public-engines/iris-species-engine/notebooks/ash316-kaggle.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "b7dbedec-9483-4b22-484d-b8a8e04c49ae",
    "_uuid": "8807ae46aec34ec427b81344d64a3c0d607b258a"
   },
   "source": [
    "### Hello Kagglers!!\n",
    "\n",
    "This is a very basic tutorial to Machine Learning for complete Beginners using the Iris Dataset. You can learn how to implement a machine learning to a given dataset by following this notebook. I have explained everything related to the implementation in detail . Hope you find it useful.\n",
    "\n",
    "For a more advanced notebook that covers some more detailed concepts, have a look at [this notebook](https://www.kaggle.com/ash316/ml-from-scratch-part-2/notebook)\n",
    "\n",
    "If this notebook to be useful, **Please Upvote!!!**\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "_cell_guid": "c8b7047a-c84c-c0ee-054d-a0c30609cc43",
    "_execution_state": "idle",
    "_uuid": "43047631b7881a23c63a655f5214b2ebaff946fa"
   },
   "outputs": [],
   "source": [
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Using MarvinData utility to download file\n",
    "from marvin_python_toolbox.common.data import MarvinData\n",
    "\n",
    "# getting the initial data set\n",
    "file_path = MarvinData.download_file(url=\"https://s3.amazonaws.com/marvin-engines-data/Iris.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "_cell_guid": "ced2723b-e83e-6aa0-4ffb-9ace2cc4a5e3",
    "_execution_state": "idle",
    "_uuid": "db8aed63638fcf4833c050541cc0fe5a0b756670"
   },
   "outputs": [],
   "source": [
    "iris = pd.read_csv(file_path) #load the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "_cell_guid": "ca50ed92-15c7-f9f6-b371-f18393505167",
    "_execution_state": "idle",
    "_uuid": "9a89db0e5a9d3e5cd7cecf06e16dbf1b6f8d3542"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Id</th>\n",
       "      <th>SepalLengthCm</th>\n",
       "      <th>SepalWidthCm</th>\n",
       "      <th>PetalLengthCm</th>\n",
       "      <th>PetalWidthCm</th>\n",
       "      <th>Species</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\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>2</td>\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",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Id  SepalLengthCm  SepalWidthCm  PetalLengthCm  PetalWidthCm      Species\n",
       "0   1            5.1           3.5            1.4           0.2  Iris-setosa\n",
       "1   2            4.9           3.0            1.4           0.2  Iris-setosa"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris.head(2) #show the first 2 rows from the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "_cell_guid": "4f9370f1-0672-0d8c-4f21-c7eeb694042c",
    "_execution_state": "idle",
    "_uuid": "46f49d63be72b4eec75da299e355d6dbaa19f65b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 150 entries, 0 to 149\n",
      "Data columns (total 6 columns):\n",
      "Id               150 non-null int64\n",
      "SepalLengthCm    150 non-null float64\n",
      "SepalWidthCm     150 non-null float64\n",
      "PetalLengthCm    150 non-null float64\n",
      "PetalWidthCm     150 non-null float64\n",
      "Species          150 non-null object\n",
      "dtypes: float64(4), int64(1), object(1)\n",
      "memory usage: 7.1+ KB\n"
     ]
    }
   ],
   "source": [
    "iris.info()  #checking if there is any inconsistency in the dataset\n",
    "#as we see there are no null values in the dataset, so the data can be processed"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "fe064d83-88de-20ee-9ec0-43e52fc49c03",
    "_uuid": "eaf309bd3956c549ca5c039a6c62151974ca9481"
   },
   "source": [
    "#### Removing the unneeded column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "_cell_guid": "af6dd1be-5c24-27f3-6319-eb6af2c65c27",
    "_execution_state": "idle",
    "_uuid": "c9b2172cc499bda6d56d2199b8d286217abbd677"
   },
   "outputs": [],
   "source": [
    "iris.drop('Id',axis=1,inplace=True) #dropping the Id column as it is unecessary, axis=1 specifies that it should be column wise, inplace =1 means the changes should be reflected into the dataframe"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "a2e19920-d24b-7551-10c4-e1088c8a4324",
    "_uuid": "f00690de3343002575e680a83ae395ef0060fe1f"
   },
   "source": [
    "## Some Exploratory Data Analysis With Iris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "_cell_guid": "09a16bf0-067b-8da0-3eed-2014dc8cfec7",
    "_execution_state": "idle",
    "_uuid": "c9fd2c2b0eb51ada3a4f57eb51023cb080a0d308"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmQAAAGDCAYAAACFuAwbAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nmRIyERERkZgpIRMRERGJ2f8Pz1i8QTDJEy0AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fa1099ac1d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = iris[iris.Species=='Iris-setosa'].plot(kind='scatter',x='SepalLengthCm',y='SepalWidthCm',color='orange', label='Setosa')\n",
    "iris[iris.Species=='Iris-versicolor'].plot(kind='scatter',x='SepalLengthCm',y='SepalWidthCm',color='blue', label='versicolor',ax=fig)\n",
    "iris[iris.Species=='Iris-virginica'].plot(kind='scatter',x='SepalLengthCm',y='SepalWidthCm',color='green', label='virginica', ax=fig)\n",
    "fig.set_xlabel(\"Sepal Length\")\n",
    "fig.set_ylabel(\"Sepal Width\")\n",
    "fig.set_title(\"Sepal Length VS Width\")\n",
    "fig=plt.gcf()\n",
    "fig.set_size_inches(10,6)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "e853b9fa-a1db-cdc8-1f8f-0f5f2f2d1ab6",
    "_uuid": "d0793e117fd202f679b6ecb1239e0ab0a8cfd137"
   },
   "source": [
    "The above graph shows relationship between the sepal length and width. Now we will check relationship between the petal length and width."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "_cell_guid": "ea5060b8-4067-cf46-99d6-a27be10a7e18",
    "_execution_state": "idle",
