def test_qaranker_local_integration(self):
relations = Relations.read(self.qa_path + "/relations.txt")
assert len(relations) == 4
text_set = TextSet.read_csv(self.qa_path + "/question_corpus.csv")
assert text_set.get_uris() == ["Q1", "Q2"]
transformed = text_set.tokenize().normalize().word2idx(
).shape_sequence(5)
relation_pairs = TextSet.from_relation_pairs(relations, transformed,
transformed)
pair_samples = relation_pairs.get_samples()
assert len(pair_samples) == 2
for sample in pair_samples:
assert list(sample.feature.shape) == [2, 10]
assert np.allclose(sample.label.to_ndarray(),
np.array([[1.0], [0.0]]))
relation_lists = TextSet.from_relation_lists(relations, transformed,
transformed)
relation_samples = relation_lists.get_samples()
assert len(relation_samples) == 2
for sample in relation_samples:
assert list(sample.feature.shape) == [2, 10]
assert list(sample.label.shape) == [2, 1]
knrm = KNRM(5,
5,
self.glove_path,
word_index=transformed.get_word_index())
model = Sequential().add(TimeDistributed(knrm, input_shape=(2, 10)))
model.compile("sgd", "rank_hinge")
model.fit(relation_pairs, batch_size=2, nb_epoch=2)
print(knrm.evaluate_ndcg(relation_lists, 3))
print(knrm.evaluate_map(relation_lists))
model.add(LSTM(
10,
return_sequences=False))
model.add(Dropout(0.2))
model.add(Dense(
output_dim=1))
model.compile(loss='mse', optimizer='rmsprop')
%%time
# Train the model
print("Training begins.")
model.fit(
x_train,
y_train,
batch_size=1024,
nb_epoch=20)
print("Training completed.")
# create the list of difference between prediction and test data
diff=[]
ratio=[]
predictions = model.predict(x_test)
p = predictions.collect()
for u in range(len(y_test)):
pr = p[u][0]
ratio.append((y_test[u]/pr)-1)
diff.append(abs(y_test[u]- pr))
# plot the predicted values and actual values (for the test data)
train_relations = Relations.read(options.data_path + "/relation_train.csv",
sc, int(options.partition_num))
train_set = TextSet.from_relation_pairs(train_relations, q_set, a_set)
validate_relations = Relations.read(options.data_path + "/relation_valid.csv",
sc, int(options.partition_num))
validate_set = TextSet.from_relation_lists(validate_relations, q_set, a_set)
if options.model:
knrm = KNRM.load_model(options.model)
else:
word_index = a_set.get_word_index()
knrm = KNRM(int(options.question_length), int(options.answer_length),
options.embedding_file, word_index)
model = Sequential().add(
TimeDistributed(
knrm,
input_shape=(2, int(options.question_length) + int(options.answer_length))))
model.compile(optimizer=SGD(learningrate=float(options.learning_rate)),
loss="rank_hinge")
for i in range(0, int(options.nb_epoch)):
model.fit(train_set, batch_size=int(options.batch_size), nb_epoch=1)
knrm.evaluate_ndcg(validate_set, 3)
knrm.evaluate_ndcg(validate_set, 5)
knrm.evaluate_map(validate_set)
if options.output_path:
knrm.save_model(options.output_path + "/knrm.model")
a_set.save_word_index(options.output_path + "/word_index.txt")
print("Trained model and word dictionary saved")
sc.stop()
