Harwinder
94b93cf1e7
- config.py: add XAU/USD and XAG/USD to SYMBOL_DISPLAY; add PIP_VALUES map for commodities (gold pip = $0.01, not $0.0001) - data_provider.py: use PIP_VALUES in get_pair_info so gold trade setup shows correct pip counts instead of 269,000 pips for a $27 SL - main.py: validate symbols in symbol_from_name — rejects non-alpha inputs like '15M' with a helpful hint to use --timeframe instead Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
594 lines
23 KiB
Python
594 lines
23 KiB
Python
"""
|
||
Forex Signal Intelligence Platform - Data Provider
|
||
====================================================
|
||
Retrieves and validates market data from Twelve Data API.
|
||
Falls back to synthetic GBM data if the API is unavailable.
|
||
"""
|
||
|
||
import hashlib
|
||
import logging
|
||
import os
|
||
import time
|
||
from collections import deque
|
||
from datetime import datetime, timedelta, timezone
|
||
from typing import Dict, List, Optional
|
||
|
||
import numpy as np
|
||
import pandas as pd
|
||
import requests
|
||
|
||
from config import PlatformConfig, Timeframe, SYMBOL_DISPLAY, PIP_VALUES
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
|
||
class DataIntegrityError(Exception):
|
||
"""Raised when data fails validation checks."""
|
||
pass
|
||
|
||
|
||
class ForexDataProvider:
|
||
"""
|
||
Forex data provider backed by Twelve Data API.
|
||
|
||
Twelve Data has native 4h candles, eliminating the H1→H4 resampling
|
||
hack needed for Yahoo Finance. Free tier: 800 credits/day, 8 req/min.
|
||
"""
|
||
|
||
TD_BASE_URL = "https://api.twelvedata.com"
|
||
|
||
TD_INTERVALS = {
|
||
Timeframe.M1: "1min",
|
||
Timeframe.M5: "5min",
|
||
Timeframe.M15: "15min",
|
||
Timeframe.M30: "30min",
|
||
Timeframe.H1: "1h",
|
||
Timeframe.H4: "4h",
|
||
Timeframe.D1: "1day",
|
||
Timeframe.W1: "1week",
|
||
}
|
||
|
||
# Approximate bars per day for each timeframe (used to size outputsize)
|
||
BARS_PER_DAY = {
|
||
Timeframe.M1: 1440,
|
||
Timeframe.M5: 288,
|
||
Timeframe.M15: 96,
|
||
Timeframe.M30: 48,
|
||
Timeframe.H1: 24,
|
||
Timeframe.H4: 6,
|
||
Timeframe.D1: 1,
|
||
Timeframe.W1: 0.143,
|
||
}
|
||
|
||
# Free plan: 8 credits/minute, 800 credits/day
|
||
RATE_LIMIT = 8
|
||
RATE_WINDOW = 60.0
|
||
DAILY_LIMIT = 800
|
||
|
||
def __init__(self, config: PlatformConfig):
|
||
self.config = config
|
||
self._api_key = (
|
||
os.environ.get("TWELVE_DATA_API_KEY")
|
||
or config.twelve_data_api_key
|
||
)
|
||
self._cache: Dict[str, pd.DataFrame] = {}
|
||
self._cache_timestamps: Dict[str, float] = {}
|
||
self._request_times: deque = deque() # timestamps of recent per-minute credits
|
||
self._daily_credits: int = 0 # credits used today
|
||
self._daily_reset: float = time.time() + 86400 # next midnight reset
|
||
self._no_api_data: set = set() # td_symbols with no values from API (use synthetic)
|
||
self._session = requests.Session()
|
||
# Docs recommend Authorization header over apikey query param
|
||
self._session.headers.update({
|
||
"User-Agent": "Mozilla/5.0 (compatible; ForexIntel/1.0)",
|
||
})
|
||
if self._api_key:
|
||
self._session.headers["Authorization"] = f"apikey {self._api_key}"
|
||
|
||
@staticmethod
|
||
def _to_td_symbol(symbol: str) -> str:
|
||
"""Convert internal symbol (EURUSD=X) to Twelve Data format (EUR/USD)."""