    "_uuid": "16a42e3a6615e48f7b8ed0a6dbb380de74dcd2c8"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmQAAAGDCAYAAACFuAwbAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3XuUFPWZ//HPAwwyCojKGBGQMRtFkLs4EjGRRCDRZcUs\nwYnxihjXmGHjSbK/qLnIupvLbtwYE9i4JhhRyURCvMXNeg2ooJFbQJDxQnSMIMqIysWA3J7fH1UD\nPcPMdA9d3VXd/X6dM6enq6urnv6ORx+/9e36mLsLAAAA8ekQdwEAAACljoYMAAAgZjRkAAAAMaMh\nAwAAiBkNGQAAQMxoyAAAAGJGQwYgr8xsjJmti7uOdMzMzexjcdeRCTPbZmYfbeW1y8xsYRvvLYi/\nB1DsaMgASNrXgHwQ/sd9vZn92Mw6ZvC+6WZ2d8R15LURMrMFZnbFQb73C2ZWb2bWbHsnM9toZhPC\n59eb2Wvh+K4zs3taOd51ZvZ/zba90sq2L0iSu3d191czrLdgGk2glNCQAUg11N27SjpL0hclfSnm\negrB/ZJ6SDqz2fbPSnJJD5vZpZIuljQ2HN+Rkp5o5XhPSTq9sRk2s16SyiQNb7btY+G+AIoADRmA\nA7j7i5KeljRIkszsWDP7nZk1hLM8/xxu/6yk6yVVhzM/K8PtU8yszsy2mtmrZvZPUdRlZpeHx33P\nzB4xs34pr7mZXRXOHL1vZjMbZ63MrKOZ/ZeZvRPWXxPu38nMvifpE5JmhJ9hRsopx7Z0vGZjtUPS\nXEmXNHvpEkm/dvfdkk6V9Ii7/yV8z1vuflsrH3OJggZsWPj8E5LmS3qp2ba/uPubKZ/9Y+HvR5nZ\ng2a2xcwWS/q7lDFqbOBWhp+1OuW1r4czehvMbEortQHIERoyAAcws4EK/qP/ZzPrIOn3klZK6q1g\n9uwaM/uMuz8s6fuS7gkvmw0ND7FR0gRJ3SVNkXSzmY3IsqaJCpq/f5RUoaBhrG222wQFzc8QSedL\n+ky4/UuSzlbQ0IyQdF7jG9z9W+GxasLPUJPB8ZqbLenzZlYe1nq4pH8It0vSnyRdYmb/YmYj27oU\n7O47JT0n6ZPhpk+G9S1stq212bGZknZI6iXp8vCn8diN7x8aftbGy6bHSDpcwd93qqSZZnZEazUC\niB4NGYBUy83sPQUN2C8l/UpBQ1Lh7je6+85wrdIvJH2htYO4+/+6+1888KSkRxU0eNm4StIP3L0u\nnHX6vqRhqbNkkn7o7u+7+18VzCo1ziidL+kWd1/n7u9J+mGG52zteE24+yJJb0v6XMr5Xnb3FeHr\nd0uapqChe1LSRjP7ZhvnfVL7m69PKGjInm627cnmbwobvUmSvuvuH7j7au1vCtuyS9KN7r7L3f8g\naZuk/hm8D0BEaMgApBrh7ke4+9+5+7fdfa+kfpKODS/bvW9m7yuYqfpIawcxs7PN7E9m9m64/zmS\nemZZWz9Jt6TU8K4kUzCr0+itlN//Jqlr+Puxkt5IeS3197a0dryW3Kn9ly0vDp/v4+5z3H2sgvVm\nV0n6NzNrbcbtKUlnmNmRCprhVyQ9o2Bt2ZEKLiW3NENWIamTmn6+19uoudGmsMltlO6zAogYDRmA\ndN6Q9Jq790j56ebu54Sve+rOZnaIpN9JuknSR9y9h6Q/KGiesq3jn5rVUe7uz2Tw3g2S+qQ879vs\ndVf27pJ0lpl9XNIoSXNa2imchfqtpOcVrtFrwbMKLiF+SdKi8H1bJL0ZbnvT3V9r4X0Nknar6ec7\nrv0fBUC+0ZABSGexpK1m9k0zKw8XyA8ys1PD19+WVBmuNZOkzpIOUdgcmNnZksa385ydzaxLyk9H\nSbdKus7MTpaCdVpmNjnD482V9FUz621mPSQ1v1z4tqQW7+OVKXevV7DOq1bSY+6+b3bNgnuB/b2Z\ndTOzDuGYnKxgrVhLx9ouaamkrym4VNloYbitxfVj7r5H0r2SppvZoeFawEub7Zb1ZwUQPRoyAG0K\n/yM/QcH6qdckvaNgfdnh4S6/DR83mdlyd98q6Z8VNEHvKbh9xoPtPO0Lkran/Exx9/sk/Yek35jZ\nFkmrFSzUz8QvFKxje17SnxXM2O2WtCd8/RYFi/LfM7OftrPWVLMVXFq9s9n2LQou8/5V0vuS/lPS\nl9291Ru2KlgjdrSCJqzR0+G2tm53UaPgcuNbku5QsA4w1XRJs8NLv+e3cRwAeWTuUczUA0DhCGeo\nbnX3fml3BoA8YIYMQNELL7WeE953rLekGyTdF3ddANCIGTIARc/MDlVwCfAkBZdA/1fSV8OF8gAQ\nOxoyAACAmHHJEgAAIGY0ZAAAADHrFHcB7dWzZ0+vrKyMuwwAAIC0li1b9o67V6Tbr+AassrKSi1d\nujTuMgAAANIys0ziy7hkCQAAEDcaMgAAgJjRkAEAAMSs4NaQtWTXrl1at26dduzYEXcpRaFLly7q\n06ePysrK4i4FAICSUBQN2bp169StWzdVVlbKzOIup6C5uzZt2qR169bp+OOPj7scAABKQlFcstyx\nY4eOOuoomrEImJmOOuooZhsBAMijomjIJNGMRYixBAAgv4qmIUuC733vezr55JM1ZMgQDRs2TM89\n91yr+95xxx16880381gdAABIqqJYQ5YEzz77rB566CEtX75chxxyiN555x3t3Lmz1f3vuOMODRo0\nSMcee2weqwQAAElUujNkOxqkTUuCxwhs2LBBPXv21CGHHCJJ6tmzp4499lgtW7ZMZ555pk455RR9\n5jOf0YYNGzRv3jwtXbpUF154oYYNG6bt27friSee0PDhwzV48GBdfvnl+vDDDyVJ1157rQYOHKgh\nQ4boG9/4hiTp97//vU477TQNHz5cY8eO1dtvvx3JZwAAAPEwd4+7hnYZOXKkN49Oqqur04ABAzI/\nSH2t9NxUqUNnae9O6bRZUuUFWdW1bds2nXHGGfrb3/6msWPHqrq6WqeffrrOPPNMPfDAA6qoqNA9\n99yjRx55RLfffrvGjBmjm266SSNHjtSOHTt0wgkn6IknntCJJ56oSy65RCNGjNDFF1+s008/XS++\n+KLMTO+//7569Oih9957Tz169JCZ6Ze//KXq6ur0X//1X1nV31y7xxQAABzAzJa5+8h0++XskqWZ\n9ZV0p6SPSHJJt7n7Lc32GSPpAUmvhZvudfcbc1WTpGBG7Lmp0p7twY8UPD9mrNQlbfZnq7p27apl\ny5bp6aef1vz581VdXa1vf/vbWr16tcaNGydJ2rNnj3r16nXAe1966SUdf/zxOvHEEyVJl156qWbO\nnKmamhp16dJFU6dO1YQJEzRhwgRJwW0+qqurtWHDBu3cuZPbUwAAUOByuYZst6Svu/tyM+smaZmZ\nPebua5rt97S7T8hhHU19UB/MjDU2Y5LUoSzYnkVDJkkdO3bUmDFjNGbMGA0ePFgzZ87UySefrGef\nffagjtepUyctXrxYTzzxhObNm6cZM2boj3/8o6ZNm6avfe1rOvfcc7VgwQJNnz49q7oBANFq+KBB\n9e/Xq7JHpSoOy+6/LdmcIx91IBo5W0Pm7hvcfXn4+1ZJdZJ65+p8GTusMrhMmWrvrmB7Fl566SW9\n8sor+56vWLFCAwYMUENDw76GbNeuXXrhhRckSd26ddPWrVslSf3791d9fb3Wrl0rSbrrrrt05pln\natu2bdq8ebPOOecc3XzzzVq5cqUkafPmzerdOxjK2bNnZ1U3ACBatatq1e8n/TTurnHq95N+ql1d\nG8s58lEHopOXRf1mVilpuKSW7gPxcTNbaWb/Z2Yn57yYLhXBmrGO5VJZ9+DxtFlZz45t27ZNl156\n6b4F+GvWrNGNN96oefPm6Zvf/KaGDh2qYcOG6ZlnnpEkXXbZZbrqqqs0bNgwubt+9atfafLkyRo8\neLA6dOigq666Slu3btWECRM0ZMgQnXHGGfrxj38sSZo+fbomT56sU045RT179sx6SAAA0Wj4oEFT\nH5yq7bu3a/OHm7V993ZNfWCqGj6I5gtkmZ4jH3UgWjm/7YWZdZX0O0nXuPuWZi8vl9TP3beZ2TmS\n7pd0QgvHuFLSlZJ03HHHZV9U5QXBmrEP6oOZsSybMUk65ZRT9jVbqXr27KmnnnrqgO2TJk3SpEmT\n9j0/66yz9Oc//7nJPr169dLixYsPeO/EiRM1ceLErGsGAESr/v16de7YWdt3718WU9axTPXv10d2\nyTCTc+SjDkQrpzNkZlamoBmb4+73Nn/d3be4+7bw9z9IKjOzA6Z83P02dx/p7iMrKiL6B6lLhXTU\nqZE0YwAASFJlj0rt3NN0WcyuPbtU2aMyr+fIRx2IVs4aMgvyd2ZJqnP3H7eyzzHhfjKzqrCeTbmq\nCQCAXKo4rEKzJs5SeadydT+ku8o7lWvWxFmRzkplco581IFo5ew+ZGZ2hqSnJa2StDfcfL2k4yTJ\n3W81sxpJX1bwjcztkr7m7gde90sRyX3IkBZjCgAHj29ZolHs9yFz94WS2kypdvcZkmbkqgYAAOJQ\ncVhFzhugTM6RjzoQjdKNTgIAAEgIGjIAAICY0ZAl1He/+109/vjj7X7fggUL9kUsAQCAwpDz+5Ch\nde4ud1eHDgf2xTfemNtIz0a7d+9Wp078YwAAQJxKdoasoUFasiR4zNa1116rmTNn7ns+ffp03XTT\nTfrRj36kU089VUOGDNENN9wgSaqvr1f//v11ySWXaNCgQXrjjTd02WWXadCgQRo8eLBuvvlmScGd\n/OfNmydJWrJkiU4//XQNHTpUVVVV2rp1q3bs2KEpU6Zo8ODBGj58uObPn39AXe+++67OO+88DRky\nRKNGjdLzzz+/r76LL75Yo0eP1sUXX5z9AABAlho+aNCS9UsK4k7ydQ11mr1ituoa6uIuBUWkJBuy\n2lqpXz9p3LjgsTbLeK/q6mrNnTt33/O5c+eqoqJCr7zyihYvXqwVK1Zo2bJl++7Y/8orr+jqq6/W\nCy+8oHfeeUfr16/X6tWrtWrVKk2ZMqXJsXfu3Knq6mrdcsstWrlypR5//HGVl5dr5syZMjOtWrVK\ntbW1uvTSS7Vjx44m773hhhs0fPhwPf/88/r+97+vSy65ZN9ra9as0eOPP67abD88AGSpkDIXp/1h\nmgb+90Bd9sBlGvjfAzXt/6bFXRKKRMk1ZA0N0tSp0vbt0ubNwePUqdnNlA0fPlwbN27Um2++qZUr\nV+qII47QqlWr9Oijj2r48OEaMWKEXnzxxX3h4/369dOoUaMkSR/96Ef16quvatq0aXr44YfVvXv3\nJsd+6aWX1KtXL5166qmSpO7du6tTp05auHChLrroIknSSSedpH79+unll19u8t6FCxfumwH79Kc/\nrU2bNmnLliC96txzz1V5efnBf2gAiEAhZS7WNdRpxpKmd2qasXgGM2WIRMk1ZPX1UufOTbeVlQXb\nszF58mTNmzdP99xzj6qrq+Xuuu6667RixQqtWLFCa9eu1dSpUyVJhx122L73HXHEEVq5cqXGjBmj\nW2+9VVdccUV2hWQotQYAiEtj5mKqxszFpFm8/sBs4ba2A+1Rcg1ZZaW0s2m8l3btCrZno7q6Wr/5\nzW80b948TZ48WZ/5zGd0++23a9u2bZKk9evXa+PGjQe875133tHevXs1adIk/fu//7uWL1/e5PX+\n/ftrw4YNWrJkiSRp69at2r17tz7xiU9ozpw5kqSXX35Zf/3rX9W/f/8m703dZ8GCBerZs+cBM3AA\nEKdCylys6l3Vru1Ae5Tc1+sqKqRZs4LLlGVlQTM2a1awPRsnn3yytm7dqt69e6tXr17q1auX6urq\n9PGPf1yS1LVrV919993q2LFjk/etX79eU6ZM0d69QbrUD37wgyavd+7cWffcc4+mTZum7du3q7y8\nXI8//riuvvpqffnLX9bgwYPVqVMn3XHHHTrkkEOavHf69Om6/PLLNWTIEB166KGaPXt2dh8SACLW\nmLk49YGpKutYpl17diU2c3FAxQDVVNVoxuL9ly1rqmo0oIKYOWQvZ1mWuRJVlmVDQ3CZsrIy+2as\nGJFlCSCfCilzsa6hTovXL1ZV7yqaMaQVe5Zl0lVU0IgBQFIUUubigIoBNGKIXMmtIQMAAEgaGjIA\nAICY0ZABAADEjIYMAAAgZjRkAIDYZZJlGcU++crMjOI8STlGMUnyeNCQ5cibb76pz3/+8+1+3xVX\nXKE1a9a0uc+tt96qO++882BLA4BEySTLMop98pWZGcV5knKMYpL08SjZ+5DFZffu3erUKfl3Gymk\nMQVQuBo+aFC/n/TT9t3b920r71Su1695fd9tMKLYJ5Nj5OvzFMoxikmc45HpfchKdoYsymnLa6+9\nVjNnztz3fPr06brppps0aNAgSdIdd9yhc889V5/+9Kd11llnae/evbr66qt10kknady4cTrnnHM0\nb948SdKYMWPU2HB27dpV3/rWtzR06FCNGjVKb7/9dpPjS9LatWs1duxYDR06VCNGjNBf/vIXbdu2\nTWeddZZGjBihwYMH64EHHsj6MwJALmSSZRnFPvnKzIziPEk5RjEphPEoyYYs6mnL6upqzZ07d9/z\nuXPn6rTTTmuyz/LlyzVv3jw9+eSTuvfee1VfX681a9borrvu0rPPPtvicT/44AONGjVKK1eu1Cc/\n+Un94he/OGCfCy+8UF/5yle0cuVKPfPMM+rVq5e6dOmi++67T8uXL9f8+fP19a9/XYU2EwqgNGSS\nZRnFPvnKzIziPEk5RjEphPEouYas4YMGTX1wqrbv3q7NH27W9t3bNfWBqVnNlA0fPlwbN27Um2++\nqZUrV+qII45Q3759m+wzbtw4HXnkkZKkhQsXavLkyerQoYOOOeYYfepTn2rxuJ07d9aECRMkSaec\ncorq6+ubvL5161atX79en/vc5yRJXbp00aGHHip31/XXX68hQ4Zo7NixWr9+/b7ZNQBIksYsy/JO\n5ep+SHeVdyo/IMsyin0yOUa+Pk+hHKOYFMJ4JH8xU8Qapy1TryM3Tltm84eZPHmy5s2bp7feekvV\n1dUHvH7YYYe1+5hlZWUyM0lSx44dtXv37ozeN2fOHDU0NGjZsmUqKytTZWWlduzY0e7zA0A+XDDo\nAo09fmybWZZR7JPJMfL1eQrlGMUk6eNRcg1ZrqYtq6ur9aUvfUnvvPOOnnzySX344Yet7jt69GjN\nnj1bl156qRoaGrRgwQJ98YtfbPc5u3Xrpj59+uj+++/Xeeedpw8//FB79uzR5s2bdfTRR6usrEzz\n58/X66+/ns1HA4CcyyTLMop98pWZGcV5knKMYpLk8Si5S5a5mrY8+eSTtXXrVvXu3Vu9evVqc99J\nkyapT58+GjhwoC666CKNGDFChx9++EGd96677tJPf/pTDRkyRKeffrreeustXXjhhVq6dKkGDx6s\nO++8UyeddNJBHRsAAORHyd72ouGDhlinLbdt26auXbtq06ZNqqqq0qJFi3TMMcfkvY7WcNsLAACy\nl+ltL0rukmWjuKctJ0yYoPfff187d+7Ud77znUQ1YwAAIL9KtiGL24IFC+IuAQAAJETJrSEDACAb\nZEzGo9jHrGgaskJbC5dkjCUAtIyMyXiUwpgVxaL+1157Td26ddNRRx21775dODjurk2bNmnr1q06\n/vjj4y4HABKDjMl4FPqYldSi/j59+mjdunVqaCjOacx869Kli/r06RN3GQCQKFHcWDxXNycvZqUy\nZkXRkJWVlTGbAwDIKTIm41EqY1Y0a8gAAMglMibjUSpjVhRryAAAyJcobiwe983JC1GhjllJrSED\nACBfyJiMR7GPGZcsAQAAYkZDBgAAEDMaMgAAgJjRkAEAAMSMhgwAACBmNGQAgJKRSUB1un2iOEZU\ntRaTUvu8zdGQAQBKQiYB1en2ieIYUdVaTErt87aEG8MCAIpeJgHV6faJ4hhR1VpMiv3zZnpjWGbI\nAABFrzGgOlVjQHWm+0RxjKhqLSal9nlbQ0MGACh6mQRUp9snimNEVWsxKbXP2xoaMgBA0cskoDrd\nPlEcI6pai0mpfd7WsIYMAFAyMgmoTrdPFMeIqtZiUqyfN9M1ZDRkAAAAOcKifgAAgAJBQwYAABAz\nGjIAAICY5awhM7O+ZjbfzNaY2Qtm9tUW9jEz+6mZrTWz581sRK7qAQAASKpczpDtlvR1dx8oaZSk\nr5jZwGb7nC3phPDnSkk/z2E9AIAcKKR8SORGPv42xf73z1lD5u4b3H15+PtWSXWSejfbbaKkOz3w\nJ0k9zKxXrmoCAESrkPIhkRv5+NuUwt8/L7e9MLNKSU9JGuTuW1K2PyTph+6+MHz+hKRvunur97Xg\nthcAkAyFlA+J3MjH36bQ//6Jue2FmXWV9DtJ16Q2Y+08xpVmttTMljY0FOdUJQAUmkLKh0Ru5ONv\nUyp//5w2ZGZWpqAZm+Pu97awy3pJfVOe9wm3NeHut7n7SHcfWVGR/G4YAEpBIeVDIjfy8bcplb9/\nLr9laZJmSapz9x+3stuDki4Jv205StJmd9+Qq5oAANEppHxI5EY+/jal8vfP2RoyMztD0tOSVkna\nG26+XtJxkuTut4ZN2wxJn5X0N0lT2lo/JrGGDACSppDyIZEb+fjbFOrfnyxLAACAmCVmUT8AAADa\nRkMGAAAQMxoyAACAmNGQAQAAxIyGDACQc+lyCOsa6jR7xWzVNdTl9DylhvEoHJ3iLgAAUNxqV9Vq\n6oNT1bljZ+3cs1OzJs7SBYMu2Pf6tD9M04wlM/Y9r6mq0c/O/lnk5yk1jEdh4bYXAICcSZdDWNdQ\np4H/PfCA9625eo0GVAyI7DylhvFIDm57AQCIXbocwsXrF7f4vta2H+x5Sg3jUXhoyAAAOZMuh7Cq\nd1WL72tt+8Gep9QwHoWHhgwAkDPpcggHVAxQTVVNk/fUVNW063JlJucpNYxH4WENGQAg59LlENY1\n1Gnx+sWq6l3V7masPecpNYxH/MiyBAAAiBmL+gEAAAoEDRkAAEDMaMgAAABiRkMGAAAQMxoyAECb\nFr1cpxvuna1FL7ecMxlFDmWSMhfTfZ4oak3KMZJ0nlJHliUAoFXjfzJNj70f5Eze+Lw0vkeNHrlm\nf85kFDmUScpcTPd5oqg1KcdI0nnAbS8AAK1Y9HKdzvj1QMlSNrq08ItrNPrEAZHkUCYpczHd54mi\n1qQcI0nnKXbc9gIAkJVHV7ecJ9m4PYocyiRlLqb7PFHUmpRjJOk8CNCQAQBaNH5Qy3mSjdujyKFM\nUuZius8TRa1JOUaSzoMADRkAoEWjTxyg8T1qJNe+n/E9ajT6xOByZBQ5lEnKXEz3eaKoNSnHSNJ5\nEGANGQCgTYtertOjqxdr/KCqfc1YqihyKJOUuZju80RRa1KOkaTzFCuyLAEAAGLGon4AAIACQUMG\nAAAQMxoyAACAmNGQAQAAxIyGDAAKVCFlDDY0SEuWBI8ADkRDBgAFqHZVrfr9pJ/G3TVO/X7ST7Wr\na+MuqVW1tVK/ftK4ccFjbXJLBWLDbS8AoMAUUsZgQ0PQhG3fX6rKy6XXX5cqklUqkBPc9gIAilQh\nZQzW10udm5aqsrJgO4D9aMgAoMAUUsZgZaW0s2mp2rUr2A5gPxoyACgwhZQxWFEhzZoVXKbs3j14\nnDWLy5VAc6whA4ACVUgZgw0NwWXKykqaMZSWTNeQdcpHMQCA6FUcVpH4RqxRRQWNGNAWLlkCAADE\njIYMAAAgZjRkAAAAMaMhAwAAiBkNGQAAQMxoyACgQEUR2J2U0O+k1JEvhRQMj/ygIQOAAhRFYHdS\nQr+TUke+FFIwPPKHG8MCQIGJIrA7KaHfSakjXwopGB7RIFwcAIpUFIHdSQn9Tkod+VJIwfDILxoy\nACgwUQR2JyX0Oyl15EshBcMjv2jIAKDARBHYnZTQ76TUkS+FFAyP/GINGQAUqCgCu5MS+p2UOvKl\nkILhkR3CxQGgyEUR2J2U0O+k1JEvhRQMj/zgkiUAAEDMaMgAAABiRkMGAAAQs5w1ZGZ2u5ltNLPV\nrbw+xsw2m9mK8Oe7uaoFAAAgydI2ZGZWYWbXm9ltYZN1u5ndnsGx75D02TT7PO3uw8KfGzMpGAAK\nQT6yGefMkSZODB4Pto4o6qyrk2bPDh5brSNNdiPZjih1mcyQPSDpcEmPS/rflJ82uftTkt7NqjoA\nKED5yGbs21e66CLpwQeDx+OOa38dUdQ5bZo0cKB02WXB47RpLdSRJruRbEcgg/uQmdkKdx92UAc3\nq5T0kLsPauG1MZJ+J2mdpDclfcPdX0h3TO5DBiDJ8pHNOGdO0IQ1d/fd0oUXZlZHFHXW1QVNWHNr\n1kgDBoR1pMluJNsRxS7KLMuHzOycCGpqbrmkfu4+VNLPJN3f2o5mdqWZLTWzpQ25nP8HgCzlI5tx\n7tz029PVEUWdixen354uu5FsRyDQakNmZlvNbIukrypoyrab2ZaU7Vlx9y3uvi38/Q+SysysZyv7\n3ubuI919ZEUp3TkQQMHJRzbj+een356ujijqrKpKvz1ddiPZjkCg1YbM3bu5e/fwsYO7l6c8757t\nic3sGDOz8PeqsJZN2R4XAOKUj2zGCy8M1pCl6tt3/+XKTOqIos4BA6Samqbbamr2X66U0mc3ku0I\nBDJZQ/aEu5+VblsL76uVNEZST0lvS7pBUpkkufutZlYj6cuSdkvaLulr7v5MuoJZQwagEOQjm3HO\nnOAy5fnnN23G2lNHFHXW1QWXKauqmjZjTc6TJruRbEcUq0zXkLXakJlZF0mHSfqjgsbKwpe6S3rY\n3U+KptT2oSEDAACFIopw8X+SdI2kYxUswG+0RdKM7MoDAABAo1YbMne/RdItZjbN3X+Wx5oAAABK\nSqsNmZn9Y/jr+pTf93H3e3NWFQAAQAlp65LlP4SPFZJGK1hLJkmfkvSMJBoyAACACLR124sp7j5F\n0iGSBrr7JHefJOlkhd+WBIBCk4+MyahkkhGZTrrPm1EOZQGNWT6Qu4lcyORO/X3cfUPK87cltZCa\nBgDJlo+MyahkkhGZTrrPm1EOZQGNWT6Qu4lcyeQ+ZDMknSCp8Z+6aklr3f0g/vWQPW57AeBg5CNj\nMiqZZESH4tDnAAAWFklEQVSmk+7zZpRDWUBjlg/kbuJgRJZl6e41kv5H0tDw57a4mjEAOFj5yJiM\nSiYZkemk+7wZ5VCmOUapIXcTudTWov59wm9UsogfQMHKR8ZkVDLJiEwn3efNKIcyzTFKDbmbyKW2\nwsUXho9bw1DxLVGGiwNAPuUjYzIqmWREppPu82aUQ1lAY5YP5G4il9KuIUsa1pAByEY+MiajkklG\nZDrpPm9GOZQFNGb5QO4m2iOKLMufKLjf2EJ3fzPi+g4aDRkAACgUUWRZrpV0nqT/NDMpaM6ekbRI\n0kp33xtFoQAAAKWurSzLGQpDxM3sWEmnhz/XSDpaUvd8FAgAAFDs2vyWpQVTY4MVNGKjJQ1UMHN2\nV+5LAwAAKA1thYs/pmAWbIWkP0n6vrtnEeABAACAlrR1Y9hXJe1VcJf+EyR9zMx65qUqACUnKXmJ\nixZJN9wQPLYmk/zHdPtEkSGZyZglZVwBpOHubf4omCUbL2m6pIclLZM0O937cvVzyimnOIDi8utf\nu5eXux9+ePD461/HU8e4ce7S/p/x4w/cp6am6T41Ne3fJ5NjpBuTTMYsKeMKlDJJSz2D/iaTLMtD\nJJ2qYA3Z6ZJGSdro7oNz1iW2gdteAMUlKXmJixZJZ5xx4PaFC6XRo4PfM8l/TLdPFBmSmYxZUsYV\nKHVZZ1ma2c1m9pykDZL+VVI3SbdK6h9XMwag+CQlL/HRR9NvzyT/Md0+UWRIZjJmSRlXAJlp61uW\nr0m6W9IKd9+Tp3oAlJik5CWOHy/deGPL2xtlkv+Ybp8oMiQzGbOkjCuAzLQ6Q+buP3X3ZTRjAHIp\nKXmJo0c3bb6k4Hnj5Uops/zHdPtEkSGZyZglZVwBZIYsSwCJkJS8xEWLgsuUzZuxVJnkP6bbJ4oM\nyUzGLCnjCpSqrLMsk4qGDAAAFIqssyzN7Mi23uju7x5MYQAAAGiqrUX9yyS5JGvhNZf00ZxUBAAA\nUGLaChc/Pp+FAAAAlKo2w8UbmdkRCuKTujRuc/enclUUAABAKWkry1KSZGZXSHpK0iMKbhD7iIIY\nJQAoOFHkQ0ZxnnwdIwnnAJBe2oZM0lcVRCe97u6fkjRc0vs5rQoAcqC2NogTGjcueKytbd/rUZ0n\nX8dIwjkAZCaTLMsl7n6qma2QdJq7f2hmL7j7yfkpsSluewHgYESRDxnFefJ1jCScA0AEWZYp1plZ\nD0n3S3rMzB6Q9Hq2BQJAPkWRDxnFefJ1jCScA0Dm0i7qd/fPhb9ON7P5kg6X9H85rQoAIhZFPmQU\n58nXMZJwDgCZy2RR/12Nv7v7k+7+oKTbc1oVAEQsinzIKM6Tr2Mk4RwAMpfJGrLl7j4i5XlHSavc\nfWCui2sJa8gAZCOKfMgozpOvYyThHEApiyI66TpJ10sqN7Mt2n/H/p2SboukSgDIs4qKthuPdK9H\ndZ58HSMJ5wCQXquXLN39B+7eTdKP3L27u3cLf45y9+vyWCMAAEBRy+Rblt8ys4vM7DuSZGZ9zawq\nx3UBAACUjEwaspmSPi7pi+HzbeE2AAAARCCTLMvT3H2Emf1Zktz9PTPrnO5NAAAAyEwmM2S7wm9W\nuiSZWYWkvTmtCgAAoIRk0pD9VNJ9ko42s+9JWijp+zmtCkBGCIZuKpPxYMwAJFHahszd50j6f5J+\nIGmDpPPc/be5LgxA2wiGbiqT8WDMACRVqzeGNbMukq6S9DFJqyTNcvfdeaytRdwYFiAYurlMxoMx\nAxCHKMLFZ0saqaAZO1vSTRHVBiBLBEM3lcl4MGYAkqytb1kOdPfBkmRmsyQtzk9JANIhGLqpTMaD\nMQOQZG3NkO1q/CUJlyoB7EcwdFOZjAdjBiDJ2lpDtkfSB41PJZVL+lv4u7t797xU2AxryID9CIZu\nKpPxYMwA5FPW4eLu3jHakgBEjWDopjIZD8YMQBJlch8yAAAA5BANGQAAQMxoyAAAAGKWs4bMzG43\ns41mtrqV183Mfmpma83seTMbkataAAAAkiyXM2R3SPpsG6+fLemE8OdKST/PYS0AslBXJ82eHTzG\neYx85FCShwkgDjlryNz9KUnvtrHLREl3euBPknqYWa9c1QPg4EybJg0cKF12WfA4bVo8x8hHDiV5\nmADi0up9yCI5uFmlpIfcfVALrz0k6YfuvjB8/oSkb7p7mzcZ4z5kQP7U1QUNVHNr1kgDBuTvGPnI\noSQPE0AuRJFlmRhmdqWZLTWzpQ1cIwDyZnErgWmtbc/VMfKRQ0keJoA4xdmQrZfUN+V5n3DbAdz9\nNncf6e4jK/jfUCBvqqratz1Xx8hHDiV5mADiFGdD9qCkS8JvW46StNndN8RYD4BmBgyQamqabqup\nyfxSY1THyEcOJXmYAOKUszVkZlYraYyknpLelnSDpDJJcvdbzcwkzVDwTcy/SZqSbv2YxBoyIA51\ndcElxqqq9jVSUR8jHzmU5GECiFKma8hyuqg/F2jIAABAoSiqRf0AAADFjIYMAAAgZjRkAAAAMaMh\nAwAAiBkNGQAAQMxoyAAAAGJGQwYAABAzGjIAAICY0ZABAADEjIYMAAAgZjRkAAAAMaMhAwAAiBkN\nGQAAQMxoyAAAAGJGQwYAABAzGjIAAICY0ZABAADEjIYMAAAgZjRkAAAAMaMhAwAAiBkNGQAAQMxo\nyAAAAGJGQwYAABAzGjIAAICY0ZABAADEjIYMAAAgZjRkAAAAMaMhAwAAiBkNGQAAQMxoyAAAAGJG\nQwYAABAzGjIAAICY0ZABAADEjIYMAAAgZjRkAAAAMaMhAwAAiBkNGQAAQMxoyAAAAGJGQwYAABAz\nGjIAAICY0ZABAADEjIas2O1okDYtCR4BAEAidYq7AORQfa303FSpQ2dp707ptFlS5QVxVwUAAJph\nhqxY7WgImrE926Vdm4PH56YyUwYAQALRkBWrD+qDmbFUHcqC7QAAIFFoyIrVYZXBZcpUe3cF2wEA\nQKLQkBWrLhXBmrGO5VJZ9+DxtFnBdgAAkCgs6i9mlRdIx4wNLlMeVkkzBgBAQtGQFbsuFTRiAAAk\nHJcsAQAAYkZDBgAAEDMaMgAAgJjltCEzs8+a2UtmttbMrm3h9cvMrMHMVoQ/V+SyHgAAgCTK2aJ+\nM+soaaakcZLWSVpiZg+6+5pmu97j7jW5qgMZ2NHANzEBAIhRLmfIqiStdfdX3X2npN9ImpjD8+Fg\n1NdKD/ST/jgueKyvjbsiAABKTi4bst6S3kh5vi7c1twkM3vezOaZWd8c1oPmyLsEACAR4l7U/3tJ\nle4+RNJjkma3tJOZXWlmS81saUMDzUJkyLsEACARctmQrZeUOuPVJ9y2j7tvcvcPw6e/lHRKSwdy\n99vcfaS7j6yoYI1TZMi7BAAgEXLZkC2RdIKZHW9mnSV9QdKDqTuYWa+Up+dKqsthPWiOvEsAABIh\nZ9+ydPfdZlYj6RFJHSXd7u4vmNmNkpa6+4OS/tnMzpW0W9K7ki7LVT1oBXmXAADEztw97hraZeTI\nkb506dK4ywAAAEjLzJa5+8h0+8W9qB8AAKDk0ZABAADEjIYMAAAgZjRkAAAAMaMhi9OOBmnTkuzu\njL9xkfT8DcHjwZ4jijqiOAYAACUqZ7e9QBr1tUFMUYfOwc1ZT5sV3IKiPZ4YL739WPD76hulj4yX\nznqkfeeIoo4ojgEAQAljhiwOUWRIbly0vxlr9Paj+2fKMjlHFHWQhwkAQNZoyOIQRYbkW4+2vT2T\nc0RRB3mYAABkjYYsDlFkSB4zvu3tmZwjijrIwwQAIGs0ZHGIIkPy6NHBmrFUHxkfbM/0HFHUQR4m\nAABZIzopTjsass+Q3LgouEx5TEoz1t5zRFFHFMcAAKDIZBqdxLcs49SlIvvm5ejRLTdi7TlHFHVE\ncQwAAEoUlywBAABiRkMGAAAQMxoyAACAmNGQAQAAxIyGLE6b66RXZwePLUmXUymRQwkAQBHgW5Zx\nWTJNemXG/ucn1Ein/mz/83Q5lRI5lAAAFAlmyOKwua5pMyYFzxtnytLlVErkUAIAUERoyOKwaXHb\n29PlVErkUAIAUERoyOJwVFXb29PlVErkUAIAUERoyOJw+IBgzViqE2qC7VL6nEqJHEoAAIoIWZZx\n2lwXXKY8qmp/M5YqXU6lRA4lAAAJRpZlITh8QMuNWKN0OZUSOZQAABQBLlkCAADEjIYMAAAgZjRk\nAAAAMaMhAwAAiBkNGQAAQMxoyFoSRdh2uuBwSVr3kPSnK4LHlqz4rvRA/+CxNS/9XHr0k8FjS16d\nIy2YGDy2hoByAABixX3ImosibDtdcLgkPTRY2rJ6//Pug6UJz+9//uvOknalvKGz9MUPmx5j7pHS\n7vf2P+90pHT+pv3P7+0r7Vi3/3mXvtI//rXpMQgoBwAgZzK9DxkzZKmiCNtOFxwuBTNiqc2YJG1Z\ntX+mbMV31bQZk6SdTWfKXvp502ZMkna/u3+m7NU5TZsxSdrxRtOZMgLKAQBIBBqyVFGEbacLDpek\ndfe3vE/j9tfvafn11O2v17ayT7j9r3Nbfj11OwHlAAAkAg1ZqijCttMFh0tSn/Na3qdxe7/qll9P\n3d6vlUuCjduPO7/l11O3E1AOAEAi0JCliiJsO11wuCT1mRCsGUvVfXCwXZKG3Sip2ayTOofbQ/2/\nHKwZS9XpyGC7JH30wmDNWJPP1zfYvu85AeUAACQBi/pbEkXYdrrgcClYM7bu/mBmrLEZS7Xiu8Fl\nyn7VTZuxVC/9PLhM2e+C/c1YqlfnBJcpjzu/aTOWioByAAByItNF/TRkAAAAOcK3LAEAAAoEDRkA\nAEDMaMgAAABiRkMGAAAQMxqyg5WP7MZMzpEuDxMAACRep7gLKEj5yG7M5BypeZivzjowDxMAABQE\nZsjaKx/ZjZmcI10eJgAAKBg0ZO2Vj+zGTM6RLg8TAAAUDBqy9spHdmMm50iXhwkAAAoGDVl75SO7\nMZNzpMvDBAAABYPopIOVj+zGTM6RLg8TAADEJtPoJL5lebC6VOQ+RDuTc/SZQCMGAECB45IlAABA\nzGjIAAAAYkZDBgAAELOcNmRm9lkze8nM1prZtS28foiZ3RO+/pyZVeayHgAAgCTKWUNmZh0lzZR0\ntqSBki4ws4HNdpsq6T13/5ikmyX9R67qAQAASKpczpBVSVrr7q+6+05Jv5E0sdk+EyXNDn+fJ+ks\nM7Mc1gQAAJA4uWzIekt6I+X5unBbi/u4+25JmyUdlcOaAAAAEqcgFvWb2ZVmttTMljY0RBjiDQAA\nkAC5bMjWS+qb8rxPuK3Ffcysk6TDJW1qfiB3v83dR7r7yIqKHN+MFQAAIM9y2ZAtkXSCmR1vZp0l\nfUHSg832eVDSpeHvn5f0Ry+0LCcAAIAs5Sw6yd13m1mNpEckdZR0u7u/YGY3Slrq7g9KmiXpLjNb\nK+ldBU0bAABASSm4cHEza5D0eh5O1VPSO3k4T6lhXKPHmEaPMc0NxjV6jGluRDmu/dw97XqrgmvI\n8sXMlmaSzo72YVyjx5hGjzHNDcY1eoxpbsQxrgXxLUsAAIBiRkMGAAAQMxqy1t0WdwFFinGNHmMa\nPcY0NxjX6DGmuZH3cWUNGQAAQMyYIQMAAIgZDVkzZna7mW00s9Vx11IszKyvmc03szVm9oKZfTXu\nmoqBmXUxs8VmtjIc13+Nu6ZiYWYdzezPZvZQ3LUUCzOrN7NVZrbCzJbGXU8xMLMeZjbPzF40szoz\n+3jcNRUyM+sf/vPZ+LPFzK7J2/m5ZNmUmX1S0jZJd7r7oLjrKQZm1ktSL3dfbmbdJC2TdJ67r4m5\ntIJmZibpMHffZmZlkhZK+qq7/ynm0gqemX1N0khJ3d19Qtz1FAMzq5c00t25Z1ZEzGy2pKfd/Zdh\nIs6h7v5+3HUVAzPrqCDe8TR3z8e9T5kha87dn1KQGoCIuPsGd18e/r5VUp2k3vFWVfg8sC18Whb+\n8H9YWTKzPpL+XtIv464FaI2ZHS7pkwoSb+TuO2nGInWWpL/kqxmTaMiQZ2ZWKWm4pOfiraQ4hJfW\nVkjaKOkxd2dcs/cTSf9P0t64CykyLulRM1tmZlfGXUwROF5Sg6RfhZfXf2lmh8VdVBH5gqTafJ6Q\nhgx5Y2ZdJf1O0jXuviXueoqBu+9x92GS+kiqMjMus2fBzCZI2ujuy+KupQid4e4jJJ0t6Svh8hAc\nvE6SRkj6ubsPl/SBpGvjLak4hJd/z5X023yel4YMeRGucfqdpDnufm/c9RSb8FLFfEmfjbuWAjda\n0rnheqffSPq0md0db0nFwd3Xh48bJd0nqSreigreOknrUmbF5ylo0JC9syUtd/e383lSGjLkXLj4\nfJakOnf/cdz1FAszqzCzHuHv5ZLGSXox3qoKm7tf5+593L1SwSWLP7r7RTGXVfDM7LDwCz0KL6uN\nl8Q32bPg7m9JesPM+oebzpLEF6WicYHyfLlSCqY8kcLMaiWNkdTTzNZJusHdZ8VbVcEbLeliSavC\n9U6SdL27/yHGmopBL0mzw28DdZA01925TQOS6COS7gv+30ydJP3a3R+Ot6SiME3SnPAS26uSpsRc\nT8EL/4dhnKR/yvu5ue0FAABAvLhkCQAAEDMaMgAAgJjRkAEAAMSMhgwAACBmNGQAAAAxoyEDkChm\ntsfMVpjZajP7rZkdmmb/6zM8br2Z9cx0e1TM7DwzG5jyfIGZjczV+QAUJhoyAEmz3d2HufsgSTsl\nXZVm/4washidJ2lg2r0AlDQaMgBJ9rSkj0mSmV1kZovD2bP/CYPVfyipPNw2J9zv/jDA+oWDDbEO\n7yx/e3i+P5vZxHD7ZWZ2r5k9bGavmNl/prxnqpm9HL7nF2Y2w8xOV5CJ96Owxr8Ld58c7veymX0i\ni/EBUCS4Uz+ARDKzTgoy5R42swGSqiWNdvddZvbfki5092vNrCYMWG90ubu/G8ZJLTGz37n7pnae\n/lsKYpMuD+OpFpvZ4+FrwyQNl/ShpJfM7GeS9kj6joIswa2S/ihppbs/Y2YPSnrI3eeFn0uSOrl7\nlZmdI+kGSWPbWR+AIkNDBiBpylMitp5WkIN6paRTFDRYklQuaWMr7/9nM/tc+HtfSSdIam9DNl5B\nyPg3wuddJB0X/v6Eu2+WJDNbI6mfpJ6SnnT3d8Ptv5V0YhvHvzd8XCapsp21AShCNGQAkmZ7sxmv\nxoD62e5+XVtvNLMxCmabPu7ufzOzBQqaqfYySZPc/aVmxz9NwcxYoz06uH+PNh7jYN8PoMiwhgxA\nIXhC0ufN7GhJMrMjzaxf+NouMysLfz9c0nthM3aSpFEHeb5HJE0LG0GZ2fA0+y+RdKaZHRFeap2U\n8tpWSd0Osg4AJYKGDEDiufsaSd+W9KiZPS/pMUm9wpdvk/R8uKj/YUmdzKxO0g8l/SnDUzxvZuvC\nnx9L+jdJZeH2F8LnbdW3XtL3JS2WtEhSvaTN4cu/kfQv4ZcD/q7lIwAodebucdcAAAXPzLq6+7Zw\nhuw+Sbe7+31x1wWgMDBDBgDRmB5+GWG1pNck3R9zPQAKCDNkAAAAMWOGDAAAIGY0ZAAAADGjIQMA\nAIgZDRkAAEDMaMgAAABiRkMGAAAQs/8P2vLh9I2biU8AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fa1099a1ad0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = iris[iris.Species=='Iris-setosa'].plot.scatter(x='PetalLengthCm',y='PetalWidthCm',color='orange', label='Setosa')\n",
