{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"text-align:center\">\n",
    "    <a href=\"https://skills.network\" target=\"_blank\">\n",
    "    <img src=\"https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/assets/logos/SN_web_lightmode.png\" width=\"200\" alt=\"Skills Network Logo\">\n",
    "    </a>\n",
    "</p>\n",
    "\n",
    "\n",
    "#  SVM (Support Vector Machines)\n",
    "\n",
    "\n",
    "Estimated time needed: **15** minutes\n",
    "    \n",
    "\n",
    "## Objectives\n",
    "\n",
    "After completing this lab you will be able to:\n",
    "\n",
    "* Use scikit-learn to Support Vector Machine to classify\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this notebook, you will use SVM (Support Vector Machines) to build and train a model using human cell records, and classify cells to whether the samples are benign or malignant.\n",
    "\n",
    "SVM works by mapping data to a high-dimensional feature space so that data points can be categorized, even when the data are not otherwise linearly separable. A separator between the categories is found, then the data is transformed in such a way that the separator could be drawn as a hyperplane. Following this, characteristics of new data can be used to predict the group to which a new record should belong.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h1>Table of contents</h1>\n",
    "\n",
    "<div class=\"alert alert-block alert-info\" style=\"margin-top: 20px\">\n",
    "    <ol>\n",
    "        <li><a href=\"#load_dataset\">Load the Cancer data</a></li>\n",
    "        <li><a href=\"#modeling\">Modeling</a></li>\n",
    "        <li><a href=\"#evaluation\">Evaluation</a></li>\n",
    "        <li><a href=\"#practice\">Practice</a></li>\n",
    "    </ol>\n",
    "</div>\n",
    "<br>\n",
    "<hr>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: scikit-learn in /opt/conda/lib/python3.12/site-packages (1.5.1)\n",
      "Requirement already satisfied: numpy>=1.19.5 in /opt/conda/lib/python3.12/site-packages (from scikit-learn) (1.26.4)\n",
      "Requirement already satisfied: scipy>=1.6.0 in /opt/conda/lib/python3.12/site-packages (from scikit-learn) (1.13.1)\n",
      "Requirement already satisfied: joblib>=1.2.0 in /opt/conda/lib/python3.12/site-packages (from scikit-learn) (1.4.2)\n",
      "Requirement already satisfied: threadpoolctl>=3.1.0 in /opt/conda/lib/python3.12/site-packages (from scikit-learn) (3.5.0)\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable.It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.\u001b[0m\u001b[33m\n",
      "\u001b[0mRequirement already satisfied: matplotlib in /opt/conda/lib/python3.12/site-packages (3.9.2)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in /opt/conda/lib/python3.12/site-packages (from matplotlib) (1.2.0)\n",
      "Requirement already satisfied: cycler>=0.10 in /opt/conda/lib/python3.12/site-packages (from matplotlib) (0.11.0)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in /opt/conda/lib/python3.12/site-packages (from matplotlib) (4.51.0)\n",
      "Requirement already satisfied: kiwisolver>=1.3.1 in /opt/conda/lib/python3.12/site-packages (from matplotlib) (1.4.4)\n",
      "Requirement already satisfied: numpy>=1.23 in /opt/conda/lib/python3.12/site-packages (from matplotlib) (1.26.4)\n",
      "Requirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.12/site-packages (from matplotlib) (24.1)\n",
      "Requirement already satisfied: pillow>=8 in /opt/conda/lib/python3.12/site-packages (from matplotlib) (10.4.0)\n",
      "Requirement already satisfied: pyparsing>=2.3.1 in /opt/conda/lib/python3.12/site-packages (from matplotlib) (3.1.2)\n",
      "Requirement already satisfied: python-dateutil>=2.7 in /opt/conda/lib/python3.12/site-packages (from matplotlib) (2.9.0.post0)\n",
      "Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.12/site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable.It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.\u001b[0m\u001b[33m\n",
      "\u001b[0mRequirement already satisfied: pandas in /opt/conda/lib/python3.12/site-packages (2.2.2)\n",
      "Requirement already satisfied: numpy>=1.26.0 in /opt/conda/lib/python3.12/site-packages (from pandas) (1.26.4)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/lib/python3.12/site-packages (from pandas) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.12/site-packages (from pandas) (2024.1)\n",
      "Requirement already satisfied: tzdata>=2022.7 in /opt/conda/lib/python3.12/site-packages (from pandas) (2023.3)\n",
      "Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable.It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.\u001b[0m\u001b[33m\n",
      "\u001b[0mRequirement already satisfied: numpy in /opt/conda/lib/python3.12/site-packages (1.26.4)\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable.It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.\u001b[0m\u001b[33m\n",
