lab_8/lab8.ipynb

@@ -0,0 +1,55 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Лабораторная работа 8 ##"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from docx import Document\n",
+    "import os\n",
+    "\n",
+    "def read_docx(file_path):\n",
+    "    doc = Document(file_path)\n",
+    "    full_text = []\n",
+    "    for paragraph in doc.paragraphs:\n",
+    "        full_text.append(paragraph.text)\n",
+    "    return \"\\n\".join(full_text)\n",
+    "\n",
+    "def load_docs(dataset_path):\n",
+    "    df = pd.DataFrame(columns=[\"doc\", \"text\"])\n",
+    "    for file_path in os.listdir(dataset_path):\n",
+    "        if file_path.startswith(\"~$\"):\n",
+    "            continue\n",
+    "        text = read_docx(dataset_path + file_path)\n",
+    "        df.loc[len(df.index)] = [file_path, text]\n",
+    "    return df\n",
+    "\n",
+    "# Загрузка данных\n",
+    "df = load_docs(\"data/text/\")\n",
+    "df[\"type\"] = df.apply(\n",
+    "    lambda row: 0 if str(row[\"doc\"]).startswith(\"tz_\") else 1, axis=1\n",
+    ")\n",
+    "df.info()\n",
+    "df.sort_values(by=[\"doc\"], inplace=True)\n",
+    "\n",
+    "display(df.head(), df.tail())"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}