def run_validation_spbn(train_data, folds, patience, result_folder, idx_fold):
hc = GreedyHillClimbing()
pool = OperatorPool([ArcOperatorSet(), ChangeNodeTypeSet()])
for k in folds:
vl = ValidatedLikelihood(train_data, k=k, seed=0)
for p in patience:
fold_folder = result_folder + '/HillClimbing/SPBN_CKDE/Validation_' + str(
k) + '_' + str(p) + '/' + str(idx_fold)
pathlib.Path(fold_folder).mkdir(parents=True, exist_ok=True)
if os.path.exists(fold_folder + '/end.lock'):
continue
cb_save = SaveModel(fold_folder)
node_types = [(name, NodeType.CKDE)
for name in train_data.columns.values]
start_model = SemiparametricBN(list(train_data.columns.values),
node_types)
bn = hc.estimate(pool,
vl,
start_model,
callback=cb_save,
patience=p,
verbose=True)
iters = sorted(glob.glob(fold_folder + '/*.pickle'))
last_file = os.path.basename(iters[-1])
number = int(os.path.splitext(last_file)[0])
bn.save(fold_folder + '/' + str(number + 1).zfill(6) + ".pickle")
with open(fold_folder + '/end.lock', 'w') as f:
pass
def train_gbn(dataset, instances):
df = pd.read_csv(dataset + "_" + str(instances) + '.csv')
hc = GreedyHillClimbing()
arc_set = ArcOperatorSet()
result_folder = 'models/' + dataset + '/' + str(
instances) + '/HillClimbing/GBN_BIC/'
pathlib.Path(result_folder).mkdir(parents=True, exist_ok=True)
if not os.path.exists(result_folder + '/end.lock'):
bic = BIC(df)
cb_save = SaveModel(result_folder)
start_model = GaussianNetwork(list(df.columns.values))
bn = hc.estimate(arc_set, bic, start_model, callback=cb_save)
iters = sorted(glob.glob(result_folder + '/*.pickle'))
last_file = os.path.basename(iters[-1])
number = int(os.path.splitext(last_file)[0])
bn.save(result_folder + '/' + str(number + 1).zfill(6) + ".pickle")
with open(result_folder + '/end.lock', 'w') as f:
pass
hc = GreedyHillClimbing()
arc_set = ArcOperatorSet()
result_folder = 'models/' + dataset + '/' + str(
instances) + '/HillClimbing/GBN_BGe/'
pathlib.Path(result_folder).mkdir(parents=True, exist_ok=True)
if not os.path.exists(result_folder + '/end.lock'):
bge = BGe(df)
cb_save = SaveModel(result_folder)
start_model = GaussianNetwork(list(df.columns.values))
bn = hc.estimate(arc_set, bge, start_model, callback=cb_save)
iters = sorted(glob.glob(result_folder + '/*.pickle'))
last_file = os.path.basename(iters[-1])
number = int(os.path.splitext(last_file)[0])
bn.save(result_folder + '/' + str(number + 1).zfill(6) + ".pickle")
with open(result_folder + '/end.lock', 'w') as f:
pass
def run_bge_gaussian(train_data, result_folder, idx_fold):
fold_folder = result_folder + '/HillClimbing/Gaussian/BGe/' + str(idx_fold)
pathlib.Path(fold_folder).mkdir(parents=True, exist_ok=True)
if os.path.exists(fold_folder + '/end.lock'):
return
hc = GreedyHillClimbing()
arc_set = ArcOperatorSet()
bge = BGe(train_data)
cb_save = SaveModel(fold_folder)
start_model = GaussianNetwork(list(train_data.columns.values))
bn = hc.estimate(arc_set, bge, start_model, callback=cb_save, verbose=True)
iters = sorted(glob.glob(fold_folder + '/*.pickle'))
last_file = os.path.basename(iters[-1])
number = int(os.path.splitext(last_file)[0])
bn.save(fold_folder + '/' + str(number+1).zfill(6) + ".pickle")
with open(fold_folder + '/end.lock', 'w') as f:
pass
def run_validation_kdebn(train_data, folds, patience, result_folder, idx_fold):
hc = GreedyHillClimbing()
arc_set = ArcOperatorSet()
for k in folds:
vl = ValidatedLikelihood(train_data, k=k, seed=0)
for p in patience:
fold_folder = result_folder + '/HillClimbing/KDEBN/Validation_' + str(k) + '_' + str(p) + '/' + str(idx_fold)
pathlib.Path(fold_folder).mkdir(parents=True, exist_ok=True)
if os.path.exists(fold_folder + '/end.lock'):
continue
cb_save = SaveModel(fold_folder)
start_model = KDENetwork(list(train_data.columns.values))
bn = hc.estimate(arc_set, vl, start_model, callback=cb_save, patience=p, verbose=True)
iters = sorted(glob.glob(fold_folder + '/*.pickle'))
last_file = os.path.basename(iters[-1])
number = int(os.path.splitext(last_file)[0])
bn.save(fold_folder + '/' + str(number+1).zfill(6) + ".pickle")
with open(fold_folder + '/end.lock', 'w') as f:
pass
small_results = pd.DataFrame()
medium_results = pd.DataFrame()
large_results = pd.DataFrame()
for n in experiments_helper.INSTANCES:
df = pd.read_csv('data/small_' + str(n) + ".csv")
executions = np.empty((800, ))
for i in range(800):
if i % 10 == 0:
print(str(i) + " executions")
vl = ValidatedLikelihood(df, k=10, seed=i)
start_model = SemiparametricBN(list(df.columns.values))
hc = GreedyHillClimbing()
pool = OperatorPool([ArcOperatorSet(), ChangeNodeTypeSet()])
start = time.time()
bn = hc.estimate(pool, vl, start_model, patience=0)
end = time.time()
executions[i] = end - start
small_results['SPBN_' + str(n)] = pd.Series(executions,
name="SPBN_" + str(n))
print("Small " + str(n) + " -- Time: " + str(executions.mean()) +
", std: " + str(np.std(executions, ddof=1)))
df = pd.read_csv('data/medium_' + str(n) + ".csv")
executions = np.empty((200, ))
small_results = pd.DataFrame()
medium_results = pd.DataFrame()
large_results = pd.DataFrame()
for n in experiments_helper.INSTANCES:
df = pd.read_csv('data/small_' + str(n) + ".csv")
executions = np.empty((20000,))
for i in range(20000):
if i % 10 == 0:
print(str(i) + " executions")
bic = BIC(df)
start_model = GaussianNetwork(list(df.columns.values))
hc = GreedyHillClimbing()
arcs = ArcOperatorSet()
start = time.time()
bn = hc.estimate(arcs, bic, start_model)
end = time.time()
executions[i] = end - start
small_results['GBN_BIC_' + str(n)] = pd.Series(executions, name="GBN_BIC_" + str(n))
print("Small " + str(n) + " -- Time: " + str(executions.mean()) + ", std: " + str(np.std(executions, ddof=1)))
df = pd.read_csv('data/medium_' + str(n) + ".csv")
executions = np.empty((20000,))
for i in range(20000):
print(str(i) + " executions")