from daily_stock_analysis import MarketAnalyzer

analyzer = MarketAnalyzer(
    llm_provider="openai",
    model="gpt-4o",
    markets=["US", "CN", "HK"],
    analysis_depth="comprehensive"
)

# Analyze a stock
result = analyzer.analyze(
    ticker="AAPL",
    timeframe="1D",
    include_news=True,
    include_technicals=True
)

print(f"Sentiment: {result.sentiment}")
print(f"Recommendation: {result.recommendation}")
print(f"Key factors: {result.factors}")

# Clone the repository
git clone https://github.com/ZhuLinsen/daily_stock_analysis.git
cd daily_stock_analysis

# Install dependencies
pip install -r requirements.txt

# Configure environment
cp .env.example .env
# Edit .env with your API keys

# .env configuration
OPENAI_API_KEY=sk-your-key
AKSHARE_TOKEN=  # Optional for extended data
TUSHARE_TOKEN=  # Optional for A-share data
TELEGRAM_BOT_TOKEN=  # For alerts

from daily_stock_analysis import StockDashboard

# Initialize dashboard
dashboard = StockDashboard(market="US")

# Add stocks to watch
dashboard.watch(["AAPL", "MSFT", "GOOGL", "AMZN"])

# Run analysis
dashboard.analyze()

# View results
dashboard.show()

# US market analysis
us_analyzer = MarketAnalyzer(market="US")

# Key features
us_analyzer.add_indicator("RSI")
us_analyzer.add_indicator("MACD")
us_analyzer.add_indicator("Bollinger Bands")
us_analyzer.add_indicator("Volume Profile")

# Real-time data
quotes = us_analyzer.get_quotes(tickers=["SPY", "QQQ", "DIA"])

# China A-share analysis
cn_analyzer = MarketAnalyzer(market="CN")

# A-share specific indicators
cn_analyzer.add_indicator("Dragon Tiger List")
cn_analyzer.add_indicator("Northbound Flow")
cn_analyzer.add_indicator("Margin Trading")
cn_analyzer.add_indicator("Block Trades")

# Sector analysis
sectors = cn_analyzer.sector_analysis(date="2026-07-07")

# HK market analysis
hk_analyzer = MarketAnalyzer(market="HK")

# HK-specific features
hk_analyzer.add_indicator("Connect Program")
hk_analyzer.add_indicator("Short Selling")
hk_analyzer.add_indicator("Turnover Analysis")

from daily_stock_analysis import SentimentEngine

engine = SentimentEngine(
    sources=["news", "social", "analyst_reports"],
    languages=["en", "zh", "hk"],
    llm_model="claude-3-5-sonnet"
)

# Analyze sentiment for a stock
sentiment = engine.analyze("NVDA")
print(f"Overall: {sentiment.overall}")
print(f"News: {sentiment.news}")
print(f"Social: {sentiment.social}")
print(f"Analysts: {sentiment.analysts}")

from daily_stock_analysis import NewsAnalyzer

analyzer = NewsAnalyzer(
    sources=["Reuters", "Bloomberg", "CNBC", "Eastmoney"],
    keywords=["AI", "semiconductor", "earnings"],
    language="en"
)

# Get relevant news
news = analyzer.get_recent(hours=24)
for item in news:
    print(f"[{item.sentiment}] {item.headline}")

from daily_stock_analysis import TechnicalAnalyzer

ta = TechnicalAnalyzer(
    timeframe="1D",
    indicators=["MA", "EMA", "RSI", "MACD", "KDJ", "WR"]
)

# Generate signals
signals = ta.generate_signals(ticker="AAPL")
for signal in signals:
    print(f"{signal.type}: {signal.action} @ {signal.price}")

from daily_stock_analysis import Dashboard

dash = Dashboard(
    layout="professional",
    theme="dark",
    refresh_interval=60  # seconds
)

# Add widgets
dash.add_widget("price_chart", ticker="SPY")
dash.add_widget("sentiment_gauge", ticker="AAPL")
dash.add_widget("news_feed", keywords=["AI", "tech"])
dash.add_widget("sector_heatmap", market="US")
dash.add_widget("alert_panel")

# Launch dashboard
dash.launch(port=8080)

# Generate daily report
python -m daily_stock_analysis.report \
  --date 2026-07-07 \
  --market US,CN,HK \
  --output daily_report.pdf

# Generate weekly summary
python -m daily_stock_analysis.report \
  --week 2026-W27 \
  --format markdown \
  --output weekly.md

from daily_stock_analysis import AlertManager

alerts = AlertManager(
    channels=["telegram", "email", "webhook"],
    retry_count=3,
    quiet_hours={"start": "22:00", "end": "08:00"}
)

# Price alerts
alerts.add(
    type="price",
    ticker="BTC",
    condition="above",
    threshold=100000,
    message="Bitcoin crossed $100K!",
    channels=["telegram", "email"]
)

# Sentiment alerts
alerts.add(
    type="sentiment_shift",
    ticker="TSLA",
    threshold=0.3,
    message="Major sentiment shift detected for TSLA"
)

# Run daily at 9 AM
0 9 * * * python -m daily_stock_analysis.daily_report >> /var/log/stock_analysis.log

# Run weekly on Monday
0 10 * * 1 python -m daily_stock_analysis.weekly_report >> /var/log/weekly.log

FROM python:3.12-slim

WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt

COPY . .

# Run daily analysis
CMD ["python", "-m", "daily_stock_analysis.scheduler"]

# Fork and clone
git clone https://github.com/YOUR_USERNAME/daily_stock_analysis.git

# Create feature branch
git checkout -b feature/new-indicator

# Run tests
pytest tests/ -v

# Submit pull request
git push origin feature/new-indicator

from daily_stock_analysis import RiskManager

risk = RiskManager(
    max_position_pct=0.1,    # Max 10% per position
    max_correlation=0.7,     # Limit correlated positions
    stop_loss_pct=0.05,      # 5% stop loss
    take_profit_pct=0.15,    # 15% take profit
)

# Check portfolio risk
portfolio_risk = risk.evaluate(portfolio=my_portfolio)
print(f"Risk score: {portfolio_risk.score}/10")
print(f"Recommendations: {portfolio_risk.suggestions}")

# Validate data before analysis
from daily_stock_analysis import DataValidator

validator = DataValidator(
    required_fields=["price", "volume", "date"],
    max_missing_pct=5,
    outlier_detection="iqr"
)

is_valid, issues = validator.validate(stock_data)
if not is_valid:
    print(f"Data issues: {issues}")

from daily_stock_analysis import CustomIndicator

class MomentumIndicator(CustomIndicator):
    name = "momentum"
    parameters = {"lookback": 14}
    
    def calculate(self, data):
        return (data['close'] - data['close'].shift(self.lookback)) / data['close'].shift(self.lookback) * 100

# Register and use
indicator = MomentumIndicator()
indicator.register()
signals = indicator.generate_signals(ticker="AAPL", lookback=20)

from daily_stock_analysis import Backtester

bt = Backtester(
    start="2020-01-01",
    end="2026-01-01",
    initial_capital=100000,
    commission=0.001,
)

# Run strategy
results = bt.run(
    strategy="llm_sentiment",
    universe="sp500",
    rebalance="monthly"
)

print(f"Total return: {results.total_return:.1%}")
print(f"Sharpe ratio: {results.sharpe:.2f}")
print(f"Max drawdown: {results.max_drawdown:.1%}")