2024-12-11 15:35:02 +04:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Бизнес-цель\n",
"Анализ ключевых факторов, влияющих на диабет. Предсказание вероятности развития диабета на основе медданных. Актуальность для планирвоания лечения.\n",
"1. Уровень давления(BloodPressure) и возраст(Age) - с
"2. Уровень инсулина(Insulin) и уровень глюкозы(Glucose) - уровень инсулина напрямую влияет на уровень с а х а р а
"3. Индекс массы тела(BMI) и возраст(Age) - с
"4. Уровень глюкозы(Glucose) и индекс массы тела(BMI) - как индекс массы тела влияет на уровень глюкозы."
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Pregnancies Glucose BloodPressure SkinThickness Insulin BMI \\\n",
"0 6 148 72 35 0 33.6 \n",
"1 1 85 66 29 0 26.6 \n",
"2 8 183 64 0 0 23.3 \n",
"3 1 89 66 23 94 28.1 \n",
"4 0 137 40 35 168 43.1 \n",
"\n",
" DiabetesPedigreeFunction Age Outcome \n",
"0 0.627 50 1 \n",
"1 0.351 31 0 \n",
"2 0.672 32 1 \n",
"3 0.167 21 0 \n",
"4 2.288 33 1 \n"
]
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from scipy.cluster.hierarchy import dendrogram, linkage, fcluster\n",
"from sklearn.cluster import KMeans\n",
"from sklearn.decomposition import PCA\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.metrics import silhouette_score\n",
"\n",
"df = pd.read_csv(\"data/diabetes.csv\")\n",
"df = df.head(1500)\n",
"print(df.head())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Очистка данных"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Glucose BloodPressure SkinThickness Insulin BMI Age Outcome\n",
"0 148 72 35 0 33.6 50 1\n",
"1 85 66 29 0 26.6 31 0\n",
"2 183 64 0 0 23.3 32 1\n",
"3 89 66 23 94 28.1 21 0\n",
"4 137 40 35 168 43.1 33 1\n"
]
}
],
"source": [
"df_cleaned = df.drop(columns=['Pregnancies', 'DiabetesPedigreeFunction'], errors='ignore').dropna()\n",
"print(df_cleaned.head())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Визуализация парных взаимодействий"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1600x1200 with 4 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"\n",
"sns.set(style=\"whitegrid\")\n",
"\n",
"plt.figure(figsize=(16, 12))\n",
"\n",
"# Визуализация взаимосвязи уровня давления и возраста\n",
"plt.subplot(2, 2, 1)\n",
"sns.scatterplot(x=df_cleaned['BloodPressure'], y=df_cleaned['Age'], alpha=0.6)\n",
"plt.title('BloodPressure_Age')\n",
"\n",
"# Визуализация взаимосвязи уровня инсулина и уровня глюкозы\n",
"plt.subplot(2, 2, 2)\n",
"sns.scatterplot(x=df_cleaned['Insulin'], y=df_cleaned['Glucose'], alpha=0.6)\n",
"plt.title('Insulin_Glucose')\n",
"\n",
"# Визуализация взаимосвязи индекса массы тела и возраста\n",
"plt.subplot(2, 2, 3)\n",
"sns.scatterplot(x=df_cleaned['BMI'], y=df_cleaned['Age'], alpha=0.6)\n",
"plt.title('BMI_Age')\n",
"\n",
