class TestCases(unittest.TestCase):
@classmethod
def setUpClass(self):
print("******* Unit Test for Statsmodels *******")
self.adapa_utility = AdapaUtility()
def getData(self):
# Non Seasonal Data
data = [266,146,183,119,180,169,232,225,193,123,337,186,194,150,210,273,191,287,
226,304,290,422,265,342,340,440,316,439,401,390,490,408,490,420,520,480]
index = pd.DatetimeIndex(start='2016-01-01', end='2018-12-01', freq='MS')
ts_data = pd.Series(data, index)
ts_data.index.name = 'date_index'
ts_data.name = 'cars_sold'
ts_data = ts_data.astype('float64')
return ts_data
def test_01(self):
ts_data = getData()
f_name='arima201_c_car_sold.pmml'
model = ARIMA(ts_data,order=(2,0,1))
result = model.fit(trend = 'c', method = 'css')
ArimaToPMML(result, f_name)
model_name = self.adapaUtilities.upload_to_zserver(f_name)
z_pred = self.adapaUtilities.score_single_record(model_name)
model_pred = result.forecast()[0][0]
self.assertEqual(model_pred, z_pred['predicted_cars_sold'])
z_pred = self.adapa_utility.score_in_zserver(model_name, 'nyoka/tests/test_car_sold.csv','TS')
model_pred = result.forecast(5)[0][-1]
self.assertEqual(model_pred, z_pred)
def test_02(self):
data=pd.read_csv("nyoka/tests/JohnsonJohnsonWithDate.csv")
data['index']=pd.to_datetime(data['index'], format='%Y-%m-%d')
data.set_index(['index'], inplace=True)
mod = SARIMAX(data,order=(1,0,0),seasonal_order=(1,0,0, 4))
result = mod.fit()
ArimaToPMML(results, 'jnj_seasonal_arima.pmml')
model_name = self.adapaUtilities.upload_to_zserver('jnj_seasonal_arima.pmml')
z_pred = self.adapaUtilities.score_single_record(model_name)
model_pred = result.forecast()[0]
self.assertEqual(model_pred, z_pred['predicted_value'])
z_pred = self.adapa_utility.score_in_zserver(model_name, 'nyoka/tests/test_jnj.csv','TS')
model_pred = result.forecast(5)[-1]
self.assertEqual(model_pred, z_pred)
@classmethod
def tearDownClass(self):
print("\n******* Finished *******\n")
def setUpClass(self):
print("******* Unit Test for lightgbm *******")
iris = datasets.load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df["Species"] = iris.target
df["Binary"] = numpy.array([i % 2 for i in range(df.shape[0])])
self.X = df[iris.feature_names]
self.Y = df["Species"]
self.Y_bin = df["Binary"]
self.features = iris.feature_names
self.test_file = 'nyoka/tests/test.csv'
self.X.to_csv(self.test_file, index=False)
self.adapa_utility = AdapaUtility()
def setUpClass(self):
print("******* Unit Test for RetinaNet *******")
url = 'https://github.com/fizyr/keras-retinanet/releases/download/0.5.1/resnet50_coco_best_v2.1.0.h5'
r = requests.get(url)
with open('resnet50_coco_best_v2.1.0.h5', 'wb') as f:
f.write(r.content)
classes = json.load(open("nyoka/tests/categories_coco.json", 'r'))
self.classes = list(classes.values())
self.adapa_utility = AdapaUtility()
self.model = load_model('resnet50_coco_best_v2.1.0.h5',
backbone_name='resnet50')
def setUpClass(self):
print("******* Unit Test for Keras *******")
self.adapa_utility = AdapaUtility()
self.data_utility = DataUtility()
model = applications.MobileNet(weights='imagenet',
include_top=False,
input_shape=(224, 224, 3))
activType = 'sigmoid'
x = model.output
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
predictions = Dense(2, activation=activType)(x)
self.model_final = Model(inputs=model.input,
outputs=predictions,
name='predictions')
def setUpClass(cls):
print("******* Unit Test for Statsmodels *******")
cls.adapa_utility = AdapaUtility()
class TestCases(unittest.TestCase):
@classmethod
def setUpClass(self):
print("******* Unit Test for lightgbm *******")
iris = datasets.load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df["Species"] = iris.target
df["Binary"] = numpy.array([i % 2 for i in range(df.shape[0])])
self.X = df[iris.feature_names]
self.Y = df["Species"]
self.Y_bin = df["Binary"]
self.features = iris.feature_names
self.test_file = 'nyoka/tests/test.csv'
self.X.to_csv(self.test_file, index=False)
self.adapa_utility = AdapaUtility()
def test_01_lgbm_classifier(self):
print(
"\ntest 01 (lgbm classifier with preprocessing) [binary-class]\n")
model = LGBMClassifier()
pipeline_obj = Pipeline([('scaler', MinMaxScaler()), ("model", model)])
pipeline_obj.fit(self.X, self.Y_bin)
file_name = "test01lgbm.pmml"
lgb_to_pmml(pipeline_obj, self.features, 'Species', file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, self.test_file)
model_pred = pipeline_obj.predict(self.X)
model_prob = pipeline_obj.predict_proba(self.X)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred),
True)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
True)
def test_02_lgbm_classifier(self):
print("\ntest 02 (lgbm classifier with preprocessing) [multi-class]\n")
model = LGBMClassifier()
pipeline_obj = Pipeline([('scaler', MaxAbsScaler()), ("model", model)])
pipeline_obj.fit(self.X, self.Y)
file_name = "test02lgbm.pmml"
lgb_to_pmml(pipeline_obj, self.features, 'Species', file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, self.test_file)
model_pred = pipeline_obj.predict(self.X)
model_prob = pipeline_obj.predict_proba(self.X)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred),
True)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
True)
def test_03_lgbm_regressor(self):
print("\ntest 03 (lgbm regressor without preprocessing)\n")
model = LGBMRegressor()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(self.X, self.Y)
file_name = "test03lgbm.pmml"
lgb_to_pmml(pipeline_obj, self.features, 'Species', file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, self.test_file)
model_pred = pipeline_obj.predict(self.X)
predictions = numpy.array(predictions)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred),
