немного нерабочее

.gitignore

@@ -179,3 +179,5 @@ cython_debug/
 /lab_2/aimenv
 
 /lab_3/aimenv
+
+lab_8/static

lab_8/lab8.ipynb

@@ -0,0 +1,118 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Загрузка датасета"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Загружено 41 документов.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import win32com.client\n",
+    "\n",
+    "# Путь к папке с распакованными файлами\n",
+    "data_dir = r\"C:/Users/Egor/Desktop/ULSTU\\AI/aim/AIM-PIbd-32-Petrushin-E-A/lab_8/static\"\n",
+    "\n",
+    "# Инициализация Word\n",
+    "word = win32com.client.Dispatch(\"Word.Application\")\n",
+    "word.visible = False\n",
+    "\n",
+    "# Чтение всех .doc файлов\n",
+    "texts = []\n",
+    "for filename in os.listdir(data_dir):\n",
+    "    if filename.endswith(\".doc\"):\n",
+    "        file_path = os.path.join(data_dir, filename)\n",
+    "        try:\n",
+    "            doc = word.Documents.Open(file_path)\n",
+    "            text = doc.Content.Text\n",
+    "            texts.append(text)\n",
+    "            doc.Close()\n",
+    "        except Exception as e:\n",
+    "            print(f\"Ошибка при чтении файла {filename}: {e}\")\n",
+    "\n",
+    "# Закрытие Word\n",
+    "word.Quit()\n",
+    "\n",
+    "# Теперь texts содержит список текстов\n",
+    "print(f\"Загружено {len(texts)} документов.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package stopwords to\n",
+      "[nltk_data]     C:\\Users\\Egor\\AppData\\Roaming\\nltk_data...\n",
+      "[nltk_data]   Unzipping corpora\\stopwords.zip.\n",
+      "[nltk_data] Downloading package wordnet to\n",
+      "[nltk_data]     C:\\Users\\Egor\\AppData\\Roaming\\nltk_data...\n"
+     ]
+    }
+   ],
+   "source": [
+    "import re\n",
+    "from nltk.corpus import stopwords\n",
+    "from nltk.stem import WordNetLemmatizer\n",
+    "import nltk\n",
+    "\n",
+    "# Загрузка стоп-слов и лемматизатора\n",
+    "nltk.download('stopwords')\n",
+    "nltk.download('wordnet')\n",
+    "stop_words = set(stopwords.words('russian'))  # Для русского языка\n",
+    "lemmatizer = WordNetLemmatizer()\n",
+    "\n",
+    "def preprocess_text(text):\n",
+    "    # Удаление спецсимволов\n",
+    "    text = re.sub(r'\\W', ' ', text)\n",
+    "    # Приведение к нижнему регистру\n",
+    "    text = text.lower()\n",
+    "    # Удаление стоп-слов и лемматизация\n",
+    "    tokens = [lemmatizer.lemmatize(word) for word in text.split() if word not in stop_words]\n",
+    "    return ' '.join(tokens)\n",
+    "\n",
+    "# Применение предобработки к каждому документу\n",
+    "texts = [preprocess_text(text) for text in texts]"
+   ]
+  }
+ ],
+ "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
+}