def setUpClass(cls):
super(TestGPRGP, cls).setUpClass()
boston = datasets.load_boston()
data = boston['data']
X_train = data[0:500]
X_test = data[500:501]
y_train = boston['target'][0:500].reshape(500, 1)
X_min = np.min(X_train, 0)
X_max = np.max(X_train, 0)
random.seed(0)
np.random.seed(0)
tf.set_random_seed(0)
model_kwargs = {}
opt_kwargs = {}
opt_kwargs['learning_rate'] = 0.01
opt_kwargs['maxiter'] = 10
opt_kwargs['bounds'] = [X_min, X_max]
opt_kwargs['ucb_beta'] = 1.0
tf.reset_default_graph()
graph = tf.get_default_graph()
gpflow.reset_default_session(graph=graph)
cls.m = gpr_models.create_model('BasicGP',
X=X_train,
y=y_train,
**model_kwargs)
cls.gpr_result = tf_optimize(cls.m.model, X_test, **opt_kwargs)
def setUpClass(cls):
super(TestGPRGPFlow, cls).setUpClass()
boston = datasets.load_boston()
data = boston['data']
X_train = data[0:500]
X_test = data[500:]
y_train = boston['target'][0:500].reshape(500, 1)
model_kwargs = {'lengthscales': 1, 'variance': 1, 'noise_variance': 1}
tf.reset_default_graph()
graph = tf.get_default_graph()
gpflow.reset_default_session(graph=graph)
cls.m = gpr_models.create_model('BasicGP', X=X_train, y=y_train,
**model_kwargs)
cls.gpr_result = gpflow_predict(cls.m.model, X_test)
def run_optimize(X, y, X_sample, model_name, opt_kwargs, model_kwargs):
timer = TimerStruct()
# Create model (this also optimizes the hyperparameters if that option is enabled
timer.start()
m = gpr_models.create_model(model_name, X=X, y=y, **model_kwargs)
timer.stop()
model_creation_sec = timer.elapsed_seconds
LOG.info(m._model.as_pandas_table())
# Optimize the DBMS's configuration knobs
timer.start()
X_new, ypred, yvar, loss = tf_optimize(m._model, X_sample, **opt_kwargs)
timer.stop()
config_optimize_sec = timer.elapsed_seconds
return X_new, ypred, m.get_model_parameters(), m.get_hyperparameters()
def run_optimize(X, y, X_samples, model_name, opt_kwargs, model_kwargs):
timer = TimerStruct()
# Create model (this also optimizes the hyperparameters if that option is enabled
timer.start()
tf.reset_default_graph()
graph = tf.get_default_graph()
gpflow.reset_default_session(graph=graph)
m = gpr_models.create_model(model_name, X=X, y=y, **model_kwargs)
timer.stop()
model_creation_sec = timer.elapsed_seconds
LOG.info(m.model.as_pandas_table())
# Optimize the DBMS's configuration knobs
timer.start()
res = tf_optimize(m.model, X_samples, **opt_kwargs)
timer.stop()
config_optimize_sec = timer.elapsed_seconds
return res.minl_conf, res.minl, m.get_model_parameters(), m.get_hyperparameters()
def configuration_recommendation(recommendation_input):
target_data, algorithm = recommendation_input
LOG.info('configuration_recommendation called')
if target_data['bad'] is True:
target_data_res = dict(
status='bad',
result_id=target_data['newest_result_id'],
info='WARNING: no training data, the config is generated randomly',
recommendation=target_data['config_recommend'],
pipeline_run=target_data['pipeline_run'])
LOG.debug('%s: Skipping configuration recommendation.\n\ndata=%s\n',
AlgorithmType.name(algorithm),
JSONUtil.dumps(target_data, pprint=True))
return target_data_res
# Load mapped workload data
mapped_workload_id = target_data['mapped_workload'][0]
latest_pipeline_run = PipelineRun.objects.get(
pk=target_data['pipeline_run'])
mapped_workload = Workload.objects.get(pk=mapped_workload_id)
workload_knob_data = PipelineData.objects.get(
pipeline_run=latest_pipeline_run,
workload=mapped_workload,
task_type=PipelineTaskType.KNOB_DATA)
workload_knob_data = JSONUtil.loads(workload_knob_data.data)
workload_metric_data = PipelineData.objects.get(
pipeline_run=latest_pipeline_run,
workload=mapped_workload,
