Update feature_engineering.py

feature_engineering.py

@@ -42,9 +42,10 @@ class IntegratedTheoryFeatures:
     def dalio_forces(self):
         """Ray Dalio's Five Forces Framework"""
         # 1. Debt Cycle
-        yield_curve = self.df.get('DGS10', 0) - self.df.get('DGS2', 0)
-        inflation_mom = self.df.get('CPIAUCSL', pd.Series(0)).pct_change(12) * 100
-        hy_spread = self.df.get('BAMLH0A0HYM2', pd.Series(0)) / 100
+        yield_curve = (self.df.get('DGS10', pd.Series(0, index=self.df.index)) - 
+                      self.df.get('DGS2', pd.Series(0, index=self.df.index)))
+        inflation_mom = self.df.get('CPIAUCSL', pd.Series(0, index=self.df.index)).pct_change(12) * 100
+        hy_spread = self.df.get('BAMLH0A0HYM2', pd.Series(0, index=self.df.index)) / 100
         self.features['dalio_debt_cycle'] = (
             yield_curve * 0.3 + 
             inflation_mom * 0.4 + 
@@ -53,15 +54,15 @@ class IntegratedTheoryFeatures:
 
         # 2. Internal Conflict (Inequality & Social Stress)
         consumer_weakness = safe_divide(
-            self.df.get('Consumer_Discretionary', 0),
-            self.df.get('Consumer_Staples', 1)
+            self.df.get('Consumer_Discretionary', pd.Series(0, index=self.df.index)),
+            self.df.get('Consumer_Staples', pd.Series(1, index=self.df.index))
         ).pct_change(63) * -1
         
-        unemployment_stress = self.df.get('UNRATE', pd.Series(0)).diff() * 2
+        unemployment_stress = self.df.get('UNRATE', pd.Series(0, index=self.df.index)).diff() * 2
         
         small_large_gap = safe_divide(
-            self.df.get('Small_Cap_Value', 0),
-            self.df.get('SP500', 1)
+            self.df.get('Small_Cap_Value', pd.Series(0, index=self.df.index)),
+            self.df.get('SP500', pd.Series(1, index=self.df.index))
         ).pct_change(63) * -1
         
         self.features['dalio_internal_conflict'] = (
@@ -71,14 +72,17 @@ class IntegratedTheoryFeatures:
         )
 
         # 3. External Conflict (Geopolitical)
-        defense_momentum = self.df.get('Defense_Stocks', pd.Series(0)).pct_change(21)
+        defense_momentum = self.df.get('Defense_Stocks', pd.Series(0, index=self.df.index)).pct_change(21)
         
-        sp_corr = self.df.get('SP500', pd.Series(0)).pct_change(5) < -0.05
-        dollar_weak = self.df.get('DXY', pd.Series(0)).pct_change(5) < 0
-        dollar_anomaly = (sp_corr & dollar_weak).astype(float)
+        sp_ret = self.df.get('SP500', pd.Series(0, index=self.df.index)).pct_change(5)
+        dxy_ret = self.df.get('DXY', pd.Series(0, index=self.df.index)).pct_change(5)
         
-        taiwan = self.df.get('Taiwan', pd.Series(0))
-        china = self.df.get('China', pd.Series(0))
+        sp_corr = (sp_ret < -0.05).astype(float)
+        dollar_weak = (dxy_ret < 0).astype(float)
+        dollar_anomaly = sp_corr * dollar_weak
+        
+        taiwan = self.df.get('Taiwan', pd.Series(0, index=self.df.index))
+        china = self.df.get('China', pd.Series(0, index=self.df.index))
         china_taiwan_tension = (taiwan.pct_change(21) - china.pct_change(21)).fillna(0)
         
         self.features['dalio_external_conflict'] = (
@@ -88,18 +92,18 @@ class IntegratedTheoryFeatures:
         )
 
