{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"authorship_tag":"ABX9TyMZvigX0h8yCq90ueauAQdK"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","execution_count":null,"metadata":{"id":"DG5gGFyhgE_K"},"outputs":[],"source":["import numpy as np\n","import pandas as pd\n","from sklearn.datasets import load_breast_cancer, fetch_california_housing\n","from sklearn.feature_selection import SelectFromModel\n","from sklearn.linear_model import Lasso, LogisticRegression\n","from sklearn.model_selection import train_test_split\n","from sklearn.preprocessing import StandardScaler"]},{"cell_type":"code","source":["breast_cancer = load_breast_cancer()\n","X = pd.DataFrame(breast_cancer.data, columns=breast_cancer.feature_names)\n","y = breast_cancer.target\n","X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)\n","X.head()"],"metadata":{"id":"S9s_HLXVgTvu","executionInfo":{"status":"ok","timestamp":1711273065702,"user_tz":-420,"elapsed":15,"user":{"displayName":"Nhật Quang Đoàn","userId":"10175964550021301622"}},"colab":{"base_uri":"https://localhost:8080/","height":290},"outputId":"fc6a6447-fff1-4074-c403-b56dfc50f79e"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["   mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\n","0        17.99         10.38          122.80     1001.0          0.11840   \n","1        20.57         17.77          132.90     1326.0          0.08474   \n","2        19.69         21.25          130.00     1203.0          0.10960   \n","3        11.42         20.38           77.58      386.1          0.14250   \n","4        20.29         14.34          135.10     1297.0          0.10030   \n","\n","   mean compactness  mean concavity  mean concave points  mean symmetry  \\\n","0           0.27760          0.3001              0.14710         0.2419   \n","1           0.07864          0.0869              0.07017         0.1812   \n","2           0.15990          0.1974              0.12790         0.2069   \n","3           0.28390          0.2414              0.10520         0.2597   \n","4           0.13280          0.1980              0.10430         0.1809   \n","\n","   mean fractal dimension  ...  worst radius  worst texture  worst perimeter  \\\n","0                 0.07871  ...         25.38          17.33           184.60   \n","1                 0.05667  ...         24.99          23.41           158.80   \n","2                 0.05999  ...         23.57          25.53           152.50   \n","3                 0.09744  ...         14.91          26.50            98.87   \n","4                 0.05883  ...         22.54          16.67           152.20   \n","\n","   worst area  worst smoothness  worst compactness  worst concavity  \\\n","0      2019.0            0.1622             0.6656           0.7119   \n","1      1956.0            0.1238             0.1866           0.2416   \n","2      1709.0            0.1444             0.4245           0.4504   \n","3       567.7            0.2098             0.8663           0.6869   \n","4      1575.0            0.1374             0.2050           0.4000   \n","\n","   worst concave points  worst symmetry  worst fractal dimension  \n","0                0.2654          0.4601                  0.11890  \n","1                0.1860          0.2750                  0.08902  \n","2                0.2430          0.3613                  0.08758  \n","3                0.2575          0.6638                  0.17300  \n","4                0.1625          0.2364                  0.07678  \n","\n","[5 rows x 30 columns]"],"text/html":["\n","  <div id=\"df-1d1a674b-2393-42de-ad68-2547105a0657\" 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>mean radius</th>\n","      <th>mean texture</th>\n","      <th>mean perimeter</th>\n","      <th>mean area</th>\n","      <th>mean smoothness</th>\n","      <th>mean compactness</th>\n","      <th>mean concavity</th>\n","      <th>mean concave points</th>\n","      <th>mean symmetry</th>\n","      <th>mean fractal dimension</th>\n","      <th>...