idc-index-data 19.0.2__tar.gz → 20.0.0__tar.gz

{idc_index_data-19.0.2 → idc_index_data-20.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: idc-index-data
-Version: 19.0.2
+Version: 20.0.0
 Summary: ImagingDataCommons index to query and download data.
 Author-Email: Andrey Fedorov <andrey.fedorov@gmail.com>, Vamsi Thiriveedhi <vthiriveedhi@mgh.harvard.edu>, Jean-Christophe Fillion-Robin <jchris.fillionr@kitware.com>
 License: Copyright 2024 Andrey Fedorov

{idc_index_data-19.0.2 → idc_index_data-20.0.0}/assets/clinical_index.sql

@@ -6,6 +6,6 @@ SELECT
   column_label,
   `values`
 FROM
-  `bigquery-public-data.idc_v19_clinical.column_metadata`
+  `bigquery-public-data.idc_v20_clinical.column_metadata`
 ORDER BY
   collection_id, table_name

{idc_index_data-19.0.2 → idc_index_data-20.0.0}/assets/sm_index.sql

@@ -26,8 +26,12 @@ WITH
     ARRAY_AGG(DISTINCT(CONCAT(SpecimenDescriptionSequence[SAFE_OFFSET(0)].PrimaryAnatomicStructureSequence[SAFE_OFFSET(0)].PrimaryAnatomicStructureModifierSequence[SAFE_OFFSET(0)].CodingSchemeDesignator,":", SpecimenDescriptionSequence[SAFE_OFFSET(0)].PrimaryAnatomicStructureSequence[SAFE_OFFSET(0)].PrimaryAnatomicStructureModifierSequence[SAFE_OFFSET(0)].CodeValue, ":", SpecimenDescriptionSequence[SAFE_OFFSET(0)].PrimaryAnatomicStructureSequence[SAFE_OFFSET(0)].PrimaryAnatomicStructureModifierSequence[SAFE_OFFSET(0)].CodeMeaning)) IGNORE NULLS)[SAFE_OFFSET(0)] AS primaryAnatomicStructureModifier_code_str,
 
     ARRAY_AGG(DISTINCT(CONCAT(OpticalPathSequence[SAFE_OFFSET(0)].IlluminationTypeCodeSequence[SAFE_OFFSET(0)].CodingSchemeDesignator,":", OpticalPathSequence[SAFE_OFFSET(0)].IlluminationTypeCodeSequence[SAFE_OFFSET(0)].CodeValue, ":", OpticalPathSequence[SAFE_OFFSET(0)].IlluminationTypeCodeSequence[SAFE_OFFSET(0)].CodeMeaning)) IGNORE NULLS)[SAFE_OFFSET(0)] AS illuminationType_code_str,
+
+    ARRAY_AGG(DISTINCT(CONCAT(AdmittingDiagnosesCodeSequence[SAFE_OFFSET(0)].CodingSchemeDesignator,":", AdmittingDiagnosesCodeSequence[SAFE_OFFSET(0)].CodeValue, ":", AdmittingDiagnosesCodeSequence[SAFE_OFFSET(0)].CodeMeaning)) IGNORE NULLS)[SAFE_OFFSET(0)] AS admittingDiagnosis_code_str
+
+
   FROM
-    `bigquery-public-data.idc_v19.dicom_all` AS dicom_all
+    `bigquery-public-data.idc_v20.dicom_all` AS dicom_all
   GROUP BY
     SeriesInstanceUID
   ),
@@ -41,7 +45,7 @@ SpecimenPreparationSequence_unnested AS (
         concept_code_sequence.CodeMeaning AS ccs_cm,
         concept_code_sequence.CodingSchemeDesignator AS ccs_csd,
         concept_code_sequence.CodeValue AS ccs_val,
-      FROM `bigquery-public-data.idc_v19.dicom_all`,
+      FROM `bigquery-public-data.idc_v20.dicom_all`,
       UNNEST(SpecimenDescriptionSequence[SAFE_OFFSET(0)].SpecimenPreparationSequence) as preparation_unnest_step1,
       UNNEST(preparation_unnest_step1.SpecimenPreparationStepContentItemSequence) as preparation_unnest_step2,
       UNNEST(preparation_unnest_step2.ConceptNameCodeSequence) as concept_name_code_sequence,
@@ -123,6 +127,9 @@ SELECT
 