      "\u001b[0m"
     ]
    }
   ],
   "source": [
    "!pip install scikit-learn\n",
    "!pip install matplotlib\n",
    "!pip install pandas \n",
    "!pip install numpy \n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import pylab as pl\n",
    "import numpy as np\n",
    "import scipy.optimize as opt\n",
    "from sklearn import preprocessing\n",
    "from sklearn.model_selection import train_test_split\n",
    "%matplotlib inline \n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h2 id=\"load_dataset\">Load the Cancer data</h2>\n",
    "The example is based on a dataset that is publicly available from the UCI Machine Learning Repository (Asuncion and Newman, 2007)[http://mlearn.ics.uci.edu/MLRepository.html]. The dataset consists of several hundred human cell sample records, each of which contains the values of a set of cell characteristics. The fields in each record are:\n",
    "\n",
    "|Field name|Description|\n",
    "|--- |--- |\n",
    "|ID|Clump thickness|\n",
    "|Clump|Clump thickness|\n",
    "|UnifSize|Uniformity of cell size|\n",
    "|UnifShape|Uniformity of cell shape|\n",
    "|MargAdh|Marginal adhesion|\n",
    "|SingEpiSize|Single epithelial cell size|\n",
    "|BareNuc|Bare nuclei|\n",
    "|BlandChrom|Bland chromatin|\n",
    "|NormNucl|Normal nucleoli|\n",
    "|Mit|Mitoses|\n",
    "|Class|Benign or malignant|\n",
    "\n",
    "<br>\n",
    "<br>\n",
    "\n",
    "For the purposes of this example, we're using a dataset that has a relatively small number of predictors in each record. To download the data, we will use `!wget` to download it from IBM Object Storage.  \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "--2025-11-18 04:00:07--  https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-ML0101EN-SkillsNetwork/labs/Module%203/data/cell_samples.csv\n",
      "Resolving cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud (cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud)... 198.23.119.245\n",
      "Connecting to cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud (cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud)|198.23.119.245|:443... connected.\n",
      "HTTP request sent, awaiting response... 200 OK\n",
      "Length: 19975 (20K) [text/csv]\n",
      "Saving to: ‘cell_samples.csv’\n",
      "\n",
      "cell_samples.csv    100%[===================>]  19.51K  --.-KB/s    in 0.1s    \n",
      "\n",
      "2025-11-18 04:00:09 (188 KB/s) - ‘cell_samples.csv’ saved [19975/19975]\n",
      "\n"
     ]
    }
   ],
   "source": [
    "#Click here and press Shift+Enter\n",
    "!wget -O cell_samples.csv https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-ML0101EN-SkillsNetwork/labs/Module%203/data/cell_samples.csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load Data From CSV File  \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\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>Clump</th>\n",
       "      <th>UnifSize</th>\n",
       "      <th>UnifShape</th>\n",
       "      <th>MargAdh</th>\n",
       "      <th>SingEpiSize</th>\n",
       "      <th>BareNuc</th>\n",
       "      <th>BlandChrom</th>\n",
       "      <th>NormNucl</th>\n",
       "      <th>Mit</th>\n",
       "      <th>Class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1000025</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1002945</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>10</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1015425</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1016277</td>\n",
       "      <td>6</td>\n",
       "      <td>8</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1017023</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        ID  Clump  UnifSize  UnifShape  MargAdh  SingEpiSize BareNuc  \\\n",
       "0  1000025      5         1          1        1            2       1   \n",
       "1  1002945      5         4          4        5            7      10   \n",
       "2  1015425      3         1          1        1            2       2   \n",
       "3  1016277      6         8          8        1            3       4   \n",
       "4  1017023      4         1          1        3            2       1   \n",
       "\n",
       "   BlandChrom  NormNucl  Mit  Class  \n",
       "0           3         1    1      2  \n",
       "1           3         2    1      2  \n",
       "2           3         1    1      2  \n",
       "3           3         7    1      2  \n",
       "4           3         1    1      2  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cell_df = pd.read_csv(\"cell_samples.csv\")\n",
    "cell_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The ID field contains the patient identifiers. The characteristics of the cell samples from each patient are contained in fields Clump to Mit. The values are graded from 1 to 10, with 1 being the closest to benign.\n",
