw:  555.660830045\n",
      "Predicted: 1.0    Actual: 1 Raw:  1069.40603885\n",
      "Predicted: -1.0    Actual: -1 Raw:  -108.832919395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -15.365653995\n",
      "Predicted: 1.0    Actual: 1 Raw:  1013.81181141\n",
      "Predicted: -1.0    Actual: -1 Raw:  -451.502031995\n",
      "Predicted: 1.0    Actual: 1 Raw:  398.852082845\n",
      "Predicted: 1.0    Actual: 1 Raw:  1076.51815593\n",
      "Predicted: -1.0    Actual: -1 Raw:  -109.401760555\n",
      "Predicted: -1.0    Actual: -1 Raw:  -121.769735275\n",
      "Predicted: 1.0    Actual: 1 Raw:  476.282427365\n",
      "Predicted: 1.0    Actual: 1 Raw:  1190.48265705\n",
      "Predicted: -1.0    Actual: -1 Raw:  -11.124161075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -294.199087995\n",
      "Predicted: -1.0    Actual: -1 Raw:  -521.690914915\n",
      "Predicted: 1.0    Actual: 1 Raw:  512.523586205\n",
      "Predicted: -1.0    Actual: -1 Raw:  -394.235131915\n",
      "Predicted: 1.0    Actual: 1 Raw:  2303.29995161\n",
      "Predicted: 1.0    Actual: 1 Raw:  657.573993365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -765.487626395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -469.645563755\n",
      "Predicted: 1.0    Actual: 1 Raw:  1033.29468241\n",
      "Predicted: -1.0    Actual: -1 Raw:  -380.209317595\n",
      "Predicted: -1.0    Actual: -1 Raw:  -768.714296715\n",
      "Predicted: -1.0    Actual: -1 Raw:  -551.449067035\n",
      "=== Loop  8  ===\n",
      "Weights: [ -9.99989560e-01   3.68100000e-03  -5.00000000e-09]\n",
      "Accuracy: 100.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3X+U3fV93/nnSKOZ0Y87Qj9GGDs4xml4K1q61M4uQlmQ\n6lAWA3G9ytHZYJ9siUn44aO6NjhpE1KoQ6I6Pi0E07pa4pQa/2p2oz1Kd5cCIvHWloxzIpy4Li68\nwacrhx5vbCEJ3ZElzWhm7v5xvyOuRnc00mh+3O93no9zOKP7uZ/56Hv5zB297uf7/by/XY1GA0mS\nJJXfovk+AEmSJM0Mg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVUT3+XSKiI3A72bmeyJi\nA/B48dSrwK9k5lhE3AncBZwCdmTmUxHRB3wRWAfUgdsz81BEXAs8WvR9LjMfKv6eB4Fbi/Z7M3N/\nRKwBvgz0Ad8HPpSZJ2fk1UuSJFXIlCt2EfFrwGeB3qJpB/DrmXk90AW8LyIuBT4CbALeC3wyIpYA\nHwa+nZmbgS8ADxRj7ARuK8bYGBFXR8S7gM2ZuRH4APCZou+DwJcycwvwLeCei33RkiRJVXQ+p2K/\nC2xtefzzmfn1iOgB3gIcBa4B9mXmSGbWaa7kXQ1cBzxTfN/TwA0RUQN6MvNA0f4scGPRdw9AZr4G\nLI6Ite3GmM4LlSRJqropg11m7gZGWh43IuLtwIvAGuA/Av00A964Y8BKoNbSPtjSVm/pO9im72Tt\n422SJEma4LyusZsoM/8KuDIifhn4PWAXzXA3rgYcoRngai1tb9AMZ+36Drf0pejTOsZQyxhTajQa\nja6urgt6XZIkSfNkRkLLBQe7iPh3wMcz87s0Q9oosB/YUZyeXQqsp7mi9zxwC/BC8XVvZg5GxFBE\nXAEcAG4CPlGM86mIeBi4HOjKzMMR8fXiez8P3AzsPZ/j7Orq4uDBwQt9eeoAAwM1567EnL/ycu7K\nzfkrt4GB2tSdzsN0Vux+F/hcRAwBx2nuiv1BRDwG7KOZOO/PzOGI2Ak8GRF7aa64fbAY4x6aO10X\nAXsycz9A0e8bxRjbi747ijHuBF5vGUOSJEktuhqNxnwfw2xp+MmlnPzUWW7OX3k5d+Xm/JXbwEBt\nRk7FWqBYkiSpIgx2kiRJFWGwkyRJqgiDnSRJUkUY7CRJkirCYCdJklQRBjtJkjpM7+5drNqyibWX\nrWLVlk307t4134ekkpjWLcUkSdLs6N29i/677