|
||
clean = symbol.replace("=X", "")
|
||
return f"{clean[:3]}/{clean[3:]}"
|
||
|
||
def fetch_ohlcv(
|
||
self,
|
||
symbol: str,
|
||
timeframe: Timeframe,
|
||
lookback_days: Optional[int] = None,
|
||
) -> pd.DataFrame:
|
||
"""
|
||
Fetch OHLCV data for a Forex pair with full validation.
|
||
|
||
Returns a DataFrame with columns: Open, High, Low, Close, Volume
|
||
Index is a timezone-aware DatetimeIndex in UTC.
|
||
"""
|
||
if lookback_days is None:
|
||
lookback_days = self.config.data_lookback_days
|
||
|
||
cache_key = f"{symbol}_{timeframe.value}"
|
||
now = time.time()
|
||
|
||
if (
|
||
cache_key in self._cache_timestamps
|
||
and (now - self._cache_timestamps[cache_key]) < self.config.refresh_interval
|
||
and cache_key in self._cache
|
||
):
|
||
cached = self._cache.get(cache_key)
|
||
if cached is not None and not cached.empty:
|
||
return cached
|
||
|
||
df = self._fetch_twelve_data(symbol, timeframe, lookback_days)
|
||
df = self._validate_and_clean(df, symbol, timeframe)
|
||
|
||
self._cache[cache_key] = df
|
||
self._cache_timestamps[cache_key] = now
|
||
return df
|
||
|
||
def prefetch_batch(
|
||
self,
|
||
symbols: List[str],
|
||
timeframes: List[Timeframe],
|
||
lookback_days: Optional[int] = None,
|
||
) -> None:
|
||
"""
|
||
Batch-fetch all symbols for each timeframe in a single API call per TF.
|
||
|
||
Twelve Data accepts comma-separated symbols, so 7 pairs × 3 timeframes
|
||
= 3 requests instead of 21 — well within the free-tier 8 req/min limit.
|
||
Results are stored in the local cache; subsequent fetch_ohlcv calls
|
||
for the same symbol/TF will be served from cache.
|
||
"""
|
||
if lookback_days is None:
|
||
lookback_days = self.config.data_lookback_days
|
||
|
||
for tf in timeframes:
|
||
try:
|
||
self._batch_fetch_timeframe(symbols, tf, lookback_days)
|
||
time.sleep(1.0) # brief pause between TF requests
|
||
except Exception as e:
|
||
logger.warning(f"Batch prefetch failed for {tf.value}: {e}")
|
||
|
||
def fetch_multiple(
|
||
self,
|
||
symbols: List[str],
|
||
timeframe: Timeframe,
|
||
lookback_days: Optional[int] = None,
|
||
) -> Dict[str, pd.DataFrame]:
|
||
"""Fetch data for multiple symbols, returning dict of DataFrames."""
|
||
results = {}
|
||
for symbol in symbols:
|
||
try:
|
||
df = self.fetch_ohlcv(symbol, timeframe, lookback_days)
|
||
results[symbol] = df
|
||
except Exception as e:
|
||
logger.warning(f"Failed to fetch {symbol}: {e}")
|
||
return results
|
||
|
||
def get_latest_price(self, symbol: str) -> Optional[float]:
|
||
"""Return the most recent close price for a symbol."""
|
||
try:
|
||
df = self.fetch_ohlcv(symbol, Timeframe.M5, lookback_days=1)
|
||
if df is not None and not df.empty:
|
||
return float(df["Close"].iloc[-1])
|
||
except Exception:
|
||
pass
|
||
return None
|
||
|
||
def get_spread_estimate(self, symbol: str) -> float:
|
||
"""Estimate typical spread from recent M5 high-low ranges."""
