Facet terms grouping + Production homepage stats

pyproject.toml

@@ -44,7 +44,7 @@ certifi = ">=2021.5.30"
 chardet = "^5.0.0"
 codeguru-profiler-agent = "^1.2.4"
 colorama = "0.3.3"
-dcicsnovault = "^11.24.0"
+dcicsnovault = "^11.26.0"
 dcicutils = "^8.18.3"
 docutils = ">=0.16,<1"
 encoded-core = "^0.9.6"

src/encoded/homepage.py

@@ -21,21 +21,33 @@ class SearchBase:
     ALL_RELEASED_FILES_SEARCH_PARAMS = {
         'type': 'File',
         'status': ['released', 'restricted', 'public'],
+        'additional_facet': [
+            'file_sets.libraries.assay.display_title'
+        ]
     }
     COLO829_RELEASED_FILES_SEARCH_PARAMS = {
         'type': 'File',
         'status': ['released', 'restricted', 'public'],
-        'dataset': ['colo829blt_50to1', 'colo829t', 'colo829bl']
+        'dataset': ['colo829blt_50to1', 'colo829t', 'colo829bl'],
+        'additional_facet': [
+            'file_sets.libraries.assay.display_title'
+        ]
     }
     HAPMAP_RELEASED_FILES_SEARCH_PARAMS = {
         'type': 'File',
         'status': ['released', 'restricted', 'public'],
-        'dataset': ['hapmap']
+        'dataset': ['hapmap'],
+        'additional_facet': [
+            'file_sets.libraries.assay.display_title'
+        ]
     }
     IPSC_RELEASED_FILES_SEARCH_PARAMS = {
         'type': 'File',
         'status': ['released', 'restricted', 'public'],
-        'dataset': ['lb_fibroblast', 'lb_ipsc_1', 'lb_ipsc_2', 'lb_ipsc_4', 'lb_ipsc_52', 'lb_ipsc_60']
+        'dataset': ['lb_fibroblast', 'lb_ipsc_1', 'lb_ipsc_2', 'lb_ipsc_4', 'lb_ipsc_52', 'lb_ipsc_60'],
+        'additional_facet': [
+            'file_sets.libraries.assay.display_title'
+        ]
     }
     TISSUES_RELEASED_FILES_SEARCH_PARAMS = {
         'type': 'File',
@@ -49,7 +61,18 @@ class SearchBase:
             'ST003-1Q',
             'ST004-1Q'
         ],
-        'additional_facet': 'donors.display_title'  # required since this is default_hidden for now
+        'additional_facet': [
+            'donors.display_title', 'file_sets.libraries.assay.display_title'
+        ]  # required since this is default_hidden for now
+    }
+    PRODUCTION_TISSUES_FILES_SEARCH_PARAMS = {
+        'type': 'File',
+        'status': ['released', 'restricted', 'public'],
+        'sample_summary.studies': ['Production'],
+        'additional_facet': [
+            'file_sets.libraries.assay.display_title',
+            'file_sets.libraries.analytes.samples.sample_sources.uberon_id'
+        ]
     }
 
 
@@ -84,16 +107,18 @@ def extract_desired_facet_from_search(facets, desired_facet_name):
     """ Grabs a single facet from a search response facets block """
     for d in facets:
         if d['field'] == desired_facet_name:
+            if 'original_terms' in d:
+                d['terms'] = d['original_terms']  # discard group_by_field information
             return d
     log.error(f'Did not locate specified facet on homepage: {desired_facet_name}')
-    return None
+    return {}
 