True)
def test_04_lgbm_regressor(self):
print("\ntest 04 (lgbm regressor with preprocessing)\n")
auto = pd.read_csv('nyoka/tests/auto-mpg.csv')
X = auto.drop(['mpg'], axis=1)
y = auto['mpg']
feature_names = [name for name in auto.columns if name not in ('mpg')]
target_name = 'mpg'
x_train, x_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
random_state=101)
pd.DataFrame(data=x_test, columns=feature_names).to_csv("test.csv",
index=False)
pipeline_obj = Pipeline([
('mapper',
DataFrameMapper([('car name', CountVectorizer()),
(['displacement'], [StandardScaler()])])),
('lgbmr', LGBMRegressor())
])
pipeline_obj.fit(x_train, y_train)
file_name = "test04lgbm.pmml"
lgb_to_pmml(pipeline_obj, feature_names, 'mpg', file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, "test.csv")
predictions = numpy.array(predictions)
model_pred = pipeline_obj.predict(x_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred),
True)
@classmethod
def tearDownClass(self):
print("\n******* Finished *******\n")
def setUpClass(self):
print("******* Unit Test for Keras *******")
self.adapa_utility = AdapaUtility()
self.data_utility = DataUtility()
class TestCases(unittest.TestCase):
@classmethod
def setUpClass(self):
print("******* Unit Test for Keras *******")
self.adapa_utility = AdapaUtility()
self.data_utility = DataUtility()
def test_01_image_classifier_with_image_as_input(self):
model = applications.MobileNet(weights='imagenet',
include_top=False,
input_shape=(224, 224, 3))
activType = 'sigmoid'
x = model.output
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
predictions = Dense(2, activation=activType)(x)
model_final = Model(inputs=model.input,
outputs=predictions,
name='predictions')
cnn_pmml = KerasToPmml(model_final,model_name="MobileNetImage",description="Demo",\
copyright="Internal User",dataSet='image',predictedClasses=['dogs','cats'])
cnn_pmml.export(open('2classMBNet.pmml', "w"), 0)
img = image.load_img('nyoka/tests/resizedCat.png')
img = img_to_array(img)
img = preprocess_input(img)
imgtf = np.expand_dims(img, axis=0)
model_pred = model_final.predict(imgtf)
model_preds = {'dogs': model_pred[0][0], 'cats': model_pred[0][1]}
model_name = self.adapa_utility.upload_to_zserver('2classMBNet.pmml')
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, 'nyoka/tests/resizedCat.png', 'DN')
self.assertEqual(
abs(probabilities['cats'] - model_preds['cats']) < 0.00001, True)
self.assertEqual(
abs(probabilities['dogs'] - model_preds['dogs']) < 0.00001, True)
def test_02_image_classifier_with_base64string_as_input(self):
model = applications.MobileNet(weights='imagenet',
include_top=False,
input_shape=(224, 224, 3))
activType = 'sigmoid'
x = model.output
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
predictions = Dense(2, activation=activType)(x)
model_final = Model(inputs=model.input,
outputs=predictions,
name='predictions')
cnn_pmml = KerasToPmml(model_final,model_name="MobileNetBase64",description="Demo",\
copyright="Internal User",dataSet='imageBase64',predictedClasses=['dogs','cats'])
cnn_pmml.export(open('2classMBNetBase64.pmml', "w"), 0)
img = image.load_img('nyoka/tests/resizedCat.png')
img = img_to_array(img)
img = preprocess_input(img)
imgtf = np.expand_dims(img, axis=0)
base64string = "data:float32;base64," + FloatBase64.from_floatArray(
img.flatten(), 12)
base64string = base64string.replace("\n", "")
csvContent = "imageBase64\n\"" + base64string + "\""
text_file = open("input.csv", "w")
text_file.write(csvContent)
text_file.close()
model_pred = model_final.predict(imgtf)
model_preds = {'dogs': model_pred[0][0], 'cats': model_pred[0][1]}
model_name = self.adapa_utility.upload_to_zserver(
'2classMBNetBase64.pmml')
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, 'input.csv', 'DN')
self.assertEqual(
abs(probabilities['cats'] - model_preds['cats']) < 0.00001, True)
self.assertEqual(
abs(probabilities['dogs'] - model_preds['dogs']) < 0.00001, True)
@unittest.skip("")
def test_03_encoded_script(self):
model = applications.MobileNet(weights='imagenet',
include_top=False,
input_shape=(224, 224, 3))
x = model.output
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
predictions = Dense(2, activation='sigmoid')(x)
model_final = Model(inputs=model.input,
outputs=predictions,
name='predictions')
script_content = open("nyoka/tests/preprocess.py", 'r').read()
pmml_obj = KerasToPmml(model_final,
dataSet='image',
predictedClasses=['cat', 'dog'],
script_args={
"content": script_content,
"def_name": "getBase64EncodedString",
"return_type": "string",
"encode": True
})
pmml_obj.export(open("script_with_keras.pmml", 'w'), 0)
self.assertEqual(os.path.isfile("script_with_keras.pmml"), True)
reconPmmlObj = pml.parse("script_with_keras.pmml", True)
content = reconPmmlObj.TransformationDictionary.DefineFunction[
0].Apply.Extension[0].anytypeobjs_[0]
content = base64.b64decode(content).decode()
self.assertEqual(script_content, content)
self.assertEqual(len(model_final.layers),
len(reconPmmlObj.DeepNetwork[0].NetworkLayer))
@unittest.skip("")
def test_04_plain_text_script(self):
model = applications.MobileNet(weights='imagenet',
include_top=False,
input_shape=(224, 224, 3))
x = model.output
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
predictions = Dense(2, activation='sigmoid')(x)
model_final = Model(inputs=model.input,
outputs=predictions,
name='predictions')
script_content = open("nyoka/tests/preprocess.py", 'r').read()
pmml_obj = KerasToPmml(model_final,
dataSet='image',
predictedClasses=['cat', 'dog'],
script_args={
"content": script_content,
"def_name": "getBase64EncodedString",
