BUG: cast DATE BQ columns to STRING

DATE is not supported by pandas

Author: fedorov

scripts/python/idc_index_data_manager.py

@@ -250,8 +250,6 @@ def execute_sql_query(
         query_job_result = self.client.query(sql_query).result()
         schema = query_job_result.schema  # Get schema from BigQuery QueryJob
         index_df = query_job_result.to_dataframe()
-        if "StudyDate" in index_df.columns:
-            index_df["StudyDate"] = index_df["StudyDate"].astype(str)
         output_basename = Path(file_path).name.split(".")[0]
         logger.debug("Executed SQL query from file: %s", file_path)
         return index_df, output_basename, schema, sql_query

scripts/sql/analysis_results_index.sql

@@ -26,7 +26,7 @@ SELECT
   Modalities,
   # description:
   # timestamp of the last update to the analysis results collection
-  Updated,
+  SAFE_CAST(Updated AS STRING) AS Updated,
   # description:
   # license URL for the analysis results collection
   license_url,

scripts/sql/collections_index.sql

@@ -35,7 +35,7 @@ SELECT
   Status,
   # description:
   # timestamp of the last update to the collection
-  Updated,
+  SAFE_CAST(Updated AS STRING) AS Updated,
   # description:
   # detailed information about the collection
   Description

scripts/sql/idc_index.sql

@@ -36,7 +36,7 @@ SELECT
   # study level attributes
   # description:
   # date of the study (de-identified) (DICOM attribute)
-  ANY_VALUE(StudyDate) AS StudyDate,
+  ANY_VALUE(SAFE_CAST(StudyDate AS STRING)) AS StudyDate,
   # description:
   # textual description of the study content (DICOM attribute)
   ANY_VALUE(StudyDescription) AS StudyDescription,