def describe(self):
output = "Answers questions of the form: 'What proteins does tranilast target?' and 'What genes are affected by " \
"Fanconi anemia?'" + "\n"
output += "You can ask: 'What X does Y Z?' where X is one of the following: \n"
for label in RU.get_node_labels():
output = output + label + "\n"
output += "\n The term Y is any of the nodes that are in our graph (currently " + str(
RU.count_nodes()) + " nodes in total). \n"
output += "\n The term Z is any relationship of the following kind: \n"
for rel in RU.get_relationship_types():
rel_split = rel.split("_")
for term in rel_split:
output += term + " "
output += "\n"
output += "Assumes that Z directly connects X and Y."
return output
def test_correct_question():
"""
Point of this test is to form a bunch of sentences, match them against all queries, and make sure the correct
question template is matched
:return: None
"""
# get a random selection of nodes
property_to_nodes = dict()
for label in RU.get_node_labels():
nodes = RU.get_random_nodes(label, property="description")
property_to_nodes[label] = nodes
# import the questions
questions = []
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)), 'Questions.tsv'), 'r') as fid:
for line in fid.readlines():
if line[0] == "#":
pass
else:
questions.append(Question(line))
# form the corpora
corpora = [q.corpus for q in questions]
for q in questions:
# populate the sentence template
parameters = dict()
# ignore the what is question
if q.parameter_names and q.parameter_names[0] != "term":
for label in q.parameter_names:
node = random.choice(property_to_nodes[label])
parameters[label] = node
input_sentence = q.restate_question(parameters)
input_sentence = input_sentence.strip(string.punctuation)
# Run it against all the questions
(corpus_index, similarity) = wd.find_corpus(input_sentence, corpora)
if questions[corpus_index].restated_question_template.template != q.restated_question_template.template:
temp_parameters = questions[corpus_index].get_parameters(input_sentence)
# test if the parameters were populated
if all([val is not None for val in temp_parameters.values()]):
print("Bad classification! input: %s\n matched template: %s" % (input_sentence, questions[corpus_index].restated_question_template.template))
print(questions[corpus_index].get_parameters(input_sentence))