def _init(self):
all_deprecated = set(t.extract_deprecated(self.graph))
concepts = set(
t.extract_by_type_uri(self.graph,
self.concept_type_uri,
remove=all_deprecated))
thesauri = set(
t.extract_by_type_uri(self.graph,
self.sub_thesaurus_type_uri,
remove=all_deprecated))
self.concept_map_ = dict(zip(map(str, concepts), range(len(concepts))))
thesaurus_features = ThesaurusFeatureTransformation(
self.graph, concepts, thesauri, self.thesaurus_relation_type_uri,
self.thesaurus_relation_is_specialisation)
labels = t.retrieve_concept_labels(self.graph,
allowed=concepts,
langs=self.langs)
nfautomat = nfa.Nfa()
if self.handle_title_case:
case_handler = case_handlers.title_case_handler
else:
case_handler = case_handlers.sentence_case_handler
expansion_funs = expansion.collect_expansion_functions(
extract_upper_case_from_braces=self.extract_upper_case_from_braces,
extract_any_case_from_braces=self.extract_any_case_from_braces,
expand_ampersand_with_spaces=self.expand_ampersand_with_spaces,
expand_abbreviation_with_punctuation=(
self.expand_abbreviation_with_punctuation),
)
if self.simple_english_plural_rules:
plural_fun = expansion.simple_english_plural_fun
else:
def plural_fun(x):
return x
for concept, label in labels:
expanded = label
for f in expansion_funs:
expanded = f(expanded)
_handle_construction(
construction.ConstructionState(
nfautomat, plural_fun(case_handler(expanded)),
str(concept)), concept, label)
nfautomat.remove_empty_transitions()
converter = conversion.NfaToDfaConverter(nfautomat)
self.dfa_ = converter.start_conversion()
self.pipeline_ = Pipeline([
("Combined Features",
ColumnTransformer([("Thesaurus Features", thesaurus_features, 0),
("Text Features", mk_text_features(), 1)])),
("Classifier",
DecisionTreeClassifier(min_samples_leaf=25, max_leaf_nodes=100))
])
def test_integration(typed_label_graph, concept_set):
result = list(
t.retrieve_concept_labels(
typed_label_graph,
allowed=concept_set,
langs={"en"},
))
assert (c.concept_ref_printed,
c.concept_prefLabel_printed_en.value) in result
assert (c.concept_ref_printed,
c.concept_altLabel_printed_en.value) in result
assert (c.concept_ref_printed,
c.concept_prefLabel_printed_de.value) not in result
assert c.thsys_ref_print not in map(lambda t: t[0], result)
def test_prefix_option(label_graph, concept_set, patch_module):
t.retrieve_concept_labels(label_graph, concept_set)
t.filter_subject_tuples_from_set.assert_called()
def test_none_prefix_option(label_graph, patch_module):
t.retrieve_concept_labels(label_graph, allowed=None)
t.filter_subject_tuples_from_set.assert_not_called()
def test_language_option(label_graph, patch_module):
t.retrieve_concept_labels(label_graph, langs={"en"})
t._filter_by_langs.assert_called()
