TradingAgents/tradingagents/dataflows/y_finance.py

from typing import Annotated
from datetime import datetime
from dateutil.relativedelta import relativedelta
import yfinance as yf
import os
from .stockstats_utils import StockstatsUtils

def get_YFin_data_online(
    symbol: Annotated[str, "ticker symbol of the company"],
    start_date: Annotated[str, "Start date in yyyy-mm-dd format"],
    end_date: Annotated[str, "End date in yyyy-mm-dd format"],
):

    datetime.strptime(start_date, "%Y-%m-%d")
    datetime.strptime(end_date, "%Y-%m-%d")

    # Create ticker object
    ticker = yf.Ticker(symbol.upper())

    # Fetch historical data for the specified date range
    data = ticker.history(start=start_date, end=end_date)

    # Check if data is empty
    if data.empty:
        return (
            f"No data found for symbol '{symbol}' between {start_date} and {end_date}"
        )

    # Remove timezone info from index for cleaner output
    if data.index.tz is not None:
        data.index = data.index.tz_localize(None)

    # Round numerical values to 2 decimal places for cleaner display
    numeric_columns = ["Open", "High", "Low", "Close", "Adj Close"]
    for col in numeric_columns:
        if col in data.columns:
            data[col] = data[col].round(2)

    # Convert DataFrame to CSV string
    csv_string = data.to_csv()

    # Add header information
    header = f"# Stock data for {symbol.upper()} from {start_date} to {end_date}\n"
    header += f"# Total records: {len(data)}\n"
    header += f"# Data retrieved on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n\n"

    return header + csv_string

def get_stock_stats_indicators_window(
    symbol: Annotated[str, "ticker symbol of the company"],
    indicator: Annotated[str, "technical indicator to get the analysis and report of"],
    curr_date: Annotated[
        str, "The current trading date you are trading on, YYYY-mm-dd"
    ],
    look_back_days: Annotated[int, "how many days to look back"],
) -> str:

    best_ind_params = {
        # Moving Averages
        "close_50_sma": (
            "50 SMA: A medium-term trend indicator. "
            "Usage: Identify trend direction and serve as dynamic support/resistance. "
            "Tips: It lags price; combine with faster indicators for timely signals."
        ),
        "close_200_sma": (
            "200 SMA: A long-term trend benchmark. "
            "Usage: Confirm overall market trend and identify golden/death cross setups. "
            "Tips: It reacts slowly; best for strategic trend confirmation rather than frequent trading entries."
        ),
        "close_10_ema": (
            "10 EMA: A responsive short-term average. "
            "Usage: Capture quick shifts in momentum and potential entry points. "
            "Tips: Prone to noise in choppy markets; use alongside longer averages for filtering false signals."
        ),
        # MACD Related
        "macd": (
            "MACD: Computes momentum via differences of EMAs. "
            "Usage: Look for crossovers and divergence as signals of trend changes. "
            "Tips: Confirm with other indicators in low-volatility or sideways markets."
        ),
        "macds": (
            "MACD Signal: An EMA smoothing of the MACD line. "
            "Usage: Use crossovers with the MACD line to trigger trades. "
            "Tips: Should be part of a broader strategy to avoid false positives."
        ),
        "macdh": (
            "MACD Histogram: Shows the gap between the MACD line and its signal. "
            "Usage: Visualize momentum strength and spot divergence early. "
            "Tips: Can be volatile; complement with additional filters in fast-moving markets."
        ),
        # Momentum Indicators
        "rsi": (
            "RSI: Measures momentum to flag overbought/oversold conditions. "
            "Usage: Apply 70/30 thresholds and watch for divergence to signal reversals. "
            "Tips: In strong trends, RSI may remain extreme; always cross-check with trend analysis."
        ),
        # Volatility Indicators
        "boll": (
            "Bollinger Middle: A 20 SMA serving as the basis for Bollinger Bands. "
            "Usage: Acts as a dynamic benchmark for price movement. "
            "Tips: Combine with the upper and lower bands to effectively spot breakouts or reversals."
        ),
        "boll_ub": (
            "Bollinger Upper Band: Typically 2 standard deviations above the middle line. "
            "Usage: Signals potential overbought conditions and breakout zones. "
            "Tips: Confirm signals with other tools; prices may ride the band in strong trends."
        ),
        "boll_lb": (
            "Bollinger Lower Band: Typically 2 standard deviations below the middle line. "
            "Usage: Indicates potential oversold conditions. "
            "Tips: Use additional analysis to avoid false reversal signals."
        ),
        "atr": (
            "ATR: Averages true range to measure volatility. "
            "Usage: Set stop-loss levels and adjust position sizes based on current market volatility. "
            "Tips: It's a reactive measure, so use it as part of a broader risk management strategy."
        ),
        # Volume-Based Indicators
        "vwma": (
            "VWMA: A moving average weighted by volume. "
            "Usage: Confirm trends by integrating price action with volume data. "
            "Tips: Watch for skewed results from volume spikes; use in combination with other volume analyses."
        ),
        "mfi": (
            "MFI: The Money Flow Index is a momentum indicator that uses both price and volume to measure buying and selling pressure. "
            "Usage: Identify overbought (>80) or oversold (<20) conditions and confirm the strength of trends or reversals. "
            "Tips: Use alongside RSI or MACD to confirm signals; divergence between price and MFI can indicate potential reversals."
        ),
    }

    if indicator not in best_ind_params:
        raise ValueError(
            f"Indicator {indicator} is not supported. Please choose from: {list(best_ind_params.keys())}"
        )

    end_date = curr_date
    curr_date_dt = datetime.strptime(curr_date, "%Y-%m-%d")
    before = curr_date_dt - relativedelta(days=look_back_days)

