def test_frame_drop(self):
print "define csv file"
csv = ta.CsvFile("/datasets/classification-compute.csv",
schema=[('a', str), ('b', ta.int32),
('labels', ta.int32),
('predictions', ta.int32)],
delimiter=',',
skip_header_lines=1)
print "create frame"
frame = ta.Frame(csv, name="test_frame_drop")
print "dropping frame by entity"
ta.drop_frames(frame)
frames = ta.get_frame_names()
self.assertFalse("test_frame_drop" in frames,
"test_frame_drop should not exist in list of frames")
frame = ta.Frame(csv, name="test_frame_drop")
print "dropping frame by name"
self.assertEqual(1, ta.drop_frames("test_frame_drop"),
"drop_frames() should have deleted one frame")
self.assertFalse("test_frame_drop" in frames,
"test_frame_drop should not exist in list of frames")
def test_access_refreshes_frames(self):
"""Tests that some actions do or do not update the last_read_date entity property"""
csv = ta.CsvFile("/datasets/dates.csv", schema= [('start', ta.datetime),
('id', int),
('stop', ta.datetime),
('color', str)], delimiter=',')
name = "update_last_read"
if name in ta.get_frame_names():
ta.drop_frames(name)
f = ta.Frame(csv, name=name) # name it, to save it from the other GC blasting test in here
t0 = f.last_read_date
t1 = f.last_read_date
#print "t0=%s" % t0.isoformat()
self.assertEqual(t0, t1)
f.schema # schema, or other meta data property reads, should not update the last read date
t2 = f.last_read_date
#print "t2=%s" % t2.isoformat()
self.assertEqual(t0, t2)
f.inspect() # inspect should update the last read date
t3 = f.last_read_date
#print "t3=%s" % t3.isoformat()
self.assertLess(t2,t3)
f.copy() # copy should update the last read date
t4 = f.last_read_date
#print "t4=%s" % t4.isoformat()
self.assertLess(t3,t4)
f.bin_column('id', [3, 5, 8])
t5 = f.last_read_date
#print "t5=%s" % t5.isoformat()
self.assertLess(t4,t5)
def test_gc_drop_stale_and_finalize(self):
csv = ta.CsvFile("/datasets/dates.csv",
schema=[('start', ta.datetime), ('id', int),
('stop', ta.datetime), ('color', str)],
delimiter=',')
f2_name = "dates_two"
if f2_name in ta.get_frame_names():
ta.drop_frames(f2_name)
f1 = ta.Frame(csv)
f1e = f1.get_error_frame()
self.assertIsNotNone(f1e)
self.assertIsNone(f1e.name)
f2 = ta.Frame(csv, name=f2_name)
f2e = f2.get_error_frame()
self.assertIsNotNone(f2e)
self.assertIsNone(f2e.name)
admin.drop_stale(
) # first, normal drop_stale, nothing should change because these frames aren't old enough
self.assertEqual("ACTIVE", f1.status)
self.assertEqual("ACTIVE", f1e.status)
self.assertEqual("ACTIVE", f2.status)
self.assertEqual("ACTIVE", f2e.status)
# print "f1.status=%s, f2.status=%s" % (f1.status, f2.status)
admin.finalize_dropped(
) # nothing is dropped, so nothing so be finalized
self.assertEqual("ACTIVE", f1.status)
self.assertEqual("ACTIVE", f1e.status)
self.assertEqual("ACTIVE", f2.status)
self.assertEqual("ACTIVE", f2e.status)
admin.drop_stale(
"1ms"
) # now drop with very tiny age, so non-name f1 should get dropped
self.assertEqual("DROPPED", f1.status)
self.assertEqual("DROPPED", f1e.status)
self.assertEqual("ACTIVE", f2.status)
self.assertEqual("ACTIVE", f2e.status)
# print "f1.status=%s, f2.status=%s" % (f1.status, f2.status)
admin.finalize_dropped(
) # on f1 and f1e are dropped, so only they should be finalized
self.assertEqual("FINALIZED", f1.status)
self.assertEqual("FINALIZED", f1e.status)
self.assertEqual("ACTIVE", f2.status)
self.assertEqual("ACTIVE", f2e.status)
def test_drop_frame_that_does_not_exist(self):
frame_name = str(uuid.uuid1()).replace('-', '_')
self.assertFalse(
frame_name in ta.get_frame_names(),
frame_name + " should not exist in the list of frames")
self.assertEqual(0, ta.drop_frames(frame_name),
"drop_frames() should not have deleted any frames")
def test_gc_drop_stale_and_finalize(self):
csv = ta.CsvFile("/datasets/dates.csv", schema= [('start', ta.datetime),
('id', int),
