SVM (salary data).ipynb

SVM (salary data).ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# 1) Prepare a classification model using SVM for salary data \n\nimport pandas as pd\nimport numpy as np",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df_test=pd.read_csv(\"SalaryData_Test(1).csv\")",
      "execution_count": 2,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df_test",
      "execution_count": 3,
      "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>age</th>\n      <th>workclass</th>\n      <th>education</th>\n      <th>educationno</th>\n      <th>maritalstatus</th>\n      <th>occupation</th>\n      <th>relationship</th>\n      <th>race</th>\n      <th>sex</th>\n      <th>capitalgain</th>\n      <th>capitalloss</th>\n      <th>hoursperweek</th>\n      <th>native</th>\n      <th>Salary</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>25</td>\n      <td>Private</td>\n      <td>11th</td>\n      <td>7</td>\n      <td>Never-married</td>\n      <td>Machine-op-inspct</td>\n      <td>Own-child</td>\n      <td>Black</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>40</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>38</td>\n      <td>Private</td>\n      <td>HS-grad</td>\n      <td>9</td>\n      <td>Married-civ-spouse</td>\n      <td>Farming-fishing</td>\n      <td>Husband</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>50</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>28</td>\n      <td>Local-gov</td>\n      <td>Assoc-acdm</td>\n      <td>12</td>\n      <td>Married-civ-spouse</td>\n      <td>Protective-serv</td>\n      <td>Husband</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>40</td>\n      <td>United-States</td>\n      <td>&gt;50K</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>44</td>\n      <td>Private</td>\n      <td>Some-college</td>\n      <td>10</td>\n      <td>Married-civ-spouse</td>\n      <td>Machine-op-inspct</td>\n      <td>Husband</td>\n      <td>Black</td>\n      <td>Male</td>\n      <td>7688</td>\n      <td>0</td>\n      <td>40</td>\n      <td>United-States</td>\n      <td>&gt;50K</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>34</td>\n      <td>Private</td>\n      <td>10th</td>\n      <td>6</td>\n      <td>Never-married</td>\n      <td>Other-service</td>\n      <td>Not-in-family</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>30</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>15055</th>\n      <td>33</td>\n      <td>Private</td>\n      <td>Bachelors</td>\n      <td>13</td>\n      <td>Never-married</td>\n      <td>Prof-specialty</td>\n      <td>Own-child</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>40</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>15056</th>\n      <td>39</td>\n      <td>Private</td>\n      <td>Bachelors</td>\n      <td>13</td>\n      <td>Divorced</td>\n      <td>Prof-specialty</td>\n      <td>Not-in-family</td>\n      <td>White</td>\n      <td>Female</td>\n      <td>0</td>\n      <td>0</td>\n      <td>36</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>15057</th>\n      <td>38</td>\n      <td>Private</td>\n      <td>Bachelors</td>\n      <td>13</td>\n      <td>Married-civ-spouse</td>\n      <td>Prof-specialty</td>\n      <td>Husband</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>50</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>15058</th>\n      <td>44</td>\n      <td>Private</td>\n      <td>Bachelors</td>\n      <td>13</td>\n      <td>Divorced</td>\n      <td>Adm-clerical</td>\n      <td>Own-child</td>\n      <td>Asian-Pac-Islander</td>\n      <td>Male</td>\n      <td>5455</td>\n      <td>0</td>\n      <td>40</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>15059</th>\n      <td>35</td>\n      <td>Self-emp-inc</td>\n      <td>Bachelors</td>\n      <td>13</td>\n      <td>Married-civ-spouse</td>\n      <td>Exec-managerial</td>\n      <td>Husband</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>60</td>\n      <td>United-States</td>\n      <td>&gt;50K</td>\n    </tr>\n  </tbody>\n</table>\n<p>15060 rows × 14 columns</p>\n</div>",
            "text/plain": "       age      workclass      education  educationno        maritalstatus  \\\n0       25        Private           11th            7        Never-married   \n1       38        Private        HS-grad            9   Married-civ-spouse   \n2       28      Local-gov     Assoc-acdm           12   Married-civ-spouse   \n3       44        Private   Some-college           10   Married-civ-spouse   \n4       34        Private           10th            6        Never-married   \n...    ...            ...            ...          ...                  ...   \n15055   33        Private      Bachelors           13        Never-married   \n15056   39        Private      Bachelors           13             Divorced   \n15057   38        Private      Bachelors           13   Married-civ-spouse   \n15058   44        Private      Bachelors           13             Divorced   \n15059   35   Self-emp-inc      Bachelors           13   Married-civ-spouse   \n\n               occupation    relationship                 race      sex  \\\n0       Machine-op-inspct       Own-child                Black     Male   \n1         Farming-fishing         Husband                White     Male   \n2         Protective-serv         Husband                White     Male   \n3       Machine-op-inspct         Husband                Black     Male   \n4           Other-service   Not-in-family                White     Male   \n...                   ...             ...                  ...      ...   \n15055      Prof-specialty       Own-child                White     Male   \n15056      Prof-specialty   Not-in-family                White   Female   \n15057      Prof-specialty         Husband                White     Male   \n15058        Adm-clerical       Own-child   Asian-Pac-Islander     Male   \n15059     Exec-managerial         Husband                White     Male   \n\n       capitalgain  capitalloss  hoursperweek          native  Salary  \n0                0            0            40   United-States   <=50K  \n1                0            0            50   United-States   <=50K  \n2                0            0            40   United-States    >50K  \n3             7688            0            40   United-States    >50K  \n4                0            0            30   United-States   <=50K  \n...            ...          ...           ...             ...     ...  \n15055            0            0            40   United-States   <=50K  \n15056            0            0            36   United-States   <=50K  \n15057            0            0            50   United-States   <=50K  \n15058         5455            0            40   United-States   <=50K  \n15059            0            0            60   United-States    >50K  \n\n[15060 rows x 14 columns]"
          },
          "execution_count": 3,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df_train=pd.read_csv(\"SalaryData_Test(1).csv\")\ndf_train",
      "execution_count": 4,
      "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>age</th>\n      <th>workclass</th>\n      <th>education</th>\n      <th>educationno</th>\n      <th>maritalstatus</th>\n      <th>occupation</th>\n      <th>relationship</th>\n      <th>race</th>\n      <th>sex</th>\n      <th>capitalgain</th>\n      <th>capitalloss</th>\n      <th>hoursperweek</th>\n      <th>native</th>\n      <th>Salary</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>25</td>\n      <td>Private</td>\n      <td>11th</td>\n      <td>7</td>\n      <td>Never-married</td>\n      <td>Machine-op-inspct</td>\n      <td>Own-child</td>\n      <td>Black</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>40</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>38</td>\n      <td>Private</td>\n      <td>HS-grad</td>\n      <td>9</td>\n      <td>Married-civ-spouse</td>\n      <td>Farming-fishing</td>\n      <td>Husband</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>50</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>28</td>\n      <td>Local-gov</td>\n      <td>Assoc-acdm</td>\n      <td>12</td>\n      <td>Married-civ-spouse</td>\n      <td>Protective-serv</td>\n      <td>Husband</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>40</td>\n      <td>United-States</td>\n      <td>&gt;50K</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>44</td>\n      <td>Private</td>\n      <td>Some-college</td>\n      <td>10</td>\n      <td>Married-civ-spouse</td>\n      <td>Machine-op-inspct</td>\n      <td>Husband</td>\n      <td>Black</td>\n      <td>Male</td>\n      <td>7688</td>\n      <td>0</td>\n      <td>40</td>\n      <td>United-States</td>\n      <td>&gt;50K</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>34</td>\n      <td>Private</td>\n      <td>10th</td>\n      <td>6</td>\n      <td>Never-married</td>\n      <td>Other-service</td>\n      <td>Not-in-family</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>30</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>15055</th>\n      <td>33</td>\n      <td>Private</td>\n      <td>Bachelors</td>\n      <td>13</td>\n      <td>Never-married</td>\n      <td>Prof-specialty</td>\n      <td>Own-child</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>40</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>15056</th>\n      <td>39</td>\n      <td>Private</td>\n      <td>Bachelors</td>\n      <td>13</td>\n      <td>Divorced</td>\n      <td>Prof-specialty</td>\n      <td>Not-in-family</td>\n      <td>White</td>\n      <td>Female</td>\n      <td>0</td>\n      <td>0</td>\n      <td>36</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>15057</th>\n      <td>38</td>\n      <td>Private</td>\n      <td>Bachelors</td>\n      <td>13</td>\n      <td>Married-civ-spouse</td>\n      <td>Prof-specialty</td>\n      <td>Husband</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>50</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>15058</th>\n      <td>44</td>\n      <td>Private</td>\n      <td>Bachelors</td>\n      <td>13</td>\n      <td>Divorced</td>\n      <td>Adm-clerical</td>\n      <td>Own-child</td>\n      <td>Asian-Pac-Islander</td>\n      <td>Male</td>\n      <td>5455</td>\n      <td>0</td>\n      <td>40</td>\n      <td>United-States</td>\n      <td>&lt;=50K</td>\n    </tr>\n    <tr>\n      <th>15059</th>\n      <td>35</td>\n      <td>Self-emp-inc</td>\n      <td>Bachelors</td>\n      <td>13</td>\n      <td>Married-civ-spouse</td>\n      <td>Exec-managerial</td>\n      <td>Husband</td>\n      <td>White</td>\n      <td>Male</td>\n      <td>0</td>\n      <td>0</td>\n      <td>60</td>\n      <td>United-States</td>\n      <td>&gt;50K</td>\n    </tr>\n  </tbody>\n</table>\n<p>15060 rows × 14 columns</p>\n</div>",
