Upload Blood-Pressure-Model/Blood-Pressure-Model.ipynb with huggingface_hub

Blood-Pressure-Model/Blood-Pressure-Model.ipynb

@@ -0,0 +1,870 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {
+        "id": "hrzjDZhCykSv"
+      },
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.neighbors import KNeighborsClassifier\n",
+        "from sklearn.tree import DecisionTreeClassifier\n",
+        "from sklearn.metrics import accuracy_score\n",
+        "import joblib"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df = pd.read_csv('/content/data.csv')\n",
+        "df.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 226
+        },
+        "id": "siRGOC_PzCmJ",
+        "outputId": "717f6dc4-a613-4c62-ffea-631977c1ede7"
+      },
+      "execution_count": 5,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "   Patient_Number  Blood_Pressure_Abnormality  Level_of_Hemoglobin  \\\n",
+              "0               1                           1                11.28   \n",
+              "1               2                           0                 9.75   \n",
+              "2               3                           1                10.79   \n",
+              "3               4                           0                11.00   \n",
+              "4               5                           1                14.17   \n",
+              "\n",
+              "   Genetic_Pedigree_Coefficient  Age  BMI  Sex  Pregnancy  Smoking  \\\n",
+              "0                          0.90   34   23    1        1.0        0   \n",
+              "1                          0.23   54   33    1        NaN        0   \n",
+              "2                          0.91   70   49    0        NaN        0   \n",
+              "3                          0.43   71   50    0        NaN        0   \n",
+              "4                          0.83   52   19    0        NaN        0   \n",
+              "\n",
+              "   Physical_activity  salt_content_in_the_diet  alcohol_consumption_per_day  \\\n",
+              "0              45961                     48071                          NaN   \n",
+              "1              26106                     25333                        205.0   \n",
+              "2               9995                     29465                         67.0   \n",
+              "3              10635                      7439                        242.0   \n",
+              "4              15619                     49644                        397.0   \n",
+              "\n",
+              "   Level_of_Stress  Chronic_kidney_disease  Adrenal_and_thyroid_disorders  \n",
+              "0                2                       1                              1  \n",
+              "1                3                       0                              0  \n",
+              "2                2                       1                              0  \n",
+              "3                1                       1                              0  \n",
+              "4                2                       0                              0  "
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-a6acadf9-54f4-4026-8fdc-1e5b8c3080d6\" 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>Patient_Number</th>\n",
+              "      <th>Blood_Pressure_Abnormality</th>\n",
+              "      <th>Level_of_Hemoglobin</th>\n",
+              "      <th>Genetic_Pedigree_Coefficient</th>\n",
+              "      <th>Age</th>\n",
+              "      <th>BMI</th>\n",
+              "      <th>Sex</th>\n",
+              "      <th>Pregnancy</th>\n",
+              "      <th>Smoking</th>\n",
+              "      <th>Physical_activity</th>\n",
+              "      <th>salt_content_in_the_diet</th>\n",
+              "      <th>alcohol_consumption_per_day</th>\n",
+              "      <th>Level_of_Stress</th>\n",
+              "      <th>Chronic_kidney_disease</th>\n",
+              "      <th>Adrenal_and_thyroid_disorders</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>1</td>\n",
+              "      <td>1</td>\n",
+              "      <td>11.28</td>\n",
+              "      <td>0.90</td>\n",
+              "      <td>34</td>\n",
+              "      <td>23</td>\n",
+              "      <td>1</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>0</td>\n",
+              "      <td>45961</td>\n",
+              "      <td>48071</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>2</td>\n",
+              "      <td>1</td>\n",
+              "      <td>1</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>2</td>\n",
+              "      <td>0</td>\n",
+              "      <td>9.75</td>\n",
+              "      <td>0.23</td>\n",
+              "      <td>54</td>\n",
+              "      <td>33</td>\n",
+              "      <td>1</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>0</td>\n",
+              "      <td>26106</td>\n",
+              "      <td>25333</td>\n",
+              "      <td>205.0</td>\n",
+              "      <td>3</td>\n",
+              "      <td>0</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>3</td>\n",
+              "      <td>1</td>\n",
+              "      <td>10.79</td>\n",
+              "      <td>0.91</td>\n",
+              "      <td>70</td>\n",
+              "      <td>49</td>\n",
+              "      <td>0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>0</td>\n",
