| """
|
| Quick Start Demo Mode for IDP System
|
| Works without trained models using rule-based extraction
|
| Allows immediate testing while models train
|
| """
|
|
|
| import re
|
| from typing import Dict, List
|
| import numpy as np
|
|
|
|
|
| class DemoClassifier:
|
| """Simple rule-based classifier for demo"""
|
|
|
| def predict(self, text: str) -> Dict:
|
| text_lower = text.lower()
|
|
|
|
|
| if 'invoice' in text_lower:
|
| return {
|
| 'predicted_class': 'INVOICE',
|
| 'confidence': 0.85,
|
| 'probabilities': {'INVOICE': 0.85, 'RECEIPT': 0.10, 'FORM': 0.03, 'OTHER': 0.02}
|
| }
|
| elif any(k in text_lower for k in ['bank statement', 'account statement', 'statement of account']):
|
| return {
|
| 'predicted_class': 'BANK_STATEMENT',
|
| 'confidence': 0.90,
|
| 'probabilities': {'INVOICE': 0.05, 'RECEIPT': 0.05, 'FORM': 0.05, 'BANK_STATEMENT': 0.85}
|
| }
|
| elif 'receipt' in text_lower:
|
| return {
|
| 'predicted_class': 'RECEIPT',
|
| 'confidence': 0.80,
|
| 'probabilities': {'INVOICE': 0.15, 'RECEIPT': 0.80, 'FORM': 0.03, 'OTHER': 0.02}
|
| }
|
| elif 'form' in text_lower or 'application' in text_lower:
|
| return {
|
| 'predicted_class': 'FORM',
|
| 'confidence': 0.75,
|
| 'probabilities': {'INVOICE': 0.05, 'RECEIPT': 0.10, 'FORM': 0.75, 'OTHER': 0.10}
|
| }
|
| else:
|
|
|
| if 'total' in text_lower and '$' in text_lower:
|
| return {
|
| 'predicted_class': 'RECEIPT',
|
| 'confidence': 0.60,
|
| 'probabilities': {'INVOICE': 0.20, 'RECEIPT': 0.60, 'FORM': 0.10, 'OTHER': 0.10}
|
| }
|
|
|
| return {
|
| 'predicted_class': 'OTHER',
|
| 'confidence': 0.70,
|
| 'probabilities': {'INVOICE': 0.10, 'RECEIPT': 0.10, 'FORM': 0.10, 'OTHER': 0.70}
|
| }
|
|
|
|
|
| class DemoNER:
|
| """Simple rule-based NER for demo"""
|
|
|
| def __init__(self):
|
| self.patterns = {
|
| 'INVOICE_NUMBER': [
|
| r'INV[-\s]?\d+',
|
| r'Invoice\s*#?\s*:?\s*([A-Z0-9\-]+)',
|
| r'\b\d{6,}\b',
|
| ],
|
| 'DATE': [
|
| r'\d{1,2}[/-]\d{1,2}[/-]\d{2,4}',
|
| r'\d{4}[/-]\d{1,2}[/-]\d{1,2}',
|
| ],
|
| 'TOTAL_AMOUNT': [
|
| r'Total\s*:?\s*[₹$€£]\s*[\d,]+\.?\d*',
|
| r'[₹$€£]\s*[\d,]+\.?\d*',
|
| ],
|
| 'TAX_AMOUNT': [
|
| r'Tax\s*:?\s*[₹$€£]\s*[\d,]+\.?\d*',
|
| r'GST\s*:?\s*[₹$€£]\s*[\d,]+\.?\d*',
|
| ],
|
| }
|
|
|
| def predict(self, text: str) -> Dict:
|
| entities = []
|
|
|
| for entity_type, patterns in self.patterns.items():
|
| for pattern in patterns:
|
| matches = re.finditer(pattern, text, re.IGNORECASE)
|
| for match in matches:
|
| entities.append({
|
| 'entity': entity_type,
|
| 'text': match.group(0).strip(),
|
| 'confidence': 0.75,
|
| 'start': match.start(),
|
| 'end': match.end()
|
| })
|
|
|
| return {'entities': entities, 'text': text}
|
|
|
|
|
| def create_demo_models_directory():
|
| """Create models directory with demo flag"""
|
| import os
|
|
|
| os.makedirs('models/classifier', exist_ok=True)
|
| os.makedirs('models/ner', exist_ok=True)
|
|
|
|
|
| with open('models/DEMO_MODE.txt', 'w') as f:
|
| f.write('Using demo mode - rule-based extraction\n')
|
| f.write('Train models with: python train_classifier.py && python train_ner.py\n')
|
|
|
| print("✓ Demo mode initialized")
|
| print(" Using rule-based extraction until models are trained")
|
|
|
|
|
| if __name__ == "__main__":
|
| create_demo_models_directory()
|
|
|
|
|
| demo_text = """
|
| INVOICE #INV-12345
|
| Date: 28/11/2025
|
| Total: $1,250.00
|
| Tax: $125.00
|
| """
|
|
|
| classifier = DemoClassifier()
|
| ner = DemoNER()
|
|
|
| print("\nDemo Classifier:")
|
| print(classifier.predict(demo_text))
|
|
|
| print("\nDemo NER:")
|
| print(ner.predict(demo_text))
|
|
|