    "iris[iris.Species=='Iris-versicolor'].plot.scatter(x='PetalLengthCm',y='PetalWidthCm',color='blue', label='versicolor',ax=fig)\n",
    "iris[iris.Species=='Iris-virginica'].plot.scatter(x='PetalLengthCm',y='PetalWidthCm',color='green', label='virginica', ax=fig)\n",
    "fig.set_xlabel(\"Petal Length\")\n",
    "fig.set_ylabel(\"Petal Width\")\n",
    "fig.set_title(\" Petal Length VS Width\")\n",
    "fig=plt.gcf()\n",
    "fig.set_size_inches(10,6)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "3068e91a-2455-f7ae-b1d0-a2114b78ea62",
    "_uuid": "dd90c7e433f42fea8e5836c91959429710491347"
   },
   "source": [
    "As we can see that the Petal Features are giving a better cluster division compared to the Sepal features. This is an indication that the Petals can help in better and accurate Predictions over the Sepal. We will check that later."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "ac6bb577-9975-39d5-aa20-376e574e703c",
    "_uuid": "aaa439a16175b442a42e845060b7fe1bd2d246f0"
   },
   "source": [
    "### Now let us see how are the length and width are distributed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "_cell_guid": "d818068d-5110-c64e-ec6e-92bda44a9723",
    "_execution_state": "idle",
    "_uuid": "0ca23638e6e067ffd7501552f346674646e3e1d2"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsUAAAF1CAYAAAAA6ZfwAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nkiQN3h/OQMI/Il7SmwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fa10889a450>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "iris.hist(edgecolor='black', linewidth=1.2)\n",
    "fig=plt.gcf()\n",
    "fig.set_size_inches(12,6)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "cdb55848-d7eb-d66c-dec1-79cbbfba2826",
    "_uuid": "3e8d0f657f996be6f4020b1850148bade9fdc588"
   },
   "source": [
    "### Now let us see how the length and width vary according to the species"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "_cell_guid": "a1d57f07-5c6b-4ab3-ad15-b8b5245c05b9",
    "_execution_state": "idle",
    "_uuid": "15e65581708a5b67ac8f0c1994fa08ef8158e799"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA3IAAAJQCAYAAADLxFZoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fa10a288dd0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(15,10))\n",
    "plt.subplot(2,2,1)\n",
    "sns.violinplot(x='Species',y='PetalLengthCm',data=iris)\n",
    "plt.subplot(2,2,2)\n",
    "sns.violinplot(x='Species',y='PetalWidthCm',data=iris)\n",
    "plt.subplot(2,2,3)\n",
    "sns.violinplot(x='Species',y='SepalLengthCm',data=iris)\n",
    "plt.subplot(2,2,4)\n",
    "sns.violinplot(x='Species',y='SepalWidthCm',data=iris)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "2497705a-9c08-5d8b-6ca0-0edc509e73b9",
    "_uuid": "0e907abebd6751fa3597fd6b08bb24eb13081443"
   },
   "source": [
    "The violinplot shows density of the length and width in the species. The thinner part denotes that there is less density whereas the fatter part conveys higher density"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "4df5f118-994c-4d7d-2fa1-b8a1ed1a82ec",
    "_uuid": "b45c7ca882bf32568268465f041282cfcd0e6fe9"
   },
   "source": [
    "### Now the given problem is a classification problem.. Thus we will be using the classification algorithms to build a model.\n",
    "**Classification**: samples belong to two or more classes and we want to learn from already labeled data how to predict the class of unlabeled data\n",
    "\n",
    "**Regression**: if the desired output consists of one or more continuous variables, then the task is called regression. An example of a regression problem would be the prediction of the length of a salmon as a function of its age and weight."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "b772ca1b-fd3c-d27a-b787-926c2df4e354",
    "_uuid": "a0436d5a5baa07027fdc10ad918d776e7fe948f4"
   },
   "source": [
    "Before we start, we need to clear some ML notations.\n",
    "\n",
    "**attributes**-->An attribute is a property of an instance that may be used to determine its classification. In the following dataset, the attributes are the petal and sepal length and width. It is also known as **Features**.\n",
    "\n",
    "**Target variable**, in the machine learning context is the variable that is or should be the output. Here the target variables are the 3 flower species."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "_cell_guid": "c27e7e16-6083-5b53-cda4-c43cf4c79a67",
    "_execution_state": "idle",
    "_uuid": "2b652b2398f95bacb6286eac49694cd422a54e6a"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/taka/.virtualenvs/iris-species-engine-env/local/lib/python2.7/site-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.\n",
      "  \"This module will be removed in 0.20.\", DeprecationWarning)\n"
     ]
    }
   ],
   "source": [
    "# importing alll the necessary packages to use the various classification algorithms\n",
    "from sklearn.linear_model import LogisticRegression  # for Logistic Regression algorithm\n",
    "from sklearn.cross_validation import train_test_split #to split the dataset for training and testing\n",
    "from sklearn.neighbors import KNeighborsClassifier  # for K nearest neighbours\n",
    "from sklearn import svm  #for Support Vector Machine (SVM) Algorithm\n",
    "from sklearn import metrics #for checking the model accuracy\n",
    "from sklearn.tree import DecisionTreeClassifier #for using Decision Tree Algoithm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "_cell_guid": "d967de9a-df34-bc84-899b-28b8804f7d58",
    "_execution_state": "idle",
    "_uuid": "15457e7fa8ff19b86c2858c365f11fa289fca723"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(150, 5)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris.shape #get the shape of the dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "21c81da1-f5f8-8d86-6c23-76928d0ec387",
    "_uuid": "a09827c482cacd56f2040afdb162d46270551512"
   },
   "source": [
