def get_scenario(name):
if name == 'incremental':
sc = scenarios.IncrementalScenarioProvider(episode_length=CI_CYCLES)
elif name == 'paintcontrol':
sc = scenarios.IndustrialDatasetScenarioProvider(tcfile='DATA/paintcontrol.csv')
elif name == 'iofrol':
sc = scenarios.IndustrialDatasetScenarioProvider(tcfile='DATA/iofrol.csv')
elif name == 'gsdtsr':
sc = scenarios.IndustrialDatasetScenarioProvider(tcfile='DATA/gsdtsr.csv')
return sc
def run_optimal(dataset,
repo_path,
datfile,
sched_time_ratio=DEFAULT_SCHED_TIME_RATIO):
scenario_provider = scenarios.IndustrialDatasetScenarioProvider(
f"{repo_path}/{dataset}/features-engineered.csv", sched_time_ratio)
logging.debug(f"Running for {dataset}")
metric = NAPFDMetric('Verdict') if dataset in [
'iofrol', 'paintcontrol', 'gsdtsr'
] else NAPFDMetric()
i = 1
mean_fitness = 0
start = time.time()
for (t, vsc) in enumerate(scenario_provider, start=1):
metric.update_available_time(vsc.get_available_time())
actions = vsc.get_testcases()
# Compute time
start_exp = time.time()
ind = [0]
if (len(actions) > 1):
# Run GA to find the best NAPFD in current commit
ind = genetic_algorithm_tcp(actions, metric)
end_exp = time.time()
metric.evaluate(sort_update_actions(np.array(ind) + 1, actions))
i += 1
mean_fitness += metric.fitness
logging.debug(
f"commit: {t} - fitness: {metric.fitness} - duration: {end_exp - start_exp}"
)
end = time.time()
logging.debug(f"Time expend to run the experiments: {end - start}")
logging.debug(mean_fitness / i)
with open(datfile, 'w') as f:
f.write(str(mean_fitness / i))
agent = agents.RandomAgent(histlen=args.histlen)
elif args.agent == 'heur_sort':
agent = agents.HeuristicSortAgent(histlen=args.histlen)
elif args.agent == 'heur_weight':
agent = agents.HeuristicWeightAgent(histlen=args.histlen)
else:
print('Unknown Agent')
sys.exit()
if args.scenario_provider == 'random':
scenario_provider = scenarios.RandomScenarioProvider()
elif args.scenario_provider == 'incremental':
scenario_provider = scenarios.IncrementalScenarioProvider(
episode_length=args.no_scenarios)
elif args.scenario_provider == 'paintcontrol':
scenario_provider = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/paintcontrol.csv')
# scenario_provider = scenarios.FileBasedSubsetScenarioProvider(scheduleperiod=datetime.timedelta(days=1),
# tcfile='paintcontrol.csv',
# solfile='paintcontrol.csv')
args.validation_interval = 0
elif args.scenario_provider == 'iofrol':
scenario_provider = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/iofrol.csv')
args.validation_interval = 0
elif args.scenario_provider == 'gsdtsr':
scenario_provider = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/gsdtsr.csv')
args.validation_interval = 0
elif args.scenario_provider == 'siemens_data':
scenario_provider = scenarios.IndustrialDatasetScenarioProvider(
else:
print('Unknown Agent')
sys.exit()
if args.scenario_provider == 'random':
scenario_provider = scenarios.RandomScenarioProvider()
elif args.scenario_provider == 'incremental':
scenario_provider = scenarios.IncrementalScenarioProvider(episode_length=args.no_scenarios)
elif args.scenario_provider == 'paintcontrol':
#scenario_provider = scenarios.IndustrialDatasetScenarioProvider(tcfile='DATA/paintcontrol.csv')
scenario_provider = scenarios.FileBasedSubsetScenarioProvider(scheduleperiod=datetime.timedelta(days=1),
tcfile='tc_data_paintcontrol.csv',
solfile='tc_sol_paintcontrol.csv')
args.validation_interval = 0
elif args.scenario_provider == 'iofrol':
scenario_provider = scenarios.IndustrialDatasetScenarioProvider(tcfile='DATA/iofrol.csv')
args.validation_interval = 0
elif args.scenario_provider == 'gsdtsr':
scenario_provider = scenarios.IndustrialDatasetScenarioProvider(tcfile='DATA/gsdtsr.csv')
args.validation_interval = 0
if args.reward == 'binary':
reward_function = reward.binary_positive_detection_reward
elif args.reward == 'failcount':
reward_function = reward.failcount
elif args.reward == 'timerank':
reward_function = reward.timerank
elif args.reward == 'tcfail':
reward_function = reward.tcfail
prefix = '{}_{}_{}_lr{}_as{}_n{}_eps{}_hist{}_{}'.format(args.agent, args.scenario_provider, args.reward,
def run_optimal(dataset, repo_path, output_dir, sched_time_ratio):
logging.debug(f"Running for {dataset}")
metric = NAPFDVerdictMetric() if dataset in [
'iofrol', 'paintcontrol', 'gsdtsr', 'lexisnexis'
] else NAPFDMetric()
reward_functions = [RNFailReward(), RRankReward(), TimeRankReward()]
all_data_file = "experiment;step;policy;reward_function;sched_time;sched_time_duration;prioritization_time;detected;missed;tests_ran;tests_not_ran;" \
+ "ttf;time_reduction;fitness;cost;rewards;avg_precision\n"
start = time.time()
# 30 independent executions
for i in range(1, 31):