task_type=PipelineTaskType.METRIC_DATA)
workload_metric_data = JSONUtil.loads(workload_metric_data.data)
newest_result = Result.objects.get(pk=target_data['newest_result_id'])
cleaned_workload_knob_data = clean_knob_data(
workload_knob_data["data"], workload_knob_data["columnlabels"],
newest_result.session)
X_workload = np.array(cleaned_workload_knob_data[0])
X_columnlabels = np.array(cleaned_workload_knob_data[1])
y_workload = np.array(workload_metric_data['data'])
y_columnlabels = np.array(workload_metric_data['columnlabels'])
rowlabels_workload = np.array(workload_metric_data['rowlabels'])
# Target workload data
newest_result = Result.objects.get(pk=target_data['newest_result_id'])
X_target = target_data['X_matrix']
y_target = target_data['y_matrix']
rowlabels_target = np.array(target_data['rowlabels'])
if not np.array_equal(X_columnlabels, target_data['X_columnlabels']):
raise Exception(('The workload and target data should have '
'identical X columnlabels (sorted knob names)'))
if not np.array_equal(y_columnlabels, target_data['y_columnlabels']):
raise Exception(('The workload and target data should have '
'identical y columnlabels (sorted metric names)'))
# Filter Xs by top 10 ranked knobs
ranked_knobs = PipelineData.objects.get(
pipeline_run=latest_pipeline_run,
workload=mapped_workload,
task_type=PipelineTaskType.RANKED_KNOBS)
ranked_knobs = JSONUtil.loads(ranked_knobs.data)[:IMPORTANT_KNOB_NUMBER]
ranked_knob_idxs = [
i for i, cl in enumerate(X_columnlabels) if cl in ranked_knobs
]
X_workload = X_workload[:, ranked_knob_idxs]
X_target = X_target[:, ranked_knob_idxs]
X_columnlabels = X_columnlabels[ranked_knob_idxs]
# Filter ys by current target objective metric
target_objective = newest_result.session.target_objective
target_obj_idx = [
i for i, cl in enumerate(y_columnlabels) if cl == 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))
metric_meta = db.target_objectives.get_metric_metadata(
newest_result.session.dbms.pk, newest_result.session.target_objective)
lessisbetter = metric_meta[
target_objective].improvement == db.target_objectives.LESS_IS_BETTER
y_workload = y_workload[:, target_obj_idx]
y_target = y_target[:, target_obj_idx]
y_columnlabels = y_columnlabels[target_obj_idx]
# Combine duplicate rows in the target/workload data (separately)
X_workload, y_workload, rowlabels_workload = DataUtil.combine_duplicate_rows(
X_workload, y_workload, rowlabels_workload)
X_target, y_target, rowlabels_target = DataUtil.combine_duplicate_rows(
X_target, y_target, rowlabels_target)
# Delete any rows that appear in both the workload data and the target
# data from the workload data
dups_filter = np.ones(X_workload.shape[0], dtype=bool)
target_row_tups = [tuple(row) for row in X_target]
for i, row in enumerate(X_workload):
if tuple(row) in target_row_tups:
dups_filter[i] = False
X_workload = X_workload[dups_filter, :]
y_workload = y_workload[dups_filter, :]
rowlabels_workload = rowlabels_workload[dups_filter]
# Combine target & workload Xs for preprocessing
X_matrix = np.vstack([X_target, X_workload])
# Dummy encode categorial variables
categorical_info = DataUtil.dummy_encoder_helper(X_columnlabels,
mapped_workload.dbms)
dummy_encoder = DummyEncoder(categorical_info['n_values'],
categorical_info['categorical_features'],
categorical_info['cat_columnlabels'],
categorical_info['noncat_columnlabels'])
X_matrix = dummy_encoder.fit_transform(X_matrix)
# below two variables are needed for correctly determing max/min on dummies
binary_index_set = set(categorical_info['binary_vars'])
total_dummies = dummy_encoder.total_dummies()
# Scale to N(0, 1)
X_scaler = StandardScaler()
X_scaled = X_scaler.fit_transform(X_matrix)
