Code-Example-020-2-Gaussian-Naive-Bayes.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Gaussian Naive Bayes (GaussianNB)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "from scipy.stats import norm\n",
    "from sklearn.datasets import make_blobs\n",
    "\n",
    "from matplotlib import pyplot\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "import matplotlib.cm as cm\n",
    "from random import sample"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import fetch_20newsgroups\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "from sklearn.feature_extraction.text import TfidfTransformer\n",
    "from sklearn.naive_bayes import MultinomialNB\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.85995085995086\n"
     ]
    }
   ],
   "source": [
    "\n",
    "\n",
    "# Load the dataset\n",
    "categories = ['alt.atheism', 'talk.religion.misc', 'comp.graphics', 'sci.space']\n",
    "my_subset_newsgroups = fetch_20newsgroups(subset='train', categories=categories)\n",
    "# newsgroups_test = fetch_20newsgroups(subset='test', categories=categories)\n",
    "\n",
    "# Split the data into training and testing sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(my_subset_newsgroups.data, my_subset_newsgroups.target, test_size=0.2, random_state=42)\n",
    "\n",
    "# Convert the text data into numerical form\n",
    "vectorizer = CountVectorizer()\n",
    "X_train_counts = vectorizer.fit_transform(X_train)\n",
    "X_test_counts = vectorizer.transform(X_test)\n",
    "\n",
    "# Apply TF-IDF transformation\n",
    "transformer = TfidfTransformer()\n",
    "X_train_tfidf = transformer.fit_transform(X_train_counts)\n",
    "X_test_tfidf = transformer.transform(X_test_counts)\n",
    "\n",
    "# Initialize the Naive Bayes classifier\n",
    "clf = MultinomialNB()\n",
    "\n",
    "# Train the model\n",
    "clf.fit(X_train_tfidf, y_train)\n",
    "\n",
    "# Make predictions\n",
    "y_pred = clf.predict(X_test_tfidf)\n",
    "\n",
    "# Calculate the accuracy\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy:\", accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}