Phoenix 13 - Final Submission

AIML Models/Anti-Plag/Plag_Check.ipynb

@@ -0,0 +1,155 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Intel(R) Extension for Scikit-learn* enabled (https://github.com/intel/scikit-learn-intelex)\n",
+      "[nltk_data] Downloading package stopwords to\n",
+      "[nltk_data]     C:\\Users\\kulsh\\AppData\\Roaming\\nltk_data...\n",
+      "[nltk_data]   Package stopwords is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import string\n",
+    "import nltk\n",
+    "from nltk.corpus import stopwords\n",
+    "import sklearnex\n",
+    "from sklearnex import patch_sklearn\n",
+    "patch_sklearn() \n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "from docx import Document\n",
+    "nltk.download('stopwords')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def preprocess_text(text):\n",
+    "    # Remove punctuation and convert to lowercase\n",
+    "    text = text.translate(str.maketrans(\"\", \"\", string.punctuation)).lower()\n",
+    "    \n",
+    "    # Remove stopwords\n",
+    "    stop_words = set(stopwords.words('english'))\n",
+    "    text = \" \".join(word for word in text.split() if word not in stop_words)\n",
+    "    \n",
+    "    return text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def extract_text_from_docx(file_path):\n",
+    "    doc = Document(file_path)\n",
+    "    paragraphs = [p.text for p in doc.paragraphs]\n",
+    "    return '\\n'.join(paragraphs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "def check_plagiarism(student_assignment_file, reference_assignment_files):\n",
+    "    # Load student assignment\n",
+    "    student_assignment = extract_text_from_docx(student_assignment_file)\n",
+    "    processed_student = preprocess_text(student_assignment)\n",
+    "    \n",
+    "    similarities = []\n",
+    "    \n",
+    "    for ref_file in reference_assignment_files:\n",
+    "        # Load reference assignment\n",
+    "        reference_assignment = extract_text_from_docx('./Assignment/'+ref_file)\n",
+    "        processed_ref = preprocess_text(reference_assignment)\n",
+    "        \n",
+    "        # Create TF-IDF vectors\n",
+    "        vectorizer = TfidfVectorizer()\n",
+    "        vectors = vectorizer.fit_transform([processed_student, processed_ref])\n",
+    "        \n",
+    "        # Calculate cosine similarity\n",
+    "        similarity = cosine_similarity(vectors[0], vectors[1])[0][0]\n",
+    "        similarities.append(similarity)\n",
+    "    \n",
+    "    return similarities"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "student_assignment_file = \"./Assignment/temp/Sujal.docx\"\n",
+    "reference_assignment_files = [doc for doc in os.listdir('./Assignment/') if doc.endswith('.doc') or doc.endswith('.docx')]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Similarity with reference assignment 1: 0.1433594398627273\n",
+      "Similarity with reference assignment 2: 0.6140647534863115\n"
+     ]
+    }
+   ],
+   "source": [
+    "similarities = check_plagiarism(student_assignment_file, reference_assignment_files)\n",
+    "for i, similarity in enumerate(similarities):\n",
+    "    print(f\"Similarity with reference assignment {i+1}: {similarity}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "tf",
+   "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": "3.9.16"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}