         # 4. Nature Force (Climate & Resources)
-        water_stress = self.df.get('Water', pd.Series(0)).pct_change(63)
-        ag_vol = self.df.get('Agricultural', pd.Series(0)).pct_change().rolling(63).std() * 100
+        water_stress = self.df.get('Water', pd.Series(0, index=self.df.index)).pct_change(63)
+        ag_vol = self.df.get('Agricultural', pd.Series(0, index=self.df.index)).pct_change().rolling(63).std() * 100
         self.features['dalio_nature_force'] = water_stress * 0.6 + ag_vol * 0.4
 
         # 5. Technology Force
         tech_outperform = safe_divide(
-            self.df.get('Technology', 0),
-            self.df.get('SP500', 1)
+            self.df.get('Technology', pd.Series(0, index=self.df.index)),
+            self.df.get('SP500', pd.Series(1, index=self.df.index))
         ).pct_change(21)
         
-        cloud_mom = self.df.get('Cloud_Computing', pd.Series(0)).pct_change(63)
-        ai_mom = self.df.get('Robotics_AI', pd.Series(0)).pct_change(63)
+        cloud_mom = self.df.get('Cloud_Computing', pd.Series(0, index=self.df.index)).pct_change(63)
+        ai_mom = self.df.get('Robotics_AI', pd.Series(0, index=self.df.index)).pct_change(63)
         
         self.features['dalio_tech_force'] = (
             tech_outperform * 0.4 + 
@@ -122,35 +126,36 @@ class IntegratedTheoryFeatures:
         """Betsey Stevenson's Economic Inequality Framework"""
         # Wealth Concentration
         asset_rich = (
-            self.df.get('Gold', 0) + 
-            self.df.get('Real_Estate', 0) + 
-            self.df.get('Growth_Stocks', 0)
+            self.df.get('Gold', pd.Series(0, index=self.df.index)) + 
+            self.df.get('Real_Estate', pd.Series(0, index=self.df.index)) + 
+            self.df.get('Growth_Stocks', pd.Series(0, index=self.df.index))
         ) / 3
         
         middle_class = (
-            self.df.get('Consumer_Staples', 0) + 
-            self.df.get('Regional_Banks', 0) + 
-            self.df.get('Small_Cap_Value', 0)
+            self.df.get('Consumer_Staples', pd.Series(0, index=self.df.index)) + 
+            self.df.get('Regional_Banks', pd.Series(0, index=self.df.index)) + 
+            self.df.get('Small_Cap_Value', pd.Series(0, index=self.df.index))
         ) / 3
         
         wealth_flow = asset_rich.pct_change(63) - middle_class.pct_change(63)
 
         # Consumer Spending Gap
-        luxury = self.df.get('Retail_Luxury', pd.Series(0)).pct_change(21)
+        luxury = self.df.get('Retail_Luxury', pd.Series(0, index=self.df.index)).pct_change(21)
         mass_market = (
-            (self.df.get('Restaurants', 0) + self.df.get('Retail', 0)) / 2
+            (self.df.get('Restaurants', pd.Series(0, index=self.df.index)) + 
+             self.df.get('Retail', pd.Series(0, index=self.df.index))) / 2
         ).pct_change(21)
         cons_gap = luxury - mass_market
 
         # Credit Access Gap
         quality = (
-            self.df.get('Investment_Grade_Spread', 0) + 
-            self.df.get('Preferred_Stock', 0)
+            self.df.get('Investment_Grade_Spread', pd.Series(0, index=self.df.index)) + 
+            self.df.get('Preferred_Stock', pd.Series(0, index=self.df.index))
         ) / 2
         junk = (
-            self.df.get('HYG', 0) + 
-            self.df.get('JNK', 0) + 
-            self.df.get('Emerging_Market_Debt', 0)
+            self.df.get('HYG', pd.Series(0, index=self.df.index)) + 
+            self.df.get('JNK', pd.Series(0, index=self.df.index)) + 
+            self.df.get('Emerging_Market_Debt', pd.Series(0, index=self.df.index))
         ) / 3
         credit_gap = quality.pct_change(63) - junk.pct_change(63)
 