    "\n",
    "The Class field contains the diagnosis, as confirmed by separate medical procedures, as to whether the samples are benign (value = 2) or malignant (value = 4).\n",
    "\n",
    "Let's look at the distribution of the classes based on Clump thickness and Uniformity of cell size:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjMAAAGwCAYAAABcnuQpAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAA4eElEQVR4nO3deXhU5eH+/3sYlrBkI7JFAokkEQURFEwDFqEEwkfhcinaEqyi/WgrS0HqhlqrIKRaUVxaLOpXqEhsq2j9iDAmCAERIWzizy0LSUwFGk1Cwi4k8/sjZCQkZJ3Mmefk/bquuS7mOZOZ+3BmMneec86Mw+12uwUAAGCoNlYHAAAAaA7KDAAAMBplBgAAGI0yAwAAjEaZAQAARqPMAAAAo1FmAACA0dpaHaClVVRUaN++fQoMDJTD4bA6DgAAaAC3261Dhw4pPDxcbdrUPfdi+zKzb98+RUREWB0DAAA0QUFBgXr37l3nbWxfZgIDAyVV/mcEBQVZnAYAADREWVmZIiIiPO/jdbF9manatRQUFESZAQDAMA05RIQDgAEAgNEoMwAAwGiUGQAAYDTbHzPTUOXl5Tp58qTVMeBF7du3r/d0PgCA+Vp9mXG73Tpw4IAOHjxodRR4WZs2bRQVFaX27dtbHQUA0IJafZmpKjLdu3dXp06d+GA9m6j6sMT9+/erT58+bFcAsLFWXWbKy8s9RSYsLMzqOPCybt26ad++fTp16pTatWtndRwAQAtp1QcUVB0j06lTJ4uToCVU7V4qLy+3OAkAoCW16jJThV0Q9sR2BYDWgTIDAACMZmmZ2bhxoyZOnKjw8HA5HA6988471Za73W49+uijCg8PV8eOHTVq1Ch9/vnn1oQF0CiZmcVas2avsrJKrI7SLC5XrubN+1ipqXlWR4Hssz3s8vpYsGCLfvazf+hPf/rE0hyWHgB85MgRXXrppbrtttv085//vMbyJ598Uk8//bSWLVum2NhYPf744xo7dqy+/vrrBn3xFBpn6tSpOnjwoKdUjho1SoMHD9bixYstzQWzFBcfU1LSarlceZ6xxMRIpaRMUGhogHXBGiknp0Rxca+rqOi4ZywsLEAZGTcrKirEumCtlF22h11eHx9+mK+EhH/J7a68vn59gR588CNt2HCTRo7s4/M8ls7M/M///I8ef/xx3XDDDTWWud1uLV68WA899JBuuOEGDRw4UMuXL9fRo0e1cuVKC9K2PqtWrdL8+fOtjlGryMhISpafSkparbS0/GpjaWn5mjz5PYsSNc3Zb5ySVFR0XMOGrbAoUetml+1hl9fHmUWmitstjRr1T0vy+O0xM7m5uTpw4IDGjRvnGevQoYOuuuoqffzxx+f8uRMnTqisrKzaxRfsMmV4pq5duzIDhkbJzCyWy5Wn8vLqv+XKy91yufKMeX24XLk13jirFBUdN34Xh2nssj3s8vpYsGBLjSJTxe2WJbuc/LbMHDhwQJLUo0ePauM9evTwLKtNcnKygoODPZeIiIgWzVlcfEzjx7+pCy/8f7r66lWKjX1F48e/qZKS2l943jJq1CjNnDlTs2fPVmhoqHr06KGlS5fqyJEjuu222xQYGKh+/fppzZo1kipPT/71r3+tqKgodezYURdeeKGeffbZeh9j9uzZnuv79+/XNddco44dOyoqKkorV66sMUPicDj08ssv6/rrr1enTp0UExOjd99917O8ITmmTp2q6667Tk899ZR69eqlsLAwTZ8+3XMq/ahRo5Sfn6+7775bDoeDs5b8SE7OwTqXZ2eb8ct669b9dS7fsmWfj5JAss/2sMvrY926b+pc/sEH+XUubwl+W2aqnP1G5Xa763zzmjt3rkpLSz2XgoKCFs1n5ZTh8uXLdd5552nbtm2aOXOm7rrrLt14440aPny4du7cqcTERP3qV7/S0aNHVVFRod69e+uf//ynvvjiCz3yyCN68MEH9c9/NnxK8JZbbtG+ffu0YcMGvfXWW1q6dKkKCwtr3O6xxx7TTTfdpD179ujqq6/WlClTVFxcLEkNzrF+/Xrl5ORo/fr1Wr58uZYtW6Zly5ZJqtz91bt3b82bN0/79+/X/v11/6KD7/TrF1Ln8ujoUN8Eaaa4uF51Lo+PD/dREkj22R52eX2MGVP3MTHjxvX1UZIf+W2Z6dmzpyTVmIUpLCysMVtzpg4dOigoKKjapaVYPWV46aWX6uGHH1ZMTIzmzp2rjh076rzzztMdd9yhmJgYPfLIIyoqKtKePXvUrl07PfbYYxo2bJiioqI0ZcoUTZ06tcFl5quvvlJaWppeeuklxcXF6bLLLtPLL7+sY8eO1bjt1KlTNXnyZEVHR2vhwoU6cuSItm3bJkkNzhEaGqoXXnhB/fv314QJE3TNNddo3bp1kip3fzmdTgUGBqpnz56e5wqsFxvbVYmJkXI6q//B4XQ6lJgYqZgYM35ZJyZGKSys9oMxw8ICNHZspG8DtXJ22R52eX089FC8zjWn4HBIDzzwE98Gkh+XmaioKPXs2VOpqamesR9++EHp6ekaPny4hcl+ZPWU4aBBgzz/djqdCgsL0yWXXOIZqyp9VbMnL774ooYOHapu3bqpS5cueumll/TNN3VPF1b5+uuv1bZtW1122WWesejoaIWG1nzxnZmrc+fOCgwMrDaD05AcAwYMkNPp9Fzv1atXrbNA8D8pKROUkFD9L7OEhL5KSZlgUaKmyci4ucYbaNXZM/A9u2wPu7w+Nmy4qUahcTgqx61g6anZhw8fVnZ2tud6bm6udu/era5du6pPnz6aPXu2Fi5cqJiYGMXExGjhwoXq1KmTkpKSLEz9I6unDM/+viGHw1FtrGp3XEVFhf75z3/q7rvv1qJFixQfH6/AwED9+c9/1tatWxv0WO5zHO1V23htuSoqKiSpwTnqug/4t9DQAK1dO0lZWSXKzi5RdHSoMX9xnikqKkTffz9Dqal52rJln+Ljw42ZAbAju2wPu7w+Ro7so4qKe/SnP32iDz7I17hxfS2ZkaliaZnZvn27Ro8e7bk+Z84cSdKtt96qZcuW6b777tOxY8c0bdo0lZSUKC4uTh988IHfnGFTNWWYlpZfbVeT0+lQQkJfv3qCbtq0ScOHD9e0adM8Yzk5OQ3++f79++vUqVPatWuXLr/8cklSdna2Dh486NMcVdq3b893Lvm5mBgzf0mfbezYSCPfNO3KLtvDLq+PBx74iaUlpoqlu5lGjRolt9td41J1oKfD4dCjjz6q/fv36/jx40pPT9fAgQOtjFyDKVOG0dHR2r59u1wulzIzM/WHP/xBGRkZDf75/v37KyEhQXfeeae2bdumXbt26c4771THjh0bdTZRc3NUiYyM1MaNG/Xtt9/q+++/b/TPAwDsw2+PmTFF1ZRhZuav9f77Nygz89dau3aS332S429/+1vdcMMN+sUvfqG4uDgVFRVVmx1piL///e/q0aOHRo4cqeuvv1533HGHAgMDFRDQ8HX1Rg5JmjdvnvLy8tSvXz9169at0T8PALAPh/tcB0PYRFlZmYKDg1VaWlrjzKbjx48rNzdXUVFRjXpDRqX//Oc/ioiIUFpamsaMGWN1nBrYvgBgrrrev89m6TEzMMuHH36ow4cP65JLLtH+/ft13333KTIyUiNHjrQ6GgCgFaPMoMFOnjypBx98UHv37lVgYKCGDx+u119/vcaZRwAA+BJlBg2WmJioxMREq2MAAFANBwADAACjUWYAAIDRKDMAAMBolBkAAGA0ygwAADAaZcZQo0aN0uzZs1v0MaZOnarrrruuRR8DAIDm4tRsnNOzzz57zm/LBgDAX1BmcE7BwcFWRwAAoF7sZvKaTElrJGX57BFPnTqlGTNmKCQkRGFhYXr44Yc9Myk//PCD7rvvPp1//vnq3Lmz4uLitGHDBs/PLlu2TCEhIXK5XLrooovUpUsXjR8/Xvv37/fc5uzdTIcOHdKUKVPUuXNn9erVS88880yN3V2RkZFauHChbr/9dgUGBqpPnz5aunRpS/9XAABaMcpMsxVLGi/pQklXS4o9fb2kxR95+fLlatu2rbZu3arnnntOzzzzjF5++WVJ0m233abNmzfrjTfe0J49e3TjjTdq/Pjxysr6sWwdPXpUTz31lF577TVt3LhR33zzje65555zPt6cOXO0efNmvfvuu0pNTdWmTZu0c+fOGrdbtGiRhg4dql27dmnatGm666679NVXX3n/PwAAALGbyQuSJKWdNZYmabKktS36yBEREXrmmWfkcDh04YUX6rPPPtMzzzyjn/3sZ0pJSdF//vMfhYeHS5LuuecerV27Vq+++qoWLlwoqfK7ll588UX169dPkjRjxgzNmzev1sc6dOiQli9frpUrV3q+IfvVV1/13P+Zrr76ak2bNk2SdP/99+uZZ57Rhg0b1L9/f6//HwAAQJlplkxJrlrGy0+PZ0mKabFH/8lPfiKHw+G5Hh8fr0WLFmn79u1yu92KjY2tdvsTJ04oLCzMc71Tp06eIiNJvXr1UmFhYa2PtXfvXp08eVJXXHGFZyw4OFgXXnhhjdsOGjTI82+Hw6GePXue834BAGguykyz5NSzPFstWWbq4nQ6tWPHDjmdzmrjXbp08fz77G+7djgc5zx7qWr8zPJ05viZarvfioqKhocHAKARKDPN0q+e5dEt+uiffPJJjesxMTEaMmSIysvLVVhYqJ/+9Kdeeax+/fqpXbt22rZtmyIiIiRJZWVlysrK0lVXXeWVxwAAoCk4ALhZYiUlSnKeNe48Pd6yszIFBQWaM2eOvv76a6WkpOj555/XrFmzFBsbqylTpuiWW27RqlWrlJubq4yMDD3xxBN6//33m/RYgYGBuvXWW3Xvvfdq/fr1+vzzz3X77berTZs2NWZrAADwJWZmmi1FlQf7nnnsTMLp8ZZ1yy236NixY7riiivkdDo1c+ZM3XnnnZIqD859/PHH9fvf/17ffvutwsLCFB8fr6uvvrrJj/f000/rt7/9rSZMmKCgoCDdd999KigoUEBAgLdWCQCARnO4bf4Rr2VlZQoODlZpaamCgoKqLTt+/Lhyc3MVFRXlhTfkLFUeIxMtq46T8bUjR47o/PPP16JFi/TrX//a6jg1eHf7AgB8qa7377MxM+M1MbJ7idm1a5e++uorXXHFFSotLfWcxn3ttddanAwA0JpRZtAoTz31lL7++mu1b99el19+uTZt2qTzzjvP6lgAgFaMMoMGGzJkiHbs2GF1DAAAquFsJgAAYDTKjGr/4DeYj+0KAK1Dqy4zVZ9Ue/ToUYuToCX88MMPklTjU5ABAPbSqo+ZcTqdCgkJ8XxvUKdOnfgAOJuoqKjQd999p06dOqlt21b9NAcA22v1v+V79uwpSXwRog21adNGffr0oaACgM21+jLjcDjUq1cvde/eXSdPnrQ6Dryoffv2atOmVe9JBYBWodWXmSpOp5NjKwAAMBB/tgIAAKNRZgAAgNEoMwAAwGiUGQAAYDTKDAAAMBplBgAAGI0yAwAAjEaZAQAARqPMAAAAo1FmAACA0SgzAADAaJQZAABgNMoMAAAwGmUGAAAYjTIDAACMRpkBAABGo8wAAACjUWYAAIDRKDMAAMBolBkAAGA0ygwAADAaZQYAABiNMgMAAIxGmQEAAEajzAAAAKNRZgAAgNEoMwAAwGiUGQAAYDTKDAAAMBplBgAAGI0yAwAAjEaZAQAARvPrMnPq1Ck9/PDDioqKUseOHXXBBRdo3rx5qqiosDoagFYjU9IaSVlWB2mWzMxirVmzV1lZJVZHAbyurdUB6vLEE0/oxRdf1PLlyzVgwABt375dt912m4KDgzVr1iyr4wGwtWJJSZJcZ4wlSkqRFGpJoqYoLj6mpKTVcrnyPGOJiZFKSZmg0NAA64IBXuTXMzNbtmzRtddeq2uuuUaRkZGaNGmSxo0bp+3bt1sdDYDtJUlKO2ssTdJkC7I0XVLSaqWl5VcbS0vL1+TJ71mUCPA+vy4zV155pdatW6fMzExJ0qeffqqPPvpIV1999Tl/5sSJEyorK6t2AYDGyVTljEz5WePlp8fN2OWUmVkslytP5eXuauPl5W65XHnscoJt+PVupvvvv1+lpaXq37+/nE6nysvLtWDBAk2efO6/jJKTk/XYY4/5MCUA+8mpZ3m2pBhfBGmWnJyDdS7Pzi5RTIw5u8yAc/HrmZl//OMfWrFihVauXKmdO3dq+fLleuqpp7R8+fJz/szcuXNVWlrquRQUFPgwMQB76FfP8mifpGiufv1C6lweHU2RgT349czMvffeqwceeEC//OUvJUmXXHKJ8vPzlZycrFtvvbXWn+nQoYM6dOjgy5gAbCdWlQf7pqn6rianpASZMCsjSbGxXZWYGKm0tPxqu5qcTocSEvoyKwPb8OuZmaNHj6pNm+oRnU4np2YD8IEUVRaXMyWcHjdHSsoEJST0rTaWkNBXKSkTLEoEeJ9fz8xMnDhRCxYsUJ8+fTRgwADt2rVLTz/9tG6//XarowGwvVBJa1V5sG+2KnctmTEjc6bQ0ACtXTtJWVklys4uUXR0KDMysB2H2+12138zaxw6dEh/+MMf9Pbbb6uwsFDh4eGaPHmyHnnkEbVv375B91FWVqbg4GCVlpYqKCiohRMDAABvaMz7t1+XGW+gzAAAYJ7GvH/79TEzAAAA9aHMAAAAo1FmAACA0SgzAADAaJQZAABgNMoMAAAwGmUGAAAYjTIDAACMRpkBAABGo8wAAACjUWYAAIDRKDMAAMBolBkAAGA0ygwAADAaZQYAABiNMgMAAIxGmQEAAEajzAAAAKNRZgAAgNEoMwAAwGiUGQAAYDTKDAAAMBplBgAAGI0yAwAAjEaZAQAARqPMAAAAo7W1OgDgLZmZxcrJOajo6FDFxIRaHQdAC+B17l9crlxt3bpf8fHhGjs20rIclBkYr7j4mJKSVsvlyvOMJSZGKiVlgkJDA6wLBsBreJ37l5ycEsXFva6iouOesbCwAGVk3KyoqBCf52E3E4yXlLRaaWn51cbS0vI1efJ7FiUC4G28zv3L2UVGkoqKjmvYsBWW5KHMwGiZmcVyufJUXu6uNl5e7pbLlaesrBKLkgHwFl7n/sXlyq1RZKoUFR1XamqebwOJMgPD5eQcrHN5dja/5ADT8Tr3L1u37q9z+ZYt+3yU5EeUGRitX7+QOpdHR3OAIGA6Xuf+JS6uV53L4+PDfZTkR5QZGC02tqsSEyPldDqqjTudDiUmRnK2A2ADvM79S2JilMLCaj/oOiwswJKzmigzMF5KygQlJPStNpaQ0FcpKRMsSgTA23id+5eMjJtrFJqqs5ms4HC73e76b2ausrIyBQcHq7S0VEFBQVbHQQvKyipRdnYJnz8B2Bivc/+SmpqnLVv2tcjnzDTm/ZsyAwAA/E5j3r/ZzQQAAIxGmQEAAEajzAAAAKNRZgAAgNEoMwAAwGiUGQAAYDTKDAAAMBplBgAAGI0yAwAAjEaZAQAARqPMAAAAo1FmAACA0SgzAADAaJQZAABgNMoMAAAwGmUGAAAYjTIDAACMRpkBAABGo8wAAACjUWYAAIDRKDMAAMBolBkAAGA0ygwAADAaZQYAABiNMgMAAIxGmQEAAEZrcpnJycnRww8/rMmTJ6uwsFCStHbtWn3++edeCwcAAFCfJpWZ9PR0XXLJJdq6datWrVqlw4cPS5L27NmjP/7xj14NCDRUZmax1qzZq6ysEqujQHbaHpmS1kjKsjoIbMQurw+XK1fz5n2s1NQ8S3O0bcoPPfDAA3r88cc1Z84cBQYGesZHjx6tZ5991mvhJOnbb7/V/fffrzVr1ujYsWOKjY3VK6+8ossvv9yrjwNzFRcfU1LSarlceZ6xxMRIpaRMUGhogHXBWin7bI9iSUmSXGeMJUpKkRRqSSKYzy6vj5ycEsXFva6iouOesbCwAGVk3KyoqBCf52nSzMxnn32m66+/vsZ4t27dVFRU1OxQVUpKSjRixAi1a9dOa9as0RdffKFFixYpJCTEa48B8yUlrVZaWn61sbS0fE2e/J5FiVo3+2yPJElpZ42lSZpsQRbYhV1eH2cXGUkqKjquYcNWWJKnSTMzISEh2r9/v6KioqqN79q1S+eff75XgknSE088oYiICL366quescjIyDp/5sSJEzpx4oTnellZmdfywP9kZhZX+wunSnm5Wy5XnrKyShQTw1/RvmKf7ZGp6jMyVcpPj2dJivFpIpjPLq8Plyu3RpGpUlR0XKmpeRo7NtKnmZo0M5OUlKT7779fBw4ckMPhUEVFhTZv3qx77rlHt9xyi9fCvfvuuxo6dKhuvPFGde/eXUOGDNFLL71U588kJycrODjYc4mIiPBaHvifnJyDdS7PzjZ7f7Rp7LM9cupZnu2TFLAXu7w+tm7dX+fyLVv2+SjJj5pUZhYsWKA+ffro/PPP1+HDh3XxxRdr5MiRGj58uB5++GGvhdu7d6+WLFmimJgYuVwu/fa3v9Xvfvc7/f3vfz/nz8ydO1elpaWeS0FBgdfywP/06xdS5/LoaP//K8dO7LM9+tWzPNonKWAvdnl9xMX1qnN5fHy4j5L8yOF2u91N/eGcnBzt2rVLFRUVGjJkiGJivDvt2r59ew0dOlQff/yxZ+x3v/udMjIytGXLlgbdR1lZmYKDg1VaWqqgoCCv5oN/GD/+TaWl5au8/MenstPpUEJCX61dO8nCZK2TfbbHeFUeI1N+xphTUoKktZYkgvns8vo477wXat3VFBYWoO+/n+GVx2jM+3eTZmY2btyowsJC9evXT5MmTdJNN92kmJgYnTx5Uhs3bmxS6Nr06tVLF198cbWxiy66SN98843XHgPmS0mZoISEvtXGEhL6KiVlgkWJWjf7bI8UVRaXMyWcHgeaxi6vj4yMmxUWVv3sq6qzmazQpJmZNm3aqEePHlq1apXi4+M94//9738VHh6u8vLyOn664ZKSklRQUKBNmzZ5xu6++25t3bq12mxNXZiZaT2yskqUnV2i6OhQIw6iszv7bI8sVR4jEy0O+oW32OX1kZqapy1b9ik+PtzrB/025v27yWVm1qxZ+tvf/qa//vWvmjp1qqTKMtOrVy9VVFQ0KfjZMjIyNHz4cD322GO66aabtG3bNt1xxx1aunSppkyZ0qD7oMwAAGCeFt/N5HA4NHfuXK1YsUIzZ87UnDlzVNWJHA5HU+6yVsOGDdPbb7+tlJQUDRw4UPPnz9fixYsbXGQAAID9NXlm5sCBA+revbt27dqla6+9VhdffLGeffZZXXzxxV7bzeQNzMwAAGCeFp+ZOdOQIUO0bds2HTx4UGPGjGnu3QEAADRKk8rMrbfeqo4dO3qu9+zZU+np6RozZoz69OnjtXAAAAD1adbnzJiA3UwAAJinMe/fDf5upj179mjgwIFq06aN9uzZU+dtBw0a1NC7BQAAaJYGl5nBgwd7DvodPHiwHA6HzpzUqbrucDj86gBgAABgbw0uM7m5uerWrZvn3wAAAP6gwWWmb9++tf4bAADASo06myk7O1s7duyoNrZu3TqNHj1aV1xxhRYuXOjVcAAAAPVpVJm599