{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"\n",
    "Name: Anand Panchdhari\n",
    "Roll No.: C013\n",
    "Aim: Implement Support Vector Machine classifier on real world dataset using sklearn package in python and evaluate its performance.\n",
    "\"\"\"\n",
    "import pandas as pd\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn import svm\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "from sklearn.metrics import classification_report, accuracy_score, precision_score, recall_score\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.microsoft.datawrangler.viewer.v0+json": {
       "columns": [
        {
         "name": "index",
         "rawType": "int64",
         "type": "integer"
        },
        {
         "name": "case",
         "rawType": "int64",
         "type": "integer"
        },
        {
         "name": "site",
         "rawType": "int64",
         "type": "integer"
        },
        {
         "name": "Pop",
         "rawType": "object",
         "type": "string"
        },
        {
         "name": "sex",
         "rawType": "object",
         "type": "string"
        },
        {
         "name": "age",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "hdlngth",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "skullw",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "totlngth",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "taill",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "footlgth",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "earconch",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "eye",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "chest",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "belly",
         "rawType": "float64",
         "type": "float"
        }
       ],
       "conversionMethod": "pd.DataFrame",
       "ref": "e492ff94-6045-4540-bb6c-89495e088fe6",
       "rows": [
        [
         "0",
         "1",
         "1",
         "Vic",
         "m",
         "8.0",
         "94.1",
         "60.4",
         "89.0",
         "36.0",
         "74.5",
         "54.5",
         "15.2",
         "28.0",
         "36.0"
        ],
        [
         "1",
         "2",
         "1",
         "Vic",
         "f",
         "6.0",
         "92.5",
         "57.6",
         "91.5",
         "36.5",
         "72.5",
         "51.2",
         "16.0",
         "28.5",
         "33.0"
        ],
        [
         "2",
         "3",
         "1",
         "Vic",
         "f",
         "6.0",
         "94.0",
         "60.0",
         "95.5",
         "39.0",
         "75.4",
         "51.9",
         "15.5",
         "30.0",
         "34.0"
        ],
        [
         "3",
         "4",
         "1",
         "Vic",
         "f",
         "6.0",
         "93.2",
         "57.1",
         "92.0",
         "38.0",
         "76.1",
         "52.2",
         "15.2",
         "28.0",
         "34.0"
        ],
        [
         "4",
         "5",
         "1",
         "Vic",
         "f",
         "2.0",
         "91.5",
         "56.3",
         "85.5",
         "36.0",
         "71.0",
         "53.2",
         "15.1",
         "28.5",
         "33.0"
        ]
       ],
       "shape": {
        "columns": 14,
        "rows": 5
       }
      },
      "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>case</th>\n",
       "      <th>site</th>\n",
       "      <th>Pop</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>hdlngth</th>\n",
       "      <th>skullw</th>\n",
       "      <th>totlngth</th>\n",
       "      <th>taill</th>\n",
       "      <th>footlgth</th>\n",
       "      <th>earconch</th>\n",
       "      <th>eye</th>\n",
       "      <th>chest</th>\n",
       "      <th>belly</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Vic</td>\n",
       "      <td>m</td>\n",
       "      <td>8.0</td>\n",
       "      <td>94.1</td>\n",
       "      <td>60.4</td>\n",
       "      <td>89.0</td>\n",
       "      <td>36.0</td>\n",
       "      <td>74.5</td>\n",
       "      <td>54.5</td>\n",
       "      <td>15.2</td>\n",
       "      <td>28.0</td>\n",
       "      <td>36.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Vic</td>\n",
       "      <td>f</td>\n",
       "      <td>6.0</td>\n",
       "      <td>92.5</td>\n",
       "      <td>57.6</td>\n",
       "      <td>91.5</td>\n",
       "      <td>36.5</td>\n",
       "      <td>72.5</td>\n",
       "      <td>51.2</td>\n",
       "      <td>16.0</td>\n",
       "      <td>28.5</td>\n",
       "      <td>33.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>Vic</td>\n",
       "      <td>f</td>\n",
       "      <td>6.0</td>\n",
       "      <td>94.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>95.5</td>\n",
       "      <td>39.0</td>\n",
       "      <td>75.4</td>\n",
       "      <td>51.9</td>\n",
       "      <td>15.5</td>\n",
       "      <td>30.0</td>\n",
       "      <td>34.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Vic</td>\n",
       "      <td>f</td>\n",
       "      <td>6.0</td>\n",
       "      <td>93.2</td>\n",
       "      <td>57.1</td>\n",
       "      <td>92.0</td>\n",