('stop', ta.datetime),
('color', str)], delimiter=',')
f2_name = "dates_two"
if f2_name in ta.get_frame_names():
ta.drop_frames(f2_name)
f1 = ta.Frame(csv)
f1e = f1.get_error_frame()
self.assertIsNotNone(f1e)
self.assertIsNone(f1e.name)
f2 = ta.Frame(csv, name=f2_name)
f2e = f2.get_error_frame()
self.assertIsNotNone(f2e)
self.assertIsNone(f2e.name)
admin.drop_stale() # first, normal drop_stale, nothing should change because these frames aren't old enough
self.assertEqual("ACTIVE", f1.status)
self.assertEqual("ACTIVE", f1e.status)
self.assertEqual("ACTIVE", f2.status)
self.assertEqual("ACTIVE", f2e.status)
# print "f1.status=%s, f2.status=%s" % (f1.status, f2.status)
admin.finalize_dropped() # nothing is dropped, so nothing so be finalized
self.assertEqual("ACTIVE", f1.status)
self.assertEqual("ACTIVE", f1e.status)
self.assertEqual("ACTIVE", f2.status)
self.assertEqual("ACTIVE", f2e.status)
admin.drop_stale("1ms") # now drop with very tiny age, so non-name f1 should get dropped
self.assertEqual("DROPPED", f1.status)
self.assertEqual("DROPPED", f1e.status)
self.assertEqual("ACTIVE", f2.status)
self.assertEqual("ACTIVE", f2e.status)
# print "f1.status=%s, f2.status=%s" % (f1.status, f2.status)
admin.finalize_dropped() # on f1 and f1e are dropped, so only they should be finalized
self.assertEqual("FINALIZED", f1.status)
self.assertEqual("FINALIZED", f1e.status)
self.assertEqual("ACTIVE", f2.status)
self.assertEqual("ACTIVE", f2e.status)
def test_frame_drop(self):
print "define csv file"
csv = ta.CsvFile("/datasets/classification-compute.csv", schema= [('a', str),
('b', ta.int32),
('labels', ta.int32),
('predictions', ta.int32)], delimiter=',', skip_header_lines=1)
print "create frame"
frame = ta.Frame(csv, name="test_frame_drop")
print "dropping frame by entity"
ta.drop_frames(frame)
frames = ta.get_frame_names()
self.assertFalse("test_frame_drop" in frames, "test_frame_drop should not exist in list of frames")
frame = ta.Frame(csv, name="test_frame_drop")
print "dropping frame by name"
self.assertEqual(1, ta.drop_frames("test_frame_drop"), "drop_frames() should have deleted one frame")
self.assertFalse("test_frame_drop" in frames, "test_frame_drop should not exist in list of frames")
def test_generic_drop_duplicate_items(self):
frame_name = str(uuid.uuid1()).replace('-','_')
frame = ta.Frame(name=frame_name)
# Check that the frame we just created now exists
self.assertTrue(frame_name in ta.get_frame_names(), frame_name + " should exist in the list of frame names")
# drop_frames() with multiple of the same item
self.assertEqual(1, ta.drop_frames([frame, frame, frame_name]), "drop_frames() should have deleted 1 item")
# Check that the frame no longer exists
self.assertFalse(frame_name in ta.get_frame_names(), frame_name + " should not be in the list of frame names")
def test_access_refreshes_frames(self):
"""Tests that some actions do or do not update the last_read_date entity property"""
csv = ta.CsvFile("/datasets/dates.csv",
schema=[('start', ta.datetime), ('id', int),
('stop', ta.datetime), ('color', str)],
delimiter=',')
name = "update_last_read"
if name in ta.get_frame_names():
ta.drop_frames(name)
f = ta.Frame(
csv, name=name
) # name it, to save it from the other GC blasting test in here
t0 = f.last_read_date
t1 = f.last_read_date
#print "t0=%s" % t0.isoformat()
self.assertEqual(t0, t1)
f.schema # schema, or other meta data property reads, should not update the last read date
t2 = f.last_read_date
#print "t2=%s" % t2.isoformat()
self.assertEqual(t0, t2)
f.inspect() # inspect should update the last read date
t3 = f.last_read_date
#print "t3=%s" % t3.isoformat()
self.assertLess(t2, t3)
f.copy() # copy should update the last read date
t4 = f.last_read_date
#print "t4=%s" % t4.isoformat()
self.assertLess(t3, t4)
f.bin_column('id', [3, 5, 8])
t5 = f.last_read_date
#print "t5=%s" % t5.isoformat()
