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 = 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')
dim = 3
#model = make_pipeline(PolynomialFeatures(6), Ridge())#DecisionTreeClassifier() #make_pipeline(PolynomialFeatures(8), Ridge())
#model = sklearn.linear_model.LinearRegression()
#from sklearn.ensemble import RandomForestRegressor
#model = RandomForestRegressor(max_depth=2, random_state=0, n_estimators=100)
#model = LinearSVC(C=0.01, class_weight=None, dual=True, fit_intercept=True,
# intercept_scaling=1, loss='squared_hinge', max_iter=1000,
# multi_class='ovr', penalty='l2', random_state=0, tol=1e-05, verbose=0)
from sklearn.linear_model import LogisticRegression
model = XGBClassifier()
src_properties = ["http://rdata2graph.sap.com/hilti_erp/property/mara_fert.maktx"]
tgt_properties = ["http://rdata2graph.sap.com/hilti_web/property/products.name"]
name = "jaccard_no_props_given"
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(W2V_1InterfaceWrapper.interface, PipelineDataTuple(line_a, line_b), PipelineDataTuple(dim))
line_ab = pipeline.append_step(muse.interface, PipelineDataTuple(line_a, line_b), PipelineDataTuple(gold_mapping))
line_ab = pipeline.append_step(EmbeddingMatcher.interface, PipelineDataTuple(line_ab),
PipelineDataTuple(model))
line_ab = pipeline.append_step(StratifiedVisualizer.interface, PipelineDataTuple(line_a, line_b), None)
line_ab = pipeline.append_step(TypeVisualizer.interface, PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(CategoriesVisualizer.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)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
def main():
logfile = os.path.join(package_directory, '..', 'results.log')
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 = 20
model = XGBClassifier()
src_properties = [
"http://rdata2graph.sap.com/hilti_erp/property/mara_fert.maktx"
]
tgt_properties = [
"http://rdata2graph.sap.com/hilti_web/property/products.name"
]
name = "HILTI_pure_syntax"
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(1, '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(PureSyntaxMatcher.interface,
PipelineDataTuple(line_ab),
PipelineDataTuple(model))
line_ab = pipeline.append_step(EmbeddingSaver.interface,
PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(StableRankSyntaxMatcher.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)
name = "HILTI_w2v_steps_walklength1"
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', 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(EmbeddingSaver.interface,
PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(StableRankMatcher.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)
name = "HILTI_w2v_steps_walklength1_muse"
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', 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(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,
calc_PLUS_SCORE=False,
use_cache=False,
use_streams=False)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "HILTI_w2v_steps_walklength3"
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', False, 3))
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(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,
calc_PLUS_SCORE=False,
use_cache=False,
use_streams=False)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "HILTI_w2v_steps_walklength1_3grams"
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(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(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,
calc_PLUS_SCORE=False,
use_cache=False,
use_streams=False)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "HILTI_w2v_batch_walklength1"
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, 'batch', 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(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,
calc_PLUS_SCORE=False,
use_cache=False,
use_streams=False)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "HILTI_w2v_steps_walklength1_dim100"
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(100, '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(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,
calc_PLUS_SCORE=False,
use_cache=False,
use_streams=False)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "HILTI_d2v_steps_walklength1_muse"
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(WalkD2V_1Embedder.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(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,
calc_PLUS_SCORE=False,
use_cache=False,
use_streams=False)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "HILTI_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(2, '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(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_ngram_string():
logfile = os.path.join(package_directory, '..', 'results.log')
src_triples = os.path.join(package_directory, '..', 'data',
'sap_hilti_data', 'sap_hilti_3grams',