   CONCAT(SPLIT(illuminationType_code_str,":")[SAFE_OFFSET(0)],":",SPLIT(illuminationType_code_str,":")[SAFE_OFFSET(1)]) as illuminationType_code_designator_value_str,
   SPLIT(illuminationType_code_str,":")[SAFE_OFFSET(2)] as illuminationType_CodeMeaning,
+
+  CONCAT(SPLIT(admittingDiagnosis_code_str,":")[SAFE_OFFSET(0)],":",SPLIT(admittingDiagnosis_code_str,":")[SAFE_OFFSET(1)]) as admittingDiagnosis_code_designator_value_str,
+  SPLIT(admittingDiagnosis_code_str,":")[SAFE_OFFSET(2)] as admittingDiagnosis_CodeMeaning,
 FROM
   temp_table
 LEFT JOIN slide_embedding on temp_table.SeriesInstanceUID = slide_embedding.SeriesInstanceUID

{idc_index_data-19.0.2 → idc_index_data-20.0.0}/assets/sm_instance_index.sql

@@ -9,7 +9,7 @@ WITH
     concept_code_sequence.CodingSchemeDesignator AS ccs_csd,
     concept_code_sequence.CodeValue AS ccs_val,
   FROM
-    `bigquery-public-data.idc_v19.dicom_all`,
+    `bigquery-public-data.idc_v20.dicom_all`,
     UNNEST(SpecimenDescriptionSequence[SAFE_OFFSET(0)].SpecimenPreparationSequence) AS preparation_unnest_step1,
     UNNEST(preparation_unnest_step1.SpecimenPreparationStepContentItemSequence) AS preparation_unnest_step2,
     UNNEST(preparation_unnest_step2.ConceptNameCodeSequence) AS concept_name_code_sequence,
@@ -105,7 +105,7 @@ SELECT
   -- attributes needed to retrieve the selected instances/files
   dicom_all.crdc_instance_uuid
 FROM
-  `bigquery-public-data.idc_current.dicom_all` AS dicom_all
+  `bigquery-public-data.idc_v20.dicom_all` AS dicom_all
 LEFT JOIN
   slide_embedding
 ON

{idc_index_data-19.0.2 → idc_index_data-20.0.0}/pyproject.toml

@@ -13,7 +13,7 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "idc-index-data"
-version = "19.0.2"
+version = "20.0.0"
 authors = [
   { name = "Andrey Fedorov", email = "andrey.fedorov@gmail.com" },
   { name = "Vamsi Thiriveedhi", email = "vthiriveedhi@mgh.harvard.edu" },

{idc_index_data-19.0.2 → idc_index_data-20.0.0}/scripts/sql/idc_index.sql

@@ -26,9 +26,9 @@ SELECT
   ANY_VALUE(CONCAT(series_aws_url,"*")) AS series_aws_url,
   ROUND(SUM(SAFE_CAST(instance_size AS float64))/1000000, 2) AS series_size_MB,
 FROM
-  `bigquery-public-data.idc_v19.dicom_all` AS dicom_all
+  `bigquery-public-data.idc_v20.dicom_all` AS dicom_all
 JOIN
-  `bigquery-public-data.idc_v19.dicom_metadata_curated` AS dicom_curated
+  `bigquery-public-data.idc_v20.dicom_metadata_curated` AS dicom_curated
 ON
   dicom_all.SOPInstanceUID = dicom_curated.SOPInstanceUID
 GROUP BY

{idc_index_data-19.0.2 → idc_index_data-20.0.0}/scripts/sql/prior_versions_index.sql

@@ -3,7 +3,7 @@
 --
 -- Step 1: Declare variables
 DECLARE idc_versions ARRAY<INT64>;
-DECLARE latest_idc_version INT64 DEFAULT 19;
+DECLARE latest_idc_version INT64 DEFAULT 20;
 DECLARE union_all_query STRING;
 
 --Step 2

{idc_index_data-19.0.2 → idc_index_data-20.0.0}/tests/test_package.py

@@ -7,7 +7,7 @@ from packaging.version import Version
 
 import idc_index_data as m
 
-EXPECTED_IDC_INDEX_VERSION = 19
+EXPECTED_IDC_INDEX_VERSION = 20
 
 
 def test_version():