+              "      <td>9995</td>\n",
+              "      <td>29465</td>\n",
+              "      <td>67.0</td>\n",
+              "      <td>2</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>4</td>\n",
+              "      <td>0</td>\n",
+              "      <td>11.00</td>\n",
+              "      <td>0.43</td>\n",
+              "      <td>71</td>\n",
+              "      <td>50</td>\n",
+              "      <td>0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>0</td>\n",
+              "      <td>10635</td>\n",
+              "      <td>7439</td>\n",
+              "      <td>242.0</td>\n",
+              "      <td>1</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>5</td>\n",
+              "      <td>1</td>\n",
+              "      <td>14.17</td>\n",
+              "      <td>0.83</td>\n",
+              "      <td>52</td>\n",
+              "      <td>19</td>\n",
+              "      <td>0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>0</td>\n",
+              "      <td>15619</td>\n",
+              "      <td>49644</td>\n",
+              "      <td>397.0</td>\n",
+              "      <td>2</td>\n",
+              "      <td>0</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a6acadf9-54f4-4026-8fdc-1e5b8c3080d6')\"\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-a6acadf9-54f4-4026-8fdc-1e5b8c3080d6 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-a6acadf9-54f4-4026-8fdc-1e5b8c3080d6');\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-ea9d1e6e-a766-48f3-9c85-119dbca73b67\">\n",
+              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-ea9d1e6e-a766-48f3-9c85-119dbca73b67')\"\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-ea9d1e6e-a766-48f3-9c85-119dbca73b67 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": "df",
+              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 2000,\n  \"fields\": [\n    {\n      \"column\": \"Patient_Number\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 577,\n        \"min\": 1,\n        \"max\": 2000,\n        \"num_unique_values\": 2000,\n        \"samples\": [\n          1861,\n          354,\n          1334\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Blood_Pressure_Abnormality\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Level_of_Hemoglobin\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.1867006376306533,\n        \"min\": 8.1,\n        \"max\": 17.56,\n        \"num_unique_values\": 757,\n        \"samples\": [\n          9.2,\n          13.78\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Genetic_Pedigree_Coefficient\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.2917358818334813,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 101,\n        \"samples\": [\n          0.72,\n          0.12\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Age\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 17,\n        \"min\": 18,\n        \"max\": 75,\n        \"num_unique_values\": 58,\n        \"samples\": [\n          34,\n          23\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"BMI\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 11,\n        \"min\": 10,\n        \"max\": 50,\n        \"num_unique_values\": 41,\n        \"samples\": [\n          18,\n          27\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Sex\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Pregnancy\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.4980801631506569,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.0,\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Smoking\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          1,\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Physical_activity\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 14015,\n        \"min\": 628,\n        \"max\": 49980,\n        \"num_unique_values\": 1951,\n        \"samples\": [\n          21467,\n          8470\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"salt_content_in_the_diet\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 14211,\n        \"min\": 22,\n        \"max\": 49976,\n        \"num_unique_values\": 1945,\n        \"samples\": [\n          27777,\n          1674\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"alcohol_consumption_per_day\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 143.65188442842302,\n        \"min\": 0.0,\n        \"max\": 499.0,\n        \"num_unique_values\": 488,\n        \"samples\": [\n          309.0,\n          467.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Level_of_Stress\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 1,\n        \"max\": 3,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          2,\n          3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Chronic_kidney_disease\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Adrenal_and_thyroid_disorders\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+            }
+          },
+          "metadata": {},
+          "execution_count": 5
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.isnull().sum()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 554
+        },
+        "id": "SwpsDsCwzh2q",
+        "outputId": "fcb0a13e-35b5-4457-d58c-f0860fa90bfa"
+      },
+      "execution_count": 6,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "Patient_Number                      0\n",
+              "Blood_Pressure_Abnormality          0\n",
