def main():
#src_triples = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'sap_hilti_full_strings',
# 'graph_triples_hilti_erp.nt')
#tgt_triples = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'sap_hilti_full_strings',
# 'graph_triples_hilti_web.nt')
#src_corpus = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'sap_hilti_full_strings',
# 'corpus_hilti_erp.txt')
#tgt_corpus = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'sap_hilti_full_strings',
# 'corpus_hilti_web.txt')
#gold_mapping = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'sap_hilti_full_strings',
# 'train_simple_sap_hilti.csv')
src_triples = os.path.join(package_directory, '..', 'data', 'oaei_data',
'graph_triples_darkscape.nt')
tgt_triples = os.path.join(package_directory, '..', 'data', 'oaei_data',
'graph_triples_oldschoolrunescape.nt')
src_corpus = os.path.join(package_directory, '..', 'data', 'oaei_data',
'corpus_darkscape.txt')
tgt_corpus = os.path.join(package_directory, '..', 'data', 'oaei_data',
'corpus_oldschoolrunescape.txt')
gold_mapping = InternalGoldStandard({'trainsets':
[os.path.join(package_directory, '..', 'data',
'oaei_data', 'oaei_gold_standard2.csv')],
'testsets':
[os.path.join(package_directory, '..', 'data',
'oaei_data', 'possible_matches.csv')]
})
dim = 2
model = XGBClassifier()#LogisticRegression()
labelfile = os.path.join(package_directory, '..', 'data', 'oaei_data','labels.txt')
src_properties = StringMatcher_Interface.get_labels_from_file(labelfile)
tgt_properties = StringMatcher_Interface.get_labels_from_file(labelfile)
name = "OAEI_visualization"
pipeline = Pipeline()
line_a = pipeline.append_step(load_kg_with_rdflib_ttl_interface, None, PipelineDataTuple(src_triples))
line_a = pipeline.append_step(GraphToolbox.interface, PipelineDataTuple(line_a), PipelineDataTuple(src_triples))
line_b = pipeline.append_step(load_kg_with_rdflib_ttl_interface, None, PipelineDataTuple(tgt_triples))
line_b = pipeline.append_step(GraphToolbox.interface, PipelineDataTuple(line_b), PipelineDataTuple(tgt_triples))
line_ab = pipeline.append_step(WalkEmbedder_1.interface, PipelineDataTuple(line_a, line_b),
PipelineDataTuple(dim, 'steps', True, 1))
line_ab = pipeline.append_step(concat_combiner.interface, PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(TSNEInterface.interface, PipelineDataTuple(line_ab), PipelineDataTuple(2))
line_ab = pipeline.append_step(EmbeddingSaver.interface, PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(CategoriesVisualizer.interface, PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(StratifiedVisualizer.interface, PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(TypeVisualizer.interface, PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(FullVisualizer.interface, PipelineDataTuple(line_ab), None)
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples, tgt_triples, gold_mapping, dim,
pipeline, src_properties, tgt_properties, calc_PLUS_SCORE=False, use_cache=False, use_streams=False)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
def main(src_triples, tgt_triples, labels, filename):
# match products
if type(labels) == str:
index_properties = smi.get_labels_from_file(labels)
else:
index_properties = labels
assert type(
index_properties
) == list, "Labels-parameter must be provided as a list of label-properties"
#print('label size: ' + str(len(index_properties)))
stringmatcher = StringMatcher(src_triples, tgt_triples, index_properties)
mappings = stringmatcher.preciseBatchMatch(filename, 0.9, index_properties,
src_triples, tgt_triples)
def main():
#src_triples = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'sap_hilti_full_strings',
# 'graph_triples_hilti_erp.nt')
#tgt_triples = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'sap_hilti_full_strings',
# 'graph_triples_hilti_web.nt')
#src_corpus = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'sap_hilti_full_strings',
# 'corpus_hilti_erp.txt')
#tgt_corpus = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'sap_hilti_full_strings',
# 'corpus_hilti_web.txt')
#gold_mapping = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'sap_hilti_full_strings',
# 'train_simple_sap_hilti.csv')
src_triples = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'balanced_walks',
'graph_triples_hilti_erp.nt')
tgt_triples = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'balanced_walks',
'graph_triples_hilti_web.nt')
src_corpus = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'balanced_walks',
'corpus_hilti_erp.txt')
tgt_corpus = os.path.join(package_directory, '..', 'data', 'sap_hilti_data', 'balanced_walks',
'corpus_hilti_web.txt')
gold_mapping = InternalGoldStandard({'trainsets':
[os.path.join(package_directory, '..', 'data',
'sap_hilti_data', 'balanced_walks', 'final_trainset.csv')],
'testsets': [os.path.join(package_directory, '..', 'data',
'sap_hilti_data', 'balanced_walks', 'possible_matches.csv')]
})
dim = 1
model = LogisticRegression()#XGBClassifier()
labelfile = os.path.join(package_directory, '..', 'data', 'sap_hilti_data','balanced_walks',
'labels.txt')
src_properties = StringMatcher_Interface.get_labels_from_file(labelfile)#["http://rdata2graph.sap.com/hilti_erp/property/mara_fert.maktx"]
tgt_properties = StringMatcher_Interface.get_labels_from_file(labelfile)#["http://rdata2graph.sap.com/hilti_web/property/products.name"]
use_streams = False
name = "test"
pipeline = Pipeline()
line_a = pipeline.append_step(load_kg_with_rdflib_ttl_interface, None, PipelineDataTuple(src_triples))
line_a = pipeline.append_step(GraphToolbox.interface, PipelineDataTuple(line_a), PipelineDataTuple(src_triples))
#line_a = pipeline.append_step(ReadSentencesInterfaceWrapper.interface, PipelineDataTuple(line_a),
# PipelineDataTuple(src_corpus))
line_b = pipeline.append_step(load_kg_with_rdflib_ttl_interface, None, PipelineDataTuple(tgt_triples))
line_b = pipeline.append_step(GraphToolbox.interface, PipelineDataTuple(line_b), PipelineDataTuple(tgt_triples))
#line_b = pipeline.append_step(ReadSentencesInterfaceWrapper.interface, PipelineDataTuple(line_b),
# PipelineDataTuple(tgt_corpus))
line_ab = pipeline.append_step(WalkEmbedder_1.interface, PipelineDataTuple(line_a, line_b),
PipelineDataTuple(dim, 'steps', False, 1))
line_ab = pipeline.append_step(concat_combiner.interface, PipelineDataTuple(line_ab), None)
#line_ab = pipeline.append_step(muse.interface, PipelineDataTuple(line_ab), PipelineDataTuple(gold_mapping))
line_ab = pipeline.append_step(FlatMatcher.interface, PipelineDataTuple(line_ab),
PipelineDataTuple(model))
#line_ab = pipeline.append_step(TSNEInterface.interface, PipelineDataTuple(line_ab), PipelineDataTuple(2))
#line_ab = pipeline.append_step(CategoriesVisualizer.interface, PipelineDataTuple(line_ab), None)
#line_ab = pipeline.append_step(StratifiedVisualizer.interface, PipelineDataTuple(line_ab), None)
#line_ab = pipeline.append_step(TypeVisualizer.interface, PipelineDataTuple(line_ab), None)
#line_ab = pipeline.append_step(FullVisualizer.interface, PipelineDataTuple(line_ab), None)
#line_ab = pipeline.append_step(EmbeddingSaver.interface, PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(StableRankMatcher.interface, PipelineDataTuple(line_ab), None)
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples, tgt_triples, gold_mapping, dim,
pipeline, src_properties, tgt_properties, use_streams, False, True)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)