def test_split_train_test_set():
vr = split_training_test_set(associations)
train, test = vr
logger.info("just random: train: %d, test: %d", len(train), len(test))
vtnd = split_training_test_set(associations, variant='target_node_disjoint')
train, test = vtnd
logger.info("target node disjoint: train: %d, test: %d",
len(train), len(test))
vnd = split_training_test_set(associations, variant='node_disjoint')
train, test = vnd
logger.info("node disjoint: train: %d, test: %d", len(train), len(test))
assert vr[0] == vtnd[0] == vnd[0], \
"train set shouldn't be influenced by different splitting variant"
assert set(vr[1]) > set(vtnd[1]) > set(vnd[1]), \
"test set expected to shrink for more restrictive splitting variants"
def test_split_train_test_set():
vr = split_training_test_set(associations)
train, test = vr
logger.info("just random: train: %d, test: %d", len(train), len(test))
vtnd = split_training_test_set(associations, variant='target_node_disjoint')
train, test = vtnd
logger.info("target node disjoint: train: %d, test: %d",
len(train), len(test))
vnd = split_training_test_set(associations, variant='node_disjoint')
train, test = vnd
logger.info("node disjoint: train: %d, test: %d", len(train), len(test))
assert vr[0] == vtnd[0] == vnd[0], \
"train set shouldn't be influenced by different splitting variant"
assert set(vr[1]) > set(vtnd[1]) > set(vnd[1]), \
"test set expected to shrink for more restrictive splitting variants"
def main():
semantic_associations = get_semantic_associations(
config.GT_ASSOCIATIONS_FILENAME)
assocs_train, assocs_test = split_training_test_set(semantic_associations,
variant='random')
# setup node expander
sparql = SPARQLWrapper(config.SPARQL_ENDPOINT)
predict_set = assocs_test
for method, query in sorted(prediction_queries.items()):
target_idxs = []
for source, target in predict_set:
prediction = predict_target_with_query(sparql, query, source)
target_idxs.append(find_in_prediction(prediction, target))
print("'%s': %s," % (method, target_idxs))
def main():
semantic_associations = get_semantic_associations(
config.GT_ASSOCIATIONS_FILENAME)
assocs_train, assocs_test = split_training_test_set(
semantic_associations, variant='random'
)
# setup node expander
sparql = SPARQLWrapper(config.SPARQL_ENDPOINT)
predict_set = assocs_test
for method, query in sorted(prediction_queries.items()):
target_idxs = []
for source, target in predict_set:
prediction = predict_target_with_query(sparql, query, source)
target_idxs.append(find_in_prediction(prediction, target))
print("'%s': %s," % (method, target_idxs))
def main():
semantic_associations = get_semantic_associations(
config.GT_ASSOCIATIONS_FILENAME)
assocs_train, assocs_test = split_training_test_set(
semantic_associations, variant='random'
)
# setup node expander
sparql = SPARQLWrapper(config.SPARQL_ENDPOINT)
predict_list = assocs_test
# degree, pagerank and hits
for method, query in sorted(prediction_queries.items()):
target_idxs = []
for source, target in predict_list:
logger.info(
'method: %s, predicting targets for %s, ground truth: %s',
method, source.n3(), target.n3())
prediction = predict_target_with_query(sparql, query, source)
idx = find_in_prediction(prediction, target)
logger.info(
format_prediction_results(method, prediction, target, idx))
target_idxs.append(idx)
print("'%s': %s," % (method, target_idxs))
# milne-witten relatedness
for method, pred in (('mw_wl', 'dbo:wikiPageWikiLink'),):
target_idxs = []
for source, target in predict_list:
logger.info(
'method: %s, predicting targets for %s, ground truth: %s',
method, source.n3(), target.n3())
prediction = predict_target_with_milne_witten(sparql, pred, source)
idx = find_in_prediction(prediction, target)
logger.info(
format_prediction_results(method, prediction, target, idx))
target_idxs.append(idx)
print("'%s': %s," % (method, target_idxs))
def main():
semantic_associations = get_semantic_associations(
config.GT_ASSOCIATIONS_FILENAME)
assocs_train, assocs_test = split_training_test_set(semantic_associations,
variant='random')
# setup node expander
sparql = SPARQLWrapper(config.SPARQL_ENDPOINT)
predict_list = assocs_test
# degree, pagerank and hits
for method, query in sorted(prediction_queries.items()):
target_idxs = []
for source, target in predict_list:
logger.info(
'method: %s, predicting targets for %s, ground truth: %s',
method, source.n3(), target.n3())
prediction = predict_target_with_query(sparql, query, source)
idx = find_in_prediction(prediction, target)
logger.info(
format_prediction_results(method, prediction, target, idx))
target_idxs.append(idx)
print("'%s': %s," % (method, target_idxs))
# milne-witten relatedness
for method, pred in (('mw_wl', 'dbo:wikiPageWikiLink'), ):
target_idxs = []
for source, target in predict_list:
logger.info(
'method: %s, predicting targets for %s, ground truth: %s',
method, source.n3(), target.n3())
prediction = predict_target_with_milne_witten(sparql, pred, source)
idx = find_in_prediction(prediction, target)
logger.info(
format_prediction_results(method, prediction, target, idx))
target_idxs.append(idx)
print("'%s': %s," % (method, target_idxs))
from gp_learner import mutate_merge_var
from gp_learner import mutate_simplify_pattern
from graph_pattern import GraphPattern
from graph_pattern import SOURCE_VAR
from graph_pattern import TARGET_VAR
from ground_truth_tools import get_semantic_associations
from ground_truth_tools import split_training_test_set
from gtp_scores import GTPScores
logger = logging.getLogger(__name__)
dbp = rdflib.Namespace('http://dbpedia.org/resource/')
wikilink = URIRef('http://dbpedia.org/ontology/wikiPageWikiLink')
ground_truth_pairs = get_semantic_associations()
ground_truth_pairs, _ = split_training_test_set(ground_truth_pairs)
gtp_scores = GTPScores(ground_truth_pairs)
def test_mutate_increase_dist():
gp = GraphPattern([(SOURCE_VAR, wikilink, TARGET_VAR)])
res = mutate_increase_dist(gp)
assert gp != res
assert gp.diameter() + 1 == res.diameter()
assert gp.vars_in_graph == {SOURCE_VAR, TARGET_VAR}
def test_mutate_merge_var():
p = Variable('p')
q = Variable('q')
gp = GraphPattern([(SOURCE_VAR, p, TARGET_VAR)])
from gp_learner import mutate_merge_var
from gp_learner import mutate_simplify_pattern
from graph_pattern import GraphPattern
from graph_pattern import SOURCE_VAR
from graph_pattern import TARGET_VAR
from ground_truth_tools import get_semantic_associations
from ground_truth_tools import split_training_test_set
from gtp_scores import GTPScores
logger = logging.getLogger(__name__)
dbp = rdflib.Namespace('http://dbpedia.org/resource/')
wikilink = URIRef('http://dbpedia.org/ontology/wikiPageWikiLink')
ground_truth_pairs = get_semantic_associations()
ground_truth_pairs, _ = split_training_test_set(ground_truth_pairs)
gtp_scores = GTPScores(ground_truth_pairs)
def test_mutate_increase_dist():
gp = GraphPattern([(SOURCE_VAR, wikilink, TARGET_VAR)])
res = mutate_increase_dist(gp)
assert gp != res
assert gp.diameter() + 1 == res.diameter()
assert gp.vars_in_graph == {SOURCE_VAR, TARGET_VAR}
def test_mutate_merge_var():
p = Variable('p')
q = Variable('q')
gp = GraphPattern([