diff --git a/Klasifikasi Tingkat Kemiskinan/Revisi_Klasifikasi_Tingkat_Kemiskinan_di_Indonesia.ipynb b/Klasifikasi Tingkat Kemiskinan/Revisi_Klasifikasi_Tingkat_Kemiskinan_di_Indonesia.ipynb
new file mode 100644
index 0000000..29ce0a5
--- /dev/null
+++ b/Klasifikasi Tingkat Kemiskinan/Revisi_Klasifikasi_Tingkat_Kemiskinan_di_Indonesia.ipynb	
@@ -0,0 +1,1684 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "source": [
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "import seaborn as sns\n",
+        "import matplotlib.pyplot as plt"
+      ],
+      "metadata": {
+        "id": "i4e7z6erwlmV"
+      },
+      "execution_count": 42,
+      "outputs": []
+    },
+    {
+      "source": [
+        "df = pd.read_csv('/content/Klasifikasi Tingkat Kemiskinan di Indonesia.csv', sep=';')\n",
+        "df.head(100)"
+      ],
+      "cell_type": "code",
+      "execution_count": 43,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "            Provinsi            Kab/Kota  \\\n",
+              "0               ACEH            Simeulue   \n",
+              "1               ACEH        Aceh Singkil   \n",
+              "2               ACEH        Aceh Selatan   \n",
+              "3               ACEH       Aceh Tenggara   \n",
+              "4               ACEH          Aceh Timur   \n",
+              "..               ...                 ...   \n",
+              "95             JAMBI               Bungo   \n",
+              "96             JAMBI          Kota Jambi   \n",
+              "97             JAMBI   Kota Sungai Penuh   \n",
+              "98  SUMATERA SELATAN   Ogan Komering Ulu   \n",
+              "99  SUMATERA SELATAN  Ogan Komering Ilir   \n",
+              "\n",
+              "   Persentase Penduduk Miskin (P0) Menurut Kabupaten/Kota (Persen)  \\\n",
+              "0                                               18,98                \n",
+              "1                                               20,36                \n",
+              "2                                               13,18                \n",
+              "3                                               13,41                \n",
+              "4                                               14,45                \n",
+              "..                                                ...                \n",
+              "95                                               6,23                \n",
+              "96                                               9,02                \n",
+              "97                                               3,41                \n",
+              "98                                              12,62                \n",
+              "99                                              14,68                \n",
+              "\n",
+              "   Rata-rata Lama Sekolah Penduduk 15+ (Tahun)  \\\n",
+              "0                                         9,48   \n",
+              "1                                         8,68   \n",
+              "2                                         8,88   \n",
+              "3                                         9,67   \n",
+              "4                                         8,21   \n",
+              "..                                         ...   \n",
+              "95                                        8,28   \n",
+              "96                                        11,2   \n",
+              "97                                       10,33   \n",
+              "98                                        8,71   \n",
+              "99                                        7,05   \n",
+              "\n",
+              "    Pengeluaran per Kapita Disesuaikan (Ribu Rupiah/Orang/Tahun)  \\\n",
+              "0                                              7148.0              \n",
+              "1                                              8776.0              \n",
+              "2                                              8180.0              \n",
+              "3                                              8030.0              \n",
+              "4                                              8577.0              \n",
+              "..                                                ...              \n",
+              "95                                            11670.0              \n",
+              "96                                            12240.0              \n",
+              "97                                            10454.0              \n",
+              "98                                            10040.0              \n",
+              "99                                            10755.0              \n",
+              "\n",
+              "   Indeks Pembangunan Manusia Umur Harapan Hidup (Tahun)  \\\n",
+              "0                       66,41                      65,28   \n",
+              "1                       69,22                      67,43   \n",
+              "2                       67,44                       64,4   \n",
+              "3                       69,44                      68,22   \n",
+              "4                       67,83                      68,74   \n",
+              "..                        ...                        ...   \n",
+              "95                      70,15                      67,83   \n",
+              "96                      79,12                      72,71   \n",
+              "97                       75,7                      72,21   \n",
+              "98                       69,6                      68,24   \n",
+              "99                      67,17                      68,67   \n",
+              "\n",
+              "   Persentase rumah tangga yang memiliki akses terhadap sanitasi layak  \\\n",
+              "0                                               71,56                    \n",
+              "1                                               69,56                    \n",
+              "2                                               62,55                    \n",
+              "3                                               62,71                    \n",
+              "4                                               66,75                    \n",
+              "..                                                ...                    \n",
+              "95                                              77,58                    \n",
+              "96                                              93,22                    \n",
+              "97                                              74,04                    \n",
+              "98                                              82,72                    \n",
+              "99                                              68,09                    \n",
+              "\n",
+              "   Persentase rumah tangga yang memiliki akses terhadap air minum layak  \\\n",
+              "0                                               87,45                     \n",
+              "1                                               78,58                     \n",
+              "2                                               79,65                     \n",
+              "3                                               86,71                     \n",
+              "4                                               83,16                     \n",
+              "..                                                ...                     \n",
+              "95                                              73,63                     \n",
+              "96                                              95,83                     \n",
+              "97                                              90,55                     \n",
+              "98                                              81,78                     \n",
+              "99                                              79,02                     \n",
+              "\n",
+              "   Tingkat Pengangguran Terbuka Tingkat Partisipasi Angkatan Kerja  \\\n",
+              "0                          5,71                             71,15    \n",
+              "1                          8,36                             62,85    \n",
+              "2                          6,46                             60,85    \n",
+              "3                          6,43                             69,62    \n",
+              "4                          7,13                             59,48    \n",
+              "..                          ...                                ...   \n",
+              "95                         5,86                             63,58    \n",
