def test_linear_regression_deserializer(self):
linear_regression = LinearRegression(fit_intercept=True,
normalize=False)
linear_regression.mlinit(input_features='a', prediction_column='e')
linear_regression.fit(self.df[['a']], self.df[['e']])
linear_regression.serialize_to_bundle(self.tmp_dir,
linear_regression.name)
# Test model.json
with open("{}/{}.node/model.json".format(
self.tmp_dir, linear_regression.name)) as json_data:
model = json.load(json_data)
# Now deserialize it back
node_name = "{}.node".format(linear_regression.name)
linear_regression_tf = LinearRegression()
linear_regression_tf = linear_regression_tf.deserialize_from_bundle(
self.tmp_dir, node_name)
res_a = linear_regression.predict(self.df[['a']])
res_b = linear_regression_tf.predict(self.df[['a']])
self.assertEqual(res_a[0], res_b[0])
self.assertEqual(res_a[1], res_b[1])
self.assertEqual(res_a[2], res_b[2])
def test_linear_regression_serializer(self):
linear_regression = LinearRegression(fit_intercept=True,
normalize=False)
linear_regression.mlinit(input_features='a', prediction_column='e')
linear_regression.fit(self.df[['a']], self.df[['e']])
linear_regression.serialize_to_bundle(self.tmp_dir,
linear_regression.name)
# Test model.json
with open("{}/{}.node/model.json".format(
self.tmp_dir, linear_regression.name)) as json_data:
model = json.load(json_data)
self.assertEqual(model['op'], 'linear_regression')
self.assertTrue(model['attributes']['intercept']['double'] is not None)
input_scalars = feature_cols,
output_vector = 'unscaled_cont_features'
)
# Vector Assembler, for serialization purposes only
feature_extractor_lr_model_tf = FeatureExtractor(
input_vectors = [feature_extractor_tf],
output_vector = 'input_features'
)
feature_extractor_lr_model_tf.skip_fit_transform = True
# Define our linear regression
lr_model = LinearRegression()
lr_model.mlinit(
input_features = 'input_features',
prediction_column = 'prijs'
)
lr_model_pipeline = Pipeline([
(feature_extractor_lr_model_tf.name, feature_extractor_lr_model_tf),
(lr_model.name, lr_model)
])
lr_model_pipeline.mlinit()
model_pipeline = Pipeline([
(feature_union.name, feature_union),
(lr_model_pipeline.name, lr_model_pipeline)
])
model_pipeline.mlinit()
### train the pipeline
lr_model_pipeline.fit(X,y)
