def test_batch_incremental():
stream = RandomTreeGenerator(tree_random_state=112, sample_random_state=112)
stream.prepare_for_use()
estimator = DecisionTreeClassifier(random_state=112)
classifier = BatchIncremental(base_estimator=estimator, n_estimators=10)
learner = Pipeline([('classifier', classifier)])
X, y = stream.next_sample(150)
learner.partial_fit(X, y)
cnt = 0
max_samples = 5000
predictions = []
true_labels = []
wait_samples = 100
correct_predictions = 0
while cnt < max_samples:
X, y = stream.next_sample()
# Test every n samples
if (cnt % wait_samples == 0) and (cnt != 0):
predictions.append(learner.predict(X)[0])
true_labels.append(y[0])
if np.array_equal(y[0], predictions[-1]):
correct_predictions += 1
learner.partial_fit(X, y)
cnt += 1
performance = correct_predictions / len(predictions)
expected_predictions = [1.0, 0.0, 1.0, 1.0, 1.0, 0.0, 1.0, 1.0, 1.0, 0.0,
0.0, 0.0, 0.0, 0.0, 1.0, 1.0, 0.0, 1.0, 0.0, 1.0,
0.0, 0.0, 1.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0, 1.0,
0.0, 1.0, 1.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0, 1.0,
0.0, 0.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.0, 1.0]
expected_correct_predictions = 31
expected_performance = 0.6326530612244898
assert np.alltrue(predictions == expected_predictions)
assert np.isclose(expected_performance, performance)
assert correct_predictions == expected_correct_predictions
assert type(learner.predict(X)) == np.ndarray
def demo():
""" _test_mol
This demo tests the MOL learner on a file stream, which reads from
the music.csv file.
The test computes the performance of the MOL learner as well as
the time to create the structure and classify all the samples in
the file.
"""
# Setup logging
logging.basicConfig(format='%(message)s', level=logging.INFO)
# Setup the file stream
opt = FileOption("FILE", "OPT_NAME", "../datasets/music.csv", "CSV", False)
stream = FileStream(opt, 0, 6)
stream.prepare_for_use()
# Setup the classifier, by default it uses Logistic Regression
#classifier = MultiOutputLearner()
#classifier = MultiOutputLearner(h=SGDClassifier(n_iter=100))
classifier = MultiOutputLearner(h=Perceptron())
# Setup the pipeline
pipe = Pipeline([('classifier', classifier)])
pretrain_size = 150
logging.info('Pre training on %s samples', str(pretrain_size))
X, y = stream.next_instance(pretrain_size)
#classifier.fit(X, y)
pipe.partial_fit(X, y, classes=stream.get_classes())
count = 0
true_labels = []
predicts = []
init_time = timer()
logging.info('Evaluating...')
while stream.has_more_instances():
X, y = stream.next_instance()
#p = classifier.predict(X)
p = pipe.predict(X)
predicts.extend(p)
true_labels.extend(y)
count += 1
perf = hamming_score(true_labels, predicts)
logging.info('Evaluation time: %s s', str(timer() - init_time))
logging.info('Total samples analyzed: %s', str(count))
logging.info('The classifier\'s static Hamming score : %0.3f' % perf)