+              "96                        10,66                             63,12    \n",
+              "97                         3,00                             64,92    \n",
+              "98                         4,57                             69,96    \n",
+              "99                         3,01                             69,68    \n",
+              "\n",
+              "    PDRB atas Dasar Harga Konstan menurut Pengeluaran (Rupiah)  \\\n",
+              "0                                           1648096.0            \n",
+              "1                                           1780419.0            \n",
+              "2                                           4345784.0            \n",
+              "3                                           3487157.0            \n",
+              "4                                           8433526.0            \n",
+              "..                                                ...            \n",
+              "95                                         13133523.0            \n",
+              "96                                         19515486.0            \n",
+              "97                                          4768840.0            \n",
+              "98                                         10114558.0            \n",
+              "99                                         20909479.0            \n",
+              "\n",
+              "    Klasifikasi Kemiskinan  \n",
+              "0                      0.0  \n",
+              "1                      1.0  \n",
+              "2                      0.0  \n",
+              "3                      0.0  \n",
+              "4                      0.0  \n",
+              "..                     ...  \n",
+              "95                     0.0  \n",
+              "96                     0.0  \n",
+              "97                     0.0  \n",
+              "98                     0.0  \n",
+              "99                     0.0  \n",
+              "\n",
+              "[100 rows x 13 columns]"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-88841055-2c61-4111-b2cd-e2db9e41ea48\" class=\"colab-df-container\">\n",
+              "    <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>Provinsi</th>\n",
+              "      <th>Kab/Kota</th>\n",
+              "      <th>Persentase Penduduk Miskin (P0) Menurut Kabupaten/Kota (Persen)</th>\n",
+              "      <th>Rata-rata Lama Sekolah Penduduk 15+ (Tahun)</th>\n",
+              "      <th>Pengeluaran per Kapita Disesuaikan (Ribu Rupiah/Orang/Tahun)</th>\n",
+              "      <th>Indeks Pembangunan Manusia</th>\n",
+              "      <th>Umur Harapan Hidup (Tahun)</th>\n",
+              "      <th>Persentase rumah tangga yang memiliki akses terhadap sanitasi layak</th>\n",
+              "      <th>Persentase rumah tangga yang memiliki akses terhadap air minum layak</th>\n",
+              "      <th>Tingkat Pengangguran Terbuka</th>\n",
+              "      <th>Tingkat Partisipasi Angkatan Kerja</th>\n",
+              "      <th>PDRB atas Dasar Harga Konstan menurut Pengeluaran (Rupiah)</th>\n",
+              "      <th>Klasifikasi Kemiskinan</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>ACEH</td>\n",
+              "      <td>Simeulue</td>\n",
+              "      <td>18,98</td>\n",
+              "      <td>9,48</td>\n",
+              "      <td>7148.0</td>\n",
+              "      <td>66,41</td>\n",
+              "      <td>65,28</td>\n",
+              "      <td>71,56</td>\n",
+              "      <td>87,45</td>\n",
+              "      <td>5,71</td>\n",
+              "      <td>71,15</td>\n",
+              "      <td>1648096.0</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>ACEH</td>\n",
+              "      <td>Aceh Singkil</td>\n",
+              "      <td>20,36</td>\n",
+              "      <td>8,68</td>\n",
+              "      <td>8776.0</td>\n",
+              "      <td>69,22</td>\n",
+              "      <td>67,43</td>\n",
+              "      <td>69,56</td>\n",
+              "      <td>78,58</td>\n",
+              "      <td>8,36</td>\n",
+              "      <td>62,85</td>\n",
+              "      <td>1780419.0</td>\n",
+              "      <td>1.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>ACEH</td>\n",
+              "      <td>Aceh Selatan</td>\n",
+              "      <td>13,18</td>\n",
+              "      <td>8,88</td>\n",
+              "      <td>8180.0</td>\n",
+              "      <td>67,44</td>\n",
+              "      <td>64,4</td>\n",
+              "      <td>62,55</td>\n",
+              "      <td>79,65</td>\n",
+              "      <td>6,46</td>\n",
+              "      <td>60,85</td>\n",
+              "      <td>4345784.0</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>ACEH</td>\n",
+              "      <td>Aceh Tenggara</td>\n",
+              "      <td>13,41</td>\n",
+              "      <td>9,67</td>\n",
+              "      <td>8030.0</td>\n",
+              "      <td>69,44</td>\n",
+              "      <td>68,22</td>\n",
+              "      <td>62,71</td>\n",
+              "      <td>86,71</td>\n",
+              "      <td>6,43</td>\n",
+              "      <td>69,62</td>\n",
+              "      <td>3487157.0</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>ACEH</td>\n",
+              "      <td>Aceh Timur</td>\n",
+              "      <td>14,45</td>\n",
+              "      <td>8,21</td>\n",
+              "      <td>8577.0</td>\n",
+              "      <td>67,83</td>\n",
+              "      <td>68,74</td>\n",
+              "      <td>66,75</td>\n",
+              "      <td>83,16</td>\n",
+              "      <td>7,13</td>\n",
+              "      <td>59,48</td>\n",
+              "      <td>8433526.0</td>\n",
+              "      <td>0.0</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",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>95</th>\n",
+              "      <td>JAMBI</td>\n",
+              "      <td>Bungo</td>\n",
+              "      <td>6,23</td>\n",
+              "      <td>8,28</td>\n",
+              "      <td>11670.0</td>\n",
+              "      <td>70,15</td>\n",
+              "      <td>67,83</td>\n",
+              "      <td>77,58</td>\n",
+              "      <td>73,63</td>\n",
+              "      <td>5,86</td>\n",
+              "      <td>63,58</td>\n",
+              "      <td>13133523.0</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>96</th>\n",
+              "      <td>JAMBI</td>\n",
+              "      <td>Kota Jambi</td>\n",
+              "      <td>9,02</td>\n",
+              "      <td>11,2</td>\n",
+              "      <td>12240.0</td>\n",
+              "      <td>79,12</td>\n",
+              "      <td>72,71</td>\n",
+              "      <td>93,22</td>\n",
+              "      <td>95,83</td>\n",
+              "      <td>10,66</td>\n",
+              "      <td>63,12</td>\n",
+              "      <td>19515486.0</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>97</th>\n",
+              "      <td>JAMBI</td>\n",
+              "      <td>Kota Sungai Penuh</td>\n",
+              "      <td>3,41</td>\n",
+              "      <td>10,33</td>\n",
+              "      <td>10454.0</td>\n",
+              "      <td>75,7</td>\n",
+              "      <td>72,21</td>\n",
+              "      <td>74,04</td>\n",
+              "      <td>90,55</td>\n",
+              "      <td>3,00</td>\n",
+              "      <td>64,92</td>\n",
+              "      <td>4768840.0</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>98</th>\n",
+              "      <td>SUMATERA SELATAN</td>\n",
+              "      <td>Ogan Komering Ulu</td>\n",
+              "      <td>12,62</td>\n",
+              "      <td>8,71</td>\n",
+              "      <td>10040.0</td>\n",
+              "      <td>69,6</td>\n",
+              "      <td>68,24</td>\n",
+              "      <td>82,72</td>\n",
+              "      <td>81,78</td>\n",
+              "      <td>4,57</td>\n",
+              "      <td>69,96</td>\n",
+              "      <td>10114558.0</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>99</th>\n",
+              "      <td>SUMATERA SELATAN</td>\n",
+              "      <td>Ogan Komering Ilir</td>\n",
+              "      <td>14,68</td>\n",
+              "      <td>7,05</td>\n",
+              "      <td>10755.0</td>\n",
+              "      <td>67,17</td>\n",
+              "      <td>68,67</td>\n",
+              "      <td>68,09</td>\n",
+              "      <td>79,02</td>\n",
+              "      <td>3,01</td>\n",
+              "      <td>69,68</td>\n",
