Spaces:
Paused
Paused
Update ml_engine/data_manager.py
Browse files- ml_engine/data_manager.py +92 -97
ml_engine/data_manager.py
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
# ============================================================
|
| 2 |
# 📂 ml_engine/data_manager.py
|
| 3 |
-
# (
|
| 4 |
# ============================================================
|
| 5 |
|
| 6 |
import asyncio
|
|
@@ -10,6 +10,7 @@ import logging
|
|
| 10 |
import pandas as pd
|
| 11 |
import numpy as np
|
| 12 |
import pandas_ta as ta
|
|
|
|
| 13 |
from typing import List, Dict, Any
|
| 14 |
|
| 15 |
import ccxt.async_support as ccxt
|
|
@@ -28,9 +29,9 @@ logging.getLogger("ccxt").setLevel(logging.WARNING)
|
|
| 28 |
|
| 29 |
class DataManager:
|
| 30 |
"""
|
| 31 |
-
DataManager
|
| 32 |
-
-
|
| 33 |
-
-
|
| 34 |
"""
|
| 35 |
|
| 36 |
def __init__(self, contracts_db, whale_monitor, r2_service=None):
|
|
@@ -47,13 +48,13 @@ class DataManager:
|
|
| 47 |
self.http_client = None
|
| 48 |
self.market_cache = {}
|
| 49 |
|
| 50 |
-
# قائمة سوداء
|
| 51 |
self.BLACKLIST_TOKENS = [
|
| 52 |
'USDT', 'USDC', 'DAI', 'TUSD', 'BUSD', 'FDUSD', 'EUR', 'PAX',
|
| 53 |
-
'UP', 'DOWN', 'BEAR', 'BULL', '3S', '3L', 'USDD', 'USDP', 'HT', 'KCS'
|
| 54 |
]
|
| 55 |
|
| 56 |
-
print(f"📦 [DataManager
|
| 57 |
|
| 58 |
async def initialize(self):
|
| 59 |
print(" > [DataManager] Starting initialization...")
|
|
@@ -85,52 +86,60 @@ class DataManager:
|
|
| 85 |
def get_contracts_db(self): return self.contracts_db
|
| 86 |
|
| 87 |
# ==================================================================
|
| 88 |
-
# 🛡️ Layer 1: The Titan Mirror Filter (
|
| 89 |
# ==================================================================
|
| 90 |
async def layer1_rapid_screening(self) -> List[Dict[str, Any]]:
|
| 91 |
"""
|
| 92 |
-
|
| 93 |
-
يجهز الساحة لنماذج Titan و Sniper.
|
| 94 |
"""
|
| 95 |
current_regime = getattr(SystemLimits, "CURRENT_REGIME", "RANGE")
|
| 96 |
min_score = getattr(SystemLimits, "L1_MIN_AFFINITY_SCORE", 15.0)
|
| 97 |
|
| 98 |
-
print(f"🔍 [L1
|
| 99 |
|
| 100 |
-
# 1. جلب Universe (تصفية أولية
|
| 101 |
-
#
|
| 102 |
-
|
| 103 |
-
|
|
|
|
|
|
|
| 104 |
|
| 105 |
if not all_tickers:
|
| 106 |
print("⚠️ [Layer 1] Universe fetch returned empty.")
