📈 Indian Stock Market Analyzer

AI-powered real-time stock analysis for NSE/BSE markets with ML predictions, technical indicators, and sentiment analysis.

---

✨ Features

• 📊 Real-Time Dashboard — Live stock prices, charts, and market indices (NIFTY 50, SENSEX, Bank NIFTY)
• 🤖 ML Predictions — Ensemble predictions using LSTM, XGBoost, and Prophet models
• 📉 Technical Indicators — 25+ indicators including RSI, MACD, Bollinger Bands, ADX, OBV
• 📰 News & Sentiment — Aggregated news from Economic Times, MoneyControl, Business Standard with NLP sentiment scoring
• 🎯 Trading Signals — AI-generated BUY/SELL/HOLD signals with confidence scores
• ⚡ WebSocket Updates — Real-time price streaming via Socket.IO
• 🇮🇳 Indian Market Focus — Top 20 NSE stocks, market hours aware scheduling

🏗️ Architecture

┌──────────────┐     ┌──────────────┐     ┌──────────────┐
│   Frontend   │────▶│   Backend    │────▶│  ML Service  │
│  React/Vite  │     │  Express/TS  │     │   FastAPI    │
│   :80/443    │     │    :4000     │     │    :8000     │
└──────────────┘     └──────┬───────┘     └──────┬───────┘
                            │                     │
                     ┌──────┴───────┐     ┌──────┴───────┐
                     │ TimescaleDB  │     │Data Pipeline │
                     │  PostgreSQL  │     │   Scheduler  │
                     │    :5432     │     │   (Python)   │
                     └──────────────┘     └──────────────┘
                     ┌──────────────┐
                     │    Redis     │
                     │    :6379     │
                     └──────────────┘

🚀 Quick Start (Docker)

The fastest way to get running — everything in one command:

# 1. Clone the repository
git clone https://github.com/adarshvermaa/analyzer.git
cd analyzer

# 2. Configure environment
cp .env.example .env
# Edit .env with your API keys (NEWS_API_KEY is required)

# 3. Start all services
docker compose up -d

# 4. Open the dashboard
open http://localhost

Note: Get a free NewsAPI key at newsapi.org for news & sentiment features.

🛠️ Tech Stack

Layer	Technology
Frontend	React 18, TypeScript, Vite, TailwindCSS, Recharts, TradingView Lightweight Charts
Backend API	Node.js, Express.js, TypeScript, Socket.IO
ML Service	Python, FastAPI, XGBoost, Prophet, scikit-learn
Data Pipeline	Python, yfinance, BeautifulSoup, TextBlob, schedule
Database	TimescaleDB (PostgreSQL with time-series)
Cache	Redis
Infrastructure	Docker, Docker Compose, Nginx

📁 Project Structure

analyzer/
├── backend/                # Express.js API server (TypeScript)
│   ├── src/index.ts        # API routes, WebSocket, DB queries
│   ├── package.json
│   ├── Dockerfile
│   └── tsconfig.json
├── frontend/               # React dashboard (TypeScript)
│   ├── src/
│   │   ├── components/     # StockChart, PredictionPanel, NewsPanel, etc.
│   │   ├── hooks/          # Custom React hooks
│   │   ├── services/       # API client
│   │   └── types/          # TypeScript interfaces
│   ├── Dockerfile
│   └── nginx.conf
├── ml-service/             # FastAPI ML predictions (Python)
│   ├── main.py             # Prediction endpoints
│   ├── training/           # Model training scripts
│   │   ├── train_xgboost.py
│   │   ├── train_prophet.py
│   │   └── train_lstm.py
│   ├── Dockerfile
│   └── requirements.txt
├── data-pipeline/          # Market data ingestion (Python)
│   ├── main.py             # Scheduler orchestrator
│   ├── fetchers/           # NSE, Yahoo Finance, news scrapers
│   ├── analyzers/          # Sentiment analysis
│   ├── indicators/         # Technical indicator calculations
│   ├── database/           # Schema & DB utilities
│   ├── Dockerfile
│   └── requirements.txt
├── scripts/                # Utility scripts
├── docker-compose.yml      # Production deployment
├── docker-compose.dev.yml  # Development with hot reload
├── Makefile                # Common operations
└── .github/workflows/      # CI/CD pipelines

🔧 Development Setup

Prerequisites

• Node.js ≥ 18
• Python 3.11 or 3.12
• Docker & Docker Compose

Manual Setup

# Start database and cache
docker compose -f docker-compose.dev.yml up -d timescaledb redis

# Backend
cd backend
npm install
npm run dev

# Frontend (new terminal)
cd frontend
npm install
npm run dev

# ML Service (new terminal)
cd ml-service
python -m venv venv
source venv/bin/activate    # Windows: .\venv\Scripts\Activate
pip install -r requirements.txt
python main.py

# Data Pipeline (new terminal)
cd data-pipeline
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python main.py

Using Make

make dev          # Start dev environment
make build        # Build Docker images
make up           # Start production stack
make down         # Stop everything
make logs         # Tail logs
make db-setup     # Initialize database

🌐 API Endpoints

Method	Endpoint	Description
GET	/api/stocks	List all tracked stocks
GET	/api/stock/:symbol	Get stock details & latest price
GET	/api/stock/:symbol/history	Historical price data
GET	/api/stock/:symbol/predictions	ML ensemble predictions
GET	/api/stock/:symbol/news	News articles with sentiment
GET	/api/stock/:symbol/sentiment	Aggregated sentiment score
GET	/api/indices	Market indices (NIFTY, SENSEX)
GET	/api/market-mood	Overall market sentiment
GET	/health	Backend health check

WebSocket Events

Event	Direction	Description
subscribe:stock	Client → Server	Subscribe to real-time updates
unsubscribe:stock	Client → Server	Unsubscribe from updates
stock:update	Server → Client	Live price update

⚙️ Configuration

All configuration is via environment variables. See .env.example for all options:

Variable	Description	Default
DB_HOST	PostgreSQL host	localhost
DB_PORT	PostgreSQL port	5432
REDIS_HOST	Redis host	localhost
NEWS_API_KEY	NewsAPI.org API key	—
DEFAULT_STOCKS	Comma-separated NSE symbols	Top 20 NSE stocks
FETCH_INTERVAL_MINUTES	Price fetch frequency	5

🚢 Production Deployment

Single Server (Docker Compose)

# On your server
git clone https://github.com/adarshvermaa/analyzer.git
cd analyzer
cp .env.example .env
# Edit .env with production values

docker compose up -d

The Nginx reverse proxy exposes the app on port 80. All services communicate internally via Docker networking.

Train ML Models

docker compose exec ml-service python -m training.train_all

🤝 Contributing

Contributions are welcome! Please read CONTRIBUTING.md for guidelines.

📄 License

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

⚠️ Disclaimer

This software is for educational and research purposes only. It does not constitute financial advice. Always do your own research before making investment decisions. The predictions generated by ML models are not guaranteed to be accurate.