Fixed code
This commit is contained in:
+294
-215
@@ -1,19 +1,21 @@
|
||||
"""
|
||||
Forex Signal Intelligence Platform - Data Provider
|
||||
====================================================
|
||||
Retrieves and validates market data from multiple sources.
|
||||
Uses Yahoo Finance as the free data backbone with integrity checks.
|
||||
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 datetime import datetime, timedelta
|
||||
from typing import Dict, List, Optional, Tuple
|
||||
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
|
||||
import yfinance as yf
|
||||
|
||||
from config import PlatformConfig, Timeframe, SYMBOL_DISPLAY
|
||||
|
||||
@@ -27,46 +29,61 @@ class DataIntegrityError(Exception):
|
||||
|
||||
class ForexDataProvider:
|
||||
"""
|
||||
Multi-source Forex data provider with validation.
|
||||
|
||||
Uses Yahoo Finance (free, no API key) as primary source.
|
||||
Implements data integrity checks to catch bad/stale data before
|
||||
it reaches the signal engine.
|
||||
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.
|
||||
"""
|
||||
|
||||
# Yahoo Finance timeframe mapping
|
||||
YF_INTERVALS = {
|
||||
Timeframe.M1: "1m",
|
||||
Timeframe.M5: "5m",
|
||||
Timeframe.M15: "15m",
|
||||
Timeframe.M30: "30m",
|
||||
Timeframe.H1: "60m",
|
||||
Timeframe.H4: "60m", # aggregate from H1
|
||||
Timeframe.D1: "1d",
|
||||
Timeframe.W1: "1wk",
|
||||
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",
|
||||
}
|
||||
|
||||
# Max lookback per interval (Yahoo limits)
|
||||
YF_MAX_RANGE = {
|
||||
Timeframe.M1: 7,
|
||||
Timeframe.M5: 60,
|
||||
Timeframe.M15: 60,
|
||||
Timeframe.M30: 60,
|
||||
Timeframe.H1: 730,
|
||||
Timeframe.H4: 730,
|
||||
Timeframe.D1: 3650,
|
||||
Timeframe.W1: 3650,
|
||||
# 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 API credits per minute (each symbol = 1 credit)
|
||||
RATE_LIMIT = 8
|
||||
RATE_WINDOW = 60.0
|
||||
|
||||
def __init__(self, config: PlatformConfig):
|
||||
self.config = config
|
||||
self._cache: Dict[str, Dict[str, pd.DataFrame]] = {}
|
||||
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 API credits used
|
||||
self._session = requests.Session()
|
||||
self._session.headers.update({
|
||||
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36"
|
||||
"User-Agent": "Mozilla/5.0 (compatible; ForexIntel/1.0)"
|
||||
})
|
||||
|
||||
@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,
|
||||
@@ -75,22 +92,16 @@ class ForexDataProvider:
|
||||
) -> pd.DataFrame:
|
||||
"""
|
||||
Fetch OHLCV data for a Forex pair with full validation.
|
||||
|
||||
|
||||
Returns a DataFrame with columns: Open, High, Low, Close, Volume
|
||||
Index is DatetimeIndex in UTC.
|
||||
|
||||
Raises DataIntegrityError if data is invalid/insufficient.
|
||||
Index is a timezone-aware DatetimeIndex in UTC.
|
||||
"""
|
||||
if lookback_days is None:
|
||||
lookback_days = min(
|
||||
self.config.data_lookback_days,
|
||||
self.YF_MAX_RANGE[timeframe],
|
||||
)
|
||||
lookback_days = self.config.data_lookback_days
|
||||
|
||||
cache_key = f"{symbol}_{timeframe.value}"
|
||||
now = time.time()
|
||||
|
||||
# Check cache (respect refresh interval)
|
||||
if (
|
||||
cache_key in self._cache_timestamps
|
||||
and (now - self._cache_timestamps[cache_key]) < self.config.refresh_interval
|
||||
@@ -100,21 +111,37 @@ class ForexDataProvider:
|
||||
if cached is not None and not cached.empty:
|
||||
return cached
|
||||
|
||||
df = self._fetch_yahoo(symbol, timeframe, lookback_days)
|
||||
|
||||
# If H4, resample from H1 data
|
||||
if timeframe == Timeframe.H4:
|
||||
df = self._resample_to_h4(df)
|
||||
|
||||
# Validate data integrity
|
||||
df = self._fetch_twelve_data(symbol, timeframe, lookback_days)
|
||||
df = self._validate_and_clean(df, symbol, timeframe)
|
||||
|
||||
# Cache it
|
||||
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],
|
||||
@@ -127,14 +154,12 @@ class ForexDataProvider:
|
||||
try:
|
||||
df = self.fetch_ohlcv(symbol, timeframe, lookback_days)
|
||||
results[symbol] = df
|
||||
time.sleep(0.3) # rate limit courtesy
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to fetch {symbol}: {e}")
|
||||
continue
|
||||
return results
|
||||
|
||||
def get_latest_price(self, symbol: str) -> Optional[float]:
|
||||
"""Get the most recent close price for a symbol."""
