def aggregate_target_results(result_id):
# Check that we've completed the background tasks at least once. We need
# this data in order to make a configuration recommendation (until we
# implement a sampling technique to generate new training data).
latest_pipeline_run = PipelineRun.objects.get_latest()
newest_result = Result.objects.get(pk=result_id)
if latest_pipeline_run is None or newest_result.session.tuning_session == 'randomly_generate':
result = Result.objects.filter(pk=result_id)
knobs_ = KnobCatalog.objects.filter(dbms=result[0].dbms, tunable=True)
knobs_catalog = {k.name: k for k in knobs_}
knobs = {k: v for k, v in list(knobs_catalog.items())}
# generate a config randomly
random_knob_result = gen_random_data(knobs)
agg_data = DataUtil.aggregate_data(result)
agg_data['newest_result_id'] = result_id
agg_data['bad'] = True
agg_data['config_recommend'] = random_knob_result
return agg_data
# Aggregate all knob config results tried by the target so far in this
# tuning session and this tuning workload.
target_results = Result.objects.filter(session=newest_result.session,
dbms=newest_result.dbms,
workload=newest_result.workload)
if len(target_results) == 0:
raise Exception(
'Cannot find any results for session_id={}, dbms_id={}'.format(
newest_result.session, newest_result.dbms))
agg_data = DataUtil.aggregate_data(target_results)
agg_data['newest_result_id'] = result_id
agg_data['bad'] = False
return agg_data
def aggregate_target_results(result_id):
# Check that we've completed the background tasks at least once. We need
# this data in order to make a configuration recommendation (until we
# implement a sampling technique to generate new training data).
latest_pipeline_run = PipelineRun.objects.get_latest()
if latest_pipeline_run is None:
result = Result.objects.filter(pk=result_id)
knobs_ = KnobCatalog.objects.filter(dbms=result[0].dbms, tunable=True)
knobs_catalog = {k.name: k for k in knobs_}
knobs = {k: v for k, v in
list(knobs_catalog.items())}
# generate a config randomly
random_knob_result = gen_random_data(knobs)
agg_data = DataUtil.aggregate_data(result)
agg_data['newest_result_id'] = result_id
agg_data['bad'] = True
agg_data['config_recommend'] = random_knob_result
return agg_data
# Aggregate all knob config results tried by the target so far in this
# tuning session and this tuning workload.
newest_result = Result.objects.get(pk=result_id)
target_results = Result.objects.filter(session=newest_result.session,
dbms=newest_result.dbms,
workload=newest_result.workload)
if len(target_results) == 0:
raise Exception('Cannot find any results for session_id={}, dbms_id={}'
.format(newest_result.session, newest_result.dbms))
agg_data = DataUtil.aggregate_data(target_results)
agg_data['newest_result_id'] = result_id
agg_data['bad'] = False
return agg_data
def aggregate_target_results(result_id, algorithm):
# Check that we've completed the background tasks at least once. We need
# this data in order to make a configuration recommendation (until we
# implement a sampling technique to generate new training data).
newest_result = Result.objects.get(pk=result_id)
has_pipeline_data = PipelineData.objects.filter(
workload=newest_result.workload).exists()
if not has_pipeline_data or newest_result.session.tuning_session == 'randomly_generate':
if not has_pipeline_data and newest_result.session.tuning_session == 'tuning_session':
LOG.debug(
"Background tasks haven't ran for this workload yet, picking random data."
)
result = Result.objects.filter(pk=result_id)
knobs = SessionKnob.objects.get_knobs_for_session(
newest_result.session)
# generate a config randomly
random_knob_result = gen_random_data(knobs)
agg_data = DataUtil.aggregate_data(result)
agg_data['newest_result_id'] = result_id
agg_data['bad'] = True
agg_data['config_recommend'] = random_knob_result
LOG.debug('%s: Finished generating a random config.\n\ndata=%s\n',
AlgorithmType.name(algorithm),
JSONUtil.dumps(agg_data, pprint=True))
else:
