def test_save_load(self):
# Create a model with a downstream task
tw = TextWiser(Embedding.Word(word_option=WordOptions.word2vec,
pretrained='en-turian'),
[
Transformation.SVD(n_components=2),
Transformation.Pool(pool_option=PoolOptions.mean)
],
dtype=torch.float32)
tw.fit(docs)
model = nn.Sequential(tw, nn.Linear(2, 1)).to(device)
# Get results of the model
expected = model(docs)
# Save the model to a temporary file
with NamedTemporaryFile() as file:
torch.save(model.state_dict(), file) # Use string name of the file
# Get rid of the original model
del tw
del model
# Create the same model
tw = TextWiser(Embedding.Word(
word_option=WordOptions.word2vec, pretrained='en-turian'), [
Transformation.SVD(n_components=2),
Transformation.Pool(pool_option=PoolOptions.mean)
],
dtype=torch.float32)
tw.fit()
model = nn.Sequential(tw, nn.Linear(2, 1)).to(device)
# Load the model from file
file.seek(0)
model.load_state_dict(torch.load(file, map_location=device))
# Do predictions with the loaded model
predicted = model(docs)
self.assertTrue(torch.allclose(predicted, expected, atol=1e-6))
def test_dtype(self):
tw = TextWiser(Embedding.Word(word_option=WordOptions.word2vec,
pretrained='en-turian'),
Transformation.Pool(pool_option=PoolOptions.max),
dtype=torch.float32)
predicted = tw.fit_transform(docs)
self.assertEqual(predicted.dtype, torch.float32)
tw = TextWiser(Embedding.Word(word_option=WordOptions.word2vec,
pretrained='en-turian'),
Transformation.Pool(pool_option=PoolOptions.max),
dtype=np.float32)
predicted = tw.fit_transform(docs)
self.assertEqual(predicted.dtype, np.float32)
with warnings.catch_warnings():
warnings.simplefilter("ignore")
tw = TextWiser(Embedding.Word(word_option=WordOptions.word2vec,
pretrained='en-turian'),
dtype=torch.float32)
predicted = tw.fit_transform(docs)
self.assertEqual(predicted[0].dtype, torch.float32)
tw = TextWiser(Embedding.Word(word_option=WordOptions.word2vec,
pretrained='en-turian'),
dtype=np.float32)
predicted = tw.fit_transform(docs)
self.assertEqual(predicted[0].dtype, np.float32)
def _test_index(self, pool_option):
index = 0 if pool_option == PoolOptions.first else -1
with warnings.catch_warnings():
warnings.simplefilter("ignore")
tw = TextWiser(Embedding.Word(word_option=WordOptions.word2vec, pretrained='en-turian'),
dtype=torch.float32)
expected = tw.fit_transform(docs[0])[0][index].view(1, -1)
tw = TextWiser(Embedding.Word(word_option=WordOptions.word2vec, pretrained='en-turian'),
Transformation.Pool(pool_option=pool_option), dtype=torch.float32)
pooled = tw.fit_transform(docs[0])
self.assertTrue(torch.allclose(expected.to(device), pooled.to(device)))
def test_fit_transform(self):
tw = TextWiser(Embedding.Word(word_option=WordOptions.word2vec, pretrained='en-turian'), Transformation.Pool(pool_option=PoolOptions.max), dtype=torch.float32)
expected = torch.from_numpy(np.genfromtxt(
self._get_test_path('data', 'pooled_embeddings.csv'),
dtype=np.float32))
self._test_fit_transform(tw, expected)
self._test_fit_before_transform(tw, expected)