Spaces:
Paused
Paused
Update ml_engine/oracle_engine.py
Browse files- ml_engine/oracle_engine.py +42 -82
ml_engine/oracle_engine.py
CHANGED
|
@@ -10,14 +10,16 @@ from typing import Dict, Any, List, Optional
|
|
| 10 |
# --- [ إعدادات النظام ] ---
|
| 11 |
warnings.filterwarnings('ignore', category=FutureWarning)
|
| 12 |
|
| 13 |
-
# العتبة الذهبية
|
| 14 |
CONFIDENCE_THRESHOLD = 0.65
|
| 15 |
|
| 16 |
class OracleEngine:
|
| 17 |
def __init__(self, model_dir: str = "ml_models/Unified_Models_V1"):
|
| 18 |
"""
|
| 19 |
-
Oracle
|
| 20 |
-
ي
|
|
|
|
|
|
|
| 21 |
"""
|
| 22 |
self.model_dir = model_dir
|
| 23 |
self.model_direction = None
|
|
@@ -26,23 +28,20 @@ class OracleEngine:
|
|
| 26 |
|
| 27 |
self.feature_cols = []
|
| 28 |
self.initialized = False
|
| 29 |
-
print("🧠 [Oracle
|
| 30 |
|
| 31 |
async def initialize(self):
|
| 32 |
"""تحميل النماذج وخريطة الميزات"""
|
| 33 |
if self.initialized: return True
|
| 34 |
|
| 35 |
-
print(f"🧠 [Oracle
|
| 36 |
try:
|
| 37 |
-
# 1. تحميل خريطة الميزات (لضمان ترتيب الأعمدة)
|
| 38 |
feat_path = os.path.join(self.model_dir, "feature_columns.pkl")
|
| 39 |
if not os.path.exists(feat_path):
|
| 40 |
print(f"❌ [Oracle] Feature map missing: {feat_path}")
|
| 41 |
return False
|
| 42 |
self.feature_cols = joblib.load(feat_path)
|
| 43 |
|
| 44 |
-
# 2. تحميل النماذج
|
| 45 |
-
# ملاحظة: تأكد من نقل ملفات .txt من Drive إلى مجلد المشروع المحلي
|
| 46 |
dir_path = os.path.join(self.model_dir, "lgbm_direction.txt")
|
| 47 |
tgt_path = os.path.join(self.model_dir, "lgbm_target_class.txt")
|
| 48 |
str_path = os.path.join(self.model_dir, "lgbm_strength.txt")
|
|
@@ -50,7 +49,6 @@ class OracleEngine:
|
|
| 50 |
if os.path.exists(dir_path):
|
| 51 |
self.model_direction = lgb.Booster(model_file=dir_path)
|
| 52 |
else:
|
| 53 |
-
print("❌ [Oracle] Direction Model missing!")
|
| 54 |
return False
|
| 55 |
|
| 56 |
if os.path.exists(tgt_path):
|
|
@@ -60,7 +58,7 @@ class OracleEngine:
|
|
| 60 |
self.model_strength = lgb.Booster(model_file=str_path)
|
| 61 |
|
| 62 |
self.initialized = True
|
| 63 |
-
print(f"✅ [Oracle
|
| 64 |
return True
|
| 65 |
|
| 66 |
except Exception as e:
|
|
@@ -68,46 +66,33 @@ class OracleEngine:
|
|
| 68 |
return False
|
| 69 |
|
| 70 |
# ==========================================================================
|
| 71 |
-
# 🛠️ هندسة الميزات (
|
| 72 |
# ==========================================================================
|
| 73 |
-
|
| 74 |
def _calculate_snapshot_features(self, df, tf_prefix):
|
| 75 |
-
"""حساب المؤشرات الفنية المضغوطة"""
|
| 76 |
df = df.copy()
|
| 77 |
-
# تحويلات لضمان الدقة
|
| 78 |
df['close'] = df['close'].astype(float)
|
| 79 |
df['volume'] = df['volume'].astype(float)
|
| 80 |
|
| 81 |
-
# 1. Slope
|
| 82 |
df[f'{tf_prefix}_slope'] = ta.slope(df['close'], length=7)
|
| 83 |
-
# 2. RSI
|
| 84 |
df[f'{tf_prefix}_rsi'] = ta.rsi(df['close'], length=14)
|
| 85 |
-
# 3. ATR Ratio
|
| 86 |
atr = ta.atr(df['high'], df['low'], df['close'], length=14)
|
| 87 |
df[f'{tf_prefix}_atr_pct'] = atr / df['close']
|
| 88 |
-
# 4. Volume Z-Score
|
| 89 |
vol_mean = df['volume'].rolling(20).mean()
|
| 90 |
vol_std = df['volume'].rolling(20).std()
|
| 91 |
df[f'{tf_prefix}_vol_z'] = (df['volume'] - vol_mean) / (vol_std + 1e-9)
|
| 92 |
|
| 93 |
-
# إرجاع الأعمدة فقط (مع ملء الفراغات للحسابات اللحظية)
|
