Add adaptive volatility window.

model.py

@@ -152,36 +152,146 @@ def analyze_trends(df):
     return smoothed_returns
 
 
-def calculate_volatility(df, short_window=30, medium_window=90, long_window=180):
+def calculate_adaptive_volatility(
+    df,
+    short_window=30,
+    medium_window=90,
+    long_window=180,
+    vol_clip_min=0.5,
+    vol_clip_max=2.0,
+):
     """
-    Final volatility calculation with precise period adjustments.
+    Calculate volatility with adaptive window sizes based on market conditions.
+    Returns a single volatility value for the most recent period.
     """
     df = df.copy()
-    if "Log_Return" not in df.columns:
+    df["Log_Return"] = np.log(df["Close"]).diff()
-        df["Log_Price"] = np.log(df["Close"])
-        df["Log_Return"] = df["Log_Price"].diff()
 
-    # Base volatility calculation
+    # Remove any NaN values that could cause issues
-    short_vol = df["Log_Return"].ewm(span=short_window, adjust=False).std().iloc[-1]
+    df = df.dropna()
-    medium_vol = df["Log_Return"].ewm(span=medium_window, adjust=False).std().iloc[-1]
-    long_vol = df["Log_Return"].ewm(span=long_window, adjust=False).std().iloc[-1]
 
-    # Standard weights
+    if len(df) < long_window:
-    base_vol = 0.2 * short_vol + 0.5 * medium_vol + 0.3 * long_vol
+        # Not enough data, fall back to simple volatility
+        return df["Log_Return"].std()
 
-    # Precise period-specific scaling
+    # Get recent data for efficiency
-    start_date = df["Date"].min()
+    lookback = max(long_window * 2, 360)  # Use enough data for stable estimates
-    if start_date >= pd.Timestamp("2020-01-01"):
+    recent_df = df.iloc[-lookback:].copy() if len(df) > lookback else df.copy()
-        base_adjustment = 0.64  # Slightly increased
-    elif start_date >= pd.Timestamp("2016-07-09"):
-        base_adjustment = 0.67  # Slightly increased
-    elif start_date >= pd.Timestamp("2015-01-01"):
-        base_adjustment = 0.69  # Increased for mid period
-    else:
-        # Early period with less aggressive scaling
-        base_adjustment = 0.70  # Fixed value for stability
 
-    return base_vol * base_adjustment
+    try:
+        # Initial volatility estimate using base windows
+        short_vol = recent_df["Log_Return"].ewm(span=short_window, adjust=False).std()
+        medium_vol = recent_df["Log_Return"].ewm(span=medium_window, adjust=False).std()
+        long_vol = recent_df["Log_Return"].ewm(span=long_window, adjust=False).std()
+
+        # Ensure we have valid volatility values
+        if short_vol.iloc[-1] == 0 or np.isnan(short_vol.iloc[-1]):
+            return df["Log_Return"].std()  # Fallback to simple volatility
+
+        # Calculate regime indicators for recent period
+        medium_vol_mean = medium_vol.rolling(min(90, len(recent_df))).mean()
+        if medium_vol_mean.iloc[-1] == 0:
+            vol_regime = pd.Series([1.0] * len(recent_df))
+        else:
+            vol_regime = short_vol / medium_vol_mean
+
+        vol_regime = vol_regime.clip(vol_clip_min, vol_clip_max)
+
+        # Get most recent regime reading
+        latest_regime = vol_regime.iloc[-1]
+
+        # Adjust window sizes based on current regime
+        adj_factor = 1 / latest_regime
+        adj_short = max(10, int(short_window * adj_factor))  # Minimum window of 10
+        adj_medium = max(30, int(medium_window * adj_factor))
+        adj_long = max(60, int(long_window * adj_factor))
+
+        # Calculate final volatilities using adjusted windows
+        final_short = recent_df["Log_Return"].iloc[-adj_short:].std()
+        final_medium = recent_df["Log_Return"].iloc[-adj_medium:].std()
+        final_long = recent_df["Log_Return"].iloc[-adj_long:].std()
+
+        # If any volatility measure is NaN or 0, fall back to simple volatility
+        if np.isnan([final_short, final_medium, final_long]).any() or 0 in [
+            final_short,
+            final_medium,
+            final_long,
+        ]:
+            return df["Log_Return"].std()
+
+        # Calculate regime-based weights
+        high_vol_weight = (latest_regime - vol_clip_min) / (vol_clip_max - vol_clip_min)
+        base_weights = np.array([0.2, 0.5, 0.3])
+        stress_weights = np.array([0.4, 0.4, 0.2])
+
+        # Interpolate between base and stress weights
+        weights = (
+            base_weights * (1 - high_vol_weight) + stress_weights * high_vol_weight
+        )
+
+        # Calculate final volatility
+        final_vol = (
+            final_short * weights[0]
+            + final_medium * weights[1]
+            + final_long * weights[2]
+        )
+
+        # Add uncertainty adjustment
+        regime_change = abs(vol_regime.diff()).fillna(0)
+        regime_change_mean = regime_change.rolling(5, min_periods=1).mean().iloc[-1]
+        if regime_change_mean == 0:
+            uncertainty_adjustment = 1.0
+        else:
+            regime_change_zscore = regime_change.iloc[-1] / regime_change_mean
+            uncertainty_adjustment = 1 + np.clip(regime_change_zscore / 2, 0, 0.5)
+
+        return max(final_vol * uncertainty_adjustment, df["Log_Return"].std() * 0.5)
+
+    except Exception as e:
+        print(f"Error in adaptive volatility calculation: {e}")
+        # Fall back to simple volatility calculation
+        return df["Log_Return"].std()
+
+
+def calculate_volatility(df, short_window=30, medium_window=90, long_window=180):
+    """
+    Calculate volatility using adaptive windows and era-specific adjustments.
+    Returns a single volatility value.
+    """
+    if len(df) < 30:
+        return 0.02  # Return a reasonable default for very short periods
+
+    try:
+        # Calculate adaptive volatility
+        base_vol = calculate_adaptive_volatility(
+            df,
+            short_window=short_window,
+            medium_window=medium_window,
+            long_window=long_window,
+        )
+
+        if np.isnan(base_vol) or base_vol == 0:
+            base_vol = df["Close"].pct_change().std()
+
+        # Era-specific adjustments
+        start_date = df["Date"].min()
+        if start_date >= pd.Timestamp("2020-01-01"):
+            base_adjustment = 0.64
+        elif start_date >= pd.Timestamp("2016-07-09"):
+            base_adjustment = 0.67
+        elif start_date >= pd.Timestamp("2015-01-01"):
+            base_adjustment = 0.69
+        else:
+            base_adjustment = 0.70
+
+        return max(
+            base_vol * base_adjustment, 0.01
+        )  # Ensure we never return 0 volatility
+
+    except Exception as e:
+        print(f"Error in volatility calculation: {e}")
+        # Fall back to simple volatility with minimum floor
+        return max(df["Close"].pct_change().std(), 0.01)
 
 
 # Era definitions