scenario_provider = scenarios.IndustrialDatasetScenarioProvider(
f"{repo_path}/{dataset}/features-engineered.csv", sched_time_ratio)
for (t, vsc) in enumerate(scenario_provider, start=1):
metric.update_available_time(vsc.get_available_time())
actions = vsc.get_testcases()
# Compute time
start_exp = time.time()
ind = [0]
if (len(actions) > 1):
# Run GA to find the best NAPFD in current commit
ind = genetic_algorithm_tcp(actions, metric)
end_exp = time.time()
last_prioritization = sort_update_actions(
np.array(ind) + 1, actions)
metric.evaluate(last_prioritization)
# Get the Test Case names
last_prioritization = [tc['Name'] for tc in last_prioritization]
time_reduction = scenario_provider.total_build_duration - metric.ttf_duration
for reward_function in reward_functions:
last_reward = reward_function.evaluate(metric,
last_prioritization)
all_data_file += f"{i};{t};GA;{reward_function.get_name()};" \
+ f"{scenario_provider.avail_time_ratio};{vsc.get_available_time()};{end_exp - start_exp};" \
+ f"{metric.detected_failures};{metric.undetected_failures};{len(metric.scheduled_testcases)};" \
+ f"{len(metric.unscheduled_testcases)};{metric.ttf};{time_reduction};" \
+ f"{metric.fitness};{metric.cost};{np.mean(last_reward)};{metric.avg_precision}\n"
logging.debug(
f"Exp {i} - Ep {t} - Policy GA - NAPFD/APFDc: {metric.fitness:.4f}/{metric.cost:.4f}"
)
end = time.time()
logging.debug(f"Time expend to run the experiments: {end - start}")
print(f"Saving in {output_dir}/{dataset}.csv")
with open(f"{output_dir}/{dataset}.csv", "w") as f:
f.write(all_data_file)
from jmetal.operator.mutation import PermutationSwapMutation
from jmetal.util.observer import PrintObjectivesObserver
from jmetal.util.density_estimator import CrowdingDistance
from jmetal.util.observer import PrintObjectivesObserver
from jmetal.util.ranking import FastNonDominatedRanking
from jmetal.util.solutions.comparator import MultiComparator
from jmetal.util.termination_criterion import StoppingByEvaluations
from problem import TCPCI
if __name__ == "__main__":
metric = NAPFDMetric()
repo_path = "data"
dataset = 'deeplearning4j@deeplearning4j'
scenario_provider = scenarios.IndustrialDatasetScenarioProvider(f"{repo_path}/{dataset}/features-engineered.csv")
for (t, vsc) in enumerate(scenario_provider, start=1):
if(t > 1):
break
available_time = vsc.get_available_time()
metric.update_available_time(available_time)
test_cases = vsc.get_testcases()
IND_SIZE = len(test_cases)
if (IND_SIZE > 1):
# Run GA to find the best NAPFD in current commit
problem = TCPCI(metric=metric, test_cases=test_cases,
number_of_variables=IND_SIZE)
# convert an array of values into a dataset matrix
def create_dataset(dataset, look_back=1):
dataX, dataY = [], []
for i in range(len(dataset) - look_back - 1):
a = dataset[i:(i + look_back), 0]
dataX.append(a)
dataY.append(dataset[i + look_back, 0])
return numpy.array(dataX), numpy.array(dataY)
# fix random seed for reproducibility
numpy.random.seed(7)
# load the dataset
#dataframe = read_csv('airline-passengers.csv', usecols=[1], engine='python')
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/paintcontrol.csv')
dataframe = sc.tcdf.loc[:, ('LastRun', 'Verdict')]
dataset = dataframe.values
#dataset = dataset.astype('float32')
# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
# split into train and test sets
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size, :], dataset[train_size:len(dataset), :]
# reshape into X=t and Y=t+1
def get_scenario(name):
if name == 'incremental':
sc = scenarios.IncrementalScenarioProvider(episode_length=CI_CYCLES)
elif name == 'paintcontrol':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/paintcontrol.csv')
elif name == 'iofrol':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/iofrol.csv')
elif name == 'gsdtsr':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/gsdtsr.csv')
elif name == 'spectrum':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/spectrum.csv')
elif name == 'group_01':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/group_01.csv')
elif name == 'group_03':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/group_03.csv')
elif name == 'group_06':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/group_06.csv')
elif name == 'group_11':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/group_11.csv')
elif name == 'mattermost':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/mattermost.csv')
elif name == 'mm1':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/mattermost_retecs_in_1.csv')
elif name == 'mm2':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/mattermost_retecs_in_2.csv')
elif name == 'mm3':
sc = scenarios.IndustrialDatasetScenarioProvider(
tcfile='DATA/mattermost_retecs_in_3.csv')
return sc