| 94 |
cols = [f'{tf_prefix}_slope', f'{tf_prefix}_rsi', f'{tf_prefix}_atr_pct', f'{tf_prefix}_vol_z']
|
| 95 |
return df[cols].ffill().bfill()
|
| 96 |
|
| 97 |
def _create_feature_vector(self, ohlcv_data: Dict[str, Any], titan_score: float, mc_score: float, pattern_score: float) -> Optional[pd.DataFrame]:
|
| 98 |
-
"""تجميع متجه الميزات ومحاكاة مدخلات الطبقة الثانية"""
|
| 99 |
try:
|
| 100 |
-
# 1. التحقق من البيانات
|
| 101 |
raw_1h = ohlcv_data.get('1h')
|
| 102 |
if not raw_1h or len(raw_1h) < 30: return None
|
| 103 |
|
| 104 |
-
# تحويل البيانات إلى DataFrame
|
| 105 |
df_1h = pd.DataFrame(raw_1h, columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])
|
| 106 |
df_15m = pd.DataFrame(ohlcv_data.get('15m', []), columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])
|
| 107 |
df_4h = pd.DataFrame(ohlcv_data.get('4h', []), columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])
|
| 108 |
|
| 109 |
-
# 2. حساب الميزات الفنية (Snapshot)
|
| 110 |
-
# نأخذ آخر صف فقط (State الحالية)
|
| 111 |
feats_1h = self._calculate_snapshot_features(df_1h, "1h").iloc[-1:].reset_index(drop=True)
|
| 112 |
|
| 113 |
if len(df_15m) > 20:
|
|
@@ -120,97 +105,81 @@ class OracleEngine:
|
|
| 120 |
else:
|
| 121 |
feats_4h = pd.DataFrame(np.zeros((1, 4)), columns=[f'4h_{c}' for c in ['slope', 'rsi', 'atr_pct', 'vol_z']])
|
| 122 |
|
| 123 |
-
# 3. التجميع (Vector Assembly)
|
| 124 |
vector = pd.concat([feats_1h, feats_15m, feats_4h], axis=1)
|
| 125 |
-
|
| 126 |
-
# 4. حقن درجات الطبقة الثانية (Injection)
|
| 127 |
-
# هنا نربط الدرجات الحقيقية بالأعمدة التي تدرب عليها النموذج (sim_...)
|
| 128 |
vector['sim_titan_score'] = float(titan_score)
|
| 129 |
vector['sim_mc_score'] = float(mc_score)
|
| 130 |
vector['sim_pattern_score'] = float(pattern_score)
|
| 131 |
|
| 132 |
-
# 5. محاذاة الأعمدة (Column Alignment)
|
| 133 |
-
# يجب أن نرسل للنموذج نفس الأعمدة بنفس الترتيب
|
| 134 |
final_vector = pd.DataFrame(columns=self.feature_cols)
|
| 135 |
for col in self.feature_cols:
|
| 136 |
if col in vector.columns:
|
| 137 |
final_vector.at[0, col] = vector[col].iloc[0]
|
| 138 |
else:
|
| 139 |
-
final_vector.at[0, col] = 0.0
|
| 140 |
|
| 141 |
return final_vector.astype(float)
|
| 142 |
|
| 143 |
except Exception as e:
|
| 144 |
-
print(f"⚠️ [Oracle] Vector build failed: {e}")
|
| 145 |
return None
|
| 146 |
|
| 147 |
# ==========================================================================
|
| 148 |
-
# 🔮 التنبؤ (Inference Logic)
|
| 149 |
# ==========================================================================
|
| 150 |
-
|
| 151 |
async def predict(self, symbol_data: Dict[str, Any]) -> Dict[str, Any]:
|
| 152 |
-
"""تحليل الفرصة
|
| 153 |
if not self.initialized:
|
| 154 |
return {'action': 'WAIT', 'reason': 'Not initialized'}
|
| 155 |
|
| 156 |
try:
|
| 157 |
-
# استلام البيانات
|
| 158 |
ohlcv = symbol_data.get('ohlcv')
|
| 159 |
current_price = symbol_data.get('current_price', 0.0)
|
| 160 |
-
|
| 161 |
-
# الدرجات القادمة من L2
|
| 162 |
titan = symbol_data.get('titan_score', 0.5)
|
| 163 |
mc = symbol_data.get('mc_score', 0.5)
|
| 164 |
patt = symbol_data.get('patterns_score', 0.5)
|
| 165 |
|
| 166 |
-
# 1. بناء المتجه
|
| 167 |
features = self._create_feature_vector(ohlcv, titan, mc, patt)
|
| 168 |
if features is None:
