Moved enrichment method check from init to enrich_rdf_graph (#62)

pandasaurus_cxg/graph_generator/graph_generator.py

@@ -68,26 +68,6 @@ def __init__(
             if keys
             else enrichment_analyzer.analyzer_manager.report_df
         )
-        if self.ea.enricher_manager.enricher.enriched_df.empty:
-            # TODO or we can just call simple_enrichment method
-            enrichment_methods = [i for i in dir(AnndataEnricher) if "_enrichment" in i]
-            enrichment_methods.sort()
-            raise MissingEnrichmentProcess(enrichment_methods)
-        self.cell_type_dict = (
-            pd.concat(
-                [
-                    self.ea.enricher_manager.enricher.enriched_df[["s", "s_label"]],
-                    self.ea.enricher_manager.enricher.enriched_df[["o", "o_label"]].rename(
-                        columns={"o": "s", "o_label": "s_label"}
-                    ),
-                ],
-                axis=0,
-                ignore_index=True,
-            )
-            .drop_duplicates()
-            .set_index("s")["s_label"]
-            .to_dict()
-        )
         self.ns = Namespace("http://example.org/")
         self.graph = Graph()
         self.label_priority = None
@@ -173,11 +153,31 @@ def enrich_rdf_graph(self):
         Returns:
 
         """
+        if self.ea.enricher_manager.enricher.enriched_df.empty:
+            # TODO or we can just call simple_enrichment method
+            enrichment_methods = [i for i in dir(AnndataEnricher) if "_enrichment" in i]
+            enrichment_methods.sort()
+            raise MissingEnrichmentProcess(enrichment_methods)
+        cell_type_dict = (
+            pd.concat(
+                [
+                    self.ea.enricher_manager.enricher.enriched_df[["s", "s_label"]],
+                    self.ea.enricher_manager.enricher.enriched_df[["o", "o_label"]].rename(
+                        columns={"o": "s", "o_label": "s_label"}
+                    ),
+                ],
+                axis=0,
+                ignore_index=True,
+            )
+            .drop_duplicates()
+            .set_index("s")["s_label"]
+            .to_dict()
+        )
         # add cell_type nodes and consists_of relations
         cl_namespace = Namespace("http://purl.obolibrary.org/obo/CL_")
         consist_of = URIRef(CONSIST_OF.get("iri"))
         self.graph.add((consist_of, RDFS.label, Literal(CONSIST_OF.get("label"))))
-        for curie, label in self.cell_type_dict.items():
+        for curie, label in cell_type_dict.items():
             resource = cl_namespace[curie.split(":")[-1]]
             self.graph.add((resource, RDFS.label, Literal(label)))
             self.graph.add((resource, RDF.type, OWL.Class))

test/graph_generator/test_graph_generator.py

@@ -54,26 +54,6 @@ def graph_generator_instance_for_kidney(enrichment_analyzer_instance_for_kidney_
     return GraphGenerator(ea)
 
 
-def test_graph_generator_init_missing_enrichment_process(
-    enrichment_analyzer_instance_for_immune_data,
-):
-    ea = enrichment_analyzer_instance_for_immune_data
-    ea.co_annotation_report()
-
-    with pytest.raises(MissingEnrichmentProcess) as exc_info:
-        GraphGenerator(ea)
-
-    exception = exc_info.value
-    expected_message = (
-        "Any of the following enrichment methods from AnndataEnricher must be used first; "
-        "contextual_slim_enrichment, full_slim_enrichment, minimal_slim_enrichment, "
-        "simple_enrichment"
-    )
-
-    assert isinstance(exception, MissingEnrichmentProcess)
-    assert exception.args[0] == expected_message
-
-
 def test_graph_generator_init_missing_analysis_process(
     enrichment_analyzer_instance_for_immune_data,
 ):
@@ -102,19 +82,6 @@ def test_graph_generator_init_with_valid_input(enrichment_analyzer_instance_for_
 
     assert graph_generator.ea == ea
     assert graph_generator.df.equals(ea.analyzer_manager.report_df)
-    assert graph_generator.cell_type_dict == {
-        "CL:0000798": "gamma-delta T cell",
-        "CL:0000809": "double-positive, alpha-beta thymocyte",
-        "CL:0000813": "memory T cell",
-        "CL:0000815": "regulatory T cell",
-        "CL:0000895": "naive thymus-derived CD4-positive, alpha-beta T cell",
-        "CL:0000897": "CD4-positive, alpha-beta memory T cell",
-        "CL:0000900": "naive thymus-derived CD8-positive, alpha-beta T cell",
-        "CL:0000909": "CD8-positive, alpha-beta memory T cell",
-        "CL:0000940": "mucosal invariant T cell",
-        "CL:0002489": "double negative thymocyte",
-        "CL:0000084": "T cell",
-    }
     assert graph_generator.ns == Namespace("http://example.org/")
     assert graph_generator.graph is not None
     assert graph_generator.label_priority is None
@@ -161,6 +128,25 @@ def test_generate_rdf_graph(graph_generator_instance_for_kidney):
     assert len(graph_generator.graph) == 1
 
 
+def test_enrich_graph_missing_enrichment_process(enrichment_analyzer_instance_for_kidney_data):
+    ea = enrichment_analyzer_instance_for_kidney_data
+    ea.co_annotation_report()
+    gg = GraphGenerator(ea)
+
+    with pytest.raises(MissingEnrichmentProcess) as exc_info:
+        gg.enrich_rdf_graph()
+
+    exception = exc_info.value
+    expected_message = (
+        "Any of the following enrichment methods from AnndataEnricher must be used first; "
+        "contextual_slim_enrichment, full_slim_enrichment, minimal_slim_enrichment, "
+        "simple_enrichment"
+    )
+
+    assert isinstance(exception, MissingEnrichmentProcess)
+    assert exception.args[0] == expected_message
+
+
 def test_enrich_rdf_graph(graph_generator_instance_for_kidney):
     graph_generator = graph_generator_instance_for_kidney
     graph_generator.generate_rdf_graph()
@@ -169,7 +155,7 @@ def test_enrich_rdf_graph(graph_generator_instance_for_kidney):
 
     graph_generator.enrich_rdf_graph()
 
-    assert len(graph_generator.graph) == 903
+    assert len(graph_generator.graph) == 1013
     assert (
         URIRef(CONSIST_OF.get("iri")),
         RDFS.label,
@@ -186,7 +172,7 @@ def test_enrich_rdf_graph(graph_generator_instance_for_kidney):
                 if str(s).startswith("http://purl.obolibrary.org/obo/CL_")
             ]
         )
-        == 417
+        == 527
     )