|
||||
"""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:
|
||||
@@ -144,20 +169,14 @@ class ForexDataProvider:
|
||||
return None
|
||||
|
||||
def get_spread_estimate(self, symbol: str) -> float:
|
||||
"""
|
||||
Estimate the typical spread for a pair based on recent data.
|
||||
Uses high-low range of 1-minute bars as a proxy.
|
||||
"""
|
||||
"""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:
|
||||
# Median range as spread estimate (conservative)
|
||||
ranges = df["High"] - df["Low"]
|
||||
return float(ranges.median())
|
||||
return float((df["High"] - df["Low"]).median())
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Fallback: typical spread estimates for majors
|
||||
fallback_spreads = {
|
||||
"EURUSD=X": 0.00010, "GBPUSD=X": 0.00015,
|
||||
"USDJPY=X": 0.010, "USDCHF=X": 0.00015,
|
||||
@@ -166,88 +185,220 @@ class ForexDataProvider:
|
||||
}
|
||||
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
|
||||
return {
|
||||
"symbol": symbol,
|
||||
"display": display,
|
||||
"pip_value": 0.01 if is_jpy else 0.0001,
|
||||
"is_jpy_pair": is_jpy,
|
||||
}
|
||||
|
||||
# ── Private Methods ────────────────────────────────────────────
|
||||
|
||||
def _fetch_yahoo(
|
||||
def _throttle(self, credits: int = 1) -> None:
|
||||
"""
|
||||
Block until `credits` API credits are available.
|
||||
|
||||
Twelve Data free tier: 8 credits/minute. Each symbol in any request
|
||||
(single or batch) consumes 1 credit. This method enforces the limit
|
||||
regardless of whether requests are batched or individual.
|
||||
"""
|
||||
while True:
|
||||
now = time.time()
|
||||
# Evict credits older than the rate window
|
||||
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:
|
||||
for _ in range(credits):
|
||||
self._request_times.append(time.time())
|
||||
return
|
||||
|
||||
# Wait until the oldest credit expires
|
||||
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
|
||||
self._throttle(credits=len(symbols))
|
||||
|
||||
resp = self._session.get(
|
||||
f"{self.TD_BASE_URL}/time_series",
|
||||
params={
|
||||
"symbol": ",".join(td_symbols),
|
||||
"interval": interval,
|
||||
"outputsize": outputsize,
|
||||
"apikey": self._api_key,
|
||||
"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:
|
||||
logger.warning(f"No values in batch response for {td_sym}")
|
||||
continue
|
||||
|
||||
records = [
|
||||
{
|
||||
"Datetime": pd.Timestamp(v["datetime"], tz="UTC"),
|
||||
"Open": float(v["open"]),
|
||||
"High": float(v["high"]),
|
||||
"Low": float(v["low"]),
|
||||
"Close": float(v["close"]),
|
||||
"Volume": float(v.get("volume") or 0),
|
||||
}
|
||||
for v in reversed(values)
|
||||
]
|
||||
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 raw OHLCV from Yahoo Finance via yfinance library.
|
||||
Falls back to realistic synthetic data if network unavailable."""