+              "Level_of_Hemoglobin                 0\n",
+              "Genetic_Pedigree_Coefficient       92\n",
+              "Age                                 0\n",
+              "BMI                                 0\n",
+              "Sex                                 0\n",
+              "Pregnancy                        1558\n",
+              "Smoking                             0\n",
+              "Physical_activity                   0\n",
+              "salt_content_in_the_diet            0\n",
+              "alcohol_consumption_per_day       242\n",
+              "Level_of_Stress                     0\n",
+              "Chronic_kidney_disease              0\n",
+              "Adrenal_and_thyroid_disorders       0\n",
+              "dtype: int64"
+            ],
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>0</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>Patient_Number</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Blood_Pressure_Abnormality</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Level_of_Hemoglobin</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Genetic_Pedigree_Coefficient</th>\n",
+              "      <td>92</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Age</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>BMI</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Sex</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Pregnancy</th>\n",
+              "      <td>1558</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Smoking</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Physical_activity</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>salt_content_in_the_diet</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>alcohol_consumption_per_day</th>\n",
+              "      <td>242</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Level_of_Stress</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Chronic_kidney_disease</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>Adrenal_and_thyroid_disorders</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div><br><label><b>dtype:</b> int64</label>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 6
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.fillna(df['Genetic_Pedigree_Coefficient'].mode()[0], inplace=True)\n",
+        "df.fillna(df['Pregnancy'].mode()[0], inplace=True)\n",
+        "df.fillna(df['alcohol_consumption_per_day'].median(), inplace=True)"
+      ],
+      "metadata": {
+        "id": "GMjkUTVVz-qu"
+      },
+      "execution_count": 7,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.drop(['Patient_Number','Adrenal_and_thyroid_disorders'], axis=1, inplace=True)"
+      ],
+      "metadata": {
+        "id": "f718ZzvP1cEa"
+      },
+      "execution_count": 8,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.info()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "9A2zk7wi040E",
+        "outputId": "89deac92-cebe-423e-8d57-46e3b14a616b"
+      },
+      "execution_count": 9,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "<class 'pandas.core.frame.DataFrame'>\n",
+            "RangeIndex: 2000 entries, 0 to 1999\n",
+            "Data columns (total 13 columns):\n",
+            " #   Column                        Non-Null Count  Dtype  \n",
+            "---  ------                        --------------  -----  \n",
+            " 0   Blood_Pressure_Abnormality    2000 non-null   int64  \n",
+            " 1   Level_of_Hemoglobin           2000 non-null   float64\n",
+            " 2   Genetic_Pedigree_Coefficient  2000 non-null   float64\n",
+            " 3   Age                           2000 non-null   int64  \n",
+            " 4   BMI                           2000 non-null   int64  \n",
+            " 5   Sex                           2000 non-null   int64  \n",
+            " 6   Pregnancy                     2000 non-null   float64\n",
+            " 7   Smoking                       2000 non-null   int64  \n",
+            " 8   Physical_activity             2000 non-null   int64  \n",
+            " 9   salt_content_in_the_diet      2000 non-null   int64  \n",
+            " 10  alcohol_consumption_per_day   2000 non-null   float64\n",
+            " 11  Level_of_Stress               2000 non-null   int64  \n",
+            " 12  Chronic_kidney_disease        2000 non-null   int64  \n",
+            "dtypes: float64(4), int64(9)\n",
+            "memory usage: 203.3 KB\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "X = df.drop('Blood_Pressure_Abnormality', axis=1)\n",
+        "y= df['Blood_Pressure_Abnormality']"
+      ],
+      "metadata": {
+        "id": "HW3rI9Jk1rsZ"
+      },
+      "execution_count": 10,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, shuffle=True)"
+      ],
+      "metadata": {
+        "id": "zCLNqLbg2cz7"
+      },
+      "execution_count": 11,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model_knn = KNeighborsClassifier(n_neighbors=5)\n",
+        "model_knn.fit(X_train, y_train)\n",
+        "y_knn_pred = model_knn.predict(X_test)\n",
+        "accuracy_knn = accuracy_score(y_test, y_knn_pred)\n",
+        "print(f\"KNN Accuracy: {accuracy_knn:.2f}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "2KlAwxHe2i7v",
+        "outputId": "10cab152-d656-4d93-e0c8-7f67c242a13c"
+      },
+      "execution_count": 12,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "KNN Accuracy: 0.52\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model_dt=DecisionTreeClassifier(random_state=42)\n",
