"""
================================================================================
Text Classification Dataset - Scripts Package
================================================================================
Project: Text Classification Dataset
Category: Text Data / NLP

Author: Molla Samser
Designer & Tester: Rima Khatun
Website: https://rskworld.in
Email: help@rskworld.in | support@rskworld.in
Phone: +91 93305 39277

Copyright (c) 2026 RSK World - All Rights Reserved
================================================================================

This package contains various scripts for text classification:

Modules:
--------
- preprocessing: Text preprocessing utilities
- train_classifier: Traditional ML model training
- train_transformers: Transformer-based model training (BERT)
- data_augmentation: Text data augmentation techniques
- visualizations: Data visualization utilities
- api_server: Flask REST API server
- model_explainability: LIME-based model explanations
- batch_processor: Batch prediction and evaluation
- hyperparameter_tuning: GridSearch and Optuna tuning
- deep_learning: PyTorch deep learning models
- data_quality: Data quality analysis
- active_learning: Active learning module

Usage:
------
from scripts.preprocessing import preprocess_text
from scripts.data_quality import DataQualityAnalyzer
from scripts.active_learning import ActiveLearner

================================================================================
"""

__version__ = "1.0.0"
__author__ = "Molla Samser"
__email__ = "help@rskworld.in"
__website__ = "https://rskworld.in"
__copyright__ = "Copyright (c) 2026 RSK World - All Rights Reserved"

# Module imports for easier access
from .preprocessing import TextPreprocessor, load_and_preprocess

# Create a simple preprocess function for convenience
def preprocess_text(text: str) -> str:
    """
    Simple text preprocessing function.
    
    Args:
        text: Input text to preprocess
        
    Returns:
        Preprocessed text
    """
    preprocessor = TextPreprocessor()
    return preprocessor.preprocess(text)

__all__ = [
    'preprocess_text',
    'TextPreprocessor',
    'load_and_preprocess',
    '__version__',
    '__author__',
    '__email__',
    '__website__',
]