Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
standard_scaler = StandardScaler(with_mean=True,
with_std=True
)
standard_scaler.mlinit(prior_tf=feature_extractor,
output_features=['a_scaled', 'b_scaled'])
standard_scaler.fit(self.df[['a', 'b']])
standard_scaler.serialize_to_bundle(self.tmp_dir, standard_scaler.name)
# Now deserialize it back
node_name = "{}.node".format(standard_scaler.name)
standard_scaler_tf = StandardScaler()
standard_scaler_tf = standard_scaler_tf.deserialize_from_bundle(self.tmp_dir, node_name)
# Transform some sample data
res_a = standard_scaler.transform(self.df[['a', 'b']])
res_b = standard_scaler_tf.transform(self.df[['a', 'b']])
self.assertEqual(res_a[0][0], res_b[0][0])
self.assertEqual(res_a[0][1], res_b[0][1])
self.assertEqual(standard_scaler.name, standard_scaler_tf.name)
self.assertEqual(standard_scaler.op, standard_scaler_tf.op)
self.assertEqual(standard_scaler.mean_[0], standard_scaler_tf.mean_[0])
self.assertEqual(standard_scaler.mean_[1], standard_scaler_tf.mean_[1])
self.assertEqual(standard_scaler.scale_[0], standard_scaler_tf.scale_[0])
self.assertEqual(standard_scaler.scale_[1], standard_scaler_tf.scale_[1])
standard_scaler = StandardScaler(with_mean=True,
with_std=True
)
standard_scaler.mlinit(prior_tf=feature_extractor,
output_features='a_scaled')
standard_scaler.fit(self.df[['a']])
standard_scaler.serialize_to_bundle(self.tmp_dir, standard_scaler.name)
# Now deserialize it back
node_name = "{}.node".format(standard_scaler.name)
standard_scaler_tf = StandardScaler()
standard_scaler_tf = standard_scaler_tf.deserialize_from_bundle(self.tmp_dir, node_name)
# Transform some sample data
res_a = standard_scaler.transform(self.df[['a']])
res_b = standard_scaler_tf.transform(self.df[['a']])
self.assertEqual(res_a[0], res_b[0])
self.assertEqual(standard_scaler.name, standard_scaler_tf.name)
self.assertEqual(standard_scaler.op, standard_scaler_tf.op)
self.assertEqual(standard_scaler.mean_, standard_scaler_tf.mean_)
self.assertEqual(standard_scaler.scale_, standard_scaler_tf.scale_)
def test_standard_scaler_multi_deserializer(self):
extract_features = ['a', 'b']
feature_extractor = FeatureExtractor(input_scalars=['a', 'b'],
output_vector='extracted_multi_outputs',
output_vector_items=["{}_out".format(x) for x in extract_features])
# Serialize a standard scaler to a bundle
standard_scaler = StandardScaler(with_mean=True,
with_std=True
)
standard_scaler.mlinit(prior_tf=feature_extractor,
output_features=['a_scaled', 'b_scaled'])
standard_scaler.fit(self.df[['a', 'b']])
standard_scaler.serialize_to_bundle(self.tmp_dir, standard_scaler.name)
# Now deserialize it back
node_name = "{}.node".format(standard_scaler.name)
standard_scaler_tf = StandardScaler()
def test_standard_scaler_serializer(self):
standard_scaler = StandardScaler(with_mean=True,
with_std=True
)
extract_features = ['a']
feature_extractor = FeatureExtractor(input_scalars=['a'],
output_vector='extracted_a_output',
output_vector_items=["{}_out".format(x) for x in extract_features])
standard_scaler.mlinit(prior_tf=feature_extractor,
output_features='a_scaled')
standard_scaler.fit(self.df[['a']])
standard_scaler.serialize_to_bundle(self.tmp_dir, standard_scaler.name)
expected_mean = self.df.a.mean()
def test_standard_scaler_deserializer(self):
extract_features = ['a']
feature_extractor = FeatureExtractor(input_scalars=['a'],
output_vector='extracted_a_output',
output_vector_items=["{}_out".format(x) for x in extract_features])
# Serialize a standard scaler to a bundle
standard_scaler = StandardScaler(with_mean=True,
with_std=True
)
standard_scaler.mlinit(prior_tf=feature_extractor,
output_features='a_scaled')
standard_scaler.fit(self.df[['a']])
standard_scaler.serialize_to_bundle(self.tmp_dir, standard_scaler.name)
# Now deserialize it back
node_name = "{}.node".format(standard_scaler.name)
standard_scaler_tf = StandardScaler()