def specifier_before_cem_and_value_phrase(self):
return (
self.specifier_phrase
+ OneOrMore(Not(self.cem_phrase | self.specifier_phrase | self.value_phrase) + Any().hide())
+ self.cem_phrase
+ OneOrMore(Not(self.cem_phrase | self.specifier_phrase | self.value_phrase) + Any().hide())
+ Optional(self.prefix)
+ self.value_phrase)('root_phrase')
def specifier_before_cem_and_value_phrase(self):
return (self.specifier_phrase + OneOrMore(
Not(self.cem_phrase | self.specifier_phrase | self.value_phrase) +
Any().hide()) #+ self.connection + Optional(self.article))
+ self.cem_phrase + OneOrMore(
Not(self.cem_phrase | self.specifier_phrase
| I('dielectric') + I('constant') | self.value_phrase
| I('not')) + Any().hide()) + Optional(self.prefix) +
self.value_phrase)('root_phrase')
def multi_entity_phrase_2(self):
"""single compound, single specifier, multiple transitions
e.g. BiFeO3 shows magnetic transitions at 1093 and 640 K
"""
return Group(self.single_cem
+ OneOrMore(Not(self.single_cem | self.specifier_phrase | self.value_phrase) + Any().hide())
+ self.specifier_phrase
+ OneOrMore(Not(self.single_cem | self.specifier_phrase | self.value_phrase) + Any().hide())
+ self.list_of_values
+ Optional(delim).hide()
+ Optional(I('respectively')))('multi_entity_phrase_2')
def multi_entity_phrase_4a(self):
"""multiple compounds, single specifier, single transition
e.g. TC of 640 K in BifEO3, LaFeO3 and MnO
"""
return Group(self.single_specifier_and_value
+ OneOrMore(Not(self.single_cem | self.specifier_phrase | self.value_phrase) + Any().hide())
+ self.list_of_cems)('multi_entity_phrase_4')
def multi_entity_phrase_1(self):
"""Single compound, multiple specifiers, values
e.g. BiFeO3 has TC1 = 1093 K and Tc2 = 640 K
"""
return Group(self.single_cem
+ OneOrMore(Not(self.single_cem | self.specifier_phrase | self.value_phrase) + Any().hide())
+ self.list_of_properties)('multi_entity_phrase_1')
def list_of_values(self):
"""List of values with either multiple units or one at the end"""
# option 1: single unit at the end
option_1 = Group(self.value_with_optional_unit
+ Optional(OneOrMore(delim.hide() + self.value_with_optional_unit))
+ Optional(delim).hide()
+ (I('and') | I('or')).hide()
+ Optional(delim).hide()
+ self.value_phrase)('value_list')
# option 2: Multiple units
option_2 = (self.value_phrase
+ Optional(OneOrMore(delim.hide() + self.value_phrase))
+ Optional(delim).hide()
+ (I('and') | I('or') | delim).hide()
+ self.value_phrase)('value_list')
return (option_1 | option_2)
def cem_before_specifier_and_value_phrase(self):
return (self.cem_phrase + OneOrMore(
Not(self.cem_phrase | self.specifier_phrase
| self.specifier_and_value) +
Any().hide()) #+ self.between_cem_specifier)
+ self.specifier_phrase +
self.specifier_and_value)('root_phrase')
def multi_entity_phrase_3a(self):
"""multiple compounds, single specifier, multiple transitions cems first
e.g. TC in BiFeO3 and LaFeO3 of 640 and 750 K
"""
return Group(Optional(self.specifier_phrase)
+ Optional(I('in') | I('for')).hide()
+ self.list_of_cems
+ OneOrMore(Not(self.single_cem | self.specifier_phrase | self.value_phrase) + Any().hide())
+ self.prefix
+ self.list_of_values
+ Optional(delim.hide() + I('respectively').hide()))('multi_entity_phrase_3')
def multi_entity_phrase_4b(self):
"""Cems first"""
return Group(self.list_of_cems
+ OneOrMore(Not(self.single_cem | self.specifier_phrase | self.value_phrase) + Any().hide())
+ self.single_specifier_and_value)('multi_entity_phrase_4')
def cem_after_specifier_and_value_phrase(self):
return (
self.specifier_and_value
+ OneOrMore(Not(self.cem_phrase | self.specifier_phrase | self.value_phrase) + Any().hide())
+ self.cem_phrase)('root_phrase')
# Add to the available models
Compound.curie_temperatures = ListType(ModelType(CurieTemperature))
# Define a very basic entity tagger
specifier = (I('curie') + I('temperature') + Optional(lrb | delim) +
Optional(R('^T(C|c)(urie)?')) + Optional(rrb)
| R('^T(C|c)(urie)?'))('specifier').add_action(join)
units = (R('^[CFK]\.?$'))('units').add_action(merge)
value = (R('^\d+(\.\,\d+)?$'))('value')
# Let the entities be any combination of chemical names, specifier values and units
entities = (chemical_name | specifier | value + units)
# Now create a very generic parse phrase that will match any combination of these entities
curie_temperature_phrase = (entities +
OneOrMore(entities | Any()))('curie_temperature')
curie_temp_entities = [chemical_name, specifier, value, units]
# Define the relationship and give it a name
curie_temp_relationship = ChemicalRelationship(curie_temp_entities,
curie_temperature_phrase,
name='curie_temperatures')
# class TestSnowball(unittest.TestCase):
# maxDiff = None
# training_corpus = 'tests/data/relex/curie_training/'
# snowball_pkl = 'tests/data/relex/curie_temperatures.pkl'
# snowball_pkl_py2 = 'tests/data/relex/curie_temperatures_py2.pkl'
# def test_load_snowball(self):