|
||
try:
|
||
df = self.fetch_ohlcv(symbol, Timeframe.M5, lookback_days=1)
|
||
if df is not None and not df.empty:
|
||
return float((df["High"] - df["Low"]).median())
|
||
except Exception:
|
||
pass
|
||
|
||
fallback_spreads = {
|
||
"EURUSD=X": 0.00010, "GBPUSD=X": 0.00015,
|
||
"USDJPY=X": 0.010, "USDCHF=X": 0.00015,
|
||
"AUDUSD=X": 0.00015, "USDCAD=X": 0.00018,
|
||
"NZDUSD=X": 0.00020,
|
||
}
|
||
return fallback_spreads.get(symbol, 0.00020)
|
||
|
||
def get_pair_info(self, symbol: str) -> Dict:
|
||
"""Return display name and pip value for a pair."""
|
||
display = SYMBOL_DISPLAY.get(symbol, symbol)
|
||
is_jpy = "JPY" in symbol
|
||
# Commodity-specific pip values take priority, then JPY pairs, then standard forex
|
||
pip_value = PIP_VALUES.get(symbol, 0.01 if is_jpy else 0.0001)
|
||
return {
|
||
"symbol": symbol,
|
||
"display": display,
|
||
"pip_value": pip_value,
|
||
"is_jpy_pair": is_jpy,
|
||
}
|
||
|
||
# ── Private Methods ────────────────────────────────────────────
|
||
|
||
def _throttle(self, credits: int = 1) -> bool:
|
||
"""
|
||
Block until `credits` per-minute API credits are available.
|
||
Returns False if the daily limit is reached (caller should use synthetic data).
|
||
|
||
Twelve Data free tier: 8 credits/minute, 800 credits/day.
|
||
Each symbol in any request (single or batch) consumes 1 credit.
|
||
"""
|
||
# Reset daily counter after 24 hours
|
||
now = time.time()
|
||
if now >= self._daily_reset:
|
||
self._daily_credits = 0
|
||
self._daily_reset = now + 86400
|
||
|
||
# Daily limit check
|
||
if self._daily_credits + credits > self.DAILY_LIMIT:
|
||
logger.warning(
|
||
f"Daily API limit reached ({self._daily_credits}/{self.DAILY_LIMIT} credits) "
|
||
"— using cached/synthetic data for remaining requests today."
|
||
)
|
||
return False
|
||
|
||
# Warn when approaching daily limit
|
||
if self._daily_credits + credits > self.DAILY_LIMIT * 0.8:
|
||
logger.warning(
|
||
f"Approaching daily API limit: {self._daily_credits}/{self.DAILY_LIMIT} credits used."
|
||
)
|
||
|
||
# Per-minute rate limit
|
||
while True:
|
||
now = time.time()
|
||
while self._request_times and now - self._request_times[0] >= self.RATE_WINDOW:
|
||
self._request_times.popleft()
|
||
|
||
available = self.RATE_LIMIT - len(self._request_times)
|
||
if available >= credits:
|
||
ts = time.time()
|
||
for _ in range(credits):
|
||
self._request_times.append(ts)
|
||
self._daily_credits += credits
|
||
return True
|
||
|
||
wait = (self._request_times[0] + self.RATE_WINDOW) - now + 0.2
|
||
logger.info(
|
||
f"Rate limit: {len(self._request_times)}/{self.RATE_LIMIT} credits used "
|
||
f"— waiting {wait:.1f}s for next window..."
|
||
)
|
||
time.sleep(wait)
|
||
|
||
def _batch_fetch_timeframe(
|
||
self, symbols: List[str], timeframe: Timeframe, lookback_days: int
|
||
) -> None:
|
||
"""
|
||
Single API call fetching all symbols for one timeframe.
|
||
Twelve Data returns a dict keyed by symbol when multiple are requested.
|
||
Parsed DataFrames are validated and stored in the cache.