    "Now, when we train any algorithm, the number of features and their correlation plays an important role. If there are features and many of the features are highly correlated, then training an algorithm with all the featues will reduce the accuracy. Thus features selection should be done carefully. This dataset has less featues but still we will see the correlation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "_cell_guid": "91f4a3b2-6e38-4d41-9ba0-52c7f43a581c",
    "_execution_state": "idle",
    "_uuid": "86e4d3c42eeec9d2df63d5f60c94e2c30b65ebd7"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeAAAAD8CAYAAACvt3fBAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fa1083fc690>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(7,4)) \n",
    "sns.heatmap(iris.corr(),annot=True,cmap='cubehelix_r') #draws  heatmap with input as the correlation matrix calculted by(iris.corr())\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "45543c97-83ae-392c-183c-24d118985163",
    "_uuid": "a2456971023a8d78416ae87fd1b09173da1e357e"
   },
   "source": [
    "**Observation--->**\n",
    "\n",
    "The Sepal Width and Length are not correlated\n",
    "The Petal Width and Length are highly correlated\n",
    "\n",
    "We will use all the features for training the algorithm and check the accuracy.\n",
    "\n",
    "Then we will use 1 Petal Feature and 1 Sepal Feature to check the accuracy of the algorithm as we are using only 2 features that are not correlated. Thus we can have a variance in the dataset which may help in better accuracy. We will check it later."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "74afdd84-2b1f-b6e3-b9e2-6c076e44cb10",
    "_uuid": "362675378d1f8d7892597877aa9dbd1caa20c0ff"
   },
   "source": [
    "### Steps To Be followed When Applying an Algorithm\n",
    "\n",
    " 1. Split the dataset into training and testing dataset. The testing dataset is generally smaller than training one as it will help in training the model better.\n",
    " 2. Select any algorithm based on the problem (classification or regression) whatever you feel may be good.\n",
    " 3. Then pass the training dataset to the algorithm to train it. We use the **.fit()** method\n",
    " 4. Then pass the testing data to the trained algorithm to predict the outcome. We use the **.predict()** method.\n",
    " 5. We then check the accuracy by **passing the predicted outcome and the actual output** to the model."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "2de179a6-ea22-00ff-8756-63d3aef6bd2d",
    "_uuid": "ffa8b5a66eb4651f46672b7263774dbcf125ecbf"
   },
   "source": [
    "### Splitting The Data into Training And Testing Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "_cell_guid": "a24c3ab9-8c7d-2a78-113f-d337c5c61f09",
    "_execution_state": "idle",
    "_uuid": "87bc90a957a8defb5e24b886b641fb0a9aa5fc42"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(105, 5)\n",
      "(45, 5)\n"
     ]
    }
   ],
   "source": [
    "train, test = train_test_split(iris, test_size = 0.3)# in this our main data is split into train and test\n",
    "# the attribute test_size=0.3 splits the data into 70% and 30% ratio. train=70% and test=30%\n",
    "print(train.shape)\n",
    "print(test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "_cell_guid": "54dd7ded-5079-fc8c-065b-70bfbfb0b83a",
    "_execution_state": "idle",
    "_uuid": "7a64738b8be79ad6b0f4899e985d3ab5e475f9e1"
   },
   "outputs": [],
   "source": [
    "train_X = train[['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm']]# taking the training data features\n",
    "train_y=train.Species# output of our training data\n",
    "test_X= test[['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm']] # taking test data features\n",
    "test_y =test.Species   #output value of test data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "c7d21e9f-8470-9aae-51ef-feea2cec6b1c",
    "_uuid": "0b18f7458fd76e93ed4a3932001f6f657cadb647"
   },
   "source": [
    "Lets check the Train and Test Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "_cell_guid": "2cf23cff-74d0-b15e-87a9-5ed72f543380",
    "_execution_state": "idle",
    "_uuid": "8fa3e8f9f4ba0b27796008dd998c41670f1ffd95"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>SepalLengthCm</th>\n",
       "      <th>SepalWidthCm</th>\n",
       "      <th>PetalLengthCm</th>\n",
       "      <th>PetalWidthCm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>5.7</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.2</td>\n",
       "      <td>1.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>4.4</td>\n",
       "      <td>2.9</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    SepalLengthCm  SepalWidthCm  PetalLengthCm  PetalWidthCm\n",
       "95            5.7           3.0            4.2           1.2\n",
       "8             4.4           2.9            1.4           0.2"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_X.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "_cell_guid": "ce373f86-18ae-095f-8629-5bb8307c1273",
    "_execution_state": "idle",
    "_uuid": "ad5d8e583245a888c9470ef155b7d69a5608d426"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>SepalLengthCm</th>\n",
       "      <th>SepalWidthCm</th>\n",
       "      <th>PetalLengthCm</th>\n",
       "      <th>PetalWidthCm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>5.5</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>144</th>\n",
       "      <td>6.7</td>\n",
       "      <td>3.3</td>\n",
       "      <td>5.7</td>\n",
       "      <td>2.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     SepalLengthCm  SepalWidthCm  PetalLengthCm  PetalWidthCm\n",
       "36             5.5           3.5            1.3           0.2\n",
       "144            6.7           3.3            5.7           2.5"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_X.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "_cell_guid": "60f7b821-4335-e2e5-b868-3d6f850ea927",
    "_execution_state": "idle",
    "_uuid": "6e5039b56dec20594cdd457127d39c0009f5572a"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "95     Iris-versicolor\n",
       "8          Iris-setosa\n",
       "131     Iris-virginica\n",
       "148     Iris-virginica\n",
       "105     Iris-virginica\n",
       "Name: Species, dtype: object"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_y.head()  ##output of the training data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "82010322-d6f3-467d-f1da-4cb3fc82d0bd",
