Gender_Prediction_4_Predictions_Methods.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Gender Prediction - 4 Predictions Methods",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "lbGcUXiXy0A6"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "%matplotlib inline"
      ],
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "93k8Zn3Qz6qx",
        "outputId": "cbc21317-4d70-4843-e7b8-ea19a21a061c"
      },
      "source": [
        "df = pd.read_csv(r'/content/drive/MyDrive/Colab Notebooks/StudentsPerformance.csv')\n",
        "df.head()"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>gender</th>\n",
              "      <th>race/ethnicity</th>\n",
              "      <th>parental level of education</th>\n",
              "      <th>lunch</th>\n",
              "      <th>test preparation course</th>\n",
              "      <th>math score</th>\n",
              "      <th>reading score</th>\n",
              "      <th>writing score</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>female</td>\n",
              "      <td>group B</td>\n",
              "      <td>bachelor's degree</td>\n",
              "      <td>standard</td>\n",
              "      <td>none</td>\n",
              "      <td>72</td>\n",
              "      <td>72</td>\n",
              "      <td>74</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>female</td>\n",
              "      <td>group C</td>\n",
              "      <td>some college</td>\n",
              "      <td>standard</td>\n",
              "      <td>completed</td>\n",
              "      <td>69</td>\n",
              "      <td>90</td>\n",
              "      <td>88</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>female</td>\n",
              "      <td>group B</td>\n",
              "      <td>master's degree</td>\n",
              "      <td>standard</td>\n",
              "      <td>none</td>\n",
              "      <td>90</td>\n",
              "      <td>95</td>\n",
              "      <td>93</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>male</td>\n",
              "      <td>group A</td>\n",
              "      <td>associate's degree</td>\n",
              "      <td>free/reduced</td>\n",
              "      <td>none</td>\n",
              "      <td>47</td>\n",
              "      <td>57</td>\n",
              "      <td>44</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>male</td>\n",
              "      <td>group C</td>\n",
              "      <td>some college</td>\n",
              "      <td>standard</td>\n",
              "      <td>none</td>\n",
              "      <td>76</td>\n",
              "      <td>78</td>\n",
              "      <td>75</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   gender race/ethnicity  ... reading score writing score\n",
              "0  female        group B  ...            72            74\n",
              "1  female        group C  ...            90            88\n",
              "2  female        group B  ...            95            93\n",
              "3    male        group A  ...            57            44\n",
              "4    male        group C  ...            78            75\n",
              "\n",
              "[5 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EGRrOMXzz6-w",
        "outputId": "2d96125b-7c47-4479-8823-5fca66b84b91"
      },
      "source": [
        "df.info()"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 1000 entries, 0 to 999\n",
            "Data columns (total 8 columns):\n",
            " #   Column                       Non-Null Count  Dtype \n",
            "---  ------                       --------------  ----- \n",
            " 0   gender                       1000 non-null   object\n",
            " 1   race/ethnicity               1000 non-null   object\n",
            " 2   parental level of education  1000 non-null   object\n",
            " 3   lunch                        1000 non-null   object\n",
            " 4   test preparation course      1000 non-null   object\n",
            " 5   math score                   1000 non-null   int64 \n",
            " 6   reading score                1000 non-null   int64 \n",
            " 7   writing score                1000 non-null   int64 \n",
            "dtypes: int64(3), object(5)\n",
            "memory usage: 62.6+ KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "L-4vEBCu0Rwy",
        "outputId": "80b10c4d-3807-48da-af37-ef75c102904b"
      },
      "source": [
        "#Checking for Null Values\n",
        "df.isnull().sum()"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "gender                         0\n",
              "race/ethnicity                 0\n",
              "parental level of education    0\n",
              "lunch                          0\n",
              "test preparation course        0\n",
              "math score                     0\n",
              "reading score                  0\n",
              "writing score                  0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_bEuVFWa0d-j"
      },
      "source": [
        "#Feature Engineering"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BKmp9QR50W-E",
        "outputId": "e7df0040-9122-48ed-f74d-082c53ca1eac"
      },
      "source": [
        "#Change Female = 1 and Male = 1\n",
        "df.gender = [1 if each == \"female\" else 0 for each in df.gender]\n",