# Aggregate all knob config results tried by the target so far in this
# tuning session and this tuning workload.
target_results = Result.objects.filter(session=newest_result.session,
dbms=newest_result.dbms,
workload=newest_result.workload)
if len(target_results) == 0:
raise Exception(
'Cannot find any results for session_id={}, dbms_id={}'.format(
newest_result.session, newest_result.dbms))
agg_data = DataUtil.aggregate_data(target_results)
agg_data['newest_result_id'] = result_id
agg_data['bad'] = False
# Clean knob data
cleaned_agg_data = clean_knob_data(agg_data['X_matrix'],
agg_data['X_columnlabels'],
newest_result.session)
agg_data['X_matrix'] = np.array(cleaned_agg_data[0])
agg_data['X_columnlabels'] = np.array(cleaned_agg_data[1])
LOG.debug('%s: Finished aggregating target results.\n\ndata=%s\n',
AlgorithmType.name(algorithm),
JSONUtil.dumps(agg_data, pprint=True))
return agg_data, algorithm
def configuration_recommendation_ddpg(result_info): # pylint: disable=invalid-name
LOG.info('Use ddpg to recommend configuration')
result_id = result_info['newest_result_id']
result = Result.objects.filter(pk=result_id)
session = Result.objects.get(pk=result_id).session
agg_data = DataUtil.aggregate_data(result)
metric_data = agg_data['y_matrix'].flatten()
metric_scalar = MinMaxScaler().fit(metric_data.reshape(1, -1))
normalized_metric_data = metric_scalar.transform(metric_data.reshape(
1, -1))[0]
cleaned_knob_data = clean_knob_data(agg_data['X_matrix'],
agg_data['X_columnlabels'], session)
knob_labels = np.array(cleaned_knob_data[1]).flatten()
knob_num = len(knob_labels)
metric_num = len(metric_data)
ddpg = DDPG(n_actions=knob_num, n_states=metric_num)
if session.ddpg_actor_model is not None and session.ddpg_critic_model is not None:
ddpg.set_model(session.ddpg_actor_model, session.ddpg_critic_model)
if session.ddpg_reply_memory is not None:
ddpg.replay_memory.set(session.ddpg_reply_memory)
knob_data = ddpg.choose_action(normalized_metric_data)
knob_bounds = np.vstack(DataUtil.get_knob_bounds(knob_labels, session))
knob_data = MinMaxScaler().fit(knob_bounds).inverse_transform(
knob_data.reshape(1, -1))[0]
conf_map = {k: knob_data[i] for i, k in enumerate(knob_labels)}
conf_map_res = {}
conf_map_res['status'] = 'good'
conf_map_res['result_id'] = result_id
conf_map_res['recommendation'] = conf_map
conf_map_res['info'] = 'INFO: ddpg'
return conf_map_res
def configuration_recommendation_ddpg(result_info): # pylint: disable=invalid-name
LOG.info('Use ddpg to recommend configuration')
result_id = result_info['newest_result_id']
result = Result.objects.filter(pk=result_id)
session = Result.objects.get(pk=result_id).session
agg_data = DataUtil.aggregate_data(result)
metric_data = agg_data['y_matrix'].flatten()
cleaned_agg_data = clean_knob_data(agg_data['X_matrix'], agg_data['X_columnlabels'],
session)
knob_labels = np.array(cleaned_agg_data[1]).flatten()
knob_num = len(knob_labels)
metric_num = len(metric_data)
ddpg = DDPG(n_actions=knob_num, n_states=metric_num, alr=ACTOR_LEARNING_RATE,
clr=CRITIC_LEARNING_RATE, gamma=GAMMA, batch_size=DDPG_BATCH_SIZE, tau=TAU)
if session.ddpg_actor_model is not None and session.ddpg_critic_model is not None:
ddpg.set_model(session.ddpg_actor_model, session.ddpg_critic_model)
if session.ddpg_reply_memory is not None:
ddpg.replay_memory.set(session.ddpg_reply_memory)
knob_data = ddpg.choose_action(metric_data)
LOG.info('recommended knob: %s', knob_data)
knob_bounds = np.vstack(DataUtil.get_knob_bounds(knob_labels, session))
knob_data = MinMaxScaler().fit(knob_bounds).inverse_transform(knob_data.reshape(1, -1))[0]
conf_map = {k: knob_data[i] for i, k in enumerate(knob_labels)}
