Add a partition_info on SOAP results. (#157)

astronomy-commons · Nov 1, 2023 · 7038f7d · 7038f7d
1 parent 46ee668
commit 7038f7d
Showing 1 changed file with 7 additions and 0 deletions.
diff --git a/src/hipscat_import/soap/map_reduce.py b/src/hipscat_import/soap/map_reduce.py
@@ -125,3 +125,10 @@ def combine_partial_results(input_path, output_path):
             file_pointer=file_io.append_paths_to_pointer(output_path, "unmatched_sources.csv"),
             index=False,
         )
+
+    primary_only = matched.groupby(["Norder", "Dir", "Npix"])["num_rows"].sum().reset_index()
+    file_io.write_dataframe_to_csv(
+        dataframe=primary_only,
+        file_pointer=file_io.append_paths_to_pointer(output_path, "partition_info.csv"),
+        index=False,
+    )