Add AI insights feature

services/production/app/ml/yield_predictor.py

@@ -62,14 +62,14 @@ class YieldPredictor:
                 - planned_quantity
                 - actual_quantity
                 - yield_percentage
-                - worker_id
+                - staff_assigned (list of staff IDs)
                 - started_at
                 - completed_at
                 - batch_size
                 - equipment_id (optional)
                 - notes (optional)
             production_context: Upcoming production context:
-                - worker_id
+                - staff_assigned (list of staff IDs)
                 - planned_start_time
                 - batch_size
                 - equipment_id (optional)
@@ -212,6 +212,9 @@ class YieldPredictor:
         df['is_small_batch'] = (df['batch_size'] < df['batch_size'].quantile(0.25)).astype(int)
 
         # Worker experience features (proxy: number of previous runs)
+        # Extract first worker from staff_assigned list
+        df['worker_id'] = df['staff_assigned'].apply(lambda x: x[0] if isinstance(x, list) and len(x) > 0 else 'unknown')
+        
         df = df.sort_values('started_at')
         df['worker_run_count'] = df.groupby('worker_id').cumcount() + 1
         df['worker_experience_level'] = pd.cut(
@@ -232,6 +235,10 @@ class YieldPredictor:
         factors = {}
 
         # Worker impact
+        # Extract worker_id from staff_assigned for analysis
+        if 'worker_id' not in feature_df.columns:
+            feature_df['worker_id'] = feature_df['staff_assigned'].apply(lambda x: x[0] if isinstance(x, list) and len(x) > 0 else 'unknown')
+        
         worker_yields = feature_df.groupby('worker_id')['yield_percentage'].agg(['mean', 'std', 'count'])
         worker_yields = worker_yields[worker_yields['count'] >= 3]  # Min 3 runs per worker
 
@@ -339,7 +346,10 @@ class YieldPredictor:
         if 'duration_hours' in feature_df.columns:
             feature_columns.append('duration_hours')
 
-        # Encode worker_id
+        # Encode worker_id (extracted from staff_assigned)
+        if 'worker_id' not in feature_df.columns:
+            feature_df['worker_id'] = feature_df['staff_assigned'].apply(lambda x: x[0] if isinstance(x, list) and len(x) > 0 else 'unknown')
+        
         worker_encoding = {worker: idx for idx, worker in enumerate(feature_df['worker_id'].unique())}
         feature_df['worker_encoded'] = feature_df['worker_id'].map(worker_encoding)
         feature_columns.append('worker_encoded')
@@ -420,11 +430,15 @@ class YieldPredictor:
     ) -> Dict[str, Any]:
         """Predict yield for upcoming production run."""
         # Extract context
-        worker_id = production_context.get('worker_id')
+        staff_assigned = production_context.get('staff_assigned', [])
+        worker_id = staff_assigned[0] if isinstance(staff_assigned, list) and len(staff_assigned) > 0 else 'unknown'
         planned_start = pd.to_datetime(production_context.get('planned_start_time'))
         batch_size = production_context.get('batch_size')
 
         # Get worker experience
+        if 'worker_id' not in feature_df.columns:
+            feature_df['worker_id'] = feature_df['staff_assigned'].apply(lambda x: x[0] if isinstance(x, list) and len(x) > 0 else 'unknown')
+        
         worker_runs = feature_df[feature_df['worker_id'] == worker_id]
         worker_run_count = len(worker_runs) if len(worker_runs) > 0 else 1
 
@@ -578,7 +592,7 @@ class YieldPredictor:
                     'action': 'review_production_factors',
                     'params': {
                         'recipe_id': recipe_id,
-                        'worker_id': production_context.get('worker_id')
+                        'worker_id': worker_id
                     }
                 }]
             })