 
-def generate_unique_facet_count(context, request, search_param, desired_fact):
+def generate_unique_facet_count(context, request, search_param, desired_facet):
     """ Helper function that extracts the number of unique facet terms """
     search_param['limit'] = 0  # we do not care about search results, just facet counts
     result = generate_admin_search_given_params(context, request, search_param)
-    facet = extract_desired_facet_from_search(result['facets'], desired_fact)
+    facet = extract_desired_facet_from_search(result['facets'], desired_facet)
     # correct for no value, worst case we check the whole list of facet terms
     # but this is usually a manageable sized list - Will 28 March 2024
     for term in facet['terms']:
@@ -139,23 +164,48 @@ def generate_ipsc_assay_count(context, request):
 
 
 def generate_tissue_file_count(context, request):
-    """ Get total file count for tissues """
+    """ Get total file count for benchmarking tissues """
     search_param = SearchBase.TISSUES_RELEASED_FILES_SEARCH_PARAMS
     return generate_search_total(context, request, search_param)
 
 
 def generate_tissue_donor_count(context, request):
-    """ Get donor count by aggregating on donor """
+    """ Get benchmarking tissue donor count by aggregating on donor """
     search_param = SearchBase.TISSUES_RELEASED_FILES_SEARCH_PARAMS
     return generate_unique_facet_count(context, request, search_param, 'donors.display_title')
 
 
 def generate_tissue_assay_count(context, request):
-    """ Get total assay count for tissues """
+    """ Get total assay count for benchmarking tissues """
     search_param = SearchBase.TISSUES_RELEASED_FILES_SEARCH_PARAMS
     return generate_unique_facet_count(context, request, search_param, 'file_sets.libraries.assay.display_title')
 
 
+def generate_production_file_count(context, request):
+    """ Get total file count for production tissues """
+    search_param = SearchBase.PRODUCTION_TISSUES_FILES_SEARCH_PARAMS
+    return generate_search_total(context, request, search_param)
+
+
+def generate_production_tissue_donor_count(context, request):
+    """ Get production tissue donor count """
+    search_param = SearchBase.PRODUCTION_TISSUES_FILES_SEARCH_PARAMS
+    return generate_unique_facet_count(context, request, search_param, 'donors.display_title')
+
+
+def generate_production_tissue_assay_count(context, request):
+    """ Get production tissue assay counts """
+    search_param = SearchBase.PRODUCTION_TISSUES_FILES_SEARCH_PARAMS
+    return generate_unique_facet_count(context, request, search_param, 'file_sets.libraries.assay.display_title')
+
+
+def generate_production_tissue_type_count(context, request):
+    """ Get production tissue type counts """
+    search_param = SearchBase.PRODUCTION_TISSUES_FILES_SEARCH_PARAMS
+    return generate_unique_facet_count(context, request, search_param,
+                                       'file_sets.libraries.analytes.samples.sample_sources.uberon_id')
+
+
 @view_config(route_name='home', request_method=['GET'])
 @debug_log
 def home(context, request):
@@ -181,6 +231,11 @@ def home(context, request):
         (generate_tissue_donor_count, {'context': context, 'request': request}),  # 7
         (generate_tissue_assay_count, {'context': context, 'request': request}),  # 8
 
+        # Production stats
+        (generate_production_file_count, {'context': context, 'request': request}),  # 9
+        (generate_production_tissue_donor_count, {'context': context, 'request': request}),  # 10
+        (generate_production_tissue_assay_count, {'context': context, 'request': request}),  # 11
+        (generate_production_tissue_type_count, {'context': context, 'request': request}),  # 12
     ])
     time = datetime.now(timezone('EST'))
     response = {
@@ -244,10 +299,10 @@ def home(context, request):
                         "title": "Primary Tissues",
                         "link": "/browse",
                         "figures": [
-                            { "value": 0, "unit": "Donors" },
-                            { "value": 0, "unit": "Tissue Types" },
-                            { "value": 0, "unit": "Assays" },
-                            { "value": 0, "unit": "Files Generated" }
+                            { "value": search_results[10], "unit": "Donors" },
+                            { "value": search_results[12], "unit": "Tissue Types" },
+                            { "value": search_results[11], "unit": "Assays" },
+                            { "value": search_results[9], "unit": "Files Generated" }
                         ]
                     }
                 ]