"# Визуализация взаимосвязи уровня глюкозы и индекса массы тела\n",
"plt.subplot(2, 2, 4)\n",
"sns.scatterplot(x=df_cleaned['Glucose'], y=df_cleaned['BMI'], alpha=0.6)\n",
"plt.title('Glucose_BMI')\n",
"\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Стандартизация данных для кластеризации"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"scaler = StandardScaler()\n",
"data_scaled = scaler.fit_transform(df_cleaned)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Агломеративная (иерархическая) кластеризация"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA1AAAAJxCAYAAABMnFMWAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAADQhklEQVR4nOzdeZxT1fnH8W8myewrszEMMOybyCKiUhUUELViLdRaq1K19eeGS12qVuu+1oKKola6qCDuULV1R6zaiii44I6I7DvDLCwzyST39wfNJckkmZtMZpIwn/fr5cshy70n99wk98lzznNshmEYAgAAAAC0KC3RDQAAAACAVEEABQAAAAAWEUABAAAAgEUEUAAAAABgEQEUAAAAAFhEAAUAAAAAFhFAAQAAAIBFBFAAAAAAYBEBFAAAAABYRAAFwJJrrrlG/fv3D/nfNddck+jmAfBTW1urESNGaNmyZaqtrdUFF1ygv//974luFgDsFxyJbgCA1FFaWqqZM2cG3HbRRRclqDUAwikoKNDZZ5+tU045RYZhqH///vrjH/+Y6GYBwH6BAAqAJR6PR9nZ2Ro2bFjA7enp6YlpEICILrroIp166qmqq6tTVVWV7HZ7opsEAPsFhvABsKSpqUmZmZmWHrtkyRKdccYZGjp0qA455BBdffXVqq6uNu+fP3+++vfvr3Xr1gU8b+zYsQHDAd1ud9hhg8Hb+uyzzzRp0iQNGTJEJ554ol577bWAbdfX1+vOO+/U+PHjdeCBB2rixIl6/vnnm+0/eD/r1q3TlClTdM011+jPf/6zfvSjH2nEiBG68MILtX79+oDnL1iwQKeddpqGDx+uwYMH67jjjtPcuXPN+xcvXmxud+nSpQHPfeKJJ9S/f3+NHTu2WXv+8Ic/BDy2trZWgwcPVv/+/bV48WLL+w/nueee0+TJkzVs2DANGTJEJ510kl599dVmxzjUsM1w/TNlypSAfbzyyiuaPHmyhg8frsMPP1w33HCDamtrzfsfeOAB9e/fX8OHD5fL5Qp47iWXXNJsqGhjY6PuvvtujRkzRoMHD9aJJ56oV155JeB5Y8eO1b333qs77rhDI0eO1KGHHqqrrrpKNTU1ll9/pKGr8+fPN/vUvx+2b9+ugw8+OGRf9u/fXwMGDNDIkSN18cUXa8eOHeZj+vfvrwceeCCgbb7jEsuxlKSSkhL16tVL77//fovDbYP39fLLL2vkyJGaPn26pMDzN/g//3Z/8803uuiii3TYYYfpgAMO0JFHHqnbbrtNDQ0N5mNcLpfuu+8+jRs3TkOGDNHEiRP1j3/8w9Ixl6QNGzbo8ssv1yGHHKKhQ4fqzDPP1FdffWVuf926derfv79efvllnX/++Ro6dKiOOuooPfjgg/J6vQH9EnxMLr/88oA+NQxDM2bM0JFHHqkRI0bo/PPP18aNG83HezwezZo1SxMnTtSQIUM0bNgwnXrqqfrggw8i9qPUvM+D/20Yhk499dSAz8trrrkm4NySpKeffjrk+QOgbZCBAmDJnj17VFBQ0OLjPvroI5199tk67LDDdN9996m2tlYzZszQr371Kz3//POWgzBp70WyJD388MPq1KmTpL0Xu8GBjySdd955OuOMM3TZZZfp+eef129/+1s98sgjGjNmjBoaGnTaaadp+/btuuSSS1RZWakFCxbouuuu07Zt23T++eeb2xkzZowuvPBC899lZWWSpLfeektFRUX6wx/+IK/Xq+nTp2vKlCl6+eWXlZWVpX//+9+aOnWqfvWrX+niiy9WQ0ODnnzySd1yyy0aPHiwhg4dam4zJydHCxcu1IgRI8zbXnnlFaWlNf9NKycnR//+979lGIZsNpsk6Y033pDH4wl4XDT79zd37lzddtttuvjiizVixAjV1tbqL3/5i6688koNHz5cnTt3Nh87c+ZMlZaWSpLZH5J08skn6+c//7n575tvvjlgHw899JDuv/9+nXbaabrsssu0du1azZgxQ59++qmeffbZgHPCZrNp0aJFGjNmjCRp165deueddwKOjWEYmjp1qj7++GNdcskl6t27t958801ddtllcrlc+ulPf2o+9sknn1RVVZXuvPNOVVdXa/r06Vq9erWefvpp2Wy2Fl//hRdeqFNPPVXS3ozOoEGDzPOje/fu+u6775od0+nTp6u+vl75+fkBt/vOLbfbre+//1533323br/9dk2bNi1k34QSzbH0cbvduuOOOyzvQ5IaGhp0yy236JxzztGJJ54YcN8NN9ygAw44wPz3L37xC/PvLVu26PTTT9ewYcN01113KT09Xe+++64effRRlZWV6dxzz5UkXXnllXrnnXd0wQUXaOjQoXrnnXd0zTXXyOl0tnjMq6urdeqppyorK0vXX3+9srKy9Pjjj+v000/X888/r969e5vtuemmmzRmzBg98MADWrp0qWbOnKndu3frd7/7XcjXvWTJEr388ssBtz322GN65JFHdNVVV6lnz5666667dOmll+rZZ5+VJE2bNk1PPfWUrrjiCvXv31+bN2/Wgw8+qEsvvVT//ve/lZWVFdWx9/fiiy/qk08+ifiY2tpa3XfffTHvA0D0CKAAWFJTU2MGE5FMnz5dPXv21COPPGIOGRo6dKhOOOEEzZs3T6effrrlfe7evVuSNHz4cBUVFUmS3nvvvZCPnTJliqZOnSpJOvLIIzVp0iQ9+OCDGjNmjObPn6/ly5fr6aef1vDhw83HNDU16aGHHtKpp56qwsJCSXsDg+BhitLeAHL+/Pnq1q2bJKlXr16aNGmSXnjhBf3yl7/UihUrNGnSJF133XXmc4YPH65DDz1UixcvDghgRo8erbfeesu8iNu0aZM++eQTHXzwwc2yWqNGjdI777yjzz77zGzXq6++qpEjRwZkPaLZv7+1a9fqN7/5TUDQWFlZqcmTJ2vp0qU64YQTzNsHDhyorl27NttG586dA45Zbm6u+Xdtba0efvhhnXLKKbrhhhvM2/v166fTTz+92TnhOza+AGrhwoUqLS0NyBq8//77eu+993Tvvffqxz/+saS9/blnzx5NmzZNEydOlMOx9+stLS1Njz76qPLy8iTt7d+pU6fqvffe0+jRoy29/u7du0vaO1w13Pnh8/nnn+vFF1/UwIEDVVdXF3Cf/3NHjhyp999/X19++WXYbQWL9lj6zJkzR7t371ZJSYnlff3rX/+S0+nUOeec02zoX58+fcIeg+XLl2vgwIGaMWOGeR786Ec/0n//+18tXrxY5557rpYvX67XX39d1157rc4880xJe8/z9evXa/HixZo4cWLEY37vvfeqpqZGTz31lCorKyXtPW9+/OMfa8aMGbr//vvNxx5wwAFmgDp69Gjt3r1bjz/+uC644IKA81SSvF6vbrvtNh1wwAEB/bJ7925deOGFOuussyTtzW7dcsstqqurU35+vrZs2aLLLrssIOuakZGhiy++WN9++23E8yWSXbt2adq0ac3aE+z+++9Xly5dArKZANoWQ/gAWLJlyxaVl5dHfMyePXv02WefacyYMTIMQ01NTWpqalK3bt3Uu3dv/fe//w14vNfrNR/T1NTUbHubNm1SWlpaswudUCZNmmT+bbPZdMwxx2jZsmVqaGjQhx9+qMrKSjN48vnJT36ixsZGffbZZy1u/6CDDjKDJ0kaNGiQunXrpo8++kiSdM455+iuu+7Srl279MUXX+iVV17RI488IknNhqSNHTtWq1at0sqVKyVJr732moYOHWpeDPrLy8vTIYccorfeekuSVF1drcWLFwcENtHu398111yjK6+8UnV1dfr000/14osvmsP+Ij3Pqk8//VQul0sTJ04MuP3ggw9WZWWlPvzww4Dbx40bp4ULF8owDEl7M3O+IMln0aJFstlsGjNmTMD5M3bsWG3dujUgKzR27FgzePL92+FwmP0Wz9dvGIZuu+02nXzyyRowYEDI+5uamuRyubRs2TItXbpUgwcPDnhM8HvCP3CM9lhK0rZt2/Tggw/q6quvVkZGhqXXsXnzZv3lL3/RaaedFvW8qSOOOEJPPPGEMjIytGLFCr311lt
"text/plain": [
"<Figure size 1000x700 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[ 4 15 6 15 2 15 2 14 1 17 8 6 7 1 3 13 4 6 10 2 12 8 6 2\n",
" 3 2 6 15 7 8 7 3 15 15 10 10 8 2 2 4 12 8 7 3 8 4 15 15\n",
" 2 16 15 15 15 3 12 15 3 10 8 10 16 6 15 11 6 10 2 8 15 11 2 11\n",
" 6 12 10 9 8 10 13 15 15 16 10 15 6 10 10 10 4 15 15 11 10 5 11 12\n",
" 10 15 15 4 6 15 8 15 8 11 8 12 10 2 3 1 10 8 3 5 6 8 15 15\n",
" 4 10 10 7 6 2 10 10 2 5 3 6 3 10 15 11 10 15 8 12 7 10 15 6\n",
" 12 17 10 10 7 15 12 8 3 1 6 4 15 15 15 4 12 10 12 15 6 2 11 15\n",
" 15 15 6 2 14 10 15 3 8 4 8 6 15 11 9 15 8 4 1 4 4 3 15 10\n",
" 6 13 15 4 15 2 2 3 15 8 15 15 12 15 3 6 10 4 15 10 12 4 2 4\n",
" 2 10 2 6 1 5 14 7 15 10 8 4 1 10 6 4 15 8 15 6 3 4 4 15\n",
" 15 10 6 2 12 5 8 1 12 15 8 8 15 10 2 2 10 15 11 3 12 13 10 7\n",
" 6 10 13 10 15 13 2 15 8 10 8 10 2 15 7 11 6 12 11 5 5 7 1 4\n",
" 15 10 10 2 4 2 7 12 3 11 2 7 13 2 10 6 8 10 3 11 2 2 15 10\n",
