Assignment17-SVM-FireForests.ipynb

Assignment17-SVM-FireForests.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "import pandas as pd\nimport numpy as np\nfrom sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer\nfrom sklearn.preprocessing import StandardScaler\n\nfrom sklearn import svm\nfrom sklearn.svm import SVC\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.metrics import classification_report\n\n\nfrom sklearn.metrics import accuracy_score, confusion_matrix\nfrom sklearn.model_selection import train_test_split, cross_val_score\n",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "forestfires = pd.read_csv(\"C:/Users/Prathmesh/Downloads/forestfires.csv\")",
      "execution_count": 2,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "forestfires.head()",
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 3,
          "data": {
            "text/plain": "  month  day  FFMC   DMC     DC  ISI  temp  RH  wind  rain  ...  monthfeb  \\\n0   mar  fri  86.2  26.2   94.3  5.1   8.2  51   6.7   0.0  ...         0   \n1   oct  tue  90.6  35.4  669.1  6.7  18.0  33   0.9   0.0  ...         0   \n2   oct  sat  90.6  43.7  686.9  6.7  14.6  33   1.3   0.0  ...         0   \n3   mar  fri  91.7  33.3   77.5  9.0   8.3  97   4.0   0.2  ...         0   \n4   mar  sun  89.3  51.3  102.2  9.6  11.4  99   1.8   0.0  ...         0   \n\n   monthjan  monthjul  monthjun  monthmar  monthmay  monthnov  monthoct  \\\n0         0         0         0         1         0         0         0   \n1         0         0         0         0         0         0         1   \n2         0         0         0         0         0         0         1   \n3         0         0         0         1         0         0         0   \n4         0         0         0         1         0         0         0   \n\n   monthsep  size_category  \n0         0          small  \n1         0          small  \n2         0          small  \n3         0          small  \n4         0          small  \n\n[5 rows x 31 columns]",
            "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>month</th>\n      <th>day</th>\n      <th>FFMC</th>\n      <th>DMC</th>\n      <th>DC</th>\n      <th>ISI</th>\n      <th>temp</th>\n      <th>RH</th>\n      <th>wind</th>\n      <th>rain</th>\n      <th>...</th>\n      <th>monthfeb</th>\n      <th>monthjan</th>\n      <th>monthjul</th>\n      <th>monthjun</th>\n      <th>monthmar</th>\n      <th>monthmay</th>\n      <th>monthnov</th>\n      <th>monthoct</th>\n      <th>monthsep</th>\n      <th>size_category</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>mar</td>\n      <td>fri</td>\n      <td>86.2</td>\n      <td>26.2</td>\n      <td>94.3</td>\n      <td>5.1</td>\n      <td>8.2</td>\n      <td>51</td>\n      <td>6.7</td>\n      <td>0.0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>small</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>oct</td>\n      <td>tue</td>\n      <td>90.6</td>\n      <td>35.4</td>\n      <td>669.1</td>\n      <td>6.7</td>\n      <td>18.0</td>\n      <td>33</td>\n      <td>0.9</td>\n      <td>0.0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>small</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>oct</td>\n      <td>sat</td>\n      <td>90.6</td>\n      <td>43.7</td>\n      <td>686.9</td>\n      <td>6.7</td>\n      <td>14.6</td>\n      <td>33</td>\n      <td>1.3</td>\n      <td>0.0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>small</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>mar</td>\n      <td>fri</td>\n      <td>91.7</td>\n      <td>33.3</td>\n      <td>77.5</td>\n      <td>9.0</td>\n      <td>8.3</td>\n      <td>97</td>\n      <td>4.0</td>\n      <td>0.2</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>small</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>mar</td>\n      <td>sun</td>\n      <td>89.3</td>\n      <td>51.3</td>\n      <td>102.2</td>\n      <td>9.6</td>\n      <td>11.4</td>\n      <td>99</td>\n      <td>1.8</td>\n      <td>0.0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>small</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 31 columns</p>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "x = forestfires.iloc[:,2:30]\ny = forestfires.iloc[:,30]",
      "execution_count": 8,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "x_train, x_test, y_train, y_test = train_test_split(x,y, test_size = 0.3)",
      "execution_count": 11,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "x_train.shape, y_train.shape, x_test.shape, y_test.shape",
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 15,
          "data": {
            "text/plain": "((361, 28), (361,), (156, 28), (156,))"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "clf = SVC()\nparam_grid = [{'kernel':['rbf'],'gamma':[50,5,10,0.5],'C':[15,14,13,12,11,10,0.1,0.001] }]\ngsv = GridSearchCV(clf,param_grid,cv=10)\ngsv.fit(x_train,y_train)",
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 25,
          "data": {
            "text/plain": "GridSearchCV(cv=10, estimator=SVC(),\n             param_grid=[{'C': [15, 14, 13, 12, 11, 10, 0.1, 0.001],\n                          'gamma': [50, 5, 10, 0.5], 'kernel': ['rbf']}])"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "gsv.best_params_ , gsv.best_score_ ",
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 26,
          "data": {
            "text/plain": "({'C': 15, 'gamma': 0.5, 'kernel': 'rbf'}, 0.734009009009009)"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "clf = SVC(C= 15, gamma = 50)\nclf.fit(x_train , y_train)\ny_pred = clf.predict(x_test)\nacc = accuracy_score(y_test, y_pred) * 100\nprint(\"Accuracy =\", acc)\nconfusion_matrix(y_test, y_pred)",
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "stream",
          "text": "Accuracy = 76.28205128205127\n",
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "execution_count": 27,
          "data": {
            "text/plain": "array([[  0,  37],\n       [  0, 119]], dtype=int64)"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.8.5",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "Assignment17-SVM-FireForests.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 4
}