self.assertLess(t4, t5)
def test_generic_drop_duplicate_items(self):
frame_name = str(uuid.uuid1()).replace('-', '_')
frame = ta.Frame(name=frame_name)
# Check that the frame we just created now exists
self.assertTrue(
frame_name in ta.get_frame_names(),
frame_name + " should exist in the list of frame names")
# drop_frames() with multiple of the same item
self.assertEqual(1, ta.drop_frames([frame, frame, frame_name]),
"drop_frames() should have deleted 1 item")
# Check that the frame no longer exists
self.assertFalse(
frame_name in ta.get_frame_names(),
frame_name + " should not be in the list of frame names")
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'])
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import trustedanalytics as ta
ta.connect()
for name in ta.get_frame_names():
print 'deleting frame: %s' % name
ta.drop_frames(name)
employees_frame = ta.Frame(
ta.CsvFile("employees.csv",
schema=[('Employee', str), ('Manager', str), ('Title', str),
('Years', ta.int64)],
skip_header_lines=1), 'employees_frame')
employees_frame.inspect()
#A bipartite graph
#Notice that this is a funny example since managers are also employees!
#Preseuambly Steve the manager and Steve the employee are the same person
#Option 1
"." + parameters.table_name))
else:
raise AtkTestException(
"Column was NOT added to table {}".format(parameters.database_name +
"." + parameters.table_name))
print("\n------------ Test: drop_column method ------------")
frame_select.drop_columns('test_column')
frame_drop_columns_list = frame_select.column_names
frame_drop_columns_len = len(frame_drop_columns_list)
if frame_drop_columns_len == column_names_len and 'test_column' not in frame_drop_columns_list:
print("Column 'test_column' was dropped in table {}".format(
parameters.database_name + "." + parameters.table_name))
else:
raise AtkTestException(
"Column was NOT dropped in table {}".format(parameters.database_name +
"." +
parameters.table_name))
print("\n------------ Test: drop_frames method ----------------")
ta.drop_frames([frame_select, frame_group])
if frame_select.status != 'Active' and frame_group.status != 'Active':
print("Frames {}, {} removed successfully".format(frame_select,
frame_group))
else:
raise AtkTestException(
"Frames {}, {} NOT deleted. Status of both frames should be Deleted ".
format(frame_select, frame_group))
def test_drop_frame_that_does_not_exist(self):
frame_name = str(uuid.uuid1()).replace('-','_')
self.assertFalse(frame_name in ta.get_frame_names(), frame_name + " should not exist in the list of frames")
self.assertEqual(0, ta.drop_frames(frame_name), "drop_frames() should not have deleted any frames")
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import trustedanalytics as ta
ta.connect()
for name in ta.get_frame_names():
print 'deleting frame: %s' %name
ta.drop_frames(name)
employees_frame = ta.Frame(ta.CsvFile("employees.csv", schema = [('Employee', str), ('Manager', str), ('Title', str), ('Years', ta.int64)], skip_header_lines=1), 'employees_frame')
employees_frame.inspect()
#A bipartite graph
#Notice that this is a funny example since managers are also employees!
#Preseuambly Steve the manager and Steve the employee are the same person
#Option 1
graph = ta.Graph()
graph.define_vertex_type('Employee')
graph.define_edge_type('worksunder', 'Employee', 'Employee', directed=False)
], skip_header_lines=1);
# In[27]:
#create frame
#frame_name = "myframe";
#if frame_name in ta.get_frame_names():
#ta.drop_frames(frame_name)
frame_name = 'myframe'
exist_frames = ta.get_frame_names()
if frame_name in exist_frames:
print "Frame exists, delete it"
ta.drop_frames(frame_name)
my_frame = ta.Frame(csv, frame_name)
my_frame.inspect(21)
# In[31]:
#feature classify
def transformation_DBP(row):
#＜60一组，60~90每10mmHg一组，≥90一组
dbp = row.DBP
if dbp < 60.0:
dbp = 1;
if dbp >= 60.0 and dbp < 70.0: