idk

pipeline/transform/price_estimation/index.py

@@ -19,6 +19,8 @@ from tqdm import tqdm
 from pipeline.transform.price_estimation.shrinkage import (
     blend_dicts,
     hierarchical_shrinkage,
+    reanchor_dict,
+    reanchor_dicts,
     shrink_dicts,
     spatial_smooth,
 )
@@ -431,6 +433,17 @@ def build_index(
             f"  {len(area_idx)} areas, {len(district_idx)} districts, {len(sector_idx)} sectors"
         )
 
+        # Re-anchor every repeat-sales dict to the global base year before any
+        # shrinkage/smoothing/blending. solve_robust_index anchors each cell to
+        # log-index 0 at its OWN earliest year, so cells with shorter histories
+        # are measured from a later origin; combining them key-by-key would
+        # otherwise average level-incompatible numbers. The hedonic fallback is
+        # already anchored at min_year, so we align everything to min_year.
+        national_idx = reanchor_dict(national_idx, min_year)
+        area_idx = reanchor_dicts(area_idx, min_year)
+        district_idx = reanchor_dicts(district_idx, min_year)
+        sector_idx = reanchor_dicts(sector_idx, min_year)
+
         # Shrinkage: national -> hedonic first, then hierarchical
         print("  Applying shrinkage...")
         national_shrunk = shrink_dicts(national_idx, hedonic_idx, national_n)