Options-SideKick/backend/app/services/market_data.py

"""
market_data.py — yfinance wrapper with 15-minute in-memory cache.

All other services call through this module.  Never import yfinance directly
outside of here — keeps caching and error handling centralized.
"""

import logging
from datetime import datetime, date, timedelta
from functools import lru_cache
from typing import Optional
import time

import pandas as pd
import yfinance as yf

logger = logging.getLogger(__name__)

# ─── Simple time-bucketed cache ───────────────────────────────────────────────
# Key: (ticker, cache_bucket)  where cache_bucket = int(time() // 900)
_CACHE: dict = {}
_CACHE_TTL_SECONDS = 900  # 15 minutes


def _bucket() -> int:
    return int(time.time() // _CACHE_TTL_SECONDS)


def _cache_get(key: tuple):
    return _CACHE.get((key, _bucket()))


def _cache_set(key: tuple, value):
    _CACHE[(key, _bucket())] = value
    # Prune old entries to avoid unbounded growth
    current = _bucket()
    stale = [k for k in list(_CACHE) if k[1] < current - 1]
    for k in stale:
        del _CACHE[k]


# ─── Price history ─────────────────────────────────────────────────────────────

def get_price_history(ticker: str, period: str = "1y") -> Optional[pd.DataFrame]:
    """
    Return OHLCV DataFrame for the past year.
    Columns: Open, High, Low, Close, Volume
    Index: DatetimeIndex
    Returns None on failure.
    """
    cache_key = ("price_history", ticker, period)
    cached = _cache_get(cache_key)
    if cached is not None:
        return cached

    try:
        df = yf.download(ticker, period=period, auto_adjust=True, progress=False)
        if df.empty:
            logger.warning(f"Empty price history for {ticker}")
            return None
        # Flatten multi-level columns if present (yfinance sometimes returns them)
        if isinstance(df.columns, pd.MultiIndex):
            df.columns = df.columns.get_level_values(0)
        _cache_set(cache_key, df)
        return df
    except Exception as e:
        logger.error(f"Failed to fetch price history for {ticker}: {e}")
        return None


# ─── Current price ─────────────────────────────────────────────────────────────

def get_current_price(ticker: str) -> Optional[float]:
    cache_key = ("current_price", ticker)
    cached = _cache_get(cache_key)
    if cached is not None:
        return cached

    try:
        t = yf.Ticker(ticker)
        price = t.fast_info.get("last_price") or t.fast_info.get("previousClose")
        if price is None:
            hist = get_price_history(ticker, period="5d")
            if hist is not None and not hist.empty:
                price = float(hist["Close"].iloc[-1])
        if price is not None:
            price = float(price)
            _cache_set(cache_key, price)
        return price
    except Exception as e:
        logger.error(f"Failed to fetch current price for {ticker}: {e}")
        return None


# ─── Options chain ─────────────────────────────────────────────────────────────

def get_option_expirations(ticker: str) -> list[str]:
    """Return list of available expiration date strings (YYYY-MM-DD)."""
    cache_key = ("expirations", ticker)
    cached = _cache_get(cache_key)
    if cached is not None:
        return cached

    try:
        t = yf.Ticker(ticker)
        expirations = list(t.options)
        _cache_set(cache_key, expirations)
        return expirations
    except Exception as e:
        logger.error(f"Failed to fetch expirations for {ticker}: {e}")
        return []


def get_options_chain(ticker: str, expiration: str) -> Optional[dict]:
    """
    Return {'calls': DataFrame, 'puts': DataFrame} for the given expiry.
    Columns include: strike, lastPrice, bid, ask, volume, openInterest,
                     impliedVolatility, delta, theta, gamma (where available).
    Returns None on failure.
    """
    cache_key = ("options_chain", ticker, expiration)
    cached = _cache_get(cache_key)
    if cached is not None:
        return cached

    try:
        t = yf.Ticker(ticker)
        chain = t.option_chain(expiration)
        result = {"calls": chain.calls.copy(), "puts": chain.puts.copy()}
        # yfinance does not always include Greeks — add NaN columns if missing
        for df in result.values():
            for col in ("delta", "theta", "gamma"):
                if col not in df.columns:
                    df[col] = float("nan")
        _cache_set(cache_key, result)
        return result
    except Exception as e:
        logger.error(f"Failed to fetch options chain for {ticker} exp={expiration}: {e}")
        return None


def get_nearest_expiry(ticker: str, target_date: date) -> Optional[str]:
    """Return the closest available expiry on or after target_date."""
    expirations = get_option_expirations(ticker)
    if not expirations:
        return None
    target_str = str(target_date)
    future = [e for e in sorted(expirations) if e >= target_str]
    return future[0] if future else None


def get_same_day_expiry(ticker: str) -> Optional[str]:
    """Return today's expiry string if it exists, else None."""
    today_str = str(date.today())
    expirations = get_option_expirations(ticker)
    return today_str if today_str in expirations else None


# ─── Earnings / dividends ──────────────────────────────────────────────────────

def get_earnings_date(ticker: str) -> Optional[date]:
    """Return the next earnings date or None."""
    cache_key = ("earnings", ticker)
    cached = _cache_get(cache_key)
    if cached is not None:
        return cached

    try:
        t = yf.Ticker(ticker)
        cal = t.calendar
        if cal is None:
            return None

        # calendar can be a dict or DataFrame depending on yfinance version
        if isinstance(cal, dict):
            earnings_info = cal.get("Earnings Date", [])
        else:
            # DataFrame — look for "Earnings Date" row or column
            try:
                earnings_info = cal.loc["Earnings Date"].tolist()
            except Exception:
                earnings_info = []

        result = None
        for item in (earnings_info if isinstance(earnings_info, list) else [earnings_info]):
            try:
                d = pd.Timestamp(item).date()
                if d >= date.today():
                    result = d
                    break
            except Exception:
                continue

        _cache_set(cache_key, result)
        return result
    except Exception as e:
        logger.error(f"Failed to fetch earnings date for {ticker}: {e}")
        return None