def test_drop_model_by_object(self):
model_name = str(uuid.uuid1()).replace('-','_')
# Create model and verify that it's in the get_model_names() list
model = ta.KMeansModel(name=model_name)
self.assertTrue(model_name in ta.get_model_names(), model_name + " should exist in the list of models")
# Drop model using the model object
self.assertEqual(1, ta.drop_models(model), "drop_models() should have deleted one model.")
self.assertFalse(model_name in ta.get_model_names(), model_name + " should not exist in the list of models")
def test_drop_model_by_object(self):
model_name = str(uuid.uuid1()).replace('-','_')
# Create model and verify that it's in the get_model_names() list
model = ta.KMeansModel(name=model_name)
self.assertTrue(model_name in ta.get_model_names(), model_name + " should exist in the list of models")
# Drop model using the model object
self.assertEqual(1, ta.drop_models(model), "drop_models() should have deleted one model.")
self.assertFalse(model_name in ta.get_model_names(), model_name + " should not exist in the list of models")
def test_model_rename(self):
model_name = str(uuid.uuid1()).replace('-','_')
new_model_name = str(uuid.uuid1()).replace('-','_')
model = ta.KMeansModel(name=model_name)
self.assertTrue(model_name in ta.get_model_names(), model_name + " should be in the list of models")
model.name = new_model_name
self.assertTrue(new_model_name in ta.get_model_names(), new_model_name + " should be in list of models")
self.assertFalse(model_name in ta.get_model_names(), model_name + " shoule not be in list of models")
def test_generic_drop_by_name(self):
model_name = str(uuid.uuid1()).replace('-','_')
ta.KMeansModel(name=model_name)
self.assertTrue(model_name in ta.get_model_names(), model_name + " should exist in the list of model names")
# drop() item by name
self.assertEqual(1, ta.drop(model_name), "drop() should have deleted one item")
# check that the model no longer exists
self.assertFalse(model_name in ta.get_model_names(), model_name + " should not exist in the list of models")
def test_generic_drop_by_name(self):
model_name = str(uuid.uuid1()).replace('-','_')
ta.KMeansModel(name=model_name)
self.assertTrue(model_name in ta.get_model_names(), model_name + " should exist in the list of model names")
# drop() item by name
self.assertEqual(1, ta.drop(model_name), "drop() should have deleted one item")
# check that the model no longer exists
self.assertFalse(model_name in ta.get_model_names(), model_name + " should not exist in the list of models")
def test_generic_drop_by_object(self):
model_name = str(uuid.uuid1()).replace('-','_')
model = ta.KMeansModel(name=model_name)
# Check that the model we just created now exists
self.assertTrue(model_name in ta.get_model_names(), model_name + " should exist in the list of model names")
# drop by entity
self.assertEqual(1, ta.drop(model), "drop() should have deleted one item")
# check that the model no longer exists
self.assertFalse(model_name in ta.get_model_names(), model_name + " should not exist in the list of models")
def test_generic_drop_by_object(self):
model_name = str(uuid.uuid1()).replace('-','_')
model = ta.KMeansModel(name=model_name)
# Check that the model we just created now exists
self.assertTrue(model_name in ta.get_model_names(), model_name + " should exist in the list of model names")
# drop by entity
self.assertEqual(1, ta.drop(model), "drop() should have deleted one item")
# check that the model no longer exists
self.assertFalse(model_name in ta.get_model_names(), model_name + " should not exist in the list of models")
def test_model_rename(self):
model_name = str(uuid.uuid1()).replace('-', '_')
