{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "id": "QwWlQvL5X0n8" }, "outputs": [], "source": [ "import pandas as pd\n", "from sklearn.feature_extraction.text import CountVectorizer\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.naive_bayes import MultinomialNB\n", "from sklearn.metrics import accuracy_score" ] }, { "cell_type": "code", "source": [ "data = {\n", " 'text': [\n", " 'Free money now',\n", " 'Call now to claim your prize',\n", " 'Meet me at the park',\n", " 'Let’s catch up later',\n", " 'Win a new car today!',\n", " 'Lunch plans?',\n", " 'Congratulations! You won a lottery',\n", " 'Can you send me the report?',\n", " 'Exclusive offer for you',\n", " 'Are you coming to the meeting?'\n", " ],\n", " 'label': ['spam', 'spam', 'not spam', 'not spam', 'spam', 'not spam', 'spam', 'not spam', 'spam', 'not spam']\n", "}\n", "\n", "df = pd.DataFrame(data)" ], "metadata": { "id": "LVDUuGd2X5t-" }, "execution_count": 2, "outputs": [] }, { "cell_type": "code", "source": [ "df['label'] = df['label'].map({'spam': 1, 'not spam': 0})" ], "metadata": { "id": "PE4_kidEX5wa" }, "execution_count": 3, "outputs": [] }, { "cell_type": "code", "source": [ "X = df['text']\n", "y = df['label']\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)" ], "metadata": { "id": "NLHC1l-FX5yq" }, "execution_count": 4, "outputs": [] }, { "cell_type": "code", "source": [ "vectorizer = CountVectorizer()\n", "X_train_vectors = vectorizer.fit_transform(X_train)\n", "X_test_vectors = vectorizer.transform(X_test)" ], "metadata": { "id": "mFE0lSH7X51C" }, "execution_count": 5, "outputs": [] }, { "cell_type": "code", "source": [ "model = MultinomialNB()\n", "model.fit(X_train_vectors, y_train)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 80 }, "id": "uY8m6D7JX53a", "outputId": "d66d110b-a228-4a5e-c3ff-eb0bfd1461df" }, "execution_count": 6, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "MultinomialNB()" ], "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.
" ] }, "metadata": {}, "execution_count": 6 } ] }, { "cell_type": "code", "source": [ "y_pred = model.predict(X_test_vectors)\n", "accuracy = accuracy_score(y_test, y_pred)\n", "print(f\"Accuracy: {accuracy * 100:.2f}%\\n\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "_LyoVw9MX55y", "outputId": "2add3aba-a212-4e5b-f4eb-475670aca2b6" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Accuracy: 66.67%\n", "\n" ] } ] }, { "cell_type": "code", "source": [ "custom_message = [\"Congratulations, you've won a free vacation\"]\n", "print(custom_message)\n", "custom_vector = vectorizer.transform(custom_message)\n", "prediction = model.predict(custom_vector)\n", "print(\"Prediction for custom message:\", \"Spam\" if prediction[0] == 1 else \"Not Spam\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "DV6lybRUX576", "outputId": "c14bcf46-0b10-4b2e-967d-dcfd175c7c90" }, "execution_count": 8, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "[\"Congratulations, you've won a free vacation\"]\n", "Prediction for custom message: Spam\n" ] } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "svUF_dojX6Iv" }, "execution_count": null, "outputs": [] } ] }