|
| 107 |
return []
|
| 108 |
|
| 109 |
-
# 2. الجلب العميق (Deep Fetch) ل
|
| 110 |
-
# ن
|
| 111 |
-
|
| 112 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 113 |
|
| 114 |
scored_candidates = []
|
| 115 |
|
| 116 |
for item in enriched_data:
|
| 117 |
df = item.get('df')
|
| 118 |
-
if df is None or len(df) < 150: continue
|
| 119 |
|
| 120 |
-
#
|
| 121 |
structural_score, reasons = self._calculate_structural_score(df, item['symbol'], current_regime)
|
| 122 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
item['l1_score'] = structural_score
|
| 124 |
item['type'] = " | ".join(reasons)
|
| 125 |
|
| 126 |
-
# الفلتر يقبل فقط العملات ذات الهيكلية السليمة
|
| 127 |
if structural_score >= min_score:
|
| 128 |
scored_candidates.append(item)
|
| 129 |
|
| 130 |
-
# الترتيب حسب
|
| 131 |
scored_candidates.sort(key=lambda x: x['l1_score'], reverse=True)
|
| 132 |
|
| 133 |
-
print(f" ->
|
| 134 |
|
| 135 |
return [
|
| 136 |
{
|
|
@@ -140,111 +149,81 @@ class DataManager:
|
|
| 140 |
'type': c.get('type', 'Structural'),
|
| 141 |
'l1_score': c.get('l1_score', 0)
|
| 142 |
}
|
| 143 |
-
for c in scored_candidates[:
|
| 144 |
]
|
| 145 |
|
| 146 |
# ==================================================================
|
| 147 |
-
# 🧬 Structural Alignment Engine
|
| 148 |
# ==================================================================
|
| 149 |
def _calculate_structural_score(self, df: pd.DataFrame, symbol: str, regime: str) -> (float, List[str]):
|
| 150 |
-
|
| 151 |
-
يحسب درجة توافق العملة مع متطلبات نماذج التعلم الآلي.
|
| 152 |
-
"""
|
| 153 |
score = 0.0
|
| 154 |
tags = []
|
| 155 |
-
|
| 156 |
try:
|
| 157 |
-
# 1. Data Prep
|
| 158 |
close = df['close']
|
| 159 |
high = df['high']
|
| 160 |
low = df['low']
|
| 161 |
volume = df['volume']
|
| 162 |
current_price = close.iloc[-1]
|
| 163 |
|
| 164 |
-
# --- Check A: Liquidity Quality (Anti-Sniper Failure) ---
|
| 165 |
-
# فحص "جودة الشموع": هل هناك الكثير من الشموع الصفرية أو الفجوات؟
|
| 166 |
zero_vol_candles = (volume == 0).sum()
|
| 167 |
-
if zero_vol_candles > 5: return -100.0, ["Illiquid"]
|
| 168 |
|
| 169 |
avg_vol = volume.rolling(20).mean().iloc[-1]
|
| 170 |
-
if avg_vol * current_price < 5000: return -100.0, ["Thin Book"]
|
| 171 |
|
| 172 |
-
# --- Check B: Trend Alignment (Titan EMA Feature) ---
|
| 173 |
-
# Titan يعتمد بشكل كبير على المسافة من EMA
|
| 174 |
ema200 = ta.ema(close, length=200)
|
| 175 |
ema50 = ta.ema(close, length=50)
|
| 176 |
|
| 177 |
if ema200 is not None and ema50 is not None:
|
| 178 |
curr_ema200 = ema200.iloc[-1]
|
| 179 |
-
curr_ema50 = ema50.iloc[-1]
|
| 180 |
-
|
| 181 |
-
# في السوق الصاعد، نريد السعر فوق المتوسطات ولكن ليس بعيداً جداً (Overextended)
|
| 182 |
dist_200 = (current_price - curr_ema200) / curr_ema200
|
| 183 |
|
| 184 |
if regime == "BULL":
|
| 185 |
if current_price > curr_ema200:
|
| 186 |
score += 20
|
| 187 |
-
if current_price >
|
| 188 |
-
if dist_200 < 0.15: score += 10
|
| 189 |
-
else: score -= 5
|
| 190 |
-
else:
|
| 191 |
-
score -= 20 # تحت التريند العام
|
| 192 |
elif regime == "BEAR":
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
if abs(dist_200) < 0.05: score += 20 # يتذبذب حول المتوسط