" 3 15 2 11 15 6 10 5 11 2 2 3 10 11 2 8 4 10 7 10 13 8 15 12\n",
" 14 6 3 6 11 10 9 8 8 12 15 14 15 9 8 8 10 15 8 5 2 13 10 3\n",
" 3 7 7 5 12 10 6 15 15 3 1 17 10 10 10 4 15 10 6 10 10 15 11 15\n",
" 11 15 2 2 3 10 10 6 11 15 6 11 10 2 15 4 6 7 4 10 6 10 6 15\n",
" 6 1 10 11 12 11 2 1 15 4 15 2 12 15 10 15 4 3 16 3 12 2 14 10\n",
" 15 8 15 13 12 8 15 8 4 10 11 6 2 4 15 10 2 11 15 6 10 14 10 4\n",
" 7 10 4 7 7 15 10 10 8 15 15 10 13 12 10 10 10 7 15 7 4 15 10 7\n",
" 3 10 15 10 13 4 1 12 15 7 10 10 10 2 16 7 15 15 3 12 11 10 9 10\n",
" 10 8 4 11 15 7 2 11 7 15 15 3 3 8 8 7 15 11 16 6 15 15 15 11\n",
" 11 15 15 8 10 14 10 13 8 7 12 4 4 2 2 10 10 3 3 11 12 12 15 10\n",
" 7 15 10 10 10 7 10 8 6 3 10 15 8 15 10 10 12 2 8 8 15 11 12 10\n",
" 15 6 8 4 4 15 7 8 1 15 6 15 3 14 2 12 6 15 12 3 8 14 6 15\n",
" 15 14 10 3 13 10 3 15 12 11 15 3 3 10 3 15 8 15 2 13 12 15 8 10\n",
" 15 10 15 8 8 15 6 10 15 11 15 6 8 15 4 15 15 8 5 14 11 1 3 4\n",
" 3 15 15 11 10 15 10 1 15 12 8 2 7 4 3 4 2 12 5 2 10 12 12 15\n",
" 10 12 7 6 5 8 6 11 15 4 10 6 17 11 15 15 11 4 15 6 10 4 15 1\n",
" 3 14 11 8 11 2 4 14 11 10 16 11 5 2 11 10 2 11 15 3 3 7 10 2\n",
" 10 10 3 12 8 10 11 11 8 15 2 6 4 15 7 10 11 10 11 6 4 15 15 5\n",
" 12 10 4 10 3 5 6 10 15 1 4 4 12 6 8 5 15 4 15 12 10 11 6 10]\n"
]
}
],
"source": [
"linkage_matrix = linkage(data_scaled, method='ward')\n",
"plt.figure(figsize=(10, 7))\n",
"dendrogram(linkage_matrix)\n",
"plt.title('Дендрограмма агломеративной кластеризации')\n",
"plt.xlabel('Индекс образца')\n",
"plt.ylabel('Расстояние')\n",
"plt.show()\n",
"\n",
"# Получение результатов кластеризации с
"result = fcluster(linkage_matrix, t=10, criterion='distance')\n",
"print(result)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Визуализация распределения кластеров"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1600x1200 with 4 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"\n",
"sns.set(style=\"whitegrid\")\n",
"\n",
"plt.figure(figsize=(16, 12))\n",
"\n",
"# Визуализация взаимосвязи уровня давления и возраста\n",
"plt.subplot(2, 2, 1)\n",
"sns.scatterplot(x=df_cleaned['BloodPressure'], y=df_cleaned['Age'], hue=df_cleaned['Outcome'], palette='Set1', alpha=0.6)\n",
"plt.title('BloodPressure_Age')\n",
"\n",
"# Визуализация взаимосвязи уровня инсулина и уровня глюкозы\n",
"plt.subplot(2, 2, 2)\n",
"sns.scatterplot(x=df_cleaned['Insulin'], y=df_cleaned['Glucose'], hue=df_cleaned['Outcome'], palette='Set1', alpha=0.6)\n",
"plt.title('Insulin_Glucose')\n",
"\n",
"# Визуализация взаимосвязи индекса массы тела и возраста\n",
"plt.subplot(2, 2, 3)\n",
"sns.scatterplot(x=df_cleaned['BMI'], y=df_cleaned['Age'], hue=df_cleaned['Outcome'], palette='Set1', alpha=0.6)\n",
"plt.title('BMI_Age')\n",
"\n",