+              "      <td>20909479.0</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>100 rows × 13 columns</p>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-88841055-2c61-4111-b2cd-e2db9e41ea48')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-88841055-2c61-4111-b2cd-e2db9e41ea48 button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-88841055-2c61-4111-b2cd-e2db9e41ea48');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "dataframe",
+              "variable_name": "df",
+              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 999,\n  \"fields\": [\n    {\n      \"column\": \"Provinsi\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 34,\n        \"samples\": [\n          \"BANTEN\",\n          \"KALIMANTAN BARAT\",\n          \"SULAWESI TENGGARA\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Kab/Kota\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 514,\n        \"samples\": [\n          \"Manggarai\",\n          \"Yahukimo\",\n          \"Gorontalo\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Persentase Penduduk Miskin (P0) Menurut Kabupaten/Kota (Persen)\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 452,\n        \"samples\": [\n          \"5,91\",\n          \"8,3\",\n          \"12,85\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Rata-rata Lama Sekolah Penduduk 15+ (Tahun)\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 377,\n        \"samples\": [\n          \"10,91\",\n          \"7,12\",\n          \"6,02\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Pengeluaran per Kapita Disesuaikan (Ribu Rupiah/Orang/Tahun)\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2717.144185738409,\n        \"min\": 3976.0,\n        \"max\": 23888.0,\n        \"num_unique_values\": 498,\n        \"samples\": [\n          5708.0,\n          13317.0,\n          9410.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Indeks Pembangunan Manusia\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 452,\n        \"samples\": [\n          \"65,87\",\n          \"70,83\",\n          \"80,59\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Umur Harapan Hidup (Tahun)\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 411,\n        \"samples\": [\n          \"73,8\",\n          \"71,58\",\n          \"70,38\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Persentase rumah tangga yang memiliki akses terhadap sanitasi layak\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 487,\n        \"samples\": [\n          \"89,49\",\n          \"91,56\",\n          \"90,56\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Persentase rumah tangga yang memiliki akses terhadap air minum layak\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 465,\n        \"samples\": [\n          \"74,11\",\n          \"85,78\",\n          \"91,43\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Tingkat Pengangguran Terbuka\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 373,\n        \"samples\": [\n          \"4,56\",\n          \"1,95\",\n          \"3,47\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Tingkat Partisipasi Angkatan Kerja\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 448,\n        \"samples\": [\n          \" 77,57 \",\n          \" 70,16 \",\n          \" 70,13 \"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"PDRB atas Dasar Harga Konstan menurut Pengeluaran (Rupiah)\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 47904920.44381927,\n        \"min\": 147485.0,\n        \"max\": 460081046.0,\n        \"num_unique_values\": 514,\n        \"samples\": [\n          3025880.0,\n          1556231.0,\n          9082312.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Klasifikasi Kemiskinan\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.3260054197106571,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          1.0,\n          0.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+            }
+          },
+          "metadata": {},
+          "execution_count": 43
+        }
+      ],
+      "metadata": {
+        "cellView": "form",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 774
+        },
+        "id": "jpmStKaasKmD",
+        "outputId": "4ab4a0d2-6833-4bf4-c7f0-fc4f940ddded"
+      }
+    },
+    {
+      "source": [
+        "df_subset = df[[\"Provinsi\", \"Klasifikasi Kemiskinan\"]]\n",
+        "df_subset.head(100)"
+      ],
+      "cell_type": "code",
+      "execution_count": 44,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "            Provinsi  Klasifikasi Kemiskinan\n",
+              "0               ACEH                     0.0\n",
+              "1               ACEH                     1.0\n",
+              "2               ACEH                     0.0\n",
+              "3               ACEH                     0.0\n",
+              "4               ACEH                     0.0\n",
+              "..               ...                     ...\n",
+              "95             JAMBI                     0.0\n",
+              "96             JAMBI                     0.0\n",
+              "97             JAMBI                     0.0\n",
+              "98  SUMATERA SELATAN                     0.0\n",
+              "99  SUMATERA SELATAN                     0.0\n",
+              "\n",
+              "[100 rows x 2 columns]"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-36c63a3d-1f6c-494c-a371-b8a7c29264bc\" class=\"colab-df-container\">\n",
+              "    <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>Provinsi</th>\n",
+              "      <th>Klasifikasi Kemiskinan</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>ACEH</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>ACEH</td>\n",
+              "      <td>1.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>ACEH</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>ACEH</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>ACEH</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>95</th>\n",
+              "      <td>JAMBI</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>96</th>\n",
+              "      <td>JAMBI</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>97</th>\n",
+              "      <td>JAMBI</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>98</th>\n",
+              "      <td>SUMATERA SELATAN</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>99</th>\n",
+              "      <td>SUMATERA SELATAN</td>\n",
+              "      <td>0.0</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>100 rows × 2 columns</p>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-36c63a3d-1f6c-494c-a371-b8a7c29264bc')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-36c63a3d-1f6c-494c-a371-b8a7c29264bc button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-36c63a3d-1f6c-494c-a371-b8a7c29264bc');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "dataframe",
+              "variable_name": "df_subset",
+              "summary": "{\n  \"name\": \"df_subset\",\n  \"rows\": 999,\n  \"fields\": [\n    {\n      \"column\": \"Provinsi\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 34,\n        \"samples\": [\n          \"BANTEN\",\n          \"KALIMANTAN BARAT\",\n          \"SULAWESI TENGGARA\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Klasifikasi Kemiskinan\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.3260054197106571,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          1.0,\n          0.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+            }
+          },
+          "metadata": {},
+          "execution_count": 44
+        }
+      ],
+      "metadata": {
+        "cellView": "form",
+        "id": "0Np7uHb3s1vm",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 424
+        },
+        "outputId": "64a56e42-4496-4f84-d17c-eb4e3d4bf4c8"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_subset = df[[\"Provinsi\", \"Klasifikasi Kemiskinan\"]]\n",
+        "df_subset = df_subset.dropna()\n",
+        "\n",
+        "plt.figure(figsize=(12, 4))\n",
+        "sns.lineplot(data=df_subset, x=\"Provinsi\", y=\"Klasifikasi Kemiskinan\", marker=\"o\")\n",
+        "\n",
+        "plt.xticks(rotation=90)\n",
+        "plt.title(\"Line Plot Klasifikasi Kemiskinan di setiap Provinsi\")\n",
+        "plt.xlabel(\"Provinsi\")\n",
+        "plt.ylabel(\"Klasifikasi Kemiskinan\")\n",
+        "plt.tight_layout()\n",
+        "plt.show()\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 398
+        },
+        "id": "9cbPJC3aKczY",
+        "outputId": "3902515a-9f48-4bfb-f03d-c968628a5577"
+      },
+      "execution_count": 45,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 1200x400 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "import seaborn as sns\n",
+        "import matplotlib.pyplot as plt\n",