new_model_name = str(uuid.uuid1()).replace('-', '_')
model = ta.KMeansModel(name=model_name)
self.assertTrue(model_name in ta.get_model_names(),
model_name + " should be in the list of models")
model.name = new_model_name
self.assertTrue(new_model_name in ta.get_model_names(),
new_model_name + " should be in list of models")
self.assertFalse(model_name in ta.get_model_names(),
model_name + " shoule not be in list of models")
def test_create_duplicate_kmeans_model(self):
model_name = str(uuid.uuid1()).replace('-','_')
ta.KMeansModel(name=model_name)
self.assertTrue(model_name in ta.get_model_names(), model_name + " should be in the list of models")
# try to create another model with the same name (we expect an exception)
with self.assertRaises(Exception):
ta.KMeansModel(name=model_name)
def test_create_duplicate_kmeans_model(self):
model_name = str(uuid.uuid1()).replace('-', '_')
ta.KMeansModel(name=model_name)
self.assertTrue(model_name in ta.get_model_names(),
model_name + " should be in the list of models")
# try to create another model with the same name (we expect an exception)
with self.assertRaises(Exception):
ta.KMeansModel(name=model_name)
def test_duplicate_graph_rename(self):
graph_name1 = str(uuid.uuid1()).replace('-', '_')
graph_name2 = str(uuid.uuid1()).replace('-', '_')
model_name = str(uuid.uuid1()).replace('-', '_')
frame_name = str(uuid.uuid1()).replace('-', '_')
# Create graphs, model, and frame
graph1 = ta.Graph(name=graph_name1)
graph2 = ta.Graph(name=graph_name2)
ta.KMeansModel(name=model_name)
ta.Frame(name=frame_name)
# After creating graphs, check that graphs with each name exists on the server
self.assertTrue(graph_name1 in ta.get_graph_names(),
graph_name1 + " should exist in list of graphs")
self.assertTrue(graph_name2 in ta.get_graph_names(),
graph_name2 + " should exist in list of graphs")
# Try to rename graph2 to have the same name as graph1 (we expect an exception here)
with self.assertRaises(Exception):
graph2.name = graph_name1
# Both graph names should still exist on the server
self.assertTrue(graph_name1 in ta.get_graph_names(),
graph_name1 + " should still exist in list of graphs")
self.assertTrue(graph_name2 in ta.get_graph_names(),
graph_name2 + " should still exist in list of graphs")
# Try to rename graph1 to have the same name as the frame (we expect an exception here)
with self.assertRaises(Exception):
graph1.name = frame_name
# graph1 and the frame name should still exist on the server
self.assertTrue(
graph_name1 in ta.get_graph_names(),
graph_name1 + " should still exist in the list of graphs")
self.assertTrue(
frame_name in ta.get_frame_names(),
frame_name + " should still exist in the list of frames")
# Try to rename graph1 to have the same name as the model (we expect an exception here)
with self.assertRaises(Exception):
graph1.name = model_name
# graph1 and the frame name should still exist on the server
self.assertTrue(
graph_name1 in ta.get_graph_names(),
graph_name1 + " should still exist in the list of graphs")
self.assertTrue(
model_name in ta.get_model_names(),
model_name + " should still exist in the list of models")
def test_duplicate_frame_rename(self):
frame_name1 = str(uuid.uuid1()).replace('-','_')
frame_name2 = str(uuid.uuid1()).replace('-','_')
graph_name = str(uuid.uuid1()).replace('-','_')
model_name = str(uuid.uuid1()).replace('-','_')
# Create frames, graph, and model to test with
frame1 = ta.Frame(name=frame_name1)
frame2 = ta.Frame(name=frame_name2)
ta.Graph(name=graph_name)
ta.KMeansModel(name=model_name)
