2024-11-15 17:21:29 +04:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Начало лабораторной\n",
"\n",
"Цены на кофе - https://www.kaggle.com/datasets/mayankanand2701/starbucks-stock-price-dataset"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Атрибуты\n",
"\n",
"Date — Дата\n",
"\n",
"Open — Открытие\n",
"\n",
"High — Макс. цена\n",
"\n",
"Low — Мин. цена\n",
"\n",
"Close — Закрытие\n",
"\n",
"Adj Close — Скорректированная цена закрытия\n",
"\n",
"Volume — Объем торгов"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Бизнес-цель: Улучшение финансового планирования\n",
"\n",
"Использование подходов кластеризации для предсказания объемов продаж и доходов по различным сегментам"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Выгружаем данные**"
]
},
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 3,
2024-11-15 17:21:29 +04:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Date Open High Low Close Adj Close Volume\n",
"0 1992-06-26 0.328125 0.347656 0.320313 0.335938 0.260703 224358400\n",
"1 1992-06-29 0.339844 0.367188 0.332031 0.359375 0.278891 58732800\n",
"2 1992-06-30 0.367188 0.371094 0.343750 0.347656 0.269797 34777600\n",
"3 1992-07-01 0.351563 0.359375 0.339844 0.355469 0.275860 18316800\n",
"4 1992-07-02 0.359375 0.359375 0.347656 0.355469 0.275860 13996800\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(\"./static/csv/Starbucks Dataset.csv\")\n",
"print(df.head()) "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Очистка данных**"
]
},
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 4,
2024-11-15 17:21:29 +04:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Open High Low Close Adj Close Volume\n",
"0 0.328125 0.347656 0.320313 0.335938 0.260703 224358400\n",
"1 0.339844 0.367188 0.332031 0.359375 0.278891 58732800\n",
"2 0.367188 0.371094 0.343750 0.347656 0.269797 34777600\n",
"3 0.351563 0.359375 0.339844 0.355469 0.275860 18316800\n",
"4 0.359375 0.359375 0.347656 0.355469 0.275860 13996800\n"
]
}
],
"source": [
"\n",
"df_cleaned = df.drop(columns=['Date'], errors='ignore').dropna()\n",
"print(df_cleaned.head()) # Вывод очищенного DataFrame\n"
]
},
2025-02-07 11:59:24 +04:00
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Date 0\n",
"Open 0\n",
"High 0\n",
"Low 0\n",
"Close 0\n",
"Adj Close 0\n",
"Volume 0\n",
"dtype: int64\n",
"Date False\n",
"Open False\n",
"High False\n",
"Low False\n",
"Close False\n",
"Adj Close False\n",
"Volume False\n",
"dtype: bool\n"
]
}
],
"source": [
"# Процент пропущенных значений признаков\n",
"for i in df.columns:\n",
" null_rate = df[i].isnull().sum() / len(df) * 100\n",
" if null_rate > 0:\n",
" print(f'{i} Процент пустых значений: %{null_rate:.2f}')\n",
"\n",
"print(df.isnull().sum())\n",
"\n",
"print(df.isnull().any())"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Date object\n",
"Open float64\n",
"High float64\n",
"Low float64\n",
"Close float64\n",
"Adj Close float64\n",
"Volume int64\n",
"dtype: object"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Проверка типов столбцов\n",
"df.dtypes"
]
},
2024-11-15 17:21:29 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Визуализация парных взаимосвязей**"
]
},
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 7,
2024-11-15 17:21:29 +04:00
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1600x1200 with 4 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"\n",
"sns.set(style=\"whitegrid\")\n",
"\n",
"plt.figure(figsize=(16, 12))\n",
"plt.subplot(2, 2, 1)\n",
"sns.scatterplot(x=df_cleaned['Open'], y=df_cleaned['High'], alpha=0.6)\n",
"plt.title('Open vs High')\n",
"\n",
"plt.subplot(2, 2, 2)\n",
"sns.scatterplot(x=df_cleaned['Low'], y=df_cleaned['Close'], alpha=0.6)\n",