|
| 197 |
|
| 198 |
-
# --- Check C: Volatility Structure (Titan BB Feature) ---
|
| 199 |
bb = ta.bbands(close, length=20, std=2)
|
| 200 |
if bb is not None:
|
| 201 |
-
#
|
| 202 |
-
upper = bb[bb.columns[0]] #
|
| 203 |
-
lower = bb[bb.columns[2]] # Upper
|
| 204 |
-
#
|
| 205 |
-
#
|
| 206 |
-
|
| 207 |
-
|
| 208 |
-
|
| 209 |
-
|
| 210 |
-
|
| 211 |
-
score
|
| 212 |
-
tags.append("Squeeze")
|
| 213 |
-
elif current_width > 0.15: # متقلب جداً
|
| 214 |
-
score -= 10 # قد يكون فات الأوان
|
| 215 |
|
| 216 |
-
# --- Check D: Momentum Integrity (RSI/ADX) ---
|
| 217 |
rsi = ta.rsi(close, length=14).iloc[-1]
|
| 218 |
adx = ta.adx(high, low, close, length=14)
|
| 219 |
curr_adx = adx.iloc[-1, 0] if adx is not None else 0
|
| 220 |
|
| 221 |
-
if 40 < rsi < 70:
|
| 222 |
-
|
| 223 |
-
elif rsi > 75 and regime == "BULL":
|
| 224 |
-
score += 10 # زخم قوي
|
| 225 |
-
elif rsi < 30 and regime == "BEAR":
|
| 226 |
-
score += 10 # ذروة بيع
|
| 227 |
|
| 228 |
-
if curr_adx > 25:
|
| 229 |
-
score += 10 # يوجد تريند حقيقي
|
| 230 |
-
tags.append("Trending")
|
| 231 |
|
| 232 |
-
# --- Check E: Volume Flow (Sniper Confirmation) ---
|
| 233 |
vol_sma = volume.rolling(20).mean().iloc[-1]
|
| 234 |
-
if volume.iloc[-1] > vol_sma * 1.5:
|
| 235 |
-
score += 15
|
| 236 |
-
tags.append("Vol Spike")
|
| 237 |
-
|
| 238 |
-
except Exception as e:
|
| 239 |
-
# print(f"⚠️ [Struct calc error] {symbol}: {e}")
|
| 240 |
-
return 0.0, ["Error"]
|
| 241 |
|
|
|
|
| 242 |
return score, tags
|
| 243 |
|
| 244 |
# ==================================================================
|
| 245 |
-
# 🌍 Universe & Batch Fetch (
|
| 246 |
# ==================================================================
|
| 247 |
-
async def _fetch_universe_tickers(self, min_volume=
|
| 248 |
try:
|
| 249 |
tickers = await self.exchange.fetch_tickers()
|
| 250 |
candidates = []
|
|
@@ -252,34 +231,51 @@ class DataManager:
|
|
| 252 |
for symbol, ticker in tickers.items():
|
| 253 |
if not symbol.endswith('/USDT'): continue
|
| 254 |
|
| 255 |
-
# تصفية العملات المحظورة
|
| 256 |
base_currency = symbol.split('/')[0]
|
| 257 |
if any(bad in base_currency for bad in self.BLACKLIST_TOKENS): continue
|
| 258 |
-
if "3S" in base_currency or "3L" in base_currency: continue
|
| 259 |
|
| 260 |
vol = ticker.get('quoteVolume')
|
| 261 |
if vol is None: vol = ticker.get('info', {}).get('volValue')
|
| 262 |
if vol is None: vol = 0.0
|
| 263 |
else: vol = float(vol)
|
| 264 |
|
|
|
|
| 265 |
if vol < min_volume: continue
|
| 266 |
|
| 267 |
-
# فلتر السبريد (
|
| 268 |
bid = float(ticker.get('bid', 0) or 0)
|
| 269 |
ask = float(ticker.get('ask', 0) or 0)
|
| 270 |
if bid > 0 and ask > 0:
|
| 271 |
spread_pct = (ask - bid) / bid
|
| 272 |
-
if spread_pct > 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 273 |
|
| 274 |
candidates.append({
|
| 275 |
'symbol': symbol,
|
| 276 |
'quote_volume': vol,
|
| 277 |
'current_price': float(ticker['last']) if ticker.get('last') else 0.0,
|
| 278 |
-
'change_24h':
|
|
|
|
| 279 |
})
|
| 280 |
|
| 281 |
-
# الترتيب حسب الس
|
| 282 |
-
candidates.sort(key=lambda x: x['
|
|
|
|
| 283 |
return candidates