"return_type": "string",
"encode": False
})
pmml_obj.export(open("script_with_keras.pmml", 'w'), 0)
self.assertEqual(os.path.isfile("script_with_keras.pmml"), True)
reconPmmlObj = pml.parse("script_with_keras.pmml", True)
content = reconPmmlObj.TransformationDictionary.DefineFunction[
0].Apply.Extension[0].anytypeobjs_
content[0] = content[0].replace("\t", "")
content = "\n".join(content)
self.assertEqual(script_content, content)
self.assertEqual(len(model_final.layers),
len(reconPmmlObj.DeepNetwork[0].NetworkLayer))
@classmethod
def tearDownClass(self):
print("\n******* Finished *******\n")
class TestCases(unittest.TestCase):
@classmethod
def setUpClass(self):
print("******* Unit Test for lightgbm *******")
iris = datasets.load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df["Species"] = iris.target
df["Binary"] = numpy.array([i % 2 for i in range(df.shape[0])])
self.X = df[iris.feature_names]
self.Y = df["Species"]
self.Y_bin = df["Binary"]
self.features = iris.feature_names
self.test_file = 'nyoka/tests/test.csv'
self.X.to_csv(self.test_file, index=False)
self.adapa_utility = AdapaUtility()
def test_01_lgbm_classifier(self):
print(
"\ntest 01 (lgbm classifier with preprocessing) [binary-class]\n")
model = LGBMClassifier()
pipeline_obj = Pipeline([('scaler', MinMaxScaler()), ("model", model)])
pipeline_obj.fit(self.X, self.Y_bin)
file_name = "test01lgbm.pmml"
lgb_to_pmml(pipeline_obj, self.features, 'Species', file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, self.test_file)
model_pred = pipeline_obj.predict(self.X)
model_prob = pipeline_obj.predict_proba(self.X)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_02_lgbm_classifier(self):
print("\ntest 02 (lgbm classifier with preprocessing) [multi-class]\n")
model = LGBMClassifier()
pipeline_obj = Pipeline([('scaler', MaxAbsScaler()), ("model", model)])
pipeline_obj.fit(self.X, self.Y)
file_name = "test02lgbm.pmml"
lgb_to_pmml(pipeline_obj, self.features, 'Species', file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, self.test_file)
model_pred = pipeline_obj.predict(self.X)
model_prob = pipeline_obj.predict_proba(self.X)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_03_lgbm_regressor(self):
print("\ntest 03 (lgbm regressor without preprocessing)\n")
model = LGBMRegressor()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(self.X, self.Y)
file_name = "test03lgbm.pmml"
lgb_to_pmml(pipeline_obj, self.features, 'Species', file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, self.test_file)
model_pred = pipeline_obj.predict(self.X)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
@classmethod
def tearDownClass(self):
print("\n******* Finished *******\n")
class TestCases(unittest.TestCase):
@classmethod
def setUpClass(self):
print("******* Unit Test for sklearn *******")
self.data_utility = DataUtility()
self.adapa_utility = AdapaUtility()
def test_01_linear_regression(self):
print("\ntest 01 (linear regression without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression(
)
model = LinearRegression()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test01sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
def test_02_linear_regression_with_scaler(self):
print("\ntest 02 (linear regression with preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression(
)
model = LinearRegression()
pipeline_obj = Pipeline([
("mapper",
DataFrameMapper([(["sepal width (cm)"], StandardScaler()),
(["petal length (cm)",
"petal width (cm)"], None)])), ("model", model)
])
pipeline_obj.fit(X, y)
file_name = 'test02sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
def test_03_logistic_regression_with_scaler(self):
print(
"\ntest 03 (logistic regression with preprocessing) [multi-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = LogisticRegression()
pipeline_obj = Pipeline([
("mapper",
DataFrameMapper([(["sepal length (cm)",
"sepal width (cm)"], MinMaxScaler()),
(["petal length (cm)",
"petal width (cm)"], None)])), ("model", model)
])
pipeline_obj.fit(X, y)
file_name = 'test03sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_04_logistic_regression_with_scaler(self):
print(
"\ntest 04 (logistic regression with preprocessing) [binary-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = LogisticRegression()
pipeline_obj = Pipeline([
("mapper",
DataFrameMapper([(["sepal length (cm)",
"sepal width (cm)"], MinMaxScaler()),
(["petal length (cm)",
"petal width (cm)"], None)])), ("model", model)
])
pipeline_obj.fit(X, y)
file_name = 'test04sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_05_logistic_regression(self):
print(
"\ntest 05 (logistic regression without preprocessing) [multi-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = LogisticRegression()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test05sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_06_logistic_regression(self):
print(
"\ntest 06 (logistic regression without preprocessing) [binary-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = LogisticRegression()
pipeline_obj = Pipeline([("mapper",
DataFrameMapper([(["test",
LabelBinarizer()])])),
("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test06sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_07_ridge_classifier(self):
print("\ntest 07 (Ridge Classifier) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = RidgeClassifier()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test07sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = model._predict_proba_lr(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_08_ridge_classifier(self):
