From 76c34f7fd4d2ee77fe740c8cb9cccabe4189ec1f Mon Sep 17 00:00:00 2001
From: "Shekwoyeyilo2.gado@live.uwe.ac.uk" <sarah.y.gado@gmail.com>
Date: Thu, 13 Mar 2025 15:08:22 +0000
Subject: [PATCH] parameters for all features
---
models copy.ipynb | 960 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 960 insertions(+)
create mode 100644 models copy.ipynb
diff --git a/models copy.ipynb b/models copy.ipynb
new file mode 100644
index 0000000..8203ec4
--- /dev/null
+++ b/models copy.ipynb
@@ -0,0 +1,960 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import ast\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.ensemble import RandomForestClassifier\n",
+ "from sklearn.tree import DecisionTreeClassifier\n",
+ "from sklearn.model_selection import cross_val_score\n",
+ "from sklearn.model_selection import RandomizedSearchCV\n",
+ "from sklearn.preprocessing import StandardScaler\n",
+ "from sklearn.model_selection import cross_val_score, KFold\n",
+ "from sklearn.svm import SVC\n",
+ "from scipy.stats import randint"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>PatientID</th>\n",
+ " <th>Age</th>\n",
+ " <th>Gender</th>\n",
+ " <th>Ethnicity</th>\n",
+ " <th>EducationLevel</th>\n",
+ " <th>BMI</th>\n",
+ " <th>Smoking</th>\n",
+ " <th>AlcoholConsumption</th>\n",
+ " <th>PhysicalActivity</th>\n",
+ " <th>DietQuality</th>\n",
+ " <th>...</th>\n",
+ " <th>MemoryComplaints</th>\n",
+ " <th>BehavioralProblems</th>\n",
+ " <th>ADL</th>\n",
+ " <th>Confusion</th>\n",
+ " <th>Disorientation</th>\n",
+ " <th>PersonalityChanges</th>\n",
+ " <th>DifficultyCompletingTasks</th>\n",
+ " <th>Forgetfulness</th>\n",
+ " <th>Diagnosis</th>\n",
+ " <th>DoctorInCharge</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>4751</td>\n",
+ " <td>73</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>22.927749</td>\n",
+ " <td>0</td>\n",
+ " <td>13.297218</td>\n",
+ " <td>6.327112</td>\n",
+ " <td>1.347214</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1.725883</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>XXXConfid</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>4752</td>\n",
+ " <td>89</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>26.827681</td>\n",
+ " <td>0</td>\n",
+ " <td>4.542524</td>\n",
+ " <td>7.619885</td>\n",
+ " <td>0.518767</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2.592424</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>XXXConfid</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>4753</td>\n",
+ " <td>73</td>\n",
+ " <td>0</td>\n",
+ " <td>3</td>\n",
+ " <td>1</td>\n",
+ " <td>17.795882</td>\n",
+ " <td>0</td>\n",
+ " <td>19.555085</td>\n",
+ " <td>7.844988</td>\n",
+ " <td>1.826335</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>7.119548</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>XXXConfid</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>4754</td>\n",
+ " <td>74</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>33.800817</td>\n",
+ " <td>1</td>\n",
+ " <td>12.209266</td>\n",
+ " <td>8.428001</td>\n",
+ " <td>7.435604</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>6.481226</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>XXXConfid</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>4755</td>\n",
+ " <td>89</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>20.716974</td>\n",
+ " <td>0</td>\n",
+ " <td>18.454356</td>\n",
+ " <td>6.310461</td>\n",
+ " <td>0.795498</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0.014691</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>XXXConfid</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2144</th>\n",
