Alfiya/PredictiveAnalytics
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
main
PredictiveAnalytics/lab5.ipynb

677 lines
214 KiB
Plaintext
Raw Permalink Normal View History

lab5
2025-01-08 18:47:28 +04:00
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"##### Кластеризация.\n",
"Распределение студентов по типам учебных заведений"
]
},
{
"cell_type": "code",
"execution_count": 6,
"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>Education Level</th>\n",
" <th>Institution Type</th>\n",
" <th>Gender</th>\n",
" <th>Age</th>\n",
" <th>Device</th>\n",
" <th>IT Student</th>\n",
" <th>Location</th>\n",
" <th>Financial Condition</th>\n",
" <th>Internet Type</th>\n",
" <th>Network Type</th>\n",
" <th>Flexibility Level</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>University</td>\n",
" <td>Private</td>\n",
" <td>Male</td>\n",
" <td>23</td>\n",
" <td>Tab</td>\n",
" <td>No</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Wifi</td>\n",
" <td>4G</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>University</td>\n",
" <td>Private</td>\n",
" <td>Female</td>\n",
" <td>23</td>\n",
" <td>Mobile</td>\n",
" <td>No</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Mobile Data</td>\n",
" <td>4G</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>College</td>\n",
" <td>Public</td>\n",
" <td>Female</td>\n",
" <td>18</td>\n",
" <td>Mobile</td>\n",
" <td>No</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Wifi</td>\n",
" <td>4G</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>School</td>\n",
" <td>Private</td>\n",
" <td>Female</td>\n",
" <td>11</td>\n",
" <td>Mobile</td>\n",
" <td>No</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Mobile Data</td>\n",
" <td>4G</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>School</td>\n",
" <td>Private</td>\n",
" <td>Female</td>\n",
" <td>18</td>\n",
" <td>Mobile</td>\n",
" <td>No</td>\n",
" <td>Town</td>\n",
" <td>Poor</td>\n",
" <td>Mobile Data</td>\n",
" <td>3G</td>\n",
" <td>Low</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",
" </tr>\n",
" <tr>\n",
" <th>1200</th>\n",
" <td>College</td>\n",
" <td>Private</td>\n",
" <td>Female</td>\n",
" <td>18</td>\n",
" <td>Mobile</td>\n",
" <td>No</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Wifi</td>\n",
" <td>4G</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1201</th>\n",
" <td>College</td>\n",
" <td>Private</td>\n",
" <td>Female</td>\n",
" <td>18</td>\n",
" <td>Mobile</td>\n",
" <td>No</td>\n",
" <td>Rural</td>\n",
" <td>Mid</td>\n",
" <td>Wifi</td>\n",
" <td>4G</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1202</th>\n",
" <td>School</td>\n",
" <td>Private</td>\n",
" <td>Male</td>\n",
" <td>11</td>\n",
" <td>Mobile</td>\n",
" <td>No</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Mobile Data</td>\n",
" <td>3G</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1203</th>\n",
" <td>College</td>\n",
" <td>Private</td>\n",
" <td>Female</td>\n",
" <td>18</td>\n",
" <td>Mobile</td>\n",
" <td>No</td>\n",
" <td>Rural</td>\n",
" <td>Mid</td>\n",
" <td>Wifi</td>\n",
" <td>4G</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1204</th>\n",
" <td>School</td>\n",
" <td>Private</td>\n",
" <td>Female</td>\n",
" <td>11</td>\n",
" <td>Mobile</td>\n",
" <td>No</td>\n",
" <td>Town</td>\n",
" <td>Poor</td>\n",
" <td>Mobile Data</td>\n",
" <td>3G</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1205 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
" Education Level Institution Type Gender Age Device IT Student \\\n",
"0 University Private Male 23 Tab No \n",
"1 University Private Female 23 Mobile No \n",
"2 College Public Female 18 Mobile No \n",
"3 School Private Female 11 Mobile No \n",
"4 School Private Female 18 Mobile No \n",
"... ... ... ... ... ... ... \n",
"1200 College Private Female 18 Mobile No \n",
"1201 College Private Female 18 Mobile No \n",