|
||||
interval = self.YF_INTERVALS[timeframe]
|
||||
period_map = {
|
||||
1: "1d", 2: "2d", 5: "5d", 7: "5d",
|
||||
30: "1mo", 60: "3mo", 90: "3mo",
|
||||
180: "6mo", 365: "1y", 730: "2y",
|
||||
}
|
||||
best_period = "3mo"
|
||||
for days, period in sorted(period_map.items()):
|
||||
if lookback_days <= days:
|
||||
best_period = period
|
||||
break
|
||||
"""
|
||||
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)
|
||||
|
||||
self._throttle(credits=1)
|
||||
|
||||
try:
|
||||
ticker = yf.Ticker(symbol)
|
||||
df = ticker.history(period=best_period, interval=interval)
|
||||
resp = self._session.get(
|
||||
f"{self.TD_BASE_URL}/time_series",
|
||||
params={
|
||||
"symbol": td_symbol,
|
||||
"interval": interval,
|
||||
"outputsize": outputsize,
|
||||
"apikey": self._api_key,
|
||||
"timezone": "UTC",
|
||||
"format": "json",
|
||||
},
|
||||
timeout=15,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
|
||||
if df is not None and not df.empty:
|
||||
# Standardize column names
|
||||
col_map = {}
|
||||
for col in df.columns:
|
||||
lower = col.lower()
|
||||
if lower == "open": col_map[col] = "Open"
|
||||
elif lower == "high": col_map[col] = "High"
|
||||
elif lower == "low": col_map[col] = "Low"
|
||||
elif lower == "close": col_map[col] = "Close"
|
||||
elif lower == "volume": col_map[col] = "Volume"
|
||||
df = df.rename(columns=col_map)
|
||||
if data.get("status") == "error":
|
||||
raise DataIntegrityError(
|
||||
f"Twelve Data API error for {td_symbol}: {data.get('message', 'unknown')}"
|
||||
)
|
||||
|
||||
for req in ["Open", "High", "Low", "Close"]:
|
||||
if req not in df.columns:
|
||||
raise DataIntegrityError(f"Missing {req} column for {symbol}")
|
||||
values = data.get("values")
|
||||
if not values:
|
||||
raise DataIntegrityError(f"Empty response from Twelve Data for {td_symbol}")
|
||||
|
||||
if "Volume" not in df.columns:
|
||||
df["Volume"] = 0
|
||||
# Values arrive newest-first; reverse to chronological order
|
||||
records = [
|
||||
{
|
||||
"Datetime": pd.Timestamp(v["datetime"], tz="UTC"),
|
||||
"Open": float(v["open"]),
|
||||
"High": float(v["high"]),
|
||||
"Low": float(v["low"]),
|
||||
"Close": float(v["close"]),
|
||||
"Volume": float(v.get("volume") or 0),
|
||||
}
|
||||
for v in reversed(values)
|
||||
]
|
||||
|
||||
if df.index.tz is None:
|
||||
df.index = df.index.tz_localize("UTC")
|
||||
else:
|
||||
df.index = df.index.tz_convert("UTC")
|
||||
df = pd.DataFrame(records).set_index("Datetime")
|
||||
df.index.name = "Datetime"
|
||||
logger.debug(f"Fetched {len(df)} bars for {td_symbol} @ {interval}")
|
||||
return df
|
||||
|
||||
df.index.name = "Datetime"
|
||||
df = df[["Open", "High", "Low", "Close", "Volume"]]
|
||||
return df
|
||||
except DataIntegrityError:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.info(f"Live data unavailable for {symbol}, using synthetic: {e}")
|
||||
|
||||
# ── Fallback: Realistic synthetic Forex data ───────────────
|
||||
return self._generate_synthetic_data(symbol, timeframe, lookback_days)
|
||||
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 data.
|
||||
|
||||
Uses GBM (Geometric Brownian Motion) with mean-reversion,
|
||||
realistic volatility per pair, and proper OHLC construction.
|
||||
This ensures the technical engine produces meaningful signals
|
||||
even without live data.
|
||||
Generate realistic synthetic Forex OHLCV using GBM with mean-reversion.
|
||||
Used as a fallback when live data is unavailable.