+ " <td>6895</td>\n",
+ " <td>61</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>39.121757</td>\n",
+ " <td>0</td>\n",
+ " <td>1.561126</td>\n",
+ " <td>4.049964</td>\n",
+ " <td>6.555306</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>4.492838</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>XXXConfid</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2145</th>\n",
+ " <td>6896</td>\n",
+ " <td>75</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>17.857903</td>\n",
+ " <td>0</td>\n",
+ " <td>18.767261</td>\n",
+ " <td>1.360667</td>\n",
+ " <td>2.904662</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>9.204952</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>XXXConfid</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2146</th>\n",
+ " <td>6897</td>\n",
+ " <td>77</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>15.476479</td>\n",
+ " <td>0</td>\n",
+ " <td>4.594670</td>\n",
+ " <td>9.886002</td>\n",
+ " <td>8.120025</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>5.036334</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>XXXConfid</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2147</th>\n",
+ " <td>6898</td>\n",
+ " <td>78</td>\n",
+ " <td>1</td>\n",
+ " <td>3</td>\n",
+ " <td>1</td>\n",
+ " <td>15.299911</td>\n",
+ " <td>0</td>\n",
+ " <td>8.674505</td>\n",
+ " <td>6.354282</td>\n",
+ " <td>1.263427</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>3.785399</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>XXXConfid</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2148</th>\n",
+ " <td>6899</td>\n",
+ " <td>72</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>33.289738</td>\n",
+ " <td>0</td>\n",
+ " <td>7.890703</td>\n",
+ " <td>6.570993</td>\n",
+ " <td>7.941404</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>8.327563</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>XXXConfid</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>2149 rows × 35 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " PatientID Age Gender Ethnicity EducationLevel BMI Smoking \\\n",
+ "0 4751 73 0 0 2 22.927749 0 \n",
+ "1 4752 89 0 0 0 26.827681 0 \n",
+ "2 4753 73 0 3 1 17.795882 0 \n",
+ "3 4754 74 1 0 1 33.800817 1 \n",
+ "4 4755 89 0 0 0 20.716974 0 \n",
+ "... ... ... ... ... ... ... ... \n",
+ "2144 6895 61 0 0 1 39.121757 0 \n",
+ "2145 6896 75 0 0 2 17.857903 0 \n",
+ "2146 6897 77 0 0 1 15.476479 0 \n",
+ "2147 6898 78 1 3 1 15.299911 0 \n",
+ "2148 6899 72 0 0 2 33.289738 0 \n",
+ "\n",
+ " AlcoholConsumption PhysicalActivity DietQuality ... \\\n",
+ "0 13.297218 6.327112 1.347214 ... \n",
+ "1 4.542524 7.619885 0.518767 ... \n",
+ "2 19.555085 7.844988 1.826335 ... \n",
+ "3 12.209266 8.428001 7.435604 ... \n",
+ "4 18.454356 6.310461 0.795498 ... \n",
+ "... ... ... ... ... \n",
+ "2144 1.561126 4.049964 6.555306 ... \n",
+ "2145 18.767261 1.360667 2.904662 ... \n",
+ "2146 4.594670 9.886002 8.120025 ... \n",
+ "2147 8.674505 6.354282 1.263427 ... \n",
+ "2148 7.890703 6.570993 7.941404 ... \n",
+ "\n",
+ " MemoryComplaints BehavioralProblems ADL Confusion \\\n",
+ "0 0 0 1.725883 0 \n",
+ "1 0 0 2.592424 0 \n",
+ "2 0 0 7.119548 0 \n",
+ "3 0 1 6.481226 0 \n",
+ "4 0 0 0.014691 0 \n",
+ "... ... ... ... ... \n",
+ "2144 0 0 4.492838 1 \n",
+ "2145 0 1 9.204952 0 \n",
+ "2146 0 0 5.036334 0 \n",
+ "2147 0 0 3.785399 0 \n",
+ "2148 0 1 8.327563 0 \n",
+ "\n",
+ " Disorientation PersonalityChanges DifficultyCompletingTasks \\\n",
+ "0 0 0 1 \n",
+ "1 0 0 0 \n",
+ "2 1 0 1 \n",
