aspect-library-v1 0.1.3

A Python library for aspect-based sentiment analysis with translation capabilities

My Aspect Library

Overview

My Aspect Library is a Python package designed for performing aspect-based sentiment analysis with integrated translation capabilities. This library allows you to easily translate text, extract aspects, and analyze sentiment, making it a powerful tool for natural language processing tasks.

Features

• Translation: Automatically translate text in your dataset to the target language before analysis.
• Aspect Extraction: Extract aspect terms from text using state-of-the-art models.
• Sentiment Analysis: Analyze sentiment associated with extracted aspects.
• Data Processing: Clean and process text data for analysis, including stopword removal and text normalization.
• Pivot Table Generation: Create pivot tables to summarize sentiment analysis results.

Installation

To install the package, you can simply clone the repository and use setup.py to install it:

git clone https://github.com/yourusername/my_aspect_library.git
cd my_aspect_library
pip install .

Alternatively, if you want to install it in editable mode:

pip install -e .

Usage

Here’s a quick example of how to use the library:

import pandas as pd
from my_aspect_library import AspectExtractor, translate_aspects, create_pivot_table, concatenate_results

# Load your dataset
df = pd.read_excel('path_to_your_file.xlsx')

# Initialize the aspect extractor
aspect_extractor = AspectExtractor()

# Perform translation and aspect extraction in one step
result_df = aspect_extractor.extract(df, column_name='Customer Comments', target_language='en')

# Translate aspects and sentiments
translated_aspects = translate_aspects(result_df)

# Create pivot table for sentiment analysis
pivot_table = create_pivot_table(translated_aspects)

# Save or further process your results as needed

Dependencies

• pandas
• deep_translator
• unlimited_machine_translator
• pyabsa
• nltk

These dependencies are automatically installed when you install the package.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contributing

If you want to contribute to this project, feel free to fork the repository and submit a pull request.

Acknowledgments

Special thanks to all the contributors and maintainers of the libraries that this project depends on.