|
||
"""
|
||
if not self._api_key:
|
||
return
|
||
|
||
td_symbols = [self._to_td_symbol(s) for s in symbols]
|
||
interval = self.TD_INTERVALS[timeframe]
|
||
outputsize = min(
|
||
int(lookback_days * self.BARS_PER_DAY[timeframe]) + 20, 5000
|
||
)
|
||
outputsize = max(outputsize, 300)
|
||
|
||
# Each symbol in a batch request costs 1 credit
|
||
if not self._throttle(credits=len(symbols)):
|
||
return # daily limit reached — callers will use synthetic data
|
||
|
||
resp = self._session.get(
|
||
f"{self.TD_BASE_URL}/time_series",
|
||
params={
|
||
"symbol": ",".join(td_symbols),
|
||
"interval": interval,
|
||
"outputsize": outputsize,
|
||
"timezone": "UTC",
|
||
"format": "json",
|
||
},
|
||
timeout=30,
|
||
)
|
||
resp.raise_for_status()
|
||
data = resp.json()
|
||
|
||
# If the whole batch request returned a top-level error, raise it
|
||
if isinstance(data, dict) and data.get("status") == "error":
|
||
raise DataIntegrityError(
|
||
f"Batch API error ({timeframe.value}): {data.get('message', 'unknown')}"
|
||
)
|
||
|
||
# Batch response: {"EUR/USD": {...}, "GBP/USD": {...}, ...}
|
||
now = time.time()
|
||
for symbol, td_sym in zip(symbols, td_symbols):
|
||
try:
|
||
sym_data = data.get(td_sym, {})
|
||
if sym_data.get("status") == "error":
|
||
logger.warning(
|
||
f"Batch fetch error for {td_sym}: {sym_data.get('message')}"
|
||
)
|
||
continue
|
||
|
||
values = sym_data.get("values")
|
||
if not values:
|
||
if td_sym not in self._no_api_data:
|
||
logger.info(
|
||
f"No API data for {td_sym} — using synthetic data"
|
||
)
|
||
self._no_api_data.add(td_sym)
|
||
# Cache synthetic so fetch_ohlcv won't make a redundant API call
|
||
try:
|
||
syn = self._generate_synthetic_data(symbol, timeframe, lookback_days)
|
||
syn = self._validate_and_clean(syn, symbol, timeframe)
|
||
cache_key = f"{symbol}_{timeframe.value}"
|
||
self._cache[cache_key] = syn
|
||
self._cache_timestamps[cache_key] = now
|
||
except Exception:
|
||
pass
|
||
continue
|
||
|
||
records = [
|
||
{
|
||
"Datetime": pd.Timestamp(v["datetime"], tz="UTC"),
|
||
"Open": float(v["open"]) if v.get("open") is not None else None,
|
||
"High": float(v["high"]) if v.get("high") is not None else None,
|
||
"Low": float(v["low"]) if v.get("low") is not None else None,
|
||
"Close": float(v["close"]) if v.get("close") is not None else None,
|
||
"Volume": float(v["volume"]) if v.get("volume") is not None else 0.0,
|
||
}
|
||
for v in reversed(values)
|
||
if v.get("datetime")
|
||
]
|
||
df = pd.DataFrame(records).set_index("Datetime")
|
||
df.index.name = "Datetime"
|
||
df = self._validate_and_clean(df, symbol, timeframe)
|
||
|
||
cache_key = f"{symbol}_{timeframe.value}"
|
||
self._cache[cache_key] = df
|
||
self._cache_timestamps[cache_key] = now
|
||
logger.debug(f"Batch cached {len(df)} bars for {td_sym} @ {interval}")
|
||
|
||
except Exception as e:
|
||
logger.warning(f"Failed to parse batch data for {td_sym}: {e}")
|
||
|
||
def _fetch_twelve_data(
|
||
self, symbol: str, timeframe: Timeframe, lookback_days: int
|
||
) -> pd.DataFrame:
|
||
"""
|
||
Fetch OHLCV from Twelve Data REST API.