"plt.title('Low vs Close')\n",
"\n",
"plt.subplot(2, 2, 3)\n",
"sns.scatterplot(x=df_cleaned['High'], y=df_cleaned['Adj Close'], alpha=0.6)\n",
"plt.title('High vs Adj Close')\n",
"\n",
"plt.subplot(2, 2, 4)\n",
"sns.scatterplot(x=df_cleaned['Volume'], y=df_cleaned['Adj Close'], alpha=0.6)\n",
"plt.title('Volume vs Adj Close')\n",
"\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"**Стандартизация данных для кластеризации**\n",
2025-02-07 11:59:24 +04:00
"\n",
"Стандартизация данных — процесс приведения всех признаков (столбцов) к одному масштабу.\n",
2024-11-15 17:21:29 +04:00
"\n"
]
},
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 8,
2024-11-15 17:21:29 +04:00
"metadata": {},
"outputs": [],
"source": [
"scaler = StandardScaler()\n",
"data_scaled = scaler.fit_transform(df_cleaned)"
]
},
2025-02-07 11:59:24 +04:00
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Преобразование в DataFrame для удобства\n",
"df_scaled = pd.DataFrame(data_scaled, columns=df_cleaned.columns)\n",
"\n",
"# Понижение размерности до 2 компонент\n",
"pca = PCA(n_components=2)\n",
"kc_pca = pca.fit_transform(df_scaled)\n",
"\n",
"# Визуализация\n",
"plt.figure(figsize=(8, 6))\n",
"plt.scatter(kc_pca[:, 0], kc_pca[:, 1], alpha=0.6)\n",
"plt.title(\"PCA Visualization of Housing Data\")\n",
"plt.xlabel(\"Principal Component 1\")\n",
"plt.ylabel(\"Principal Component 2\")\n",
"plt.show()"
]
},
2024-11-15 17:21:29 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
2025-02-07 11:59:24 +04:00
"**Агломеративная (иерархическая) кластеризация**\n",
"\n",
"Иерархическая кластеризация — метод машинного обучения, предназначенный для группировки объектов (точек данных) на основе их схожести или расстояния друг от друга. Основная идея заключается в создании структуры кластеров в виде дерева (дендрограммы), которое показывает, как объекты группируются на разных уровнях.\n"
2024-11-15 17:21:29 +04:00
]
},
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 10,
2024-11-15 17:21:29 +04:00
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1000x700 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[11 9 6 ... 14 14 15]\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) # Вывод результатов кластеризации"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"**Визуализация распределения кластеров**\n"
]
},
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 11,
2024-11-15 17:21:29 +04:00
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1600x1200 with 4 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.figure(figsize=(16, 12))\n",
"plt.subplot(2, 2, 1)\n",
"sns.scatterplot(x=df_cleaned['Open'], y=df_cleaned['High'], hue=result, palette='Set1', alpha=0.6)\n",
"plt.title('Open vs High Clusters')\n",
"\n",
"plt.subplot(2, 2, 2)\n",
"sns.scatterplot(x=df_cleaned['Low'], y=df_cleaned['Close'], hue=result, palette='Set1', alpha=0.6)\n",
"plt.title('Low vs Close Clusters')\n",
"\n",
"plt.subplot(2, 2, 3)\n",
"sns.scatterplot(x=df_cleaned['High'], y=df_cleaned['Adj Close'], hue=result, palette='Set1', alpha=0.6)\n",
"plt.title('High vs Adj Close Clusters')\n",
"\n",
"plt.subplot(2, 2, 4)\n",
"sns.scatterplot(x=df_cleaned['Volume'], y=df_cleaned['Adj Close'], hue=result, palette='Set1', alpha=0.6)\n",
"plt.title('Volume vs Adj Close Clusters')\n",
"\n",
"plt.tight_layout()\n",
"plt.show()\n"
]
},
2025-02-07 11:59:24 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"Неиерархическая кластеризация — метод группировки данных, при котором объекты распределяются по заданному числу кластеров(в нашем случае - 𝑘 В с
"\n",
"K-Means:\n",
"\n",
"Один из самых популярных методов.\n",
"Делит данные на 𝑘
"Центроиды обновляются итеративно, пока результат не стабилизируется."