</th>\n","      <th>worst radius</th>\n","      <th>worst texture</th>\n","      <th>worst perimeter</th>\n","      <th>worst area</th>\n","      <th>worst smoothness</th>\n","      <th>worst compactness</th>\n","      <th>worst concavity</th>\n","      <th>worst concave points</th>\n","      <th>worst symmetry</th>\n","      <th>worst fractal dimension</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>17.99</td>\n","      <td>10.38</td>\n","      <td>122.80</td>\n","      <td>1001.0</td>\n","      <td>0.11840</td>\n","      <td>0.27760</td>\n","      <td>0.3001</td>\n","      <td>0.14710</td>\n","      <td>0.2419</td>\n","      <td>0.07871</td>\n","      <td>...</td>\n","      <td>25.38</td>\n","      <td>17.33</td>\n","      <td>184.60</td>\n","      <td>2019.0</td>\n","      <td>0.1622</td>\n","      <td>0.6656</td>\n","      <td>0.7119</td>\n","      <td>0.2654</td>\n","      <td>0.4601</td>\n","      <td>0.11890</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>20.57</td>\n","      <td>17.77</td>\n","      <td>132.90</td>\n","      <td>1326.0</td>\n","      <td>0.08474</td>\n","      <td>0.07864</td>\n","      <td>0.0869</td>\n","      <td>0.07017</td>\n","      <td>0.1812</td>\n","      <td>0.05667</td>\n","      <td>...</td>\n","      <td>24.99</td>\n","      <td>23.41</td>\n","      <td>158.80</td>\n","      <td>1956.0</td>\n","      <td>0.1238</td>\n","      <td>0.1866</td>\n","      <td>0.2416</td>\n","      <td>0.1860</td>\n","      <td>0.2750</td>\n","      <td>0.08902</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>19.69</td>\n","      <td>21.25</td>\n","      <td>130.00</td>\n","      <td>1203.0</td>\n","      <td>0.10960</td>\n","      <td>0.15990</td>\n","      <td>0.1974</td>\n","      <td>0.12790</td>\n","      <td>0.2069</td>\n","      <td>0.05999</td>\n","      <td>...</td>\n","      <td>23.57</td>\n","      <td>25.53</td>\n","      <td>152.50</td>\n","      <td>1709.0</td>\n","      <td>0.1444</td>\n","      <td>0.4245</td>\n","      <td>0.4504</td>\n","      <td>0.2430</td>\n","      <td>0.3613</td>\n","      <td>0.08758</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>11.42</td>\n","      <td>20.38</td>\n","      <td>77.58</td>\n","      <td>386.1</td>\n","      <td>0.14250</td>\n","      <td>0.28390</td>\n","      <td>0.2414</td>\n","      <td>0.10520</td>\n","      <td>0.2597</td>\n","      <td>0.09744</td>\n","      <td>...</td>\n","      <td>14.91</td>\n","      <td>26.50</td>\n","      <td>98.87</td>\n","      <td>567.7</td>\n","      <td>0.2098</td>\n","      <td>0.8663</td>\n","      <td>0.6869</td>\n","      <td>0.2575</td>\n","      <td>0.6638</td>\n","      <td>0.17300</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>20.29</td>\n","      <td>14.34</td>\n","      <td>135.10</td>\n","      <td>1297.0</td>\n","      <td>0.10030</td>\n","      <td>0.13280</td>\n","      <td>0.1980</td>\n","      <td>0.10430</td>\n","      <td>0.1809</td>\n","      <td>0.05883</td>\n","      <td>...</td>\n","      <td>22.54</td>\n","      <td>16.67</td>\n","      <td>152.20</td>\n","      <td>1575.0</td>\n","      <td>0.1374</td>\n","      <td>0.2050</td>\n","      <td>0.4000</td>\n","      <td>0.1625</td>\n","      <td>0.2364</td>\n","      <td>0.07678</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>5 rows × 30 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-1d1a674b-2393-42de-ad68-2547105a0657')\"\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-1d1a674b-2393-42de-ad68-2547105a0657 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-1d1a674b-2393-42de-ad68-2547105a0657');\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 id=\"df-dce1475b-fbd6-4bb1-b6c1-78f8a8973b12\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-dce1475b-fbd6-4bb1-b6c1-78f8a8973b12')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-dce1475b-fbd6-4bb1-b6c1-78f8a8973b12 button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","\n","    </div>\n","  </div>\n"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"dataframe","variable_name":"X"}},"metadata":{},"execution_count":3}]},{"cell_type":"code","source":["scaler = StandardScaler()\n","scaler.fit(X_train)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":74},"id":"TKmrxvrogXmH","executionInfo":{"status":"ok","timestamp":1710599949063,"user_tz":-420,"elapsed":397,"user":{"displayName":"Nhật Quang