+ "3 0 0 0 \n",
+ "4 0 1 1 \n",
+ "... ... ... ... \n",
+ "2144 0 0 0 \n",
+ "2145 0 0 0 \n",
+ "2146 0 0 0 \n",
+ "2147 0 0 0 \n",
+ "2148 1 0 0 \n",
+ "\n",
+ " Forgetfulness Diagnosis DoctorInCharge \n",
+ "0 0 0 XXXConfid \n",
+ "1 1 0 XXXConfid \n",
+ "2 0 0 XXXConfid \n",
+ "3 0 0 XXXConfid \n",
+ "4 0 0 XXXConfid \n",
+ "... ... ... ... \n",
+ "2144 0 1 XXXConfid \n",
+ "2145 0 1 XXXConfid \n",
+ "2146 0 1 XXXConfid \n",
+ "2147 1 1 XXXConfid \n",
+ "2148 1 0 XXXConfid \n",
+ "\n",
+ "[2149 rows x 35 columns]"
+ ]
+ },
+ "execution_count": 29,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df = pd.read_csv('alzheimers_disease_data.csv')\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Age</th>\n",
+ " <th>Gender</th>\n",
+ " <th>Ethnicity</th>\n",
+ " <th>EducationLevel</th>\n",
+ " <th>BMI</th>\n",
+ " <th>Smoking</th>\n",
+ " <th>AlcoholConsumption</th>\n",
+ " <th>PhysicalActivity</th>\n",
+ " <th>DietQuality</th>\n",
+ " <th>SleepQuality</th>\n",
+ " <th>...</th>\n",
+ " <th>FunctionalAssessment</th>\n",
+ " <th>MemoryComplaints</th>\n",
+ " <th>BehavioralProblems</th>\n",
+ " <th>ADL</th>\n",
+ " <th>Confusion</th>\n",
+ " <th>Disorientation</th>\n",
+ " <th>PersonalityChanges</th>\n",
+ " <th>DifficultyCompletingTasks</th>\n",
+ " <th>Forgetfulness</th>\n",
+ " <th>Diagnosis</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>73</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>22.927749</td>\n",
+ " <td>0</td>\n",
+ " <td>13.297218</td>\n",
+ " <td>6.327112</td>\n",
+ " <td>1.347214</td>\n",
+ " <td>9.025679</td>\n",
+ " <td>...</td>\n",
+ " <td>6.518877</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1.725883</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>89</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>26.827681</td>\n",
+ " <td>0</td>\n",
+ " <td>4.542524</td>\n",
+ " <td>7.619885</td>\n",
+ " <td>0.518767</td>\n",
+ " <td>7.151293</td>\n",
+ " <td>...</td>\n",
+ " <td>7.118696</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2.592424</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>73</td>\n",
+ " <td>0</td>\n",
+ " <td>3</td>\n",
+ " <td>1</td>\n",
+ " <td>17.795882</td>\n",
+ " <td>0</td>\n",
+ " <td>19.555085</td>\n",
+ " <td>7.844988</td>\n",
+ " <td>1.826335</td>\n",
+ " <td>9.673574</td>\n",
+ " <td>...</td>\n",
+ " <td>5.895077</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>7.119548</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>74</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>33.800817</td>\n",
+ " <td>1</td>\n",
+ " <td>12.209266</td>\n",
+ " <td>8.428001</td>\n",
+ " <td>7.435604</td>\n",
+ " <td>8.392554</td>\n",
+ " <td>...</td>\n",
+ " <td>8.965106</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>6.481226</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>89</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>20.716974</td>\n",
+ " <td>0</td>\n",
+ " <td>18.454356</td>\n",
+ " <td>6.310461</td>\n",
+ " <td>0.795498</td>\n",
+ " <td>5.597238</td>\n",
+ " <td>...</td>\n",
+ " <td>6.045039</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0.014691</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2144</th>\n",
+ " <td>61</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>39.121757</td>\n",
+ " <td>0</td>\n",
+ " <td>1.561126</td>\n",
+ " <td>4.049964</td>\n",
+ " <td>6.555306</td>\n",
+ " <td>7.535540</td>\n",
+ " <td>...</td>\n",
+ " <td>0.238667</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>4.492838</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2145</th>\n",