|
| 169 |
return {'action': 'WAIT', 'reason': 'Features failed'}
|
| 170 |
|
| 171 |
-
#
|
| 172 |
-
#
|
| 173 |
-
|
| 174 |
-
# أو إذا كان Binary (0=Long, 1=Short) يعيد احتمالية Short.
|
| 175 |
-
# *تذكير*: في كود التدريب الأخير استخدمنا: y - 1. إذن: 0=Long, 1=Short.
|
| 176 |
|
| 177 |
-
dir_probs = self.model_direction.predict(features)[0] # Array [Prob_Long, Prob_Short]
|
| 178 |
-
|
| 179 |
-
# التعامل مع نوع المخرجات (حسب نسخة LightGBM)
|
| 180 |
if isinstance(dir_probs, (np.ndarray, list)):
|
| 181 |
prob_long = dir_probs[0]
|
| 182 |
prob_short = dir_probs[1]
|
| 183 |
else:
|
| 184 |
-
# Binary objective case
|
| 185 |
prob_short = dir_probs
|
| 186 |
prob_long = 1.0 - dir_probs
|
| 187 |
|
| 188 |
-
#
|
| 189 |
-
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 195 |
|
| 196 |
-
#
|
| 197 |
if confidence < CONFIDENCE_THRESHOLD:
|
| 198 |
return {
|
| 199 |
'action': 'WAIT',
|
| 200 |
-
'reason': f'Low Confidence ({confidence:.2f}
|
| 201 |
-
'direction':
|
| 202 |
}
|
| 203 |
|
| 204 |
-
#
|
| 205 |
-
|
| 206 |
-
# Strength (Regression: 0.0 - 1.0)
|
| 207 |
strength = 0.5
|
| 208 |
if self.model_strength:
|
| 209 |
strength = float(self.model_strength.predict(features)[0])
|
| 210 |
-
strength = max(0.0, min(1.0, strength))
|
| 211 |
|
| 212 |
-
|
| 213 |
-
tp_class_idx = 1 # Default TP2
|
| 214 |
if self.model_target:
|
| 215 |
tgt_probs = self.model_target.predict(features)[0]
|
| 216 |
tp_class_idx = np.argmax(tgt_probs)
|
|
@@ -218,41 +187,32 @@ class OracleEngine:
|
|
| 218 |
tp_labels = ['TP1', 'TP2', 'TP3', 'TP4']
|
| 219 |
target_profile = tp_labels[tp_class_idx]
|
| 220 |
|
| 221 |
-
#
|
| 222 |
-
# نحتاج قيمة ATR الحالية
|
| 223 |
atr_pct_val = features['1h_atr_pct'].iloc[0]
|
| 224 |
atr_abs = atr_pct_val * current_price
|
| 225 |
|
| 226 |
-
dir_mult = 1 if direction == "LONG" else -1
|
| 227 |
-
|
| 228 |
-
# خريطة الأهداف
|
| 229 |
tp_map = {
|
| 230 |
-
'TP1': current_price + (
|
| 231 |
-
'TP2': current_price + (
|
| 232 |
-
'TP3': current_price + (
|
| 233 |
-
'TP4': current_price + (
|
| 234 |
}
|
| 235 |
|
| 236 |
-
# الهدف الأساسي الموصى به
|
| 237 |
primary_tp = tp_map[target_profile]
|
| 238 |
-
|
| 239 |
-
# الوقف (Stop Loss) - دائماً 1.2 ATR كبداية
|
| 240 |
-
sl_price = current_price - (dir_mult * 1.2 * atr_abs)
|
| 241 |
|
| 242 |
return {
|
| 243 |
-
'action': 'WATCH', # إشارة صالحة
|
| 244 |
-
'action_type': 'BUY'
|
| 245 |
'confidence': float(confidence),
|
| 246 |
'strength': float(strength),
|
| 247 |
'target_class': target_profile,
|
| 248 |
'primary_tp': float(primary_tp),
|
| 249 |
'sl_price': float(sl_price),
|
| 250 |
'tp_map': tp_map,
|
| 251 |
-
'analysis_summary': f"
|
| 252 |
}
|
| 253 |
|
| 254 |
except Exception as e:
|
| 255 |
print(f"❌ [Oracle] Prediction Error: {e}")
|
| 256 |
-
import traceback
|
| 257 |
-
traceback.print_exc()
|
| 258 |
return {'action': 'WAIT', 'reason': 'Error'}
|
|
|
|
| 10 |
# --- [ إعدادات النظام ] ---
|
| 11 |
warnings.filterwarnings('ignore', category=FutureWarning)
|
| 12 |
|
| 13 |
+
# العتبة الذهبية (للدخول شراء فقط)
|
| 14 |
CONFIDENCE_THRESHOLD = 0.65
|
| 15 |
|
| 16 |
class OracleEngine:
|
| 17 |
def __init__(self, model_dir: str = "ml_models/Unified_Models_V1"):
|
| 18 |
"""
|
| 19 |
+
Oracle V4.0: Spot-Only Strategic Brain
|
| 20 |
+
- يحلل الاتجاه (صعود/هبوط).