+        "model_dt.fit(X_train, y_train)\n",
+        "y_dt_pred = model_dt.predict(X_test)\n",
+        "accuracy_dt = accuracy_score(y_test, y_dt_pred)\n",
+        "print(f\"Decision Tree Accuracy: {accuracy_dt:.2f}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "L6f3-RKW29Fc",
+        "outputId": "4f71f2c9-1e12-4511-dec4-3262223e4dee"
+      },
+      "execution_count": 13,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Decision Tree Accuracy: 0.82\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "joblib.dump(model_knn, 'model_knn.pkl')\n",
+        "joblib.dump(model_dt, 'model_dt.pkl')"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "GB3vleCu3HwI",
+        "outputId": "985ba36a-afae-4d37-b404-72854358aaec"
+      },
+      "execution_count": 14,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "['model_dt.pkl']"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 14
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "loaded_knn = joblib.load('model_knn.pkl')\n",
+        "loaded_dt = joblib.load('model_dt.pkl')"
+      ],
+      "metadata": {
+        "id": "k0MoDhbE4WXG"
+      },
+      "execution_count": 15,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.info()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "qjJ5unz850gH",
+        "outputId": "88af5db0-f828-4245-8197-a9774761c1e9"
+      },
+      "execution_count": 16,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "<class 'pandas.core.frame.DataFrame'>\n",
+            "RangeIndex: 2000 entries, 0 to 1999\n",
+            "Data columns (total 13 columns):\n",
+            " #   Column                        Non-Null Count  Dtype  \n",
+            "---  ------                        --------------  -----  \n",
+            " 0   Blood_Pressure_Abnormality    2000 non-null   int64  \n",
+            " 1   Level_of_Hemoglobin           2000 non-null   float64\n",
+            " 2   Genetic_Pedigree_Coefficient  2000 non-null   float64\n",
+            " 3   Age                           2000 non-null   int64  \n",
+            " 4   BMI                           2000 non-null   int64  \n",
+            " 5   Sex                           2000 non-null   int64  \n",
+            " 6   Pregnancy                     2000 non-null   float64\n",
+            " 7   Smoking                       2000 non-null   int64  \n",
+            " 8   Physical_activity             2000 non-null   int64  \n",
+            " 9   salt_content_in_the_diet      2000 non-null   int64  \n",
+            " 10  alcohol_consumption_per_day   2000 non-null   float64\n",
+            " 11  Level_of_Stress               2000 non-null   int64  \n",
+            " 12  Chronic_kidney_disease        2000 non-null   int64  \n",
+            "dtypes: float64(4), int64(9)\n",
+            "memory usage: 203.3 KB\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "data_test= pd.DataFrame({\n",
+        "    'Level_of_Hemoglobin': np.random.uniform(12.0, 16.0, 400),  # بين 12 و 16 g/dL\n",
+        "    'Genetic_Pedigree_Coefficient': np.random.uniform(0.1, 1.0, 400),  # 0.1 إلى 1\n",
+        "    'Age': np.random.randint(18, 80, 400),  # العمر بين 18 و 80 سنة\n",
+        "    'BMI': np.random.randint(18, 35, 400),  # بين 18 و 35\n",
+        "    'Sex': np.random.randint(0, 2, 400),  # 0 أو 1\n",
+        "    'Pregnancy': np.random.uniform(0, 1, 400),  # بين 0 و 1\n",
+        "    'Smoking': np.random.randint(0, 2, 400),  # 0 أو 1\n",
+        "    'Physical_activity': np.random.randint(0, 2, 400),  # 0 أو 1\n",
+        "    'salt_content_in_the_diet': np.random.randint(1, 10, 400),  # بين 1 و 10\n",
+        "    'alcohol_consumption_per_day': np.random.uniform(0, 400),  # 0 كوب\n",
+        "    'Level_of_Stress': np.random.randint(0, 5, 400),  # بين 0 و 4\n",
+        "    'Chronic_kidney_disease': np.random.randint(0, 2, 400),  # 0 أو 1\n",
+        "})\n",
+        "\n",
+        "y_loaded_pred_k = loaded_knn.predict(data_test)\n",
+        "y_loaded_pred_d = loaded_dt.predict(data_test)"
+      ],
+      "metadata": {
+        "id": "we-HUFaH4cez"
+      },
+      "execution_count": 17,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(\"Predictions from KNN model:\", y_loaded_pred_k[:10])  # عرض أول 10 قيم من التنبؤات\n",
+        "print(\"Predictions from Decision Tree model:\", y_loaded_pred_d[:10])"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "sjSzwAEQ6nfQ",
+        "outputId": "0f43af23-8cb0-4079-9fb5-7c4314a015ba"
+      },
+      "execution_count": 18,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Predictions from KNN model: [0 0 0 0 0 0 0 0 0 0]\n",
+            "Predictions from Decision Tree model: [1 1 1 1 1 0 0 0 0 1]\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# حساب الدقة\n",
+        "accuracy_k = accuracy_score(y_test, y_loaded_pred_k)\n",
+        "accuracy_d = accuracy_score(y_test, y_loaded_pred_d)\n",
+        "\n",
+        "print(\"Accuracy of KNN model:\", accuracy_k)\n",
+        "print(\"Accuracy of Decision Tree model:\", accuracy_d)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "cq53m8ZQ8ETU",
+        "outputId": "42f79c47-7693-41b3-8436-350cbfadddd3"
+      },
+      "execution_count": 19,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Accuracy of KNN model: 0.5575\n",
+            "Accuracy of Decision Tree model: 0.5525\n"
+          ]
+        }
+      ]
+    }
+  ]
+}