+        "from sklearn.model_selection import train_test_split, cross_val_score\n",
+        "from sklearn.preprocessing import LabelEncoder\n",
+        "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n",
+        "from sklearn.ensemble import RandomForestClassifier\n",
+        "from sklearn.linear_model import LogisticRegression\n",
+        "from sklearn.impute import SimpleImputer\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "LIvFHTtMw5mI"
+      },
+      "execution_count": 46,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "y = pd.to_numeric(df[\"Klasifikasi Kemiskinan\"], errors='coerce')\n",
+        "y = y.fillna(0).astype(int)\n",
+        "\n",
+        "X = df.drop(\"Klasifikasi Kemiskinan\", axis=1)"
+      ],
+      "metadata": {
+        "id": "LPcA1dxyxERN"
+      },
+      "execution_count": 47,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "X = X.apply(lambda s: s.astype(str).str.replace(\",\", \".\").str.replace(\" \", \"\", regex=True))\n",
+        "\n",
+        "for col in X.columns:\n",
+        "    X[col] = pd.to_numeric(X[col], errors='coerce')\n",
+        "\n",
+        "label_enc = LabelEncoder()\n",
+        "X[\"Provinsi\"] = label_enc.fit_transform(X[\"Provinsi\"].astype(str))\n",
+        "X[\"Kab/Kota\"] = label_enc.fit_transform(X[\"Kab/Kota\"].astype(str))\n",
+        "\n",
+        "imputer = SimpleImputer(strategy='mean')\n",
+        "X[X.columns] = imputer.fit_transform(X)"
+      ],
+      "metadata": {
+        "id": "g_oElrw_xSFf"
+      },
+      "execution_count": 48,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "X_train, X_test, y_train, y_test = train_test_split(\n",
+        "    X, y, test_size=0.2, random_state=42\n",
+        ")\n"
+      ],
+      "metadata": {
+        "id": "QubEOuCOxVE7"
+      },
+      "execution_count": 49,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "rf = RandomForestClassifier(n_estimators=200, random_state=42)\n",
+        "rf.fit(X_train, y_train)\n",
+        "\n",
+        "pred_rf = rf.predict(X_test)\n",
+        "\n",
+        "print(\"=== Random Forest Accuracy ===\")\n",
+        "print(accuracy_score(y_test, pred_rf))\n",
+        "print(\"\\n=== Classification Report ===\")\n",
+        "print(classification_report(y_test, pred_rf))\n",
+        "print(\"\\n=== Confusion Matrix ===\")\n",
+        "print(confusion_matrix(y_test, pred_rf))\n",
+        "\n",
+        "cv_rf = cross_val_score(rf, X, y, cv=5)\n",
+        "print(\"\\n=== Cross Validation (Random Forest) ===\")\n",
+        "print(cv_rf)\n",
+        "print(\"Mean CV Score:\", cv_rf.mean())"
+      ],
+      "metadata": {
+        "id": "aEaCyi8XxXql",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "62e33b8a-50ac-4b55-d7ef-a6037409acde"
+      },
+      "execution_count": 50,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "=== Random Forest Accuracy ===\n",
+            "0.99\n",
+            "\n",
+            "=== Classification Report ===\n",
+            "              precision    recall  f1-score   support\n",
+            "\n",
+            "           0       0.99      1.00      0.99       190\n",
+            "           1       1.00      0.80      0.89        10\n",
+            "\n",
+            "    accuracy                           0.99       200\n",
+            "   macro avg       0.99      0.90      0.94       200\n",
+            "weighted avg       0.99      0.99      0.99       200\n",
+            "\n",
+            "\n",
+            "=== Confusion Matrix ===\n",
+            "[[190   0]\n",
+            " [  2   8]]\n",
+            "\n",
+            "=== Cross Validation (Random Forest) ===\n",
+            "[0.99 1.   0.97 0.99 1.  ]\n",
+            "Mean CV Score: 0.99\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import matplotlib.pyplot as plt\n",
+        "import numpy as np\n"
+      ],
+      "metadata": {
+        "id": "l_Bms2snyjks"
+      },
+      "execution_count": 51,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "accuracy = 0.99\n",
+        "\n",
+        "conf_matrix = np.array([\n",
+        "    [190, 0],\n",
+        "    [2,   8]\n",
+        "])"
+      ],
+      "metadata": {
+        "id": "isQJoC9Tyq5G"
+      },
+      "execution_count": 52,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "classes = [\"0\", \"1\"]\n",
+        "precision = [0.99, 1.00]\n",
+        "recall = [1.00, 0.80]\n",
+        "f1 = [0.99, 0.89]\n",
+        "\n",
+        "cv_scores = np.array([0.99, 1.00, 0.97, 0.99, 1.00])"
+      ],
+      "metadata": {
+        "id": "ZmNBm0wyzKA8"
+      },
+      "execution_count": 53,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "plt.figure()\n",
+        "plt.bar([\"Accuracy\"], [accuracy])\n",
+        "plt.title(\"Random Forest Accuracy\")\n",
+        "plt.ylabel(\"Score\")\n",
+        "plt.ylim(0, 1)\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 452
+        },
+        "id": "kTf7LP5my2ja",
+        "outputId": "2509abb4-6847-47e5-f741-b95fb74a99a9"
+      },
+      "execution_count": 54,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "conf_matrix = np.array([[190, 0],\n",
+        "                        [2, 8]])\n",
+        "\n",
+        "plt.figure(figsize=(6,4))\n",
+        "plt.imshow(conf_matrix)\n",
+        "plt.title(\"Confusion Matrix Random Forest\")\n",
+        "plt.colorbar()\n",
+        "plt.xticks([0,1], [\"Pred 0\", \"Pred 1\"])\n",
+        "plt.yticks([0,1], [\"Actual 0\", \"Actual 1\"])\n",
+        "plt.show()\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 391
+        },
+        "id": "mV2_uYR1y5zj",
+        "outputId": "867ff4fb-231d-4339-d6c6-a42c0bf03c7f"
+      },
+      "execution_count": 55,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 600x400 with 2 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "x = np.arange(len(classes))\n",
+        "width = 0.25\n",
+        "\n",
+        "plt.figure()\n",
+        "plt.bar(x - width, precision, width, label=\"Precision\")\n",
+        "plt.bar(x, recall, width, label=\"Recall\")\n",
+        "plt.bar(x + width, f1, width, label=\"F1-Score\")\n",
+        "\n",
+        "plt.xticks(x, classes)\n",
+        "plt.ylabel(\"Score\")\n",
+        "plt.title(\"Classification Metrics per Class\")\n",
+        "plt.legend()\n",
+        "plt.ylim(0, 1)\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 452
+        },
+        "id": "OgLQduE6y85d",
+        "outputId": "5a09c65b-c91b-47dd-911d-8ba2842d25e8"
+      },
+      "execution_count": 56,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "cv_scores = [0.99, 1.00, 0.97, 0.99, 1.00]\n",
+        "\n",
+        "plt.figure(figsize=(7,4))\n",
+        "plt.plot(cv_scores, marker='o')\n",
+        "plt.title(\"Cross Validation Scores (Random Forest)\")\n",
+        "plt.xlabel(\"Fold\")\n",
+        "plt.ylabel(\"Score\")\n",
+        "plt.ylim(0,1)\n",
+        "plt.grid(True)\n",
+        "plt.show()\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 410
+        },
+        "id": "EhayQ2eQyyIL",
+        "outputId": "16b84d11-0298-4827-dda7-717ff7d21435"
+      },
+      "execution_count": 57,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 700x400 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "logreg = LogisticRegression(max_iter=2000)\n",
+        "logreg.fit(X_train, y_train)\n",
+        "\n",
+        "pred_lr = logreg.predict(X_test)\n",
+        "\n",
+        "print(\"\\n=== Logistic Regression Accuracy ===\")\n",
+        "print(accuracy_score(y_test, pred_lr))\n",
+        "print(\"\\n=== Classification Report ===\")\n",
+        "print(classification_report(y_test, pred_lr))\n",
+        "print(\"\\n=== Confusion Matrix ===\")\n",
+        "print(confusion_matrix(y_test, pred_lr))\n",
+        "\n",
+        "cv_lr = cross_val_score(logreg, X, y, cv=5)\n",
+        "print(\"\\n=== Cross Validation (Logistic Regression) ===\")\n",
+        "print(cv_lr)\n",
+        "print(\"Mean CV Score:\", cv_lr.mean())\n",
+        "\n",
+        "\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "8pScuIEBxcuQ",
+        "outputId": "228fa067-58a2-4c65-c4dd-0148cd3627f5"
+      },
+      "execution_count": 58,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\n",
+            "=== Logistic Regression Accuracy ===\n",
+            "0.985\n",
+            "\n",
+            "=== Classification Report ===\n",
+            "              precision    recall  f1-score   support\n",
+            "\n",
+            "           0       0.98      1.00      0.99       190\n",
+            "           1       1.00      0.70      0.82        10\n",
+            "\n",
+            "    accuracy                           0.98       200\n",
+            "   macro avg       0.99      0.85      0.91       200\n",