conf_map_res = {}
conf_map_res['status'] = 'good'
conf_map_res['result_id'] = result_id
conf_map_res['recommendation'] = conf_map
conf_map_res['info'] = 'INFO: ddpg'
for k in knob_labels:
LOG.info('%s: %f', k, conf_map[k])
return conf_map_res
def aggregate_results():
unique_clusters = WorkloadCluster.objects.all()
unique_clusters = filter(lambda x: x.isdefault is False, unique_clusters)
all_data = {}
all_labels = {}
for cluster in unique_clusters:
results = ResultData.objects.filter(cluster=cluster)
if len(results) < 2:
continue
if cluster.dbms.pk not in all_labels:
knob_labels = np.asarray(
sorted(JSONUtil.loads(results[0].param_data).keys()))
metric_labels = np.asarray(
sorted(JSONUtil.loads(results[0].metric_data).keys()))
all_labels[cluster.dbms.pk] = (knob_labels, metric_labels)
else:
knob_labels, metric_labels = all_labels[cluster.dbms.pk]
entry = DataUtil.aggregate_data(results, knob_labels, metric_labels)
key = (cluster.dbms.pk, cluster.hardware.pk)
if key not in all_data:
all_data[key] = {}
all_data[key][cluster.pk] = entry
ts = now()
tsf = ts.strftime("%Y%m%d-%H%M%S")
for (dbkey, hwkey), cluster_data in all_data.iteritems():
task_name = PipelineTaskType.TYPE_NAMES[
PipelineTaskType.AGGREGATED_DATA].replace(' ', '').upper()
savepaths = {}
for clusterkey, entry in cluster_data.iteritems():
fname = '{}_{}_{}_{}_{}.npz'.format(task_name, dbkey, hwkey,
clusterkey, tsf)
savepath = os.path.join(PIPELINE_DIR, fname)
savepaths[clusterkey] = savepath
np.savez_compressed(savepath, **entry)
value = {'data': savepaths}
new_res = PipelineResult()
new_res.dbms = DBMSCatalog.objects.get(pk=dbkey)
new_res.hardware = Hardware.objects.get(pk=hwkey)
new_res.creation_timestamp = ts
new_res.task_type = PipelineTaskType.AGGREGATED_DATA
new_res.value = JSONUtil.dumps(value)
new_res.save()
def configuration_recommendation_ddpg(result_info): # pylint: disable=invalid-name
start_ts = time.time()
LOG.info('Use ddpg to recommend configuration')
result_id = result_info['newest_result_id']
result_list = Result.objects.filter(pk=result_id)
result = result_list.first()
session = result.session
params = JSONUtil.loads(session.hyperparameters)
agg_data = DataUtil.aggregate_data(result_list)
metric_data, _ = clean_metric_data(agg_data['y_matrix'],
agg_data['y_columnlabels'], session)
metric_data = metric_data.flatten()
metric_scalar = MinMaxScaler().fit(metric_data.reshape(1, -1))
normalized_metric_data = metric_scalar.transform(metric_data.reshape(
1, -1))[0]
cleaned_knob_data = clean_knob_data(agg_data['X_matrix'],
agg_data['X_columnlabels'], session)
knob_labels = np.array(cleaned_knob_data[1]).flatten()
knob_num = len(knob_labels)
metric_num = len(metric_data)
ddpg = DDPG(n_actions=knob_num,
n_states=metric_num,
a_hidden_sizes=params['DDPG_ACTOR_HIDDEN_SIZES'],
c_hidden_sizes=params['DDPG_CRITIC_HIDDEN_SIZES'],
use_default=params['DDPG_USE_DEFAULT'])
if session.ddpg_actor_model is not None and session.ddpg_critic_model is not None:
ddpg.set_model(session.ddpg_actor_model, session.ddpg_critic_model)
if session.ddpg_reply_memory is not None:
ddpg.replay_memory.set(session.ddpg_reply_memory)
knob_data = ddpg.choose_action(normalized_metric_data)
knob_bounds = np.vstack(DataUtil.get_knob_bounds(knob_labels, session))
knob_data = MinMaxScaler().fit(knob_bounds).inverse_transform(
knob_data.reshape(1, -1))[0]
conf_map = {k: knob_data[i] for i, k in enumerate(knob_labels)}
conf_map_res = create_and_save_recommendation(recommended_knobs=conf_map,
result=result,
status='good',
info='INFO: ddpg')
save_execution_time(start_ts, "configuration_recommendation_ddpg", result)
return conf_map_res
def aggregate_data(workload):