]
},
2024-11-15 17:21:29 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"**KMeans (неиерархическая кластеризация) для сравнения**\n"
]
},
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 12,
2024-11-15 17:21:29 +04:00
"metadata": {},
"outputs": [
2025-02-07 11:59:24 +04:00
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\a3012\\AIM-PIbd-31-Zhirnova-A-E\\aimenv\\Lib\\site-packages\\joblib\\externals\\loky\\backend\\context.py:136: UserWarning: Could not find the number of physical cores for the following reason:\n",
"found 0 physical cores < 1\n",
"Returning the number of logical cores instead. You can silence this warning by setting LOKY_MAX_CPU_COUNT to the number of cores you want to use.\n",
" warnings.warn(\n",
" File \"c:\\Users\\a3012\\AIM-PIbd-31-Zhirnova-A-E\\aimenv\\Lib\\site-packages\\joblib\\externals\\loky\\backend\\context.py\", line 282, in _count_physical_cores\n",
" raise ValueError(f\"found {cpu_count_physical} physical cores < 1\")\n"
]
},
2024-11-15 17:21:29 +04:00
{
"name": "stdout",
"output_type": "stream",
"text": [
"Центры кластеров:\n",
" [[1.11514668e+01 1.12730106e+01 1.10263573e+01 1.11517428e+01\n",
" 8.88448878e+00 1.38211576e+07]\n",
" [7.75090604e+01 7.82228147e+01 7.67780822e+01 7.75181228e+01\n",
" 7.11609142e+01 8.57799102e+06]\n",
" [6.49827065e+00 6.66207109e+00 6.35238963e+00 6.51956023e+00\n",
" 5.11050859e+00 4.27841811e+07]]\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1600x1200 with 4 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"random_state = 9\n",
"kmeans = KMeans(n_clusters=3, random_state=random_state)\n",
"labels = kmeans.fit_predict(data_scaled)\n",
"centers = kmeans.cluster_centers_\n",
"\n",
"# Отображение центроидов\n",
"centers = scaler.inverse_transform(centers) # Обратная стандартизация\n",
"print(\"Центры кластеров:\\n\", centers)\n",
"\n",
"# Визуализация результатов кластеризации KMeans\n",
"plt.figure(figsize=(16, 12))\n",
"plt.subplot(2, 2, 1)\n",
"sns.scatterplot(x=df_cleaned['Open'], y=df_cleaned['High'], 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: Open vs High')\n",
"plt.legend()\n",
"\n",
"plt.subplot(2, 2, 2)\n",
"sns.scatterplot(x=df_cleaned['Low'], y=df_cleaned['Close'], 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: Low vs Close')\n",
"plt.legend()\n",
"\n",
"plt.subplot(2, 2, 3)\n",
"sns.scatterplot(x=df_cleaned['High'], y=df_cleaned['Adj Close'], hue=labels, palette='Set1', alpha=0.6)\n",
"plt.scatter(centers[:, 1], centers[:, 4], s=300, c='red', label='Centroids')\n",
"plt.title('KMeans Clustering: High vs Adj Close')\n",
"plt.legend()\n",
"\n",
"plt.subplot(2, 2, 4)\n",
"sns.scatterplot(x=df_cleaned['Volume'], y=df_cleaned['Adj Close'], hue=labels, palette='Set1', alpha=0.6)\n",
"plt.scatter(centers[:, 3], centers[:, 4], s=300, c='red', label='Centroids')\n",
"plt.title('KMeans Clustering: Volume vs Adj Close')\n",
"plt.legend()\n",
"\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
2025-02-07 11:59:24 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"PCA (Principal Component Analysis) — метод сокращения размерности, используемый для преобразования высокоразмерных данных в пространство с
"\n",
"В
]
},
2024-11-15 17:21:29 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"**PCA для визуализации сокращенной размерности**\n"
]
},
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 13,
2024-11-15 17:21:29 +04:00
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1600x600 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"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",
"plt.subplot(1, 2, 1)\n",
"sns.scatterplot(x=reduced_data[:, 0], y=reduced_data[:, 1], hue=result, palette='Set1', alpha=0.6)\n",
"plt.title('PCA reduced data: Agglomerative Clustering')\n",
"\n",
"plt.subplot(1, 2, 2)\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",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"**Анализ инерции для метода локтя (метод оценки суммы квадратов расстояний)**\n"
]
},
2025-02-07 11:59:24 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Анализ инерции для метода локтя — это техника, используемая для определения оптимального числа кластеров в задаче кластеризации (например, для алгоритма K-Means). Метод основывается на оценке суммы квадратичных отклонений (или инерции) объектов от центров их кластеров.\n",
"\n",
"Инерция (в контексте кластеризации) — это метрика, которая измеряет \"плотность\" кластеров, то есть, насколько близко точки внутри каждого кластера расположены к е г о
"\n",
"Метод локтя:\n",
"\n",
"Для различных значений 𝑘
"Значения инерции отображаются на графике в зависимости от 𝑘