'graph_triples_hilti_erp.nt')
tgt_triples = os.path.join(package_directory, '..', 'data',
'sap_hilti_data', 'sap_hilti_3grams',
'graph_triples_hilti_web.nt')
src_corpus = os.path.join(package_directory, '..', 'data',
'sap_hilti_data', 'sap_hilti_3grams',
'corpus_hilti_erp.txt')
tgt_corpus = os.path.join(package_directory, '..', 'data',
'sap_hilti_data', 'sap_hilti_3grams',
'corpus_hilti_web.txt')
gold_mapping = InternalGoldStandard({
'trainsets': [
os.path.join(package_directory, '..', 'data', 'sap_hilti_data',
'sap_hilti_3grams', 'train_simple_sap_hilti.csv'),
os.path.join(package_directory, '..', 'data', 'sap_hilti_data',
'sap_hilti_3grams', 'train_hard_sap_hilti.csv')
],
'testsets': [
os.path.join(package_directory, '..', 'data', 'sap_hilti_data',
'sap_hilti_3grams', 'test_simple_sap_hilti.csv'),
os.path.join(package_directory, '..', 'data', 'sap_hilti_data',
'sap_hilti_3grams', 'test_hard_sap_hilti.csv')
]
})
dim = 20
model = XGBClassifier()
src_properties = [
"http://rdata2graph.sap.com/hilti_erp/property/mara_fert.maktx"
]
tgt_properties = [
"http://rdata2graph.sap.com/hilti_web/property/products.name"
]
name = "3gram: simpletriplesembedding xgb"
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(SimpleTriplesEmbedder.interface,
PipelineDataTuple(line_a),
PipelineDataTuple(dim))
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(SimpleTriplesEmbedder.interface,
PipelineDataTuple(line_b),
PipelineDataTuple(dim))
line_ab = pipeline.append_step(concat_combiner.interface,
PipelineDataTuple(line_a, line_b), None)
line_ab = pipeline.append_step(FlatMatcher.interface,
PipelineDataTuple(line_ab),
PipelineDataTuple(model))
line_a = pipeline.append_step(TSNEInterface.interface,
PipelineDataTuple(line_a),
PipelineDataTuple(2))
line_b = pipeline.append_step(TSNEInterface.interface,
PipelineDataTuple(line_b),
PipelineDataTuple(2))
line_ab = pipeline.append_step(CategoriesVisualizer.interface,
PipelineDataTuple(line_a, line_b), 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)
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples,
tgt_triples, gold_mapping, dim, pipeline,
src_properties, tgt_properties)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "3gram: simpletriplesembedding_1 xgb"
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(SimpleTriplesEmbedder_1.interface,
PipelineDataTuple(line_a, line_b),
PipelineDataTuple(dim))
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)
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples,
tgt_triples, gold_mapping, dim, pipeline,
src_properties, tgt_properties)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples,
tgt_triples, gold_mapping, dim, pipeline,
src_properties, tgt_properties)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "3gram: w2v xgb"
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_a = pipeline.append_step(W2VInterfaceWrapper.interface,
PipelineDataTuple(line_a),
PipelineDataTuple(dim))
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_b = pipeline.append_step(W2VInterfaceWrapper.interface,
PipelineDataTuple(line_b),
PipelineDataTuple(dim))
line_ab = pipeline.append_step(concat_combiner.interface,
PipelineDataTuple(line_a, line_b), None)
line_ab = pipeline.append_step(FlatMatcher.interface,
PipelineDataTuple(line_ab),
PipelineDataTuple(model))
line_a = pipeline.append_step(TSNEInterface.interface,
PipelineDataTuple(line_a),
PipelineDataTuple(2))
line_b = pipeline.append_step(TSNEInterface.interface,
PipelineDataTuple(line_b),
PipelineDataTuple(2))
line_ab = pipeline.append_step(CategoriesVisualizer.interface,
PipelineDataTuple(line_a, line_b), 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)
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples,
tgt_triples, gold_mapping, dim, pipeline,
src_properties, tgt_properties)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "3gram: d2v xgb"
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(D2VInterfaceWrapper.interface,
PipelineDataTuple(line_a),
PipelineDataTuple(dim))
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(D2VInterfaceWrapper.interface,
PipelineDataTuple(line_b),
PipelineDataTuple(dim))
line_ab = pipeline.append_step(concat_combiner.interface,
PipelineDataTuple(line_a, line_b), None)
line_ab = pipeline.append_step(FlatMatcher.interface,
PipelineDataTuple(line_ab),
PipelineDataTuple(model))
line_a = pipeline.append_step(TSNEInterface.interface,
PipelineDataTuple(line_a),
PipelineDataTuple(2))
line_b = pipeline.append_step(TSNEInterface.interface,
PipelineDataTuple(line_b),
PipelineDataTuple(2))
line_ab = pipeline.append_step(CategoriesVisualizer.interface,
PipelineDataTuple(line_a, line_b), 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)
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples,
tgt_triples, gold_mapping, dim, pipeline,
src_properties, tgt_properties)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