"# Визуализация взаимосвязи уровня глюкозы и индекса массы тела\n",
"plt.subplot(2, 2, 4)\n",
"sns.scatterplot(x=df_cleaned['Glucose'], y=df_cleaned['BMI'], hue=df_cleaned['Outcome'], palette='Set1', alpha=0.6)\n",
"plt.title('Glucose_BMI')\n",
"\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## KMeans (неиерархическая кластеризация) для сравнения"
]
},
{
"cell_type": "code",
2024-12-11 15:47:49 +04:00
"execution_count": 24,
2024-12-11 15:35:02 +04:00
"metadata": {},
2024-12-11 15:47:49 +04:00
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Центры кластеров:\n",
" [[103.03726708 33.13167702 72.86335404 29.18322981]\n",
" [105.31168831 25.04350649 45.6038961 25.57792208]\n",
" [136.91472868 29.89457364 78.20155039 53.64341085]\n",
" [158.21472393 37.96809816 76.68711656 32.34969325]]\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1600x1200 with 4 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
2024-12-11 15:35:02 +04:00
"source": [
"from sklearn.cluster import KMeans\n",
"from sklearn.preprocessing import StandardScaler\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"\n",
"# Масштабирование данных\n",
"scaler = StandardScaler()\n",
"data_scaled = scaler.fit_transform(df_cleaned[['Glucose', 'BMI', 'BloodPressure', 'Age']])\n",
"\n",
"# Обучение K-Means\n",
"random_state = 17\n",
"kmeans = KMeans(n_clusters=4, random_state=random_state)\n",
"labels = kmeans.fit_predict(data_scaled)\n",
"centers = kmeans.cluster_centers_\n",
"\n",
"# Обратная стандартизация центров кластеров\n",
"centers = scaler.inverse_transform(centers)\n",
"print(\"Центры кластеров:\\n\", centers)\n",
"\n",
"# Визуализация кластеризации\n",
"plt.figure(figsize=(16, 12))\n",
"\n",
"# Взаимосвязь Glucose и BMI\n",
"plt.subplot(2, 2, 1)\n",
"sns.scatterplot(x=df_cleaned['Glucose'], y=df_cleaned['BMI'], hue=labels, palette='Set1', alpha=0.6)\n",
"plt.scatter(centers[:, 0], centers[:, 1], s=300, c='red', label='Centroids')\n",
"plt.title('KMeans Clustering: Glucose vs BMI')\n",
"plt.legend()\n",
"\n",
"# Взаимосвязь Glucose и Age\n",
"plt.subplot(2, 2, 2)\n",
"sns.scatterplot(x=df_cleaned['Glucose'], y=df_cleaned['Age'], hue=labels, palette='Set1', alpha=0.6)\n",
"plt.scatter(centers[:, 0], centers[:, 3], s=300, c='red', label='Centroids')\n",
"plt.title('KMeans Clustering: Glucose vs Age')\n",
"plt.legend()\n",
"\n",
"# Взаимосвязь BloodPressure и BMI\n",
"plt.subplot(2, 2, 3)\n",
"sns.scatterplot(x=df_cleaned['BloodPressure'], y=df_cleaned['BMI'], hue=labels, palette='Set1', alpha=0.6)\n",
"plt.scatter(centers[:, 2], centers[:, 1], s=300, c='red', label='Centroids')\n",
"plt.title('KMeans Clustering: BloodPressure vs BMI')\n",
"plt.legend()\n",
"\n",
"# Взаимосвязь BloodPressure и Age\n",
"plt.subplot(2, 2, 4)\n",
