Scripts calcul hyperopt multiple

tools/detect_regime.py

@@ -33,44 +33,67 @@ if 'close' not in df.columns or 'timestamp' not in df.columns:
     sys.exit(1)
 
 # --- paramètres ---
-SMOOTH_WIN = 5   # EMA pour lisser la pente
-NUM_TOP = 3      # nombre de segments à garder par classe
+SMOOTH_WIN = 10   # EMA pour lisser la pente
+NUM_TOP = 1      # nombre de segments à garder par classe
 
 # --- charger les données ---
 df['timestamp'] = pd.to_datetime(df['timestamp'], errors='coerce')
 
+# filtrer uniquement 2024 et 2025
+df = df[df['timestamp'].dt.year.isin([2024, 2025])]
+
 # --- calcul SMA14 ---
-df['sma14'] = ta.trend.sma_indicator(df['close'], 14)
+df['sma'] = talib.SMA(df, timeperiod=20) #ta.trend.sma_indicator(df['close'], 14)
 
 # --- pente brute ---
-df['slope'] = df['sma14'].diff()
+df['slope'] = df['sma'].diff()
 
 # --- lissage EMA ---
 df['slope_smooth'] = df['slope'].ewm(span=SMOOTH_WIN, adjust=False).mean()
 
+#df["slope_smooth"] = savgol_filter(df["slope_smooth"], window_length=21, polyorder=3)
+
 # --- normalisation relative ---
 df['slope_norm'] = df['slope_smooth'] / df['close']
-df['slope_norm'].fillna(0, inplace=True)
+# df['slope_norm'].fillna(0, inplace=True)
+df['slope_norm'] = df['slope_norm'].fillna(0)
+
 
 # --- classification dynamique via quantiles ---
-q = df['slope_norm'].quantile([0.07, 0.21, 0.35, 0.65, 0.79, 0.93]).values
-q1, q2, q3, q4, q5, q6 = q
+
+q = df['slope_norm'].quantile([0.125, 0.375, 0.625, 0.875]).values
+q1, q2, q3, q4 = q
 
 def classify(v):
     if v <= q1:
-        return 'BR3'
-    elif v <= q2:
         return 'BR2'
-    elif v <= q3:
+    elif v <= q2:
         return 'BR1'
-    elif v <= q4:
+    elif v <= q3:
         return 'RG'
-    elif v <= q5:
+    elif v <= q4:
         return 'BU1'
-    elif v <= q6:
-        return 'BU2'
     else:
-        return 'BU3'
+        return 'BU2'
+
+# q = df['slope_norm'].quantile([0.7, 0.21, 0.35, 0.65, 0.79, 0.93]).values
+# q1, q2, q3, q4, q5, q6 = q
+#
+# def classify(v):
+#     if v <= q1:
+#         return 'BR3'
+#     elif v <= q2:
+#         return 'BR2'
+#     elif v <= q3:
+#         return 'BR1'
+#     elif v <= q4:
+#         return 'RG'
+#     elif v <= q5:
+#         return 'BU1'
+#     elif v <= q6:
+#         return 'BU2'
+#     else:
+#         return 'BU3'
 
 df['trend_class'] = df['slope_norm'].apply(classify)
 
@@ -100,7 +123,7 @@ if trend is not None and start_idx is not None:
 
 # --- extraire les 5 plus longs segments par classe ---
 top_segments_by_class = {}
-for cls in ['BR3','BR2','BR1','RG','BU1','BU2','BU3']:
+for cls in ['BR2','BR1','RG','BU1','BU2']:
     cls_segments = [(t,s,e) for t,s,e in segments if t==cls]
     # calcul de la durée
     cls_segments = [(t,s,e,(e-s).total_seconds()) for t,s,e in cls_segments]

