def run(pipeline):
'''Run a complete pipeline of graph operations.
Parameters
----------
pipeline : dict
The pipeline description.
Returns
-------
The result from running the pipeline with the provided arguments.
'''
# INPUT
if 'graph' in pipeline:
graph = pipeline['graph']
elif 'text' in pipeline:
ts = []
try:
ts.append(pipeline.get('parser', DEF_PARSER) + '_parse')
except KeyError:
pass
try:
ts += pipeline.get('transformers', DEF_TRANSFORMERS)
T = transformers.get_pipeline(ts)
except KeyError:
raise ValueError("Unknown transformer pipeline")
T_args = pipeline.get('transformer_args', DEF_T_ARGS)
graph = CG(transformer=T,
transformer_args=T_args,
text=pipeline['text'])
else:
raise ValueError('Must provide either graph or text')
# OPERATIONS
for operation in pipeline.get('operations', []):
try:
name = operation.pop('op')
except KeyError:
raise ValueError("No name for the operation")
try:
graph = operate(graph, name, **operation)
except TypeError as e:
raise ValueError(e)
operation['op'] = name
# OUTPUT
if 'linearizers' in pipeline:
try:
L = linearizers.get_pipeline(
pipeline.get('linearizers', DEF_LINEARIZERS))
except KeyError:
raise ValueError("Unknown linearizer pipeline")
L_args = pipeline.get('linearizer_args', DEF_L_ARGS)
return graph.linearize(linearizer=L, linearizer_args=L_args)
else:
return graph
def run (pipeline):
'''Run a complete pipeline of graph operations.
Parameters
----------
pipeline : dict
The pipeline description.
Returns
-------
The result from running the pipeline with the provided arguments.
'''
# INPUT
if 'graph' in pipeline:
graph = pipeline['graph']
elif 'text' in pipeline:
ts = []
try:
ts.append(pipeline.get('parser', DEF_PARSER)+'_parse')
except KeyError:
pass
try:
ts += pipeline.get('transformers', DEF_TRANSFORMERS)
T = transformers.get_pipeline(ts)
except KeyError:
raise ValueError("Unknown transformer pipeline")
T_args = pipeline.get('transformer_args', DEF_T_ARGS)
graph = CG(transformer=T,transformer_args=T_args,text=pipeline['text'])
else:
raise ValueError('Must provide either graph or text')
# OPERATIONS
for operation in pipeline.get('operations', []):
try:
name = operation.pop('op')
except KeyError:
raise ValueError("No name for the operation")
try:
graph = operate(graph, name, **operation)
except TypeError as e:
raise ValueError(e)
operation['op'] = name
# OUTPUT
if 'linearizers' in pipeline:
try:
L = linearizers.get_pipeline(pipeline.get('linearizers', DEF_LINEARIZERS))
except KeyError:
raise ValueError("Unknown linearizer pipeline")
L_args = pipeline.get('linearizer_args', DEF_L_ARGS)
return graph.linearize(linearizer=L,linearizer_args=L_args)
else:
return graph
class Analysis:
def __init__(self, text, superficial=False, autocorrect=True):
# Corrects posible misspelled words in the queries
if autocorrect:
self.text = correct_phrase(text)
else:
self.text = text
if superficial:
# Parses the query without generating the semantic graph
self.parse = nlp(self.text)
else:
# Deeply parses the query generating the semantic graph
self.graph = CG(transformer=semantic_analyzer, text=self.text)
self.parse = self.graph.spacy_parse
#Returns the similarity between this object and another of its same type.
def similarity(self, other):
return self.parse.similarity(other.parse)
#Returns the most relevant terms from the analyzed text represented by this object.
def content_words(self):
return [
tok.lemma_ for tok in self.parse
if not (tok.is_stop or tok.is_punct)
]
# Generates MATCH queries to solve the question introduce by the user
def cypher_query(self, ground_id):
if self.graph.question_type == closed:
return self.graph.linearize(linearizer=cypher_closed_linearizer,
linearizer_args={
'cypher_extra_params': {
'ground_id': ground_id
}
})
elif self.graph.question_type == open:
return self.graph.linearize(linearizer=cypher_open_linearizer,
linearizer_args={
'cypher_extra_params': {
'ground_id': ground_id
}
})
# Generates CREATE queries to add the information to the NEO4J graph database
def cypher_create(self, ground_id):
return self.graph.linearize(
linearizer=cypher_create_linearizer,
linearizer_args={'cypher_extra_params': {
'ground_id': ground_id
}})
class Analysis:
def __init__(self, text, superficial=False, autocorrect=True):
if autocorrect:
self.text = correct_phrase(text)
else:
self.text = text
if superficial:
self.parse = nlp(self.text)
else:
self.graph = CG(transformer=semantic_analyzer, text=self.text)
self.parse = self.graph.spacy_parse
def similarity(self, other):
return self.parse.similarity(other.parse)
def content_words(self):
return [
tok.lemma_ for tok in self.parse
if not (tok.is_stop or tok.is_punct)
]
def cypher_query(self, ground_id):
if self.graph.question_type == closed:
return self.graph.linearize(linearizer=cypher_closed_linearizer,
linearizer_args={
'cypher_extra_params': {
'ground_id': ground_id
}
})
elif self.graph.question_type == open:
return self.graph.linearize(linearizer=cypher_open_linearizer,
linearizer_args={
'cypher_extra_params': {
'ground_id': ground_id
}
})
def cypher_create(self, ground_id):
return self.graph.linearize(
linearizer=cypher_create_linearizer,
linearizer_args={'cypher_extra_params': {
'ground_id': ground_id
}})
def __init__(self, text, superficial=False, autocorrect=True):
if autocorrect:
self.text = correct_phrase(text)
else:
self.text = text
if superficial:
self.parse = nlp(self.text)
else:
self.graph = CG(transformer=semantic_analyzer, text=self.text)
self.parse = self.graph.spacy_parse
def __init__(self, text, superficial=False, autocorrect=True):
# Corrects posible misspelled words in the queries
if autocorrect:
self.text = correct_phrase(text)
else:
self.text = text
if superficial:
# Parses the query without generating the semantic graph
self.parse = nlp(self.text)
else:
# Deeply parses the query generating the semantic graph
self.graph = CG(transformer=semantic_analyzer, text=self.text)
self.parse = self.graph.spacy_parse
def operate(graph, **args):
subgraph, main_entity = spot_domain(graph)
r = CG(graph, subgraph=subgraph)
r.gram['main_entity'] = main_entity
return r
def compose_answer(question, answer_graph):
g = CG(original=question.graph)
graft(g, question.graph.questions[0], answer_graph, answer_graph.roots[0])
return (g.linearize(linearizer=nlg))
def operate (graph, **args):
subgraph, main_entity = spot_domain(graph)
r = CG(graph, subgraph=subgraph)
r.gram['main_entity'] = main_entity
return r