|
--- |
|
title: Advanced Sentiment Classifier |
|
emoji: 🏃 |
|
colorFrom: green |
|
colorTo: green |
|
sdk: gradio |
|
sdk_version: 4.36.1 |
|
app_file: app.py |
|
pinned: false |
|
license: apache-2.0 |
|
--- |
|
|
|
# Sentiment Analyzer |
|
|
|
This project provides a web-based tool to analyze the sentiment of reviews using a pre-trained model from Hugging Face's `transformers` library. Users can upload a text file containing reviews, and the tool will display a DataFrame with the sentiment analysis results and a pie chart visualizing the sentiment distribution. |
|
|
|
## Features |
|
|
|
- **Sentiment Analysis**: Uses a pre-trained model to classify the sentiment of each review as positive or negative. |
|
- **File Upload**: Allows users to upload a text file containing reviews. |
|
- **DataFrame Display**: Shows a DataFrame with the original reviews, sentiment labels, and confidence scores. |
|
- **Pie Chart Visualization**: Displays a pie chart showing the percentage of positive and negative reviews. |
|
|
|
## Requirements |
|
|
|
- Python 3.6 or higher |
|
- `transformers` library |
|
- `pandas` library |
|
- `matplotlib` library |
|
- `gradio` library |
|
|
|
## Installation |
|
|
|
1. Clone the repository: |
|
```bash |
|
git clone https://github.com/your-username/sentiment-analyzer.git |
|
cd sentiment-analyzer |
|
``` |
|
|
|
2. Install the required libraries: |
|
```bash |
|
pip install transformers pandas matplotlib gradio |
|
``` |
|
|
|
## Usage |
|
|
|
1. Save your reviews in a text file named `reviews.txt`, with each review on a new line. |
|
|
|
2. Run the script: |
|
```bash |
|
python app.py |
|
``` |
|
|
|
3. Open your web browser and go to the local server URL provided by Gradio (usually `http://127.0.0.1:7860`). |
|
|
|
4. Upload the `reviews.txt` file. |
|
|
|
5. The tool will display a DataFrame with the sentiment analysis results and a pie chart visualizing the sentiment distribution. |
|
|
|
## Code Explanation |
|
|
|
- **read_reviews_to_dataframe**: Reads reviews from a text file and converts them into a pandas DataFrame. |
|
- **analyzer**: Applies sentiment analysis to a given text and returns the label and score. |
|
- **evaluate_reviews**: Adds sentiment evaluation to each review in the DataFrame and splits it into 'Sentiment' and 'Score' columns. |
|
- **create_pie_chart**: Creates and saves a pie chart showing the distribution of sentiments. |
|
- **process_reviews**: Processes the uploaded file, evaluates reviews, and generates the pie chart. |
|
- **gradio_interface**: Function for Gradio interface that processes the file and returns the DataFrame and chart path. |
|
|
|
## Example |
|
|
|
1. Prepare a text file `reviews.txt` with the following content: |
|
``` |
|
The product quality is excellent! |
|
The battery life is awful. |
|
Very satisfied with the purchase. |
|
Will not buy again, very disappointed. |
|
``` |
|
|
|
2. Run the script: |
|
```bash |
|
python app.py |
|
``` |
|
|
|
3. Upload `reviews.txt` via the Gradio interface. |
|
|
|
4. View the DataFrame and pie chart displaying the sentiment analysis results. |
|
|
|
## License |
|
|
|
This project is licensed under the MIT License. |
|
|
|
## Author |
|
|
|
This tool was created by **Walid Ahmed**. |
|
|