# After creating frames, check that frames with each name exists on the server
self.assertTrue(frame_name1 in ta.get_frame_names(), frame_name1 + " should exist in list of frames")
self.assertTrue(frame_name2 in ta.get_frame_names(), frame_name2 + " should exist in list of frames")
# Try to rename frame2 to have the same name as frame1 (we expect an exception here)
with self.assertRaises(Exception):
frame2.name = frame_name1
# Both frame names should still exist on the server
self.assertTrue(frame_name1 in ta.get_frame_names(), frame_name1 + " should still exist in list of frames")
self.assertTrue(frame_name2 in ta.get_frame_names(), frame_name2 + " should still exist in list of frames")
# Try to rename frame1 to have the same name as the graph (we expect an exception here)
with self.assertRaises(Exception):
frame1.name = graph_name
# frame1 and the graph should still exist on the server
self.assertTrue(frame_name1 in ta.get_frame_names(), frame_name1 + " should still exist in the list of frames")
self.assertTrue(graph_name in ta.get_graph_names(), graph_name + " should still exist in the list of graphs")
# Try to rename frame1 to have the same name as the model (we expect an exception here)
with self.assertRaises(Exception):
frame1.name = model_name
# frame1 and the model should still exist on the server
self.assertTrue(frame_name1 in ta.get_frame_names(), frame_name1 + " should still exist in the list of frames")
self.assertTrue(model_name in ta.get_model_names(), model_name + " should still exist in the list of models")
def test_naive_bayes(self):
print "define csv file"
csv = ta.CsvFile("hdfs://nameservice1/org/intel/hdfsbroker/userspace/ae6a38d3-191f-494f-86a6-3fe1b2255902/e3327582-f475-4dc9-8efa-96070abb606d/000000_1",
schema=[
("GXY",ta.int32),
#("HPI",ta.ignore),
("Age",ta.int32),
("Sex",ta.int32),
("Height",ta.float64),
("Weight",ta.float64),
("BMI",ta.float64),
("DBP",ta.float64),
("SBP",ta.float64),
("HCT",ta.float64),
("MCV",ta.float64),
("RDW_SD",ta.float64),
("RDW_CV",ta.float64),
("HGB",ta.float64),
("MCH",ta.float64),
("MCHC",ta.float64),
("RBC",ta.float64),
("WBC",ta.float64),
("NEUT1",ta.float64),
("LYMPH",ta.float64),
("MONO1",ta.float64),
("EO1",ta.float64),
("BASO1",ta.float64),
("NEUT2",ta.float64),
("MONO2",ta.float64),
("EO2",ta.float64),
("BASO2",ta.float64),
("PLT",ta.float64),
#("PDW",ta.ignore),
("MPV",ta.float64),
("P_LCR",ta.float64),
("PCT",ta.float64),
("Lymph_3",ta.float64),
("ESR",ta.float64),
("PH",ta.float64),
("PRO",ta.float64),
("GIu",ta.float64),
("KET",ta.float64),
("BLD",ta.float64),
("BIL",ta.float64),
("URO",ta.float64),
("NIT",ta.float64),
("SG",ta.float64),
("LEU",ta.float64),
("N_QT",ta.float64),
("VC",ta.float64),
#("ECG",ta.ignore),
#("BCJC1",ta.ignore),
#("IRDS",ta.ignore),
#("WK",ta.ignore),
("OB",ta.float64),
("FBG",ta.float64),
("HBsAg",ta.float64),
("HBsAb",ta.float64),
("HBeAg",ta.float64),
("HBeAb",ta.float64),
("HBcAb",ta.float64),
("TBiL",ta.float64),
("ALT",ta.float64),
("AST",ta.float64),
("AKP",ta.float64),
("GGT",ta.float64),
("ADA",ta.float64),
("TPO",ta.float64),
("Aib",ta.float64),
("Gib",ta.float64),
("A_G",ta.float64),
("PA",ta.float64),
("AST_ALT",ta.float64),
("BUN",ta.float64),
("Cr",ta.float64),
("UA",ta.float64),
("CK",ta.float64),
("LDH",ta.float64),
("CK_MB",ta.float64),
("LDH_MB",ta.float64),
("a_HBD",ta.float64),
("TNI",ta.float64),
("Fg",ta.float64),
("K1",ta.float64),
("AFP",ta.float64),
("CEA",ta.float64),
("Free_PSA",ta.float64),
("CA125",ta.float64),
("CA19_9",ta.float64),
("NSE",ta.float64),
("CA242",ta.float64),
("B_HCG",ta.float64),
("CA15_3",ta.float64),
("CA50",ta.float64),
("CA72_4",ta.float64),
("HGH",ta.float64),
("SF",ta.float64),
("QJD",ta.float64),
