def background_knowledge_example():
domain = Domain.make(["a", "b"], ["x", "y"], [(0, 1), (0, 1)])
a, b, x, y = domain.get_symbols(domain.variables)
formula = (a | b) & (~a | ~b) & (x >= 0) & (x <= y) & (y <= 1)
thresholds = {v: 0.1 for v in domain.real_vars}
data = uniform(domain, 10000)
labels = evaluate(domain, formula, data)
data = data[labels == 1]
labels = labels[labels == 1]
def learn_inc(_data, _labels, _i, _k, _h):
strategy = OneClassStrategy(
RandomViolationsStrategy(10),
thresholds) #, background_knowledge=(a | b) & (~a | ~b))
learner = KCnfSmtLearner(_k, _h, strategy, "mvn")
initial_indices = LearnOptions.initial_random(20)(list(
range(len(_data))))
# learner.add_observer(LoggingObserver(None, _k, _h, None, True))
learner.add_observer(
PlottingObserver(domain, "test_output/bg",
"run_{}_{}_{}".format(_i, _k,
_h), domain.real_vars[0],
domain.real_vars[1], None, False))
return learner.learn(domain, _data, _labels, initial_indices)
(new_data, new_labels,
formula), k, h = learn_bottom_up(data, labels, learn_inc, 1, 1, 1, 1,
None, None)
print("Learned CNF(k={}, h={}) formula {}".format(k, h,
pretty_print(formula)))
print("Data-set grew from {} to {} entries".format(len(labels),
len(new_labels)))
def main():
domain, formula, name = checker_problem()
thresholds = {v: 0.1 for v in domain.real_vars}
data = uniform(domain, 1000)
labels = evaluate(domain, formula, data)
data = data[labels == 1]
labels = labels[labels == 1]
def learn_inc(_data, _labels, _i, _k, _h):
strategy = OneClassStrategy(RandomViolationsStrategy(10), thresholds)
learner = KCnfSmtLearner(_k, _h, strategy, "mvn")
initial_indices = LearnOptions.initial_random(20)(list(
range(len(_data))))
# learner.add_observer(LoggingObserver(None, _k, _h, None, True))
learner.add_observer(
PlottingObserver(domain, "test_output/checker",
"run_{}_{}_{}".format(_i, _k,
_h), domain.real_vars[0],
domain.real_vars[1], None, False))
return learner.learn(domain, _data, _labels, initial_indices)
(new_data, new_labels,
formula), k, h = learn_bottom_up(data, labels, learn_inc, 1, 1, 1, 1,
None, None)
print("Learned CNF(k={}, h={}) formula {}".format(k, h,
pretty_print(formula)))
print("Data-set grew from {} to {} entries".format(len(labels),
len(new_labels)))
def negative_samples_example(background_knowledge):
domain = Domain.make(["a", "b"], ["x", "y"], [(0, 1), (0, 1)])
a, b, x, y = domain.get_symbols(domain.variables)
formula = (a | b) & (~a | ~b) & (x <= y) & domain.get_bounds()
background_knowledge = (a | b) & (~a
| ~b) if background_knowledge else None
thresholds = {"x": 0.1, "y": 0.2}
data = uniform(domain, 10000)
labels = evaluate(domain, formula, data)
data = data[labels == 1]
labels = labels[labels == 1]
original_sample_count = len(labels)
start_time = time.time()
data, labels = OneClassStrategy.add_negatives(domain, data, labels,
thresholds, 100,
background_knowledge)
print("Created {} negative examples".format(
len(labels) - original_sample_count))
directory = "test_output{}bg_sampled{}{}".format(
os.path.sep, os.path.sep, time.strftime("%Y-%m-%d %Hh%Mm%Ss"))
def learn_inc(_data, _labels, _i, _k, _h):
strategy = OneClassStrategy(RandomViolationsStrategy(10),
thresholds,
background_knowledge=background_knowledge)
learner = KCnfSmtLearner(_k, _h, strategy, "mvn")
initial_indices = LearnOptions.initial_random(20)(list(
range(len(_data))))
learner.add_observer(
PlottingObserver(domain, directory,
"run_{}_{}_{}".format(_i, _k,
_h), domain.real_vars[0],
domain.real_vars[1], None, False))
return learner.learn(domain, _data, _labels, initial_indices)
(new_data, new_labels,