# Aggregates both the knob & metric data for the given workload.
#
# Parameters:
# workload: aggregate data belonging to this specific workload
#
# Returns: two dictionaries containing the knob & metric data as
# a tuple
# Find the results for this workload
wkld_results = Result.objects.filter(workload=workload)
# Now call the aggregate_data helper function to combine all knob &
# metric data into matrices and also create row/column labels
# (see the DataUtil class in website/utils.py)
#
# The aggregate_data helper function returns a dictionary of the form:
# - 'X_matrix': the knob data as a 2D numpy matrix (results x knobs)
# - 'y_matrix': the metric data as a 2D numpy matrix (results x metrics)
# - 'rowlabels': list of result ids that correspond to the rows in
# both X_matrix & y_matrix
# - 'X_columnlabels': a list of the knob names corresponding to the
# columns in the knob_data matrix
# - 'y_columnlabels': a list of the metric names corresponding to the
# columns in the metric_data matrix
aggregated_data = DataUtil.aggregate_data(wkld_results)
# Separate knob & workload data into two "standard" dictionaries of the
# same form
knob_data = {
'data': aggregated_data['X_matrix'],
'rowlabels': aggregated_data['rowlabels'],
'columnlabels': aggregated_data['X_columnlabels']
}
metric_data = {
'data': aggregated_data['y_matrix'],
'rowlabels': copy.deepcopy(aggregated_data['rowlabels']),
'columnlabels': aggregated_data['y_columnlabels']
}
# Return the knob & metric data
return knob_data, metric_data
def aggregate_data(workload):
# Aggregates both the knob & metric data for the given workload.
#
# Parameters:
# workload: aggregate data belonging to this specific workload
#
# Returns: two dictionaries containing the knob & metric data as
# a tuple
# Find the results for this workload
wkld_results = Result.objects.filter(workload=workload)
# Now call the aggregate_data helper function to combine all knob &
# metric data into matrices and also create row/column labels
# (see the DataUtil class in website/utils.py)
#
# The aggregate_data helper function returns a dictionary of the form:
# - 'X_matrix': the knob data as a 2D numpy matrix (results x knobs)
# - 'y_matrix': the metric data as a 2D numpy matrix (results x metrics)
# - 'rowlabels': list of result ids that correspond to the rows in
# both X_matrix & y_matrix
# - 'X_columnlabels': a list of the knob names corresponding to the
# columns in the knob_data matrix
# - 'y_columnlabels': a list of the metric names corresponding to the
# columns in the metric_data matrix
aggregated_data = DataUtil.aggregate_data(wkld_results)
# Separate knob & workload data into two "standard" dictionaries of the
# same form
knob_data = {
'data': aggregated_data['X_matrix'],
'rowlabels': aggregated_data['rowlabels'],
'columnlabels': aggregated_data['X_columnlabels']
}
metric_data = {
'data': aggregated_data['y_matrix'],
'rowlabels': copy.deepcopy(aggregated_data['rowlabels']),
'columnlabels': aggregated_data['y_columnlabels']
}
# Return the knob & metric data
return knob_data, metric_data
def aggregate_data(wkld_results):
# Aggregates both the knob & metric data for the given workload.
#
# Parameters:
# wkld_results: result data belonging to this specific workload
#
# Returns: two dictionaries containing the knob & metric data as
# a tuple
# Now call the aggregate_data helper function to combine all knob &
# metric data into matrices and also create row/column labels
# (see the DataUtil class in website/utils.py)
#
# The aggregate_data helper function returns a dictionary of the form:
# - 'X_matrix': the knob data as a 2D numpy matrix (results x knobs)
# - 'y_matrix': the metric data as a 2D numpy matrix (results x metrics)
# - 'rowlabels': list of result ids that correspond to the rows in
# both X_matrix & y_matrix
# - 'X_columnlabels': a list of the knob names corresponding to the
# columns in the knob_data matrix
# - 'y_columnlabels': a list of the metric names corresponding to the
# columns in the metric_data matrix
start_ts = time.time()
aggregated_data = DataUtil.aggregate_data(
wkld_results, ignore=['range_test', 'default', '*'])
# Separate knob & workload data into two "standard" dictionaries of the
# same form
knob_data = {
'data': aggregated_data['X_matrix'],
'rowlabels': aggregated_data['rowlabels'],
'columnlabels': aggregated_data['X_columnlabels']
}
metric_data = {
'data': aggregated_data['y_matrix'],
'rowlabels': copy.deepcopy(aggregated_data['rowlabels']),
'columnlabels': aggregated_data['y_columnlabels']
}
# Return the knob & metric data
save_execution_time(start_ts, "aggregate_data")
return knob_data, metric_data
def aggregate_target_results(result_id):
