def as_vector(self):
'''
turn this record to a vector that can be fed into a prediction model
'''
# assert self.tag == MetricsTag.ENC, 'metrics un-encoded, unable to vectorize'
assert self.tag == 'enc', 'metrics un-encoded, unable to vectorize'
conf = LumosConf()
inst_id = conf.get_inst_id(self.inst_type)
d_info = conf.get_inst_detailed_conf(self.inst_type)
n_fam, n_cpu, n_mem = d_info['family'], d_info['cpu'], d_info['memory']
scale_id = conf.get_scale_id(self.scale)
X = np.array(
[inst_id, n_fam, n_cpu, n_mem, scale_id, self.ts[0], self.ts[1]])
X = np.concatenate((X, self.metrics), axis=0)
Y = self.jct
return X, Y
def get_train_test_data(self,
train_scale='tiny',
test_wl='',
flag='single'):
'''
get the training data that profiled on a concrete instance type
param:
@t_inst_type: the instance type that is used for profiling
@test_wl: the workload that is to be used for testing
'''
rankize_data = self.get_data_rankize()
assert test_wl in self.__data['1'] or test_wl in (
'HiBench', 'BigBench'), 'invalid test workload'
assert flag in ('single',
'multi'), 'indicating single/multi testing workloads'
def is_test_wl(wl):
if flag == 'single':
return wl == test_wl
else:
if test_wl == 'BigBench':
return 'hive' in wl
elif test_wl == 'HiBench':
return 'hive' not in wl
conf = LumosConf()
truncate = conf.get('dataset', 'truncate')
fft_stat_encoder = FFTStatEncoder(truncate=truncate)
train_data = defaultdict(lambda: defaultdict(lambda: {
'X': [],
'Y': []
}))
test_data = defaultdict(lambda: defaultdict(lambda: \
defaultdict(lambda: defaultdict(lambda: {
'X': [],
'Y': []
}))))
predict_scales = ['tiny', 'small', 'large', 'huge']
if train_scale == 'small':
predict_scales.remove('tiny')
for rnd, rnd_data in rankize_data.items():
for wl, wl_data in rnd_data.items():
if is_test_wl(wl): continue
for record1 in wl_data[train_scale]:
t_inst_type = record1.inst_type
test_conf = conf.get_inst_detailed_conf(t_inst_type,
format='list')
test_metrics_vec = fft_stat_encoder.encode(
record1.metrics,
record1.raw_metrics,
sampling_interval=self.sampling_interval)
for scale in predict_scales:
target_scale = conf.get_scale_id(scale)
for record2 in wl_data[scale]:
target_conf = conf.get_inst_detailed_conf(
record2.inst_type, format='list')
target_rank = record2.rank
target_jct = record2.jct
X = test_conf.copy()
X.extend(target_conf)
X.append(target_scale)
X.extend(test_metrics_vec)
train_data[rnd][t_inst_type]['X'].append(X)
if self.ordinal:
train_data[rnd][t_inst_type]['Y'].append(
target_rank)
else:
train_data[rnd][t_inst_type]['Y'].append(
target_jct)
for rnd, rnd_data in rankize_data.items():
for wl, wl_data in rnd_data.items():
if not is_test_wl(wl): continue
# wl_data = rnd_data[test_wl]
for record1 in wl_data[train_scale]:
t_inst_type = record1.inst_type
test_conf = conf.get_inst_detailed_conf(t_inst_type,
format='list')
test_metrics_vec = fft_stat_encoder.encode(
record1.metrics,
record1.raw_metrics,
sampling_interval=self.sampling_interval)
for scale in predict_scales:
target_scale = conf.get_scale_id(scale)
for record2 in wl_data[scale]:
target_conf = conf.get_inst_detailed_conf(
record2.inst_type, format='list')
target_rank = record2.rank
target_jct = record2.jct
X = test_conf.copy()
X.extend(target_conf)
X.append(target_scale)
X.extend(test_metrics_vec)
test_data[wl][rnd][t_inst_type][scale]['X'].append(
X)
if self.ordinal:
test_data[wl][rnd][t_inst_type][scale][
'Y'].append(target_rank)
else:
test_data[wl][rnd][t_inst_type][scale][
'Y'].append(target_jct)
return train_data, test_data