            "text/plain": "       age      workclass      education  educationno        maritalstatus  \\\n0       25        Private           11th            7        Never-married   \n1       38        Private        HS-grad            9   Married-civ-spouse   \n2       28      Local-gov     Assoc-acdm           12   Married-civ-spouse   \n3       44        Private   Some-college           10   Married-civ-spouse   \n4       34        Private           10th            6        Never-married   \n...    ...            ...            ...          ...                  ...   \n15055   33        Private      Bachelors           13        Never-married   \n15056   39        Private      Bachelors           13             Divorced   \n15057   38        Private      Bachelors           13   Married-civ-spouse   \n15058   44        Private      Bachelors           13             Divorced   \n15059   35   Self-emp-inc      Bachelors           13   Married-civ-spouse   \n\n               occupation    relationship                 race      sex  \\\n0       Machine-op-inspct       Own-child                Black     Male   \n1         Farming-fishing         Husband                White     Male   \n2         Protective-serv         Husband                White     Male   \n3       Machine-op-inspct         Husband                Black     Male   \n4           Other-service   Not-in-family                White     Male   \n...                   ...             ...                  ...      ...   \n15055      Prof-specialty       Own-child                White     Male   \n15056      Prof-specialty   Not-in-family                White   Female   \n15057      Prof-specialty         Husband                White     Male   \n15058        Adm-clerical       Own-child   Asian-Pac-Islander     Male   \n15059     Exec-managerial         Husband                White     Male   \n\n       capitalgain  capitalloss  hoursperweek          native  Salary  \n0                0            0            40   United-States   <=50K  \n1                0            0            50   United-States   <=50K  \n2                0            0            40   United-States    >50K  \n3             7688            0            40   United-States    >50K  \n4                0            0            30   United-States   <=50K  \n...            ...          ...           ...             ...     ...  \n15055            0            0            40   United-States   <=50K  \n15056            0            0            36   United-States   <=50K  \n15057            0            0            50   United-States   <=50K  \n15058         5455            0            40   United-States   <=50K  \n15059            0            0            60   United-States    >50K  \n\n[15060 rows x 14 columns]"
          },
          "execution_count": 4,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "from sklearn.preprocessing import LabelEncoder\nlb=LabelEncoder()",
      "execution_count": 5,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df_test['Salary']=lb.fit_transform(df_test['Salary'])\ndf_train['Salary']=lb.fit_transform(df_train['Salary'])",
      "execution_count": 6,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df1_test=pd.get_dummies(df_test)\ndf1_train=pd.get_dummies(df_train)",
      "execution_count": 7,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "x_train=df1_train.drop('Salary',axis=1)\ny_train=df1_train['Salary']\nx_test=df1_test.drop('Salary',axis=1)\ny_test=df1_test['Salary']",
      "execution_count": 8,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "y_train",
      "execution_count": 9,
      "outputs": [
        {
          "data": {
            "text/plain": "0        0\n1        0\n2        1\n3        1\n4        0\n        ..\n15055    0\n15056    0\n15057    0\n15058    0\n15059    1\nName: Salary, Length: 15060, dtype: int32"
          },
          "execution_count": 9,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "from sklearn.svm import SVC",
      "execution_count": 10,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "model=SVC()\nmodel.fit(x_train,y_train)",
      "execution_count": 11,
      "outputs": [
        {
          "data": {
            "text/plain": "SVC()"
          },
          "execution_count": 11,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "pred=model.predict(x_test)",
      "execution_count": 12,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "pred",
      "execution_count": 13,
      "outputs": [
        {
          "data": {
            "text/plain": "array([0, 0, 0, ..., 0, 0, 0])"
          },
          "execution_count": 13,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "from sklearn.metrics import classification_report,confusion_matrix",
      "execution_count": 14,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "print(confusion_matrix(pred,y_test))\nprint(classification_report(pred,y_test))",
      "execution_count": 15,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "[[10997  2703]\n [  363   997]]\n              precision    recall  f1-score   support\n\n           0       0.97      0.80      0.88     13700\n           1       0.27      0.73      0.39      1360\n\n    accuracy                           0.80     15060\n   macro avg       0.62      0.77      0.64     15060\nweighted avg       0.90      0.80      0.83     15060\n\n"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "np.mean(pred==y_test)*100",
      "execution_count": 16,
      "outputs": [
        {
          "data": {
            "text/plain": "79.64143426294821"
          },
          "execution_count": 16,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "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": "SVM (salary data).ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 4
}