"Смотрится точка, после которой уменьшение инерции значительно замедляется. Эта точка называется локтем, и соответствующее значение 𝑘
]
},
2024-11-15 17:21:29 +04:00
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 14,
2024-11-15 17:21:29 +04:00
"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, 11)\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()"
]
},
2025-02-07 11:59:24 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Можно заметить, что после 9-г о о г о
]
},
2024-11-15 17:21:29 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"**Расчет коэффициентов силуэта**\n"
]
},
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 15,
2024-11-15 17:21:29 +04:00
"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()"
]
},
2025-02-07 11:59:24 +04:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Средний коэффициент силуэта (silhouette score) используется для оценки качества кластеризации. Е г о
"\n",
"Близко к 1.0 (0.7–
"\n",
"От 0.5 до 0.7: Кластеры четко различимы, но есть некоторое пересечение между ними. Это хороший результат.\n",
"\n",
"От 0.25 до 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",
"\n",
"Близко к 0.0: Кластеры сильно перекрываются или распределение данных не позволяет выделить четкие группы. В
"\n",
"Меньше 0.0: Плохая кластеризация: точки ближе к центрам чужих кластеров, чем к своим. Это сигнал о
]
},
2024-11-15 17:21:29 +04:00
{
"cell_type": "code",
2025-02-07 11:59:24 +04:00
"execution_count": 16,
2024-11-15 17:21:29 +04:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Средний коэффициент силуэта: 0.547\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",
"\n",
"# ========================\n",
"# Применение K-Means\n",
"# ========================\n",
"kmeans = KMeans(n_clusters=3, random_state=42) \n",
"df_clusters = kmeans.fit_predict(df_scaled)\n",
"\n",
"# ========================\n",
"# Оценка качества кластеризации\n",
"# ========================\n",
"silhouette_avg = silhouette_score(df_scaled, df_clusters)\n",
"print(f'Средний коэффициент силуэта: {silhouette_avg:.3f}')\n",
"\n",
"# ========================\n",
"# Визуализация кластеров\n",
"# ========================\n",
"from sklearn.decomposition import PCA\n",
"\n",
"pca = PCA(n_components=2)\n",
"df_pca = pca.fit_transform(df_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",
2024-11-15 19:20:46 +04:00
"plt.show()\n",
"# что-то такое"
2024-11-15 17:21:29 +04:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2025-02-07 11:59:24 +04:00
"Средний коэффициент силуэта, равный 0.547, указывает на умеренно хорошую кластеризацию.\n",
"Кластеры четко различимы, но есть некоторое пересечение между ними. Это хороший результат."
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Средний коэффициент силуэта (агломеративная кластеризация): 0.578\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1000x700 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from sklearn.cluster import AgglomerativeClustering\n",
"\n",
"# ========================\n",
"# Агломеративная кластеризация\n",
"# ========================\n",
"agg_cluster = AgglomerativeClustering(n_clusters=3) \n",
"labels_agg = agg_cluster.fit_predict(df_scaled)\n",
"\n",
"# ========================\n",
"# Оценка качества кластеризации\n",
"# ========================\n",
"silhouette_avg_agg = silhouette_score(df_scaled, labels_agg)\n",
"print(f'Средний коэффициент силуэта (агломеративная кластеризация): {silhouette_avg_agg:.3f}')\n",
"\n",
"# ========================\n",
"# Визуализация кластеров\n",
"# ========================\n",
"pca = PCA(n_components=2)\n",
"df_pca = pca.fit_transform(df_scaled)\n",
"\n",
"plt.figure(figsize=(10, 7))\n",
"sns.scatterplot(x=df_pca[:, 0], y=df_pca[:, 1], hue=labels_agg, 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": [
"Значение коэффициента силуэта лежит в диапазоне от -1 до 1. Ближе к 1: Хорошо сформированные, плотные кластеры, четко отделенные друг от друга.\n",
"\n",
"Ближе к 0: Кластеры пересекаются или слабо разделены, не имеют четких границ. Точки расположены одинаково близко как к своему кластеру, так и к соседним. Ближе к -1 (Отрицательные значения): Некоторые точки скорее относятся к другим кластерам, чем к текущему (ближе к центрам других кластеров). Очень плохая кластеризация.\n",
"Ближе к 1: В с е о о б
"\n",
"Значение 0.578 указывает на то, что кластеры хорошо сформированные, плотные кластеры, четко отделенные друг от друга."
2024-11-15 17:21:29 +04:00
]
}
],
"metadata": {
"kernelspec": {
"display_name": "aimenv",
"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": "3.12.6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