# Check that we've completed the background tasks at least once. We need
# this data in order to make a configuration recommendation (until we
# implement a sampling technique to generate new training data).
latest_pipeline_run = PipelineRun.objects.get_latest()
if latest_pipeline_run is None:
raise Exception("No previous data available. Implement me!")
# Aggregate all knob config results tried by the target so far in this
# tuning session.
newest_result = Result.objects.get(pk=result_id)
target_results = Result.objects.filter(
session=newest_result.session, dbms=newest_result.dbms)
if len(target_results) == 0:
raise Exception('Cannot find any results for session_id={}, dbms_id={}'
.format(newest_result.session, newest_result.dbms))
agg_data = DataUtil.aggregate_data(target_results)
agg_data['newest_result_id'] = result_id
return agg_data
def aggregate_target_results(result_id):
newest_result = Result.objects.get(pk=result_id)
target_results = Result.objects.filter(
application=newest_result.application, dbms=newest_result.dbms)
if len(target_results) == 0:
raise Exception(
'Cannot find any results for app_id={}, dbms_id={}'.format(
newest_result.application, newest_result.dbms))
target_result_datas = [
ResultData.objects.get(result=tres) for tres in target_results
]
knob_labels = np.asarray(
sorted(JSONUtil.loads(target_result_datas[0].param_data).keys()))
metric_labels = np.asarray(
sorted(JSONUtil.loads(target_result_datas[0].metric_data).keys()))
agg_data = DataUtil.aggregate_data(target_result_datas, knob_labels,
metric_labels)
agg_data['newest_result_id'] = result_id
return agg_data
def test_aggregate(self):
workload2 = Result.objects.filter(workload=2)
num_results = Result.objects.filter(workload=2).count()
knobs = list(JSONUtil.loads(workload2[0].knob_data.data).keys())
metrics = list(JSONUtil.loads(workload2[0].metric_data.data).keys())
num_knobs = len(knobs)
num_metrics = len(metrics)
test_result = DataUtil.aggregate_data(workload2)
self.assertTrue('X_matrix' in list(test_result.keys()))
self.assertTrue('y_matrix' in list(test_result.keys()))
self.assertTrue('rowlabels' in list(test_result.keys()))
self.assertTrue('X_columnlabels' in list(test_result.keys()))
self.assertTrue('y_columnlabels' in list(test_result.keys()))
self.assertEqual(test_result['X_columnlabels'], knobs)
self.assertEqual(test_result['y_columnlabels'], metrics)
self.assertEqual(test_result['X_matrix'].shape[0], num_results)
self.assertEqual(test_result['y_matrix'].shape[0], num_results)
self.assertEqual(test_result['X_matrix'].shape[1], num_knobs)
self.assertEqual(test_result['y_matrix'].shape[1], num_metrics)
def test_aggregate(self):
workload2 = Result.objects.filter(workload=2)
num_results = Result.objects.filter(workload=2).count()
knobs = list(JSONUtil.loads(workload2[0].knob_data.data).keys())
metrics = list(JSONUtil.loads(workload2[0].metric_data.data).keys())
num_knobs = len(knobs)
num_metrics = len(metrics)
test_result = DataUtil.aggregate_data(workload2)
self.assertTrue('X_matrix' in list(test_result.keys()))
self.assertTrue('y_matrix' in list(test_result.keys()))
self.assertTrue('rowlabels' in list(test_result.keys()))
self.assertTrue('X_columnlabels' in list(test_result.keys()))
self.assertTrue('y_columnlabels' in list(test_result.keys()))
self.assertEqual(test_result['X_columnlabels'], knobs)
self.assertEqual(test_result['y_columnlabels'], metrics)
self.assertEqual(test_result['X_matrix'].shape[0], num_results)
self.assertEqual(test_result['y_matrix'].shape[0], num_results)
self.assertEqual(test_result['X_matrix'].shape[1], num_knobs)
self.assertEqual(test_result['y_matrix'].shape[1], num_metrics)
def train_ddpg(result_id):
LOG.info('Add training data to ddpg and train ddpg')
result = Result.objects.get(pk=result_id)
session = Result.objects.get(pk=result_id).session
session_results = Result.objects.filter(
session=session, creation_time__lt=result.creation_time)
result_info = {}
result_info['newest_result_id'] = result_id
if len(session_results) == 0:
LOG.info('No previous result. Abort.')