if y_target.shape[0] < 5: # FIXME
# FIXME (dva): if there are fewer than 5 target results so far
# then scale the y values (metrics) using the workload's
# y_scaler. I'm not sure if 5 is the right cutoff.
y_target_scaler = None
y_workload_scaler = StandardScaler()
y_matrix = np.vstack([y_target, y_workload])
y_scaled = y_workload_scaler.fit_transform(y_matrix)
else:
# FIXME (dva): otherwise try to compute a separate y_scaler for
# the target and scale them separately.
try:
y_target_scaler = StandardScaler()
y_workload_scaler = StandardScaler()
y_target_scaled = y_target_scaler.fit_transform(y_target)
y_workload_scaled = y_workload_scaler.fit_transform(y_workload)
y_scaled = np.vstack([y_target_scaled, y_workload_scaled])
except ValueError:
y_target_scaler = None
y_workload_scaler = StandardScaler()
y_scaled = y_workload_scaler.fit_transform(y_target)
# Set up constraint helper
constraint_helper = ParamConstraintHelper(
scaler=X_scaler,
encoder=dummy_encoder,
binary_vars=categorical_info['binary_vars'],
init_flip_prob=INIT_FLIP_PROB,
flip_prob_decay=FLIP_PROB_DECAY)
# FIXME (dva): check if these are good values for the ridge
# ridge = np.empty(X_scaled.shape[0])
# ridge[:X_target.shape[0]] = 0.01
# ridge[X_target.shape[0]:] = 0.1
# FIXME: we should generate more samples and use a smarter sampling
# technique
num_samples = NUM_SAMPLES
X_samples = np.empty((num_samples, X_scaled.shape[1]))
X_min = np.empty(X_scaled.shape[1])
X_max = np.empty(X_scaled.shape[1])
X_scaler_matrix = np.zeros([1, X_scaled.shape[1]])
session_knobs = SessionKnob.objects.get_knobs_for_session(
newest_result.session)
# Set min/max for knob values
for i in range(X_scaled.shape[1]):
if i < total_dummies or i in binary_index_set:
col_min = 0
col_max = 1
else:
col_min = X_scaled[:, i].min()
col_max = X_scaled[:, i].max()
for knob in session_knobs:
if X_columnlabels[i] == knob["name"]:
X_scaler_matrix[0][i] = knob["minval"]
col_min = X_scaler.transform(X_scaler_matrix)[0][i]
X_scaler_matrix[0][i] = knob["maxval"]
col_max = X_scaler.transform(X_scaler_matrix)[0][i]
X_min[i] = col_min
X_max[i] = col_max
X_samples[:, i] = np.random.rand(num_samples) * (col_max -
col_min) + col_min
# Maximize the throughput, moreisbetter
# Use gradient descent to minimize -throughput
if not lessisbetter:
y_scaled = -y_scaled
q = queue.PriorityQueue()
for x in range(0, y_scaled.shape[0]):
q.put((y_scaled[x][0], x))
i = 0
while i < TOP_NUM_CONFIG:
try:
item = q.get_nowait()
# Tensorflow get broken if we use the training data points as
# starting points for GPRGD. We add a small bias for the
# starting points. GPR_EPS default value is 0.001
# if the starting point is X_max, we minus a small bias to
# make sure it is within the range.
dist = sum(np.square(X_max - X_scaled[item[1]]))
if dist < 0.001:
X_samples = np.vstack(
(X_samples, X_scaled[item[1]] - abs(GPR_EPS)))
else:
X_samples = np.vstack(
(X_samples, X_scaled[item[1]] + abs(GPR_EPS)))
i = i + 1
except queue.Empty:
break
session = newest_result.session
res = None
if algorithm == AlgorithmType.DNN:
# neural network model
model_nn = NeuralNet(n_input=X_samples.shape[1],
batch_size=X_samples.shape[0],
explore_iters=DNN_EXPLORE_ITER,
noise_scale_begin=DNN_NOISE_SCALE_BEGIN,
noise_scale_end=DNN_NOISE_SCALE_END,
debug=DNN_DEBUG,
debug_interval=DNN_DEBUG_INTERVAL)
if session.dnn_model is not None:
model_nn.set_weights_bin(session.dnn_model)
model_nn.fit(X_scaled, y_scaled, fit_epochs=DNN_TRAIN_ITER)
res = model_nn.recommend(X_samples,
X_min,
X_max,
explore=DNN_EXPLORE,
recommend_epochs=MAX_ITER)
session.dnn_model = model_nn.get_weights_bin()
session.save()
elif algorithm == AlgorithmType.GPR:
# default gpr model
if USE_GPFLOW:
model_kwargs = {}
model_kwargs['model_learning_rate'] = HP_LEARNING_RATE
model_kwargs['model_maxiter'] = HP_MAX_ITER
opt_kwargs = {}
opt_kwargs['learning_rate'] = DEFAULT_LEARNING_RATE
opt_kwargs['maxiter'] = MAX_ITER
opt_kwargs['bounds'] = [X_min, X_max]
ucb_beta = 'get_beta_td'
opt_kwargs['ucb_beta'] = ucb.get_ucb_beta(ucb_beta,
scale=DEFAULT_UCB_SCALE,
t=i + 1.,
ndim=X_scaled.shape[1])
tf.reset_default_graph()
graph = tf.get_default_graph()
gpflow.reset_default_session(graph=graph)
m = gpr_models.create_model('BasicGP',
X=X_scaled,
y=y_scaled,
**model_kwargs)
res = tf_optimize(m.model, X_samples, **opt_kwargs)
else:
model = GPRGD(length_scale=DEFAULT_LENGTH_SCALE,
magnitude=DEFAULT_MAGNITUDE,
max_train_size=MAX_TRAIN_SIZE,
batch_size=BATCH_SIZE,
num_threads=NUM_THREADS,
learning_rate=DEFAULT_LEARNING_RATE,
epsilon=DEFAULT_EPSILON,
max_iter=MAX_ITER,
sigma_multiplier=DEFAULT_SIGMA_MULTIPLIER,
mu_multiplier=DEFAULT_MU_MULTIPLIER)
model.fit(X_scaled, y_scaled, X_min, X_max, ridge=DEFAULT_RIDGE)
res = model.predict(X_samples, constraint_helper=constraint_helper)
best_config_idx = np.argmin(res.minl.ravel())
best_config = res.minl_conf[best_config_idx, :]
best_config = X_scaler.inverse_transform(best_config)
# Decode one-hot encoding into categorical knobs
best_config = dummy_encoder.inverse_transform(best_config)
# Although we have max/min limits in the GPRGD training session, it may
# lose some precisions. e.g. 0.99..99 >= 1.0 may be True on the scaled data,
# when we inversely transform the scaled data, the different becomes much larger
# and cannot be ignored. Here we check the range on the original data
# directly, and make sure the recommended config lies within the range
X_min_inv = X_scaler.inverse_transform(X_min)
X_max_inv = X_scaler.inverse_transform(X_max)
best_config = np.minimum(best_config, X_max_inv)
best_config = np.maximum(best_config, X_min_inv)
conf_map = {k: best_config[i] for i, k in enumerate(X_columnlabels)}
conf_map_res = dict(status='good',
result_id=target_data['newest_result_id'],
recommendation=conf_map,
info='INFO: training data size is {}'.format(
X_scaled.shape[0]),
pipeline_run=latest_pipeline_run.pk)
LOG.debug('%s: Finished selecting the next config.\n\ndata=%s\n',
AlgorithmType.name(algorithm),
JSONUtil.dumps(conf_map_res, pprint=True))
return conf_map_res
def configuration_recommendation(recommendation_input):
target_data, algorithm = recommendation_input
LOG.info('configuration_recommendation called')
newest_result = Result.objects.get(pk=target_data['newest_result_id'])
session = newest_result.session
params = JSONUtil.loads(session.hyperparameters)
if target_data['bad'] is True:
target_data_res = create_and_save_recommendation(
recommended_knobs=target_data['config_recommend'],
result=newest_result,
status='bad',
info='WARNING: no training data, the config is generated randomly',
pipeline_run=target_data['pipeline_run'])
LOG.debug('%s: Skipping configuration recommendation.\n\ndata=%s\n',
AlgorithmType.name(algorithm),
JSONUtil.dumps(target_data, pprint=True))
return target_data_res
X_columnlabels, X_scaler, X_scaled, y_scaled, X_max, X_min,\
dummy_encoder, constraint_helper = combine_workload(target_data)
# FIXME: we should generate more samples and use a smarter sampling
# technique
num_samples = params['NUM_SAMPLES']
X_samples = np.empty((num_samples, X_scaled.shape[1]))
for i in range(X_scaled.shape[1]):
X_samples[:, i] = np.random.rand(num_samples) * (X_max[i] -
X_min[i]) + X_min[i]
q = queue.PriorityQueue()
for x in range(0, y_scaled.shape[0]):
q.put((y_scaled[x][0], x))
i = 0
while i < params['TOP_NUM_CONFIG']:
try:
item = q.get_nowait()
# Tensorflow get broken if we use the training data points as
# starting points for GPRGD. We add a small bias for the
# starting points. GPR_EPS default value is 0.001
# if the starting point is X_max, we minus a small bias to
# make sure it is within the range.
dist = sum(np.square(X_max - X_scaled[item[1]]))
if dist < 0.001:
X_samples = np.vstack(
(X_samples, X_scaled[item[1]] - abs(params['GPR_EPS'])))
else:
X_samples = np.vstack(
(X_samples, X_scaled[item[1]] + abs(params['GPR_EPS'])))
i = i + 1
except queue.Empty:
break
res = None
if algorithm == AlgorithmType.DNN:
# neural network model
model_nn = NeuralNet(n_input=X_samples.shape[1],
batch_size=X_samples.shape[0],
explore_iters=params['DNN_EXPLORE_ITER'],
noise_scale_begin=params['DNN_NOISE_SCALE_BEGIN'],
noise_scale_end=params['DNN_NOISE_SCALE_END'],
debug=params['DNN_DEBUG'],
debug_interval=params['DNN_DEBUG_INTERVAL'])
if session.dnn_model is not None:
model_nn.set_weights_bin(session.dnn_model)
model_nn.fit(X_scaled, y_scaled, fit_epochs=params['DNN_TRAIN_ITER'])
res = model_nn.recommend(X_samples,
X_min,
X_max,
explore=params['DNN_EXPLORE'],
recommend_epochs=params['DNN_GD_ITER'])
session.dnn_model = model_nn.get_weights_bin()
session.save()
elif algorithm == AlgorithmType.GPR:
# default gpr model
if params['GPR_USE_GPFLOW']:
model_kwargs = {}
model_kwargs['model_learning_rate'] = params[
'GPR_HP_LEARNING_RATE']
model_kwargs['model_maxiter'] = params['GPR_HP_MAX_ITER']
opt_kwargs = {}
opt_kwargs['learning_rate'] = params['GPR_LEARNING_RATE']
opt_kwargs['maxiter'] = params['GPR_MAX_ITER']
opt_kwargs['bounds'] = [X_min, X_max]
opt_kwargs['debug'] = params['GPR_DEBUG']
opt_kwargs['ucb_beta'] = ucb.get_ucb_beta(
params['GPR_UCB_BETA'],
scale=params['GPR_UCB_SCALE'],
t=i + 1.,
ndim=X_scaled.shape[1])
tf.reset_default_graph()
graph = tf.get_default_graph()
gpflow.reset_default_session(graph=graph)
m = gpr_models.create_model(params['GPR_MODEL_NAME'],
X=X_scaled,
y=y_scaled,
**model_kwargs)
res = tf_optimize(m.model, X_samples, **opt_kwargs)
else:
model = GPRGD(length_scale=params['GPR_LENGTH_SCALE'],
magnitude=params['GPR_MAGNITUDE'],
max_train_size=params['GPR_MAX_TRAIN_SIZE'],
batch_size=params['GPR_BATCH_SIZE'],
num_threads=params['TF_NUM_THREADS'],
learning_rate=params['GPR_LEARNING_RATE'],
epsilon=params['GPR_EPSILON'],
max_iter=params['GPR_MAX_ITER'],
sigma_multiplier=params['GPR_SIGMA_MULTIPLIER'],
mu_multiplier=params['GPR_MU_MULTIPLIER'],
ridge=params['GPR_RIDGE'])
model.fit(X_scaled, y_scaled, X_min, X_max)
res = model.predict(X_samples, constraint_helper=constraint_helper)
best_config_idx = np.argmin(res.minl.ravel())
best_config = res.minl_conf[best_config_idx, :]
best_config = X_scaler.inverse_transform(best_config)
if ENABLE_DUMMY_ENCODER:
# Decode one-hot encoding into categorical knobs
best_config = dummy_encoder.inverse_transform(best_config)
# Although we have max/min limits in the GPRGD training session, it may
# lose some precisions. e.g. 0.99..99 >= 1.0 may be True on the scaled data,
# when we inversely transform the scaled data, the different becomes much larger
# and cannot be ignored. Here we check the range on the original data
# directly, and make sure the recommended config lies within the range
X_min_inv = X_scaler.inverse_transform(X_min)
X_max_inv = X_scaler.inverse_transform(X_max)
best_config = np.minimum(best_config, X_max_inv)
best_config = np.maximum(best_config, X_min_inv)
conf_map = {k: best_config[i] for i, k in enumerate(X_columnlabels)}
conf_map_res = create_and_save_recommendation(
recommended_knobs=conf_map,
result=newest_result,
status='good',
info='INFO: training data size is {}'.format(X_scaled.shape[0]),
pipeline_run=target_data['pipeline_run'])
LOG.debug('%s: Finished selecting the next config.\n\ndata=%s\n',
AlgorithmType.name(algorithm),
JSONUtil.dumps(conf_map_res, pprint=True))
return conf_map_res
def map_workload(map_workload_input):
start_ts = time.time()
target_data, algorithm = map_workload_input
if target_data['bad']:
assert target_data is not None
target_data['pipeline_run'] = None
LOG.debug('%s: Skipping workload mapping.\n\ndata=%s\n',
AlgorithmType.name(algorithm),
JSONUtil.dumps(target_data, pprint=True))