print("\ntest 08 (Ridge Classifier) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = RidgeClassifier()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test08sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = model._predict_proba_lr(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_09_sgd_classifier(self):
print("\ntest 09 (SGD Classifier with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = SGDClassifier(loss="log")
pipeline_obj = Pipeline([("scaler", StandardScaler()),
("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test09sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_10_sgd_classifier(self):
print("\ntest 10 (SGD Classifier with preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = SGDClassifier(loss="log")
pipeline_obj = Pipeline([("scaler", StandardScaler()),
("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test10sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_11_lda(self):
print("\ntest 11 (LDA with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = LinearDiscriminantAnalysis()
pipeline_obj = Pipeline([("scaler", MaxAbsScaler()), ("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test11sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_12_lda(self):
print("\ntest 12 (LDA with preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = LinearDiscriminantAnalysis()
pipeline_obj = Pipeline([("scaler", StandardScaler()),
("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test12sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_13_linearsvc(self):
print("\ntest 13 (LinearSVC with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = LinearSVC()
pipeline_obj = Pipeline([("scaler", StandardScaler()),
("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test13sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.decision_function(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_14_linearsvc(self):
print("\ntest 14 (LinearSVC with preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = LinearSVC()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test14sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = model._predict_proba_lr(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_15_linearsvr(self):
print("\ntest 15 (linear svr without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression(
)
model = LinearSVR()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test15sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
def test_16_linearsvr(self):
print("\ntest 16 (linear svr with preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression(
)
model = LinearSVR()
pipeline_obj = Pipeline([("scaler", MinMaxScaler()), ("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test16sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
def test_17_decisiontreeclassifier(self):
print(
"\ntest 17 (decision tree classifier with preprocessing) [multi-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = DecisionTreeClassifier()
pipeline_obj = Pipeline([("scaler", Binarizer()), ("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test17sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_18_decisiontreeclassifier(self):
print(
"\ntest 18 (decision tree classifier with preprocessing) [binary-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = DecisionTreeClassifier()
pipeline_obj = Pipeline([("scaler", Binarizer()), ("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test18sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_19_decisiontreeclassifier(self):
print(
"\ntest 19 (decision tree classifier without preprocessing) [multi-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = DecisionTreeClassifier()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test19sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_20_decisiontreeclassifier(self):
print(
"\ntest 20 (decision tree classifier without preprocessing) [binary-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = DecisionTreeClassifier()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test20sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_21_svr(self):
print("\ntest 21 (SVR without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression(
)
model = SVR()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test21sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
def test_22_gaussian_nb(self):
print("\ntest 22 (GaussianNB without preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = GaussianNB()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test22sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_23_gaussian_nb(self):
print("\ntest 23 (GaussianNB without preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = GaussianNB()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test23sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_24_gaussian_nb(self):
print("\ntest 24 (GaussianNB with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = GaussianNB()
pipeline_obj = Pipeline([('scaler', StandardScaler()),
("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test24sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_25_random_forest_regressor(self):
print("\ntest 25 (random forest regressor without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression(
)
model = RandomForestRegressor()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test25sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
def test_26_random_forest_classifier(self):
print(
"\ntest 26 (random forest classifier with preprocessing) [multi-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = RandomForestClassifier()