    "_uuid": "41536ca3ef126cf761c2b8aca8f02ffa407a5996"
   },
   "source": [
    "### Support Vector Machine (SVM)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "_cell_guid": "be869394-0f6d-f062-dd1f-8d2c68f06104",
    "_execution_state": "idle",
    "_uuid": "94ed6a0a8a1acc6c42e37db3e50ab6f9380e17f8"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('The accuracy of the SVM is:', 0.97777777777777775)\n"
     ]
    }
   ],
   "source": [
    "model = svm.SVC() #select the algorithm\n",
    "model.fit(train_X,train_y) # we train the algorithm with the training data and the training output\n",
    "prediction=model.predict(test_X) #now we pass the testing data to the trained algorithm\n",
    "print('The accuracy of the SVM is:',metrics.accuracy_score(prediction,test_y))#now we check the accuracy of the algorithm. \n",
    "#we pass the predicted output by the model and the actual output"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "78e50a4b-ea63-c546-a8c4-07f4e4084c27",
    "_uuid": "9e9fb51ffb0823fb9a7459ad0f164e52a800c15a"
   },
   "source": [
    "SVM is giving very good accuracy . We will continue to check the accuracy for different models.\n",
    "\n",
    "Now we will follow the same steps as above for training various machine learning algorithms."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "35d98035-f0ae-7d10-fe90-ec13865c5a14",
    "_uuid": "a2d76e51ba5e61a1a6f19675295f4405c2633eba"
   },
   "source": [
    "### Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "_cell_guid": "ca772378-d3c4-4c87-ada6-b9d50a383b01",
    "_execution_state": "idle",
    "_uuid": "2b53cac02465732a986be2463b3f3411ab043716"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('The accuracy of the Logistic Regression is', 0.9555555555555556)\n"
     ]
    }
   ],
   "source": [
    "model = LogisticRegression()\n",
    "model.fit(train_X,train_y)\n",
    "prediction=model.predict(test_X)\n",
    "print('The accuracy of the Logistic Regression is',metrics.accuracy_score(prediction,test_y))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "7dfab2de-ebb7-4864-675c-aafef45db7a1",
    "_uuid": "756183a2d33bfd269b75b11ce7980f7f22925004"
   },
   "source": [
    "### Decision Tree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "_cell_guid": "f918247c-a76b-4c58-5145-1fb0e8ab70b4",
    "_execution_state": "idle",
    "_uuid": "3c8158a18da7910b9ba8c3a5169a3009fb27c84f"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('The accuracy of the Decision Tree is', 0.91111111111111109)\n"
     ]
    }
   ],
   "source": [
    "model=DecisionTreeClassifier()\n",
    "model.fit(train_X,train_y)\n",
    "prediction=model.predict(test_X)\n",
    "print('The accuracy of the Decision Tree is',metrics.accuracy_score(prediction,test_y))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "3e4594d9-5fe6-0568-1fc6-e02975278305",
    "_uuid": "3410b37d9410b8d9f0ebd5c6509b3250ed7714c1"
   },
   "source": [
    "### K-Nearest Neighbours"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "_cell_guid": "bcd55de7-cfab-c81d-25a8-1db8f0deee94",
    "_execution_state": "idle",
    "_uuid": "dda9e73ae95627994e68db9542d769b897d43bec"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('The accuracy of the KNN is', 0.97777777777777775)\n"
     ]
    }
   ],
   "source": [
    "model=KNeighborsClassifier(n_neighbors=3) #this examines 3 neighbours for putting the new data into a class\n",
    "model.fit(train_X,train_y)\n",
    "prediction=model.predict(test_X)\n",
    "print('The accuracy of the KNN is',metrics.accuracy_score(prediction,test_y))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "e6787513-11b0-5cdb-10ac-457292de9b55",
    "_uuid": "9cd754bcd0f4494014b69c4fe11d3b228b5eee3f"
   },
   "source": [
    "### Let's check the accuracy for various values of n for K-Nearest nerighbours"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "_cell_guid": "2c79e403-480a-0620-dd84-01ca038c72bd",
    "_execution_state": "idle",
    "_uuid": "abe2f8b04c14ad0618c13edd1777e7a8c2985781"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAD8CAYAAACb4nSYAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fa0f4fa08d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "a_index=list(range(1,11))\n",
    "a=pd.Series()\n",
    "x=[1,2,3,4,5,6,7,8,9,10]\n",
    "for i in list(range(1,11)):\n",
    "    model=KNeighborsClassifier(n_neighbors=i) \n",
    "    model.fit(train_X,train_y)\n",
    "    prediction=model.predict(test_X)\n",
    "    a=a.append(pd.Series(metrics.accuracy_score(prediction,test_y)))\n",
    "plt.plot(a_index, a)\n",
    "plt.xticks(x)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "de478d66-f9c6-6382-4a89-05c159bf657f",
    "_uuid": "0f1e3fad4a5403e758e4a3766c7887c65c9ab24b"
   },
   "source": [
    "Above is the graph showing the accuracy for the KNN models using different values of n. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "cd3deccf-1025-320b-a269-40a99c7dd3f5",
    "_uuid": "8ad86c41920a005f238e20d4a84585079d558d16"
   },
   "source": [
    "### We used all the features of iris in above models. Now we will use Petals and Sepals Seperately"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "74a20365-8410-1b88-5f76-522c73c39a09",
    "_uuid": "a5b27b547f5c0ad1ec8405aec1117e0e48180633"
   },
   "source": [
    "### Creating Petals And Sepals Training Data "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "_cell_guid": "80dc70f3-ad29-fc83-27d7-f378a32f0a46",
    "_execution_state": "idle",
    "_uuid": "a5c6805e5ea06a4f1c9bf2b4879e609b4951780b"
   },
   "outputs": [],
   "source": [
    "petal=iris[['PetalLengthCm','PetalWidthCm','Species']]\n",
    "sepal=iris[['SepalLengthCm','SepalWidthCm','Species']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "_cell_guid": "7048f50d-5ad5-3c48-3eaa-26a0f5bcb034",
    "_execution_state": "idle",
    "_uuid": "70b5ef63a17330a3d1f1d918831407bdf535e2bf"
   },
   "outputs": [],
   "source": [
    "train_p,test_p=train_test_split(petal,test_size=0.3,random_state=0)  #petals\n",
    "train_x_p=train_p[['PetalWidthCm','PetalLengthCm']]\n",
    "train_y_p=train_p.Species\n",
    "test_x_p=test_p[['PetalWidthCm','PetalLengthCm']]\n",
    "test_y_p=test_p.Species\n",
    "\n",
    "\n",
