def test_to_indexed_instance_converts_correctly(self):
instance = QuestionAnswerInstance("a A b", ["d", "e f D"], 1)
data_indexer = DataIndexer()
a_index = data_indexer.add_word_to_index("a")
d_index = data_indexer.add_word_to_index("d")
oov_index = data_indexer.get_word_index(data_indexer._oov_token) # pylint: disable=protected-access
indexed_instance = instance.to_indexed_instance(data_indexer)
assert indexed_instance.question_indices == [a_index, a_index, oov_index]
assert len(indexed_instance.option_indices) == 2
assert indexed_instance.option_indices[0] == [d_index]
assert indexed_instance.option_indices[1] == [oov_index, oov_index, d_index]
def read_instance_message(self, instance_message):
# pylint: disable=redefined-variable-type
instance_type = instance_message.type
if instance_type == message_pb2.TRUE_FALSE:
text = instance_message.question
instance = TrueFalseInstance(text, None, None)
elif instance_type == message_pb2.MULTIPLE_TRUE_FALSE:
options = []
for instance in instance_message.contained_instances:
options.append(self.read_instance_message(instance))
instance = MultipleTrueFalseInstance(options)
elif instance_type == message_pb2.QUESTION_ANSWER:
question = instance_message.question
options = instance_message.answer_options
instance = QuestionAnswerInstance(question, options, None, None)
elif instance_type == message_pb2.CHARACTER_SPAN:
question = instance_message.question
passage = instance_message.passage
instance = CharacterSpanInstance(question, passage, None, None)
else:
raise RuntimeError("Unrecognized instance type: " + instance_type)
if instance_message.background_instances:
background = instance_message.background_instances
background_instances = [
self.read_instance_message(instance) for instance in background
]
instance = BackgroundInstance(instance, background_instances)
return instance
def test_read_from_line_handles_three_column(self):
question = "what is the answer"
answers = ['a', 'b', 'c']
label = 1
line = self.instance_to_line(question, answers, label)
instance = QuestionAnswerInstance.read_from_line(line)
assert instance.question_text == question
assert instance.answer_options == answers
assert instance.label is label
assert instance.index is None
def test_words_includes_question_and_answers(self):
instance = QuestionAnswerInstance("a b c", ["d", "e f"], 1)
assert instance.words() == {'words': ['a', 'b', 'c', 'd', 'e', 'f']}