chor: fixing cross product missing data

experiments/procesing/elasticity.py

@@ -52,6 +52,13 @@ class TemporalElasticityEstimator(BaseEstimator, TransformerMixin):
         elasticities = []
         for pid, series in product_series.items():
             if len(series) < self.min_observations:
+                # assign 0 elasticity for products with insufficient data
+                elasticities.append({
+                    'productId': pid,
+                    'elasticity': 0.0,
+                    'std_error': 0.0,
+                    'n_obs': len(series)
+                })
                 continue
 
             # apply smoothing if requested
@@ -59,11 +66,10 @@ class TemporalElasticityEstimator(BaseEstimator, TransformerMixin):
                 series = self._smooth_series(series, self.smooth_window)
 
             elast = self._compute_elasticity(series)
-            if elast is not None:
             elasticities.append({
                 'productId': pid,
                 'elasticity': elast['value'],
-                    'std_error': elast.get('std_error', np.nan),
+                'std_error': elast.get('std_error', 0.0),
                 'n_obs': len(series)
             })
 
@@ -127,7 +133,7 @@ class TemporalElasticityEstimator(BaseEstimator, TransformerMixin):
     def _compute_elasticity(self, series):
         """Compute elasticity from time series."""
         if len(series) < 2:
-            return None
+            return {'value': 0.0, 'std_error': 0.0}
 
         prices = np.array([s['price'] for s in series])
         quantities = np.array([s['quantity'] for s in series])
@@ -135,7 +141,7 @@ class TemporalElasticityEstimator(BaseEstimator, TransformerMixin):
         # filter out zero/negative values
         valid = (prices > 0) & (quantities > 0)
         if valid.sum() < 2:
-            return None
+            return {'value': 0.0, 'std_error': 0.0}
 
         prices = prices[valid]
         quantities = quantities[valid]
@@ -153,20 +159,23 @@ class TemporalElasticityEstimator(BaseEstimator, TransformerMixin):
         log(Q) = a + b*log(P), elasticity = b
         """
         if len(prices) < 2:
-            return None
+            return {'value': 0.0, 'std_error': 0.0}
 
         log_p = np.log(prices)
         log_q = np.log(quantities)
 
         # simple linear regression
         if log_p.std() == 0:
-            return None
+            return {'value': 0.0, 'std_error': 0.0}
 
         cov = np.cov(log_p, log_q)[0, 1]
         var = np.var(log_p)
         b = cov / var
 
-        # std error estimate
+        # std error estimate (avoid div by zero)
+        if len(prices) <= 2:
+            se_b = 0.0
+        else:
             residuals = log_q - (log_q.mean() + b * (log_p - log_p.mean()))
             mse = (residuals ** 2).sum() / (len(prices) - 2)
             se_b = np.sqrt(mse / (len(prices) * var))

experiments/procesing/pricing.py

@@ -88,17 +88,28 @@ if __name__ == "__main__":
     interaction_data = interaction_pipeline.fit_transform(None)
     price_data = price_data_pipeline.fit_transform(None)
 
-    price_elasticity = elasticity_pipeline(interaction_data, price_data, window_size="30s")
-    price_elasticity = price_elasticity['elasticity'].values if price_elasticity is not None and not price_elasticity.empty else np.array([])
+    elasticity_df = elasticity_pipeline(interaction_data, price_data, window_size="30s")
 
-    price_data = price_data['price'].values if not price_data.empty else np.array([])
+    # align elasticity with price data by productId, fill missing with 0
+    if not price_data.empty and elasticity_df is not None and not elasticity_df.empty:
+        price_data_merged = price_data.merge(
+            elasticity_df[['productId', 'elasticity']],
+            on='productId',
+            how='left'
+        ).fillna({'elasticity': 0.0})
 
-    print(price_elasticity)
-    print(price_data)
+        prices = price_data_merged['price'].values
+        elasticities = price_data_merged['elasticity'].values
+    else:
+        prices = np.array([])
+        elasticities = np.array([])
+
+    print(elasticities)
+    print(prices)
 
     state_space = StateSpace(
-        demand=price_elasticity,
-        prices=price_data,
+        demand=elasticities,
+        prices=prices,
         session_features=interaction_data
     )