579c4773iu5+bmauLEiWrfvr3i4+OVnJysxYsXezkiAADAuTV4N5Mkbd++Xffdd5/n+uuvv67Y2Fi5XC5JlWcxPf/885o9e7ZXQwIAAJxLo2Zmvv/+e/Xu3dtzff369Zo4caLn+qhRo5SXl+e1cAAAAPVpVJnp2rWr9u/fL0mqqKjQ9u3bFRcX51n+ww8/yOafwQcAAPxMo8rMVVddpfnz56ugoECLFy9WRUWFRo8e7Vn+xRdfKDIy0tsZAQAAzqlRx8wsWLBAY8eOVd++feV0OvXcc8+pc+fOnuWvvfaafvazn3k9JAAAwLk0uMyUlZUpKipKX375pb744gt169ZN4eHh1W7z2GOPVTumBgAAoKU1eDdTaGioCgsL1a5dO919993q1KlTjdtceumlCgsL82pAAACAujS4zHTp0kVFRUWSpA0bNujkyZMtFgoAAKChGrybKSEhQaNHj9ZFF10kSbr++uvVvn37Wm/74YcfeicdAABAPRpcZlasWKHly5crJydH6enpGjBgQK27mgAAAHzJ4W7CB8OMHj1ab7/9tkJCQlogkneVlZUpODhYpaWlCgoKsjoOAABogMa8fzfq1Owq69evb1IwAAAAb2twmZkzZ47mz5+vzp07a86cOXXe9umnn252MAAAgIZocJnZtWuX5wymXbt2nfN2Doej+akAAAAaqEnHzJiEY2YAADBPY96/G/XdTAAAAP6mSQcAHzlyRH/605+0bt06FRYWqqKiotryvXv3eiUcAABAfZpUZv73f/9X6enp+tWvfqVevXpxnIzhMjOLlZNzUNHRoYqJCbU6TpPZZT3sgu3hX9ge/sXlytXWrfsVHx+usWMjrY7TZP6yHk0qM2vWrNHq1as1YsQIb+eBDxUXH1NS0mq5XHmescTESKWkTFBoaIB1wRrJLuthF2wP/8L28C85OSWKi3tdRUXHPWNhYQHKyLhZUVEh1gVrJH9bjyYdMxMaGqquXbt6Owt8LClptdLS8quNpaXla/Lk9yxK1DR2WQ+7YHv4F7aHfzm7AEhSUdFxDRu2wqJETeNv69GkMjN//nw98sgjOnr0qLfzwEcyM4vlcuWpvLz6yWzl5W65XHnKyiqxKFnj2GU97ILt4V/YHv7F5cqtUQCqFBUdV2pqnm8DNZE/rkeTysyiRYvkcrnUo0cPXXLJJbrsssuqXeD/cnIO1rk8O9uMX3J2WQ+7YHv4F7aHf9m6dX+dy7ds2eejJM3jj+vRpGNmrr32Wg76NVy/fiF1Lo+ONuMAQbush12wPfwL28O/xMX1qnN5fHy4j5I0jz+uR5PKzKOPPurlGPC12NiuSkyMVFpafrUpaKfToYSEvsac7WCX9bALtod/YXv4l8TEKIWFBdS6iyYsLMCYs5r8cT0atZupTZs2cjqdNS6hoaH6yU9+olWrVrVUTrSAlJQJSkjoW20sIaGvUlImWJSoaeyyHnbB9vAvbA//kpFxs8LCqp9FVnUWkEn8bT0a9XUG//73v2sdP3jwoLZt26ZXX31Vy5cv14033ui1gM3F1xnULyurRNnZJcZ//oRd1sMu2B7+he3hX1JT87Rlyz7LP5+luVpyPRrz/u3V72b6y1/+or///e/aunWrt+6y2SgzAACYx7LvZho3bpwyMzO9eZcAAAB18mqZOXbsmAIC+ERJAADgO14tMy+99JKGDBnizbsEAACoU6NOzZ4zZ06t46Wlpdq+fbtycnK0adMmrwQDAABoiEaVmV27dtU6HhQUpPHjx2vatGnq27dvrbcBAABoCY0qM+vXr2+pHAAAAE3i1WNmAAAAfI0yAwAAjEaZAQAARqPMAAAAo1FmAACA0SgzAADAaJQZAABgNMoMAAAwGmUGAAAYjTIDAACMRpkBAABGo8wAAACjUWYAAIDRKDMAAMBolBkAAGA0ygwAADAaZQYAABiNMgMAAIxGmQEAAEajzAAAAKNRZgAAgNGMKjPJyclyOByaPXu21VEA1CM3d5syMv6f8vK2Wx0FkjIzi7VmzV5lZZVYHaVZWA//4nLlat68j5WammdpjraWPnojZGRkaOnSpRo0aJDVUQDUoaTkW+XkXKOhQz9VVFTl2Pbtlyo6eo1CQnpZG64VKi4+pqSk1XK58jxjiYmRSkmZoNDQAOuCNRLr4V9yckoUF/e6ioqOe8bCwgKUkXGzoqJCfJ7HiJmZw4cPa8qUKXrppZcUGhpqdRwAdcjJuUaDB++pNjZ48B5lZ/+PRYlat6Sk1UpLy682lpaWr8mT37MoUdOwHv7l7CIjSUVFxzVs2ApL8hhRZqZPn65rrrlGCQkJ9d72xIkTKisrq3YB4Bu5uds0dOinatvWXW28bVu3hg79lF1OPpaZWSyXK0/l5dW3R3m5Wy5XnjG7OFgP/+Jy5dYoMlWKio5bssvJ78vMG2+8oZ07dyo5OblBt09OTlZwcLDnEhER0cIJAVT5/vv/r87l3323p87l8K6cnIN1Ls/ONuPNk/XwL1u37q9z+ZYt+3yU5Ed+XWYKCgo0a9YsrVixQgEBDduXOHfuXJWWlnouBQUFLZwSQJXzzhtY5/Ju3TjmzZf69Qupc3l0tBm77VkP/xIXV/exb/Hx4T5K8iO/LjM7duxQYWGhLr/8crVt21Zt27ZVenq6nnvuObVt21bl5eU1fqZDhw4KCgqqdgHgG1FRV2j79kt16pSj2vipUw5t336pIiOHWpSsdYqN7arExEg5ndW3h9PpUGJipGJizHjzZD38S2JilMLCap9gCAsL0Nixkb4NJD8vM2PGjNFnn32m3bt3ey5Dhw7VlClTtHv3bjmdTqsjAjhLdPQa7d5dfQZm9+5Bio5eY1Gi1i0lZYISEvpWG0tI6KuUlAkWJWoa1sO/ZGTcXKPQVJ3NZAWH2+12138z/zFq1CgNHjxYixcvbtDty8rKFBwcrNLSUmZpAB/Ky9uu777bo27dBjEj4weyskqUnV2i6OhQY2YAasN6+JfU1Dxt2bJP8fHhXp+Racz7N2UGAAD4nca8fxvzoXlVNmzYYHUEAADgR/z6mBkAAID6UGYAAIDRKDMAAMBolBkAAGA0ygwAADAaZQYAABiNMgMAAIxGmQEAAEajzAAAAKNRZgAAgNEoMwAAwGiUGQAAYDTKDAAAMBplBgAAGI0yAwAAjEaZAQAARqPMAAAAo1FmAACA0SgzAADAaJQZAABgNMoMAAAwGmUGAAAYjTIDAACMRpkBAABGo8wAAACjUWYAAIDR2lodwGyZknIkRUuKsThL02VmFisn56Cio0MVExNqdZwms8t62MWSJf9Qfv4uRUVdrt/85kar4zSZXZ5XLleutm7dr/j4cI0dG2l1nCazy/awC395XlFmmqRYUpIk1xljiZJSJJnz4iouPqakpNVyufI8Y4mJkUpJmaDQ0ADrgjWSXdbDLjZu/FRHj96ku+7K9IytXRuroKA3NXz4JRYmaxy7PK9yckoUF/e6ioqOe8bCwgKUkXGzoqJCrAvWSHbZHnbhb88rdjM1SZKktLPG0iRNtiBL0yUlrVZaWn61sbS0fE2e/J5FiZrGLuthF0eP3qSEhKxqYwkJWSorm2RRoqaxy/Pq7DccSSoqOq5hw1ZYlKhp7LI97MLfnleUmUbLVOWMTPlZ4+Wnx7Nq/IQ/yswslsuVp/Jyd7Xx8nK3XK48ZWWVWJSsceyyHnaxZMk/NH58ptq2rb492rZ1a/z4TP3tb/+yKFnj2OV55XLl1njDqVJUdFypqXm+DdREdtkeduGPzyvKTKPl1LM82ycpmisn52Cdy7OzzfjlYJf1sIv8/F11Ls/N3eGjJM1jl+fV1q3761y+Zcs+HyVpHrtsD7vwx+cVZabR+tWzPNonKZqrX7+QOpdHR5tx7I9d1sMu+vYdUufyqKjLfZSkeezyvIqL61Xn8vj4cB8laR67bA+78MfnFWWm0WJVebCv86xx5+lxM85qio3tqsTESDmdjmrjTqdDiYmRxpwlYJf1sIu77vqF1q6N1alT1bfHqVMOrV0ba8xZTXZ5XiUmRiksrPaDY8PCAow5q8ku28Mu/PF5RZlpkhRJCWeNJZweN0dKygQlJPStNpaQ0FcpKRMsStQ0dlkPuwgKelNpadVLfVpajIKC3rQoUdPY5XmVkXFzjTeeqrNOTGKX7WEX/va8crjdbnf9NzNXWVmZgoODVVpaqqCgIC/fe5Yqj5Ex+3NmsrJKlJ1dYvznNthlPezib3/7l3Jzdxj/OTN2eV6lpuZpy5Z9ln8eSHPZZXvYRUs+rxrz/k2ZAQAAfqcx79/sZgIAAEajzAAAAKNRZgAAgNEoMwAAwGiUGQAAYDTKDAAAMBplBgAAGI0yAwAAjEaZAQAARqPMAAAAo1FmAACA0SgzAADAaJQZAABgNMoMAAAwGmUGAAAYjTIDAACMRpkBAABGo8wAAACjUWYAAIDRKDMAAMBolBkAAGA0ygwAADAaZQYAABiNMgMAAIxGmQEAAEajzAAAAKNRZgAAgNEoMwAAwGh+XWaSk5M1bNgwBQYGqnv37rruuuv09ddfWx3LhjIlrZGUZXWQZmI9/MmmTeu0cuUibd683uoozWSP7WEXLleu5s37WKmpeVZHgR9pa3WAuqSnp2v69OkaNmyYTp06pYceekjjxo3TF198oc6dO1sdzwaKJSVJcp0xligpRVKoJYmahvXwJ7m5e7V37wSNGfOlZ2zduosUHf2++vaNtC5Yo9lje9hFTk6J4uJeV1HRcc9YWFiAMjJuVlRUiHXB4BccbrfbbXWIhvruu+/UvXt3paena+TIkQ36mbKyMgUHB6u0tFRBQUEtnNA04yWlSSo/Y8wpKUHSWksSNQ3r4U/WrbtYV131ldq2/fFXy6lTDqWn99eYMV9YmKyx7LE97OK8816oVmSqhIUF6PvvZ1iQCC2tMe/ffr2b6WylpaWSpK5du57zNidOnFBZWVm1C2qTqcq/OMvPGi8/PW7KlDrr4U82bVqnMWO+rFZkJKltW7fGjPnSoF1O9tgeduFy5dZaZCSpqOg4u5xgTplxu92aM2eOrrzySg0cOPCct0tOTlZwcLDnEhER4cOUJsmpZ3m2T1I0H+vhTwoKdte5PD9/p2+CNJs9toddbN26v87lW7bs81ES+CtjysyMGTO0Z88epaSk1Hm7uXPnqrS01HMpKCjwUULT9KtnebRPUjQf6+FPIiIG17m8b9/LfBOk2eyxPewiLq5Xncvj48N9lAT+yogyM3PmTL377rtav369evfuXedtO3TooKCgoGoX1CZWlQczOs8ad54ej/F5oqZhPfzJT386RuvWXaRTpxzVxk+dcmjduos0YsRoi5I1lj22h10kJkYpLCyg1mVhYQEaOzbSt4Hgd/y6zLjdbs2YMUOrVq3Shx9+qKioKKsj2UyKKg9mPFPC6XGTsB7+JDr6faWn9682lp7eX9HR71uUqKnssT3sIiPj5hqFpupsJsCvz2aaNm2aVq5cqX//+9+68MILPePBwcHq2LFjg+6Ds5kaIkuVxwBEy+y/OFkPf7J583rl5+9U376XGTQjUxt7bA+7SE3N05Yt+xQfH86MjM015v3br8uMw+GodfzVV1/V1KlTG3QflBkAAMzTmPdvv/7QPD/uWQAAwE/49TEzAAAA9aHMAAAAo1FmAACA0SgzAADAaJQZAABgNMoMAAAwGmUGAAAYjTIDAACMRpkBAABGo8wAAACjUWYAAIDRKDMAAMBolBkAAGA0ygwAADAaZQYAABiNMgMAAIxGmQEAAEajzAAAAKNRZgAAgNEoMwAAwGiUGQAAYDTKDAAAMBplBgAAGI0yAwAAjEaZAQAARqPMAAAAo1FmmiVClf+FfawO0kzDJXWWdKXVQZrpekk9JE2yOkgz2WU9XpH0K0nLLM7RXJmS1kjKsjoIgHOgzDTJrZIckv4jyS2p4PT1O60M1QTzVJl7i6Sjkjafvv4nK0M1wRJV5n5HUqGkt05ff8XCTE1hl/XYIam9pP+VtELSbaev77YwU1MUSxov6UJJV0uKPX29xMpQAGrhcLvdbqtDtKSysjIFBwertLRUQUFBXrpXRx3LTPrvZD38i13Wo72kk7WMt5P0g4+zNMd4SWmSys8Yc0pKkLTWkkRAa9KY929mZhotop7lpuxyGl7PclN2OV1fz3JTdtXYZT1eUe1FRqfHl/kuSrNkSnKpepHR6esuscsJ8C+UmUb7tp7l//FJiub7tJ7lu3ySovk+rmf5Jp+kaD67rMeGepav80UIL8ipZ3m2T1IAaBjKTKOdX8/y3j5J0XyX1rN8iE9SNF99M0w/9UmK5rPLeoyqZ/kYX4Twgn71LI/2SQoADcMxM01il2MbWA//Ypf14JgZAM3HMTMt7o5Gjvur5EaO+6uXGznur+yyHttUWVzO1O70uElSVFlczpRwehyAP2Fmpln6qPIYmd6SvvHyffvSlao8RmaIpI8sztIck1R5bMlPJb1pcZbmsMt6LFPlMTJjJE21NEnzZKnyGJloSTEWZwFaj8a8f1NmAACA32E3EwAAaDUoMwAAwGiUGQAAYDTKDAAAMBplBgAAGI0yAwAAjEaZAQAARqPMAAAAo1FmAACA0SgzAADAaG2tDtDSqr6toayszOIkAACgoaretxvyrUu2LzOHDh2SJEVERFicBAAANNahQ4cUHBxc521s/0WTFRUV2rdvnwIDA+VwOKyO45fKysoUERGhgoICvozTD7A9/Avbw7+wPfxLS24Pt9utQ4cOKTw8XG3a1H1UjO1nZtq0aaPevXtbHcMIQUFB/HLwI2wP/8L28C9sD//SUtujvhmZKhwADAAAjEaZAQAARqPMQB06dNAf//hHdejQweooENvD37A9/Avbw7/4y/aw/QHAAADA3piZAQAARqPMAAAAo1FmAACA0SgzAADAaJSZVio5OVnDhg1TYGCgunfvruuuu05ff/211bFwWnJyshwOh2bPnm11lFbt22+/1c0336ywsDB16tRJgwcP1o4dO6yO1SqdOnVKDz/8sKKiotSxY0ddcMEFmjdvnioqKqyO1ips3LhREydOVHh4uBwOh955551qy91utx599FGFh4erY8eOGjVqlD7//HOf5aPMtFLp6emaPn26PvnkE6WmpurUqVMaN26cjhw5YnW0Vi8jI0NLly7VoEGDrI7SqpWUlGjEiBFq166d1qxZoy+++EKLFi1SSEiI1dFapSeeeEIvvviiXnjhBX355Zd68skn9ec//1nPP/+81dFahSNHjujSSy/VCy+8UOvyJ598Uk8//bReeOEFZWRkqGfPnho7dqzn+xFbGqdmQ5L03XffqXv37kpPT9fIkSOtjtNqHT58WJdddpn++te/6vHHH9fgwYO1ePFiq2O1Sg888IA2b96sTZs2WR0FkiZMmKAePXrolVde8Yz9/Oc/V6dOnfTaa69ZmKz1cTgcevvtt3XddddJqpyVCQ8P1+zZs3X//fdLkk6cOKEePXroiSee0G9+85sWz8TMDCRJpaWlkqSuXbtanKR1mz59uq655holJCRYHaXVe/fddzV06FDdeOON6t69u4YMGaKXXnrJ6lit1pVXXql169YpMzNTkvTpp5/qo48+0tVXX21xMuTm5urAgQMaN26cZ6xDhw666qqr9PHHH/skg+2/aBL1c7vdmjNnjq688koNHDjQ6jit1htvvKGdO3cqIyPD6iiQtHfvXi1ZskRz5szRgw8+qG3btul3v/udOnTooFtuucXqeK3O/fffr9LSUvXv319Op1Pl5eVasGCBJk+ebHW0Vu/AgQOSpB49elQb79Gjh/Lz832SgTIDzZgxQ3v27NFHH31kdZRWq6CgQLNmzdIHH3yggIAAq+NAUkVFhYYOHaqFCxdKkoYMGaLPP/9cS5YsocxY4B//+IdWrFihlStXasCAAdq9e7dmz56t8PBw3XrrrVbHgyp3P53J7XbXGGsplJlWbubMmXr33Xe1ceNG9e7d2+o4rdaOHTtUWFioyy+/3DNWXl6ujRs36oUXXtCJEyfkdDotTNj69OrVSxdffHG1sYsuukhvvfWWRYlat3vvvVcPPPCAfvnLX0qSLrnkEuXn5ys5OZkyY7GePXtKqpyh6dWrl2e8sLCwxmxNS+GYmVbK7XZrxowZWrVqlT788ENFRUVZHalVGzNmjD777DPt3r3bcxk6dKimTJmi3bt3U2QsMGLEiBofV5CZmam+fftalKh1O3r0qNq0qf6W5XQ6OTXbD0RFRalnz55KTU31jP3www9KT0/X8OHDfZKBmZlWavr06Vq5cqX+/e9/KzAw0LPPMzg4WB07drQ4XesTGBhY43ilzp07KywsjOOYLHL33Xdr+PDhWrhwoW666SZt27ZNS5cu1dKlS62O1ipNnDhRCxYsUJ8+fTRgwADt2rVLTz/9tG6//Xaro7UKhw8fVnZ2tud6bm6udu/era5du6pPnz6aPXu2Fi5cqJiYGMXExGjhwoXq1KmTkpKSfBPQjVZJUq2XV1991epoOO2qq65yz5o1y+oYrdr//d//uQcOHOju0KGDu3///u6lS5daHanVKisrc8+aNcvdp08fd0BAgPuCCy5wP/TQQ+4TJ05YHa1VWL9+fa3vGbfeeqvb7Xa7Kyoq3H/84x/dPXv2dHfo0ME9cuRI92effeazfHzODAAAMBrHzAAAAKNRZgAAgNEoMwAAwGiUGQAAYDTKDAAAMBplBgAAGI0yAwAAjEaZAQAARqPMAPArDodD77zzjtUxABiEMgPApw4cOKCZM2fqggsuUIcOHRQREaGJEydq3bp1VkcDYCi+aBKAz+Tl5WnEiBEKCQnRk08+qUGDBunkyZNyuVyaPn26vvrqK6sjAjAQMzMAfGbatGlyOBzatm2bJk2apNjYWA0YMEBz5szRJ598UuP2GzZskMPh0MGDBz1ju3fvlsPhUF5eniRp2bJlCgkJ0XvvvacLL7xQnTp10qRJk3TkyBEtX75ckZGRCg0N1cyZM1VeXu65n8jISM2fP19JSUnq0qWLwsPD9fzzz7f0fwGAFkCZAeATxcXFWrt2raZPn67OnTvXWB4SEtLk+z569Kiee+45vfHGG1q7dq02bNigG264Qe+//77ef/99vfbaa1q6dKnefPPNaj/35z//WYMGDdLOnTs1d+5c3X333UpNTW1yDgDWYDcTAJ/Izs6W2+1W//79vX7fJ0+e1JIlS9SvXz9J0qRJk/Taa6/pv//9r7p06aKLL75Yo0eP1vr16/WLX/zC83MjRozQAw88IEmKjY3V5s2b9cwzz2js2LFezwig5TAzA8An3G63pMqzlbytU6dOniIjST169FBkZKS6dOlSbaywsLDaz8XHx9e4/uWXX3o9H4CWRZkB4BMxMTFyOByNKgtt2lT+iqoqQlLlLMzZ2rVrV+26w+GodayioqLex2yJsgWgZVFmAPhE165dlZiYqL/85S86cuRIjeVnHuRbpVu3bpKk/fv3e8Z2797ttUxnH3T8ySeftMhuMAAtizIDwGf++te/qry8XFdccYXeeustZWVl6csvv9Rzzz1XY5ePJEVHRysiIkKPPvqoMjMztXr1ai1atMhreTZv3qwnn3xSmZmZ+stf/qJ//etfmjVrltfuH4BvUGYA+ExUVJR27typ0aNH6/e//70GDhyosWPHat26dVqyZEmN27dr104pKSn66quvdOmll+qJJ57Q448/7rU8v//977Vjxw4NGTJE8+fP16JFi5SYmOi1+wfgGw73mTujAaCViIyM1OzZszV79myrowBoJmZmAACA0SgzAADAaOxmAgAARmNmBgAAGI0yAwAAjEaZAQAARqPMAAAAo1FmAACA0SgzAADAaJQZAABgNMoMAAAw2v8Pe4S6//bao5QAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = cell_df[cell_df['Class'] == 4][0:50].plot(kind='scatter', x='Clump', y='UnifSize', color='DarkBlue', label='malignant');\n",