("DCJC",ta.float64),
("MJJC",ta.float64),
("RUT",ta.float64),
("PGI_PGII",ta.float64),
("Ca2",ta.float64),
("P3",ta.float64),
("K2",ta.float64),
("Na",ta.float64),
("CI",ta.float64)
], skip_header_lines=1)
print "create frame"
frame_name = 'ModelNaiveBayesFrame'
exist_frames = ta.get_frame_names()
if frame_name in exist_frames:
print "Frame exists, delete it"
ta.drop_frames(frame_name)
train_frame = ta.Frame(csv, frame_name)
print "Initializing a RandomForestModel object"
model_name = 'POCModelNaiveBayesModel'
exist_models = ta.get_model_names()
if model_name in exist_models:
print "Model exist, delete"
ta.drop_models(model_name)
naive = ta.NaiveBayesModel(name=model_name)
print "Training the model on the Frame"
naive.train(train_frame,'GXY',['Age','Sex','Height','Weight','BMI','DBP','SBP','HCT','MCV','RDW_SD',
'RDW_CV','HGB','MCH','MCHC','RBC','WBC','NEUT1','LYMPH','MONO1','EO1','BASO1','NEUT2',
'MONO2','EO2','BASO2','PLT','MPV','P_LCR','PCT','Lymph_3','ESR','PH','PRO',
'GIu','KET','BLD','BIL','URO','NIT','SG','LEU','N_QT','VC',
'OB','FBG','HBsAg','HBsAb','HBeAg','HBeAb','HBcAb','TBiL','ALT','AST','AKP','GGT',
'ADA','TPO','Aib','Gib','A_G','PA','AST_ALT','BUN','Cr','UA','CK','LDH','CK_MB',
'LDH_MB','a_HBD','TNI','Fg','K1','AFP','CEA','Free_PSA','CA125','CA19_9','NSE','CA242',
'B_HCG','CA15_3','CA50','CA72_4','HGH','SF','QJD','DCJC','MJJC','RUT','PGI_PGII',
'Ca2','P3','K2','Na','CI'],num_classes=2)
print "Predicting on the Frame"
output = naive.predict(train_frame)
self.assertEqual(output.column_names,['GXY','Age','Sex','Height','Weight','BMI','DBP','SBP','HCT',
'MCV','RDW_SD','RDW_CV','HGB','MCH','MCHC','RBC','WBC','NEUT1','LYMPH',
'MONO1','EO1','BASO1','NEUT2','MONO2','EO2','BASO2','PLT','MPV',
'P_LCR','PCT','Lymph_3','ESR','PH','PRO','GIu','KET','BLD','BIL','URO',
'NIT','SG','LEU','N_QT','VC','OB','FBG','HBsAg',
'HBsAb','HBeAg','HBeAb','HBcAb','TBiL','ALT','AST','AKP','GGT','ADA',
'TPO','Aib','Gib','A_G','PA','AST_ALT','BUN','Cr','UA','CK','LDH',
'CK_MB','LDH_MB','a_HBD','TNI','Fg','K1','AFP','CEA','Free_PSA','CA125',
'CA19_9','NSE','CA242','B_HCG','CA15_3','CA50','CA72_4','HGH','SF','QJD',
'DCJC','MJJC','RUT','PGI_PGII','Ca2','P3','K2','Na','CI','predicted_class'])
def testLinearRegression(self):
print "define csv file"
csv = ta.CsvFile("hdfs://nameservice1/org/intel/hdfsbroker/userspace/9bb351fa-7b17-4a81-b3b0-521639c1d473/d342214b-c4c0-4963-aeaf-5adf054e22b6/000000_1",
schema=[
("GXY",ta.int32),
#("HPI",ta.ignore),
("Age",ta.int32),
("Sex",ta.int32),
("Height",ta.float64),
("Weight",ta.float64),
("BMI",ta.float64),
("DBP",ta.float64),
("SBP",ta.float64),
("HCT",ta.float64),
("MCV",ta.float64),
("RDW_SD",ta.float64),
("RDW_CV",ta.float64),
("HGB",ta.float64),
("MCH",ta.float64),
("MCHC",ta.float64),
("RBC",ta.float64),
("WBC",ta.float64),
("NEUT1",ta.float64),
("LYMPH",ta.float64),
("MONO1",ta.float64),
("EO1",ta.float64),
("BASO1",ta.float64),
("NEUT2",ta.float64),
("MONO2",ta.float64),
("EO2",ta.float64),
("BASO2",ta.float64),
("PLT",ta.float64),
#("PDW",ta.ignore),
("MPV",ta.float64),
("P_LCR",ta.float64),
("PCT",ta.float64),
("Lymph_3",ta.float64),
("ESR",ta.float64),
("PH",ta.float64),
("PRO",ta.float64),
("GIu",ta.float64),
("KET",ta.float64),
("BLD",ta.float64),
("BIL",ta.float64),
("URO",ta.float64),
("NIT",ta.float64),
("SG",ta.float64),
("LEU",ta.float64),
("N_QT",ta.float64),
("VC",ta.float64),
#("ECG",ta.ignore),
#("BCJC1",ta.ignore),
#("IRDS",ta.ignore),
#("WK",ta.ignore),
("OB",ta.float64),
("FBG",ta.float64),
("HBsAg",ta.float64),
("HBsAb",ta.float64),
("HBeAg",ta.float64),
("HBeAb",ta.float64),
("HBcAb",ta.float64),
("TBiL",ta.float64),
("ALT",ta.float64),
