From 5a8253fbd678b5dfb2a3f40c5a8bc866d4cb3ac8 Mon Sep 17 00:00:00 2001
From: Omj69 <144990466+Omj69@users.noreply.github.com>
Date: Thu, 17 Apr 2025 09:58:31 +0530
Subject: [PATCH] Add files via upload
---
Fake_News_Detector_Improved.ipynb | 647 ++++++++++++++++++++++++++++++
1 file changed, 647 insertions(+)
create mode 100644 Fake_News_Detector_Improved.ipynb
diff --git a/Fake_News_Detector_Improved.ipynb b/Fake_News_Detector_Improved.ipynb
new file mode 100644
index 0000000..dbe7c65
--- /dev/null
+++ b/Fake_News_Detector_Improved.ipynb
@@ -0,0 +1,647 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "b6edf3ba",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import re\n",
+ "import pickle\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+ "from sklearn.naive_bayes import MultinomialNB\n",
+ "from sklearn.metrics import accuracy_score, confusion_matrix\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "a8b8f15a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def preprocess(text):\n",
+ " text = text.lower()\n",
+ " text = re.sub(r'\\W', ' ', text)\n",
+ " text = re.sub(r'\\s+', ' ', text)\n",
+ " return text.strip()\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "cb9f81aa",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Load datasets\n",
+ "true = pd.read_csv('data/True.csv')\n",
+ "fake = pd.read_csv('data/Fake.csv')\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "610f29ba",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Add labels\n",
+ "true['label'] = 1\n",
+ "fake['label'] = 0\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "e5bd1bae",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Preprocess\n",
+ "true['text'] = true['text'].apply(preprocess)\n",
+ "fake['text'] = fake['text'].apply(preprocess)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "7013c671",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Balance dataset\n",
+ "min_len = min(len(true), len(fake))\n",
+ "true = true.sample(min_len, random_state=42)\n",
+ "fake = fake.sample(min_len, random_state=42)\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "90325fb1",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Combine and shuffle\n",
+ "df = pd.concat([true, fake])\n",
+ "df = df.sample(frac=1, random_state=42).reset_index(drop=True)\n",
+ "\n",
+ "X = df['text']\n",
+ "y = df['label']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "2565508c",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+ "\n",
+ "# Improved vectorizer settings\n",
+ "vectorizer = TfidfVectorizer(stop_words='english', max_df=0.9, min_df=2, ngram_range=(1,2))\n",
+ "X_train_vec = vectorizer.fit_transform(X_train)\n",
+ "X_test_vec = vectorizer.transform(X_test)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "id": "2fdcccc5",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "MultinomialNB()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.