    # online gathering only
    ind_string = ""
    while curr_date_dt >= before:
        indicator_value = get_stockstats_indicator(
            symbol, indicator, curr_date_dt.strftime("%Y-%m-%d")
        )

        ind_string += f"{curr_date_dt.strftime('%Y-%m-%d')}: {indicator_value}\n"

        curr_date_dt = curr_date_dt - relativedelta(days=1)

    result_str = (
        f"## {indicator} values from {before.strftime('%Y-%m-%d')} to {end_date}:\n\n"
        + ind_string
        + "\n\n"
        + best_ind_params.get(indicator, "No description available.")
    )

    return result_str


def get_stockstats_indicator(
    symbol: Annotated[str, "ticker symbol of the company"],
    indicator: Annotated[str, "technical indicator to get the analysis and report of"],
    curr_date: Annotated[
        str, "The current trading date you are trading on, YYYY-mm-dd"
    ],
) -> str:

    curr_date_dt = datetime.strptime(curr_date, "%Y-%m-%d")
    curr_date = curr_date_dt.strftime("%Y-%m-%d")

    try:
        indicator_value = StockstatsUtils.get_stock_stats(
            symbol,
            indicator,
            curr_date,
        )
    except Exception as e:
        print(
            f"Error getting stockstats indicator data for indicator {indicator} on {curr_date}: {e}"
        )
        return ""

    return str(indicator_value)


def get_balance_sheet(
    ticker: Annotated[str, "ticker symbol of the company"],
    freq: Annotated[str, "frequency of data: 'annual' or 'quarterly'"] = "quarterly",
    curr_date: Annotated[str, "current date (not used for yfinance)"] = None
):
    """Get balance sheet data from yfinance."""
    try:
        ticker_obj = yf.Ticker(ticker.upper())
        
        if freq.lower() == "quarterly":
            data = ticker_obj.quarterly_balance_sheet
        else:
            data = ticker_obj.balance_sheet
            
        if data.empty:
            return f"No balance sheet data found for symbol '{ticker}'"
            
        # Convert to CSV string for consistency with other functions
        csv_string = data.to_csv()
        
        # Add header information
        header = f"# Balance Sheet data for {ticker.upper()} ({freq})\n"
        header += f"# Data retrieved on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n\n"
        
        return header + csv_string
        
    except Exception as e:
        return f"Error retrieving balance sheet for {ticker}: {str(e)}"


def get_cashflow(
    ticker: Annotated[str, "ticker symbol of the company"],
    freq: Annotated[str, "frequency of data: 'annual' or 'quarterly'"] = "quarterly",
    curr_date: Annotated[str, "current date (not used for yfinance)"] = None
):
    """Get cash flow data from yfinance."""
    try:
        ticker_obj = yf.Ticker(ticker.upper())
        
        if freq.lower() == "quarterly":
            data = ticker_obj.quarterly_cashflow
        else:
            data = ticker_obj.cashflow
            
        if data.empty:
            return f"No cash flow data found for symbol '{ticker}'"
            
        # Convert to CSV string for consistency with other functions
        csv_string = data.to_csv()
        
        # Add header information
        header = f"# Cash Flow data for {ticker.upper()} ({freq})\n"
        header += f"# Data retrieved on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n\n"
        
        return header + csv_string
        
    except Exception as e:
        return f"Error retrieving cash flow for {ticker}: {str(e)}"


def get_income_statement(
    ticker: Annotated[str, "ticker symbol of the company"],
    freq: Annotated[str, "frequency of data: 'annual' or 'quarterly'"] = "quarterly",
    curr_date: Annotated[str, "current date (not used for yfinance)"] = None
):
    """Get income statement data from yfinance."""
    try:
        ticker_obj = yf.Ticker(ticker.upper())
        
        if freq.lower() == "quarterly":
            data = ticker_obj.quarterly_income_stmt
        else:
            data = ticker_obj.income_stmt
            
        if data.empty:
            return f"No income statement data found for symbol '{ticker}'"
            
        # Convert to CSV string for consistency with other functions
        csv_string = data.to_csv()
        
        # Add header information
        header = f"# Income Statement data for {ticker.upper()} ({freq})\n"
        header += f"# Data retrieved on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n\n"
        
        return header + csv_string
        
    except Exception as e:
        return f"Error retrieving income statement for {ticker}: {str(e)}"


def get_insider_transactions(
    ticker: Annotated[str, "ticker symbol of the company"]
):
    """Get insider transactions data from yfinance."""
    try:
        ticker_obj = yf.Ticker(ticker.upper())
        data = ticker_obj.insider_transactions
        
        if data is None or data.empty:
            return f"No insider transactions data found for symbol '{ticker}'"
            
        # Convert to CSV string for consistency with other functions
        csv_string = data.to_csv()
        
        # Add header information
        header = f"# Insider Transactions data for {ticker.upper()}\n"
        header += f"# Data retrieved on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n\n"
        
        return header + csv_string
        
    except Exception as e:
        return f"Error retrieving insider transactions for {ticker}: {str(e)}"