tools/read_trends.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+import os
+import json
+from pathlib import Path
+
+def load_params_tree(base_path="user_data/strategies/params/"):
+    base = Path(base_path)
+    params_tree = {}
+    if not base.exists():
+        raise FileNotFoundError(f"Base path '{base_path}' not found.")
+
+    for pair_dir in base.iterdir():
+        if not pair_dir.is_dir():
+            continue
+        pair = pair_dir.name  # ex : BTC-USDT
+        params_tree.setdefault(pair, {})
+
+        for trend_dir in pair_dir.iterdir():
+            if not trend_dir.is_dir():
+                continue
+            trend = trend_dir.name  # ex : bull / bear / range
+            params_tree[pair].setdefault(trend, [])
+
+            for file in trend_dir.glob("*-hyperopt_result.json"):
+                filename = file.name
+
+                # Extraire START et END
+                try:
+                    prefix = filename.replace("-hyperopt_result.json", "")
+                    start, end = prefix.split("-", 1)  # split en 2
+                except Exception:
+                    start = None
+                    end = None
+
+                # Lire le JSON
+                try:
+                    with open(file, "r") as f:
+                        content = json.load(f)
+                except Exception as err:
+                    content = {"error": str(err)}
+
+                params_tree[pair][trend].append({
+                    "start": start,
+                    "end": end,
+                    "file": str(file),
+                    "content": content,
+                })
+
+    return params_tree
+
+def getTrend(data, pair, trend, space, param):
+    return data[pair][trend][0]['content']['params'][space][param]
+
+
+if __name__ == "__main__":
+    data = load_params_tree("user_data/strategies/params/")
+    # print(data)
+    # Test affichage minimal
+    for pair, trends in data.items():
+        for trend, entries in trends.items():
+            if entries:
+                indic_5m = getTrend(data, pair, trend, 'buy', 'indic_5m')
+                indic_deriv1_5m = getTrend(data, pair, trend, 'buy', 'indic_deriv1_5m')
+                indic_deriv2_5m = getTrend(data, pair, trend, 'buy', 'indic_deriv2_5m')
+
+                indic_5m_sell = getTrend(data, pair, trend, 'sell', 'indic_5m_sell')
+                indic_deriv1_5m_sell = getTrend(data, pair, trend, 'sell', 'indic_deriv1_5m_sell')
+                indic_deriv2_5m_sell = getTrend(data, pair, trend, 'sell', 'indic_deriv2_5m_sell')
+
+                print(f"{pair} -> {trend} -> {indic_5m} {indic_deriv1_5m} {indic_deriv2_5m} {indic_5m_sell} {indic_deriv1_5m_sell} {indic_deriv2_5m_sell}")
+                # for entry in entries:
+                #     print(entry)

tools/run_hyperopt_batch.sh

@@ -47,10 +47,10 @@ while read -r PAIR; do
             continue
         fi
 
-        if [[ "$START" < "2024-09-01" ]]; then
-            echo "TOO OLD $START"
-            continue
-        fi
+#        if [[ "$START" < "2024-09-01" ]]; then
+#            echo "TOO OLD $START"
+#            continue
+#        fi
 
         TIMERANGE="${START//-/}-${END//-/}"
         echo "Running hyperopt for $PAIR $REGIME with timerange $TIMERANGE"
@@ -63,7 +63,7 @@ while read -r PAIR; do
 
 #        COLUMNS=200 LINES=40 script -q -c "
 
-        freqtrade hyperopt --strategy $STRATEGIE --config user_data/config.json --hyperopt-loss OnlyProfitHyperOptLoss --timerange $TIMERANGE --timeframe 5m --spaces sell buy protection --pair $converted -e 80 -j7
+        freqtrade hyperopt --strategy $STRATEGIE --config user_data/config.json --hyperopt-loss OnlyProfitHyperOptLoss --timerange $TIMERANGE --timeframe 5m --spaces sell buy --pair $converted -e 80 -j7 --print-all
 
         echo "Saved hyperopt output to $OUTPUT_JSON"
 

