def get_stub():
server_channel_address = os.environ.get('TA2_SERVER_CONN')
# complain in the return if we didn't get an address to connect to
if server_channel_address is None:
tangelo.http_status(500)
return {'error': 'TA2_SERVER_CONN environment variable is not set!'}
channel = grpc.insecure_channel(server_channel_address)
stub = core_pb2_grpc.CoreStub(channel)
return stub
def test_session(self):
channel = grpc.insecure_channel('localhost:45042')
stub = core_pb2_grpc.CoreStub(channel)
msg = core_pb2.SessionRequest(user_agent="unittest", version="Foo")
session = stub.StartSession(msg)
self.assertTrue(session.response_info.status.code == core_pb2.OK)
session_end_response = stub.EndSession(session.context)
self.assertTrue(session_end_response.status.code == core_pb2.OK)
# Try to end a session that does not exist
fake_context = core_pb2.SessionContext(session_id="fake context")
session_end_response = stub.EndSession(fake_context)
self.assertTrue(
session_end_response.status.code == core_pb2.SESSION_UNKNOWN)
def post(port=None):
# get the protocol version
version = core_pb2.DESCRIPTOR.GetOptions().Extensions[
core_pb2.protocol_version]
# get the address from an environment variable. This must be set in the executing shell.
# During automated evaluation runs, the environment variable will be set by Kubernetes
server_channel_address = os.environ.get('TA2_SERVER_CONN')
# complain in the return if we didn't get an address to connect to
if server_channel_address is None:
tangelo.http_status(500)
return {'error': 'TA2_SERVER_CONN environment variable is not set!'}
#channel = grpc.insecure_channel('localhost:%d' % (int(port)))
channel = grpc.insecure_channel(server_channel_address)
stub = core_pb2_grpc.CoreStub(channel)
resp = stub.StartSession(
core_pb2.SessionRequest(user_agent='modsquad', version=version))
return MessageToJson(resp)
def get_grpc_stub():
"""Make sure the gRPC channel is initialized and return the CoreStub."""
global _GRPC_CORE_STUB
if _GRPC_CORE_STUB is not None: # channel already initialized
return _GRPC_CORE_STUB, None
if not settings.TA2_TEST_SERVER_URL:
"""No server set!!!"""
return None, ('No TA2 server url was found in'
' the TwoRavens settings (see'
' "TA2_TEST_SERVER_URL")')
try:
channel = grpc.insecure_channel(settings.TA2_TEST_SERVER_URL)
except Exception as ex:
return None, 'Could not initialize gRPC channel.(1) %s' % ex
try:
_GRPC_CORE_STUB = cpb_grpc.CoreStub(channel)
except Exception as ex:
return None, 'Could not initialize gRPC channel.(2) %s' % ex
return _GRPC_CORE_STUB, None
def test_pipeline(self):
"Tries setting up a new pipeline"
channel = grpc.insecure_channel('localhost:45042')
stub = core_pb2_grpc.CoreStub(channel)
msg = core_pb2.SessionRequest(user_agent="unittest", version="Foo")
session = stub.StartSession(msg)
self.assertTrue(session.response_info.status.code == core_pb2.OK)
pipeline_request = core_pb2.PipelineCreateRequest(
context=session.context,
dataset_uri=
"file:///home/sheath/projects/D3M/cmu-ta3/test-data/185_baseball/TRAIN/dataset_TRAIN/datasetDoc.json",
task=core_pb2.TASK_TYPE_UNDEFINED,
task_subtype=core_pb2.TASK_SUBTYPE_UNDEFINED,
task_description="",
output=core_pb2.OUTPUT_TYPE_UNDEFINED,
metrics=[],
target_features=[],
predict_features=[],
max_pipelines=10)
p = stub.CreatePipelines(pipeline_request)
for response in p:
self.assertTrue(response.response_info.status.code == core_pb2.OK)
def run():
channel = grpc.insecure_channel('localhost:45042')
stub = crpc.CoreStub(channel)
dstub = drpc.DataExtStub(channel)
dfstub = dfrpc.DataflowExtStub(channel)
# Start Session
session_response = stub.StartSession(
core.SessionRequest(user_agent="xxx", version="1.0"))
session_context = session_response.context
print("Session started (%s)" % str(session_context.session_id))
# Send pipeline creation request
dataset_uri = "file:///tmp/data/185_baseball/185_baseball_dataset/datasetDoc.json"
some_features = [
core.Feature(resource_id="0", feature_name="d3mIndex"),
core.Feature(resource_id="0", feature_name="Games_played"),
core.Feature(resource_id="0", feature_name="Runs"),
core.Feature(resource_id="0", feature_name="Hits"),
core.Feature(resource_id="0", feature_name="Home_runs")
]
target_features = [
core.Feature(resource_id="0", feature_name="Hall_of_Fame")
]
task = core.TaskType.Value('CLASSIFICATION')
task_subtype = core.TaskSubtype.Value('MULTICLASS')
task_description = "Classify Hall of Fame"
output = core.OutputType.Value('OUTPUT_TYPE_UNDEFINED')
metrics = [
core.PerformanceMetric.Value('F1_MICRO'),
core.PerformanceMetric.Value('F1_MACRO')
]
max_pipelines = 10
pipeline_ids = []
print("Training with some features")
pc_request = core.PipelineCreateRequest(context=session_context,
dataset_uri=dataset_uri,
predict_features=some_features,
task=task,
task_subtype=task_subtype,
task_description=task_description,
output=output,
metrics=metrics,
target_features=target_features,
max_pipelines=max_pipelines)
'''
# Iterate over results
for pcr in stub.CreatePipelines(pc_request):
print(str(pcr))
if len(pcr.pipeline_info.scores) > 0:
pipeline_ids.append(pcr.pipeline_id)
print("Training with some features")
pc_request = core.PipelineCreateRequest(
context = session_context,
train_features = some_features,
task = task,
task_subtype = task_subtype,
task_description = task_description,
output = output,
metrics = metrics,
target_features = target_features,
max_pipelines = max_pipelines
)
'''
result = stub.CreatePipelines(pc_request)
# Iterate over results
for pcr in result:
print(str(pcr))
'''
for gdr in dfstub.GetDataflowResults(dfext.PipelineReference(context = session_context,
pipeline_id = pcr.pipeline_id)):
print(gdr)
'''
if len(pcr.pipeline_info.scores) > 0:
pipeline_id = pcr.pipeline_id
pipeline_ids.append(pipeline_id)
dflow = dfstub.DescribeDataflow(
dfext.PipelineReference(context=session_context,
pipeline_id=pipeline_id))
print(dflow)
exres = stub.ExportPipeline(
core.PipelineExportRequest(
context=session_context,
pipeline_id=pipeline_id,
pipeline_exec_uri="file:///tmp/{}".format(pipeline_id)))
print(exres)
'''
if pcr.pipeline_info.predict_result_uri is not None:
df = pandas.read_csv(pcr.pipeline_info.predict_result_uri, index_col="d3mIndex")
print(df)
'''
print("************** Executing/Testing Pipelines")
# Execute pipelines
for pipeline_id in pipeline_ids:
print("Executing Pipeline %s" % pipeline_id)
ep_request = core.PipelineExecuteRequest(context=session_context,
pipeline_id=pipeline_id,
dataset_uri=dataset_uri)
for ecr in stub.ExecutePipeline(ep_request):
print(str(ecr))
if ecr.result_uri is not None:
df = pandas.read_csv(ecr.result_uri, index_col="d3mIndex")
print(df)
list_request = core.PipelineListRequest(context=session_context)
lrr = stub.ListPipelines(list_request)
print(lrr.pipeline_ids)
print("************** Cached pipeline create results")
pcrr = core.PipelineCreateResultsRequest(context=session_context,
pipeline_ids=lrr.pipeline_ids)
for gcpr in stub.GetCreatePipelineResults(pcrr):
print(str(gcpr))
print("************** Cached pipeline execute results")
perr = core.PipelineExecuteResultsRequest(context=session_context,
pipeline_ids=lrr.pipeline_ids)
for gepr in stub.GetExecutePipelineResults(perr):
print(str(gepr))
print("*********** Updating Metric to Accuracy.. Create pipelines again")
metric = core.PerformanceMetric.Value('ACCURACY')
ups_request = core.SetProblemDocRequest(
context=session_context,
updates=[
core.SetProblemDocRequest.ReplaceProblemDocField(metric=metric)
])
print(stub.SetProblemDoc(ups_request))
print("********** Re-running pipeline creation")
for pcr in stub.CreatePipelines(
core.PipelineCreateRequest(context=session_context)):
print(str(pcr))
stub.EndSession(session_context)
def setUp(self):
self.protocol_version = core_pb2.DESCRIPTOR.GetOptions().Extensions[
core_pb2.protocol_version]
channel = grpc.insecure_channel('localhost:50052')
self.stub = core_pb2_grpc.CoreStub(channel)