pipeline_obj = Pipeline([('scaler', MinMaxScaler()), ("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test26sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_27_random_forest_classifier(self):
print(
"\ntest 27 (random forest classifier with preprocessing) [binary-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = RandomForestClassifier()
pipeline_obj = Pipeline([('scaler', MinMaxScaler()), ("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test27sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_28_gradient_boosting_classifier(self):
print(
"\ntest 28 (gradient boosting classifier with preprocessing) [binary-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = GradientBoostingClassifier()
pipeline_obj = Pipeline([('scaler', MinMaxScaler()), ("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test28sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_29_gradient_boosting_classifier(self):
print(
"\ntest 29 (gradient boosting classifier with preprocessing) [multi-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = GradientBoostingClassifier()
pipeline_obj = Pipeline([('scaler', MaxAbsScaler()), ("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test29sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_30_gradient_boosting_regressor(self):
print(
"\ntest 30 (gradient boosting regressor without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression(
)
model = GradientBoostingRegressor()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test30sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
def test_31_knn_classifier(self):
print(
"\ntest 31 (knn classifier without preprocessing) [binary-class]\n"
)
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification(
)
model = KNeighborsClassifier()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test31sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_32_knn_classifier(self):
print(
"\ntest 32 (knn classifier without preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = KNeighborsClassifier()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test32sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
def test_33_knn_regressor(self):
print("\ntest 33 (knn regressor without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression(
)
model = KNeighborsRegressor()
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test33sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
def test_34_kmeans(self):
print("\ntest 34 (kmeans without preprocessing\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification(
)
model = KMeans(n_clusters=2)
pipeline_obj = Pipeline([("model", model)])
pipeline_obj.fit(X, y)
file_name = 'test34sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.transform(X_test)
self.assertEqual(
self.adapa_utility.compare_predictions(predictions, model_pred), 0)
self.assertEqual(
self.adapa_utility.compare_probability(probabilities, model_prob),
0)
@classmethod
def tearDownClass(self):
print("\n******* Finished *******\n")
class TestCases(unittest.TestCase):
@classmethod
def setUpClass(self):
print("******* Unit Test for sklearn *******")
self.data_utility = DataUtility()
self.adapa_utility = AdapaUtility()
def test_01_linear_regression(self):
print("\ntest 01 (linear regression without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()
model = LinearRegression()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test01sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
def test_02_linear_regression_with_scaler(self):
print("\ntest 02 (linear regression with preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()
model = LinearRegression()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test02sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
def test_03_logistic_regression_with_scaler(self):
print("\ntest 03 (logistic regression with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = LogisticRegression()
pipeline_obj = Pipeline([
("mapper", DataFrameMapper([
(["sepal length (cm)", "sepal width (cm)"], MinMaxScaler()),
(["petal length (cm)", "petal width (cm)"], None)
])
),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test03sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_04_logistic_regression_with_scaler(self):
print("\ntest 04 (logistic regression with preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = LogisticRegression()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test04sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_05_logistic_regression(self):
print("\ntest 05 (logistic regression without preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = LogisticRegression()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test05sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_06_logistic_regression(self):
print("\ntest 06 (logistic regression without preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = LogisticRegression()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test06sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_07_ridge_classifier(self):
print("\ntest 07 (Ridge Classifier) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = RidgeClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test07sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = model._predict_proba_lr(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_08_ridge_classifier(self):
print("\ntest 08 (Ridge Classifier) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = RidgeClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test08sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = model._predict_proba_lr(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
@unittest.skip("")
def test_09_sgd_classifier(self):