    "cell_df[cell_df['Class'] == 2][0:50].plot(kind='scatter', x='Clump', y='UnifSize', color='Yellow', label='benign', ax=ax);\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data pre-processing and selection\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's first look at columns data types:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ID              int64\n",
       "Clump           int64\n",
       "UnifSize        int64\n",
       "UnifShape       int64\n",
       "MargAdh         int64\n",
       "SingEpiSize     int64\n",
       "BareNuc        object\n",
       "BlandChrom      int64\n",
       "NormNucl        int64\n",
       "Mit             int64\n",
       "Class           int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cell_df.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It looks like the __BareNuc__ column includes some values that are not numerical. We can drop those rows:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ID             int64\n",
       "Clump          int64\n",
       "UnifSize       int64\n",
       "UnifShape      int64\n",
       "MargAdh        int64\n",
       "SingEpiSize    int64\n",
       "BareNuc        int64\n",
       "BlandChrom     int64\n",
       "NormNucl       int64\n",
       "Mit            int64\n",
       "Class          int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cell_df = cell_df[pd.to_numeric(cell_df['BareNuc'], errors='coerce').notnull()]\n",
    "cell_df['BareNuc'] = cell_df['BareNuc'].astype('int')\n",
    "cell_df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 5,  1,  1,  1,  2,  1,  3,  1,  1],\n",
       "       [ 5,  4,  4,  5,  7, 10,  3,  2,  1],\n",
       "       [ 3,  1,  1,  1,  2,  2,  3,  1,  1],\n",
       "       [ 6,  8,  8,  1,  3,  4,  3,  7,  1],\n",
       "       [ 4,  1,  1,  3,  2,  1,  3,  1,  1]])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "feature_df = cell_df[['Clump', 'UnifSize', 'UnifShape', 'MargAdh', 'SingEpiSize', 'BareNuc', 'BlandChrom', 'NormNucl', 'Mit']]\n",
    "X = np.asarray(feature_df)\n",
    "X[0:5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We want the model to predict the value of Class (that is, benign (=2) or malignant (=4)).\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 2, 2, 2, 2])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y = np.asarray(cell_df['Class'])\n",
    "y [0:5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Train/Test dataset\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We split our dataset into train and test set:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train set: (546, 9) (546,)\n",
      "Test set: (137, 9) (137,)\n"
     ]
    }
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.2, random_state=4)\n",
    "print ('Train set:', X_train.shape,  y_train.shape)\n",
    "print ('Test set:', X_test.shape,  y_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h2 id=\"modeling\">Modeling (SVM with Scikit-learn)</h2>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The SVM algorithm offers a choice of kernel functions for performing its processing. Basically, mapping data into a higher dimensional space is called kernelling. The mathematical function used for the transformation is known as the kernel function, and can be of different types, such as:\n",
    "\n",
    "    1.Linear\n",
    "    2.Polynomial\n",
    "    3.Radial basis function (RBF)\n",
    "    4.Sigmoid\n",
    "Each of these functions has its characteristics, its pros and cons, and its equation, but as there's no easy way of knowing which function performs best with any given dataset. We usually choose different functions in turn and compare the results. Let's just use the default, RBF (Radial Basis Function) for this lab.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-1 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-1 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-1 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-1 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div></div></div>"
      ],
      "text/plain": [
       "SVC()"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn import svm\n",
    "clf = svm.SVC(kernel='rbf')\n",
    "clf.fit(X_train, y_train) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "After being fitted, the model can then be used to predict new values:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 4, 2, 4, 2])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "yhat = clf.predict(X_test)\n",
    "yhat [0:5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h2 id=\"evaluation\">Evaluation</h2>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report, confusion_matrix\n",
