PROJECT_INFO.md requirements.txt QUICKSTART.md handlers.py semantic_understanding.py

PROJECT_INFO.md

# NLP Text Analysis Bot - Project Information

**Developer: RSK World**
**Website: https://rskworld.in**
**Email: help@rskworld.in**
**Phone: +91 93305 39277**
**Year: 2026**

## Project Details

- **ID**: 4
- **Title**: NLP Text Analysis Bot
- **Category**: NLP Chatbots
- **Difficulty**: Intermediate
- **Description**: Chatbot with natural language processing capabilities for text understanding and analysis.
- **Full Description**: This chatbot project uses advanced NLP techniques for text analysis, sentiment detection, and language understanding. Features include text preprocessing, entity recognition, and semantic analysis.

## Technologies Used

- NLTK
- spaCy
- Python
- NLP
- Transformers

## Features

1. Text preprocessing
2. Sentiment analysis
3. Entity recognition
4. Semantic understanding
5. NLP pipeline

## Project Structure

```
nlp-text-analysis-bot/
├── app.py # Flask web application
├── nlp_pipeline.py # Main NLP pipeline orchestrator
├── text_preprocessing.py # Text cleaning and preprocessing
├── sentiment_analysis.py # Sentiment analysis module
├── entity_recognition.py # Named entity recognition
├── semantic_understanding.py # Semantic analysis module
├── config.py # Configuration settings
├── test_analysis.py # Test script
├── example_usage.py # Usage examples
├── templates/
│ └── index.html # Web interface
├── static/
│ ├── css/
│ │ └── style.css # Custom styles
│ └── js/
│ └── main.js # JavaScript functions
├── requirements.txt # Python dependencies
├── setup.py # Package setup
├── install.sh # Installation script (Linux/Mac)
├── install.bat # Installation script (Windows)
├── README.md # Project documentation
├── LICENSE # License file
└── .gitignore # Git ignore rules
```

## Quick Start

1. Install dependencies: `pip install -r requirements.txt`
2. Download spaCy model: `python -m spacy download en_core_web_sm`
3. Run application: `python app.py`
4. Open browser: `http://localhost:5000`

## API Endpoints

- `GET /` - Web interface
- `POST /api/analyze` - Text analysis endpoint
- `GET /api/health` - Health check

## Contact

For support and inquiries:
- **Website**: https://rskworld.in
- **Email**: help@rskworld.in
- **Phone**: +91 93305 39277

---

**Developed by RSK World - 2026**

requirements.txt

Raw Download

# NLP Text Analysis Bot - Requirements
# Developer: RSK World
# Website: https://rskworld.in
# Email: help@rskworld.in
# Phone: +91 93305 39277
# Year: 2026

Flask==3.0.0
nltk==3.8.1
spacy==3.7.2
transformers==4.35.2
torch==2.1.0
numpy==1.24.3
requests==2.31.0
langdetect==1.0.9
textstat==0.7.3
scikit-learn==1.3.2

19 lines•334 B

text

QUICKSTART.md

Raw Download

QUICKSTART.md

# Quick Start Guide - NLP Text Analysis Bot

**Developer: RSK World**
**Website: https://rskworld.in**
**Email: help@rskworld.in**
**Phone: +91 93305 39277**
**Year: 2026**

## Installation Steps

### 1. Install Python Dependencies
```bash
pip install -r requirements.txt
```

### 2. Download spaCy English Model
```bash
python -m spacy download en_core_web_sm
```

### 3. Download NLTK Data (Automatic)
The project will automatically download required NLTK data on first run, or you can download manually:
```python
import nltk
nltk.download('punkt')
nltk.download('stopwords')
nltk.download('wordnet')
nltk.download('vader_lexicon')
nltk.download('averaged_perceptron_tagger')
```

### 4. Validate Installation
```bash
python validate_project.py
```

### 5. Run the Application
```bash
python app.py
```

### 6. Access the Web Interface
Open your browser and navigate to:
```
http://localhost:5000
```

## Using the API

### Analyze Text
```bash
curl -X POST http://localhost:5000/api/analyze \
-H "Content-Type: application/json" \
-d '{"text": "Your text to analyze here"}'
```

### Calculate Text Similarity
```bash
curl -X POST http://localhost:5000/api/similarity \
-H "Content-Type: application/json" \
-d '{"text1": "First text", "text2": "Second text"}'
```

### Health Check
```bash
curl http://localhost:5000/api/health
```

## Troubleshooting

### Issue: Module not found
**Solution**: Run `pip install -r requirements.txt`

### Issue: spaCy model not found
**Solution**: Run `python -m spacy download en_core_web_sm`

### Issue: NLTK data missing
**Solution**: The project will download automatically, or run the NLTK download commands above

