Stock Analyzer

A comprehensive stock analysis tool that combines historical performance analysis with news sentiment to recommend potentially profitable stocks.

🌐 Now with Interactive Web Dashboard! - Share your stock analysis with anyone via a beautiful web interface.

Features

• 🌐 Interactive Web Dashboard:

  • Beautiful, user-friendly interface
  • Interactive charts and visualizations
  • Real-time stock analysis
  • Mobile-friendly design
  • Deploy to the web for free (Streamlit Cloud)
  • Share with anyone - no installation required

• 🔍 Stock Screener & Discovery:

  • Automatically discover top performing stocks
  • 60+ curated stocks across 8 sectors
  • Preset lists: Top 10, Tech Giants, FAANG+, Finance, and more
  • No need to know which stocks to analyze - the tool finds them for you
  • Customizable screening criteria

• Historical Performance Analysis: Analyzes stock performance using technical indicators including:

  • Moving averages (20, 50, 200-day)
  • Relative Strength Index (RSI)
  • Price momentum and returns
  • Volatility metrics

• News Sentiment Analysis: Fetches and analyzes recent news articles to gauge market sentiment:

  • Alpha Vantage (recommended): Pre-calculated sentiment scores with bullish/bearish indicators
  • News API: Real-time news with TextBlob sentiment analysis
  • Aggregated sentiment metrics across multiple sources

• Smart Recommendations: Combines both analyses to provide actionable stock recommendations:

  • Weighted scoring system
  • Multiple recommendation levels (Strong Buy, Buy, Hold, Watch, Avoid)
  • Detailed explanations for each recommendation

Installation

Prerequisites

• Python 3.8 or higher
• pip (Python package manager)

Setup

1. Clone the repository:

git clone <your-repo-url>
cd First-Project

2. Install required packages:

pip install -r requirements.txt

3. Download TextBlob corpora (optional, only needed if using News API):

python -m textblob.download_corpora

4. Configure API keys:

cp .env.example .env

Edit .env and add your API key(s):

Option 1: Alpha Vantage (Recommended)

ALPHA_VANTAGE_API_KEY=your_actual_api_key_here
DATA_SOURCE=alpha_vantage

Get a free Alpha Vantage API key: Sign up at https://www.alphavantage.co/support/#api-key

Alpha Vantage provides:

• Historical stock data
• Pre-calculated news sentiment (bullish/bearish indicators)
• All-in-one solution with one API key

Option 2: yfinance + News API

DATA_SOURCE=yfinance
NEWS_API_KEY=your_actual_api_key_here

Get a free News API key: Sign up at https://newsapi.org/

Usage

🌐 Web Dashboard (Recommended)

Launch the interactive web dashboard:

streamlit run app.py

The dashboard will open in your browser at http://localhost:8501

Features:

• 📊 Interactive stock selection
• 📈 Real-time analysis with progress tracking
• 🎨 Beautiful visualizations and charts
• 📱 Mobile-friendly interface
• 🚀 Easy to share and deploy

Deploy to the web for free: See DEPLOYMENT.md for instructions on deploying to Streamlit Cloud and sharing with others.

💻 Command Line Interface

Basic Usage - Analyze default stocks (AAPL, GOOGL, MSFT, TSLA, AMZN):

python main.py

Analyze Specific Stocks - Provide stock symbols as command-line arguments:

python main.py AAPL MSFT NVDA

Analyze Multiple Stocks:

python main.py AAPL GOOGL MSFT AMZN TSLA META NVDA

Configuration

Edit .env file to customize:

# Alpha Vantage API Key (recommended)
ALPHA_VANTAGE_API_KEY=your_api_key_here

# News API Key (optional, if using yfinance)
NEWS_API_KEY=your_api_key_here

# Data source: 'alpha_vantage' or 'yfinance'
DATA_SOURCE=alpha_vantage

# Default stocks to analyze
DEFAULT_STOCKS=AAPL,GOOGL,MSFT,TSLA,AMZN

# Number of days of historical data to analyze
HISTORICAL_DAYS=90

# Number of days back to fetch news articles
NEWS_DAYS_BACK=7

# Minimum sentiment score threshold
MIN_SENTIMENT_SCORE=0.1

How It Works

1. Data Collection

• Alpha Vantage mode: Fetches historical stock prices and news with sentiment from Alpha Vantage
• yfinance mode: Fetches historical stock prices using yfinance and news from News API

2. Performance Analysis

The tool calculates:

• Returns: 7-day, 14-day, 30-day, and total returns
• Moving Averages: 20, 50, and 200-day MAs
• RSI: Relative Strength Index to identify overbought/oversold conditions
• Momentum Score: Composite score based on multiple technical indicators

3. Sentiment Analysis

• Analyzes news article headlines and descriptions
• Uses TextBlob for natural language processing
• Calculates polarity scores (negative to positive)
• Aggregates sentiment across multiple articles

4. Recommendation Engine

• Combines performance score (60% weight) and sentiment score (40% weight)
• Generates overall recommendation score (0-100)
• Provides recommendation levels:
  • Strong Buy (80-100): High potential
  • Buy (70-79): Good potential
  • Hold/Consider (60-69): Moderate potential
  • Hold (50-59): Neutral
  • Watch (40-49): Low potential
  • Avoid (0-39): Poor outlook

