Add geosure data

pipeline/transform/merge.py

@@ -41,6 +41,7 @@ def _build_wide(
     noise_path: Path,
     school_proximity_path: Path,
     broadband_path: Path,
+    geosure_path: Path,
 ) -> pl.DataFrame:
     """Build the wide dataframe by joining epc_pp with all auxiliary data."""
     wide = pl.scan_parquet(epc_pp_path)
@@ -136,6 +137,9 @@ def _build_wide(
     )
     wide = wide.join(broadband, left_on="postcode", right_on="bb_postcode", how="left")
 
+    geosure = pl.scan_parquet(geosure_path)
+    wide = wide.join(geosure, on="postcode", how="left")
+
     # Use built_form (Terraced, Semi-detached) when available, otherwise epc_property_type
     wide = wide.with_columns(
         pl.when(pl.col("pp_property_type").is_in(["Terraced", "Semi-Detached"]))
@@ -208,6 +212,14 @@ def _build_wide(
                 "max_download_speed": "Max available download speed (Mbps)",
                 "serious_crime_avg_yr": "Serious crime (avg/yr)",
                 "minor_crime_avg_yr": "Minor crime (avg/yr)",
+                "transaction_year": "Transaction year",
+                "environmental_risk": "Environmental risk",
+                "collapsible_deposits_risk": "Collapsible deposits risk",
+                "compressible_ground_risk": "Compressible ground risk",
+                "landslide_risk": "Landslide risk",
+                "running_sand_risk": "Running sand risk",
+                "shrink_swell_risk": "Shrink-swell risk",
+                "soluble_rocks_risk": "Soluble rocks risk",
             }
         )
     )
@@ -276,6 +288,12 @@ def main():
         required=True,
         help="Broadband performance by output area parquet file",
     )
+    parser.add_argument(
+        "--geosure",
+        type=Path,
+        required=True,
+        help="GeoSure ground stability parquet file",
+    )
     parser.add_argument(
         "--output", type=Path, required=True, help="Output parquet file path"
     )
@@ -293,6 +311,7 @@ def main():
         noise_path=args.noise,
         school_proximity_path=args.school_proximity,
         broadband_path=args.broadband,
+        geosure_path=args.geosure,
     )
 
     print(f"Columns: {wide.columns}")