def test_fit(self):
model_path = fth.fasttext_fit(self.train_path, {'-bucket': 1000},
self.ft_path,
model_path=self.model_path,
thread=1,
compress_model=False)
expected_model_path = self.model_path + '.bin'
assert model_path == expected_model_path
assert os.path.isfile(model_path)
os.remove(model_path)
def test_predict(self):
model_path = fth.fasttext_fit(self.train_path, {'-bucket': 1000},
self.ft_path,
model_path=self.model_path,
thread=1,
compress_model=False)
fth.fasttext_predict(model_path, self.test_path, self.ft_path,
self.probability_path)
assert os.path.isfile(self.probability_path)
os.remove(model_path)
os.remove(self.probability_path)
def test_fit_pretrained_vectors(self):
model_path = fth.fasttext_fit(
self.train_path, {'-bucket': 1000},
self.ft_path,
model_path=self.model_path,
thread=1,
compress_model=False,
pretrained_vectors_path=self.pretrained_vectors_path)
expected_model_path = self.model_path + '.bin'
self.assertEqual(model_path, expected_model_path)
self.assertTrue(os.path.isfile(model_path))
os.remove(model_path)
def test_fit_compressed(self):
model_path = fth.fasttext_fit(self.train_path, {
'-bucket': 1000,
'-wordNgrams': 2
},
self.ft_path,
model_path=self.model_path,
thread=1,
compress_model=True)
expected_model_path = self.model_path + '.ftz'
assert model_path == expected_model_path
assert os.path.isfile(model_path)
os.remove(model_path)
def test_fasttext_class_probabilities(self):
model_path = fth.fasttext_fit(self.train_path, {'-bucket': 1000},
self.ft_path,
model_path=self.model_path,
thread=1,
compress_model=False)
fth.fasttext_predict(model_path, self.test_path, self.ft_path,
self.probability_path)
probabilities = fth.load_fasttext_class_probabilities(
self.probability_path)
assert len(probabilities) == 40
assert all([x > 0.75 for x in probabilities[:20]])
assert all([x < 0.25 for x in probabilities[20:]])
os.remove(model_path)
os.remove(self.probability_path)
compression='infer',
header=None,
index_col=None)
test_df.columns = [
'pmid', 'paragraph', 'sentence', 'entity1', 'entity2', 'text', 'class',
'distance', 'pairs', 'key'
]
del test_df['key']
del test_df['pairs']
perfomance = list()
for i in range(repeats):
model_file = fasttext_fit(ft_train_path,
ft_params,
fasttext_path,
thread=ft_threads,
compress_model=True,
model_path=tmp_model_path + str(i),
pretrained_vectors_path=pretrained_embeddings)
fth.fasttext_predict(tmp_model_path + str(i) + '.ftz', ft_test_path,
fasttext_path, prob_path)
probabilities = fth.load_fasttext_class_probabilities(prob_path)
test_df = test_df.assign(predicted=probabilities)
_, tmp_file_path = tempfile.mkstemp(text=True, suffix='.gz')
with gzip.open(tmp_file_path, 'wt') as test_out:
test_df.to_csv(test_out,
sep='\t',
header=False,
index=False,