+ " <td>75</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>17.857903</td>\n",
+ " <td>0</td>\n",
+ " <td>18.767261</td>\n",
+ " <td>1.360667</td>\n",
+ " <td>2.904662</td>\n",
+ " <td>8.555256</td>\n",
+ " <td>...</td>\n",
+ " <td>8.687480</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>9.204952</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2146</th>\n",
+ " <td>77</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>15.476479</td>\n",
+ " <td>0</td>\n",
+ " <td>4.594670</td>\n",
+ " <td>9.886002</td>\n",
+ " <td>8.120025</td>\n",
+ " <td>5.769464</td>\n",
+ " <td>...</td>\n",
+ " <td>1.972137</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>5.036334</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2147</th>\n",
+ " <td>78</td>\n",
+ " <td>1</td>\n",
+ " <td>3</td>\n",
+ " <td>1</td>\n",
+ " <td>15.299911</td>\n",
+ " <td>0</td>\n",
+ " <td>8.674505</td>\n",
+ " <td>6.354282</td>\n",
+ " <td>1.263427</td>\n",
+ " <td>8.322874</td>\n",
+ " <td>...</td>\n",
+ " <td>5.173891</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>3.785399</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2148</th>\n",
+ " <td>72</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>33.289738</td>\n",
+ " <td>0</td>\n",
+ " <td>7.890703</td>\n",
+ " <td>6.570993</td>\n",
+ " <td>7.941404</td>\n",
+ " <td>9.878711</td>\n",
+ " <td>...</td>\n",
+ " <td>6.307543</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>8.327563</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>2149 rows × 33 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Age Gender Ethnicity EducationLevel BMI Smoking \\\n",
+ "0 73 0 0 2 22.927749 0 \n",
+ "1 89 0 0 0 26.827681 0 \n",
+ "2 73 0 3 1 17.795882 0 \n",
+ "3 74 1 0 1 33.800817 1 \n",
+ "4 89 0 0 0 20.716974 0 \n",
+ "... ... ... ... ... ... ... \n",
+ "2144 61 0 0 1 39.121757 0 \n",
+ "2145 75 0 0 2 17.857903 0 \n",
+ "2146 77 0 0 1 15.476479 0 \n",
+ "2147 78 1 3 1 15.299911 0 \n",
+ "2148 72 0 0 2 33.289738 0 \n",
+ "\n",
+ " AlcoholConsumption PhysicalActivity DietQuality SleepQuality ... \\\n",
+ "0 13.297218 6.327112 1.347214 9.025679 ... \n",
+ "1 4.542524 7.619885 0.518767 7.151293 ... \n",
+ "2 19.555085 7.844988 1.826335 9.673574 ... \n",
+ "3 12.209266 8.428001 7.435604 8.392554 ... \n",
+ "4 18.454356 6.310461 0.795498 5.597238 ... \n",
+ "... ... ... ... ... ... \n",
+ "2144 1.561126 4.049964 6.555306 7.535540 ... \n",
+ "2145 18.767261 1.360667 2.904662 8.555256 ... \n",
+ "2146 4.594670 9.886002 8.120025 5.769464 ... \n",
+ "2147 8.674505 6.354282 1.263427 8.322874 ... \n",
+ "2148 7.890703 6.570993 7.941404 9.878711 ... \n",
+ "\n",
+ " FunctionalAssessment MemoryComplaints BehavioralProblems ADL \\\n",
+ "0 6.518877 0 0 1.725883 \n",
+ "1 7.118696 0 0 2.592424 \n",
+ "2 5.895077 0 0 7.119548 \n",
+ "3 8.965106 0 1 6.481226 \n",
+ "4 6.045039 0 0 0.014691 \n",
+ "... ... ... ... ... \n",
+ "2144 0.238667 0 0 4.492838 \n",
+ "2145 8.687480 0 1 9.204952 \n",
+ "2146 1.972137 0 0 5.036334 \n",
+ "2147 5.173891 0 0 3.785399 \n",
+ "2148 6.307543 0 1 8.327563 \n",
+ "\n",
+ " Confusion Disorientation PersonalityChanges \\\n",
+ "0 0 0 0 \n",
+ "1 0 0 0 \n",
+ "2 0 1 0 \n",
+ "3 0 0 0 \n",
+ "4 0 0 1 \n",
+ "... ... ... ... \n",
+ "2144 1 0 0 \n",
+ "2145 0 0 0 \n",
+ "2146 0 0 0 \n",
+ "2147 0 0 0 \n",
+ "2148 0 1 0 \n",
+ "\n",
+ " DifficultyCompletingTasks Forgetfulness Diagnosis \n",
+ "0 1 0 0 \n",
+ "1 0 1 0 \n",
+ "2 1 0 0 \n",
+ "3 0 0 0 \n",
+ "4 1 0 0 \n",
+ "... ... ... ... \n",
+ "2144 0 0 1 \n",
+ "2145 0 0 1 \n",
+ "2146 0 0 1 \n",
+ "2147 0 1 1 \n",
+ "2148 0 1 0 \n",