|
||||
"""
|
||||
# Realistic base prices and volatilities (annualized) for major pairs
|
||||
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},
|
||||
"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},
|
||||
"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},
|
||||
"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})
|
||||
@@ -255,7 +406,6 @@ class ForexDataProvider:
|
||||
annual_vol = params["vol"]
|
||||
annual_drift = params["drift"]
|
||||
|
||||
# Calculate bar parameters
|
||||
tf_minutes = {
|
||||
Timeframe.M1: 1, Timeframe.M5: 5, Timeframe.M15: 15,
|
||||
Timeframe.M30: 30, Timeframe.H1: 60, Timeframe.H4: 240,
|
||||
@@ -266,40 +416,29 @@ class ForexDataProvider:
|
||||
dt = 1.0 / bars_per_year
|
||||
|
||||
n_bars = min(int(lookback_days * 24 * 60 / bar_minutes), 2000)
|
||||
n_bars = max(n_bars, 300) # minimum for indicators
|
||||
n_bars = max(n_bars, 300)
|
||||
|
||||
# Use a seed based on symbol for reproducibility within a session
|
||||
# but add time-based component so it changes between runs
|
||||
import hashlib
|
||||
seed_base = int(hashlib.md5(symbol.encode()).hexdigest()[:8], 16)
|
||||
time_component = int(time.time()) // 3600 # changes hourly
|
||||
time_component = int(time.time()) // 3600
|
||||
np.random.seed((seed_base + time_component) % (2**31))
|
||||
|
||||
# Generate returns using GBM with mean reversion
|
||||
bar_vol = annual_vol * np.sqrt(dt)
|
||||
bar_drift = annual_drift * dt
|
||||
|
||||
# Add trending behavior (occasional trends + mean reversion)
|
||||
regime_len = np.random.randint(20, 80)
|
||||
trend_strength = np.random.normal(0, 0.3)
|
||||
|
||||
returns = np.zeros(n_bars)
|
||||
|
||||
price = base_price
|
||||
prices = [price]
|
||||
|
||||
for i in range(1, n_bars):
|
||||
# Regime changes
|
||||
if i % regime_len == 0:
|
||||
regime_len = np.random.randint(20, 80)
|
||||
trend_strength = np.random.normal(0, 0.3)
|
||||
|
||||
# Mean reversion component
|
||||
mr_force = -0.001 * (price - base_price) / base_price
|
||||
|
||||
# Combined return
|
||||
ret = bar_drift + trend_strength * dt + mr_force + bar_vol * np.random.randn()
|
||||
|
||||
# Occasional volatility spikes (simulates news events)
|
||||
|
||||
if np.random.random() < 0.02:
|
||||
ret *= np.random.uniform(2.0, 4.0)
|
||||
|
||||
@@ -307,101 +446,63 @@ class ForexDataProvider:
|
||||
prices.append(price)
|
||||
|
||||
prices = np.array(prices)
|
||||
|
||||
# Construct OHLC from close prices
|
||||
opens = np.roll(prices, 1)
|
||||
opens[0] = prices[0]
|
||||
|
||||
# Realistic High/Low generation
|
||||
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))
|
||||
|
||||
# Ensure OHLC consistency
|
||||
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))
|
||||
lows = np.minimum(lows, np.minimum(opens, prices))
|
||||
|
||||
# Volume (tick volume approximation)
|
||||
base_vol = np.random.lognormal(mean=10, sigma=0.5, size=n_bars)
|
||||
# Higher volume during London/NY overlap hours
|
||||
volume = base_vol.astype(int)
|
||||
volume = np.random.lognormal(mean=10, sigma=0.5, size=n_bars).astype(int)
|
||||
|
||||
# Generate timestamps
|
||||
end_time = pd.Timestamp.now(tz="UTC").floor(f"{bar_minutes}min")
|
||||
freq_map = {
|
||||
Timeframe.M1: "1min", Timeframe.M5: "5min",
|
||||
Timeframe.M1: "1min", Timeframe.M5: "5min",
|
||||
Timeframe.M15: "15min", Timeframe.M30: "30min",
|
||||
Timeframe.H1: "1h", Timeframe.H4: "4h",
|
||||
Timeframe.D1: "1D", Timeframe.W1: "1W",
|
||||
Timeframe.H1: "1h", Timeframe.H4: "4h",
|
||||
Timeframe.D1: "D", Timeframe.W1: "W",
|
||||
}
|
||||
freq = freq_map.get(timeframe, "1h")
|
||||
|
||||
# Create business-hours aware index
|
||||
index = pd.date_range(
|
||||
end=end_time, periods=n_bars, freq=freq, tz="UTC"
|
||||
)
|
||||
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,
|
||||
"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 _resample_to_h4(self, df: pd.DataFrame) -> pd.DataFrame:
|
||||
"""Resample H1 data to H4 candles."""