return target_data, algorithm
# Get the latest version of pipeline data that's been computed so far.
latest_pipeline_run = PipelineRun.objects.get_latest()
assert latest_pipeline_run is not None
target_data['pipeline_run'] = latest_pipeline_run.pk
newest_result = Result.objects.get(pk=target_data['newest_result_id'])
session = newest_result.session
params = JSONUtil.loads(session.hyperparameters)
target_workload = newest_result.workload
X_columnlabels = np.array(target_data['X_columnlabels'])
y_columnlabels = np.array(target_data['y_columnlabels'])
# Find all pipeline data belonging to the latest version with the same
# DBMS and hardware as the target
pipeline_data = PipelineData.objects.filter(
pipeline_run=latest_pipeline_run,
workload__dbms=target_workload.dbms,
workload__hardware=target_workload.hardware,
workload__project=target_workload.project)
# FIXME (dva): we should also compute the global (i.e., overall) ranked_knobs
# and pruned metrics but we just use those from the first workload for now
initialized = False
global_ranked_knobs = None
global_pruned_metrics = None
ranked_knob_idxs = None
pruned_metric_idxs = None
unique_workloads = pipeline_data.values_list('workload',
flat=True).distinct()
workload_data = {}
# Compute workload mapping data for each unique workload
for unique_workload in unique_workloads:
workload_obj = Workload.objects.get(pk=unique_workload)
wkld_results = Result.objects.filter(workload=workload_obj)
if wkld_results.exists() is False:
# delete the workload
workload_obj.delete()
continue
# Load knob & metric data for this workload
knob_data = load_data_helper(pipeline_data, unique_workload,
PipelineTaskType.KNOB_DATA)
knob_data["data"], knob_data["columnlabels"] = clean_knob_data(
knob_data["data"], knob_data["columnlabels"],
newest_result.session)
metric_data = load_data_helper(pipeline_data, unique_workload,
PipelineTaskType.METRIC_DATA)
X_matrix = np.array(knob_data["data"])
y_matrix = np.array(metric_data["data"])
rowlabels = np.array(knob_data["rowlabels"])
assert np.array_equal(rowlabels, metric_data["rowlabels"])
if not initialized:
# For now set ranked knobs & pruned metrics to be those computed
# for the first workload
global_ranked_knobs = load_data_helper(
pipeline_data, unique_workload, PipelineTaskType.RANKED_KNOBS
)[:params['IMPORTANT_KNOB_NUMBER']]
global_pruned_metrics = load_data_helper(
pipeline_data, unique_workload,
PipelineTaskType.PRUNED_METRICS)
ranked_knob_idxs = [
i for i in range(X_matrix.shape[1])
if X_columnlabels[i] in global_ranked_knobs
]
pruned_metric_idxs = [
i for i in range(y_matrix.shape[1])
if y_columnlabels[i] in global_pruned_metrics
]
# Filter X & y columnlabels by top ranked_knobs & pruned_metrics
X_columnlabels = X_columnlabels[ranked_knob_idxs]
y_columnlabels = y_columnlabels[pruned_metric_idxs]
initialized = True
# Filter X & y matrices by top ranked_knobs & pruned_metrics
X_matrix = X_matrix[:, ranked_knob_idxs]
y_matrix = y_matrix[:, pruned_metric_idxs]
# Combine duplicate rows (rows with same knob settings)
X_matrix, y_matrix, rowlabels = DataUtil.combine_duplicate_rows(
X_matrix, y_matrix, rowlabels)
workload_data[unique_workload] = {
'X_matrix': X_matrix,
'y_matrix': y_matrix,
'rowlabels': rowlabels,
}
if len(workload_data) == 0:
# The background task that aggregates the data has not finished running yet
target_data.update(mapped_workload=None, scores=None)