Output Example

================================================================================
           STOCK RECOMMENDATIONS
================================================================================

+--------+--------+----------------+--------+-----------+------------+-------+
| Symbol | Price  | Recommendation | Score  | 7d Return | 30d Return | News  |
+========+========+================+========+===========+============+=======+
| NVDA   | $495.50| Strong Buy     | 85.3   | +5.20%    | +12.40%    | 18    |
+--------+--------+----------------+--------+-----------+------------+-------+
| MSFT   | $378.90| Buy            | 72.1   | +2.10%    | +8.30%     | 15    |
+--------+--------+----------------+--------+-----------+------------+-------+
| AAPL   | $182.30| Hold/Consider  | 65.5   | +1.50%    | +4.20%     | 20    |
+--------+--------+----------------+--------+-----------+------------+-------+

Project Structure

First-Project/
├── app.py                       # 🌐 Web dashboard (Streamlit)
├── main.py                      # CLI application entry point
├── requirements.txt             # Python dependencies
├── .env.example                 # Environment variables template
├── .env                         # Your configuration (create this)
├── README.md                    # This file
├── DEPLOYMENT.md                # Web deployment guide
├── runtime.txt                  # Python version for deployment
├── packages.txt                 # System packages for deployment
├── .streamlit/
│   ├── config.toml              # Streamlit configuration
│   └── secrets.toml.example     # Secrets template for deployment
└── src/
    ├── stock_fetcher.py         # Fetches historical stock data (yfinance)
    ├── news_fetcher.py          # Fetches news articles (News API)
    ├── alpha_vantage_fetcher.py # Fetches stock data (Alpha Vantage)
    ├── alpha_vantage_news.py    # Fetches news with sentiment (Alpha Vantage)
    ├── performance_analyzer.py  # Analyzes stock performance
    ├── sentiment_analyzer.py    # Analyzes news sentiment
    └── recommender.py           # Generates recommendations

Technical Details

Dependencies

• alpha-vantage: Alpha Vantage API client for stock data and news sentiment
• yfinance: Yahoo Finance API wrapper for stock data (alternative source)
• pandas/numpy: Data manipulation and analysis
• newsapi-python: News API client (alternative source)
• textblob: Natural language processing for sentiment analysis (used with News API)
• colorama: Terminal color output
• tabulate: Formatted table display
• requests: HTTP library for API calls

Scoring Algorithm

Performance Score (0-100):

• Base score: 50 (neutral)
• Positive recent returns: +points
• Price above moving averages: +points
• Optimal RSI range (40-60): +points
• Oversold (RSI < 30): +points (reversal potential)
• Overbought (RSI > 70): -points

Sentiment Score (0-100):

• Based on average news article polarity
• Boosted by high positive article ratio
• Reduced by high negative article ratio

Combined Score:

• 60% Performance + 40% Sentiment
• Normalized to 0-100 scale

Limitations and Disclaimers

⚠️ Important: This tool is for educational and informational purposes only.

• Not Financial Advice: Recommendations are algorithmic and should not be considered professional financial advice
• No Guarantees: Past performance does not guarantee future results
• Market Risk: All investments carry risk
• Data Limitations: Analysis quality depends on data availability and accuracy
• API Limits: News API has rate limits on free tier
• Do Your Research: Always conduct thorough research before making investment decisions
• Consult Professionals: Consider consulting with a licensed financial advisor

Troubleshooting

Alpha Vantage rate limits

• Free tier: 5 API calls per minute, 500 calls per day
• The tool automatically waits 12 seconds between requests to respect rate limits
• For analyzing 5 stocks, expect ~2 minutes (5 stocks × 2 API calls × 12 seconds)
• Consider upgrading to a paid plan for faster analysis

No news data appearing

• Alpha Vantage: Verify your API key is correct in .env
• News API: Verify your API key and check rate limits (free tier: 100 requests/day)
• Ensure internet connection is active
• Check API rate limits haven't been exceeded

Stock data not loading

• Verify stock symbols are correct
• Check internet connection
• Some stocks may not have sufficient historical data
• If using Alpha Vantage, wait for rate limit delays (normal behavior)

TextBlob errors

• Only needed if using News API mode
• Run: python -m textblob.download_corpora

Switching between data sources

• Edit .env and change DATA_SOURCE=alpha_vantage or DATA_SOURCE=yfinance
• Alpha Vantage is slower but provides better sentiment data
• yfinance is faster but requires separate News API key

Future Enhancements

Potential improvements:

• Add more technical indicators (MACD, Bollinger Bands)
• Implement machine learning predictions
• Add portfolio optimization
• Create web dashboard
• Support for cryptocurrencies
• Real-time price alerts
• Backtesting capabilities

Contributing

Contributions are welcome! Please feel free to submit issues or pull requests.

License

This project is open source and available for educational purposes.

Acknowledgments

• Yahoo Finance for stock data (via yfinance)
• News API for news articles
• TextBlob for sentiment analysis