zj9uPul79B/9x3UgaGt2+bvwFQKrthJktRBlj36\ncPv2Tz8yx0eiMjLYSZLUQRa/8vIFtUutDHaSJHWQ0SvXX1C71MpgJ0lSBzn+sY+3b//ofXN8JCoj\ng50kSR1kaOs26o8/wciGq2h0dzOy4Srqjz/hxgmdF3fFSpLUYYa2bjPIaVpcsZMkSaoIg50kSVJF\nGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIq\nwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJU\nEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEd3n0yki\nNgK/m5nviYi/BTwGjABDwN/LzIMRcSdwF3AK2JGZT0VEH/BFYB1QB27PzEMRcS3waNH3ucx8qPh7\nHgRuLdrvzcz9EbEG+DLQB3wf+FBmnpyp/wGSJElVMeWKXUT8GvBZoLdoehTYnpk/C+wG/lFEXAp8\nBNgEvBf4ZEQsAT4MfDszNwNfAB4oxtgJ3JaZ1wMbI+LqiHgXsDkzNwIfAD5T9H0Q+FJmbgG+Bdxz\nsS9akiSpis7nVOx3ga0tj38hM/9T8edu4CRwDbAvM0cysw68ClwNXAc8U/R9GrghImpAT2YeKNqf\nBW4s+u4ByMzXgMURsbbdGBf6IiVJkhaCKYNdZu6medp1/PEPACLiZ4DtwO8B/cDRlm87BqwEai3t\ngy1t9Za+g236TtY+3iZJkqQJzusau4ki4heA3wBuKa6Zq9MMd+NqwBGaAa7W0vYGzXDWru9wS1+K\nPq1jDLWMcV4GBmpTd1JHcu7KzfkrL+eu3Jw/XXCwi4hfpLlJ4m9n5njI+nPgdyKiB1gKrAdeBJ4H\nbgFeKL7uzczBiBiKiCuAA8BNwCeAUeBTEfEwcDnQlZmHI+Lrxfd+HrgZ2Hu+x3rw4OCFvjx1gIGB\nmnNXYs5feTl35eb8ldtMhfILCnYRsQj4NPA9YHdENICvZuZvRcRjwD6gC7g/M4cjYifwZETspbni\n9sFiqHto7nRdBOzJzP3F+HuBbxRjbC/67ijGuBN4vWUMSZIktehqNBrzfQyzpeEnl3LyU2e5OX/l\n5dyVm/NXbgMDta6ZGMcCxZIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIk\nVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIk\nqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIk\nSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMk\nSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRXRfT6dImIj8LuZ\n+Z6WtkeAlzPz94vHdwJ3AaeAHZn5VET0AV8E1gF14PbMPBQR1wKPFn2fy8yHijEeBG4t2u/NzP0R\nsQb4MtAHfB/4UGaenIHXLkmSVClTrthFxK8BnwV6i8drI+LfA+9r6XMp8BFgE/Be4JMRsQT4MPDt\nzNwMfAF4oPiWncBtmXk9sDEiro6IdwGbM3Mj8AHgM0XfB4EvZeYW4FvAPRf5miVJkirpfE7FfhfY\n2vJ4BfBPaAa1cdcA+zJzJDPrwKvA1cB1wDNFn6eBGyKiBvRk5oGi/VngxqLvHoDMfA1YHBFr241x\nIS9QkiRpoZgy2GXmbmCk5fGBzNwPdLV06weOtjw+BqwEai3tgy1t9Za+g236TtY+3iZJkqQJzusa\nu/NQpxnuxtWAI0V7raXtDZrhrF3f4Za+FH1axxhqGUOSJEkTXEiw6zrHc38O/E5E9ABLgfXAi8Dz\nwC3AC8XXvZk5GBFDEXEFcAC4CfgEMAp8KiIeBi4HujLzcER8vfjezwM3A3vP94AHBmpTd1JHcu7K\nzfkrL+eu3Jw/XUiwa0z2ODN/EBGPAftoBsD7M3M4InYCT0bEXporbh8svuUemjtdFwF7ilO7FP2+\nUYyxvei7oxjjTuD1ljGmdPDg4AW8PHWKgYGac1dizl95OXfl5vyV20yF8q5GY2Jeq4yGP+Dl5C+n\ncnP+ysu5Kzfnr9wGBmrnOjN63ixQLEmSVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmq\nCIOdJElSRRjsJEmSKsJgJ0mSVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmqCIOdJElS\nRRjsJEmSKsJgJ0mSVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmqCIOdJElSRRjsJEmS\nKsJgJ0mSVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmqCIOdJElSRRjsJEmSKsJgJ0mS\nVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmqCIOdJElSRRjsJEmSKsJgJ0mSVBEGO0mS\npIroPp9OEbER+N3MfE9E/ATwOWAMeDEztxd97gTuAk4BOzLzqYjoA74IrAPqwO2ZeSgirgUeLfo+\nl5kPFWM8CNxatN+bmfsjYg3wZaAP+D7wocw8OTMvX5IkqTqmXLGLiF8DPgv0Fk2PAPdn5hZgUUS8\nPyIuBT4CbALeC3wyIpYAHwa+nZmbgS8ADxRj7ARuy8zrgY0RcXVEvAvYnJkbgQ8Anyn6Pgh8qfj7\nvgXcc9GvWpIkqYLO51Tsd4GtLY9/OjP3Fn9+GrgRuAbYl5kjmVkHXgWuBq4Dnmnpe0NE1ICezDxQ\ntD9bjHEdsAcgM18DFkfE2nZjXOiLlCRJWgimDHaZuRsYaWnqavnzINAP1ICjLe3HgJUT2gdb2uoT\nxpjYd7L28TZJkiRNcF7X2E0w1vLnGvAGzaDWP6H9SNFem9B3cJK+wy19Kfq0jjHUMsZ5GRioTd1J\nHcm5Kzfnr7ycu3Jz/jSdYPcXEbE5M78G3Ax8BdgP7IiIHmApsB54EXgeuAV4ofi6NzMHI2IoIq4A\nDgA3AZ8ARoFPRcTDwOVAV2YejoivF9/7+eLv28t5OnhwcBovT/NtYKDm3JWY81dezl25OX/lNlOh\nfDrB7leBzxabI14CdmVmIyIeA/bRPFV7f2YOR8RO4MmI2Etzxe2DxRj30NzpugjYk5n7AYp+3yjG\n2F703VGMcSfwessYkiRJatHVaDTm+xhmS8NPLuXkp85yc/7Ky7krN+ev3AYGal1T95qaBYolSZIq\nwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJU\nEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZJU\nCb27d7FqyybWXraKVVs20bt713wf0pzrnu8DkCRJuli9u3fRf/cdpx93v/Qd+u++gzowtHXb/B3Y\nHHPFTpIkld6yRx9u3/7pR+b4SOaXwU6SJJXe4ldevqD2qjLYSZKk0hu9cv0FtVeVwU6S5ogXdkuz\n5/jHPt6+/aP3zfGRzC83T0jSHPDCbml2DW3dRp3mNXWLX3mZ0SvXc/yj9y2495fBTpLmwLku7F5o\n//BIs2Vo67YF/37yVKwkzQEv7JY0Fwx2kjQHvLBb0lww2EnSHPDCbklzwWAnSXNgaOs26o8/wciG\nq2h0dzOy4Srqjz+x4K8HkjSz3DwhSXPEC7slzTZX7CRJkirCYCdJklQRBjtJkqSKMNhJkiRVhMFO\nkiSpIgx2kiRJFWGwkyRJqgiDnSRJUkUY7CRJkirCYCdJklQRBjtJkqSKmNa9YiOiB/g3wDuBo8D2\n4qnPAWPAi5m5veh7J3AXcArYkZlPRUQf8EVgHVAHbs/MQxFxLfBo0fe5zHyoGONB4Nai/d7M3D+d\n45YkSaqy6a7Y3QkMZuYm4CPAZ4BHgPszcwuwKCLeHxGXFs9vAt4LfDIilgAfBr6dmZuBLwAPFOPu\nBG7LzOuBjRFxdUS8C9icmRuBDxR/lyRJkiaYbrDbADwNkJmvAj8FvDsz9xbPPw3cCFwD7MvMkcys\nA68CVwPXAc+09L0hImpAT2YeKNqfLca4DthT/F2vAYsjYs00j1uSJKmyphvsvgX8HEBx+vRtE8Ya\nBPqBGs1TteOOASsntA+2tNUnjDGxb+sYkiqsd/cuVm3ZxNrLVrFqyyZ6d++a70OSpI43rWvsgCeA\nn4qIrwFfB74JXNbyfA14g2ZQ65/QfqRor03oOzhJ3+GWvq39pzQwUJu6kzqSc1duFz1/f/iHcPcd\npx92v/Qd+u++A/qXwm23XeTR6Vx875Wb86fpBrv/HvjTzLwvIn4a+HHgryNiS2Z+FbgZ+AqwH9hR\nbLZYCqwHXgSeB24BXii+7s3MwYgYiogrgAPATcAngFHgUxHxMHA50JWZh8/nIA8eHJzmy9N8Ghio\nOXclNhPzt+qh32n7y2nkt3dw5IZbL2psTc73Xrk5f+U2U6F8usHuVeC3I+I3aa6q/TLNlbTPFpsj\nXgJ2ZWYjIh4D9gFdNDdXDEfETuDJiNgLDAEfLMa9B/gyzdO6e8Z3vxb9vlGMMb4DV1JFLX7l5Qtq\nlyQ1dTUajfk+htnS8JNLOfmps9xmZMVuyya6X/rOWe0jG67iyH94/qLG1uR875Wb81duAwO1rpkY\nxwLFkjrO8Y99vH37R++b4yORpHIx2EnqOENbt1F//AlGNlxFo7ubkQ1XUX/8CYa2bpvvQ5Okjjbd\na+wkaVYNbd1mkJOkC+SKnSRJUkUY7CRJkirCYCdJklQRBjtJkqSKMNhJkiRVhMFOEr27d7FqyybW\nXraKVVs20bt713wfkiRpGix3Ii1wvbt30X/3Hacfd7/0HfrvvoM6WG5EkkrGFTtpgVv26MPt2z/9\nyBwfiSTpYhnsVFqePpwZi195+YLaJUmdy2CnUho/fdj90nfoGh09ffrQcHfhRq9cf0HtkqTOZbBT\nKXn6cOYc/9jH27d/9L45PhJJ0sUy2KmUPH04c4a2bqP++BOMbLiKRnc3Ixuuov74E26ckKQScles\nSmn0yvV0v/Sdtu26cENbtxnkJKkCXLFTKXn6UJKksxnsVEqePpQk6WyeilVpefpQkqQzuWInSZJU\nEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZI6\nXO/uXazasom1l61i1ZZN9O7eNd+HpA7lLcUkSepgvbt30X/3Hacfd7/0HfrvvoM6eFtFncUVuyn4\nKUmSNJ+WPfpw+/ZPPzLHR6IycMXuHPyUJEmab4tfefmC2rWwuWJ3Dn5KkiTNt9Er119QuxY2g905\n+ClJkjTfjn/s4+3bP3rfHB+JysBgdw5+SpIkzbehrduoP/4EIxuuotHdzciGq6g//oSXBKktr7E7\nh+Mf+/gZ19idbvdTkiRpDg1t3WaQ03lxxe4c/JQkSZLKxBW7KfgpSZIklYUrdpIkSRVhsJMkSaoI\ng50kSVJFTOsau4joBp4E3gGMAHcCo8DngDHgxczcXvS9E7gLOAXsyMynIqIP+CKwDqgDt2fmoYi4\nFni06PtcZj5UjPEgcGvRfm9m7p/Wq5UkSaqw6a7Y3QIszsz/Afht4J8CjwD3Z+YWYFFEvD8iLgU+\nAmwC3gt8MiKWAB8Gvp2Zm4EvAA8U4+4EbsvM64GNEXF1RLwL2JyZG4EPAJ+Z5jFLkiRV2nSD3StA\nd0R0AStprqS9OzP3Fs8/DdwIXAPsy8yRzKwDrwJXA9cBz7T0vSEiakBPZh4o2p8txrgO2AOQma8B\niyNizTSPW5IkqbKmW+7kGHAF8DKwBngfcH3L84NAP1ADjk74vpUT2gdb2uoTxngncAI41GaM1jZJ\nkqQFb7rB7l7gmcz8zYh4G/AfgJ6W52vAGzSDWv+E9iNFe21C38FJ+g639G3tP6WBgdrUndSRnLty\nc/7Ky7krN+dP0w12h2mefoVmyOoG/jIitmTmV4Gbga8A+4EdEdEDLAXWAy8Cz9O8Tu+F4uvezByM\niKGIuAI4ANwEfILmpoxPRcTDwOVAV2YePp+DPHhwcJovT/NpYKDm3JWY81dezl25OX/lNlOhfLrB\n7lHgiYj4GrAE+HXgm8AfFJsjXgJ2ZWYjIh4D9gFdNDdXDEfETuDJiNgLDAEfLMa9B/gyzWv/9ozv\nfi36faMYY/s0j1mSJKnSuhqNxnwfw2xp+MmlnPzUWW7OX3k5d+Xm/JXbwECtaybGsUCxJElSRRjs\nJEmSKsJgJ0mSVBEGO0mSpIow2EmSFqTe3btYtWUTay9bxaotm+jdvWu+D0m6aNMtdyJJUmn17t5F\n/913nH7c/dJ36L/7DurA0NZt83dg0kVyxU6StOAse/Th9u2ffmSOj0SaWQY7SdKCs/iVly+oXSoL\ng50kacEZvXL9BbVLZWGwkyQtOMc/9vH27R+9b46PRJpZBjtJ0oIztHUb9cefYGTDVTS6uxnZcBX1\nx59w44RKz12xkqQFaWjrNoOcKscVO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbCTJEmqCIOdJElS\nRRjsJEmSKsJgJ0mSVBEGO0mSpIow2EmSJFWEwU6SJKkiDHaSJEkVYbDTOfXu3sWqLZtYe9kqVm3Z\nRO/uXfN9SNKs8eddUtl1z/cBqHP17t5F/913nH7c/dJ36L/7DurA0NZt83dg0izw511SFbhip0kt\ne/Th9u2ffmSOj0Saff68S6oCg50mtfiVly+oXSozf94lVYHBTpMavXL9BbVLZebPu6QqMNhpUsc/\n9vH27R+9b46PRJp9/rxLqgKDnSY1tHUb9cefYGTDVTS6uxnZcBX1x5/wQnJVkj/vkqqgq9FozPcx\nzJbGwYOD830MmoaBgRrOXXk5f+Xl3JWb81duAwO1rpkYxxU7SZKkijDYSZIkVYTBTrPOav6SJM0N\n7zyhWWU1f0mS5o4rdppVVvOXJGnuGOw0q6zmL0nS3DHYaVZZzV+SpLljsNOsspq/JuOmGkmaeW6e\n0Kwa2rqNOs1r6ha/8jKjV67n+Efvc+PEAuemGkmaHQY7zbqhrdv8x1pnONemGn9WJGn6phXsIuJ2\n4JeABrAUuBq4HngUGANezMztRd87gbuAU8COzHwqIvqALwLrgDpwe2YeiohrizFOAc9l5kPFGA8C\ntxbt92bm/um9XEmdwE01kjQ7pnWNXWY+mZnvycyfBb4J/APgQeD+zNwCLIqI90fEpcBHgE3Ae4FP\nRsQS4MPAtzNzM/AF4IFi6J3AbZl5PbAxIq6OiHcBmzNzI/AB4DPTfrWSOoKbaiRpdlzU5omI+O+A\nDZn5B8BPZ+be4qmngRuBa4B9mTmSmXXgVZqre9cBz7T0vSEiakBPZh4o2p8txrgO2AOQma8BiyNi\nzcUct6T55aYaSZodF7sr9jeAT7RpHwT6gRpwtKX9GLByQvtgS1t9whgT+7aOIamkhrZuo/74E4xs\nuIpGdzcjG66i/vgTXl8nSRdp2psnImIlcGVmfq1oGmt5uga8QTOo9U9oP1K01yb0HZyk73BL39b+\nUxoYqE3dSR3JuSu385q/uz7U/I/mL6L+c/fWHPG9V27Ony5mV+xm4E9bHv9lRGwugt7NwFeA/cCO\niOihucliPfAi8DxwC/BC8XVvZg5GxFBEXAEcAG6iuRo4CnwqIh4GLge6MvPw+RzgwYODF/HyNF8G\nBmrOXYk5f+Xl3JWb81duMxXKL+ZUbAD/peXxrwIPRcTXgSXArsz8AfAYsA/4E5qbK4ZpbpK4KiL2\nAr8C/FYxxj3Al4E/A/4iM/dn5l8Ae4FvAH8EbL+IYy4FC7dKkqTp6Go0GvN9DLOlUcZPLhMLt45b\nSNcf+amz3Jy/8nLuys35K7eBgVrXTIzjLcU6zLkKt0qSJJ2Lwa7DWLhVkiRNl8Guw1i4VZIkTZfB\nrsNYuFWSJE2Xwa7DWLhVkiRN18XUsdMsGdq6zSAnSZIumCt2kiRJFeGKnSRJ0nkaHRvjSH2IQ/WT\nHP3RMBvesZoVS5fM92GdZrCTJEkqDJ0a5XD9JIeOnuT14uuhlq9HBodovbfD/3TdFfzd666YvwOe\nwGAnSZIWhEajwY9OjpwV1sZD3OH6SQaPn2r7vV1dcMmKXn7ibStZ29/HmpXN/65Zv26OX8W5Gewk\nSVIljDUaHD02XAS1ExyuD50V3oaGR9t+b/fiRazp7+XydStYMx7c+vtYW3y9pNZL9+LO35pgsJMk\nSaVwamSMI4OTnyY9XB9idKzR9nuX9nYzsHLp6aC2ZmUfq/t7WbOyj7X9fdSW97Coa0Zu1zqvDHaS\nJKkjnBgaOesUaetqW/3YMO1jG6xc3sOPv6XG6v6+N0+Vtnxd1rcwIs/CeJWSJGleNRoNBo+fejOo\nnV5lezPA/ejkSNvvXbyoi1W1Xq68/JIzA1ux2ra6v5cl3Yvn+BV1JoOdJEm6aKNjYxwZHDp9XdvE\nU6WH6ycZHhlr+709Sxaxpr+PK97a33a17ZIVvSxaVP7TpHPBYCdJkqY0fGq0GdImnio9XQZkmLFG\n+xOlK5Yu4bI1y98MbMW1beOPVyxdQlcFrm/rBAY7SZIWuEajwfGhkdNB7fUzNiQ0/1yfogzIO9/W\nX5wWnbji1ktfj3Fjrvh/WpKkijtdBqTltOjEU6UnpygD8raBFaevaWsNbqtKUgZkoTDYSZJUciOj\nY/z1oR/xyveOtN1RenjwJCOjk5UBWXxGCZDW0FalMiALhcFOkqQOd3J45KzSH62Pj56jDEj/8h4u\nX1dru9q2kMqALBTOpiRJ86jRaDB44tQZGxFOfy3+fD5lQN52aY3lPYstA7LAGewkSZpFo2NjvDE4\n3H5HadE2fOrCyoCsLm511VoGZGCgxsGDg3P50tSBDHaSJF2E8TIgh+tDHKoXhXdbwtuRwaFzlwFZ\nvfz07a3WTrjOzTIgulAGO0mSJnFGGZBJbnU1aRkQ4JJaL+98a/9Z17VZBkSzxZ8oSdKCNdZoUP/R\n8Dk3JkxeBqSL1f19bcuArF7Zx2rLgGgeGOwkSZU1MjrG4cGhSTcmHK5PXgakb3wjQkvpj9bH/ZYB\nUQcy2EmSSmtiGZBDxXVu421vDA5NXgZk2RIuX7eizSnS5saEZX1L5vS1SDPBYCdJ6kjjZUDGb2nV\n7jTpZGVAFnU1y4D85OWXnHFN25v3Ku2jZ4llQFQ9BjtJ0rwYG2vwxrGh5i7SCy0D0r2I1f19vOOy\n/ranSi+p9bB4kde3aeEx2EmSZsWpkdHmqdEiqL1+9M0byh+qN8uAjI61P1G6vK+bt6xa1n436co+\napYBkdoy2EmSpuX4yVNnBLeJp0rrPxpu+31dwMoVPbzjstoZq22rWwLc0l7/eZKmw3eOJOksp8uA\nTDxF2nKa9MRQ+zIgixd1saa/j7e+/ZK2u0pX1fpY0u1pUmk2GOwkaQEaGR3jyOCZq20/Gh7lv/5g\n8PRdFEZG21/f1tuzuBnSfqxd0d0+Vq6wDIg0Xwx2klRBQ8Ojp0+L3nEXLO0/zrL+EyztP87S/uP0\nLT9J1ySLZrVlS/ixgeVnrbaNnypd3tft9W1ShzLYSVLJNBoNjp04Vay0DbXdUXrsxJu3ufpvb3zz\ne8fGujjiCsQlAAASIUlEQVQ52Mfh76/hRH0p9/zK4tPh7SffsYaukVHLgEglZrCTpA4zXgZkYmAb\nX4E7XB9i6FT769vGy4D8+Fve3Jjw4G9cwon6Mo7XlzJ0rI9G482lup///ODpPw8M1Dh4cLDdsJJK\nwmAnSXPs1Mgoh+tDb+4gnbDaNlUZkEtXLZ3kpvJ91JadXQbkl1+qzcXLktQBDHaSNMOOnxw5x2rb\nSY5OUgYEijIgb6lNGtwsAyLpXPwNIUkXoFGUAWmt13a4uM5t/A4KJ4ba3+Zq8aIuVvf3st4yIJJm\nicFOklqMjI7xxuCZQW3iTeanLgOykjX9fawu7k26tr956nTl8h4WLXI3qaTZY7CTtKAMDY+eLrDb\n7lTpG8eGaLS/vI3asiW8bWD5Gfckbf3aqWVAfvhDN0RIC8W0g11E/Drwd4ElwL8CvgZ8DhgDXszM\n7UW/O4G7gFPAjsx8KiL6gC8C64A6cHtmHoqIa4FHi77PZeZDxRgPArcW7fdm5v7pHrek6mo0Gvzo\n5EgzqLWEtsP1N4NbaxmQVl1dsKrWy99428q2p0lX9/fRaxkQSR1uWsEuIrYAmzLzZyJiOfCrwCPA\n/Zm5NyJ2RsT7gT8DPgK8G1gG7IuIPcCHgW9n5kMR8QvAA8DHgJ3A1sw8EBFPRcTVwCJgc2ZujIjL\ngf8DuOaiXrWkUhovA9LcUXri9KnR1pW3ycqALBkvA3LpitNBbU1/H2uLEHdJrZfuxV7fJqncprti\ndxPwYkT8MVAD/iHwK5m5t3j+aeB/pLl6ty8zR4B6RLwKXA1cB3yqpe8/joga0JOZB4r2Z4EbgSFg\nD0BmvhYRiyNiTWYemuaxS+pQp0bGODzYvgTI60fPXQZkWW8361Ytba60jZ8ibVl5629TBkSSqma6\nwW4t8Hbg54B3Av8nzZW1cYNAP83Qd7Sl/RiwckL7YEtbfcIY7wROAIfajGGwk0rmxNDIGdezTbzO\n7ZxlQJb3nFF0d+KpUsuASNL0g90h4KViJe6ViDgJ/FjL8zXgDZpBrX9C+5GivTah7+AkfYdb+rb2\nl9RBGo0G9eOnOHLiCN/93uEzV92K4Hb8HGVAVtWKMiAtwW316XuU9rKk2+vbJGkq0w12+4B/APxe\nRLwVWA78aURsycyvAjcDXwH2AzsiogdYCqwHXgSeB24BXii+7s3MwYgYiogrgAM0T/d+AhgFPhUR\nDwOXA12Zefh8DnJgwGrrZeXcdZ7R0TFeP3qSHx45zsEjJzh45Dg/PHKieNxsGx5pXwakr2cxA6uW\n8VOrlrJu1TIGiq/rVi1j3eqlXFLrY7FlQDqC771yc/40rWBX7Gy9PiL+HOiiuRniAPAHEbEEeAnY\nlZmNiHiMZhDsorm5YjgidgJPRsRemtfQfbAY+h7gyzRP6+4Z3/1a9PtGMcb28z1O73lYTt6vcn4M\nnRo9awfpxNtcTVYGZMXSJVy2tlkG5Mfe0