LOG.debug(
'%s: Skipping workload mapping because there is no parsed workload.\n',
AlgorithmType.name(algorithm))
return target_data, algorithm
# Stack all X & y matrices for preprocessing
Xs = np.vstack(
[entry['X_matrix'] for entry in list(workload_data.values())])
ys = np.vstack(
[entry['y_matrix'] for entry in list(workload_data.values())])
# Scale the X & y values, then compute the deciles for each column in y
X_scaler = StandardScaler(copy=False)
X_scaler.fit(Xs)
y_scaler = StandardScaler(copy=False)
y_scaler.fit_transform(ys)
y_binner = Bin(bin_start=1, axis=0)
y_binner.fit(ys)
del Xs
del ys
# Filter the target's X & y data by the ranked knobs & pruned metrics.
X_target = target_data['X_matrix'][:, ranked_knob_idxs]
y_target = target_data['y_matrix'][:, pruned_metric_idxs]
# Now standardize the target's data and bin it by the deciles we just
# calculated
X_target = X_scaler.transform(X_target)
y_target = y_scaler.transform(y_target)
y_target = y_binner.transform(y_target)
scores = {}
for workload_id, workload_entry in list(workload_data.items()):
predictions = np.empty_like(y_target)
X_workload = workload_entry['X_matrix']
X_scaled = X_scaler.transform(X_workload)
y_workload = workload_entry['y_matrix']
y_scaled = y_scaler.transform(y_workload)
for j, y_col in enumerate(y_scaled.T):
# Using this workload's data, train a Gaussian process model
# and then predict the performance of each metric for each of
# the knob configurations attempted so far by the target.
y_col = y_col.reshape(-1, 1)
if params['GPR_USE_GPFLOW']:
model_kwargs = {
'lengthscales': params['GPR_LENGTH_SCALE'],
'variance': params['GPR_MAGNITUDE'],
'noise_variance': params['GPR_RIDGE']
}
tf.reset_default_graph()
graph = tf.get_default_graph()
gpflow.reset_default_session(graph=graph)
m = gpr_models.create_model(params['GPR_MODEL_NAME'],
X=X_scaled,
y=y_col,
**model_kwargs)
gpr_result = gpflow_predict(m.model, X_target)
else:
model = GPRNP(length_scale=params['GPR_LENGTH_SCALE'],
magnitude=params['GPR_MAGNITUDE'],
max_train_size=params['GPR_MAX_TRAIN_SIZE'],
batch_size=params['GPR_BATCH_SIZE'])
model.fit(X_scaled, y_col, ridge=params['GPR_RIDGE'])
gpr_result = model.predict(X_target)
predictions[:, j] = gpr_result.ypreds.ravel()
# Bin each of the predicted metric columns by deciles and then
# compute the score (i.e., distance) between the target workload
# and each of the known workloads
predictions = y_binner.transform(predictions)
dists = np.sqrt(
np.sum(np.square(np.subtract(predictions, y_target)), axis=1))
scores[workload_id] = np.mean(dists)
# Find the best (minimum) score
best_score = np.inf
best_workload_id = None
best_workload_name = None
scores_info = {}
for workload_id, similarity_score in list(scores.items()):
workload_name = Workload.objects.get(pk=workload_id).name
if similarity_score < best_score:
best_score = similarity_score
best_workload_id = workload_id
best_workload_name = workload_name
scores_info[workload_id] = (workload_name, similarity_score)
target_data.update(mapped_workload=(best_workload_id, best_workload_name,
best_score),
scores=scores_info)
LOG.debug('%s: Finished mapping the workload.\n\ndata=%s\n',
AlgorithmType.name(algorithm),
JSONUtil.dumps(target_data, pprint=True))
save_execution_time(start_ts, "map_workload", newest_result)
return target_data, algorithm