# name = "3gram: pseudod2v xgb"
# 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(PseudoD2VInterfaceWrapper.interface, PipelineDataTuple(line_a), PipelineDataTuple(dim))
# 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(PseudoD2VInterfaceWrapper.interface, PipelineDataTuple(line_b), PipelineDataTuple(dim))
# line_ab = pipeline.append_step(concat_combiner.interface, PipelineDataTuple(line_a, line_b), None)
# 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(StratifiedVisualizer.interface, PipelineDataTuple(line_ab), None)
# line_ab = pipeline.append_step(TypeVisualizer.interface, PipelineDataTuple(line_ab), None)
# line_ab = pipeline.append_step(CategoriesVisualizer.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)
#
# configuration = Configuration(name, src_corpus, tgt_corpus, src_triples, tgt_triples, gold_mapping, dim,
# pipeline, src_properties, tgt_properties)
# configuration_handler = ConfigurationHandler()
# configuration_handler.execute(configuration)
name = "3gram: W2V_1 xgb"
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(W2V_1InterfaceWrapper.interface,
PipelineDataTuple(line_a, line_b),
PipelineDataTuple(dim))
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(StratifiedVisualizer.interface,
PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(TypeVisualizer.interface,
PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(CategoriesVisualizer.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)
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples,
tgt_triples, gold_mapping, dim, pipeline,
src_properties, tgt_properties)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "3gram: D2V_1 xgb"
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(D2V_1InterfaceWrapper.interface,
PipelineDataTuple(line_a, line_b),
PipelineDataTuple(dim))
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(StratifiedVisualizer.interface,
PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(TypeVisualizer.interface,
PipelineDataTuple(line_ab), None)
line_ab = pipeline.append_step(CategoriesVisualizer.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)
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples,
tgt_triples, gold_mapping, dim, pipeline,
src_properties, tgt_properties)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
def main():
logfile = os.path.join(package_directory, '..', 'results.log')
try:
os.remove(logfile)
except:
pass
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',
'sap_hilti_gold.csv')
dim = 20
model = XGBClassifier()
name = "w2v d2v concat muse xgb"
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_a = pipeline.append_step(W2VInterfaceWrapper.interface, PipelineDataTuple(line_a), PipelineDataTuple(dim))
line_a = pipeline.append_step(D2VInterfaceWrapper.interface, PipelineDataTuple(line_a), PipelineDataTuple(dim))
line_a = pipeline.append_step(concat_combiner.interface, PipelineDataTuple(line_a), None)
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_b = pipeline.append_step(W2VInterfaceWrapper.interface, PipelineDataTuple(line_b), PipelineDataTuple(dim))
line_b = pipeline.append_step(D2VInterfaceWrapper.interface, PipelineDataTuple(line_b), PipelineDataTuple(dim))
line_b = pipeline.append_step(concat_combiner.interface, PipelineDataTuple(line_b), None)
line_ab = pipeline.append_step(muse.interface, PipelineDataTuple(line_a, line_b), PipelineDataTuple(gold_mapping))
line_ab = pipeline.append_step(FlatMatcher.interface, PipelineDataTuple(line_ab),
PipelineDataTuple(gold_mapping, model, logfile, name))
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples, tgt_triples, gold_mapping, logfile, dim,
pipeline)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "w2v d2v concat xgb"
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_a = pipeline.append_step(W2VInterfaceWrapper.interface, PipelineDataTuple(line_a), PipelineDataTuple(dim))
line_a = pipeline.append_step(D2VInterfaceWrapper.interface, PipelineDataTuple(line_a), PipelineDataTuple(dim))
line_a = pipeline.append_step(concat_combiner.interface, PipelineDataTuple(line_a), None)
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_b = pipeline.append_step(W2VInterfaceWrapper.interface, PipelineDataTuple(line_b), PipelineDataTuple(dim))
line_b = pipeline.append_step(D2VInterfaceWrapper.interface, PipelineDataTuple(line_b), PipelineDataTuple(dim))
line_b = pipeline.append_step(concat_combiner.interface, PipelineDataTuple(line_b), None)
line_ab = pipeline.append_step(FlatMatcher.interface, PipelineDataTule(line_a, line_b),
PipelineDataTuple(gold_mapping, model, logfile, name))
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples, tgt_triples, gold_mapping, logfile, dim,
pipeline)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "w2v muse xgb"
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_a = pipeline.append_step(W2VInterfaceWrapper.interface, PipelineDataTuple(line_a), PipelineDataTuple(dim))