    "train_s,test_s=train_test_split(sepal,test_size=0.3,random_state=0)  #Sepal\n",
    "train_x_s=train_s[['SepalWidthCm','SepalLengthCm']]\n",
    "train_y_s=train_s.Species\n",
    "test_x_s=test_s[['SepalWidthCm','SepalLengthCm']]\n",
    "test_y_s=test_s.Species"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "c7bc7029-2397-93a9-e063-afb7c129af8d",
    "_uuid": "05ed84baa609e7379bcb84bdad50c60650b86e49"
   },
   "source": [
    "### SVM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "_cell_guid": "bf8b63a2-7f74-f2d3-3f42-fb480ae26139",
    "_execution_state": "idle",
    "_uuid": "2abd62b140e7918b900c05400372ff1b5f1b2e97"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('The accuracy of the SVM using Petals is:', 0.97777777777777775)\n",
      "('The accuracy of the SVM using Sepal is:', 0.80000000000000004)\n"
     ]
    }
   ],
   "source": [
    "model=svm.SVC()\n",
    "model.fit(train_x_p,train_y_p) \n",
    "prediction=model.predict(test_x_p) \n",
    "print('The accuracy of the SVM using Petals is:',metrics.accuracy_score(prediction,test_y_p))\n",
    "\n",
    "model=svm.SVC()\n",
    "model.fit(train_x_s,train_y_s) \n",
    "prediction=model.predict(test_x_s) \n",
    "print('The accuracy of the SVM using Sepal is:',metrics.accuracy_score(prediction,test_y_s))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "4fd9e81b-8aad-1e15-8b88-819112c17071",
    "_uuid": "1fea5c6c187d41fe71248597fff47e49621fd83d"
   },
   "source": [
    "### Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "_cell_guid": "8353f86a-d1fe-6f07-7eb5-4f651eba1197",
    "_execution_state": "idle",
    "_uuid": "f732c0dc0789acd023476ed80107c7a6f4ddeb71"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('The accuracy of the Logistic Regression using Petals is:', 0.68888888888888888)\n",
      "('The accuracy of the Logistic Regression using Sepals is:', 0.64444444444444449)\n"
     ]
    }
   ],
   "source": [
    "model = LogisticRegression()\n",
    "model.fit(train_x_p,train_y_p) \n",
    "prediction=model.predict(test_x_p) \n",
    "print('The accuracy of the Logistic Regression using Petals is:',metrics.accuracy_score(prediction,test_y_p))\n",
    "\n",
    "model.fit(train_x_s,train_y_s) \n",
    "prediction=model.predict(test_x_s) \n",
    "print('The accuracy of the Logistic Regression using Sepals is:',metrics.accuracy_score(prediction,test_y_s))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "d8905552-47ed-3654-6dcc-a9603fe2cd12",
    "_uuid": "8fff15cad2855cedd186d19af2e419c79a5e3e4f"
   },
   "source": [
    "### Decision Tree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "_cell_guid": "1383aeef-0009-c16c-3f2c-97d400de6282",
    "_execution_state": "idle",
    "_uuid": "973393361c06902445a5e8a2a6a1a3c3acdec967"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('The accuracy of the Decision Tree using Petals is:', 0.9555555555555556)\n",
      "('The accuracy of the Decision Tree using Sepals is:', 0.64444444444444449)\n"
     ]
    }
   ],
   "source": [
    "model=DecisionTreeClassifier()\n",
    "model.fit(train_x_p,train_y_p) \n",
    "prediction=model.predict(test_x_p) \n",
    "print('The accuracy of the Decision Tree using Petals is:',metrics.accuracy_score(prediction,test_y_p))\n",
    "\n",
    "model.fit(train_x_s,train_y_s) \n",
    "prediction=model.predict(test_x_s) \n",
    "print('The accuracy of the Decision Tree using Sepals is:',metrics.accuracy_score(prediction,test_y_s))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "0d1fcf97-a603-ef57-5085-fab9b931c186",
    "_uuid": "52cb931113963aa7790c83c8427f49e03f109a65"
   },
   "source": [
    "### K-Nearest Neighbours"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "_cell_guid": "89fc030a-1c30-ee0d-7c62-7495fa476dba",
    "_execution_state": "idle",
    "_uuid": "122bd22d9a7e63f0e1f86be80a2d2dde82182536"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('The accuracy of the KNN using Petals is:', 0.97777777777777775)\n",
      "('The accuracy of the KNN using Sepals is:', 0.73333333333333328)\n"
     ]
    }
   ],
   "source": [
    "model=KNeighborsClassifier(n_neighbors=3)\n",
    "model.fit(train_x_p,train_y_p) \n",
    "prediction=model.predict(test_x_p) \n",
    "print('The accuracy of the KNN using Petals is:',metrics.accuracy_score(prediction,test_y_p))\n",
    "\n",
    "model.fit(train_x_s,train_y_s) \n",
    "prediction=model.predict(test_x_s) \n",
    "print('The accuracy of the KNN using Sepals is:',metrics.accuracy_score(prediction,test_y_s))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "752b273a-43f6-9905-c42b-0a3003ad204c",
    "_uuid": "453bb5a7b5ee35d4dcbac52b6ee717d61d578c7f"
   },
   "source": [
    "### Observations:\n",
    "\n",
    " - Using Petals over Sepal for training the data gives a much better accuracy.\n",
    " - This was expected as we saw in the heatmap above that the correlation between the Sepal Width and Length was very low whereas the correlation between Petal Width and Length was very high. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "6e6e1e3a-07aa-201a-b959-1d3619103325",
    "_uuid": "0f45b63a88d023709700b04fd14605ae53c94550"
   },
   "source": [
    "Thus we have just implemented some of the common Machine Learning. Since the dataset is small with very few features, I didn't cover some concepts as they would be relevant when we have many features.\n",
    "\n",
    "I have compiled a notebook covering some advanced ML concepts using a larger dataset. Have a look at that tooo."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "66bef947-c001-01e6-3064-cec367662f19",
    "_execution_state": "idle",
    "_uuid": "f561aab5cae104858575057eb7f93e7e8abaa77e"
   },
   "source": [
    "I hope the notebook was useful to you to get started with Machine Learning.\n",
    "\n",
    "If  find this notebook, **Please Upvote**.\n",
    "\n",
    "Thank You!!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "_cell_guid": "14bcdd2b-fc7c-42e2-88c7-ed5d221ecbef",
    "_execution_state": "idle",
    "_uuid": "41c25d25019131c90859443d37b93d8fbb0fb33f"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "_change_revision": 0,
  "_is_fork": false,
  "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": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}