"1202 School Private Male 11 Mobile No \n",
"1203 College Private Female 18 Mobile No \n",
"1204 School Private Female 11 Mobile No \n",
"\n",
" Location Financial Condition Internet Type Network Type Flexibility Level \n",
"0 Town Mid Wifi 4G Moderate \n",
"1 Town Mid Mobile Data 4G Moderate \n",
"2 Town Mid Wifi 4G Moderate \n",
"3 Town Mid Mobile Data 4G Moderate \n",
"4 Town Poor Mobile Data 3G Low \n",
"... ... ... ... ... ... \n",
"1200 Town Mid Wifi 4G Low \n",
"1201 Rural Mid Wifi 4G Moderate \n",
"1202 Town Mid Mobile Data 3G Moderate \n",
"1203 Rural Mid Wifi 4G Low \n",
"1204 Town Poor Mobile Data 3G Moderate \n",
"\n",
"[1205 rows x 11 columns]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"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>Education Level</th>\n",
" <th>Institution Type</th>\n",
" <th>Age</th>\n",
" <th>Location</th>\n",
" <th>Financial Condition</th>\n",
" <th>Flexibility Level</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>University</td>\n",
" <td>Private</td>\n",
" <td>23</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>University</td>\n",
" <td>Private</td>\n",
" <td>23</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>College</td>\n",
" <td>Public</td>\n",
" <td>18</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>School</td>\n",
" <td>Private</td>\n",
" <td>11</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>School</td>\n",
" <td>Private</td>\n",
" <td>18</td>\n",
" <td>Town</td>\n",
" <td>Poor</td>\n",
" <td>Low</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",
" </tr>\n",
" <tr>\n",
" <th>1200</th>\n",
" <td>College</td>\n",
" <td>Private</td>\n",
" <td>18</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1201</th>\n",
" <td>College</td>\n",
" <td>Private</td>\n",
" <td>18</td>\n",
" <td>Rural</td>\n",
" <td>Mid</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1202</th>\n",
" <td>School</td>\n",
" <td>Private</td>\n",
" <td>11</td>\n",
" <td>Town</td>\n",
" <td>Mid</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1203</th>\n",
" <td>College</td>\n",
" <td>Private</td>\n",
" <td>18</td>\n",
" <td>Rural</td>\n",
" <td>Mid</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1204</th>\n",
" <td>School</td>\n",
" <td>Private</td>\n",
" <td>11</td>\n",
" <td>Town</td>\n",
" <td>Poor</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1205 rows × 6 columns</p>\n",
"</div>"
],
"text/plain": [
" Education Level Institution Type Age Location Financial Condition \\\n",
"0 University Private 23 Town Mid \n",
"1 University Private 23 Town Mid \n",
"2 College Public 18 Town Mid \n",
"3 School Private 11 Town Mid \n",
"4 School Private 18 Town Poor \n",
"... ... ... ... ... ... \n",
"1200 College Private 18 Town Mid \n",
"1201 College Private 18 Rural Mid \n",
"1202 School Private 11 Town Mid \n",
"1203 College Private 18 Rural Mid \n",
"1204 School Private 11 Town Poor \n",
"\n",
" Flexibility Level \n",
"0 Moderate \n",
"1 Moderate \n",
"2 Moderate \n",
"3 Moderate \n",
"4 Low \n",
"... ... \n",
"1200 Low \n",
"1201 Moderate \n",
"1202 Moderate \n",
"1203 Low \n",
"1204 Moderate \n",
"\n",
"[1205 rows x 6 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Импорт необходимых библиотек\n",
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.cluster import KMeans, AgglomerativeClustering\n",
"from sklearn.decomposition import PCA\n",
"from sklearn.metrics import silhouette_score\n",
"from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
"from sklearn.compose import ColumnTransformer\n",
"\n",
"# Загрузка данных\n",
"df = pd.read_csv(\"data/students_education.csv\")\n",
"df.columns\n",
"display(df)\n",
"df = df.drop(['Gender', 'IT Student', 'Device', 'Internet Type','Network Type'], axis=1)\n",
"\n",
"# Удаление целевой переменной 'Institution Type'\n",
"X = df.drop(['Institution Type'], axis=1)\n",
"\n",
"# Преобразование категориальных переменных\n",