@@ -162,20 +167,20 @@ class IntegratedTheoryFeatures:
     def thiel_monopoly(self):
         """Peter Thiel's Zero to One / Monopoly Framework"""
         # Cash Flow Moats
-        tech = self.df.get('Technology', 0)
-        finance = self.df.get('Financials', 1)
+        tech = self.df.get('Technology', pd.Series(0, index=self.df.index))
+        finance = self.df.get('Financials', pd.Series(1, index=self.df.index))
         cash_moat = tech.pct_change(63) - finance.pct_change(63)
 
         # Network Effects
         network = (
-            self.df.get('Cloud_Computing', 0) * 0.4 +
-            self.df.get('Communication_Services', 0) * 0.3 +
-            self.df.get('Fintech', 0) * 0.3
+            self.df.get('Cloud_Computing', pd.Series(0, index=self.df.index)) * 0.4 +
+            self.df.get('Communication_Services', pd.Series(0, index=self.df.index)) * 0.3 +
+            self.df.get('Fintech', pd.Series(0, index=self.df.index)) * 0.3
         ).pct_change(63)
 
         # Defensibility (Low volatility + semiconductor dominance)
-        tech_vol = self.df.get('Technology', pd.Series(1)).pct_change().rolling(63).std()
-        chip = self.df.get('Semiconductors', pd.Series(0)).pct_change(63)
+        tech_vol = self.df.get('Technology', pd.Series(1, index=self.df.index)).pct_change().rolling(63).std()
+        chip = self.df.get('Semiconductors', pd.Series(0, index=self.df.index)).pct_change(63)
         defensibility = safe_divide(1, tech_vol) * 0.01 + chip * 0.5
 
         self.features['thiel_monopoly_norm'] = normalize(
@@ -186,34 +191,35 @@ class IntegratedTheoryFeatures:
     def gundlach_reckoning(self):
         """Jeffrey Gundlach's Debt Reckoning Framework"""
         # Yield Anomalies
-        fed = self.df.get('DGS3MO', pd.Series(0))
-        teny = self.df.get('DGS10', pd.Series(0))
-        yield_anomaly = (
-            ((fed.diff() < -0.05) & (teny.diff() > 0)).astype(float) + 
-            (teny - fed)
-        )
+        fed = self.df.get('DGS3MO', pd.Series(0, index=self.df.index))
+        teny = self.df.get('DGS10', pd.Series(0, index=self.df.index))
+        
+        fed_drop = (fed.diff() < -0.05).astype(float)
+        teny_rise = (teny.diff() > 0).astype(float)
+        yield_anomaly = fed_drop * teny_rise + (teny - fed)
 
         # Flight to Safety Shift (Gold vs Bonds)
-        gold_ret = self.df.get('Gold', pd.Series(0)).pct_change(21)
-        tlt_ret = self.df.get('US_Treasuries_Long', pd.Series(1)).pct_change(21)
+        gold_ret = self.df.get('Gold', pd.Series(0, index=self.df.index)).pct_change(21)
+        tlt_ret = self.df.get('US_Treasuries_Long', pd.Series(1, index=self.df.index)).pct_change(21)
         flight_shift = safe_divide(gold_ret, tlt_ret)
 
         # Capital Flow Reversal
-        dxy_weak = self.df.get('DXY', pd.Series(0)).pct_change(21) * -1
-        em = (self.df.get('Emerging_Markets', 0) + self.df.get('Europe', 0)) / 2
+        dxy_weak = self.df.get('DXY', pd.Series(0, index=self.df.index)).pct_change(21) * -1
+        em = (self.df.get('Emerging_Markets', pd.Series(0, index=self.df.index)) + 
+              self.df.get('Europe', pd.Series(0, index=self.df.index))) / 2
         em_out = em.pct_change(21)
-        sp_ret = self.df.get('SP500', pd.Series(0)).pct_change(21)
+        sp_ret = self.df.get('SP500', pd.Series(0, index=self.df.index)).pct_change(21)
         capital_reversal = dxy_weak * 0.5 + (em_out - sp_ret) * 0.5
         self.features['gundlach_capital_reversal'] = capital_reversal
 