("AST",ta.float64),
("AKP",ta.float64),
("GGT",ta.float64),
("ADA",ta.float64),
("TPO",ta.float64),
("Aib",ta.float64),
("Gib",ta.float64),
("A_G",ta.float64),
("PA",ta.float64),
("AST_ALT",ta.float64),
("BUN",ta.float64),
("Cr",ta.float64),
("UA",ta.float64),
("CK",ta.float64),
("LDH",ta.float64),
("CK_MB",ta.float64),
("LDH_MB",ta.float64),
("a_HBD",ta.float64),
("TNI",ta.float64),
("Fg",ta.float64),
("K1",ta.float64),
("AFP",ta.float64),
("CEA",ta.float64),
("Free_PSA",ta.float64),
("CA125",ta.float64),
("CA19_9",ta.float64),
("NSE",ta.float64),
("CA242",ta.float64),
("B_HCG",ta.float64),
("CA15_3",ta.float64),
("CA50",ta.float64),
("CA72_4",ta.float64),
("HGH",ta.float64),
("SF",ta.float64),
("QJD",ta.float64),
("DCJC",ta.float64),
("MJJC",ta.float64),
("RUT",ta.float64),
("PGI_PGII",ta.float64),
("Ca2",ta.float64),
("P3",ta.float64),
("K2",ta.float64),
("Na",ta.float64),
("CI",ta.float64)
], skip_header_lines=1)
print "create frame"
frame_name = 'Random_forest_SampleFrame'
exist_frames = ta.get_frame_names()
if frame_name in exist_frames:
print "Frame exists, delete it"
ta.drop_frames(frame_name)
frame = ta.Frame(csv, frame_name)
#frame = ta.Frame(csv)
print "Initializing a RandomForestModel object"
model_name = 'POCRandom_forest_SampleModel'
exist_models = ta.get_model_names()
if model_name in exist_models:
print "Model exist, delete"
ta.drop_models(model_name)
#model = ta.LinearRegressionModel(name=model_name)
classifier = ta.RandomForestClassifierModel(name=model_name)
print "Training the model on the Frame"
classifier .train(frame,'GXY',['Age','Sex','Height','Weight','BMI','DBP','SBP','HCT','MCV','RDW_SD',
'RDW_CV','HGB','MCH','MCHC','RBC','WBC','NEUT1','LYMPH','MONO1','EO1','BASO1','NEUT2',
'MONO2','EO2','BASO2','PLT','MPV','P_LCR','PCT','Lymph_3','ESR','PH','PRO',
'GIu','KET','BLD','BIL','URO','NIT','SG','LEU','N_QT','VC',
'OB','FBG','HBsAg','HBsAb','HBeAg','HBeAb','HBcAb','TBiL','ALT','AST','AKP','GGT',
'ADA','TPO','Aib','Gib','A_G','PA','AST_ALT','BUN','Cr','UA','CK','LDH','CK_MB',
'LDH_MB','a_HBD','TNI','Fg','K1','AFP','CEA','Free_PSA','CA125','CA19_9','NSE','CA242',
'B_HCG','CA15_3','CA50','CA72_4','HGH','SF','QJD','DCJC','MJJC','RUT','PGI_PGII',
'Ca2','P3','K2','Na','CI'],num_classes=2)
print "Predicting on the Frame"
output = classifier.predict(frame)
self.assertEqual(output.column_names,['GXY','Age','Sex','Height','Weight','BMI','DBP','SBP','HCT',
'MCV','RDW_SD','RDW_CV','HGB','MCH','MCHC','RBC','WBC','NEUT1','LYMPH',
'MONO1','EO1','BASO1','NEUT2','MONO2','EO2','BASO2','PLT','MPV',
'P_LCR','PCT','Lymph_3','ESR','PH','PRO','GIu','KET','BLD','BIL','URO',
'NIT','SG','LEU','N_QT','VC','OB','FBG','HBsAg',
'HBsAb','HBeAg','HBeAb','HBcAb','TBiL','ALT','AST','AKP','GGT','ADA',
'TPO','Aib','Gib','A_G','PA','AST_ALT','BUN','Cr','UA','CK','LDH',
'CK_MB','LDH_MB','a_HBD','TNI','Fg','K1','AFP','CEA','Free_PSA','CA125',
'CA19_9','NSE','CA242','B_HCG','CA15_3','CA50','CA72_4','HGH','SF','QJD',
'DCJC','MJJC','RUT','PGI_PGII','Ca2','P3','K2','Na','CI','predicted_class'])
def test_drop_model_that_does_not_exist(self):
model_name = str(uuid.uuid1()).replace('-','_')
self.assertFalse(model_name in ta.get_model_names(), model_name + " should not exist in the list of models")
self.assertEqual(0, ta.drop_models(model_name), "drop_models() shouldn't have deleted any models.")
def test_drop_model_that_does_not_exist(self):
model_name = str(uuid.uuid1()).replace('-','_')
self.assertFalse(model_name in ta.get_model_names(), model_name + " should not exist in the list of models")
self.assertEqual(0, ta.drop_models(model_name), "drop_models() shouldn't have deleted any models.")