{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "markdown", "source": [ "Assignment 3: Write a program to recognize a document is positive or negative based on polarity\n", "words using suitable classification method." ], "metadata": { "id": "93rFRa0BNhai" } }, { "cell_type": "code", "source": [ "import nltk\n", "\n", "# Check if punkt is installed\n", "try:\n", " nltk.data.find('tokenizers/punkt')\n", " print(\"Punkt tokenizer is already installed!\")\n", "except LookupError:\n", " print(\"Punkt tokenizer is missing. Downloading it now.\")\n", " nltk.download('punkt')\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "__ArjvaFOFg2", "outputId": "6c7b8a42-f772-4589-f58d-31840760e1a1" }, "execution_count": 22, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Punkt tokenizer is already installed!\n" ] } ] }, { "cell_type": "code", "source": [ "import nltk\n", "\n", "# Set the NLTK data path to a specific folder\n", "nltk.data.path.append(\"/root/nltk_data\")\n", "\n", "# Try downloading punkt again\n", "nltk.download('punkt')\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "1dC12VgJOG_t", "outputId": "ec1d2995-b089-40d3-df9e-5041dd6b308c" }, "execution_count": 23, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "[nltk_data] Downloading package punkt to /root/nltk_data...\n", "[nltk_data] Package punkt is already up-to-date!\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "True" ] }, "metadata": {}, "execution_count": 23 } ] }, { "cell_type": "code", "source": [ "!pip install nltk\n", "import nltk\n", "\n", "# Download 'punkt' and 'punkt_tab' datasets\n", "nltk.download('punkt')\n", "nltk.download('punkt_tab')\n", "\n", "\n", "# ... (rest of the code remains the same)\n", "\n", "import pandas as pd\n", "import nltk\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 classification_report, accuracy_score\n", "\n", "# Sample dataset with polarity words (positive/negative sentences)\n", "data = {\n", " 'text': [\n", " \"I love this product, it's amazing!\",\n", " \"I hate this product, it's terrible.\",\n", " \"The movie was awesome, I enjoyed it!\",\n", " \"It was the worst movie I've ever seen.\",\n", " \"Such a great experience, I'm so happy!\",\n", " \"I will never buy from this store again, very disappointed.\",\n", " \"Fantastic service, I am really pleased.\",\n", " \"Horrible, worst service ever.\",\n", " \"I am thrilled with the results, totally recommend!\",\n", " \"It was an awful experience, very frustrating.\"\n", " ],\n", " 'label': [\n", " 'positive', 'negative', 'positive', 'negative', 'positive',\n", " 'negative', 'positive', 'negative', 'positive', 'negative'\n", " ]\n", "}\n", "\n", "# Create DataFrame\n", "df = pd.DataFrame(data)\n", "\n", "# Step 1: Define polarity words (positive and negative)\n", "positive_words = ['love', 'awesome', 'great', 'happy', 'enjoyed', 'fantastic', 'pleased', 'thrilled', 'recommend']\n", "negative_words = ['hate', 'terrible', 'worst', 'never', 'disappointed', 'horrible', 'awful', 'frustrating']\n", "\n", "# Step 2: Function to calculate polarity score for each document\n", "def polarity_score(text):\n", " words = nltk.word_tokenize(text.lower()) # Tokenize the text\n", " positive_count = sum(1 for word in words if word in positive_words)\n", " negative_count = sum(1 for word in words if word in negative_words)\n", "\n", " # Classify based on word counts\n", " if positive_count > negative_count:\n", " return 'positive'\n", " elif negative_count > positive_count:\n", " return 'negative'\n", " else:\n", " return 'neutral'\n", "\n", "# Step 3: Apply polarity_score function to the dataset\n", "df['predicted_label'] = df['text'].apply(polarity_score)\n", "\n", "# Step 4: Train a classification model (Naive Bayes for simplicity)\n", "X = df['text']\n", "y = df['label']\n", "\n", "# Vectorize the text data\n", "vectorizer = CountVectorizer(stop_words='english')\n", "X_vec = vectorizer.fit_transform(X)\n", "\n", "# Train-test split\n", "X_train, X_test, y_train, y_test = train_test_split(X_vec, y, test_size=0.3, random_state=42)\n", "\n", "# Train Naive Bayes classifier\n", "classifier = MultinomialNB()\n", "classifier.fit(X_train, y_train)\n", "\n", "# Step 5: Predict on the test set\n", "y_pred = classifier.predict(X_test)\n", "\n", "# Step 6: Evaluate the classifier\n", "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n", "print(\"Classification Report:\")\n", "print(classification_report(y_test, y_pred))\n", "\n", "# Example of classifying a new document\n", "new_document = \"I absolutely love this new phone, it's perfect!\"\n", "new_document_vec = vectorizer.transform([new_document])\n", "prediction = classifier.predict(new_document_vec)\n", "print(f\"The sentiment of the document is: {prediction[0]}\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "OKeImZ4dNitU", "outputId": "37e7aa1b-0cad-4f28-fffa-7385a3d9d22c" }, "execution_count": 27, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Requirement already satisfied: nltk in /usr/local/lib/python3.11/dist-packages (3.9.1)\n", "Requirement already satisfied: click in /usr/local/lib/python3.11/dist-packages (from nltk) (8.1.8)\n", "Requirement already satisfied: joblib in /usr/local/lib/python3.11/dist-packages (from nltk) (1.4.2)\n", "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.11/dist-packages (from nltk) (2024.11.6)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from nltk) (4.67.1)\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "[nltk_data] Downloading package punkt to /root/nltk_data...\n", "[nltk_data] Package punkt is already up-to-date!\n", "[nltk_data] Downloading package punkt_tab to /root/nltk_data...\n", "[nltk_data] Unzipping tokenizers/punkt_tab.zip.\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "Accuracy: 0.0\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " negative 0.00 0.00 0.00 2.0\n", " positive 0.00 0.00 0.00 1.0\n", "\n", " accuracy 0.00 3.0\n", " macro avg 0.00 0.00 0.00 3.0\n", "weighted avg 0.00 0.00 0.00 3.0\n", "\n", "The sentiment of the document is: positive\n" ] } ] } ] }