+            "weighted avg       0.99      0.98      0.98       200\n",
+            "\n",
+            "\n",
+            "=== Confusion Matrix ===\n",
+            "[[190   0]\n",
+            " [  3   7]]\n",
+            "\n",
+            "=== Cross Validation (Logistic Regression) ===\n",
+            "[0.975 0.98  0.965 0.99  1.   ]\n",
+            "Mean CV Score: 0.982\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import matplotlib.pyplot as plt\n",
+        "import numpy as np"
+      ],
+      "metadata": {
+        "id": "PdQqzT5Xxgce"
+      },
+      "execution_count": 59,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "accuracy = 0.985"
+      ],
+      "metadata": {
+        "id": "RfPb1-Ao2WNr"
+      },
+      "execution_count": 60,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "classes = [\"0\", \"1\"]\n",
+        "precision = [0.98, 1.00]\n",
+        "recall = [1.00, 0.70]\n",
+        "f1 = [0.99, 0.82]"
+      ],
+      "metadata": {
+        "id": "0FViVUXj2Z3V"
+      },
+      "execution_count": 61,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "conf_matrix = np.array([[190, 0],\n",
+        "                        [3, 7]])"
+      ],
+      "metadata": {
+        "id": "jPpaJQ_Q2fNt"
+      },
+      "execution_count": 62,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "cv_scores = np.array([0.975, 0.98, 0.965, 0.99, 1.0])"
+      ],
+      "metadata": {
+        "id": "r4kFvyrF2i1J"
+      },
+      "execution_count": 63,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "plt.figure()\n",
+        "plt.bar([\"Accuracy\"], [accuracy])\n",
+        "plt.title(\"Logistic Regression Accuracy\")\n",
+        "plt.ylabel(\"Score\")\n",
+        "plt.ylim(0, 1)\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "dLeeMyia2oWm",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 452
+        },
+        "outputId": "5838a47b-6b5d-4680-e832-82868c377941"
+      },
+      "execution_count": 64,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "plt.figure()\n",
+        "plt.imshow(conf_matrix)\n",
+        "plt.title(\"Confusion Matrix Logistic Regression\")\n",
+        "plt.colorbar()\n",
+        "plt.xticks([0,1], [\"Pred 0\", \"Pred 1\"])\n",
+        "plt.yticks([0,1], [\"Actual 0\", \"Actual 1\"])\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "uqY9L5R82sCw",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 452
+        },
+        "outputId": "6d17854c-34d5-40ff-bc26-3d3039e62688"
+      },
+      "execution_count": 65,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 2 Axes>"
+            ],
+            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAhcAAAGzCAYAAACcvDUtAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAQWBJREFUeJzt3XlclWX+//H3QeXgwiIiIiOCopkrbmmOpZimoplrhUuDS9piWWrm16kUKUdHyyxzyQm1RcuazMrS3CUL98jJyhFzKwW3BMVU4Ny/PxzOzyOiwLlvEXk9H4/7Ueferus+HDkfPp/rum+bYRiGAAAATOJR1B0AAAC3FoILAABgKoILAABgKoILAABgKoILAABgKoILAABgKoILAABgKoILAABgKoILAABgKoILFNrevXvVsWNH+fr6ymazadmyZaae/8CBA7LZbFq4cKGp5y3OIiMjFRkZWdTdcMvChQtls9l04MABU84XGxsrm81myrlwycCBAxUWFlbU3UAxRnBRzO3bt0+PPvqoatasKS8vL/n4+Kh169Z6/fXX9eeff1radkxMjP7zn/9o0qRJeu+999S8eXNL27uRBg4cKJvNJh8fn6u+j3v37pXNZpPNZtMrr7xS4PMfOXJEsbGxSkpKMqG3hWez2fTkk08WaR/y49y5c4qNjdWGDRssbScnUMlZypQpo7CwMI0YMUKnT5+2tG3gVlK6qDuAwvvyyy/1wAMPyG63629/+5saNGigixcvatOmTRozZox2796tefPmWdL2n3/+qcTERD3//POWfTmFhobqzz//VJkyZSw5//WULl1a586d0xdffKEHH3zQZduiRYvk5eWl8+fPF+rcR44c0cSJExUWFqbGjRvn+7hVq1YVqr2bycMPP6zo6GjZ7fZ8H3Pu3DlNnDhRknJlbl544QX93//9n5ld1Jw5c1ShQgVlZGRo7dq1mjlzpnbu3KlNmzaZ2s7N6l//+pccDkdRdwPFGMFFMbV//35FR0crNDRU69atU9WqVZ3bhg8fruTkZH355ZeWtX/8+HFJkp+fn2Vt2Gw2eXl5WXb+67Hb7WrdurU++OCDXMHF4sWL1bVrV33yySc3pC/nzp1TuXLl5OnpeUPas1KpUqVUqlQp085XunRplS5t7q+yPn36KCAgQJL06KOPKjo6WkuWLNHWrVvVokULU9u6FofDoYsXL97wfwdFFdDj1kFZpJiaOnWqzp49q/j4eJfAIketWrX09NNPO19nZWXppZdeUnh4uOx2u8LCwvT3v/9dFy5ccDkuLCxM9913nzZt2qQWLVrIy8tLNWvW1LvvvuvcJzY2VqGhoZKkMWPGyGazOeuzedVqr1YXX716te666y75+fmpQoUKqlOnjv7+9787t+c15mLdunW6++67Vb58efn5+al79+76+eefr9pecnKyBg4cKD8/P/n6+mrQoEE6d+5c3m/sFfr166cVK1a4pMS3bdumvXv3ql+/frn2P3XqlJ599lk1bNhQFSpUkI+Pj6KiovTDDz8499mwYYPuuOMOSdKgQYOcKfic64yMjFSDBg20Y8cOtWnTRuXKlXO+L1eOuYiJiZGXl1eu6+/UqZMqVqyoI0eO5Pta85KRkaHRo0crJCREdrtdderU0SuvvKIrH6j8559/asSIEQoICJC3t7fuv/9+/f7777LZbIqNjXXud7UxF9u3b1enTp0UEBCgsmXLqkaNGho8eLCkS5+DypUrS5ImTpzofL9yzpnXmIv3339fLVq0ULly5VSxYkW1adOm0Jmfu+++W9KlMuTltmzZos6dO8vX11flypVT27Zt9e233+Y6fsOGDWrevLm8vLwUHh6ut95666r9zilTLVq0SPXr15fdbtfKlSslSb///rsGDx6sKlWqyG63q379+po/f36utmbOnKn69es7r7t58+ZavHixc/uZM2f0zDPPKCwsTHa7XYGBgbr33nu1c+dO5z5X+3ec389BzjUsW7ZMDRo0cPY15zpQMpC5KKa++OIL1axZU3/961/ztf8jjzyid955R3369NHo0aO1ZcsWTZ48WT///LM+/fRTl32Tk5PVp08fDRkyRDExMZo/f74GDhyoZs2aqX79+urVq5f8/Pw0cuRI9e3bV126dFGFChUK1P/du3frvvvuU6NGjRQXFye73a7k5OSr/mK+3Jo1axQVFaWaNWsqNjZWf/75p2bOnKnWrVtr586duX4hPvjgg6pRo4YmT56snTt36u2331ZgYKD++c9/5qufvXr10mOPPaalS5c6v+wWL16s22+/XU2bNs21/6+//qply5bpgQceUI0aNZSamqq33npLbdu21U8//aTg4GDVrVtXcXFxGj9+vIYNG+b84rr8Z3ny5ElFRUUpOjpaAwYMUJUqVa7av9dff13r1q1TTEyMEhMTVapUKb311ltatWqV3nvvPQUHB+frOvNiGIbuv/9+rV+/XkOGDFHjxo319ddfa8yYMfr999/12muvOfcdOHCgPvroIz388MO68847tXHjRnXt2vW6bRw7dkwdO3ZU5cqV9X//93/y8/PTgQMHtHTpUklS5cqVNWfOHD3++OPq2bOnevXqJUlq1KhRnuecOHGiYmNj9de//lVxcXHy9PTUli1btG7dOnXs2LHA70NOIFSxYkXnunXr1ikqKkrNmjXThAkT5OHhoQULFuiee+7RN99848xwfP/99+rcubOqVq2qiRMnKjs7W3Fxcc6A6Urr1q3TRx99pCeffFIBAQEKCwtTamqq7rzzTucXd+XKlbVixQoNGTJE6enpeuaZZyRdKmeMGDFCffr00dNPP63z589r165d2rJlizMYfuyxx/Tvf/9bTz75pOrVq6eTJ09q06ZN+vnnn6/6mZYK9jmQpE2bNmnp0qV64okn5O3trTfeeEO9e/fWoUOHVKlSpQK//yiGDBQ7aWlphiSje/fu+do/KSnJkGQ88sgjLuufffZZQ5Kxbt0657rQ0FBDkpGQkOBcd+zYMcNutxujR492rtu/f78hyZg2bZrLOWNiYozQ0NBcfZgwYYJx+cfttddeMyQZx48fz7PfOW0sWLDAua5x48ZGYGCgcfLkSee6H374wfDw8DD+9re/5Wpv8ODBLufs2bOnUalSpTzbvPw6ypcvbxiGYfTp08do3769YRiGkZ2dbQQFBRkTJ0686ntw/vx5Izs7O9d12O12Iy4uzrlu27Ztua4tR9u2bQ1Jxty5c6+6rW3bti7rvv76a0OS8fLLLxu//vqrUaFCBaNHjx7XvUbDMAxJxvDhw/PcvmzZMue5L9enTx/DZrMZycnJhmEYxo4dOwxJxjPPPOOy38CBAw1JxoQJE5zrFixYYEgy9u/fbxiGYXz66aeGJGPbtm159uP48eO5zpPjys/W3r17DQ8PD6Nnz565fhYOhyPPNi4/1549e4zjx48bBw4cMObPn2+ULVvWqFy5spGRkeE8T+3atY1OnTq5nPPcuXNGjRo1jHvvvde5rlu3bka5cuWM33//3aWPpUuXNq78FSzJ8PDwMHbv3u2yfsiQIUbVqlWNEydOuKyPjo42fH19jXPnzhmGYRjdu3c36tevf81r9PX1vebP3DBy/zvO7+cg5xo8PT1d1v3www+GJGPmzJnXbBe3DsoixVB6erokydvbO1/7f/XVV5KkUaNGuawfPXq0JOUam1GvXj3nX9PSpb8c69Spo19//bXQfb5SzliNzz77LN8Dx44ePaqkpCQNHDhQ/v7+zvWNGjXSvffe67zOyz322GMur++++26dPHnS+R7mR79+/bRhwwalpKRo3bp1SklJuWpJRLo0TsPD49I/q+zsbJ08edJZ8rk87Xw9drtdgwYNyte+HTt21KOPPqq4uDj16tVLXl5eeuutt/Ld1rV89dVXKlWqlEaMGOGyfvTo0TIMQytWrJAkZ8r7iSeecNnvqaeeum4bOZ+F5cuXKzMz0+0+L1u2TA6HQ+PHj3f+LHLkd8pqnTp1VLlyZYWFhWnw4MGqVauWVqxYoXLlykmSkpKSnKWxkydP6sSJEzpx4oQyMjLUvn17JSQkyOFwKDs7W2vWrFGPHj1cski1atVSVFTUVdtu27at6tWr53xtGIY++eQTdevWTYZhONs6ceKEOnXqpLS0NOdny8/PT7/99pu2bduW57X5+flpy5YtBSqZ5fdzkKNDhw4KDw93vm7UqJF8fHxM/R2CmxvBRTHk4+Mj6VLtND8OHjwoDw8P1apVy2V9UFCQ/Pz8dPDgQZf11atXz3WOihUr6o8//ihkj3N76KGH1Lp1az3yyCOqUqWKoqOj9dFHH10z0MjpZ506dXJtq1u3rvOX++WuvJactHZBrqVLly7y9vbWkiVLtGjRIt1xxx253sscDodDr732mmrXri273a6AgABVrlxZu3btUlpaWr7b/Mtf/lKgwZuvvPKK/P39lZSUpDfeeEOBgYH5PvZaDh48qODg4FyBbN26dZ3bc/7r4eGhGjVquOyX1/t0ubZt26p3796aOHGiAgIC1L17dy1YsCDXeKD82rdvnzw8PFy+oAvqk08+0erVq7V48WLdeeedOnbsmMqWLevcvnfvXkmXxrxUrlzZZXn77bd14cIFpaWl6dixY/rzzz+v+j7k9d5c+R4eP35cp0+f1rx583K1lROAHjt2TJI0duxYVahQQS1atFDt2rU1fPjwXKXGqVOn6scff1RISIhatGih2NjY637p5/dzkONG/A7BzY0xF8WQj4+PgoOD9eOPPxbouPz+1ZbXSH7jioFbBWkjOzvb5XXZsmWVkJCg9evX68svv9TKlSu1ZMkS3XPPPVq1apVpswncuZYcdrtdvXr10jvvvKNff/3VZXDilf7xj3/oxRdf1ODBg/XSSy/J399fHh4eeuaZZwo0te/yL7L8+P77751fMP/5z3/Ut2/fAh1flGw2m/79739r8+bN+uKLL/T1119r8ODBevXVV7V58+YCj+cxQ5s2bZyzRbp166aGDRuqf//+2rFjhzw8PJw/y2nTpuU5lbhChQqFmqp85c8+p60BAwYoJibmqsfkjD+pW7eu9uzZo+XLl2vlypX65JNPNHv2bI0fP945lffBBx/U3XffrU8//VSrVq3StGnT9M9//lNLly7NM5tSUGb8u0PxRuaimLrvvvu0b98+JSYmXnff0NBQORwO519bOVJTU3X69GnnzA8zVKxY8ao3G7ryLxtJ8vDwUPv27TV9+nT99NNPmjRpktatW6f169df9dw5/dyzZ0+ubb/88osCAgJUvnx59y4gD/369dP333+vM2fOKDo6Os/9/v3vf6tdu3aKj49XdHS0OnbsqA4dOuR6T8y8o2RGRoYGDRqkevXqadiwYZo6deo10+IFERoaqiNHjuTKkv3yyy/O7Tn/dTgc2r9/v8t+ycnJ+W7rzjvv1KRJk7R9+3YtWrRIu3fv1ocffiipYO9XeHi4HA6Hfvrpp3wfcy0VKlTQhAkTlJSUpI8++sjZhnQp0O/QocNVlzJlyigwMFBeXl5XfR/y+95UrlxZ3t7eys7OzrOtyzNV5cuX10MPPaQFCxbo0KFD6tq1qyZNmuQS6FStWlVPPPGEli1bpv3796tSpUqaNGlSnn3I7+cAyEFwUUw999xzKl++vB555BGlpqbm2r5v3z69/vrrki6l9SVpxowZLvtMnz5dkvI1oj+/wsPDlZaWpl27djnXHT16NNeMlFOnTuU6NucvwLzS4VWrVlXjxo31zjvvuHxZ//jjj1q1apXzOq3Qrl07vfTSS3rzzTcVFBSU536lSpXK9dfZxx9/rN9//91lXU4QZMZdH8eOHatDhw7pnXfe0fTp0xUWFqaYmJhClxUu16VLF2VnZ+vNN990Wf/aa6/JZrM5/9Lt1KmTJGn27Nku+82cOfO6bfzxxx+53rMrPws5Yx3y83716NFDHh4eiouLy5UtKuxfzv3791e1atWcs4yaNWum8PBwvfLKKzp79myu/XPuA1OqVCl16NBBy5YtcxnjkJycnGucQl5KlSql3r1765NPPrlqtjKnLenSLKPLeXp6ql69ejIMQ5mZmcrOzs5VngsMDFRwcPA1Py/5/RwAOSiLFFPh4eFavHixHnroIdWtW9flDp3fffedPv74Yw0cOFCSFBERoZiYGM2bN0+nT59W27ZttXXrVr3zzjvq0aOH2rVrZ1q/oqOjNXbsWPXs2VMjRozQuXPnNGfOHN12220