|
||
Falls back to synthetic GBM data if API is unavailable or key is missing.
|
||
"""
|
||
if not self._api_key:
|
||
logger.warning("No Twelve Data API key — using synthetic data. "
|
||
"Set TWELVE_DATA_API_KEY env var or config.twelve_data_api_key.")
|
||
return self._generate_synthetic_data(symbol, timeframe, lookback_days)
|
||
|
||
td_symbol = self._to_td_symbol(symbol)
|
||
interval = self.TD_INTERVALS[timeframe]
|
||
outputsize = min(
|
||
int(lookback_days * self.BARS_PER_DAY[timeframe]) + 20,
|
||
5000,
|
||
)
|
||
outputsize = max(outputsize, 300)
|
||
|
||
if not self._throttle(credits=1):
|
||
return self._generate_synthetic_data(symbol, timeframe, lookback_days)
|
||
|
||
try:
|
||
resp = self._session.get(
|
||
f"{self.TD_BASE_URL}/time_series",
|
||
params={
|
||
"symbol": td_symbol,
|
||
"interval": interval,
|
||
"outputsize": outputsize,
|
||
"timezone": "UTC",
|
||
"format": "json",
|
||
},
|
||
timeout=15,
|
||
)
|
||
resp.raise_for_status()
|
||
data = resp.json()
|
||
|
||
if data.get("status") == "error":
|
||
raise DataIntegrityError(
|
||
f"Twelve Data API error for {td_symbol}: {data.get('message', 'unknown')}"
|
||
)
|
||
|
||
values = data.get("values")
|
||
if not values:
|
||
raise DataIntegrityError(f"Empty response from Twelve Data for {td_symbol}")
|
||
|
||
# Values arrive newest-first; reverse to chronological order
|
||
# API may return null for any OHLC field — map to None for pandas NaN handling
|
||
records = [
|
||
{
|
||
"Datetime": pd.Timestamp(v["datetime"], tz="UTC"),
|
||
"Open": float(v["open"]) if v.get("open") is not None else None,
|
||
"High": float(v["high"]) if v.get("high") is not None else None,
|
||
"Low": float(v["low"]) if v.get("low") is not None else None,
|
||
"Close": float(v["close"]) if v.get("close") is not None else None,
|
||
"Volume": float(v["volume"]) if v.get("volume") is not None else 0.0,
|
||
}
|
||
for v in reversed(values)
|
||
if v.get("datetime")
|
||
]
|
||
|
||
df = pd.DataFrame(records).set_index("Datetime")
|
||
df.index.name = "Datetime"
|
||
logger.debug(f"Fetched {len(df)} bars for {td_symbol} @ {interval}")
|
||
return df
|
||
|
||
except DataIntegrityError:
|
||
raise
|
||
except Exception as e:
|
||
logger.info(f"Twelve Data fetch failed for {symbol} ({e}), using synthetic data.")
|
||
return self._generate_synthetic_data(symbol, timeframe, lookback_days)
|
||
|
||
def _generate_synthetic_data(
|
||
self, symbol: str, timeframe: Timeframe, lookback_days: int
|
||
) -> pd.DataFrame:
|
||
"""
|
||
Generate realistic synthetic Forex OHLCV using GBM with mean-reversion.
|
||
Used as a fallback when live data is unavailable.
