def test_awe_scope_map():
"""
Text axiom weight estimation, syn scopes
"""
ont = Ontology()
assert ont.nodes() == []
lexmap = LexicalMapEngine()
ont.add_node('X:1', 'x1')
ont.add_node('Y:1', 'y1')
ont.add_node('Z:1', 'z1')
ont.add_synonym(Synonym('X:1', val='related', pred='hasRelatedSynonym'))
ont.add_synonym(Synonym('Y:1', val='related', pred='hasRelatedSynonym'))
ont.add_synonym(Synonym('Y:1', val='exact', pred='hasExactSynonym'))
ont.add_synonym(Synonym('Z:1', val='exact', pred='hasExactSynonym'))
lexmap.index_ontology(ont)
xg = lexmap.get_xref_graph()
df = lexmap.as_dataframe(xg)
print(df.to_csv(sep="\t"))
P_XY = lexmap.weighted_axioms('X:1', 'Y:1', xg)
P_YZ = lexmap.weighted_axioms('Y:1', 'Z:1', xg)
logging.info('P_XY={} P_XZ={}'.format(P_XY, P_YZ))
assert P_XY[2] > P_XY[0]
assert P_XY[2] > P_XY[1]
assert P_XY[2] > P_XY[3]
assert P_XY[2] < P_YZ[2]
def test_awe_1_to_many_default():
"""
As previous test, but with defaults
"""
ont = Ontology()
lexmap = LexicalMapEngine(
config={
'cardinality_weights': [{
'cardinality': 'm1',
'weights': [1.0, -1.0, -2.0, 0.0]
}]
})
ont.add_node('X:1', 'foo 1')
ont.add_node('Y:1a', 'foo 1a')
ont.add_synonym(Synonym('Y:1a', val='foo 1', pred='hasRelatedSynonym'))
ont.add_node('Y:1b', 'foo 1b')
ont.add_synonym(Synonym('Y:1b', val='foo 1', pred='hasExactSynonym'))
lexmap.index_ontology(ont)
xg = lexmap.get_xref_graph()
df = lexmap.as_dataframe(xg)
print(df.to_csv(sep="\t"))
P = lexmap.weighted_axioms('X:1', 'Y:1a', xg)
logging.info('P={}'.format(P))
assert P[0] < P[1]
assert P[1] > P[2]
def test_awe_1_to_many_flat():
"""
Text axiom weight estimation, for a 1-to-many situation, where the many are not inter-related
"""
ont = Ontology()
lexmap = LexicalMapEngine(
config={
'cardinality_weights': [{
'prefix1': 'X',
'prefix2': 'Y',
'cardinality': '1m',
'weights': [-1.0, 1.0, -2.0, 0.0]
}]
})
ont.add_node('X:1', 'foo 1')
ont.add_node('Y:1a', 'foo 1a')
ont.add_synonym(Synonym('Y:1a', val='foo 1', pred='hasRelatedSynonym'))
ont.add_node('Y:1b', 'foo 1b')
ont.add_synonym(Synonym('Y:1b', val='foo 1', pred='hasExactSynonym'))
lexmap.index_ontology(ont)
xg = lexmap.get_xref_graph()
df = lexmap.as_dataframe(xg)
print(df.to_csv(sep="\t"))
P = lexmap.weighted_axioms('X:1', 'Y:1a', xg)
logging.info('P={}'.format(P))
assert P[0] < P[1]
assert P[1] > P[2]
def test_mutable():
"""
Test mutability of ontology class
"""
ont = Ontology()
ont.add_node('TEST:1', 'foo bar')
ont.add_node('TEST:2', 'bar foo')
ont.add_node('TEST:3', 'foo bar')
ont.add_node('TEST:4', 'wiz')
syn = Synonym('TEST:4', val='bar foo', pred='hasExactSynonym')
ont.add_synonym(syn)
w = GraphRenderer.create('obo')
w.write(ont)
for n in ont.nodes():
meta = ont._meta(n)
print('{} -> {}'.format(n, meta))
assert ont.label('TEST:1') == 'foo bar'
assert ont.synonyms('TEST:1') == []
assert ont.synonyms('TEST:4')[0].val == 'bar foo'
def test_lexmap_basic():