    "import itertools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_confusion_matrix(cm, classes,\n",
    "                          normalize=False,\n",
    "                          title='Confusion matrix',\n",
    "                          cmap=plt.cm.Blues):\n",
    "    \"\"\"\n",
    "    This function prints and plots the confusion matrix.\n",
    "    Normalization can be applied by setting `normalize=True`.\n",
    "    \"\"\"\n",
    "    if normalize:\n",
    "        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n",
    "        print(\"Normalized confusion matrix\")\n",
    "    else:\n",
    "        print('Confusion matrix, without normalization')\n",
    "\n",
    "    print(cm)\n",
    "\n",
    "    plt.imshow(cm, interpolation='nearest', cmap=cmap)\n",
    "    plt.title(title)\n",
    "    plt.colorbar()\n",
    "    tick_marks = np.arange(len(classes))\n",
    "    plt.xticks(tick_marks, classes, rotation=45)\n",
    "    plt.yticks(tick_marks, classes)\n",
    "\n",
    "    fmt = '.2f' if normalize else 'd'\n",
    "    thresh = cm.max() / 2.\n",
    "    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n",
    "        plt.text(j, i, format(cm[i, j], fmt),\n",
    "                 horizontalalignment=\"center\",\n",
    "                 color=\"white\" if cm[i, j] > thresh else \"black\")\n",
    "\n",
    "    plt.tight_layout()\n",
    "    plt.ylabel('True label')\n",
    "    plt.xlabel('Predicted label')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           2       1.00      0.94      0.97        90\n",
      "           4       0.90      1.00      0.95        47\n",
      "\n",
      "    accuracy                           0.96       137\n",
      "   macro avg       0.95      0.97      0.96       137\n",
      "weighted avg       0.97      0.96      0.96       137\n",
      "\n",
      "Confusion matrix, without normalization\n",
      "[[85  5]\n",
      " [ 0 47]]\n"
     ]
    }
   ],
   "source": [
    "# Compute confusion matrix\n",
    "cnf_matrix = confusion_matrix(y_test, yhat, labels=[2,4])\n",
    "np.set_printoptions(precision=2)\n",
    "\n",
    "print (classification_report(y_test, yhat))\n",
    "\n",
    "# Plot non-normalized confusion matrix\n",
    "plt.figure()\n",
    "plot_confusion_matrix(cnf_matrix, classes=['Benign(2)','Malignant(4)'],normalize= False,  title='Confusion matrix')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can also easily use the __f1_score__ from sklearn library:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9639038982104676"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import f1_score\n",
    "f1_score(y_test, yhat, average='weighted') "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's try the jaccard index for accuracy:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9444444444444444"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import jaccard_score\n",
    "jaccard_score(y_test, yhat,pos_label=2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h2 id=\"practice\">Practice</h2>\n",
    "Can you rebuild the model, but this time with a __linear__ kernel? You can use __kernel='linear'__ option, when you define the svm. How the accuracy changes with the new kernel function?\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "# write your code here\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<details><summary>Click here for the solution</summary>\n",
    "\n",
    "```python\n",
    "clf2 = svm.SVC(kernel='linear')\n",
    "clf2.fit(X_train, y_train) \n",
    "yhat2 = clf2.predict(X_test)\n",
    "print(\"Avg F1-score: %.4f\" % f1_score(y_test, yhat2, average='weighted'))\n",
    "print(\"Jaccard score: %.4f\" % jaccard_score(y_test, yhat2,pos_label=2))\n",
    "\n",
    "```\n",
    "\n",
    "</details>\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Thank you for completing this lab!\n",
    "\n",
    "\n",
    "## Author\n",
    "\n",
    "Saeed Aghabozorgi\n",
    "\n",
    "\n",
    "### Other Contributors\n",
    "\n",
    "<a href=\"https://www.linkedin.com/in/joseph-s-50398b136/\" target=\"_blank\">Joseph Santarcangelo</a>\n",
    "\n",
    "## <h3 align=\"center\"> © IBM Corporation 2020. All rights reserved. <h3/>\n",
    "\n",
    "<!--\n",
    "## Change Log\n",
    "\n",
    "\n",
    "|  Date (YYYY-MM-DD) |  Version | Changed By  |  Change Description |\n",
    "|---|---|---|---|\n",
    "| 2021-01-21  | 2.2  | Lakshmi  |  Updated sklearn library |\n",
    "| 2020-11-03  | 2.1  | Lakshmi  |  Updated URL of csv |\n",
    "| 2020-08-27  | 2.0  | Lavanya  |  Moved lab to course repo in GitLab |\n",
    "|   |   |   |   |\n",
    "|   |   |   |   |\n",
    "--!>\n",
    "\n",
    "\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.2"
  },
  "prev_pub_hash": "33c7dcfb268d8bbcaef711e72c89e89dc7bc1929452f1913b971040b140900c5"
 },
 "nbformat": 4,
 "nbformat_minor": 4
}