|
| 284 |
|
| 285 |
except Exception as e:
|
|
@@ -288,13 +284,12 @@ class DataManager:
|
|
| 288 |
|
| 289 |
async def _batch_fetch_ta_data(self, candidates, timeframe='15m', limit=200):
|
| 290 |
results = []
|
| 291 |
-
chunk_size = 20
|
| 292 |
for i in range(0, len(candidates), chunk_size):
|
| 293 |
chunk = candidates[i:i+chunk_size]
|
| 294 |
tasks = [self._fetch_ohlcv_safe(c, timeframe, limit) for c in chunk]
|
| 295 |
chunk_res = await asyncio.gather(*tasks)
|
| 296 |
results.extend([r for r in chunk_res if r is not None])
|
| 297 |
-
# تأخير بسيط جداً لتجنب حظر API
|
| 298 |
await asyncio.sleep(0.05)
|
| 299 |
return results
|
| 300 |
|
|
@@ -303,10 +298,10 @@ class DataManager:
|
|
| 303 |
ohlcv = await self.exchange.fetch_ohlcv(candidate['symbol'], tf, limit=limit)
|
| 304 |
if not ohlcv: return None
|
| 305 |
df = pd.DataFrame(ohlcv, columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])
|
| 306 |
-
|
| 307 |
-
|
| 308 |
-
df[
|
| 309 |
-
|
| 310 |
candidate['df'] = df
|
| 311 |
return candidate
|
| 312 |
except: return None
|
|
|
|
| 1 |
# ============================================================
|
| 2 |
# 📂 ml_engine/data_manager.py
|
| 3 |
+
# (V43.0 - GEM-Architect: Hot-Flow Sort)
|
| 4 |
# ============================================================
|
| 5 |
|
| 6 |
import asyncio
|
|
|
|
| 10 |
import pandas as pd
|
| 11 |
import numpy as np
|
| 12 |
import pandas_ta as ta
|
| 13 |
+
import math # ✅ مكتبة مهمة للمعادلة اللوغاريتمية
|
| 14 |
from typing import List, Dict, Any
|
| 15 |
|
| 16 |
import ccxt.async_support as ccxt
|
|
|
|
| 29 |
|
| 30 |
class DataManager:
|
| 31 |
"""
|
| 32 |
+
DataManager V43.0 (Hot-Flow Sort)
|
| 33 |
+
- Replaced 'Raw Volume' sort with 'Volume-Weighted Momentum'.
|
| 34 |
+
- Prioritizes active mid-caps over stagnant giants (XRP, TRX, BNB).
|
| 35 |
"""
|
| 36 |
|
| 37 |
def __init__(self, contracts_db, whale_monitor, r2_service=None):
|
|
|
|
| 48 |
self.http_client = None
|
| 49 |
self.market_cache = {}
|
| 50 |
|
| 51 |
+
# القائمة السوداء
|
| 52 |
self.BLACKLIST_TOKENS = [
|
| 53 |
'USDT', 'USDC', 'DAI', 'TUSD', 'BUSD', 'FDUSD', 'EUR', 'PAX',
|
| 54 |
+
'UP', 'DOWN', 'BEAR', 'BULL', '3S', '3L', 'USDD', 'USDP', 'HT', 'KCS', 'WBTC'
|
| 55 |
]
|
| 56 |
|
| 57 |
+
print(f"📦 [DataManager V43.0] Hot-Flow Engine Online.")
|
| 58 |
|
| 59 |
async def initialize(self):
|
| 60 |
print(" > [DataManager] Starting initialization...")
|
|
|
|
| 86 |
def get_contracts_db(self): return self.contracts_db
|
| 87 |
|
| 88 |
# ==================================================================
|
| 89 |
+
# 🛡️ Layer 1: The Titan Mirror Filter (Hot-Flow Edition)
|
| 90 |
# ==================================================================
|
| 91 |
async def layer1_rapid_screening(self) -> List[Dict[str, Any]]:
|
| 92 |
"""
|
| 93 |
+
يقوم بفرز العملات بناءً على "السخونة" (Hotness) وليس الحجم فقط.
|
|
|
|
| 94 |
"""
|
| 95 |
current_regime = getattr(SystemLimits, "CURRENT_REGIME", "RANGE")
|
| 96 |
min_score = getattr(SystemLimits, "L1_MIN_AFFINITY_SCORE", 15.0)
|
| 97 |
|
| 98 |
+
print(f"🔍 [L1 Hot-Flow] Scanning for Active Momentum (Regime: {current_regime})...")