learned_formula), k, h = learn_bottom_up(data, labels, learn_inc, 1, 1, 1,
1, None, None)
if background_knowledge:
learned_formula = learned_formula & background_knowledge
duration = time.time() - start_time
print("{}".format(smt_to_nested(learned_formula)))
print("Learned CNF(k={}, h={}) formula {}".format(
k, h, pretty_print(learned_formula)))
print("Data-set grew from {} to {} entries".format(len(labels),
len(new_labels)))
print("Learning took {:.2f}s".format(duration))
test_data, labels = OneClassStrategy.add_negatives(domain, data, labels,
thresholds, 1000,
background_knowledge)
assert all(evaluate(domain, learned_formula, test_data) == labels)
def learn_wrap(data, labels, learn_inc, queue):
res = learn_bottom_up(data, labels, learn_inc, 1, 1, 1, 1, None, None)
(new_data, new_labels, formula), k, h = res
msg = "Learned CNF(k={}, h={})"
logger.debug(msg.format(k, h))
msg = "Data-set grew from {} to {} entries"
logger.debug(msg.format(len(labels), len(new_labels)))
queue.put((formula, k, h))
def experiment():
random.seed(888)
np.random.seed(888)
start = time.time()
domain = Domain.make(["b0", "b1", "b2"], ["x0", "x1"], [(0, 1), (0, 1)])
# thresholds = {"x": 0.1, "y": 0.1}
# data, _ = RejectionEngine(domain, formula, x * x, 100000).get_samples(50)
filename = "/Users/samuelkolb/Downloads/input-ijcai-rh/ijcai-rh_2_3_2_100_50_4_3.problem_0.train_dataset.data"
data = np.loadtxt(filename, delimiter=",", skiprows=0)
k = 4
nearest_neighbors = []
for i in range(len(data)):
nearest_neighbors.append([])
for j in range(len(data)):
if i != j:
distance = 1 if any(data[i, b] != data[j, b] for b, v in enumerate(domain.variables)
if domain.is_bool(v))\
else max(abs(data[i, r] - data[j, r]) / (domain.var_domains[v][1] - domain.var_domains[v][0]) for r, v in enumerate(domain.variables) if domain.is_real(v))
if len(nearest_neighbors[i]) < k:
nearest_neighbors[i].append((j, distance))
else:
index_of_furthest = None
for fi, f in enumerate(nearest_neighbors[i]):
if index_of_furthest is None or f[
1] > nearest_neighbors[i][index_of_furthest][1]:
index_of_furthest = fi
if distance < nearest_neighbors[i][index_of_furthest][1]:
nearest_neighbors[i][index_of_furthest] = (j, distance)
print(nearest_neighbors)
t = [[
sum(n[1] for n in nearest_neighbors[i]) / len(nearest_neighbors[i]) *
(domain.var_domains[v][1] - domain.var_domains[v][0])
if domain.is_real(v) else 0 for v in domain.variables
] for i in range(len(nearest_neighbors))]
t = np.array(t) * 1.5
print(t)
# data = uniform(domain, 400)
labels = np.ones(len(data))
data, labels = OneClassStrategy.add_negatives(domain, data, labels, t,
1000)
directory = "output{}lariat-synthetic{}{}".format(
os.path.sep, os.path.sep, time.strftime("%Y-%m-%d %Hh%Mm%Ss"))
os.makedirs(directory)
name = os.path.join(directory, "combined.png")
plot.plot_combined("x0", "x1", domain, None, (data, labels), None, name,
set(), set())
def learn_inc(_data, _labels, _i, _k, _h):
# strategy = OneClassStrategy(RandomViolationsStrategy(10), thresholds)
strategy = DecisionTreeSelection()
learner = KCnfSmtLearner(_k, _h, strategy, "mvn")
initial_indices = LearnOptions.initial_random(20)(list(
range(len(_data))))
learner.add_observer(
PlottingObserver(domain, directory,
"run_{}_{}_{}".format(_i, _k,
_h), domain.real_vars[0],
domain.real_vars[1], None, False))
return learner.learn(domain, _data, _labels, initial_indices)
(new_data, new_labels,
learned_formula), k, h = learn_bottom_up(data, labels, learn_inc, 1, 1, 2,
4, None, None)
duration = time.time() - start
Formula(domain, learned_formula).to_file(
os.path.join(directory,
"result_{}_{}_{}.json".format(k, h, int(duration))))