return result_info
# Extract data from result
result = Result.objects.filter(pk=result_id)
base_result_id = session_results[0].pk
base_result = Result.objects.filter(pk=base_result_id)
agg_data = DataUtil.aggregate_data(result)
metric_data = agg_data['y_matrix'].flatten()
base_metric_data = (
DataUtil.aggregate_data(base_result))['y_matrix'].flatten()
metric_scalar = MinMaxScaler().fit(metric_data.reshape(1, -1))
normalized_metric_data = metric_scalar.transform(metric_data.reshape(
1, -1))[0]
# Clean knob data
cleaned_knob_data = clean_knob_data(agg_data['X_matrix'],
agg_data['X_columnlabels'], session)
knob_data = np.array(cleaned_knob_data[0])
knob_labels = np.array(cleaned_knob_data[1])
knob_bounds = np.vstack(
DataUtil.get_knob_bounds(knob_labels.flatten(), session))
knob_data = MinMaxScaler().fit(knob_bounds).transform(knob_data)[0]
knob_num = len(knob_data)
metric_num = len(metric_data)
LOG.info('knob_num: %d, metric_num: %d', knob_num, metric_num)
# Filter ys by current target objective metric
result = Result.objects.get(pk=result_id)
target_objective = result.session.target_objective
target_obj_idx = [
i for i, n in enumerate(agg_data['y_columnlabels'])
if n == target_objective
]
if len(target_obj_idx) == 0:
raise Exception(('Could not find target objective in metrics '
'(target_obj={})').format(target_objective))
elif len(target_obj_idx) > 1:
raise Exception(
('Found {} instances of target objective in '
'metrics (target_obj={})').format(len(target_obj_idx),
target_objective))
objective = metric_data[target_obj_idx]
base_objective = base_metric_data[target_obj_idx]
metric_meta = db.target_objectives.get_metric_metadata(
result.session.dbms.pk, result.session.target_objective)
# Calculate the reward
objective = objective / base_objective
if metric_meta[target_objective].improvement == '(less is better)':
reward = -objective
else:
reward = objective
LOG.info('reward: %f', reward)
# Update ddpg
ddpg = DDPG(n_actions=knob_num,
n_states=metric_num,
alr=ACTOR_LEARNING_RATE,
clr=CRITIC_LEARNING_RATE,
gamma=0,
batch_size=DDPG_BATCH_SIZE)
if session.ddpg_actor_model and session.ddpg_critic_model:
ddpg.set_model(session.ddpg_actor_model, session.ddpg_critic_model)
if session.ddpg_reply_memory:
ddpg.replay_memory.set(session.ddpg_reply_memory)
ddpg.add_sample(normalized_metric_data, knob_data, reward,
normalized_metric_data)
for _ in range(25):
ddpg.update()
session.ddpg_actor_model, session.ddpg_critic_model = ddpg.get_model()
session.ddpg_reply_memory = ddpg.replay_memory.get()
session.save()
return result_info
def train_ddpg(result_id):
LOG.info('Add training data to ddpg and train ddpg')
result = Result.objects.get(pk=result_id)
session = Result.objects.get(pk=result_id).session
params = JSONUtil.loads(session.hyperparameters)
session_results = Result.objects.filter(
session=session, creation_time__lt=result.creation_time)
result_info = {}
result_info['newest_result_id'] = result_id
# Extract data from result and previous results
result = Result.objects.filter(pk=result_id)
if len(session_results) == 0:
base_result_id = result_id
prev_result_id = result_id
else:
base_result_id = session_results[0].pk
prev_result_id = session_results[len(session_results) - 1].pk
base_result = Result.objects.filter(pk=base_result_id)
prev_result = Result.objects.filter(pk=prev_result_id)
agg_data = DataUtil.aggregate_data(result)
base_metric_data = (
DataUtil.aggregate_data(base_result))['y_matrix'].flatten()
prev_metric_data = (