|
| 99 |
|
| 100 |
+
# 1. جلب Universe (تصفية أولية)
|
| 101 |
+
# خفضنا الحد الأدنى للحجم للسماح للعملات المتوسطة "الساخنة" بالدخول
|
| 102 |
+
# في السابق كان الرقم مرتفعاً جداً مما يقتل الفرص
|
| 103 |
+
min_vol_floor = 1000000 if current_regime == "BEAR" else 5000000
|
| 104 |
+
|
| 105 |
+
all_tickers = await self._fetch_universe_tickers(min_volume=min_vol_floor)
|
| 106 |
|
| 107 |
if not all_tickers:
|
| 108 |
print("⚠️ [Layer 1] Universe fetch returned empty.")
|
| 109 |
return []
|
| 110 |
|
| 111 |
+
# 2. الجلب العميق (Deep Fetch) لأكثر العملات سخونة
|
| 112 |
+
# نأخذ أفضل 150 عملة بناءً على معادلة (الحجم × الحركة)
|
| 113 |
+
scan_limit = 150
|
| 114 |
+
top_candidates = all_tickers[:scan_limit]
|
| 115 |
+
|
| 116 |
+
print(f" -> Deep scanning top {len(top_candidates)} active assets...")
|
| 117 |
+
|
| 118 |
+
enriched_data = await self._batch_fetch_ta_data(top_candidates, timeframe='15m', limit=200)
|
| 119 |
|
| 120 |
scored_candidates = []
|
| 121 |
|
| 122 |
for item in enriched_data:
|
| 123 |
df = item.get('df')
|
| 124 |
+
if df is None or len(df) < 150: continue
|
| 125 |
|
| 126 |
+
# تطبيق فلتر المرآة الهيكلية
|
| 127 |
structural_score, reasons = self._calculate_structural_score(df, item['symbol'], current_regime)
|
| 128 |
|
| 129 |
+
# 🔥 Bonus: إضافة نقاط إضافية للعملات الساخنة جداً
|
| 130 |
+
hot_score = item.get('hot_score', 0)
|
| 131 |
+
if hot_score > 50: structural_score += 5 # Boost for super active coins
|
| 132 |
+
|
| 133 |
item['l1_score'] = structural_score
|
| 134 |
item['type'] = " | ".join(reasons)
|
| 135 |
|
|
|
|
| 136 |
if structural_score >= min_score:
|
| 137 |
scored_candidates.append(item)
|
| 138 |
|
| 139 |
+
# الترتيب النهائي حسب جودة الهيكل
|
| 140 |
scored_candidates.sort(key=lambda x: x['l1_score'], reverse=True)
|
| 141 |
|
| 142 |
+
print(f" -> Filter selected {len(scored_candidates)} candidates.")
|
| 143 |
|
| 144 |
return [
|
| 145 |
{
|
|
|
|
| 149 |
'type': c.get('type', 'Structural'),
|
| 150 |
'l1_score': c.get('l1_score', 0)
|
| 151 |
}
|
| 152 |
+
for c in scored_candidates[:30]
|
| 153 |
]
|
| 154 |
|
| 155 |
# ==================================================================
|
| 156 |
+
# 🧬 Structural Alignment Engine
|
| 157 |
# ==================================================================
|
| 158 |
def _calculate_structural_score(self, df: pd.DataFrame, symbol: str, regime: str) -> (float, List[str]):
|
| 159 |
+
# (نفس منطق الفلتر الهيكلي السابق - لم يتغير لأنه ممتاز)
|
|
|
|
|
|
|
| 160 |
score = 0.0
|
| 161 |
tags = []
|
|
|
|
| 162 |
try:
|
|
|
|
| 163 |
close = df['close']
|
| 164 |
high = df['high']
|
| 165 |
low = df['low']
|
| 166 |
volume = df['volume']
|
| 167 |
current_price = close.iloc[-1]
|
| 168 |
|
|
|
|
|
|
|
| 169 |
zero_vol_candles = (volume == 0).sum()
|
| 170 |
+
if zero_vol_candles > 5: return -100.0, ["Illiquid"]
|
| 171 |
|
| 172 |
avg_vol = volume.rolling(20).mean().iloc[-1]
|
| 173 |
+
