{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import re\n",
    "import string\n",
    "import nltk\n",
    "from nltk.corpus import stopwords\n",
    "from sklearn.decomposition import LatentDirichletAllocation\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.cluster import KMeans\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import joblib\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package stopwords to C:\\Users\\Regino Balogo\n",
      "[nltk_data]     Jr\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Unzipping corpora\\stopwords.zip.\n"
     ]
    }
   ],
   "source": [
    "# Download NLTK stopwords\n",
    "nltk.download('stopwords')\n",
    "stop_words = set(stopwords.words('english'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load dataset\n",
    "fake_df = pd.read_csv(\"Fake.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Initial Data:\n",
      "                                               title  \\\n",
      "0   Donald Trump Sends Out Embarrassing New Year’...   \n",
      "1   Drunk Bragging Trump Staffer Started Russian ...   \n",
      "2   Sheriff David Clarke Becomes An Internet Joke...   \n",
      "3   Trump Is So Obsessed He Even Has Obama’s Name...   \n",
      "4   Pope Francis Just Called Out Donald Trump Dur...   \n",
      "\n",
      "                                                text  \n",
      "0  Donald Trump just couldn t wish all Americans ...  \n",
      "1  House Intelligence Committee Chairman Devin Nu...  \n",
      "2  On Friday, it was revealed that former Milwauk...  \n",
      "3  On Christmas day, Donald Trump announced that ...  \n",
      "4  Pope Francis used his annual Christmas Day mes...  \n"
     ]
    }
   ],
   "source": [
    "print(\"Initial Data:\")\n",
    "print(fake_df.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Data after dropping missing values:\n",
      "                                               title  \\\n",
      "0   Donald Trump Sends Out Embarrassing New Year’...   \n",
      "1   Drunk Bragging Trump Staffer Started Russian ...   \n",
      "2   Sheriff David Clarke Becomes An Internet Joke...   \n",
      "3   Trump Is So Obsessed He Even Has Obama’s Name...   \n",
      "4   Pope Francis Just Called Out Donald Trump Dur...   \n",
      "\n",
      "                                                text  \n",
      "0  Donald Trump just couldn t wish all Americans ...  \n",
      "1  House Intelligence Committee Chairman Devin Nu...  \n",
      "2  On Friday, it was revealed that former Milwauk...  \n",
      "3  On Christmas day, Donald Trump announced that ...  \n",
      "4  Pope Francis used his annual Christmas Day mes...  \n"
     ]
    }
   ],
   "source": [
    "# Keep only relevant columns\n",
    "fake_df = fake_df[['title', 'text']].dropna()\n",
    "print(\"Data after dropping missing values:\")\n",
    "print(fake_df.head())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Combine title and text\n",
    "fake_df['content'] = fake_df['title'] + \" \" + fake_df['text']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Function to clean text\n",
    "def clean_text(text):\n",
    "    text = text.lower()\n",
    "    text = re.sub(f\"[{string.punctuation}]\", \"\", text)\n",
    "    text = re.sub(r\"\\d+\", \"\", text)\n",
    "    text = \" \".join([word for word in text.split() if word not in stop_words])\n",
    "    return text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Data after text cleaning:\n",
      "                                             content  \\\n",
      "0   Donald Trump Sends Out Embarrassing New Year’...   \n",
      "1   Drunk Bragging Trump Staffer Started Russian ...   \n",
      "2   Sheriff David Clarke Becomes An Internet Joke...   \n",
      "3   Trump Is So Obsessed He Even Has Obama’s Name...   \n",
      "4   Pope Francis Just Called Out Donald Trump Dur...   \n",
      "\n",
      "                                          clean_text  \n",
      "0  donald trump sends embarrassing new year’s eve...  \n",
      "1  drunk bragging trump staffer started russian c...  \n",
      "2  sheriff david clarke becomes internet joke thr...  \n",
      "3  trump obsessed even obama’s name coded website...  \n",
      "4  pope francis called donald trump christmas spe...  \n"
     ]
    }
   ],
   "source": [
    "# Apply text cleaning\n",
    "fake_df['clean_text'] = fake_df['content'].apply(clean_text)\n",
    "print(\"Data after text cleaning:\")\n",
    "print(fake_df[['content', 'clean_text']].head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert text to TF-IDF vectors\n",
    "vectorizer = TfidfVectorizer(max_features=5000)\n",
    "X = vectorizer.fit_transform(fake_df['clean_text'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cluster assignments:\n",
      "                                               title  cluster\n",
      "0   Donald Trump Sends Out Embarrassing New Year’...        2\n",
      "1   Drunk Bragging Trump Staffer Started Russian ...        2\n",
      "2   Sheriff David Clarke Becomes An Internet Joke...        1\n",
      "3   Trump Is So Obsessed He Even Has Obama’s Name...        2\n",
      "4   Pope Francis Just Called Out Donald Trump Dur...        1\n"
     ]
    }
   ],
   "source": [
    "# Apply K-Means clustering\n",
    "num_clusters = 3  # Try clustering articles into 3 groups\n",
    "kmeans = KMeans(n_clusters=num_clusters, random_state=42)\n",
    "fake_df['cluster'] = kmeans.fit_predict(X)\n",
    "print(\"Cluster assignments:\")\n",
    "print(fake_df[['title', 'cluster']].head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualizing the clusters\n",
    "sns.countplot(x=fake_df['cluster'])\n",
    "plt.title(\"Fake News Clustering\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Apply LDA for topic modeling\n",
    "num_topics = 5\n",
    "lda = LatentDirichletAllocation(n_components=num_topics, random_state=42)\n",
    "topic_matrix = lda.fit_transform(X)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Topic 0: republican said vote state president people republicans would obama trump\n",
      "Topic 1: students us school gun people video muslim said black police\n",
      "Topic 2: one said like people clinton president video donald hillary trump\n",
      "Topic 3: judge maxine jeanine nancy bundy flint waters video moore pelosi\n",
      "Topic 4: investigation intelligence comey us hillary russian fbi russia clinton trump\n"
     ]
    }
   ],
   "source": [
    "# Show top words for each topic\n",
    "words = np.array(vectorizer.get_feature_names_out())\n",
    "top_words = []\n",
    "for topic_idx, topic in enumerate(lda.components_):\n",
    "    top_words.append(\" \".join(words[np.argsort(topic)][-10:]))\n",
    "    print(f\"Topic {topic_idx}: {top_words[-1]}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['tfidf_vectorizer.pkl']"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Save model and vectorizer\n",
    "joblib.dump(kmeans, \"kmeans_fake_news.pkl\")\n",
    "joblib.dump(lda, \"lda_fake_news.pkl\")\n",
    "joblib.dump(vectorizer, \"tfidf_vectorizer.pkl\")\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}