"sns.scatterplot(x=df_cleaned['BloodPressure'], y=df_cleaned['Age'], hue=labels, palette='Set1', alpha=0.6)\n",
"plt.scatter(centers[:, 2], centers[:, 3], s=300, c='red', label='Centroids')\n",
"plt.title('KMeans Clustering: BloodPressure vs Age')\n",
"plt.legend()\n",
"\n",
"plt.tight_layout()\n",
"plt.show()"
]
2024-12-11 15:47:49 +04:00
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## PCA для визуализации сокращенной размерности"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABi8AAAJHCAYAAADoqsXxAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdeXxU1fk/8M+9d/Yl+x4SCISENSRsgshatIr70toKWqtW/UqLrbut4t5qpW7g/tNqXalLi0sV911kEZBVgYQlQPZlJrPP3PP7Y8iQIZMQkslkAp/368Wr5Z479z4zcwfvuc8555GEEAJERERERERERERERERxQu7rAIiIiIiIiIiIiIiIiNpi8oKIiIiIiIiIiIiIiOIKkxdERERERERERERERBRXmLwgIiIiIiIiIiIiIqK4wuQFERERERERERERERHFFSYviIiIiIiIiIiIiIgorjB5QUREREREREREREREcYXJCyIiIiIiIiIiIiIiiitMXhARUZcIIfo6BOpl/I6JiIiIqKv6471jf4yZjgy/Y6KjC5MXRNShCy+8EMXFxWF/Ro0ahRkzZuCOO+5Ac3Nzu9dUVFTg9ttvx+zZs1FSUoIZM2bgmmuuwdatWzs8z4MPPoji4mLcdddd3Y5r2LBhGDt2LM455xwsW7as2++5re+++w7FxcX47rvvonK8nqqsrERxcTHefPPNDvdZvHhxu8+mpKQEP//5z3HfffehqanpiM9rs9lwww03YPXq1T2IPrLO3tOKFStQWlqK008/HfX19aF9i4uLsXTp0ojHs9vtGD16dFx9b0eiq7+fWbNm4aabborqubdt24Zf//rXUTlWV65VIiIi6n/YP2D/AOjd/kErr9eLF154Ab/4xS8wduxYjB07FmeffTaeffZZuFyubh3zsccewzPPPBPlSPvO8uXLcemll+L4449HaWkpTjvtNDz22GNoaWkJ7dNX1+yFF16ICy+8MPT3H3/8EWeddRZGjRqFOXPm4M0330RxcTEqKyujet5Dv+PW65+I+i9NXwdARPFtxIgRuO2220J/9/l82LRpEx544AFs2bIFr7zyCiRJAgB88MEHuOGGGzB06FD83//9HwYMGICqqio8//zz+OUvf4nHH38cU6ZMCTu+qqr473//i6KiIixbtgzXXXcdjEbjEccVCARQVVWF5557DjfccAOSkpIwffr0KH0K/U/rw30hBJxOJzZs2ICnn34an3zyCV555RWkpKR0+VhbtmzBsmXLcO655/ZWuO2sXLkSV155JQoKCvDss88iOTk5dGMryzLef/99nH/++e1e9+GHH8Lr9cYszmjqzu8nmt5//32sXbs2KsfKyMjA0qVLkZ+fH5XjERERUfxg/6B/6k/9A7vdjt/97nfYunUrfv3rX2PBggWQJAmrV6/G448/jv/85z94+umnkZWVdUTHffjhh/H73/++V2KOJVVVcf311+P999/Hueeei1//+tcwm81Yt24dnnnmGXz00Ud47rnnkJCQ0Gcxtv0tAsCjjz6Kffv24dFHH0VKSgpyc3OxdOlSZGRkRPW8h37Hv/jFLzB16tSonoOIYovJCyLqlMViQWlpadi2CRMmwOFw4JFHHsH69etRWlqK3bt348Ybb8TUqVPx0EMPQVGU0P4nnXQSfv3rX+PGG2/EJ598Ap1OF2r76quvUFVVhQceeADz5s3DO++8g1/84hfdigsApk2bhsmTJ+PNN988pjsnh342U6ZMwfHHH48LLrgADzzwAO6+++6+CawLVq1ahSuuuAKFhYV49tln2910jx07Ft999x0aGhradbLeffddDB8+HFu2bIllyD3W3d9PvNLpdBF/n0RERNT/sX/QP/Wn/sFf/vIXbNu2Da+++iqGDRsW2n7CCSfgzDPPxK9//Wtcd911eOGFF0KJsmPJ//t//w/vvPMOlixZghNPPDG0ffLkyZg4cSLmzp2LRx99FDfffHOfxVhYWBj298bGRhQVFYX9Bo8kYdZdWVlZR5zkIqL4wmWjiKhbRo0aBQDYt28fAOCFF16A1+vFLbfcEtYxAQCj0Ygbb7wR5557brup5G+88QaKioowbtw4HHfccR0uB9RVer0eOp0u7CZWVVU89dRTOPHEEzFq1Cj8/Oc/xwsvvNDuta+++ip+/vOfo6SkBPPmzQu9t1YdTTktLi7G4sWLQ39vaWnBXXfdhalTp6K0tBTnnnsuPvvss7DXvPbaazj11FND0+wXL16MQCAQts8HH3yAM844AyUlJTj77LM7nVrfFSUlJTjppJPw3//+N2yq9WuvvYZzzjkHpaWlKCkpwZlnnon33nsPQHCa8UUXXQQAuOiii0JTfwOBAJ566imcdtppKCkpQWlpKX71q19hxYoVoeO2TmNv+9kczurVq3H55ZejuLi4w9FCJ554ImRZxocffhi2vbGxEStWrMCpp57a7jX79u3DNddcg4kTJ2LMmDH4zW9+g82bN4ftU1lZiRtuuAEnnHACRo4cicmTJ+OGG25AY2NjaJ9Zs2bhkUcewX333Yfjjz8eJSUluPTSS7Fz587QPg0NDbj22msxZcoUjB49GmeeeSb++9//dvq+u/v7ATqeCn7oVO2NGzfiN7/5DcaNG4eysjJcfPHFWLduHYDgtb1kyRIA4ddzV347F154Ia677josWLAApaWl+O1vf9tuCYM333wTI0aMwPr163H++edj9OjRmDlzZrtp+zU1NfjTn/6EiRMnYsKECVi4cCEefPBBzJo1q9PPj4iIiPoe+wcHsX/Q/f7Btm3bsHz5clxxxRVhiYtWBQUFuPrqq7Fq1arQsbvyPbS2L1myJGzfdevW4ZJLLsHYsWMxadIkXHPNNaiurg6119TU4Oabb8b06dNRUlKC8847Dx9//HG787zyyiu46aabMG7cOEycOBF333033G437rvvPkyaNAnHHXcc/vKXv8Dj8YRe19XrsC2fz4dnn30W06ZNC0tctBo3bhwWLFjQLnnQ1kcffYQLLrgAZWVlGDVqFE4++WS89NJLYfs8//zzOPnkkzF69GhMnToVt99+e9hyVF9//TV++ctfoqysDBMmTMD//d//YceOHaH2tn2R4uJirFy5EqtWrQr1ESItG/X555/jV7/6FUpLS3HCCSdg4cKFsNlsofZVq1bh0ksvxYQJEzBq1CjMmjULixcvhqqqofMA4d9xpGvjf//7H8455xyUlZVhypQpWLhwYdi/Q4sXL8aJJ56Izz77DKeffnrouzlcn46IegeTF0TULRUVFQCAvLw8AMCXX36JESNGIDMzM+L+kydPxp/+9Cekp6eHtjU1NeGTTz7BWWedBQA4++yzsWHDBmzatOmw5xdCwO/3h/54PB6Ul5fj5ptvhsPhwJlnnhna9/bbb8cjjzyCM844A0888QROPvlk/PWvf8Wjjz4a2ufFF1/EbbfdhunTp+Oxxx7DmDFjcOuttx7x5xIIBHDJJZfg7bffxhVXXIHHHnsMgwcPxvz580Nrwj755JO49dZbMXnyZDzxxBOYO3cunn766bDzffLJJ1iwYAGKi4vx6KOP4pRTTsH1119/xPEcasqUKfD5fNiwYQMA4KWXXsLChQsxe/ZsPPnkk1i0aBF0Oh2uu+46VFVVYeTIkVi4cCEAYOHChaHpv4sWLcJjjz2G888/H//v//0/3HXXXWhqasLVV18d6vi0Lh3UlZFyALBmzRr87ne/Q3FxMZ555hlYLJaI+yUkJGDKlCl4//33w7YvX74cOTk5KCkpCdve0NCAX/3qV9i0aRNuvfVW/OMf/4Cqqpg7d27oBtvlcuGiiy7Cjh07cNttt+GZZ57BRRddhHfffRcPPvhg2PH+9a9/oby8HH/7299w9913Y+PGjbjxxhtD7ddffz127NiBO+64A08//TRGjBiBG2+8Mazjdqju/H6OREtLCy677DIkJydj8eLFePDBB+FyuXDppZfCbrfjF7/4Bc477zwACPvOuvLbAYD33nsPZrMZjz/+OC677LKIMaiqij/+8Y+YM2cOnnrqKYwdOxZ///vf8eWXXwIIrmv8m9/8Bt9
"text/plain": [
"<Figure size 1600x600 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from sklearn.decomposition import PCA\n",
"\n",
"# Снижение размерности с
"pca = PCA(n_components=2)\n",
"reduced_data = pca.fit_transform(data_scaled)\n",
"\n",
"# Визуализация сокращенных данных\n",
"plt.figure(figsize=(16, 6))\n",
"\n",
"# Визуализация для KMeans кластеризации\n",
"plt.subplot(1, 2, 1)\n",
"sns.scatterplot(x=reduced_data[:, 0], y=reduced_data[:, 1], hue=labels, palette='Set1', alpha=0.6)\n",
"plt.title('PCA Reduced Data: KMeans Clustering')\n",
"\n",
"# Визуализация для исходных данных с
"plt.subplot(1, 2, 2)\n",
"sns.scatterplot(x=reduced_data[:, 0], y=reduced_data[:, 1], hue=df_cleaned['Outcome'], palette='Set2', alpha=0.6)\n",
"plt.title('PCA Reduced Data: Outcome Classification')\n",
"\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Выбор количества кластеров на основе инерции\n",
"Инерция -- сумма квадратов расстояний выборок до ближайшего центра кластера, взвешенная по весам выборок, если таковые имеются."