tools/statistique/ewm.py

@@ -0,0 +1,41 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+np.random.seed(42)
+
+# Générer 100 valeurs simulant un prix réel avec fluctuations
+t = np.arange(100)
+trend = np.sin(t/10) * 2  # tendance ondulante
+noise = np.random.randn(100) * 0.5  # bruit
+prices = 50 + trend + noise      # prix centré autour de 50
+
+df = pd.DataFrame({"price": prices})
+
+# Rolling simple sur 5 périodes
+df["rolling5"] = df["price"].rolling(5).mean()
+
+# EMA plus réactive (span=5)
+# EMA5 standard
+df["ema5"] = df["price"].ewm(span=5, adjust=False).mean()
+
+# EMA5 “lissée” avec double application
+df["ema5_smooth"] = df["price"].ewm(span=5, adjust=False).mean().ewm(span=5, adjust=False).mean()
+
+
+# EMA plus lissée (span=20)
+df["ema20"] = df["price"].ewm(span=20, adjust=False).mean()
+
+# Plot
+plt.figure(figsize=(12,6))
+plt.plot(df["price"], label="Prix", color='black', alpha=0.6)
+plt.plot(df["rolling5"], label="Rolling 5", linestyle="--", color='blue')
+plt.plot(df["ema5"], label="EMA 5", color='red')
+plt.plot(df["ema5_smooth"], label="EMA 5S", color='blue')
+plt.plot(df["ema20"], label="EMA 20", color='green')
+plt.title("Rolling vs Exponential Moving Average (prix réaliste)")
+plt.xlabel("Période")
+plt.ylabel("Prix")
+plt.legend()
+plt.grid(True)
+plt.show()

tools/statistique/savgol.py

@@ -0,0 +1,27 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from scipy.interpolate import make_interp_spline
+from scipy.signal import savgol_filter
+
+np.random.seed(42)
+
+# Générer 100 valeurs simulant un prix réel avec fluctuations
+t = np.arange(100)
+trend = np.sin(t/10) * 2  # tendance ondulante
+noise = np.random.randn(100) * 0.5  # bruit
+prices = 50 + trend + noise      # prix centré autour de 50
+
+df = pd.DataFrame({"price": prices})
+
+df["ema5"] = df["price"].ewm(span=5, adjust=False).mean()
+# ATTENTION cela regarde dans le futur
+df["ema5_savgol"] = savgol_filter(df["ema5"], window_length=21, polyorder=3)
+
+# Plot
+# fenetre=21 points, poly order 3
+plt.plot(df["price"], alpha=0.5, label="Prix")
+plt.plot(df["ema5_savgol"], label="EMA5 lissée Savitzky-Golay", color="red")
+plt.legend()
+plt.show()
+

tools/statistique/spline.py

@@ -0,0 +1,35 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from scipy.interpolate import make_interp_spline
+
+np.random.seed(42)
+
+# Générer 100 valeurs simulant un prix réel avec fluctuations
+t = np.arange(100)
+trend = np.sin(t/10) * 2  # tendance ondulante
+noise = np.random.randn(100) * 0.5  # bruit
+prices = 50 + trend + noise      # prix centré autour de 50
+
+df = pd.DataFrame({"price": prices})
+
+df["ema5"] = df["price"].ewm(span=5, adjust=False).mean()
+
+x = np.arange(len(df))
+y = df["ema5"].values
+
+# Créer une nouvelle série de points x plus dense
+x_smooth = np.linspace(x.min(), x.max(), 300)
+
+# Spline (B-spline)
+spl = make_interp_spline(x, y, k=3)  # k=3 pour cubic spline
+y_smooth = spl(x_smooth)
+
+# Plot
+plt.figure(figsize=(12,6))
+plt.plot(df["price"], label="Prix", alpha=0.5, color="black")
+plt.plot(df["ema5"], label="EMA 5", color='blue')
+plt.plot(x_smooth, y_smooth, label="EMA5 lissée Bézier", color="red")
+plt.title("EMA5 très lisse avec spline")
+plt.legend()
+plt.show()