src/encoded/static/scss/encoded/modules/_search.scss

@@ -200,6 +200,11 @@ $facetlist-excluding: #450000;
 						& > .facet-item {
 							color: #727272;
 							font-size: 0.813rem;
+
+							&.facet-item-group-header {
+								color: #3B3A3A;
+								font-weight: 500;
+							}
 						}
 						& > .facet-count {
 							color: #727272;

src/encoded/tests/test_homepage.py

@@ -8,8 +8,8 @@ def test_extract_desired_facet():
         {'field': 'type', 'title': 'Data Type', 'total': 0, 'hide_from_view': True, 'aggregation_type': 'terms',
          'terms': [{'key': 'File', 'doc_count': 7}, {'key': 'Item', 'doc_count': 7}]}
     ]
-    assert extract_desired_facet_from_search(example_facets, 'type') is not None
-    assert extract_desired_facet_from_search(example_facets, 'not-found') is None
+    assert extract_desired_facet_from_search(example_facets, 'type') is not {}
+    assert extract_desired_facet_from_search(example_facets, 'not-found') is {}
 
 
 @pytest.mark.workbook

src/encoded/types/file.py

@@ -665,7 +665,7 @@ def meta_workflow_run_outputs(self, request: Request) -> Union[List[str], None]:
         result = self.rev_link_atids(request, "meta_workflow_run_outputs")
         if result:
             request_handler = RequestHandler(request = request)
-            mwfrs=[ 
+            mwfrs=[
                 mwfr for mwfr in result
                 if get_property_value_from_identifier(
                     request_handler,
@@ -786,7 +786,7 @@ def release_tracker_title(
             request_handler,
             file_properties=self.properties
         )
-        return result     
+        return result
 
     def _get_libraries(
         self, request: Request, file_sets: Optional[List[str]] = None
@@ -968,7 +968,7 @@ def _get_group_coverage(
         self, request_handler: Request, file_properties: Optional[List[str]] = None
     ) -> Union[List[str], None]:
         """"Get group coverage for display on file overview page.
-        
+
         Use override_group_coverage if present, otherwise grab target_coverage from sequencing."""
         if (override_group_coverage := file_utils.get_override_group_coverage(file_properties)):
             return [override_group_coverage]
@@ -1092,7 +1092,7 @@ def _get_release_tracker_title(
         ) -> Union[str, None]:
         """Get release tracker title for display on the home page."""
         to_include = None
-        if "file_sets" in file_properties:    
+        if "file_sets" in file_properties:
             if (cell_culture_mixture_title := get_unique_values(
                 request_handler.get_items(
                     file_utils.get_cell_culture_mixtures(file_properties, request_handler)),

src/encoded/types/file_set.py

@@ -66,9 +66,9 @@ def _build_file_set_embedded_list():
         "libraries.analytes.samples.sample_sources.code",
         "libraries.analytes.samples.sample_sources.uberon_id",
         "libraries.analytes.samples.sample_sources.cell_line.code",
+        "libraries.analytes.samples.sample_sources.uberon_id",
         "libraries.analytes.samples.sample_sources.donor.display_title",
 
-
         # Sequencing/Sequencer LinkTo - used in file_merge_group
         "sequencing.submitted_id",
         "sequencing.target_coverage",
@@ -84,7 +84,7 @@ def _build_file_set_embedded_list():
         "files.file_format.display_title",
         "files.file_status_tracking",
         "files.quality_metrics.overall_quality_status",
-        
+
         "meta_workflow_runs.meta_workflow.display_title",
         "meta_workflow_runs.meta_workflow.category",
         "meta_workflow_runs.accession",
@@ -337,8 +337,8 @@ def validate_compatible_assay_and_sequencer_on_edit(context, request):
 
 def check_compatible_assay_and_sequencer(request, libraries: List[str], sequencing: str):
     """Checks that if library.assay has a valid_sequencer property, that sequencing.sequencer is among them.
-    
-    The assays with `valid_sequencers` property may need to be updated as new techologies come out 
+
+    The assays with `valid_sequencers` property may need to be updated as new techologies come out
     or are added to the portal.
     """
     assays = []