wip

Author: mivanit

spd/clustering/merge_history.py

@@ -1,6 +1,5 @@
 import io
 import json
-import sys
 import zipfile
 from dataclasses import dataclass
 from pathlib import Path
@@ -280,13 +279,12 @@ def normalized(self) -> tuple[MergesArray, dict[str, Any]]:
                 dtype=np.int16,
             )
         except Exception as e:
-            print(
+            err_msg = (
                 f"failed to create merge array, probably due to issues with getting shape.\n"
                 f"{self = }\n"
-                f"{self.data = }\n",
-                file=sys.stderr,
+                f"{self.data = }\n"
             )
-            raise e
+            raise RuntimeError(err_msg) from e
 
         overlap_stats: Float[np.ndarray, " n_ens"] = np.full(
             self.n_ensemble,
@@ -342,6 +340,7 @@ def normalized(self) -> tuple[MergesArray, dict[str, Any]]:
                 history_metadatas.append(None)
 
         return (
+            # TODO: dataclass this
             merges_array,
             dict(
                 component_labels=unique_labels,

spd/clustering/pipeline/s3_normalize_histories.py

@@ -15,10 +15,11 @@ def normalize_and_save(
 ) -> MergesArray:
     """Main function to load merge histories and compute distances"""
     # load
-    data = [MergeHistory.read(p) for p in history_paths]
-    ensemble = MergeHistoryEnsemble(data=data)
+    data: list[MergeHistory] = [MergeHistory.read(p) for p in history_paths]
+    ensemble: MergeHistoryEnsemble = MergeHistoryEnsemble(data=data)
 
     # normalize
+    normalized_merge_array: MergesArray
     normalized_merge_array, normalized_merge_meta = ensemble.normalized()
 
     # save
@@ -30,10 +31,4 @@ def normalize_and_save(
     np.savez_compressed(enseble_merge_arr_path, merges=normalized_merge_array)
     logger.info(f"merge array saved to {enseble_merge_arr_path}")
 
-    # TODO: double check we're already saving everything we need outside of the zanj file
-
-    # path_hist_ensemble: Path = output_dir / "ensemble_raw.zanj"
-    # ZANJ().save(ensemble, path_hist_ensemble)
-    # logger.info(f"Ensemble saved to {path_hist_ensemble}")
-
     return normalized_merge_array