         # Private Credit Risk
         reg_banks = safe_divide(
-            self.df.get('Regional_Banks', 0),
-            self.df.get('Financials', 1)
+            self.df.get('Regional_Banks', pd.Series(0, index=self.df.index)),
+            self.df.get('Financials', pd.Series(1, index=self.df.index))
         ).pct_change(21)
         
-        mortgage_reit = self.df.get('Mortgage_REITs', pd.Series(0)).pct_change(21)
-        real_estate_vol = self.df.get('Real_Estate', pd.Series(1)).pct_change().rolling(21).std() * 100
+        mortgage_reit = self.df.get('Mortgage_REITs', pd.Series(0, index=self.df.index)).pct_change(21)
+        real_estate_vol = self.df.get('Real_Estate', pd.Series(1, index=self.df.index)).pct_change().rolling(21).std() * 100
         
         private_credit_risk = (
             reg_banks * -0.4 + 
@@ -235,22 +241,23 @@ class IntegratedTheoryFeatures:
     def geopolitical_indicators(self):
         """Enhanced Geopolitical Risk Indicators"""
         # Middle East Risk
-        oil_vol = self.df.get('Oil', pd.Series(1)).pct_change().rolling(3).std() * 100
-        def_spike = self.df.get('Defense_Stocks', pd.Series(0)).pct_change(5)
-        gold_haven = self.df.get('Gold_Safe_Haven', pd.Series(0)).pct_change(5)
+        oil_vol = self.df.get('Oil', pd.Series(1, index=self.df.index)).pct_change().rolling(3).std() * 100
+        def_spike = self.df.get('Defense_Stocks', pd.Series(0, index=self.df.index)).pct_change(5)
+        gold_haven = self.df.get('Gold_Safe_Haven', pd.Series(0, index=self.df.index)).pct_change(5)
         me_risk = oil_vol * 0.4 + def_spike * 0.3 + gold_haven * 0.3
 
         # Europe Risk
-        gas_vol = self.df.get('NaturalGas', pd.Series(1)).pct_change().rolling(5).std() * 100
-        eu_decline = self.df.get('Europe', pd.Series(0)).pct_change(21) * -1
-        chf_str = self.df.get('Swiss_Franc', pd.Series(0)).pct_change(21) * -1
+        gas_vol = self.df.get('NaturalGas', pd.Series(1, index=self.df.index)).pct_change().rolling(5).std() * 100
+        eu_decline = self.df.get('Europe', pd.Series(0, index=self.df.index)).pct_change(21) * -1
+        chf_str = self.df.get('Swiss_Franc', pd.Series(0, index=self.df.index)).pct_change(21) * -1
         eu_risk = gas_vol * 0.5 + eu_decline * 0.3 + chf_str * 0.2
 
         # Asia-Pacific Risk
-        chip_stress = self.df.get('Semiconductors', pd.Series(1)).pct_change().rolling(21).std() * 100
-        tw_kr = (self.df.get('Taiwan', 0) + self.df.get('South_Korea', 0)) / 2
-        china_div = tw_kr.pct_change(21) - self.df.get('China', pd.Series(0)).pct_change(21)
-        rare_earth = self.df.get('Rare_Earth', pd.Series(0)).pct_change(21)
+        chip_stress = self.df.get('Semiconductors', pd.Series(1, index=self.df.index)).pct_change().rolling(21).std() * 100
+        tw_kr = (self.df.get('Taiwan', pd.Series(0, index=self.df.index)) + 
+                 self.df.get('South_Korea', pd.Series(0, index=self.df.index))) / 2
+        china_div = tw_kr.pct_change(21) - self.df.get('China', pd.Series(0, index=self.df.index)).pct_change(21)
+        rare_earth = self.df.get('Rare_Earth', pd.Series(0, index=self.df.index)).pct_change(21)
         asia_risk = chip_stress * 0.4 + china_div * 0.3 + rare_earth * 0.3
 