+ "\n",
+ "[2149 rows x 33 columns]"
+ ]
+ },
+ "execution_count": 30,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "a_df =df.drop(['DoctorInCharge', 'PatientID'], axis=1, inplace=True)\n",
+ "\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Data Pre-processing"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X = df.drop('Diagnosis', axis= 1)\n",
+ "y = df['Diagnosis']\n",
+ "\n",
+ "#split the data into test and train\n",
+ "\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+ "\n",
+ "#apply scaler\n",
+ "scaler = StandardScaler()\n",
+ "X_train_scaled = scaler.fit_transform(X_train)\n",
+ "X_test_scaled = scaler.transform(X_test)\n",
+ "\n",
+ "#X_train"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Building the models"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 32,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "kf = KFold(n_splits= 5, shuffle= True, random_state= 42)\n",
+ "\n",
+ "models = {\n",
+ " 'DecisionTree': DecisionTreeClassifier(), 'RandomForest': RandomForestClassifier(), 'svc': SVC()\n",
+ "}\n",
+ "\n",
+ "# Define parameters to test using the randomized grid search\n",
+ "param_grids = {\n",
+ " 'DecisionTree': {\n",
+ " 'criterion': ['gini', 'entropy'],\n",
+ " 'max_depth': [None, 10, 20, 30, 50],\n",
+ " 'min_samples_split': randint(2, 10),\n",
+ " 'min_samples_leaf': randint(1, 5)\n",
+ " },\n",
+ " \n",
+ " 'RandomForest': {\n",
+ " 'n_estimators': randint(50, 200),\n",
+ " 'criterion': ['gini', 'entropy'],\n",
+ " 'max_depth': [None, 10, 20, 30, 50],\n",
+ " 'min_samples_split': randint(2, 10),\n",
+ " 'min_samples_leaf': randint(1, 5)\n",
+ " },\n",
+ " \n",
+ " 'svc': {\n",
+ " 'C': [0.1, 1, 10, 100, 1000],\n",
+ " 'kernel': ['linear', 'poly', 'rbf', 'sigmoid'],\n",
+ " 'gamma': ['scale', 'auto', 0.001, 0.01, 0.1, 1, 10]\n",
+ " }\n",
+ "}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Running RandomizedSearchCV for DecisionTree...\n",
+ "Best parameters for DecisionTree: {'criterion': 'gini', 'max_depth': 10, 'min_samples_leaf': 4, 'min_samples_split': 5}\n",
+ "\n",
+ "Running RandomizedSearchCV for RandomForest...\n",
+ "Best parameters for RandomForest: {'criterion': 'entropy', 'max_depth': 10, 'min_samples_leaf': 1, 'min_samples_split': 5, 'n_estimators': 173}\n",
+ "\n",
+ "Running RandomizedSearchCV for svc...\n",
+ "Best parameters for svc: {'kernel': 'rbf', 'gamma': 0.001, 'C': 100}\n",
+ "\n"
+ ]
+ }
+ ],
+ "source": [
+ "for name, model in models.items():\n",
+ " #print(name)\n",
+ " print(f\"Running RandomizedSearchCV for {name}...\")\n",
+ " random_search = RandomizedSearchCV(model, param_distributions=param_grids[name], cv =kf, n_iter =100, random_state=42, n_jobs=-1)\n",
+ " random_search.fit(X_train_scaled, y_train)\n",
+ " print(f\"Best parameters for {name}: {random_search.best_params_}\\n\")\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Running RandomizedSearchCV for DecisionTree...\n",
+ "Best parameters for DecisionTree: {'criterion': 'gini', 'max_depth': 10, 'min_samples_leaf': 4, 'min_samples_split': 5}\n",
+ "\n",
+ "Running RandomizedSearchCV for RandomForest...\n",
+ "Best parameters for RandomForest: {'criterion': 'entropy', 'max_depth': 10, 'min_samples_leaf': 1, 'min_samples_split': 5, 'n_estimators': 173}\n",
+ "\n",
+ "Running RandomizedSearchCV for svc...\n",
+ "Best parameters for svc: {'kernel': 'rbf', 'gamma': 0.001, 'C': 100}\n"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "base",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.12.4"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
--
GitLab