s+yJYvOuwzI2PAIhw8dm8VXpvPle6/cnL9ym6lQ3tWY\n7Dd1+TX8AS8nfznNvNYyIJPVb5uqDMhk17atrvXR2/PmaVLnr7ycu3Jz/sptYKA2I6ctvNpYqoCx\nRoOjx4aLoNamDEj9JEPD7cuAdC9exJr+Xt5+6YozwptlQCSpfAx2UgmcqwzIofpJDtcnLwOytLeb\ngZVLTwc1y4BIUnUZ7KQO0K4MyOGWU6VHj02vDMjq/j6W9fk2l6SFwt/40iwbLwNyemNCm+vcLAMi\nSZoJBjvpIo2OjXFkcGiSjQlDHK6f5NQkZUBGhhfz9rf28ROn70965iaFS1b0ssgyIJKk82Swk6Yw\ndGr0jNOircHtcP0kRwaHGZtkd/mKpUt469rl/NneFZyoL+VEfRknBpdyvL6ME/VlnDq5hB/+0FIf\nkqSZYbDTgtZaBmSy+m2DxycvA3LJil7e+bb+06U/zrjOrf/NMiDr/qFFQ2faunWT/z/94Q/bl3yY\nzvdIUpkY7FRpp8uATHJv0tfPowzI5essAyJJKgeDnUptZHTsjNOkh+tnXut2ePAkI6MXVgZkdX8v\na/v7qC3vYZFlQCRJJWKwU0c7MTTSDG6TXON29Ngwk907ZeXyHt5+ae2s06Pjf7YMiCSpavyXTfOm\n0WgweOLUWUV3B0+O8P8dPMah+kl+dPLcZUCuvPySM69tswyIJGkBM9hp1oyOjfHG4PBZq22tK3DD\nk5QB6VmyiDX9fVzx1vYbE8pWBsQL8yVpdrk5qslgp2kbPjV6+pZWb664DZ1+fGRw6JxlQC5bs/ys\nwLZ2ZR8/ecUaho4PeZsrSZIukMFObTUaDY4Xt7l6c2PCmadM65OVAQEuqfXyzrf2n10CpCjC29cz\n+Y/eyhW9HDwx+S20JJjeJ/CF9Kld0sJksFug2pYBmRDcTk5aBqSL1f19vG1gxelr2lqD2yrLgEiS\nNC8MdhV1ugxIvf2trs5dBmTx6RIgq9sEt37LgEiS1JEMdiV1cnjkrEK751sGpH95D5evq52xg7T1\nGrdlfUvm9LVIkqSZYbDrQG3LgEwIbpOVAVnU1SwD8pOXX3J6ha21AO/qWi89SywDIklSFRns5sEZ\nZUDa3eqqfpLhU5OUAelexJqVfVxxWZuNCf19XFLrYfEir2+TJC0sbo5qMtjNglMjo2dc2/b6hAK8\n5yoDsryvm7esWtZ+N+nKPmpLl1gGRJIktWWwm4bjJ081w9okN5afqgzIFW998zZXrRsTVvf3sbTX\nKZEkSdNjiphgvHJ1V9cY6975A5avOsay/hMsrR3np69t3ubqxNA5yoDUijIgbVbbVlsGZFZZdVy6\ncGe/b9587PtGKh+D3SQuu/L7vPvWb57R9vrRxWeENcuASJKkTmKwm8QP/stb+NYz7+LUySUcry/j\nxOAyvv/ayfk+LElSiXlmQbPNYDeJ0VPd/Nf//PYJrQY7SZLUuQx2kiRp3rmaOTO8kl+SJKkiDHaS\nJEkV4anYCVzuLS/nTrpwre+bgYEaBw/6PpLKzBU7SZKkinDFTpKkOeKZBc02g50kSdIF6OQdvAY7\nSZI07+Y7EFWF19hJkiRVhMFOkiSpIgx2kiRJFWGwkyRJqgiDnSRJUkW4K1aSJOkCdPIOXlfsJEmS\nKsJgJ0mSVBEGO0mSpIqY9jV2EfFN4Gjx8P8F/inwOWAMeDEztxf97gTuAk4BOzLzqYjoA74IrAPq\nwO2ZeSgirgUeLfo+l5kPFWM8CNxatN+bmfune9ySJElVNa0Vu4joBcjMny3++2XgEeD+zNwCLIqI\n90fEpcBHgE3Ae4FPRsQS4MPAtzNzM/AF4IFi6J3AbZl5PbAxIq6OiHcBmzNzI/AB4DPTfrWSJEkV\nNt1TsVcDyyPi2Yj4k4jYCLw7M/cWzz8N3AhcA+zLzJHMrAOvFt97HfBMS98bIqIG9GTmgaL92WKM\n64A9AJn5GrA4ItZM87glSZIqa7rB7jjwzzLzJpqrb18CulqeHwT6gRpvnq4FOAasnNA+2NJWnzDG\nxL6tY0iSJKnFdK+xewX4LkBmvhoRh4B3tzxfA96gGdT6J7QfKdprE/oOTtJ3uKVva/8pDQzUpu6k\njuTclZvzV17OXbk5f5pusLsD+JvA9oh4K81AticitmTmV4Gbga8A+4EdEdEDLAXWAy8CzwO3AC8U\nX/dm5mBEDEXEFcAB4CbgE8Ao8KmIeBi4HOjKzMPnc5AHD3ZuAUFNbmCg5tyVmPNXXs5duTl/5TZT\noXy6we5fA/8mIvbS3AX7S8Ah4A+KzREvAbsysxERjwH7aJ6qvT8zhyNiJ/Bk8f1DwAeLce8Bvkzz\nFPGe8d2vRb9vFGNsn+YxS5IkVVpXo9GY72OYLY25/uSybt3kabsTbj/S6cc3zk+d5eb8lZdzV27O\nX7kNDNS6pu41NQsUS5IkVcS0CxRLkqqvLCv9kppcsZMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEW6e\nmEGdfiFxpx+fyuvsC+zffOzPnSTNHVfsJEmSKsIVO0nSpFxxlcrFYHcO1m+SJEll4qlYSZKkijDY\nSZIkVYTBTpIkqSK8xk7SRWu95nRgoMbBg16DKml+LPTr412xkyRJqgiDnSRJUkV4KvYcFsKSrSRJ\nc2mhnyqdba7YSZIkVYTBTpIkqSIMdpIkSRXhNXaSJKkyFvp1eq7YSZIkVYTBTpIkqSI8FStJkubM\nQj9VOttcsZMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVh\nsJMkSaoIg50kSVJFGOwkSZIqwmAnSZJUEQY7SZKkijDYSZIkVYTBTpIkqSIMdpIkSRVhsJMkSaoI\ng50kSVJFdF/MN0fEOuAF4O8Ao8DngDHgxczcXvS5E7gLOAXsyMynIqIP+CKwDqgDt2fmoYi4Fni0\n6PtcZj5UjPEgcGvRfm9m7r+Y45YkSaqiaa/YRUQ38L8Cx4umR4D7M3MLsCgi3h8RlwIfATYB7wU+\nGRFLgA8D387MzcAXgAeKMXYCt2Xm9cDGiLg6It4FbM7MjcAHgM9M95glSZKq7GJOxf5zmkHs+0AX\n8O7M3Fs89zRwI3ANsC8zRzKzDrwKXA1cBzzT0veGiKgBPZl5oGh/thjjOmAPQGa+BiyOiDUXcdyS\nJEmVNK1gFxG/BPwwM5+jGeomjjUI9AM14GhL+zFg5YT2wZa2+oQxJvZtHUOSJEktpnuN3YeAsYi4\nkeYK3OeBgZbna8AbNINa/4T2I0V7bULfwUn6Drf0be0/la6BgdrUvdSRnLtyc/7Ky7krN+dP01qx\ny8wtmfmezHwP8C3gfwGejojNRZebgb3AfuC6iOiJiJXAeuBF4HnglqLvLcDezBwEhiLiiojoAm4q\nxngeuCkiuiLi7UBXZh6e1quVJEmqsIvaFTvBrwKfLTZHvATsysxGRDwG7KN5yvb+zByOiJ3AkxGx\nFxgCPliMcQ/wZZqBc8/47tei3zeKMbbP4DFLkiRVRlej0ZjvY5AkSdIMsECxJElSRRjsJEmSKsJg\nJ0mSVBEzuXli1hV3u3gCeAfQA+wA/jMXeSuzOX4ZC1K7ucvM/6t47hHg5cz8/eKxc9dhJnnv/RXw\nL4ARmpug/l5mHnT+Osskc/dd4PeLLq8Cv5KZY85d55nid+cHgb+fmT9TPHb+Oswk77/XgP8beKXo\ntjMz/2im5q9sK3a/CLxe3IrsvcC/ZGZuZabZ1zp3NwP/MiLWRMS/B9433sm561jt3nuPAtsz82eB\n3cA/cv46Uru52wH8enH7xi7gfc5dxzrrdydAcbvNO8Y7OX8dq938vRt4ODN/tvjvj2Zy/soW7P53\n3nxRi2muFFzMrcz+zlwduM6Yu0U0P5GsAP4JzR/Wcc5dZ5r43jsF/EJm/qeirRs4ifPXic6au8z8\n+cz8ekT0AG+heXcf564znfW7MyJWA78DfLSln/PXmdr92/fTwM9FxFcj4rMRsYIZnL9SnYrNzOMA\nxX1l/wj4TZr3rB13obcya73ThWZRu7nLzO8B34uIW1q69uPcdZxJ5u+HRdvP0KwvOb4i5Px1kEl+\nb1IUfP8Tmnfy+Y80i8U7dx2mzfw9APxr4D6al0CM83dnB2ozf/8Y6AX+IDP/MiJ+g+YCx7eYofkr\n24odEXE58BXgycz8Q5rX1o2bzq3MNEcmzN3/Nkk3565DtZu/iPgF4F8BtxTXfTh/Hajd3GXmX2Xm\nlcDjwO/R/MfDuetArfNH8/rIvwHsBP4tsKG4Ttn3Xodqk1v+ODP/snj6j4G/xQy+/0q1Ylecg36W\n5nU9/0/R/JcRsTkzv0bz/PVXaN7KbEdxmmEpZ9/K7IXi6140JyaZu3b+HPgd566ztJu/iPhFmhf6\n/u3MHP9l4/x1mEnm7t8BH8/M79JcBRjF35sdaZLfnX+zeO7HgX+bmfcV/XzvdZhJ5u/ZiPj7mfkC\ncAPwTWbw/VeqO09ExKPA/wy8TPOC3wbNawz+BTB+K7M7i1uZ/TJwd9FvR2b+cUQspfmJ5zKKW5mN\nn07S7Jpk7m7OzKGIeBD465Zdsc5dh2kzf4uB/wb4Hs1Pmg3gq5n5W85fZ5nkvfebwD+jORfHae6K\n/YFz13mm+N05HuzGd8U6fx1mivffMPDXwF2ZeWym5q9UwU6SJEmTK901dpIkSWrPYCdJklQRBjtJ\nkqSKMNhJkiRVhMFOkiSpIgx2kiRJFWGwkyRJqgiDnSRJUkX8//Fc+U9EWZJdAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xb70a518>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted: -1.0    Actual: -1 Raw:  -13.514952955\n",
      "Predicted: 1.0    Actual: 1 Raw:  1018.84606793\n",
      "Predicted: -1.0    Actual: -1 Raw:  -291.589932075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -228.969817235\n",
      "Predicted: 1.0    Actual: 1 Raw:  492.230339365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -264.969441395\n",
      "Predicted: 1.0    Actual: 1 Raw:  644.280673445\n",
      "Predicted: 1.0    Actual: 1 Raw:  555.660830045\n",
      "Predicted: 1.0    Actual: 1 Raw:  1069.40603885\n",
      "Predicted: -1.0    Actual: -1 Raw:  -108.832919395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -15.365653995\n",
      "Predicted: 1.0    Actual: 1 Raw:  1013.81181141\n",
