refactoring

shared_utils.py

@@ -9,10 +9,6 @@ from typing import Dict, List, Optional, Sequence, Tuple
 import numpy as np
 import pandas as pd
 import pyodbc
-try:
-    import pywt
-except ImportError:  # pragma: no cover - optional dependency
-    pywt = None
 
 DEFAULT_CONFIG_PATH = Path("config/pattern_knn_config.json")
 
@@ -91,58 +87,6 @@ def z_norm(arr: np.ndarray) -> Optional[np.ndarray]:
     return (arr - mu) / (sd + 1e-12)
 
 
-def wavelet_denoise(
-    series: pd.Series,
-    wavelet: str = "db3",
-    level: int = 3,
-    mode: str = "symmetric",
-    threshold_mode: str = "soft",
-) -> Optional[pd.Series]:
-    """Denoise/reshape the series with a wavelet decomposition.
-
-    Keeps the original index length; if PyWavelets is missing the function
-    returns None so callers can gracefully fall back to the raw signal.
-    """
-    if pywt is None:
-        print("[WARN] pywt non installato: salto il filtraggio wavelet.")
-        return None
-    s = pd.to_numeric(series, errors="coerce")
-    if s.dropna().empty:
-        return None
-
-    w = pywt.Wavelet(wavelet)
-    max_level = pywt.dwt_max_level(len(s.dropna()), w.dec_len)
-    lvl = max(1, min(level, max_level)) if max_level > 0 else 1
-
-    valid = s.dropna()
-    coeffs = pywt.wavedec(valid.values, w, mode=mode, level=lvl)
-    # Universal threshold (Donoho-Johnstone)
-    sigma = np.median(np.abs(coeffs[-1])) / 0.6745 if len(coeffs[-1]) > 0 else 0.0
-    thresh = sigma * np.sqrt(2 * np.log(len(valid))) if sigma > 0 else 0.0
-    if thresh <= 0:
-        coeffs_f = coeffs
-    else:
-        def _safe_thresh(c: np.ndarray) -> np.ndarray:
-            if c is None or c.size == 0:
-                return c
-            if threshold_mode == "hard":
-                return pywt.threshold(c, value=thresh, mode="hard")
-            # soft threshold without divide-by-zero warnings
-            mag = np.abs(c)
-            mask = mag > thresh
-            out = np.zeros_like(c)
-            out[mask] = np.sign(c[mask]) * (mag[mask] - thresh)
-            return out
-
-        coeffs_f = [coeffs[0]] + [_safe_thresh(c) for c in coeffs[1:]]
-
-    rec = pywt.waverec(coeffs_f, w, mode=mode)
-    rec = rec[: len(valid)]
-    filt = pd.Series(rec, index=valid.index)
-    # Re-allineamento all'indice originale
-    return filt.reindex(s.index).interpolate(limit_direction="both")
-
-
 def build_pattern_library(
     ret_series: pd.Series,
     wp: int,
@@ -262,23 +206,16 @@ def hurst_rs(series: pd.Series) -> Optional[float]:
     return float(h)
 
 
-def build_hurst_map(
-    returns_long: pd.DataFrame,
-    lookback: Optional[int] = None,
-    min_length: int = 100,
-) -> Dict[str, float]:
+def build_hurst_map(returns_long: pd.DataFrame, lookback: int = 252) -> Dict[str, float]:
     if returns_long.empty:
         return {}
     ret_wide = returns_long.pivot(index="Date", columns="ISIN", values="Ret").sort_index()
     hurst_map: Dict[str, float] = {}
     for isin in ret_wide.columns:
         series = ret_wide[isin].dropna().astype(float)
-        if len(series) < max(1, int(min_length)):
+        if len(series) < max(lookback, 100):
             continue
-        window = len(series) if lookback is None else min(len(series), int(lookback))
-        if window <= 0:
-            continue
-        h_val = hurst_rs(series.iloc[-window:])
+        h_val = hurst_rs(series.iloc[-lookback:])
         if h_val is None or not np.isfinite(h_val):
             continue
         hurst_map[str(isin)] = float(h_val)