print("\ntest 09 (SGD Classifier with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = SGDClassifier(loss="log")
pipeline_obj = Pipeline([
("scaler", StandardScaler()),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test09sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_10_sgd_classifier(self):
print("\ntest 10 (SGD Classifier with preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = SGDClassifier(loss="log")
pipeline_obj = Pipeline([
("scaler", StandardScaler()),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test10sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_11_lda(self):
print("\ntest 11 (LDA with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = LinearDiscriminantAnalysis()
pipeline_obj = Pipeline([
("scaler", MaxAbsScaler()),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test11sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_12_lda(self):
print("\ntest 12 (LDA with preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = LinearDiscriminantAnalysis()
pipeline_obj = Pipeline([
("scaler", StandardScaler()),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test12sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_13_linearsvc(self):
print("\ntest 13 (LinearSVC with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = LinearSVC()
pipeline_obj = Pipeline([
("scaler", StandardScaler()),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test13sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.decision_function(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_14_linearsvc(self):
print("\ntest 14 (LinearSVC with preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = LinearSVC()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test14sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = model._predict_proba_lr(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_15_linearsvr(self):
print("\ntest 15 (linear svr without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()
model = LinearSVR()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test15sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
def test_16_linearsvr(self):
print("\ntest 16 (linear svr with preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()
model = LinearSVR()
pipeline_obj = Pipeline([
("scaler", MinMaxScaler()),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test16sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
def test_17_decisiontreeclassifier(self):
print("\ntest 17 (decision tree classifier with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = DecisionTreeClassifier()
pipeline_obj = Pipeline([
("scaler", Binarizer()),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test17sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_18_decisiontreeclassifier(self):
print("\ntest 18 (decision tree classifier with preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = DecisionTreeClassifier()
pipeline_obj = Pipeline([
("scaler", Binarizer()),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test18sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_19_decisiontreeclassifier(self):
print("\ntest 19 (decision tree classifier without preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = DecisionTreeClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test19sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_20_decisiontreeclassifier(self):
print("\ntest 20 (decision tree classifier without preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = DecisionTreeClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test20sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_21_svr(self):
print("\ntest 21 (SVR without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()
model = SVR()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test21sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
def test_22_gaussian_nb(self):
print("\ntest 22 (GaussianNB without preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = GaussianNB()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test22sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_23_gaussian_nb(self):
print("\ntest 23 (GaussianNB without preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = GaussianNB()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test23sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_24_gaussian_nb(self):
print("\ntest 24 (GaussianNB with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = GaussianNB()
pipeline_obj = Pipeline([
('scaler', StandardScaler()),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test24sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
@unittest.skip("")
def test_25_random_forest_regressor(self):
print("\ntest 25 (random forest regressor without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()
model = RandomForestRegressor()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test25sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
@unittest.skip("")
def test_26_random_forest_classifier(self):
print("\ntest 26 (random forest classifier with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = RandomForestClassifier()
pipeline_obj = Pipeline([
('scaler',MinMaxScaler()),
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test26sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
@unittest.skip("")
def test_27_random_forest_classifier(self):
print("\ntest 27 (random forest classifier with preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = RandomForestClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test27sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_28_gradient_boosting_classifier(self):