|
||
"""
|
||
pair_params = {
|
||
"EURUSD=X": {"price": 1.1350, "vol": 0.07, "drift": -0.001},
|
||
"GBPUSD=X": {"price": 1.3200, "vol": 0.08, "drift": 0.002},
|
||
"USDJPY=X": {"price": 144.50, "vol": 0.09, "drift": 0.003},
|
||
"USDCHF=X": {"price": 0.8850, "vol": 0.07, "drift": -0.001},
|
||
"AUDUSD=X": {"price": 0.6550, "vol": 0.10, "drift": -0.002},
|
||
"USDCAD=X": {"price": 1.3650, "vol": 0.07, "drift": 0.001},
|
||
"NZDUSD=X": {"price": 0.6100, "vol": 0.10, "drift": -0.001},
|
||
"EURGBP=X": {"price": 0.8590, "vol": 0.06, "drift": 0.000},
|
||
"EURJPY=X": {"price": 163.90, "vol": 0.09, "drift": 0.002},
|
||
"GBPJPY=X": {"price": 190.70, "vol": 0.11, "drift": 0.003},
|
||
"AUDJPY=X": {"price": 94.60, "vol": 0.11, "drift": 0.001},
|
||
"EURCHF=X": {"price": 0.9380, "vol": 0.05, "drift": 0.000},
|
||
"CADJPY=X": {"price": 105.80, "vol": 0.09, "drift": 0.001},
|
||
}
|
||
|
||
params = pair_params.get(symbol, {"price": 1.0000, "vol": 0.08, "drift": 0.000})
|
||
base_price = params["price"]
|
||
annual_vol = params["vol"]
|
||
annual_drift = params["drift"]
|
||
|
||
tf_minutes = {
|
||
Timeframe.M1: 1, Timeframe.M5: 5, Timeframe.M15: 15,
|
||
Timeframe.M30: 30, Timeframe.H1: 60, Timeframe.H4: 240,
|
||
Timeframe.D1: 1440, Timeframe.W1: 10080,
|
||
}
|
||
bar_minutes = tf_minutes.get(timeframe, 60)
|
||
bars_per_year = (365.25 * 24 * 60) / bar_minutes
|
||
dt = 1.0 / bars_per_year
|
||
|
||
n_bars = min(int(lookback_days * 24 * 60 / bar_minutes), 2000)
|
||
n_bars = max(n_bars, 300)
|
||
|
||
seed_base = int(hashlib.md5(symbol.encode()).hexdigest()[:8], 16)
|
||
time_component = int(time.time()) // 3600
|
||
np.random.seed((seed_base + time_component) % (2**31))
|
||
|
||
bar_vol = annual_vol * np.sqrt(dt)
|
||
bar_drift = annual_drift * dt
|
||
|
||
regime_len = np.random.randint(20, 80)
|
||
trend_strength = np.random.normal(0, 0.3)
|
||
|
||
price = base_price
|
||
prices = [price]
|
||
|
||
for i in range(1, n_bars):
|
||
if i % regime_len == 0:
|
||
regime_len = np.random.randint(20, 80)
|
||
trend_strength = np.random.normal(0, 0.3)
|
||
|
||
mr_force = -0.001 * (price - base_price) / base_price
|
||
ret = bar_drift + trend_strength * dt + mr_force + bar_vol * np.random.randn()
|
||
|
||
if np.random.random() < 0.02:
|
||
ret *= np.random.uniform(2.0, 4.0)
|
||
|
||
price *= (1 + ret)
|
||
prices.append(price)
|
||
|
||
prices = np.array(prices)
|
||
opens = np.roll(prices, 1)
|
||
opens[0] = prices[0]
|
||
|
||
typical_range = bar_vol * base_price * 1.5
|
||
highs = np.maximum(prices, opens) + np.abs(np.random.normal(0, typical_range * 0.6, n_bars))
|
||
lows = np.minimum(prices, opens) - np.abs(np.random.normal(0, typical_range * 0.6, n_bars))
|
||
highs = np.maximum(highs, np.maximum(opens, prices))
|
||
lows = np.minimum(lows, np.minimum(opens, prices))
|
||
|
||
volume = np.random.lognormal(mean=10, sigma=0.5, size=n_bars).astype(int)
|
||
|
||
freq_map = {
|
||
Timeframe.M1: "1min", Timeframe.M5: "5min",
|
||
Timeframe.M15: "15min", Timeframe.M30: "30min",
|
||
Timeframe.H1: "1h", Timeframe.H4: "4h",
|
||
Timeframe.D1: "D", Timeframe.W1: "W",
|
||
}
|
||
freq = freq_map.get(timeframe, "1h")
|
||
end_time = pd.Timestamp.now(tz="UTC").floor(f"{bar_minutes}min")
|
||
index = pd.date_range(end=end_time, periods=n_bars, freq=freq, tz="UTC")
|
||
|
||
df = pd.DataFrame({
|
||
"Open": opens, "High": highs, "Low": lows,
|
||
"Close": prices, "Volume": volume,
|
||
}, index=index)
|
||
df.index.name = "Datetime"
|
||
|
||
logger.info(
|
||
f"Generated {n_bars} synthetic {timeframe.value} bars for "
|
||
f"{SYMBOL_DISPLAY.get(symbol, symbol)} @ {prices[-1]:.5f}"
|
||
)
|
||
return df
|
||
|
||
def _validate_and_clean(
|
||
self, df: pd.DataFrame, symbol: str, timeframe: Timeframe
|
||
) -> pd.DataFrame:
|
||
"""
|
||
Validate and clean OHLCV data.