        "df.gender.value_counts()"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    518\n",
              "0    482\n",
              "Name: gender, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5RlM7L2x1hZt",
        "outputId": "e7d6fa43-7f5c-4a1b-80da-5d1c6310e54b"
      },
      "source": [
        "y = df.gender\n",
        "df.drop([\"gender\"],axis = 1 , inplace = True)\n",
        "df.columns"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['race/ethnicity', 'parental level of education', 'lunch',\n",
              "       'test preparation course', 'math score', 'reading score',\n",
              "       'writing score'],\n",
              "      dtype='object')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mI2qiYpV1tSp",
        "outputId": "8fa0faac-672a-4996-c244-e5182a782f9f"
      },
      "source": [
        "#Final Dataset with Conversion of Categorical Variables into Respected Columns\n",
        "final = pd.get_dummies(df,columns = [\"race/ethnicity\",\"lunch\",\"parental level of education\",\n",
        "                                      \"test preparation course\"])\n",
        "final.info()"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 1000 entries, 0 to 999\n",
            "Data columns (total 18 columns):\n",
            " #   Column                                          Non-Null Count  Dtype\n",
            "---  ------                                          --------------  -----\n",
            " 0   math score                                      1000 non-null   int64\n",
            " 1   reading score                                   1000 non-null   int64\n",
            " 2   writing score                                   1000 non-null   int64\n",
            " 3   race/ethnicity_group A                          1000 non-null   uint8\n",
            " 4   race/ethnicity_group B                          1000 non-null   uint8\n",
            " 5   race/ethnicity_group C                          1000 non-null   uint8\n",
            " 6   race/ethnicity_group D                          1000 non-null   uint8\n",
            " 7   race/ethnicity_group E                          1000 non-null   uint8\n",
            " 8   lunch_free/reduced                              1000 non-null   uint8\n",
            " 9   lunch_standard                                  1000 non-null   uint8\n",
            " 10  parental level of education_associate's degree  1000 non-null   uint8\n",
            " 11  parental level of education_bachelor's degree   1000 non-null   uint8\n",
            " 12  parental level of education_high school         1000 non-null   uint8\n",
            " 13  parental level of education_master's degree     1000 non-null   uint8\n",
            " 14  parental level of education_some college        1000 non-null   uint8\n",
            " 15  parental level of education_some high school    1000 non-null   uint8\n",
            " 16  test preparation course_completed               1000 non-null   uint8\n",
            " 17  test preparation course_none                    1000 non-null   uint8\n",
            "dtypes: int64(3), uint8(15)\n",
            "memory usage: 38.2 KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 490
        },
        "id": "ulEaFAOO2CS2",
        "outputId": "7baa1425-c2e4-40cf-a18f-142be6eaf5a3"
      },
      "source": [
        "x = final.astype(int)\n",
        "x"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>math score</th>\n",
              "      <th>reading score</th>\n",
              "      <th>writing score</th>\n",
              "      <th>race/ethnicity_group A</th>\n",
              "      <th>race/ethnicity_group B</th>\n",
              "      <th>race/ethnicity_group C</th>\n",
              "      <th>race/ethnicity_group D</th>\n",
              "      <th>race/ethnicity_group E</th>\n",
              "      <th>lunch_free/reduced</th>\n",
              "      <th>lunch_standard</th>\n",
              "      <th>parental level of education_associate's degree</th>\n",
              "      <th>parental level of education_bachelor's degree</th>\n",
              "      <th>parental level of education_high school</th>\n",
              "      <th>parental level of education_master's degree</th>\n",
              "      <th>parental level of education_some college</th>\n",
              "      <th>parental level of education_some high school</th>\n",
              "      <th>test preparation course_completed</th>\n",
              "      <th>test preparation course_none</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>72</td>\n",
              "      <td>72</td>\n",
              "      <td>74</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>1</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>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>69</td>\n",
              "      <td>90</td>\n",
              "      <td>88</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>1</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>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>90</td>\n",
              "      <td>95</td>\n",
              "      <td>93</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>1</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>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>47</td>\n",