|
| 21 |
+
- يمرر فقط فرص الصعود (Long) للتنفيذ.
|
| 22 |
+
- يحجب فرص الهبوط (Short) ويعتبرها "مخاطرة" (WAIT).
|
| 23 |
"""
|
| 24 |
self.model_dir = model_dir
|
| 25 |
self.model_direction = None
|
|
|
|
| 28 |
|
| 29 |
self.feature_cols = []
|
| 30 |
self.initialized = False
|
| 31 |
+
print("🧠 [Oracle V4 - Spot] Engine Instance Created.")
|
| 32 |
|
| 33 |
async def initialize(self):
|
| 34 |
"""تحميل النماذج وخريطة الميزات"""
|
| 35 |
if self.initialized: return True
|
| 36 |
|
| 37 |
+
print(f"🧠 [Oracle V4] Loading artifacts from {self.model_dir}...")
|
| 38 |
try:
|
|
|
|
| 39 |
feat_path = os.path.join(self.model_dir, "feature_columns.pkl")
|
| 40 |
if not os.path.exists(feat_path):
|
| 41 |
print(f"❌ [Oracle] Feature map missing: {feat_path}")
|
| 42 |
return False
|
| 43 |
self.feature_cols = joblib.load(feat_path)
|
| 44 |
|
|
|
|
|
|
|
| 45 |
dir_path = os.path.join(self.model_dir, "lgbm_direction.txt")
|
| 46 |
tgt_path = os.path.join(self.model_dir, "lgbm_target_class.txt")
|
| 47 |
str_path = os.path.join(self.model_dir, "lgbm_strength.txt")
|
|
|
|
| 49 |
if os.path.exists(dir_path):
|
| 50 |
self.model_direction = lgb.Booster(model_file=dir_path)
|
| 51 |
else:
|
|
|
|
| 52 |
return False
|
| 53 |
|
| 54 |
if os.path.exists(tgt_path):
|
|
|
|
| 58 |
self.model_strength = lgb.Booster(model_file=str_path)
|
| 59 |
|
| 60 |
self.initialized = True
|
| 61 |
+
print(f"✅ [Oracle V4] Ready (Spot Mode). Threshold: {CONFIDENCE_THRESHOLD}")
|
| 62 |
return True
|
| 63 |
|
| 64 |
except Exception as e:
|
|
|
|
| 66 |
return False
|
| 67 |
|
| 68 |
# ==========================================================================
|
| 69 |
+
# 🛠️ هندسة الميزات (مطابقة لـ DataFactory)
|
| 70 |
# ==========================================================================
|
|
|
|
| 71 |
def _calculate_snapshot_features(self, df, tf_prefix):
|
|
|
|
| 72 |
df = df.copy()
|
|
|
|
| 73 |
df['close'] = df['close'].astype(float)
|
| 74 |
df['volume'] = df['volume'].astype(float)
|
| 75 |
|
|
|
|
| 76 |
df[f'{tf_prefix}_slope'] = ta.slope(df['close'], length=7)
|
|
|
|
| 77 |
df[f'{tf_prefix}_rsi'] = ta.rsi(df['close'], length=14)
|
|
|
|
| 78 |
atr = ta.atr(df['high'], df['low'], df['close'], length=14)
|
| 79 |
df[f'{tf_prefix}_atr_pct'] = atr / df['close']
|
|
|
|
| 80 |
vol_mean = df['volume'].rolling(20).mean()
|
| 81 |
vol_std = df['volume'].rolling(20).std()
|
| 82 |
df[f'{tf_prefix}_vol_z'] = (df['volume'] - vol_mean) / (vol_std + 1e-9)
|
| 83 |
|
|
|
|
| 84 |
cols = [f'{tf_prefix}_slope', f'{tf_prefix}_rsi', f'{tf_prefix}_atr_pct', f'{tf_prefix}_vol_z']
|
| 85 |
return df[cols].ffill().bfill()
|
| 86 |
|
| 87 |
def _create_feature_vector(self, ohlcv_data: Dict[str, Any], titan_score: float, mc_score: float, pattern_score: float) -> Optional[pd.DataFrame]:
|
|
|
|
| 88 |
try:
|
|
|
|
| 89 |
raw_1h = ohlcv_data.get('1h')
|
| 90 |
if not raw_1h or len(raw_1h) < 30: return None
|
| 91 |
|
|
|
|
| 92 |
df_1h = pd.DataFrame(raw_1h, columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])
|
| 93 |
df_15m = pd.DataFrame(ohlcv_data.get('15m', []), columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])
|
| 94 |
df_4h = pd.DataFrame(ohlcv_data.get('4h', []), columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])
|
| 95 |
|
|
|
|
|
|
|
| 96 |
feats_1h = self._calculate_snapshot_features(df_1h, "1h").iloc[-1:].reset_index(drop=True)
|
| 97 |
|
| 98 |
if len(df_15m) > 20:
|
|
|
|
| 105 |
else:
|
| 106 |
feats_4h = pd.DataFrame(np.zeros((1, 4)), columns=[f'4h_{c}' for c in ['slope', 'rsi', 'atr_pct', 'vol_z']])
|
| 107 |
|
|
|
|
| 108 |
vector = pd.concat([feats_1h, feats_15m, feats_4h], axis=1)
|
|
|
|
|
|
|
|
|
|
| 109 |
vector['sim_titan_score'] = float(titan_score)
|
| 110 |
vector['sim_mc_score'] = float(mc_score)
|
| 111 |
vector['sim_pattern_score'] = float(pattern_score)
|
| 112 |
|
|
|
|
|
|
|
| 113 |
final_vector = pd.DataFrame(columns=self.feature_cols)
|
| 114 |
for col in self.feature_cols:
|
| 115 |
if col in vector.columns:
|
| 116 |
final_vector.at[0, col] = vector[col].iloc[0]
|
| 117 |
else:
|
| 118 |
+
final_vector.at[0, col] = 0.0
|
| 119 |
|
| 120 |
return final_vector.astype(float)
|
| 121 |
|
| 122 |
except Exception as e:
|
|
|
|
| 123 |
return None
|
| 124 |
|
| 125 |
# ==========================================================================
|
| 126 |
+
# 🔮 التنبؤ (Inference Logic - SPOT MODE)
|
| 127 |
# ==========================================================================
|
|
|
|
| 128 |
async def predict(self, symbol_data: Dict[str, Any]) -> Dict[str, Any]:
|
| 129 |
+
"""تحليل الفرصة: هل هي صالحة للشراء (SPOT)؟"""
|
| 130 |
if not self.initialized:
|
| 131 |
return {'action': 'WAIT', 'reason': 'Not initialized'}
|
| 132 |
|
| 133 |
try:
|
|
|
|
| 134 |
ohlcv = symbol_data.get('ohlcv')
|
| 135 |
current_price = symbol_data.get('current_price', 0.0)
|
|
|
|
|
|
|
| 136 |
titan = symbol_data.get('titan_score', 0.5)
|
| 137 |
mc = symbol_data.get('mc_score', 0.5)
|
| 138 |
patt = symbol_data.get('patterns_score', 0.5)
|
| 139 |
|
|
|
|
| 140 |
features = self._create_feature_vector(ohlcv, titan, mc, patt)
|
| 141 |
if features is None:
|
| 142 |
return {'action': 'WAIT', 'reason': 'Features failed'}
|
| 143 |
|
| 144 |
+
# 1. التنبؤ بالاتجاه (Direction)
|
| 145 |
+
# 0=Long (Buy), 1=Short (Drop/Avoid)
|
| 146 |
+
dir_probs = self.model_direction.predict(features)[0]
|
|
|
|
|
|
|
| 147 |
|
|
|
|
|
|
|
|
|
|
| 148 |
if isinstance(dir_probs, (np.ndarray, list)):
|
| 149 |
prob_long = dir_probs[0]
|
| 150 |
prob_short = dir_probs[1]
|
| 151 |
else:
|
|
|
|
| 152 |
prob_short = dir_probs
|
| 153 |
prob_long = 1.0 - dir_probs
|
| 154 |
|
| 155 |
+
# --- [SPOT LOGIC ENFORCEMENT] ---
|
| 156 |
+
# إذا كان احتمال الهبوط (Short) أعلى، فهذا يعني "تجنب العملة".
|
| 157 |
+
# لا نفتح صفقة Short، بل نقول WAIT.
|
| 158 |
+
if prob_short > prob_long:
|
| 159 |
+
return {
|
| 160 |
+
'action': 'WAIT',
|
| 161 |
+
'reason': f'Bearish Forecast (Short Prob: {prob_short:.2f})',
|
| 162 |
+
'direction': 'SHORT' # For debugging only
|
| 163 |
+
}
|
| 164 |
+
|
| 165 |
+
# إذا وصلنا هنا، فالاتجاه هو LONG (شراء)
|
| 166 |
+
confidence = prob_long
|
| 167 |
|
| 168 |
+
# 2. البوابة المنطقية (Threshold Check)
|
| 169 |
if confidence < CONFIDENCE_THRESHOLD:
|
| 170 |
return {
|
| 171 |
'action': 'WAIT',
|
| 172 |
+
'reason': f'Low Buy Confidence ({confidence:.2f})',
|
| 173 |
+
'direction': 'LONG'
|
| 174 |
}
|
| 175 |
|
| 176 |
+
# 3. التنبؤ بالأهداف والقوة
|
|
|
|
|
|
|
| 177 |
strength = 0.5
|
| 178 |
if self.model_strength:
|
| 179 |
strength = float(self.model_strength.predict(features)[0])
|
| 180 |
+
strength = max(0.0, min(1.0, strength))
|
| 181 |
|
| 182 |
+
tp_class_idx = 1
|
|
|
|
| 183 |
if self.model_target:
|
| 184 |
tgt_probs = self.model_target.predict(features)[0]
|
| 185 |
tp_class_idx = np.argmax(tgt_probs)
|
|
|
|
| 187 |
tp_labels = ['TP1', 'TP2', 'TP3', 'TP4']
|
| 188 |
target_profile = tp_labels[tp_class_idx]
|
| 189 |
|
| 190 |
+
# 4. حساب المستويات السعرية (للاتجاه الصاعد فقط)
|
|
|
|
| 191 |
atr_pct_val = features['1h_atr_pct'].iloc[0]
|
| 192 |
atr_abs = atr_pct_val * current_price
|
| 193 |
|
|
|
|
|
|
|
|
|
|
| 194 |
tp_map = {
|
| 195 |
+
'TP1': current_price + (1.0 * atr_abs),
|
| 196 |
+
'TP2': current_price + (1.8 * atr_abs),
|
| 197 |
+
'TP3': current_price + (2.8 * atr_abs),
|
| 198 |
+
'TP4': current_price + (4.5 * atr_abs),
|
| 199 |
}
|
| 200 |
|
|
|
|
| 201 |
primary_tp = tp_map[target_profile]
|
| 202 |
+
sl_price = current_price - (1.2 * atr_abs) # وقف الخسارة تحت السعر
|
|
|
|
|
|
|
| 203 |
|
| 204 |
return {
|
| 205 |
+
'action': 'WATCH', # إشارة شراء صالحة
|
| 206 |
+
'action_type': 'BUY', # دائماً BUY في Spot
|
| 207 |
'confidence': float(confidence),
|
| 208 |
'strength': float(strength),
|
| 209 |
'target_class': target_profile,
|
| 210 |
'primary_tp': float(primary_tp),
|
| 211 |
'sl_price': float(sl_price),
|
| 212 |
'tp_map': tp_map,
|
| 213 |
+
'analysis_summary': f"SPOT BUY (Conf: {confidence:.0%}) | Str: {strength:.2f} | Aim: {target_profile}"
|
| 214 |
}
|
| 215 |
|
| 216 |
except Exception as e:
|
| 217 |
print(f"❌ [Oracle] Prediction Error: {e}")
|
|
|
|
|
|
|
| 218 |
return {'action': 'WAIT', 'reason': 'Error'}
|