### Issue: Port already in use
**Solution**: Change the port in `app.py` (line 79) from `5000` to another port

## Testing

### Run Test Script
```bash
python test_analysis.py
```

### Run Example Usage
```bash
python example_usage.py
```

## Project Structure

```
nlp-text-analysis-bot/
├── app.py # Flask application
├── nlp_pipeline.py # Main pipeline
├── text_preprocessing.py # Text cleaning
├── sentiment_analysis.py # Sentiment analysis
├── entity_recognition.py # NER
├── semantic_understanding.py # Semantic analysis
├── text_summarization.py # Summarization
├── language_detection.py # Language detection
├── text_classification.py # Classification
├── readability_analysis.py # Readability
├── emotion_detection.py # Emotion detection
├── advanced_keywords.py # TF-IDF keywords
├── pos_tagging.py # POS tagging
├── text_similarity.py # Similarity calculation
├── templates/
│ └── index.html # Web interface
├── static/
│ ├── css/
│ └── js/
└── requirements.txt # Dependencies
```

## Support

For issues or questions:
- **Website**: https://rskworld.in
- **Email**: help@rskworld.in
- **Phone**: +91 93305 39277

---

**Developed by RSK World - 2026**

semantic_understanding.py

Raw Download

"""
Semantic Understanding Module
Provides semantic analysis and topic extraction

Developer: RSK World
Website: https://rskworld.in
Email: help@rskworld.in
Phone: +91 93305 39277
Year: 2026
"""

import spacy
from collections import Counter
from text_preprocessing import TextPreprocessor

class SemanticAnalyzer:
    """
    Semantic analysis class for understanding text meaning
    Developer: RSK World - https://rskworld.in
    """
    
    def __init__(self):
        """Initialize semantic analyzer"""
        try:
            self.nlp = spacy.load("en_core_web_sm")
        except OSError:
            print("Warning: spaCy English model not found.")
            print("Please install it using: python -m spacy download en_core_web_sm")
            self.nlp = None
        
        self.preprocessor = TextPreprocessor()
    
    def extract_keywords(self, text, top_n=10):
        """
        Extract keywords from text
        
        Args:
            text (str): Input text
            top_n (int): Number of top keywords to return
            
        Returns:
            list: List of top keywords
        """
        if self.nlp is None:
            # Fallback to simple frequency-based extraction
            preprocessed = self.preprocessor.preprocess(text)
            word_freq = Counter(preprocessed['filtered_tokens'])
            return [word for word, count in word_freq.most_common(top_n)]
        
        doc = self.nlp(text)
        
        # Extract keywords (nouns and important adjectives)
        keywords = []
        for token in doc:
            if (token.pos_ in ['NOUN', 'PROPN', 'ADJ'] and 
                not token.is_stop and 
                not token.is_punct and
                len(token.text) > 2):
                keywords.append(token.lemma_.lower())
        
        # Count frequency
        keyword_freq = Counter(keywords)
        return [word for word, count in keyword_freq.most_common(top_n)]
    
    def extract_topics(self, text, top_n=5):
        """
        Extract main topics from text
        
        Args:
            text (str): Input text
            top_n (int): Number of topics to return
            
        Returns:
            list: List of main topics
        """
        keywords = self.extract_keywords(text, top_n * 2)
        return keywords[:top_n]
    
    def analyze_semantic_similarity(self, text1, text2):
        """
        Calculate semantic similarity between two texts
        
        Args:
            text1 (str): First text
            text2 (str): Second text
            
        Returns:
            float: Similarity score (0-1)
        """
        if self.nlp is None:
            return 0.0
        
        doc1 = self.nlp(text1)
        doc2 = self.nlp(text2)
        
        return doc1.similarity(doc2)
    
    def extract_phrases(self, text):
        """
        Extract important phrases and noun chunks
        
        Args:
            text (str): Input text
            
        Returns:
            list: List of important phrases
        """
        if self.nlp is None:
            return []
        
        doc = self.nlp(text)
        phrases = []
        
        # Extract noun chunks
        for chunk in doc.noun_chunks:
            if len(chunk.text.split()) > 1:  # Multi-word phrases
                phrases.append(chunk.text)
        
        return phrases[:10]  # Return top 10 phrases
    
    def analyze(self, text):
        """
        Complete semantic analysis
        
        Args:
            text (str): Input text
            
        Returns:
            dict: Semantic analysis results
        """
        keywords = self.extract_keywords(text)
        topics = self.extract_topics(text)
        phrases = self.extract_phrases(text)
        
        result = {
            'keywords': keywords,
            'topics': topics,
            'phrases': phrases,
            'key_concepts': topics[:3]  # Top 3 concepts
        }
        
        return result

144 lines•4 KB

python

Theme Settings

Color Scheme

Display Options

Font Size

PROJECT_INFO.md

QUICKSTART.md

Theme Settings

Color Scheme

Display Options

Font Size

PROJECT_INFO.md

QUICKSTART.md

🚀 Support RSK World