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_b = pipeline.append_step(W2VInterfaceWrapper.interface, PipelineDataTuple(line_b), PipelineDataTuple(dim))
line_ab = pipeline.append_step(muse.interface, PipelineDataTuple(line_a, line_b), PipelineDataTuple(gold_mapping))
line_ab = pipeline.append_step(FlatMatcher.interface, PipelineDataTuple(line_ab),
PipelineDataTuple(gold_mapping, model, logfile, name))
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples, tgt_triples, gold_mapping, logfile, dim,
pipeline)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "w2v xgb"
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_a = pipeline.append_step(W2VInterfaceWrapper.interface, PipelineDataTuple(line_a), PipelineDataTuple(dim))
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_b = pipeline.append_step(W2VInterfaceWrapper.interface, PipelineDataTuple(line_b), PipelineDataTuple(dim))
line_ab = pipeline.append_step(FlatMatcher.interface, PipelineDataTuple(line_a, line_b),
PipelineDataTuple(gold_mapping, model, logfile, name))
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples, tgt_triples, gold_mapping, logfile, dim,
pipeline)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "d2v muse xgb"
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(D2VInterfaceWrapper.interface, PipelineDataTuple(line_a), PipelineDataTuple(dim))
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(D2VInterfaceWrapper.interface, PipelineDataTuple(line_b), PipelineDataTuple(dim))
line_ab = pipeline.append_step(muse.interface, PipelineDataTuple(line_a, line_b), PipelineDataTuple(gold_mapping))
line_ab = pipeline.append_step(FlatMatcher.interface, PipelineDataTuple(line_ab),
PipelineDataTuple(gold_mapping, model, logfile, name))
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples, tgt_triples, gold_mapping, logfile, dim,
pipeline)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
name = "d2v xgb"
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(D2VInterfaceWrapper.interface, PipelineDataTuple(line_a), PipelineDataTuple(dim))
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(D2VInterfaceWrapper.interface, PipelineDataTuple(line_b), PipelineDataTuple(dim))
line_ab = pipeline.append_step(FlatMatcher.interface, PipelineDataTuple(line_a, line_b),
PipelineDataTuple(gold_mapping, model, logfile, name))
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples, tgt_triples, gold_mapping, logfile, dim,
pipeline)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
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 = InternalGoldStandard({'trainsets':
[os.path.join(package_directory, '..', 'data',
'sap_hilti_data', 'sap_hilti_full_strings', 'train_simple_sap_hilti.csv'),
os.path.join(package_directory, '..', 'data', 'sap_hilti_data',
'sap_hilti_full_strings', 'train_hard_sap_hilti.csv')],
'testsets': [os.path.join(package_directory, '..', 'data',
'sap_hilti_data', 'sap_hilti_full_strings', 'test_simple_sap_hilti.csv'),
os.path.join(package_directory, '..', 'data', 'sap_hilti_data',
'sap_hilti_full_strings', 'test_hard_sap_hilti.csv')]
})
dim = 20
model = LogisticRegression()
src_properties = None#["http://rdata2graph.sap.com/hilti_erp/property/mara_fert.maktx"]
tgt_properties = None#["http://rdata2graph.sap.com/hilti_web/property/products.name"]
##name = "W2V_1 muse xgb with 50k only on embeddings"
##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(W2V_1InterfaceWrapper.interface, PipelineDataTuple(line_a, line_b), PipelineDataTuple(dim))
##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(EmbeddingMatcher.interface, PipelineDataTuple(line_ab),
## PipelineDataTuple(model))
##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)
##configuration_handler = ConfigurationHandler()
##configuration_handler.execute(configuration)
##
##
##
##
##name = "W2V_1 muse xgb with 50k on embeddings and sim"
##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(W2V_1InterfaceWrapper.interface, PipelineDataTuple(line_a, line_b), PipelineDataTuple(dim))
##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(EmbeddingMatcher.interface, PipelineDataTuple(line_ab),
## PipelineDataTuple(model))
##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)
##configuration_handler = ConfigurationHandler()
##configuration_handler.execute(configuration)
name = "jacc_no_schema_given"
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(PseudoD2V_1InterfaceWrapper_2.interface, PipelineDataTuple(line_a, line_b), PipelineDataTuple(dim))
line_ab = pipeline.append_step(SimpleTriplesEmbedder_1.interface, PipelineDataTuple(line_a, line_b), PipelineDataTuple(dim))
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)
configuration = Configuration(name, src_corpus, tgt_corpus, src_triples, tgt_triples, gold_mapping, dim,
pipeline, src_properties, tgt_properties)
configuration_handler = ConfigurationHandler()
configuration_handler.execute(configuration)
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)