|
||||
resampled = df.resample("4h").agg({
|
||||
"Open": "first",
|
||||
"High": "max",
|
||||
"Low": "min",
|
||||
"Close": "last",
|
||||
"Volume": "sum",
|
||||
}).dropna()
|
||||
return resampled
|
||||
|
||||
def _validate_and_clean(
|
||||
self, df: pd.DataFrame, symbol: str, timeframe: Timeframe
|
||||
) -> pd.DataFrame:
|
||||
"""
|
||||
Comprehensive data validation and cleaning.
|
||||
|
||||
Checks:
|
||||
1. Sufficient data points for indicator calculation
|
||||
2. No future timestamps
|
||||
3. OHLC logical consistency (High >= Low, etc.)
|
||||
4. No extreme outliers (>10 sigma moves in a single bar)
|
||||
5. Forward-fill small gaps, reject large ones
|
||||
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)
|
||||
|
||||
# 1. Drop rows with all NaN OHLC
|
||||
df = df.dropna(subset=["Open", "High", "Low", "Close"], how="all")
|
||||
|
||||
# 2. Forward-fill small gaps (up to 3 consecutive NaN bars)
|
||||
df = df.ffill(limit=3)
|
||||
df = df.dropna(subset=["Close"])
|
||||
|
||||
# 3. No future timestamps
|
||||
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]
|
||||
|
||||
# 4. OHLC logical consistency
|
||||
invalid_ohlc = (
|
||||
(df["High"] < df["Low"]) |
|
||||
(df["High"] < df["Open"]) |
|
||||
@@ -410,31 +511,25 @@ class ForexDataProvider:
|
||||
(df["Low"] > df["Close"])
|
||||
)
|
||||
if invalid_ohlc.any():
|
||||
count = invalid_ohlc.sum()
|
||||
logger.warning(f"{symbol}: Fixing {count} OHLC-inconsistent bars")
|
||||
# Fix by recalculating High/Low from OHLC
|
||||
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"]])
|
||||
df.loc[idx, "Low"] = min(vals + [df.loc[idx, "Low"]])
|
||||
|
||||
# 5. Outlier detection (>10 sigma single-bar return)
|
||||
returns = df["Close"].pct_change()
|
||||
mean_ret = returns.mean()
|
||||
std_ret = returns.std()
|
||||
if std_ret > 0:
|
||||
outlier_mask = (returns - mean_ret).abs() > 10 * std_ret
|
||||
outlier_mask = (returns - returns.mean()).abs() > 10 * std_ret
|
||||
if outlier_mask.any():
|
||||
count = outlier_mask.sum()
|
||||
logger.warning(f"{symbol}: Removing {count} extreme outlier bars")
|
||||
logger.warning(f"{symbol}: Removing {outlier_mask.sum()} extreme outlier bars")
|
||||
df = df[~outlier_mask]
|
||||
|
||||
# 6. Minimum data check
|
||||
min_required = max(
|
||||
self.config.technical.ema_trend,
|
||||
self.config.technical.ichimoku_senkou_b,
|
||||
200,
|
||||
) + 10 # buffer
|
||||
) + 10
|
||||
|
||||
if len(df) < min_required:
|
||||
logger.warning(
|
||||
@@ -442,10 +537,7 @@ class ForexDataProvider:
|
||||
f"(need {min_required}). Some indicators will be partial."
|
||||
)
|
||||
|
||||
# 7. Sort by time (paranoia check)
|
||||
df = df.sort_index()
|
||||
|
||||
# 8. Remove duplicate timestamps
|
||||
df = df[~df.index.duplicated(keep="last")]
|
||||
|
||||
cleaned = original_len - len(df)
|
||||
@@ -453,16 +545,3 @@ class ForexDataProvider:
|
||||
logger.info(f"{symbol}: Cleaned {cleaned}/{original_len} bars")
|
||||
|
||||
return df
|
||||
|
||||
def get_pair_info(self, symbol: str) -> Dict:
|
||||
"""Get display name and pip value for a pair."""
|
||||
display = SYMBOL_DISPLAY.get(symbol, symbol)
|
||||
# JPY pairs have 2 decimal places, others have 4-5
|
||||
is_jpy = "JPY" in symbol
|
||||
pip_value = 0.01 if is_jpy else 0.0001
|
||||
return {
|
||||
"symbol": symbol,
|
||||
"display": display,
|
||||
"pip_value": pip_value,
|
||||
"is_jpy_pair": is_jpy,
|
||||
}
|
||||
Reference in New Issue
Block a user