Đoàn","userId":"10175964550021301622"}},"outputId":"a163f11f-4b3d-4cac-a622-559b65b4f4f0"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["StandardScaler()"],"text/html":["<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>StandardScaler()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div>"]},"metadata":{},"execution_count":18}]},{"cell_type":"code","source":["sel_ = SelectFromModel(\n","    LogisticRegression(C=0.5, penalty='l1', solver='liblinear', random_state=10))\n","sel_.fit(scaler.transform(X_train), y_train)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":117},"id":"nb_jL139gZKE","executionInfo":{"status":"ok","timestamp":1710599962515,"user_tz":-420,"elapsed":328,"user":{"displayName":"Nhật Quang Đoàn","userId":"10175964550021301622"}},"outputId":"1bc8144a-bce1-49d2-f825-31daf37aed86"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["SelectFromModel(estimator=LogisticRegression(C=0.5, penalty='l1',\n","                                             random_state=10,\n","                                             solver='liblinear'))"],"text/html":["<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SelectFromModel(estimator=LogisticRegression(C=0.5, penalty=&#x27;l1&#x27;,\n","                                             random_state=10,\n","                                             solver=&#x27;liblinear&#x27;))</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SelectFromModel</label><div class=\"sk-toggleable__content\"><pre>SelectFromModel(estimator=LogisticRegression(C=0.5, penalty=&#x27;l1&#x27;,\n","                                             random_state=10,\n","                                             solver=&#x27;liblinear&#x27;))</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(C=0.5, penalty=&#x27;l1&#x27;, random_state=10, solver=&#x27;liblinear&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(C=0.5, penalty=&#x27;l1&#x27;, random_state=10, solver=&#x27;liblinear&#x27;)</pre></div></div></div></div></div></div></div></div></div></div>"]},"metadata":{},"execution_count":19}]},{"cell_type":"code","source":["sel_.get_support()\n","#False =0, True = 1\n","# weight of irrelevant features = 0"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"B32FGTcggdDL","executionInfo":{"status":"ok","timestamp":1710600270396,"user_tz":-420,"elapsed":406,"user":{"displayName":"Nhật Quang Đoàn","userId":"10175964550021301622"}},"outputId":"ac504646-6016-4e53-b63f-e18d84b76fba"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["array([False,  True, False, False, False, False, False,  True,  True,\n","       False,  True, False, False, False, False,  True, False, False,\n","       False,  True,  True,  True,  True,  True,  True, False,  True,\n","        True,  True, False])"]},"metadata":{},"execution_count":23}]},{"cell_type":"code","source":["# k-nn for the full features\n","# k-nn for the selected True features\n","# compare performances before/after feature selection"],"metadata":{"id":"aWwbnFPNJIKn"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["np.corrcoef(X)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"gclRh90euoG1","executionInfo":{"status":"ok","timestamp":1710601180513,"user_tz":-420,"elapsed":324,"user":{"displayName":"Nhật Quang Đoàn","userId":"10175964550021301622"}},"outputId":"5904cd20-7780-4665-a57b-fdc60dc10bf7"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["array([[1.        , 0.9892786 , 0.98703483, ..., 0.97919942, 0.98785229,\n","        0.97683484],\n","       [0.9892786 , 1.        , 0.999713  , ..., 0.99774113, 0.99972889,\n","        0.98469916],\n","       [0.98703483, 0.999713  , 1.        , ..., 0.99878867, 0.99988251,\n","        0.98591229],\n","       ...,\n","       [0.97919942, 0.99774113, 0.99878867, ..., 1.        , 0.99875905,\n","        0.98800384],\n","       [0.98785229, 0.99972889, 0.99988251, ..., 0.99875905, 1.        ,\n","        0.98765632],\n","       [0.97683484, 0.98469916, 0.98591229, ..., 0.98800384, 0.98765632,\n","        1.        ]])"]},"metadata":{},"execution_count":32}]},{"cell_type":"code","source":["removed_feats = X_train.columns[(sel_.estimator_.coef_ == 0).ravel().tolist()]\n","X_train_selected = sel_.transform(scaler.transform(X_train))\n","X_test_selected = sel_.transform(scaler.transform(X_test))"],"metadata":{"id":"kQXvJVKWuJ_D"},"execution_count":null,"outputs":[]}]}