      "Predicted: -1.0    Actual: -1 Raw:  -451.502031995\n",
      "Predicted: 1.0    Actual: 1 Raw:  398.852082845\n",
      "Predicted: 1.0    Actual: 1 Raw:  1076.51815593\n",
      "Predicted: -1.0    Actual: -1 Raw:  -109.401760555\n",
      "Predicted: -1.0    Actual: -1 Raw:  -121.769735275\n",
      "Predicted: 1.0    Actual: 1 Raw:  476.282427365\n",
      "Predicted: 1.0    Actual: 1 Raw:  1190.48265705\n",
      "Predicted: -1.0    Actual: -1 Raw:  -11.124161075\n",
      "Predicted: -1.0    Actual: -1 Raw:  -294.199087995\n",
      "Predicted: -1.0    Actual: -1 Raw:  -521.690914915\n",
      "Predicted: 1.0    Actual: 1 Raw:  512.523586205\n",
      "Predicted: -1.0    Actual: -1 Raw:  -394.235131915\n",
      "Predicted: 1.0    Actual: 1 Raw:  2303.29995161\n",
      "Predicted: 1.0    Actual: 1 Raw:  657.573993365\n",
      "Predicted: -1.0    Actual: -1 Raw:  -765.487626395\n",
      "Predicted: -1.0    Actual: -1 Raw:  -469.645563755\n",
      "Predicted: 1.0    Actual: 1 Raw:  1033.29468241\n",
      "Predicted: -1.0    Actual: -1 Raw:  -380.209317595\n",
      "Predicted: -1.0    Actual: -1 Raw:  -768.714296715\n",
      "Predicted: -1.0    Actual: -1 Raw:  -551.449067035\n",
      "=== Loop  9  ===\n",
      "Weights: [ -9.99989560e-01   3.68100000e-03  -5.00000000e-09]\n",
      "Accuracy: 100.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnYAAAHhCAYAAADj3/OfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xbb841d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "### Let us now simulate the perceptron\n",
    "\n",
    "## We are going to run the Perceptron in two Dimensions: Price and Footage\n",
    "##  f((Footage, Price, -1)) = w1*Footage + w2*Price - w3; where w3 is Theta\n",
    "\n",
    "## let's select learning rate\n",
    "\n",
    "Rate = 0    ### pick the appropriate rate. Note, it can be very small, because our numbers are large\n",
    "\n",
    "\n",
    "## Starting vector\n",
    "\n",
    "w = np.array([0,0,0])    ### pick the right starting vector. Note: [0,0,0] might not actually work.\n",
    "\n",
    "\n",
    "### Below is a VERY SIMPLE training loop. We simply call trainPerceptron() 10 times in a row\n",
    "### (chaining the w), and compute the accuracy of the perceptron after each step. We also\n",
    "### draw the state of the plane after each iteration\n",
    "\n",
    "for i in range(10):\n",
    "    w = trainPerceptron(simpleData, w, Rate)\n",
    "    accuracy = getPerceptronAccuracy(simpleData,w)\n",
    "    print(\"=== Loop \", i,\" ===\")\n",
    "    print(\"Weights:\",w)\n",
    "    print(\"Accuracy:\", accuracy)\n",
    "    plotW(simpleSlo,simplePaso, w)\n",
    "    \n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [Root]",
   "language": "python",
   "name": "Python [Root]"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}