uAxrj4uKUkJCgrl27KjQ0VMeOHdPs2bNVrVo13XXXXXmef9q0aYqKilKrVq00ZMgQ51RUX1/fa5Yr3OXh4aEXXnjhuvvdd999iouL06BBg/TXv/5V//nPf7Ro0SLVrFnTZb/w8HD5+flp7ty58vb2Vvny5dWyZctc9fbrWbdunWbPnq0JEyY4pxEuWLBAkZGRevHFFzV16tTrnmP79u16+eWXc62PjIxUt27d1K5dOz3//PM6cOCAIiIitGrVKn322Wd65plnnH/BN2vWTL1799aMGTN08uRJ51TU//73v5KunXl45513NHv2bPXs2VPh4eE6c+aM/vWvf8nHx8cZMJYtW1b16tXTkiVLdNttt8nf318NGjRQgwYNcp2vVq1aev755/XSSy/p7rvvVq9evWS327Vt2zYFBwdr8uTJ139jr1CmTBk9/fTTGjNmjFauXKnOnTvr7bffVlRUlOrXr69BgwbpL3/5i37//XetX79ePj4++uKLLyRdug/HqlWr1Lp1az3++OPOL+kGDRrk+/bvU6ZM0fr169WyZUsNHTpU9erV06lTp7Rz506tWbPGGax37NhRQUFBat26tapUqaKff/5Zb775prp27Spvb2+dPn1a1apVU58+fRQREaEKFSpozZo12rZtm1599dU828/v5wBwKqJZKjDJf//7X2Po0KFGWFiY4enpaXh7exutW7c2Zs6caZw/f965X2ZmpjFx4kSjRo0aRpkyZYyQkBBj3LhxLvsYxqWpqF27ds3VzpVTIPOaimoYhrFq1SqjQYMGhqenp1GnTh3j/fffzzVdcO3atUb37t2N4OBgw9PT0wgODjb69u1r/Pe//83VxpXTNdesWWO0bt3aKFu2rOHj42N069bN+Omnn1z2yWnvyqmuV06DzMvlU1HzktdU1NGjRxtVq1Y1ypYta7Ru3dpITEy86hTSzz77zKhXr55zSmLOdbZt2zbP6YSXnyc9Pd0IDQ01mjZtamRmZrrsN3LkSMPDw8NITEy85jVIynN56aWXDMMwjDNnzhgjR440goODjTJlyhi1a9c2pk2blmtaZ0ZGhjF8+HDD39/fOR12z549hiRjypQpzv2u/Bns3LnT6Nu3r1G9enXDbrcbgYGBxn333Wds377d5fzfffed0axZM8PT09NlWuqVn60c8+fPN5o0aWLY7XajYsWKRtu2bY3Vq1df8/3I63NjGJemgPv6+rr8HL///nujV69eRqVKlQy73W6EhoYaDz74oLF27VqXY9euXWs0adLE8PT0NMLDw423337bGD16tOHl5ZXr55HXNNHU1FRj+PDhRkhIiFGmTBkjKCjIaN++vTFv3jznPm+99ZbRpk0bZ3/Cw8ONMWPGGGlpaYZhGMaFCxeMMWPGGBEREYa3t7dRvnx5IyIiwpg9e7ZLW1ebUp7fz0Fe1xAaGmrExMRc9dpw67EZBiNsAFgjKSlJTZo00fvvv6/+/fsXdXduKj169NDu3btzjYUCbgWMuQBgiqs9PXbGjBny8PBQmzZtiqBHN48r35u9e/fqq6++yvUQNuBWwZgLAKaYOnWqduzYoXbt2ql06dJasWKFVqxYoWHDhikkJKSou1ekatasqYEDB6pmzZo6ePCg5syZI09PTz333HNF3TXAEpRFAJhi9erVmjhxon766SedPXtW1atX18MPP6znn3/e9KeWFjeDBg3S+vXrlZKSIrvdrlatWukf//hHns/yAIo7ggsAAGAqxlwAAABTEVwAAABTlexCaCE4HA4dOXJE3t7ept7CGQBgPcMwdObMGQUHB+d6aq6Zzp8/r4sXL7p9Hk9PT3l5eZnQoxuL4KKAjhw5UuJHvgNAcXf48GFVq1bNknOfP39eNUIrKOVY9vV3vo6goCDt37+/2AUYBBcFlPPI4YM7w+RTgaoSbk09b2tY1F0ALJGlTG3SV7keH2+mixcvKuVYtvbvCJWPd+G/J9LPOFSj2UFdvHiR4OJWl1MK8ang4daHBriZlbaVKeouANb43/zIG1HW9vEuud8TBBcAAFgg23Ao242bPWQbjuvvdJMiuAAAwAIOGXKo8NGFO8cWNYILAAAs4JBD7uQe3Du6aJXMYhAAALAMmQsAACyQbRjKduMJG+4cW9QILgAAsEBJHnNBWQQAAJiKzAUAABZwyFB2Cc1cEFwAAGAByiIAAAAmIXMBAIAFmC0CAABM5fjf4s7xxRVlEQAAYCoyFwAAWCDbzdki7hxb1AguAACwQLYhN5+Kal5fbjSCCwAALMCYCwAAAJOQuQAAwAIO2ZQtm1vHF1cEFwAAWMBhXFrcOb64oiwCAABMReYCAAALZLtZFnHn2KJGcAEAgAVKcnBBWQQAgFtEQkKCunXrpuDgYNlsNi1btsxlu81mu+oybdo05z5hYWG5tk+ZMqVA/SBzAQCABRyGTQ7DjdkihTg2IyNDERERGjx4sHr16pVr+9GjR11er1ixQkOGDFHv3r1d1sfFxWno0KHO197e3gXqB8EFAAAWKIqySFRUlKKiovLcHhQU5PL6s88+U7t27VSzZk2X9d7e3rn2LQjKIgAA3MTS09NdlgsXLphy3tTUVH355ZcaMmRIrm1TpkxRpUqV1KRJE02bNk1ZWVkFOjeZCwAALJAtD2W78Td89v/+GxIS4rJ+woQJio2NLXzH/uedd96Rt7d3rvLJiBEj1LRpU/n7++u7777TuHHjdPToUU2fPj3f5ya4AADAAoabYy6M/x17+PBh+fj4ONfb7Xa3+yZJ8+fPV//+/eXl5eWyftSoUc7/b9SokTw9PfXoo49q8uTJ+W6b4AIAAAuYNebCx8fHJbgwwzfffKM9e/ZoyZIl1923ZcuWysrK0oEDB1SnTp18nZ8xFwAAlDDx8fFq1qyZIiIirrtvUlKSPDw8FBgYmO/zk7kAAMAC2YaHsg03xlwU4tkiZ8+eVXJysvP1/v37lZSUJH9/f1WvXl3SpQGiH3/8sV599dVcxycmJmrLli1q166dvL29lZiYqJEjR2rAgAGqWLFivvtBcAEAgAUcssnhRoHAoYJHF9u3b1e7du2cr3PGT8TExGjhwoWSpA8//FCGYahv3765jrfb7frwww8VGxurCxcuqEaNGho5cqTLOIz8ILgAAOAWERkZKcO4dlAybNgwDRs27KrbmjZtqs2bN7vdD4ILAAAsUJKfLUJwAQCABdwfc1GIQRc3CWaLAAAAU5G5AADAApcGdLrx4DLKIgAA4HION2//XZjZIjcLyiIAAMBUZC4AALBASR7QSXABAIAFHPK44TfRulkQXAAAYIFsw6ZsN56K6s6xRY0xFwAAwFRkLgAAsEC2m7NFsimLAACAyzkMDzncGNDpKMYDOimLAAAAU5G5AADAApRFAACAqRxyb8aHw7yu3HCURQAAgKnIXAAAYAH3b6JVfP/+J7gAAMAC7t/+u/gGF8W35wAA4KZE5gIAAAs4ZJND7gzoLL63/ya4AADAAiW5LEJwAQCABdy/z0XxDS6Kb88BAMBNicwFAAAWcBg2Ody5iVYxfuQ6wQUAABZwuFkWKc73uSi+PQcAADclMhcAAFjA/UeuF9+//wkuAACwQLZsynbjXhXuHFvUim9YBAAAbkpkLgAAsABlEQAAYKpsuVfayDavKzdc8Q2LAADATYnMBQAAFqAsAgAATMWDywAAgKkMNx+5bjAVFQAA4BIyFwAAWICyCAAAMFVJfipq8Q2LAACAi4SEBHXr1k3BwcGy2WxatmyZy/aBAwfKZrO5LJ07d3bZ59SpU+rfv798fHzk5+enIUOG6OzZswXqB8EFAAAWyP7fI9fdWQoqIyNDERERmjVrVp77dO7cWUePHnUuH3zwgcv2/v37a/fu3Vq9erWWL1+uhIQEDRs2rED9oCwCAIAFzCqLpKenu6y32+2y2+1XPSYqKkpRUVHXPK/dbldQUNBVt/38889auXKltm3bpubNm0uSZs6cqS5duuiVV15RcHBwvvpO5gIAgJtYSEiIfH19ncvkyZPdOt+GDRsUGBioOnXq6PHHH9fJkyed2xITE+Xn5+cMLCSpQ4cO8vDw0JYtW/LdBpkLAAAs4JCHHG78DZ9z7OHDh+Xj4+Ncn1fWIj86d+6sXr16qUaNGtq3b5/+/ve/KyoqSomJiSpVqpRSUlIUGBjockzp0qXl7++vlJSUfLdDcAEAgAWyDZuy3SiL5Bzr4+PjEly4Izo62vn/DRs2VKNGjRQeHq4NGzaoffv2prQhURYBAKDEqlmzpgICApScnCxJCgoK0rFjx1z2ycrK0qlTp/Icp3E1BBcAAFggZ0CnO4vVfvvtN508eVJVq1aVJLVq1UqnT5/Wjh07nPusW7dODodDLVu2zPd5KYsAAGABw82nohqFOPbs2bPOLIQk7d+/X0lJSfL395e/v78mTpyo3r17KygoSPv27dNzzz2nWrVqqVOnTpKkunXrqnPnzho6dKjmzp2rzMxMPfnkk4qOjs73TBGJzAUAAJbIls3tpaC2b9+uJk2aqEmTJpKkUaNGqUmTJho/frxKlSqlXbt26f7779dtt92mIUOGqFmzZvrmm29cBokuWrRIt99+u9q3b68uXbrorrvu0rx58wrUDzIXAADcIiIjI2UYRp7bv/766+uew9/fX4sXL3arHwQXAABYwGG493wQR94xwk2P4AIAAAs43Bxz4c6xRa349vwqrvaQFgAAcGMVKrjIuZNX165dC3xsWFiYZsyYUZhmTTFr1iyFhYXJy8tLLVu21NatW4usLwCAW5dDNreX4qpQwUV8fLyeeuopJSQk6MiRI2b3yTJLlizRqFGjNGHCBO3cuVMRERHq1KlTrhuGAADgrpw7dLqzFFcFDi7Onj2rJUuW6PHHH1fXrl21cOHCXPt88cUXuuOOO+Tl5aWAgAD17NlT0qVRrAcPHtTIkSOdz5GXpNjYWDVu3NjlHDNmzFBYWJjz9bZt23TvvfcqICBAvr6+atu2rXbu3Fmgvk+fPl1Dhw7VoEGDVK9ePc2dO1flypXT/PnzC3QeAACQtwIHFx999JFuv/121alTRwMGDND8+fNdpr18+eWX6tmzp7p06aLvv/9ea9euVYsWLSRJS5cuVbVq1RQXF+d8jnx+nTlzRjExMdq0aZM2b96s2rVrq0uXLjpz5ky+jr948aJ27NihDh06ONd5eHioQ4cOSkxMzPO4CxcuKD093WUBAOB6cgZ0urMUVwWeLRIfH68BAwZIuvR0tbS0NG3cuFGRkZGSpEmTJik6OloTJ050HhMRESHp0tzZUqVKydvbu0D3KJeke+65x+X1vHnz5Ofnp40bN+q+++677vEnTpxQdna2qlSp4rK+SpUq+uWXX/I8bvLkyS7XAgBAfjjk3i28S8yYiz179mjr1q3q27evpEuPYX3ooYcUHx/v3CcpKcnUJ6vlSE1N1dChQ1W7dm35+vrKx8dHZ8+e1aFDh0xv63Ljxo1TWlqaczl8+LCl7QEAUNwVKHMRHx+vrKwsl/uLG4Yhu92uN998U76+vipbtmyBO+Hh4ZHrjmKZmZkur2NiYnTy5Em9/vrrCg0Nld1uV6tWrXTx4sV8tREQEKBSpUopNTXVZX1qauo1syh2u93ltqgAAOSH4eaMD6MkZC6ysrL07rvv6tVXX1VSUpJz+eGHHxQcHKwPPvhAktSoUSOtXbs2z/N4enoqOzvbZV3lypWVkpLiEmAkJSW57PPtt99qxIgR6tKli+rXry+73a4TJ07kt/vy9PRUs2bNXPrmcDi0du1atWrVKt/nAQAgP4rDU1Gtku/MxfLly/XHH39oyJAh8vX1ddnWu3dvxcfH67HHHtOECRPUvn17hYeHKzo6WllZWfrqq680duxYSZfuc5GQkKDo6GjZ7XYFBAQoMjJSx48f19SpU9WnTx+tXLlSK1askI+Pj7ON2rVr67333lPz5s2Vnp6uMWPGFDhLMmrUKMXExKh58+Zq0aKFZsyYoYyMDA0aNKhA5wEA4Hq4Q2c+xMfHq0OHDrkCC+lScLF9+3bt2rVLkZGR+vjjj/X555+rcePGuueee1xuVBUXF6cDBw4oPDxclStXlnTpEa+zZ8/WrFmzFBERoa1bt+rZZ5/N1f4ff/yhpk2b6uGHH9aIESMUGBhYoIt96KGH9Morr2j8+PFq3LixkpKStHLlylyDPAEAQOHZjGs9Pg25pKeny9fXV3/8t6Z8vItvVAlcS6fgxkXdBcASWUamNugzpaWluWTHzZTzPdF91WCVKe9Z6PNkZlzUZx3nW9pXq/DgMgAALODuLbxLzFRUAACA6yFzAQCABdyd8VEiZosAAID8K8nBBWURAABgKjIXAABYoCRnLgguAACwQEkOLiiLAAAAU5G5AADAAobcu1dFcb7DJcEFAAAWKMllEYILAAAsUJKDC8ZcAAAAU5G5AADAAiU5c0FwAQCABUpycEFZBAAAmIrMBQAAFjAMmww3sg/uHFvUCC4AALCAQza37nPhzrFFjbIIAAAwFZkLAAAsUJIHdBJcAABggZI85oKyCAAAMBWZCwAALEBZBAAAmIqyCAAAMJXxv8xFYZfCBBcJCQnq1q2bgoODZbPZtGzZMue2zMxMjR07Vg0bNlT58uUVHBysv/3tbzpy5IjLOcLCwmSz2VyWKVOmFKgfBBcAANwiMjIyFBERoVmzZuXadu7cOe3cuVMvvviidu7cqaVLl2rPnj26//77c+0bFxeno0ePOpennnqqQP2gLAIAgAUMSYbh3vEFFRUVpaioqKtu8/X11erVq13Wvfnmm2rRooUOHTqk6tWrO9d7e3srKCioED24hMwFAAAWyLlDpzuLJKWnp7ssFy5cMK2PaWlpstls8vPzc1k/ZcoUVapUSU2aNNG0adOUlZVVoPOSuQAA4CYWEhLi8nrChAmKjY11+7znz5/X2LFj1bdvX/n4+DjXjxgxQk2bNpW/v7++++47jRs3TkePHtX06dPzfW6CCwAALGDWbJHDhw+7fPnb7Xa3+5aZmakHH3xQhmFozpw5LttGjRrl/P9GjRrJ09NTjz76qCZPnpzvtgkuAACwgMOwyWbCfS58fHxcggt35QQWBw8e1Lp166577pYtWyorK0sHDhxQnTp18tUGwQUAACVETmCxd+9erV+/XpUqVbruMUlJSfLw8FBgYGC+2yG4AADAAobh5myRQhx79uxZJScnO1/v379fSUlJ8vf3V9WqVdWnTx/t3LlTy5cvV3Z2tlJSUiRJ/v7+8vT0VGJiorZs2aJ27drJ29tbiYmJGjlypAYMGKCKFSvmux8EFwAAWKAo7tC5fft2tWvXzvk6Z/xETEyMYmNj9fnnn0uSGjdu7HLc+vXrFRkZKbvdrg8//FCxsbG6cOGCatSooZEjR7qMw8gPggsAAG4RkZGRMq6R8rjWNklq2rSpNm/e7HY/CC4AALBASX62CMEFAAAWMGu2SHFEcAEAgAWKYkDnzYLbfwMAAFORuQAAwAKXMhfujLkwsTM3GMEFAAAWKMkDOimLAAAAU5G5AADAAsb/FneOL64ILgAAsABlEQAAAJOQuQAAwAoluC5CcAEAgBXcLIuoGJdFCC4AALAAd+gEAAAwCZkLAAAsUJJnixBcAABgBcPm3riJYhxcUBYBAACmInMBAIAFSvKAToILAACsUILvc0FZBAAAmIrMBQAAFmC2CAAAMF8xLm24g7IIAAAwFZkLAAAsQFkEAACYqwTPFiG4AADAErb/Le4cXzwx5gIAAJiKzAUAAFagLAIAAExVgoMLyiIAAMBUZC4AALBCCX7kOsEFAAAWKMlPRaUsAgAATEXmAgAAK5TgAZ0EFwAAWKEEj7mgLAIAAExF5gIAAAvYjEuLO8cXVwQXAABYoQSPuaAsAgCAFXLGXLizFFBCQoK6deum4OBg2Ww2LVu2zLVLhqHx48eratWqKlu2rDp06KC9e/e67HPq1Cn1799fPj4+8vPz05AhQ3T27NkC9YPgAgCAW0RGRoYiIiI0a9asq26fOnWq3njjDc2dO1dbtmxR+fLl1alTJ50/f965T//+/bV7926tXr1ay5cvV0JCgoYNG1agflAWAQDACkVQFomKilJUVNTVT2cYmjFjhl544QV1795dkvTuu++qSpUqWrZsmaKjo/Xzzz9r5cqV2rZtm5o3by5Jmjlzprp06aJXXnlFwcHB+eoHmQsAAKxgmLBISk9Pd1kuXLhQqO7s379fKSkp6tChg3Odr6+vWrZsqcTERElSYmKi/Pz8nIGFJHXo0EEeHh7asmVLvtsiuAAA4CYWEhIiX19f5zJ58uRCnSclJUWSVKVKFZf1VapUcW5LSUlRYGCgy/bSpUvL39/fuU9+UBYBAMAKJpVFDh8+LB8fH+dqu93uVrduBDIXAABYwaTZIj4+Pi5LYYOLoKAgSVJqaqrL+tTUVOe2oKAgHTt2zGV7VlaWTp065dwnPwguAAAoAWrUqKGgoCCtXbvWuS49PV1btmxRq1atJEmtWrXS6dOntWPHDuc+69atk8PhUMuWLfPdFmURAAAsUBR36Dx79qySk5Odr/fv36+kpCT5+/urevXqeuaZZ/Tyyy+rdu3aqlGjhl588UUFBwerR48ekqS6deuqc+fOGjp0qObOnavMzEw9+eSTio6OzvdMEYngAgAAaxTBVNTt27erXbt2ztejRo2SJMXExGjhwoV67rnnlJGRoWHDhun06dO66667tHLlSnl5eTmPWbRokZ588km1b99eHh4e6t27t954440C9YPgAgCAW0RkZKQMI++oxGazKS4uTnFxcXnu4+/vr8WLF7vVD8ZcAAAAU5G5AADAAja5OebCtJ7ceAQXhdSrfjOVtpUp6m4AlvDwvvnn0QOF4WFclM7coMYK+fAxl+OLKcoiAADAVGQuAACwQhHMFrlZEFwAAGCFEhxcUBYBAACmInMBAIAFiuIOnTcLggsAAKxAWQQAAMAcZC4AALBCCc5cEFwAAGCBkjzmgrIIAAAwFZkLAACsUIJv/01wAQCAFRhzAQAAzMSYCwAAAJOQuQAAwAqURQAAgKncLIsU5+CCsggAADAVmQsAAKxAWQQAAJiqBAcXlEUAAICpyFwAAGAB7nMBAABgEoILAABgKsoiAABYoQQP6CS4AADAAiV5zAXBBQAAVinGAYI7GHMBAABMReYCAAArMOYCAACYqSSPuaAsAgAATEXmAgAAK1AWAQAAZqIsAgAAYBIyFwAAWIGyCAAAMFUJDi4oiwAAcAsICwuTzWbLtQwfPlySFBkZmWvbY489ZklfyFwAAGCBGz2gc9u2bcrOzna+/vHHH3XvvffqgQcecK4bOnSo4uLinK/LlStX+A5eA8EFAABWMKkskp6e7rLabrfLbrfn2r1y5cour6dMmaLw8HC1bdvWua5cuXIKCgpyo1P5Q1kEAAArGCYskkJCQuTr6+tcJk+efN2mL168qPfff1+DBw+WzWZzrl+0aJECAgLUoEEDjRs3TufOnTPral2QuQAA4CZ2+PBh+fj4OF9fLWtxpWXLlun06dMaOHCgc12/fv0UGhqq4OBg7dq1S2PHjtWePXu0dOlS0/tMcAEAgAXMGnPh4+PjElzkR3x8vKKiohQcHOxcN2zYMOf/N2zYUFWrVlX79u21b98+hYeHF76jV0FZBAAAK5hUFimogwcPas2aNXrkkUeuuV/Lli0lScnJyYVr6BoILgAAuIUsWLBAgYGB6tq16zX3S0pKkiRVrVrV9D5QFgEAwAJF8WwRh8OhBQsWKCYmRqVL//+v+H379mnx4sXq0qWLKlWqpF27dmnkyJFq06aNGjVqVPhO5oHgAgAAKxTBHTrXrFmjQ4cOafDgwS7rPT09tWbNGs2YMUMZGRkKCQlR79699cILL7jRwbwRXAAAcIvo2LGjDCN3VBISEqKNGzfesH4QXAAAYIUS/GwRggsAACxg+9/izvHFFbNFAACAqchcAABgBcoiAADATEUxFfVmQXABAIAVSnDmgjEXAADAVGQuAACwSjHOPriD4AIAAAuU5DEXlEUAAICpyFwAAGCFEjygk+ACAAALUBYBAAAwCZkLAACsQFkEAACYibIIAACASchcAABgBcoiAADAVAQXAADATIy5AAAAMAmZCwAArEBZBAAAmMlmGLIZhY8Q3Dm2qFEWAQAApiJzAQCAFSiLAAAAMzFbBAAAwCRkLgAAsAJlEQAAYCbKIgAAACYhcwEAgBUoiwAAADOV5LIIwQUAAFYowZkLxlwAAABTkbkAAMAixbm04Q6CCwAArGAYlxZ3ji+mKIsAAABTkbkAAMACJXm2CJkLAACsYJiwFEBsbKxsNpvLcvvttzu3nz9/XsOHD1elSpVUoUIF9e7dW6mpqW5e5NURXAAAcIuoX7++jh496lw2bdrk3DZy5Eh98cUX+vjjj7Vx40YdOXJEvXr1sqQflEUAALCAzXFpcef4gipdurSCgoJyrU9LS1N8fLwWL16se+65R5K0YMEC1a1bV5s3b9add95Z+I5eBZkLAACsYFJZJD093WW5cOFCnk3u3btXwcHBqlmzpvr3769Dhw5Jknbs2KHMzEx16NDBue/tt9+u6tWrKzEx0dTLlm6x4MJms2nZsmVF3Q0AAEwTEhIiX19f5zJ58uSr7teyZUstXLhQK1eu1Jw5c7R//37dfffdOnPmjFJSUuTp6Sk/Pz+XY6pUqaKUlBTT+1yo4CIxMVGlSpVS165dC3xsWFiYZsyYUZhm3ZaQkKBu3bopODiYQAQAYKmc2SLuLJJ0+PBhpaWlOZdx48Zdtb2oqCg98MADatSokTp16qSvvvpKp0+f1kcffXQDr/qSQgUX8fHxeuqpp5SQkKAjR46Y3SfLZGRkKCIiQrNmzSrqrgAAbnU5N9FyZ5Hk4+Pjstjt9nw17+fnp9tuu03JyckKCgrSxYsXdfr0aZd9UlNTrzpGw10FDi7Onj2rJUuW6PHHH1fXrl21cOHCXPt88cUXuuOOO+Tl5aWAgAD17NlTkhQZGamDBw9q5MiRzmky0qXpM40bN3Y5x4wZMxQWFuZ8vW3bNt17770KCAiQr6+v2rZtq507dxao71FRUXr55Zed/QEAwCpmZS4K6+zZs9q3b5+qVq2qZs2aqUyZMlq7dq1z+549e3To0CG1atXKzSvNrcDBxUcffaTbb79dderU0YABAzR//nwZl92i9Msvv1TPnj3VpUsXff/991q7dq1atGghSVq6dKmqVaumuLg45zSZ/Dpz5oxiYmK0adMmbd68WbVr11aXLl105syZgl5CgVy4cCHXYBoAAG42zz77rDZu3KgDBw7ou+++U8+ePVWqVCn17dtXvr6+GjJkiEaNGqX169drx44dGjRokFq1amX6TBGpEFNR4+PjNWDAAElS586dlZaWpo0bNyoyMlKSNGnSJEVHR2vixInOYyIiIiRJ/v7+KlWqlLy9vQuchsmZOpNj3rx58vPz08aNG3XfffcV9DLybfLkyS7XAgBAvtzgR67/9ttv6tu3r06ePKnKlSvrrrvu0ubNm1W5cmVJ0muvvSYPDw/17t1bFy5cUKdOnTR79mw3Opi3AgUXe/bs0datW/Xpp59eOrh0aT300EOKj493BhdJSUkaOnSo6R1NTU3VCy+8oA0bNujYsWPKzs7WuXPnnNNsrDJu3DiNGjXK+To9PV0hISGWtgkAKP5u9O2/P/zww2tu9/Ly0qxZs27IuMMCBRfx8fHKyspScHCwc51hGLLb7XrzzTfl6+ursmXLFrgTHh4eLqUVScrMzHR5HRMTo5MnT+r1119XaGio7Ha7WrVqpYsXLxa4vYKw2+35HjwDAAAKMOYiKytL7777rl599VUlJSU5lx9++EHBwcH64IMPJEmNGjVyGTByJU9PT2VnZ7usq1y5slJSUlwCjKSkJJd9vv32W40YMUJdunRR/fr1ZbfbdeLEifx2HwCAG8uk2SLFUb4zF8uXL9cff/yhIUOGyNfX12Vb7969FR8fr8cee0wTJkxQ+/btFR4erujoaGVlZemrr77S2LFjJV26z0VCQoKio6Nlt9sVEBCgyMhIHT9+XFOnTlWfPn20cuVKrVixQj4+Ps42ateurffee0/NmzdXenq6xowZU+AsydmzZ5WcnOx8vX//fiUlJcnf31/Vq1cv0LkAALgWnoqaD/Hx8erQoUOuwEK6FFxs375du3btUmRkpD7++GN9/vnnaty4se655x5t3brVuW9cXJwOHDig8PBw5yCTunXravbs2Zo1a5YiIiK0detWPfvss7na/+OPP9S0aVM9/PDDGjFihAIDAwt0sdu3b1eTJk3UpEkTSdKoUaPUpEkTjR8/vkDnAQAAebMZVw52wDWlp6fL19dX7co8oNK2MkXdHcASNi/GGeHWlGVc1Lozi5SWluaSHTdTzvdEq85xKl3Gq9Dnyco8r8SV4y3tq1V4KioAABagLAIAAGASMhcAAFjBYVxa3Dm+mCK4AADACjf4Dp03E4ILAAAsYJObYy5M68mNx5gLAABgKjIXAABYwd27bBbjO0UQXAAAYAGmogIAAJiEzAUAAFZgtggAADCTzTBkc2PchDvHFjXKIgAAwFRkLgAAsILjf4s7xxdTBBcAAFiAsggAAIBJyFwAAGAFZosAAABTcYdOAABgJu7QCQAAYBIyFwAAWIGyCAAAMJPNcWlx5/jiirIIAAAwFZkLAACsQFkEAACYqgTf54KyCAAAMBWZCwAALFCSny1CcAEAgBVK8JgLyiIAAMBUZC4AALCCIcmde1UU38QFwQUAAFZgzAUAADCXITfHXJjWkxuOMRcAAMBUZC4AALACs0UAAICpHCYsBTB58mTdcccd8vb2VmBgoHr06KE9e/a47BMZGSmbzeayPPbYY25c5NURXAAAcAvYuHGjhg8frs2bN2v16tXKzMxUx44dlZGR4bLf0KFDdfToUecydepU0/tCWQQAAAvc6NkiK1eudHm9cOFCBQYGaseOHWrTpo1zfbly5RQUFFTofuUHmQsAAKyQM+bCnUVSenq6y3LhwoV8NZ+WliZJ8vf3d1m/aNEiBQQEqEGDBho3bpzOnTtn7nWLzAUAADe1kJAQl9cTJkxQbGzsNY9xOBx65pln1Lp1azVo0MC5vl+/fgoNDVVwcLB27dqlsWPHas+ePVq6dKmpfSa4AADACibNFjl8+LB8fHycq+12+3UPHT58uH788Udt2rTJZf2wYcOc/9+wYUNVrVpV7du31759+xQeHl74vl6B4AIAACuYFFz4+Pi4BBfX8+STT2r58uVKSEhQtWrVrrlvy5YtJUnJyckEFwAAwJVhGHrqqaf06aefasOGDapRo8Z1j0lKSpIkVa1a1dS+EFwAAGAFhySbm8cXwPDhw7V48WJ99tln8vb2VkpKiiTJ19dXZcuW1b59+7R48WJ16dJFlSpV0q5duzRy5Ei1adNGjRo1cqOjuRFcAABggRs9FXXOnDmSLt0o63ILFizQwIED5enpqTVr1mjGjBnKyMhQSEiIevfurRdeeKHQfcwLwQUAAFa4wbf/Nq6zf0hIiDZu3Fj4/hQA97kAAACmInMBAIAVHIZkcyNz4Si+Dy4juAAAwAo8FRUAAMAcZC4AALCEm5kLFd/MBcEFAABWoCwCAABgDjIXAABYwWHIrdIGs0UAAIALw3Fpcef4YoqyCAAAMBWZCwAArFCCB3QSXAAAYAXGXAAAAFOV4MwFYy4AAICpyFwAAGAFQ25mLkzryQ1HcAEAgBUoiwAAAJiDzAUAAFZwOCS5cSMsR/G9iRbBBQAAVqAsAgAAYA4yFwAAWKEEZy4ILgAAsEIJvkMnZREAAGAqMhcAAFjAMBwy3HhsujvHFjWCCwAArGAY7pU2GHMBAABcGG6OuSjGwQVjLgAAgKnIXAAAYAWHQ7K5MW6CMRcAAMAFZREAAABzkLkAAMAChsMhw42yCFNRAQCAK8oiAAAA5iBzAQCAFRyGZCuZmQuCCwAArGAYktyZilp8gwvKIgAAwFRkLgAAsIDhMGS4URYxyFwAAAAXhsP9pRBmzZqlsLAweXl5qWXLltq6davJF3Z9BBcAAFjAcBhuLwW1ZMkSjRo1ShMmTNDOnTsVERGhTp066dixYxZcYd4ILgAAuEVMnz5dQ4cO1aBBg1SvXj3NnTtX5cqV0/z5829oPxhzUUA5NbAsI7OIewJYx2bYiroLgCVyfnffiPEMWcYFtx4+lqVLfU1PT3dZb7fbZbfbc+1/8eJF7dixQ+PGjXOu8/DwUIcOHZSYmFjofhQGwUUBnTlzRpL0Tdayou0IYCViZ9zizpw5I19fX0vO7enpqaCgIG1K+crtc1WoUEEhISEu6yZMmKDY2Nhc+544cULZ2dmqUqWKy/oqVarol19+cbsvBUFwUUDBwcE6fPiwvL29ZbPx153V0tPTFRISosOHD8vHx6eouwOYjs/4jWUYhs6cOaPg4GDL2vDy8tL+/ft18eJFt89lGEau75qrZS1uNgQXBeTh4aFq1aoVdTdKHB8fH37x4pbGZ/zGsSpjcTkvLy95eXlZ3s7lAgICVKpUKaWmprqsT01NVVBQ0A3tCwM6AQC4BXh6eqpZs2Zau3atc53D4dDatWvVqlWrG9oXMhcAANwiRo0apZiYGDVv3lwtWrTQjBkzlJGRoUGDBt3QfhBc4KZmt9s1YcKEYlFjBAqDzzjM9NBDD+n48eMaP368UlJS1LhxY61cuTLXIE+r2YzifH9RAABw02HMBQAAMBXBBQAAMBXBBQAAMBXBBQAAMBXBBYqtgQMHqkePHkXdDcAyfMZRXBFcwFQDBw6UzWaTzWaTp6enatWqpbi4OGVlZRVJf3bt2qW7775bXl5eCgkJ0dSpU4ukH7h13Eyf8fPnz2vgwIFq2LChSpcuTSCCmwbBBUzXuXNnHT16VHv37tXo0aMVGxuradOmXXVfM+69n5f09HR17NhRoaGh2rFjh6ZNm6bY2FjNmzfPsjZRMtwsn/Hs7GyVLVtWI0aMUIcOHSxrBygogguYzm63KygoSKGhoXr88cfVoUMHff7555L+f5p30qRJCg4OVp06dSRJhw8f1oMPPig/Pz/5+/ure/fuOnDggPOc2dnZGjVqlPz8/FSpUiU999xz131k8qJFi3Tx4kXNnz9f9evXV3R0tEaMGKHp06dbdu0oGW6Wz3j58uU1Z84cDR069IY/OwK4FoILWK5s2bIuf72tXbtWe/bs0erVq7V8+XJlZmaqU6dO8vb21jfffKNvv/1WFSpUUOfOnZ3Hvfrqq1q4cKHmz5+vTZs26dSpU/r000+v2W5iYqLatGkjT09P57pOnTppz549+uOPP6y5WJRIRfUZB25W3P4bljEMQ2vXrtXXX3+tp556yrm+fPnyevvtt51f+u+//74cDofefvtt56OFFyxYID8/P23YsEEdO3bUjBkzNG7cOPXq1UuSNHfuXH399dfXbD8lJUU1atRwWZdzC9yUlBRVrFjRtGtFyVTUn3HgZkVwAdMtX75cFSpUUGZmphwOh/r166fY2Fjn9oYNG7pkE3744QclJyfL29vb5Tznz5/Xvn37lJaWpqNHj6ply5bObaVLl1bz5s2vmzYGrMBnHLg2gguYrl27dpozZ448PT0VHBys0qVdP2bly5d3eX327Fk1a9ZMixYtynWuypUrF7ofQUFBSk1NdVmX85r6NNxxs3zGgZsVYy5guvLly6tWrVqqXr16rl+6V9O0aVPt3btXgYGBqlWrlsvi6+srX19fVa1aVVu2bHEek5WVpR07dlzzvK1atVJCQoIyMzOd61avXq06depQEoFbbpbPOHCzIrhAkevfv78CAgLUvXt3ffPNN9q/f782bNigESNG6LfffpMkPf3005oyZYqWLVumX375RU888YROnz59zfP269dPnp6eGjJkiHbv3q0lS5bo9ddf16hRo27AVQH/n1WfcUn66aeflJSUpFOnTiktLU1JSUlKSkqy9oKA66AsgiJXrlw5JSQkaOzYserVq5fOnDmjv/zlL2rfvr18fHwkSaNHj9bRo0cVExMjDw8PDR48WD179lRaWlqe5/X19dWqVas0fPhwNWvWTAEBARo/fryGDRt2oy4NkGTdZ1ySunTpooMHDzpfN2nSRJIYq4EiZTP4BAIAABNRFgEAAKYiuAAAAKYiuAAAAKYiuAAAAKYiuAAAAKYiuAAAAKYiuAAAAKYiuAAAAKYiuAAAAKYiuAAAAKYiuAAAAKb6fxsA9HSF/ysLAAAAAElFTkSuQmCC\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "x = np.arange(len(classes))\n",
+        "width = 0.25\n",
+        "\n",
+        "plt.figure()\n",
+        "plt.bar(x - width, precision, width, label=\"Precision\")\n",
+        "plt.bar(x, recall, width, label=\"Recall\")\n",
+        "plt.bar(x + width, f1, width, label=\"F1-Score\")\n",
+        "plt.xticks(x, classes)\n",
+        "plt.ylabel(\"Score\")\n",
+        "plt.title(\"Classification Metrics per Class (Logistic Regression)\")\n",
+        "plt.legend()\n",
+        "plt.ylim(0, 1)\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "5XsjRubu21tt",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 452
+        },
+        "outputId": "5c326aba-cbc8-4601-d722-be7d1d12c02a"
+      },
+      "execution_count": 66,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "plt.figure()\n",
+        "plt.plot(cv_scores, marker='o')\n",
+        "plt.title(\"Cross Validation Scores (Logistic Regression)\")\n",
+        "plt.xlabel(\"Fold\")\n",
+        "plt.ylabel(\"Score\")\n",
+        "plt.ylim(0, 1)\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "sF-dgugW28Dt",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 472
+        },
+        "outputId": "2426d410-f614-4401-b32b-5359963ac987"
+      },
+      "execution_count": 67,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "\n",