"categorical_features = ['Education Level','Location','Financial Condition','Flexibility Level']\n",
"numerical_features = ['Age']\n",
"display(df)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Создание ColumnTransformer для обработки данных\n",
"preprocessor = ColumnTransformer(\n",
" transformers=[\n",
" ('num', StandardScaler(), numerical_features),\n",
" ('cat', OneHotEncoder(), categorical_features)\n",
" ])\n",
"\n",
"# Преобразование данных\n",
"X_scaled = preprocessor.fit_transform(X)\n",
"\n",
"# Понижение размерности с помощью PCA\n",
"pca = PCA(n_components=2)\n",
"X_pca = pca.fit_transform(X_scaled)\n",
"\n",
"# Визуализация данных после PCA\n",
"plt.figure(figsize=(8, 6))\n",
"plt.scatter(X_pca[:, 0], X_pca[:, 1], alpha=0.5)\n",
"plt.title('Данные после PCA')\n",
"plt.xlabel('PC1')\n",
"plt.ylabel('PC2')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Определение оптимального количества кластеров с помощью метода локтя\n",
"inertia = []\n",
"for k in range(1, 11):\n",
" kmeans = KMeans(n_clusters=k, random_state=42)\n",
" kmeans.fit(X_scaled)\n",
" inertia.append(kmeans.inertia_)\n",
"\n",
"# Визуализация метода локтя\n",
"plt.figure(figsize=(8, 6))\n",
"plt.plot(range(1, 11), inertia, marker='o')\n",
"plt.title('Метод локтя')\n",
"plt.xlabel('Количество кластеров')\n",
"plt.ylabel('Инерция')\n",
"plt.show()"
]
},
{
"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": [
"# Определение оптимального количества кластеров с помощью коэффициента силуэта\n",
"silhouette_scores = []\n",
"for k in range(2, 11): # Коэффициент силуэта не определен для k=1\n",
" kmeans = KMeans(n_clusters=k, random_state=42)\n",
" kmeans.fit(X_scaled)\n",
" score = silhouette_score(X_scaled, kmeans.labels_)\n",
" silhouette_scores.append(score)\n",
"\n",
"# Визуализация коэффициента силуэта\n",
"plt.figure(figsize=(8, 6))\n",
"plt.plot(range(2, 11), silhouette_scores, marker='o')\n",
"plt.title('Коэффициент силуэта')\n",
"plt.xlabel('Количество кластеров')\n",
"plt.ylabel('Коэффициент силуэта')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"# Кластеризация с использованием K-Means\n",
"optimal_k = 3 # Выберите оптимальное количество кластеров на основе графиков\n",
"kmeans = KMeans(n_clusters=optimal_k, random_state=42)\n",
"kmeans_labels = kmeans.fit_predict(X_scaled)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"# Кластеризация с использованием Agglomerative Clustering\n",
"agg_clustering = AgglomerativeClustering(n_clusters=optimal_k)\n",
"agg_labels = agg_clustering.fit_predict(X_scaled)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Text(0, 0.5, 'PC2')"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1600x800 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Визуализация результатов кластеризации\n",
"plt.figure(figsize=(16, 8))\n",
"\n",
"# K-Means\n",
"plt.subplot(1, 2, 1)\n",
"plt.scatter(X_pca[:, 0], X_pca[:, 1], c=kmeans_labels, cmap='viridis', alpha=0.5)\n",
"plt.title('Неиерархическая кластеризация')\n",
"plt.xlabel('PC1')\n",
"plt.ylabel('PC2')"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Agglomerative Clustering\n",
"plt.subplot(1, 2, 2)\n",
"plt.scatter(X_pca[:, 0], X_pca[:, 1], c=agg_labels, cmap='viridis', alpha=0.5)\n",
"plt.title('Иерархическая кластеризация')\n",
"plt.xlabel('PC1')\n",
"plt.ylabel('PC2')\n",
"\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Коэффициент силуэта для K-Means: 0.3456393814525895\n",
"Коэффициент силуэта для Agglomerative Clustering: 0.3584732406902143\n"
]
}
],
"source": [
"# Оценка качества кластеризации\n",
"print(\"Коэффициент силуэта для K-Means:\", silhouette_score(X_scaled, kmeans_labels))\n",
"print(\"Коэффициент силуэта для Agglomerative Clustering:\", silhouette_score(X_scaled, agg_labels))"
]
}
],
"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"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue Copy Permalink