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1000x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"inertias = []\n",
"clusters_range = range(1, 23)\n",
"for i in clusters_range:\n",
" kmeans = KMeans(n_clusters=i, random_state=random_state)\n",
" kmeans.fit(data_scaled)\n",
" inertias.append(kmeans.inertia_)\n",
"\n",
"\n",
"plt.figure(figsize=(10, 6))\n",
"plt.plot(clusters_range, inertias, marker='o')\n",
"plt.title('Метод локтя для оптимального k')\n",
"plt.xlabel('Количество кластеров')\n",
"plt.ylabel('Инерция')\n",
"plt.grid(True)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"+- после 18-г о о г о
"\n",
"Расчитаем коэффициенты силуэта"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1000x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"silhouette_scores = []\n",
"for i in clusters_range[1:]: \n",
" kmeans = KMeans(n_clusters=i, random_state=random_state)\n",
" labels = kmeans.fit_predict(data_scaled)\n",
" score = silhouette_score(data_scaled, labels)\n",
" silhouette_scores.append(score)\n",
"\n",
"# Построение диаграммы значений силуэта\n",
"plt.figure(figsize=(10, 6))\n",
"plt.plot(clusters_range[1:], silhouette_scores, marker='o')\n",
"plt.title('Коэффициенты силуэта для разных k')\n",
"plt.xlabel('Количество кластеров')\n",
"plt.ylabel('Коэффициент силуэта')\n",
"plt.grid(True)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Средний коэффициент силуэта (silhouette score) используется для оценки качества кластеризации. Е г о
"\n",
"0.7–
"0.5-0.7 : Кластеры четко различимы, но есть некоторое пересечение между ними. Это хороший результат.\n",
"0.25-0.5 : Кластеры перекрываются, что указывает на менее четкую границу между группами. Качество кластеризации удовлетворительное, но может потребоваться уточнение числа кластеров или доработка данных.\n",
"Близко к 0.0: Кластеры сильно перекрываются или распределение данных не позволяет выделить четкие группы. В
"Меньше 0.0: Плохая кластеризация: точки ближе к центрам чужих кластеров, чем к своим. Это сигнал о
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Средний коэффициент силуэта: 0.213\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1000x700 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.metrics import silhouette_score\n",
"from sklearn.cluster import KMeans\n",
"from sklearn.decomposition import PCA\n",
"\n",
"scaler = StandardScaler()\n",
"data_scaled = scaler.fit_transform(df_cleaned[['Glucose', 'BMI', 'BloodPressure', 'Age']])\n",
"\n",
"# Применение K-Means\n",
"kmeans = KMeans(n_clusters=4, random_state=42) \n",
"df_clusters = kmeans.fit_predict(data_scaled)\n",
"\n",
"# Оценка качества кластеризации\n",
"silhouette_avg = silhouette_score(data_scaled, df_clusters)\n",
"print(f'Средний коэффициент силуэта: {silhouette_avg:.3f}')\n",
"\n",
"# Визуализация кластеров\n",
"pca = PCA(n_components=2)\n",
"df_pca = pca.fit_transform(data_scaled)\n",
"\n",
"plt.figure(figsize=(10, 7))\n",
"sns.scatterplot(x=df_pca[:, 0], y=df_pca[:, 1], hue=df_clusters, palette='viridis', alpha=0.7)\n",
"plt.title('Визуализация кластеров с
"plt.xlabel('Первая ко о е
"plt.ylabel('Вторая ко о е
"plt.legend(title='Кластер', loc='upper right')\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"В Н а
]
2024-12-11 15:35:02 +04:00
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"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": "3.12.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