+        "from sklearn.model_selection import train_test_split, cross_val_score, StratifiedKFold\n",
+        "from sklearn.tree import DecisionTreeClassifier\n",
+        "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report\n",
+        "\n",
+        "import matplotlib.pyplot as plt\n",
+        "import seaborn as sns"
+      ],
+      "metadata": {
+        "id": "ddHu3Ditf64F"
+      },
+      "execution_count": 68,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "X.select_dtypes(include=['object']).columns"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "V2tkXdJzy4Cq",
+        "outputId": "99e24208-36b8-48c4-b494-635f58553e8a"
+      },
+      "execution_count": 69,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "Index([], dtype='object')"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 69
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "X = pd.get_dummies(X, drop_first=True)"
+      ],
+      "metadata": {
+        "id": "ajcLVhfnwd0t"
+      },
+      "execution_count": 70,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "y = pd.to_numeric(df[\"Klasifikasi Kemiskinan\"], errors='coerce')\n",
+        "y = y.fillna(0).astype(int)\n",
+        "\n",
+        "X = df.drop(\"Klasifikasi Kemiskinan\", axis=1)\n",
+        "\n",
+        "# Re-apply preprocessing steps from g_oElrw_xSFf\n",
+        "X = X.apply(lambda s: s.astype(str).str.replace(\",\", \".\").str.replace(\" \", \"\", regex=True))\n",
+        "\n",
+        "for col in X.columns:\n",
+        "    X[col] = pd.to_numeric(X[col], errors='coerce')\n",
+        "\n",
+        "label_enc = LabelEncoder()\n",
+        "X[\"Provinsi\"] = label_enc.fit_transform(X[\"Provinsi\"].astype(str))\n",
+        "X[\"Kab/Kota\"] = label_enc.fit_transform(X[\"Kab/Kota\"].astype(str))\n",
+        "\n",
+        "imputer = SimpleImputer(strategy='mean')\n",
+        "X[X.columns] = imputer.fit_transform(X)\n"
+      ],
+      "metadata": {
+        "id": "mJFidT4pkw_h"
+      },
+      "execution_count": 71,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from sklearn.model_selection import train_test_split\n",
+        "\n",
+        "X_train, X_test, y_train, y_test = train_test_split(\n",
+        "    X,\n",
+        "    y,\n",
+        "    test_size=0.2,\n",
+        "    random_state=42,\n",
+        "    stratify=y\n",
+        ")"
+      ],
+      "metadata": {
+        "id": "LxqkKvx8lDJh"
+      },
+      "execution_count": 72,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dt = DecisionTreeClassifier(random_state=42)\n",
+        "dt.fit(X_train, y_train)\n",
+        "\n",
+        "pred_dt = dt.predict(X_test)\n",
+        "\n",
+        "print(\"=== Decision Tree Accuracy ===\")\n",
+        "print(accuracy_score(y_test, pred_dt))\n",
+        "print(\"\\n=== Classification Report ===\")\n",
+        "print(classification_report(y_test, pred_dt))\n",
+        "print(\"\\n=== Confusion Matrix ===\")\n",
+        "print(confusion_matrix(y_test, pred_dt))\n",
+        "\n",
+        "cv_rf = cross_val_score(dt, X, y, cv=5)\n",
+        "print(\"\\n=== Cross Validation (Decision Tree) ===\")\n",
+        "print(cv_rf)\n",
+        "print(\"Mean CV Score:\", cv_rf.mean())"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "NWhQ1SKXf9PY",
+        "outputId": "4e93d1f8-827e-4075-cbca-767fdb48ce3a"
+      },
+      "execution_count": 79,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "=== Decision Tree Accuracy ===\n",
+            "0.985\n",
+            "\n",
+            "=== Classification Report ===\n",
+            "              precision    recall  f1-score   support\n",
+            "\n",
+            "           0       0.99      0.99      0.99       188\n",
+            "           1       0.91      0.83      0.87        12\n",
+            "\n",
+            "    accuracy                           0.98       200\n",
+            "   macro avg       0.95      0.91      0.93       200\n",
+            "weighted avg       0.98      0.98      0.98       200\n",
+            "\n",
+            "\n",
+            "=== Confusion Matrix ===\n",
+            "[[187   1]\n",
+            " [  2  10]]\n",
+            "\n",
+            "=== Cross Validation (Decision Tree) ===\n",
+            "[0.93       0.985      0.97       0.99       0.96984925]\n",
+            "Mean CV Score: 0.9689698492462311\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import matplotlib.pyplot as plt\n",
+        "import numpy as np\n",
+        "from sklearn.metrics import confusion_matrix\n",
+        "from sklearn.tree import DecisionTreeClassifier\n",
+        "\n",
+        "# Initialize and train the Decision Tree model\n",
+        "dt = DecisionTreeClassifier(random_state=42)\n",
+        "dt.fit(X_train, y_train)\n",
+        "\n",
+        "# Make predictions\n",
+        "y_pred = dt.predict(X_test)\n",
+        "\n",
+        "# Now, compute the confusion matrix\n",
+        "cm = confusion_matrix(y_test, y_pred)\n",
+        "\n",
+        "plt.figure()\n",
+        "plt.imshow(cm)\n",
+        "plt.title(\"Confusion Matrix - Decision Tree\")\n",
+        "plt.xlabel(\"Predicted Label\")\n",
+        "plt.ylabel(\"True Label\")\n",
+        "plt.xticks([0, 1], ['Kelas 0', 'Kelas 1'])\n",
+        "plt.yticks([0, 1], ['Kelas 0', 'Kelas 1'])\n",
+        "\n",
+        "# Menampilkan nilai di dalam matriks\n",
+        "for i in range(cm.shape[0]):\n",
+        "    for j in range(cm.shape[1]):\n",
+        "        plt.text(j, i, cm[i, j], ha='center', va='center')\n",
+        "\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 472
+        },
+        "id": "MrObTJ_GlwwV",
+        "outputId": "7aa74fa1-8bae-453a-fbcc-d4734f2c998c"
+      },
+      "execution_count": 73,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "accuracy = accuracy_score(y_test, y_pred)\n",
+        "\n",
+        "plt.figure()\n",
+        "plt.bar(['Decision Tree'], [accuracy])\n",
+        "plt.title('Accuracy Model Decision Tree')\n",
+        "plt.ylabel('Accuracy')\n",
+        "plt.ylim(0, 1)\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 452
+        },
+        "id": "r6NBUXRJmHQJ",
+        "outputId": "da84bac8-6747-4921-9a15-e880ea3b37ed"
+      },
+      "execution_count": 74,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from sklearn.metrics import classification_report\n",
+        "\n",
+        "report = classification_report(y_test, y_pred, output_dict=True)\n",
+        "\n",
+        "metrics = ['precision', 'recall', 'f1-score']\n",
+        "class_0 = [report['0'][m] for m in metrics]\n",
+        "class_1 = [report['1'][m] for m in metrics]\n",
+        "\n",
+        "x = np.arange(len(metrics))\n",
+        "width = 0.35\n",
+        "\n",
+        "plt.figure()\n",
+        "plt.bar(x - width/2, class_0, width, label='Kelas 0')\n",
+        "plt.bar(x + width/2, class_1, width, label='Kelas 1')\n",
+        "\n",
+        "plt.xticks(x, metrics)\n",
+        "plt.ylabel('Score')\n",
+        "plt.title('Precision, Recall, dan F1-Score per Kelas')\n",
+        "plt.legend()\n",
+        "plt.ylim(0, 1)\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 452
+        },
+        "id": "ZU8PYqK2mKs7",
+        "outputId": "9ba9f57c-1b11-4611-9508-4bd30034420c"
+      },
+      "execution_count": 75,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "kfold = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)\n",
+        "cv_scores = cross_val_score(\n",
+        "    estimator=dt,\n",
+        "    X=X,\n",
+        "    y=y,\n",
+        "    cv=kfold,\n",
+        "    scoring='accuracy'\n",
+        ")\n",
+        "print(\"Hasil Cross Validation per fold:\", cv_scores)\n",
+        "print(\"Rata-rata CV Accuracy:\", cv_scores.mean())"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "H7FNZpqhlXRJ",
+        "outputId": "8a885310-0a19-4a5c-f02f-d8170d14aa52"
+      },
+      "execution_count": 76,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Hasil Cross Validation per fold: [0.985      0.995      0.975      0.985      0.98994975]\n",
+            "Rata-rata CV Accuracy: 0.9859899497487437\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "plt.figure()\n",
+        "plt.plot(cv_scores, marker='o')\n",
+        "plt.title(\"Cross Validation Scores (Decision Tree)\")\n",
+        "plt.xlabel(\"Fold\")\n",
+        "plt.ylabel(\"Score\")\n",
+        "plt.ylim(0.9, 1.0)\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "vbOQrFNdxHjm",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 472
+        },
+        "outputId": "f0cbb1cd-f6c5-4eee-fee7-1638a7f31408"
+      },
+      "execution_count": 77,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    }
+  ]
+}
\ No newline at end of file