#009 Latihan SKLearn Logistic Regression.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Latihan SKLearn Logistic Regression.ipynb",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "9Jc53yoGpgNz",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 202
        },
        "outputId": "61d62be5-f719-4fe3-ecae-95c0c9f76c37"
      },
      "source": [
        "import pandas as pd #Mengimport Library\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "df = pd.read_csv('Social_Network_Ads.csv')  #Mengconvert DataSet ke DataFrame\n",
        "df.head() #Melihat Informasi Mengenai Data"
      ],
      "execution_count": 2,
      "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>User ID</th>\n",
              "      <th>Gender</th>\n",
              "      <th>Age</th>\n",
              "      <th>EstimatedSalary</th>\n",
              "      <th>Purchased</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>15624510</td>\n",
              "      <td>Male</td>\n",
              "      <td>19</td>\n",
              "      <td>19000</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>15810944</td>\n",
              "      <td>Male</td>\n",
              "      <td>35</td>\n",
              "      <td>20000</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>15668575</td>\n",
              "      <td>Female</td>\n",
              "      <td>26</td>\n",
              "      <td>43000</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>15603246</td>\n",
              "      <td>Female</td>\n",
              "      <td>27</td>\n",
              "      <td>57000</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>15804002</td>\n",
              "      <td>Male</td>\n",
              "      <td>19</td>\n",
              "      <td>76000</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "    User ID  Gender  Age  EstimatedSalary  Purchased\n",
              "0  15624510    Male   19            19000          0\n",
              "1  15810944    Male   35            20000          0\n",
              "2  15668575  Female   26            43000          0\n",
              "3  15603246  Female   27            57000          0\n",
              "4  15804002    Male   19            76000          0"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 2
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "x52aowB-rqE4",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 225
        },
        "outputId": "08433dce-2e35-4c56-edd8-806421027fb7"
      },
      "source": [
        "df.info() #Melihat apakah ada nilai kosong pada atribut"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 400 entries, 0 to 399\n",
            "Data columns (total 5 columns):\n",
            " #   Column           Non-Null Count  Dtype \n",
            "---  ------           --------------  ----- \n",
            " 0   User ID          400 non-null    int64 \n",
            " 1   Gender           400 non-null    object\n",
            " 2   Age              400 non-null    int64 \n",
            " 3   EstimatedSalary  400 non-null    int64 \n",
            " 4   Purchased        400 non-null    int64 \n",
            "dtypes: int64(4), object(1)\n",
            "memory usage: 15.8+ KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aYwNh6WusLXM",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 415
        },
        "outputId": "f94653ed-1a85-447d-ade7-6334afe28b28"
      },
      "source": [
        "data = df.drop(columns=['User ID']) #Menghapus Data Kolom User ID\n",
        "data = pd.get_dummies(data) #Menjalankan Infromasi Setelah di Hapus\n",
        "data"
      ],
      "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>Age</th>\n",
              "      <th>EstimatedSalary</th>\n",
              "      <th>Purchased</th>\n",
              "      <th>Gender_Female</th>\n",
              "      <th>Gender_Male</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>19</td>\n",
              "      <td>19000</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>35</td>\n",
              "      <td>20000</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>26</td>\n",
              "      <td>43000</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>27</td>\n",
              "      <td>57000</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>19</td>\n",
              "      <td>76000</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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>395</th>\n",
              "      <td>46</td>\n",
              "      <td>41000</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>396</th>\n",
              "      <td>51</td>\n",
              "      <td>23000</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>397</th>\n",
              "      <td>50</td>\n",
              "      <td>20000</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>398</th>\n",
              "      <td>36</td>\n",
              "      <td>33000</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>399</th>\n",
              "      <td>49</td>\n",
              "      <td>36000</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>400 rows × 5 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "     Age  EstimatedSalary  Purchased  Gender_Female  Gender_Male\n",
              "0     19            19000          0              0            1\n",
              "1     35            20000          0              0            1\n",
              "2     26            43000          0              1            0\n",
              "3     27            57000          0              1            0\n",
              "4     19            76000          0              0            1\n",
              "..   ...              ...        ...            ...          ...\n",
              "395   46            41000          1              1            0\n",
              "396   51            23000          1              0            1\n",
              "397   50            20000          1              1            0\n",
              "398   36            33000          0              0            1\n",
              "399   49            36000          1              1            0\n",
              "\n",
              "[400 rows x 5 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tZFRRzO5tEVF",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "outputId": "8dc399cf-2ede-4a00-b890-d3c003201710"
      },
      "source": [
        "#Memisahkan antara atribut dan tabel\n",
        "predictions = ['Age', 'EstimatedSalary', 'Gender_Female', 'Gender_Male']\n",
        "x = data[predictions]\n",
        "y = data['Purchased']\n",
        "#Membagi data antara train set dan test set\n",
        "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=42)\n",
        "#Melatih Model dengan train set\n",
        "from sklearn import linear_model\n",
        "model = linear_model.LogisticRegression()\n",
        "model.fit(x_train, y_train)\n",
        "#Menguji Akurasi pada test set\n",
        "model.score(x_test, y_test)"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.63"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    }
  ]
}