print("\ntest 28 (gradient boosting classifier with preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = GradientBoostingClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test28sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
@unittest.skip("")
def test_29_gradient_boosting_classifier(self):
print("\ntest 29 (gradient boosting classifier with preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = GradientBoostingClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test29sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
@unittest.skip("")
def test_30_gradient_boosting_regressor(self):
print("\ntest 30 (gradient boosting regressor without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()
model = GradientBoostingRegressor()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test30sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
@unittest.skip("")
def test_31_knn_classifier(self):
print("\ntest 31 (knn classifier without preprocessing) [binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = KNeighborsClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test31sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_32_knn_classifier(self):
print("\ntest 32 (knn classifier without preprocessing) [multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = KNeighborsClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test32sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_33_knn_regressor(self):
print("\ntest 33 (knn regressor without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()
model = KNeighborsRegressor()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test33sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
def test_34_kmeans(self):
print("\ntest 34 (kmeans without preprocessing\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = KMeans(n_clusters=2)
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test34sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.transform(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
@unittest.skip("")
def test_35_isolation_forest(self):
print("\ntest 34 (Isolation Forest\n")
detection_map = {
'true': -1,
'false': 1
}
X = numpy.array([
[1,2,3,4],
[2,1,3,4],
[3,2,1,4],
[3,2,4,1],
[4,3,2,1],
[2,4,3,1]
], dtype=numpy.float32)
test_data = numpy.array([[0,4,0,7],[4,0,4,7]])
features = ['a','b','c','d']
model = IsolationForest(n_estimators=40,contamination=0)
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X)
file_name = 'test35sklearn.pmml'
skl_to_pmml(pipeline_obj, features, '', file_name)
model_pred = pipeline_obj.predict(test_data)
model_scores = model.score_samples(test_data)
model_name = self.adapa_utility.upload_to_zserver(file_name)
z_predictions = self.adapa_utility.score_in_zserver(model_name,'nyoka/tests/test_forest.csv','ANOMALY')
cnt = 0
for idx, value in enumerate(z_predictions):
score, is_anomaly = value.split(",")
score = -1 * float(score)
if "{:.6f}".format(score) != "{:.6f}".format(model_scores[idx]) or model_pred[idx] != detection_map[is_anomaly]:
cnt += 1
self.assertEqual(cnt,0)
@unittest.skip("")
def test_36_one_class_svm(self):
print("\ntest 36 (One Class SVM\n")
detection_map = {
'true': -1,
'false': 1
}
df = pd.read_csv("nyoka/tests/train_ocsvm.csv")
df_test = pd.read_csv("nyoka/tests/test_ocsvm.csv")
features = df.columns
model = OneClassSVM(nu=0.1)
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(df)
file_name = 'test36sklearn.pmml'
skl_to_pmml(pipeline_obj, features, '', file_name)
model_pred = pipeline_obj.predict(df_test)
model_scores = pipeline_obj.decision_function(df_test)
model_name = self.adapa_utility.upload_to_zserver(file_name)
z_predictions = self.adapa_utility.score_in_zserver(model_name,'nyoka/tests/test_ocsvm.csv','ANOMALY')
cnt = 0
for idx, value in enumerate(z_predictions):
score, is_anomaly = value.split(",")
score = float(score)
if "{:.6f}".format(score) != "{:.6f}".format(model_scores[idx]) or model_pred[idx] != detection_map[is_anomaly]:
cnt += 1
self.assertEqual(cnt,0)
def test_37_mlp_regressor(self):
print("\ntest 37 (mlp regressor without preprocessing)\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()
model = MLPRegressor()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test37sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
def test_38_mlp_classifier(self):
print("\ntest 38 (mlp classifier without preprocessing)[multi-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()
model = MLPClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test38sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
def test_39_mlp_classifier(self):
print("\ntest 39 (mlp classifier without preprocessing)[binary-class]\n")
X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()
model = MLPClassifier()
pipeline_obj = Pipeline([
("model", model)
])
pipeline_obj.fit(X,y)
file_name = 'test39sklearn.pmml'
skl_to_pmml(pipeline_obj, features, target, file_name)
model_name = self.adapa_utility.upload_to_zserver(file_name)
predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
model_pred = pipeline_obj.predict(X_test)
model_prob = pipeline_obj.predict_proba(X_test)
self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True)
@classmethod
def tearDownClass(self):
print("\n******* Finished *******\n")
def setUpClass(self):
print("******* Unit Test for Statsmodels *******")
self.adapa_utility = AdapaUtility()
class TestCases(unittest.TestCase):
@classmethod
def setUpClass(self):
print("******* Unit Test for RetinaNet *******")
url = 'https://github.com/fizyr/keras-retinanet/releases/download/0.5.1/resnet50_coco_best_v2.1.0.h5'
r = requests.get(url)
with open('resnet50_coco_best_v2.1.0.h5', 'wb') as f:
f.write(r.content)
classes = json.load(open("nyoka/tests/categories_coco.json", 'r'))
self.classes = list(classes.values())
self.adapa_utility = AdapaUtility()
self.model = load_model('resnet50_coco_best_v2.1.0.h5',
backbone_name='resnet50')
def test_01(self):
RetinanetToPmml(model=self.model,
input_shape=(224, 224, 3),
input_format='image',
backbone_name='resnet',
trained_classes=classes,
pmml_file_name="RetinaNet.pmml")
model_name = self.adapa_utility.upload_to_zserver('RetinaNet.pmml')
z_boxes, z_scores, z_labels = self.adapa_utility.score_in_zserver(
model_name, 'nyoka/tests/test_image_retinanet.png', 'RN')
img = load_img('nyoka/tests/test_image_retinanet.png')
img = img_to_array(img)
img = preprocess_input(img)
test = np.expand_dims(img, axis=0)
boxes, scores, labels = self.model.predict(test)
scores = scores.flatten()
boxes = boxes.reshape(-1, 4)
labels = labels.flatten()
scores_cnt = 0
for a, b in zip(scores, z_scores):
a = "{:.4f}".format(a)
b = "{:.4f}".format(b)
if a != b:
scores_cnt += 1
labels_cnt = 0
for a, b in zip(labels, z_labels):
b = self.classes.index(b)
if a != b:
labels_cnt += 1
boxes_cnt = 0
for a, b in zip(boxes, z_boxes):
for a_, b_ in zip(a, b):
a_ = "{:.2f}".format(a_)
b_ = "{:.2f}".format(b_)
if a_ != b_:
boxes_cnt += 1
self.assertEqual(scores_cnt, 0)
self.assertEqual(labels_cnt, 0)
self.assertEqual(boxes_cnt, 0)
@classmethod
def tearDownClass(self):
print("\n******* Finished *******\n")
class TestCases(unittest.TestCase):
@classmethod
def setUpClass(self):
print("******* Unit Test for Keras *******")
self.adapa_utility = AdapaUtility()
self.data_utility = DataUtility()
def test_01_image_classifier_with_image_as_input(self):
model = applications.MobileNet(weights='imagenet',
include_top=False,
input_shape=(224, 224, 3))
activType = 'sigmoid'
x = model.output
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
predictions = Dense(2, activation=activType)(x)
model_final = Model(inputs=model.input,
outputs=predictions,
name='predictions')
cnn_pmml = KerasToPmml(model_final,model_name="MobileNetImage",description="Demo",\
copyright="Internal User",dataSet='image',predictedClasses=['dogs','cats'])
cnn_pmml.export(open('2classMBNet.pmml', "w"), 0)
img = image.load_img('nyoka/tests/resizedCat.png')
img = img_to_array(img)
img = preprocess_input(img)
imgtf = np.expand_dims(img, axis=0)
model_pred = model_final.predict(imgtf)
model_preds = {'dogs': model_pred[0][0], 'cats': model_pred[0][1]}
model_name = self.adapa_utility.upload_to_zserver('2classMBNet.pmml')
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, 'nyoka/tests/resizedCat.png', True)
self.assertEqual(
abs(probabilities['cats'] - model_preds['cats']) < 0.00001, True)
self.assertEqual(
abs(probabilities['dogs'] - model_preds['dogs']) < 0.00001, True)
def test_02_image_classifier_with_base64string_as_input(self):
model = applications.MobileNet(weights='imagenet',
include_top=False,
input_shape=(224, 224, 3))
activType = 'sigmoid'
x = model.output
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
predictions = Dense(2, activation=activType)(x)
model_final = Model(inputs=model.input,
outputs=predictions,
name='predictions')
cnn_pmml = KerasToPmml(model_final,model_name="MobileNetBase64",description="Demo",\
copyright="Internal User",dataSet='imageBase64',predictedClasses=['dogs','cats'])
cnn_pmml.export(open('2classMBNetBase64.pmml', "w"), 0)
img = image.load_img('nyoka/tests/resizedCat.png')
img = img_to_array(img)
img = preprocess_input(img)
imgtf = np.expand_dims(img, axis=0)
base64string = "data:float32;base64," + FloatBase64.from_floatArray(
img.flatten(), 12)
base64string = base64string.replace("\n", "")
csvContent = "imageBase64\n\"" + base64string + "\""
text_file = open("input.csv", "w")
text_file.write(csvContent)
text_file.close()
model_pred = model_final.predict(imgtf)
model_preds = {'dogs': model_pred[0][0], 'cats': model_pred[0][1]}
model_name = self.adapa_utility.upload_to_zserver(
'2classMBNetBase64.pmml')
predictions, probabilities = self.adapa_utility.score_in_zserver(
model_name, 'input.csv', True)
self.assertEqual(
abs(probabilities['cats'] - model_preds['cats']) < 0.00001, True)
self.assertEqual(
abs(probabilities['dogs'] - model_preds['dogs']) < 0.00001, True)
# def test_03_SimpleDNN(self):
# X_train, X_test, y_train, columns, target_name, test_file = self.data_utility.get_data_for_regression()
# model = Sequential()
# model.add(Dense(13, input_dim=3, kernel_initializer='normal', activation='relu'))
# model.add(Dense(23))
# model.add(Dense(1, kernel_initializer='normal'))
# model.compile(loss='mean_squared_error', optimizer='adam')
# model.fit(X_train, y_train, epochs=1000, verbose=0)
# pmmlObj=KerasToPmml(model, model_name='Sequential', description="Demo", copyright="Internal User",\
# dataSet="inputBase64")
# pmmlObj.export(open('sequentialModel.pmml','w'),0)
# base64string = "data:float32;base64," + FloatBase64.from_floatArray(np.array(X_test).flatten(),12)
# base64string = base64string.replace("\n", "")
# csvContent = "inputBase64\n\"" + base64string + "\""
# text_file = open(test_file, "w")
# text_file.write(csvContent)
# text_file.close()
# model_pred = model.predict(X_test)
# model_name = self.adapa_utility.upload_to_zserver('sequentialModel.pmml')
# predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file,True)
# print(model_pred)
# print(predictions)
# print(probabilities)
@classmethod
def tearDownClass(self):
print("\n******* Finished *******\n")
def setUpClass(cls):
print("******* Unit Test for sklearn *******")
cls.data_utility = DataUtility()
cls.adapa_utility = AdapaUtility()