       "      <td>38.0</td>\n",
       "      <td>76.1</td>\n",
       "      <td>52.2</td>\n",
       "      <td>15.2</td>\n",
       "      <td>28.0</td>\n",
       "      <td>34.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>Vic</td>\n",
       "      <td>f</td>\n",
       "      <td>2.0</td>\n",
       "      <td>91.5</td>\n",
       "      <td>56.3</td>\n",
       "      <td>85.5</td>\n",
       "      <td>36.0</td>\n",
       "      <td>71.0</td>\n",
       "      <td>53.2</td>\n",
       "      <td>15.1</td>\n",
       "      <td>28.5</td>\n",
       "      <td>33.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   case  site  Pop sex  age  hdlngth  skullw  totlngth  taill  footlgth  \\\n",
       "0     1     1  Vic   m  8.0     94.1    60.4      89.0   36.0      74.5   \n",
       "1     2     1  Vic   f  6.0     92.5    57.6      91.5   36.5      72.5   \n",
       "2     3     1  Vic   f  6.0     94.0    60.0      95.5   39.0      75.4   \n",
       "3     4     1  Vic   f  6.0     93.2    57.1      92.0   38.0      76.1   \n",
       "4     5     1  Vic   f  2.0     91.5    56.3      85.5   36.0      71.0   \n",
       "\n",
       "   earconch   eye  chest  belly  \n",
       "0      54.5  15.2   28.0   36.0  \n",
       "1      51.2  16.0   28.5   33.0  \n",
       "2      51.9  15.5   30.0   34.0  \n",
       "3      52.2  15.2   28.0   34.0  \n",
       "4      53.2  15.1   28.5   33.0  "
      ]
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.read_csv(\"datasets/possum.csv\")\n",
    "data=data.dropna()\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "X = data[['totlngth']]\n",
    "Y = (data['hdlngth'] >= 93).astype(int)\n",
    "logis = LogisticRegression(random_state=100)\n",
    "logis.fit(X=X, y=Y)\n",
    "y_prob = logis.predict_proba(X)[:,1]\n",
    "plt.scatter(X, Y, color='blue', label=\"Actual Data\")\n",
    "\n",
    "plt.plot(X, y_prob, color='red', linewidth=2, label=\"Logistic Regression Curve\")\n",
    "\n",
    "plt.xlabel(\"Total length of possum\")\n",
    "plt.ylabel(\"Length of head of possum\")\n",
    "plt.title(\"Linear Regression Model\")\n",
    "plt.legend()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "===== Linear Kernel =====\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.80      0.62      0.70        13\n",
      "           1       0.55      0.75      0.63         8\n",
      "\n",
      "    accuracy                           0.67        21\n",
      "   macro avg       0.67      0.68      0.66        21\n",
      "weighted avg       0.70      0.67      0.67        21\n",
      "\n",
      "===== Polynomial Kernel =====\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      0.15      0.27        13\n",
      "           1       0.42      1.00      0.59         8\n",
      "\n",
      "    accuracy                           0.48        21\n",
      "   macro avg       0.71      0.58      0.43        21\n",
      "weighted avg       0.78      0.48      0.39        21\n",
      "\n",
      "===== RBF Kernel =====\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.80      0.62      0.70        13\n",
      "           1       0.55      0.75      0.63         8\n",
      "\n",
      "    accuracy                           0.67        21\n",
      "   macro avg       0.67      0.68      0.66        21\n",
      "weighted avg       0.70      0.67      0.67        21\n",
      "\n",
      "===== Sigmoid Kernel =====\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.00      0.00      0.00        13\n",
      "           1       0.38      1.00      0.55         8\n",
      "\n",
      "    accuracy                           0.38        21\n",
      "   macro avg       0.19      0.50      0.28        21\n",
      "weighted avg       0.15      0.38      0.21        21\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/data/python/lib/python3.12/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)\n",
    "\n",
    "models = {\n",
    "    \"Linear\": svm.SVC(kernel=\"linear\"),\n",
    "    \"Polynomial\": svm.SVC(kernel=\"poly\"),\n",
    "    \"RBF\": svm.SVC(kernel=\"rbf\"),\n",
    "    \"Sigmoid\": svm.SVC(kernel=\"sigmoid\")\n",
    "}\n",
    "\n",
    "metrics = {}\n",
    "\n",
    "for name, clf in models.items():\n",
    "    clf.fit(X_train, Y_train)\n",
    "    Y_pred = clf.predict(X_test)\n",
    "    \n",
    "    accuracy = accuracy_score(Y_test, Y_pred)\n",
    "    precision = precision_score(Y_test, Y_pred)\n",
    "    recall = recall_score(Y_test, Y_pred)\n",
    "    metrics[name] = [accuracy, precision, recall]\n",
    "    print(f\"===== {name} Kernel =====\")\n",
    "    print(classification_report(Y_test, Y_pred))\n",
    "\n",
    "metrics_array = np.array(list(metrics.values()))\n",
    "\n",
    "plt.figure(figsize=(8, 5))\n",
    "sns.heatmap(metrics_array, annot=True, cmap=\"Blues\", xticklabels=[\"Accuracy\", \"Precision\", \"Recall\"], yticklabels=models.keys())\n",
    "plt.title(\"SVM Model Performance\")\n",
    "plt.show()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "language": "python",
   "name": "venv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}