if avg_vol * current_price < 5000: return -100.0, ["Thin Book"]
|
| 174 |
|
|
|
|
|
|
|
| 175 |
ema200 = ta.ema(close, length=200)
|
| 176 |
ema50 = ta.ema(close, length=50)
|
| 177 |
|
| 178 |
if ema200 is not None and ema50 is not None:
|
| 179 |
curr_ema200 = ema200.iloc[-1]
|
|
|
|
|
|
|
|
|
|
| 180 |
dist_200 = (current_price - curr_ema200) / curr_ema200
|
| 181 |
|
| 182 |
if regime == "BULL":
|
| 183 |
if current_price > curr_ema200:
|
| 184 |
score += 20
|
| 185 |
+
if current_price > ema50.iloc[-1]: score += 10
|
| 186 |
+
if dist_200 < 0.15: score += 10
|
| 187 |
+
else: score -= 5
|
| 188 |
+
else: score -= 20
|
|
|
|
| 189 |
elif regime == "BEAR":
|
| 190 |
+
if dist_200 < -0.20: score += 30
|
| 191 |
+
else:
|
| 192 |
+
if abs(dist_200) < 0.05: score += 20
|
|
|
|
| 193 |
|
|
|
|
| 194 |
bb = ta.bbands(close, length=20, std=2)
|
| 195 |
if bb is not None:
|
| 196 |
+
# حساب الـ Bandwidth يدوياً للأمان
|
| 197 |
+
upper = bb[bb.columns[0]] # Lower band usually index 0 in pandas_ta default
|
| 198 |
+
lower = bb[bb.columns[2]] # Upper band
|
| 199 |
+
# نستخدم أسماء الأعمدة إذا أمكن للتأكد، ولكن للسرعة:
|
| 200 |
+
# pandas_ta returns: Lower, Mid, Upper, Bandwidth, Percent
|
| 201 |
+
# لنتأكد من الـ Bandwidth مباشرة
|
| 202 |
+
width_col = next((c for c in bb.columns if c.startswith('BBB')), None)
|
| 203 |
+
if width_col:
|
| 204 |
+
current_width = bb[width_col].iloc[-1] / 100.0 # pandas_ta returns pct
|
| 205 |
+
if current_width < 0.05: score += 25; tags.append("Squeeze")
|
| 206 |
+
elif current_width > 0.15: score -= 10
|
|
|
|
|
|
|
|
|
|
| 207 |
|
|
|
|
| 208 |
rsi = ta.rsi(close, length=14).iloc[-1]
|
| 209 |
adx = ta.adx(high, low, close, length=14)
|
| 210 |
curr_adx = adx.iloc[-1, 0] if adx is not None else 0
|
| 211 |
|
| 212 |
+
if 40 < rsi < 70: score += 15
|
| 213 |
+
elif rsi > 75 and regime == "BULL": score += 10
|
|
|
|
|
|
|
|
|
|
|
|
|
| 214 |
|
| 215 |
+
if curr_adx > 25: score += 10; tags.append("Trending")
|
|
|
|
|
|
|
| 216 |
|
|
|
|
| 217 |
vol_sma = volume.rolling(20).mean().iloc[-1]
|
| 218 |
+
if volume.iloc[-1] > vol_sma * 1.5: score += 15; tags.append("Vol Spike")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 219 |
|
| 220 |
+
except Exception as e: return 0.0, ["Error"]
|
| 221 |
return score, tags
|
| 222 |
|
| 223 |
# ==================================================================
|
| 224 |
+
# 🌍 Universe & Batch Fetch (The Hot-Flow Logic)
|
| 225 |
# ==================================================================
|
| 226 |
+
async def _fetch_universe_tickers(self, min_volume=300_000) -> List[Dict[str, Any]]:
|
| 227 |
try:
|
| 228 |
tickers = await self.exchange.fetch_tickers()
|
| 229 |
candidates = []
|
|
|
|
| 231 |
for symbol, ticker in tickers.items():
|
| 232 |
if not symbol.endswith('/USDT'): continue
|
| 233 |
|
|
|
|
| 234 |
base_currency = symbol.split('/')[0]
|
| 235 |
if any(bad in base_currency for bad in self.BLACKLIST_TOKENS): continue