         self.features['geopolitical_risk_norm'] = normalize(
@@ -272,19 +279,21 @@ class IntegratedTheoryFeatures:
         )
 
         # Stagflation Probability
-        inflation_high = (df['CPIAUCSL'].pct_change(12) * 100 > 2.5).astype(float)
+        cpi_ret = df['CPIAUCSL'].pct_change(12) * 100
+        inflation_high = (cpi_ret > 2.5).astype(float)
         unemp_rising = (df['UNRATE'].diff() > 0).astype(float)
+        
         f['prob_stagflation'] = np.clip(
-            (inflation_high & unemp_rising) * 0.3 +
+            inflation_high * unemp_rising * 0.3 +
             safe_zscore(f['dalio_external_conflict']) * 0.03 +
-            safe_zscore(f.get('gundlach_capital_reversal', pd.Series(0))) * 0.02 +
+            safe_zscore(f.get('gundlach_capital_reversal', pd.Series(0, index=f.index))) * 0.02 +
             f['stevenson_inequality_norm'] * 0.2,
             0, 1
         )
 
         # Tech Boom Probability
-        china_tech = df.get('China_Tech', pd.Series(0)).pct_change(63)
-        tech = df.get('Technology', pd.Series(0)).pct_change(63)
+        china_tech = df.get('China_Tech', pd.Series(0, index=df.index)).pct_change(63)
+        tech = df.get('Technology', pd.Series(0, index=df.index)).pct_change(63)
         china_tech_lag = (china_tech < tech).astype(float)
         
         f['prob_tech_boom'] = np.clip(
@@ -301,15 +310,13 @@ class IntegratedTheoryFeatures:
         f = self.features
         
         # Binary regime flags
-        f['debt_unsustainable'] = (
-            (f['gundlach_reckoning_norm'] > 0.5) & 
-            (f['prob_credit_collapse'] > 0.3)
-        ).astype(int)
+        gundlach_high = (f['gundlach_reckoning_norm'] > 0.5).astype(float)
+        credit_risk_high = (f['prob_credit_collapse'] > 0.3).astype(float)
+        f['debt_unsustainable'] = (gundlach_high * credit_risk_high).astype(int)
         
-        f['inequality_trap'] = (
-            (f['stevenson_inequality_norm'] > 0.6) & 
-            (f['prob_stagflation'] > 0.4)
-        ).astype(int)
+        inequality_high = (f['stevenson_inequality_norm'] > 0.6).astype(float)
+        stag_high = (f['prob_stagflation'] > 0.4).astype(float)
+        f['inequality_trap'] = (inequality_high * stag_high).astype(int)
         
         f['tech_monopoly'] = (f['thiel_monopoly_norm'] > 0.6).astype(int)
         
@@ -317,10 +324,10 @@ class IntegratedTheoryFeatures:
 
         # Regime classification
         conditions = [
-            f['debt_unsustainable'],
-            f['tech_monopoly'],
-            f['inequality_trap'],
-            f['geopolitical_shock']
+            f['debt_unsustainable'] == 1,
+            f['tech_monopoly'] == 1,
+            f['inequality_trap'] == 1,
+            f['geopolitical_shock'] == 1
         ]
         choices = ['CRISIS', 'TECH_MONOPOLY', 'INEQUALITY_TRAP', 'GEOPOLITICAL_SHOCK']
         f['regime'] = np.select(conditions, choices, default='TRANSITION')