"""
Text lexical mapping
"""
factory = OntologyFactory()
print("Creating ont")
ont = factory.create('tests/resources/lexmap_test.json')
lexmap = LexicalMapEngine()
lexmap.index_ontology(ont)
print(lexmap.lmap)
print(ont.all_synonyms())
g = lexmap.get_xref_graph()
for x, y, d in g.edges_iter(data=True):
print("{}<->{} :: {}".format(x, y, d))
for x in g.nodes():
print("{} --> {}".format(x, lexmap.grouped_mappings(x)))
assert g.has_edge('Z:2', 'ZZ:2') # roman numerals
assert g.has_edge('Z:2', 'Y:2') # case insensitivity
assert g.has_edge('A:1', 'B:1') # synonyms
assert g.has_edge('B:1', 'A:1') # bidirectional
for x, y, d in g.edges_iter(data=True):
print("{}<->{} :: {}".format(x, y, d))
cpr = d[lexmap.CONDITIONAL_PR]
assert cpr > 0 and cpr <= 1.0
df = lexmap.as_dataframe(g)
print(df.to_csv(sep="\t"))
lexmap = LexicalMapEngine(
config=dict(synsets=[dict(word="", synonym="ignoreme", weight=-2.0)],
normalized_form_confidence=0.25,
abbreviation_confidence=0.5,
meaningful_ids=True,
ontology_configurations=[
dict(prefix='AA', normalized_form_confidence=-1000)
]))
assert len(lexmap._get_config_val('NULL', 'synsets')) == 1
assert lexmap._normalize_label('ignoreme foo', {'ignoreme': ''}) == 'foo'
assert lexmap._normalize_label('replaceme foo',
{'replaceme': 'zz'}) == 'foo zz'
ont.add_node('TEST:1', 'foo bar')
ont.add_node('TEST:2', 'bar foo')
ont.add_node('TEST:3', 'foo bar')
ont.add_node('TEST:4', 'wiz')
syn = Synonym('TEST:4', val='bar foo', pred='hasRelatedSynonym')
ont.add_synonym(syn)
ont.add_node('http://x.org/wiz#FooBar')
ont.add_node('TEST:6', '123')
ont.add_node('TEST:7', '123')
ont.add_node('TEST:8', 'bar ignoreme foo')
ont.add_node('AA:1', 'foo bar')
ont.add_node('AA:2', 'bar foo')
ont.add_node('ABBREV:1', 'ABCD')
ont.add_node('ABBREV:2', 'ABCD')
for s in ont.synonyms('TEST:4'):
print('S={}'.format(s))
lexmap.index_ontology(ont)
g = lexmap.get_xref_graph()
for x, d in g['TEST:1'].items():
print('XREF: {} = {}'.format(x, d))
assert g.has_edge('TEST:1', 'TEST:2') # normalized
logging.info('E 1-2 = {}'.format(g['TEST:1']['TEST:2']))
assert int(g['TEST:1']['TEST:2']['score']) == 25
assert int(g['TEST:1']['TEST:3']['score']) == 100
assert int(g['TEST:1']['TEST:4']['score']) < 25
assert g.has_edge('TEST:3', 'http://x.org/wiz#FooBar') # IDs and CamelCase
assert not g.has_edge('TEST:6',
'TEST:7') # should omit syns with no alphanumeric
# test exclude normalized form
assert not g.has_edge('AA:1', 'AA:2')
# test custom synsets are used
assert g.has_edge('TEST:8', 'TEST:2')
assert g.has_edge('TEST:8', 'AA:2')
assert not g.has_edge('TEST:8', 'AA:1') # do not normalize AAs
assert lexmap.smap['ABBREV:1'][0].is_abbreviation()
assert lexmap.smap['ABBREV:2'][0].is_abbreviation()
assert g.has_edge('ABBREV:1', 'ABBREV:2')
assert int(g['ABBREV:1']['ABBREV:2']['score']) == 25
df = lexmap.unmapped_dataframe(g)
print(df.to_csv())