|
| 236 |
+
if "3S" in base_currency or "3L" in base_currency: continue
|
| 237 |
|
| 238 |
vol = ticker.get('quoteVolume')
|
| 239 |
if vol is None: vol = ticker.get('info', {}).get('volValue')
|
| 240 |
if vol is None: vol = 0.0
|
| 241 |
else: vol = float(vol)
|
| 242 |
|
| 243 |
+
# 1. فلتر الحد الأدنى المطلق (لإبعاد العملات الميتة)
|
| 244 |
if vol < min_volume: continue
|
| 245 |
|
| 246 |
+
# 2. فلتر السبريد (للحماية)
|
| 247 |
bid = float(ticker.get('bid', 0) or 0)
|
| 248 |
ask = float(ticker.get('ask', 0) or 0)
|
| 249 |
if bid > 0 and ask > 0:
|
| 250 |
spread_pct = (ask - bid) / bid
|
| 251 |
+
if spread_pct > 0.015: continue # تساهلنا قليلاً (1.5%) للسماح بعملات الـ Meme النشطة
|
| 252 |
+
|
| 253 |
+
# 3. حساب درجة السخونة 🔥 (Hot Score)
|
| 254 |
+
# المعادلة: Log10(Volume) * (1 + Abs(Change%))
|
| 255 |
+
# هذا يعطي وزناً للحجم، لكن يضرب بقوة في التغير السعري
|
| 256 |
+
change_pct = float(ticker.get('percentage', 0.0))
|
| 257 |
+
|
| 258 |
+
# نستخدم Log10 لتقليص الفارق بين المليار والمليون
|
| 259 |
+
# Log10(1B) = 9, Log10(10M) = 7 (الفارق بسيط)
|
| 260 |
+
# بينما التغير السعري: 1% vs 10% (الفارق 10 أضعاف)
|
| 261 |
+
# هذا يجعل التغير السعري هو العامل الحاسم في الترتيب
|
| 262 |
+
|
| 263 |
+
log_vol = math.log10(vol + 1)
|
| 264 |
+
volatility_factor = abs(change_pct) + 1.0 # نضيف 1 لكي لا نضرب في صفر
|
| 265 |
+
|
| 266 |
+
hot_score = log_vol * volatility_factor
|
| 267 |
|
| 268 |
candidates.append({
|
| 269 |
'symbol': symbol,
|
| 270 |
'quote_volume': vol,
|
| 271 |
'current_price': float(ticker['last']) if ticker.get('last') else 0.0,
|
| 272 |
+
'change_24h': change_pct,
|
| 273 |
+
'hot_score': hot_score # الدرجة الجديدة
|
| 274 |
})
|
| 275 |
|
| 276 |
+
# 🔥 الترتيب حسب درجة السخونة وليس الحجم المطلق
|
| 277 |
+
candidates.sort(key=lambda x: x['hot_score'], reverse=True)
|
| 278 |
+
|
| 279 |
return candidates
|
| 280 |
|
| 281 |
except Exception as e:
|
|
|
|
| 284 |
|
| 285 |
async def _batch_fetch_ta_data(self, candidates, timeframe='15m', limit=200):
|
| 286 |
results = []
|
| 287 |
+
chunk_size = 20
|
| 288 |
for i in range(0, len(candidates), chunk_size):
|
| 289 |
chunk = candidates[i:i+chunk_size]
|
| 290 |
tasks = [self._fetch_ohlcv_safe(c, timeframe, limit) for c in chunk]
|
| 291 |
chunk_res = await asyncio.gather(*tasks)
|
| 292 |
results.extend([r for r in chunk_res if r is not None])
|
|
|
|
| 293 |
await asyncio.sleep(0.05)
|
| 294 |
return results
|
| 295 |
|
|
|
|
| 298 |
ohlcv = await self.exchange.fetch_ohlcv(candidate['symbol'], tf, limit=limit)
|
| 299 |
if not ohlcv: return None
|
| 300 |
df = pd.DataFrame(ohlcv, columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])
|
| 301 |
+
# تحويل البيانات لأرقام
|
| 302 |
+
cols = ['open', 'high', 'low', 'close', 'volume']
|
| 303 |
+
df[cols] = df[cols].apply(pd.to_numeric, errors='coerce')
|
| 304 |
+
|
| 305 |
candidate['df'] = df
|
| 306 |
return candidate
|
| 307 |
except: return None
|