def execute_pipeline_parse():
"""...PipelineExecuteRequest"""
req = core_pb2.PipelineExecuteRequest()
req.context.session_id = 'session_01'
req.pipeline_id = 'pipeline_01'
feature_names = ('cylinders displacement horsepower'
' weight acceleration model class').split()
for feature_name in feature_names:
req.predict_features.add(feature_id=feature_name,
data_uri='<<DATA_URI>>')
content = MessageToJson(req, including_default_value_fields=True)
print('JSON:\n')
print(content)
print('-' * 40)
#content = content.replace('pipelineIds', 'pipeline_ids').replace('sessionId', 'session_id')
print(content)
print('-' * 40)
print('gRPC:\n')
json_parse(content, core_pb2.PipelineExecuteRequest)
print('-' * 40)
def executePipeline(context=None, pipeline=None, data_uri=None):
stub = get_stub()
# add file descriptor if it is missing. some systems might be inconsistent, but file:// is the standard
if data_uri[0:4] != 'file':
data_uri = 'file://%s' % (data_uri)
context_in = cpb.SessionContext(session_id=context)
request_in = cpb.PipelineExecuteRequest(context=context_in,
pipeline_id=pipeline,
dataset_uri=data_uri)
resp = stub.ExecutePipeline(request_in)
executedPipes = map(lambda x: json.loads(MessageToJson(x)), resp)
print executedPipes
# now loop through the returned pipelines and copy their data
map(lambda x: copyToWebRoot(x), executedPipes)
return executedPipes
def executePipeline(port=None,
session=None,
pipeline=None,
data=None,
predictor=None):
stub = get_stub(int(port))
data_uri = 'file://%s' % (data)
predictor = json.loads(predictor)
resp = stub.ExecutePipeline(
cpb.PipelineExecuteRequest(context=Parse(session,
cpb.SessionContext()),
pipeline_id=pipeline,
predict_features=[
cpb.Feature(feature_id=pred,
data_uri=data_uri)
for pred in predictor
]))
return map(lambda x: json.loads(MessageToJson(x)), resp)
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 execute_pipeline(info_str=None):
"""Ask a TA2 to ListPipelines via gRPC
This call is a bit different b/c it writes part of the data to a file
and places that file uri into the original request
Success: (updated request str, grpc json response)
Failure: (None, error message)
"""
if info_str is None:
info_str = get_test_info_str()
if info_str is None:
err_msg = 'UI Str for PipelineListResult is None'
return None, get_failed_precondition_response(err_msg)
if info_str.find(VAL_DATA_URI) == -1:
err_msg = ('Expected to see place holder for file uri.'
' Placeholder is "%s"') % VAL_DATA_URI
return None, get_failed_precondition_response(err_msg)
d3m_config = get_latest_d3m_config()
if not d3m_config:
err_msg = ('The D3M configuration is not available.'
' Therefore, there is no "temp_storage_root" directory to'
' write the data.')
return None, get_failed_precondition_response(err_msg)
# --------------------------------
# Is this valid JSON?
# --------------------------------
try:
info_dict = json.loads(info_str, object_pairs_hook=OrderedDict)
except json.decoder.JSONDecodeError as err_obj:
err_msg = 'Failed to convert UI Str to JSON: %s' % (err_obj)
return None, get_failed_precondition_response(err_msg)
if not KEY_DATA in info_dict:
err_msg = ('The JSON request did not contain a "%s" key.') % KEY_DATA
return None, get_failed_precondition_response(err_msg)
file_uri, err_msg = write_data_for_execute_pipeline(
d3m_config, info_dict[KEY_DATA])
if err_msg is not None:
return None, get_failed_precondition_response(err_msg)
# Reformat the original content
#
# (1) remove the data key
if KEY_DATA in info_dict:
del info_dict[KEY_DATA]
# (2) convert it back to a JSON string
info_str = json.dumps(info_dict)
# (3) replace the VAL_DATA_URI with the file_uri
info_str_formatted = info_str.replace(VAL_DATA_URI, file_uri)
# --------------------------------
# convert the JSON string to a gRPC request
# --------------------------------
try:
req = Parse(info_str_formatted, core_pb2.PipelineExecuteRequest())
except ParseError as err_obj:
err_msg = 'Failed to convert JSON to gRPC: %s' % (err_obj)
return None, get_failed_precondition_response(err_msg)
if settings.TA2_STATIC_TEST_MODE:
#return info_str_formatted,\
# get_grpc_test_json('test_responses/execute_results_1pipe_ok.json',
# dict())
#---
template_info = get_predict_file_info_dict()
template_str = get_grpc_test_json(
'test_responses/execute_results_1pipe_ok.json', template_info)
# These next lines embed file uri content into the JSON
embed_util = FileEmbedUtil(template_str)
if embed_util.has_error:
return get_failed_precondition_response(embed_util.error_message)
test_note = ('Test. An actual result would be the test JSON with'
' the "data" section removed and DATA_URI replaced'
' with a file path to where the "data" section was'
' written.')
return json.dumps(dict(note=test_note)), embed_util.get_final_results()
#---
#return info_str_formatted,\
# get_grpc_test_json('test_responses/execute_results_1pipe_ok.json',
# dict())
# --------------------------------
# Get the connection, return an error if there are channel issues
# --------------------------------
core_stub, err_msg = TA2Connection.get_grpc_stub()
if err_msg:
return None, get_failed_precondition_response(err_msg)
# --------------------------------
# Send the gRPC request - returns a stream
# --------------------------------
try:
reply = core_stub.ExecutePipeline(req)
except Exception as ex:
return None, get_failed_precondition_response(str(ex))
# --------------------------------
# Convert the reply to JSON and send it on
# --------------------------------
results = map(MessageToJson, reply)
result_str = '[' + ', '.join(results) + ']'
embed_util = FileEmbedUtil(result_str)
if embed_util.has_error:
return get_failed_precondition_response(embed_util.error_message)
return info_str_formatted, embed_util.get_final_results()