DataUtil.aggregate_data(prev_result))['y_matrix'].flatten()
result = Result.objects.get(pk=result_id)
target_objective = result.session.target_objective
prev_obj_idx = [
i for i, n in enumerate(agg_data['y_columnlabels'])
if n == target_objective
]
# Clean metric data
metric_data, metric_labels = clean_metric_data(agg_data['y_matrix'],
agg_data['y_columnlabels'],
session)
metric_data = metric_data.flatten()
metric_scalar = MinMaxScaler().fit(metric_data.reshape(1, -1))
normalized_metric_data = metric_scalar.transform(metric_data.reshape(
1, -1))[0]
# Clean knob data
cleaned_knob_data = clean_knob_data(agg_data['X_matrix'],
agg_data['X_columnlabels'], session)
knob_data = np.array(cleaned_knob_data[0])
knob_labels = np.array(cleaned_knob_data[1])
knob_bounds = np.vstack(
DataUtil.get_knob_bounds(knob_labels.flatten(), session))
knob_data = MinMaxScaler().fit(knob_bounds).transform(knob_data)[0]
knob_num = len(knob_data)
metric_num = len(metric_data)
LOG.info('knob_num: %d, metric_num: %d', knob_num, metric_num)
# Filter ys by current target objective metric
target_obj_idx = [
i for i, n in enumerate(metric_labels) if n == target_objective
]
if len(target_obj_idx) == 0:
raise Exception(('Could not find target objective in metrics '
'(target_obj={})').format(target_objective))
elif len(target_obj_idx) > 1:
raise Exception(
('Found {} instances of target objective in '
'metrics (target_obj={})').format(len(target_obj_idx),
target_objective))
objective = metric_data[target_obj_idx]
base_objective = base_metric_data[prev_obj_idx]
prev_objective = prev_metric_data[prev_obj_idx]
metric_meta = db.target_objectives.get_metric_metadata(
result.session.dbms.pk, result.session.target_objective)
# Calculate the reward
if params['DDPG_SIMPLE_REWARD']:
objective = objective / base_objective
if metric_meta[target_objective].improvement == '(less is better)':
reward = -objective
else:
reward = objective
else:
if metric_meta[target_objective].improvement == '(less is better)':
if objective - base_objective <= 0: # positive reward
reward = (np.square((2 * base_objective - objective) / base_objective) - 1)\
* abs(2 * prev_objective - objective) / prev_objective
else: # negative reward
reward = -(np.square(objective / base_objective) -
1) * objective / prev_objective
else:
if objective - base_objective > 0: # positive reward
reward = (np.square(objective / base_objective) -
1) * objective / prev_objective
else: # negative reward
reward = -(np.square((2 * base_objective - objective) / base_objective) - 1)\
* abs(2 * prev_objective - objective) / prev_objective
LOG.info('reward: %f', reward)
# Update ddpg
ddpg = DDPG(n_actions=knob_num,
n_states=metric_num,
alr=params['DDPG_ACTOR_LEARNING_RATE'],
clr=params['DDPG_CRITIC_LEARNING_RATE'],
gamma=params['DDPG_GAMMA'],
batch_size=params['DDPG_BATCH_SIZE'],
a_hidden_sizes=params['DDPG_ACTOR_HIDDEN_SIZES'],
c_hidden_sizes=params['DDPG_CRITIC_HIDDEN_SIZES'],
use_default=params['DDPG_USE_DEFAULT'])
if session.ddpg_actor_model and session.ddpg_critic_model:
ddpg.set_model(session.ddpg_actor_model, session.ddpg_critic_model)
if session.ddpg_reply_memory:
ddpg.replay_memory.set(session.ddpg_reply_memory)
ddpg.add_sample(normalized_metric_data, knob_data, reward,
normalized_metric_data)
for _ in range(params['DDPG_UPDATE_EPOCHS']):
ddpg.update()
session.ddpg_actor_model, session.ddpg_critic_model = ddpg.get_model()
session.ddpg_reply_memory = ddpg.replay_memory.get()
session.save()
return result_info