              "      <td>57</td>\n",
              "      <td>44</td>\n",
              "      <td>1</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>1</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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>76</td>\n",
              "      <td>78</td>\n",
              "      <td>75</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>1</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>1</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",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>995</th>\n",
              "      <td>88</td>\n",
              "      <td>99</td>\n",
              "      <td>95</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>1</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>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>996</th>\n",
              "      <td>62</td>\n",
              "      <td>55</td>\n",
              "      <td>55</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</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>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>997</th>\n",
              "      <td>59</td>\n",
              "      <td>71</td>\n",
              "      <td>65</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</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>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>998</th>\n",
              "      <td>68</td>\n",
              "      <td>78</td>\n",
              "      <td>77</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>1</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>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>999</th>\n",
              "      <td>77</td>\n",
              "      <td>86</td>\n",
              "      <td>86</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</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>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1000 rows × 18 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "     math score  ...  test preparation course_none\n",
              "0            72  ...                             1\n",
              "1            69  ...                             0\n",
              "2            90  ...                             1\n",
              "3            47  ...                             1\n",
              "4            76  ...                             1\n",
              "..          ...  ...                           ...\n",
              "995          88  ...                             0\n",
              "996          62  ...                             1\n",
              "997          59  ...                             0\n",
              "998          68  ...                             0\n",
              "999          77  ...                             1\n",
              "\n",
              "[1000 rows x 18 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ujHrrDmD2g7J"
      },
      "source": [
        "#Noramlise Data using Simple Technique\n",
        "x= (final-np.min(final)) / (np.max(final)-np.min(final))"
      ],
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 490
        },
        "id": "mJNgGz9C2o9W",
        "outputId": "4bbaa3b8-0040-4a85-bf8e-24dba05f1b2b"
      },
      "source": [
        "x"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>math score</th>\n",
              "      <th>reading score</th>\n",
              "      <th>writing score</th>\n",
              "      <th>race/ethnicity_group A</th>\n",
              "      <th>race/ethnicity_group B</th>\n",
              "      <th>race/ethnicity_group C</th>\n",
              "      <th>race/ethnicity_group D</th>\n",
              "      <th>race/ethnicity_group E</th>\n",
              "      <th>lunch_free/reduced</th>\n",
              "      <th>lunch_standard</th>\n",
              "      <th>parental level of education_associate's degree</th>\n",
              "      <th>parental level of education_bachelor's degree</th>\n",
              "      <th>parental level of education_high school</th>\n",
              "      <th>parental level of education_master's degree</th>\n",
              "      <th>parental level of education_some college</th>\n",
              "      <th>parental level of education_some high school</th>\n",
              "      <th>test preparation course_completed</th>\n",
              "      <th>test preparation course_none</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.72</td>\n",
              "      <td>0.662651</td>\n",
              "      <td>0.711111</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.69</td>\n",
              "      <td>0.879518</td>\n",
              "      <td>0.866667</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.90</td>\n",
              "      <td>0.939759</td>\n",
              "      <td>0.922222</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.47</td>\n",
              "      <td>0.481928</td>\n",
              "      <td>0.377778</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.76</td>\n",
              "      <td>0.734940</td>\n",
              "      <td>0.722222</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</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",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>995</th>\n",
              "      <td>0.88</td>\n",
              "      <td>0.987952</td>\n",
              "      <td>0.944444</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>996</th>\n",
              "      <td>0.62</td>\n",
              "      <td>0.457831</td>\n",
              "      <td>0.500000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>997</th>\n",
              "      <td>0.59</td>\n",
              "      <td>0.650602</td>\n",
              "      <td>0.611111</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>998</th>\n",
              "      <td>0.68</td>\n",
              "      <td>0.734940</td>\n",
              "      <td>0.744444</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>999</th>\n",
              "      <td>0.77</td>\n",
              "      <td>0.831325</td>\n",
              "      <td>0.844444</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1000 rows × 18 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "     math score  ...  test preparation course_none\n",
              "0          0.72  ...                           1.0\n",
              "1          0.69  ...                           0.0\n",
              "2          0.90  ...                           1.0\n",
              "3          0.47  ...                           1.0\n",
              "4          0.76  ...                           1.0\n",
              "..          ...  ...                           ...\n",
              "995        0.88  ...                           0.0\n",
              "996        0.62  ...                           1.0\n",
              "997        0.59  ...                           0.0\n",
              "998        0.68  ...                           0.0\n",
              "999        0.77  ...                           1.0\n",
              "\n",
              "[1000 rows x 18 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xBGVbP8d3SkV"
      },
      "source": [
        "#SkLearn Library Work Starts Here Spliting Data\n",
        "from sklearn.model_selection import train_test_split\n",
        "x_train , x_test , y_train, y_test = train_test_split(x,y,test_size = 0.2 , random_state = 42)"
      ],
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uiIAAUZg30TU"
      },
      "source": [
        "#Prediction\n",
        "\n",
        "1. Support Vector Machine"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "S75SXu1h3w66",
        "outputId": "6dd1f961-15fa-4d41-82e7-e0988d4417e5"
      },
      "source": [
        "from sklearn.svm import SVC\n",
        "svm1 = SVC(gamma = 0.01 , C = 500 , kernel = \"rbf\")\n",
        "svm1.fit(x_train,y_train)\n",
        "svm1_score = svm1.score(x_test,y_test)\n",
        "print(\"Accuracy : \", svm1_score)"
      ],
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy :  0.925\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "sLmgqUEG4HMY"
      },
      "source": [
        "2. K-Nearest Neighbour"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UUv2bH-13-Il",
        "outputId": "730330d7-ecc1-418b-8c03-2a9a9a80ff20"
      },
      "source": [
        "knn_list = []\n",
        "from sklearn.neighbors import KNeighborsClassifier\n",
        "for each in range(1,100):\n",
        "    knn1 = KNeighborsClassifier(n_neighbors = each,weights = \"uniform\",metric = \"euclidean\" )\n",
        "    knn1.fit(x_train,y_train)\n",
        "    knn1_score = knn1.score(x_test,y_test)\n",
        "    knn_list.append(knn1_score)\n",
        "knn_max = np.max(knn_list)\n",
        "print(\"Accuracy= \",knn_max)"
      ],
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy=  0.75\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "TWKPiUHN4TSW"
      },
      "source": [
        "3. Logistic Regression"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4RD71WUl4Qc7",
        "outputId": "045f36c3-85de-4ac0-8033-1a447a2f3de2"
      },
      "source": [
        "from sklearn.linear_model import LogisticRegression\n",
        "lr = LogisticRegression(C = 10.0, penalty = \"l2\")\n",
        "lr.fit(x_train,y_train)\n",
        "print(\"Logistic Regression Max Score : \",lr.score(x_test,y_test))\n",
        "lr_max = lr.score(x_test,y_test)"
      ],
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Logistic Regression Max Score :  0.915\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "u-WyWung4aWF"
      },
      "source": [
        "4.Random Forest Classifier"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VRSnU4BX4Wx_",
        "outputId": "9e97e983-eb0b-4002-dc2a-b6ac102d8d98"
      },
      "source": [
        "\n",
        "score_list = []\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "for each in range (1,100):\n",
        "    rf = RandomForestClassifier(n_estimators = each,random_state = 7,bootstrap = \"False\",criterion=\"gini\",\n",
        "                                    min_samples_split = 10 , min_samples_leaf = 1)\n",
        "    rf.fit(x_train,y_train)\n",
        "    score_list.append(rf.score(x_test,y_test))\n",
        "    \n",
        "rf_max = np.max(score_list)\n",
        "print(\"RF Max Score : \",rf_max)"
      ],
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "RF Max Score :  0.9\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-QjvLR_i4w7C"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "s-x2gJDf4d-h"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}