|
||
|
||
Steps: drop all-NaN rows → ffill small gaps → remove future timestamps
|
||
→ fix OHLC inconsistencies → remove >10-sigma outliers → sort & deduplicate.
|
||
"""
|
||
if df is None or df.empty:
|
||
raise DataIntegrityError(f"Empty dataset for {symbol}")
|
||
|
||
original_len = len(df)
|
||
|
||
df = df.dropna(subset=["Open", "High", "Low", "Close"], how="all")
|
||
df = df.ffill(limit=3)
|
||
df = df.dropna(subset=["Close"])
|
||
|
||
now = pd.Timestamp.utcnow()
|
||
future_mask = df.index > now + pd.Timedelta(minutes=5)
|
||
if future_mask.any():
|
||
logger.warning(f"{symbol}: Dropping {future_mask.sum()} future timestamps")
|
||
df = df[~future_mask]
|
||
|
||
invalid_ohlc = (
|
||
(df["High"] < df["Low"]) |
|
||
(df["High"] < df["Open"]) |
|
||
(df["High"] < df["Close"]) |
|
||
(df["Low"] > df["Open"]) |
|
||
(df["Low"] > df["Close"])
|
||
)
|
||
if invalid_ohlc.any():
|
||
logger.warning(f"{symbol}: Fixing {invalid_ohlc.sum()} OHLC-inconsistent bars")
|
||
for idx in df[invalid_ohlc].index:
|
||
vals = [df.loc[idx, "Open"], df.loc[idx, "Close"]]
|
||
df.loc[idx, "High"] = max(vals + [df.loc[idx, "High"]])
|
||
df.loc[idx, "Low"] = min(vals + [df.loc[idx, "Low"]])
|
||
|
||
returns = df["Close"].pct_change()
|
||
std_ret = returns.std()
|
||
if std_ret > 0:
|
||
outlier_mask = (returns - returns.mean()).abs() > 10 * std_ret
|
||
if outlier_mask.any():
|
||
logger.warning(f"{symbol}: Removing {outlier_mask.sum()} extreme outlier bars")
|
||
df = df[~outlier_mask]
|
||
|
||
min_required = max(
|
||
self.config.technical.ema_trend,
|
||
self.config.technical.ichimoku_senkou_b,
|
||
200,
|
||
) + 10
|
||
|
||
if len(df) < min_required:
|
||
logger.warning(
|
||
f"{symbol} {timeframe.value}: Only {len(df)} bars "
|
||
f"(need {min_required}). Some indicators will be partial."
|
||
)
|
||
|
||
df = df.sort_index()
|
||
df = df[~df.index.duplicated(keep="last")]
|
||
|
||
cleaned = original_len - len(df)
|
||
if cleaned > 0:
|
||
logger.info(f"{symbol}: Cleaned {cleaned}/{original_len} bars")
|
||
|
||
return df
|