add normalization for contamination and completeness

microbiomedata · Nov 15, 2024 · 98d4322 · 98d4322
1 parent 9cdda69
commit 98d4322
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 1 deletion.
diff --git a/nmdc_automation/models/nmdc.py b/nmdc_automation/models/nmdc.py
@@ -84,6 +84,11 @@ def _normalize_mags_record(record: Dict[str, Any]) -> Dict[str, Any]:
         # add type to eukaryotic_evaluation if it exists
         if "eukaryotic_evaluation" in mag:
             record["mags_list"][i]["eukaryotic_evaluation"]["type"] = "nmdc:EukEval"
+            # conpleteness and contamination need to be converted from string to float
+            if "completeness" in mag["eukaryotic_evaluation"]:
+                record["mags_list"][i]["eukaryotic_evaluation"]["completeness"] = float(mag["eukaryotic_evaluation"]["completeness"])
+            if "contamination" in mag["eukaryotic_evaluation"]:
+                record["mags_list"][i]["eukaryotic_evaluation"]["contamination"] = float(mag["eukaryotic_evaluation"]["contamination"])
         # gene count should be a positive integer - remove if 'null'
         if "gene_count" in mag and mag["gene_count"] == "null":
             mag.pop("gene_count")

diff --git a/nmdc_automation/workflow_automation/watch_nmdc.py b/nmdc_automation/workflow_automation/watch_nmdc.py
@@ -327,7 +327,6 @@ def cycle(self):
             )
             if validation_report.results:
                 logger.error(f"Validation error: {validation_report.results[0].message}")
-                logger.error(job_dict)
                 continue
 
             # post workflow execution and data objects to the runtime api