def train_tree(csv_path, tree):
print("Training the tree")
stream = FileStream(csv_path)
accuracy = 0
n_samples = 0
correct_cnt = 0
t0 = time.time()
while stream.has_more_samples():
X, y = stream.next_sample()
y_pred = tree.predict(X)
if y[0] == y_pred[0]:
correct_cnt += 1
tree = tree.partial_fit(X, y)
n_samples += 1
t1 = time.time()
total = t1 - t0
accuracy = 100.0 * correct_cnt / n_samples
print("Training data instances: ", n_samples)
print("Tree trained on ", n_samples, " instances & has ", accuracy,
"% accuracy.")
print("Training tree completed in ", total, " (s)")
def test_file_stream(test_path, package_path):
test_file = os.path.join(package_path,
'src/skmultiflow/data/datasets/sea_stream.csv')
stream = FileStream(test_file)
stream.prepare_for_use()
assert stream.n_remaining_samples() == 40000
expected_names = ['attrib1', 'attrib2', 'attrib3']
assert stream.feature_names == expected_names
expected_targets = [0, 1]
assert stream.target_values == expected_targets
assert stream.target_names == ['class']
assert stream.n_features == 3
assert stream.n_cat_features == 0
assert stream.n_num_features == 3
assert stream.n_targets == 1
assert stream.get_data_info() == 'sea_stream.csv - 1 target(s), 2 classes'
assert stream.has_more_samples() is True
assert stream.is_restartable() is True
# Load test data corresponding to first 10 instances
test_file = os.path.join(test_path, 'sea_stream_file.npz')
data = np.load(test_file)
X_expected = data['X']
y_expected = data['y']
X, y = stream.next_sample()
assert np.alltrue(X[0] == X_expected[0])
assert np.alltrue(y[0] == y_expected[0])
X, y = stream.last_sample()
assert np.alltrue(X[0] == X_expected[0])
assert np.alltrue(y[0] == y_expected[0])
stream.restart()
X, y = stream.next_sample(10)
assert np.alltrue(X == X_expected)
assert np.alltrue(y == y_expected)
assert stream.n_targets == np.array(y).ndim
assert stream.n_features == X.shape[1]
assert 'stream' == stream._estimator_type
expected_info = "FileStream(filename='sea_stream.csv', target_idx=-1, n_targets=1, cat_features=None)"
assert stream.get_info() == expected_info
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
stream = FileStream("../datasets/music.csv", 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_sample(pretrain_size)
# classifier.fit(X, y)
pipe.partial_fit(X, y, classes=stream.get_targets())
count = 0
true_labels = []
predicts = []
init_time = timer()
logging.info('Evaluating...')
while stream.has_more_samples():
X, y = stream.next_sample()
# 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)
def test_tree(csv_path, tree):
print("Testing the tree")
stream = FileStream(csv_path)
n_samples = 0
correct_cnt = 0
t2 = time.time()
y_true_all = list()
y_pred_all = list()
while stream.has_more_samples():
X, y = stream.next_sample()
y_pred = tree.predict(X)
if y[0] == y_pred[0]:
correct_cnt += 1
tree = tree.partial_fit(X, y)
n_samples += 1
y_true_all.append(y[0])
y_pred_all.append(y_pred[0])
t3 = time.time()
total = t3-t2
accuracy = 100.0 * correct_cnt / n_samples
fscore = f1_score(y_true_all, y_pred_all, average='binary')
gm = geometric_mean_score(y_true_all, y_pred_all, average='binary')
print("Test data instances: ", n_samples)
print("Tree tested on ", n_samples, " instances & has ", accuracy, "% accuracy.")
print("Tree has F-score: %.3f" % fscore)
print("Tree has GM: %.3f" % gm)
print("Testing tree completed in ", total, " (s)")
return round(fscore,3), round(gm,3)
# Retrieving 5 samples data_stream.next_sample(5) # Output- #(array([[ 36. , 0. , 7. , 3. , 1. , 118. , 13. , # 18. , 50. , 239.554, 97. , 1. , 1. , 1. , # 1. , 0. , 0. , 98. , 178. , 31. ], # [ 3. , 23. , 7. , 4. , 1. , 179. , 51. , # 18. , 38. , 239.554, 97. , 0. , 1. , 0. , # 1. , 0. , 0. , 89. , 170. , 31. ], # [ 7. , 7. , 7. , 5. , 1. , 279. , 5. , # 14. , 39. , 239.554, 97. , 0. , 1. , 2. , # 1. , 1. , 0. , 68. , 168. , 24. ], # [ 11. , 23. , 7. , 5. , 1. , 289. , 36. , # 13. , 33. , 239.554, 97. , 0. , 1. , 2. , # 1. , 0. , 1. , 90. , 172. , 30. ], # [ 3. , 23. , 7. , 6. , 1. , 179. , 51. , # 18. , 38. , 239.554, 97. , 0. , 1. , 0. , # 1. , 0. , 0. , 89. , 170. , 31. ]]), # array([0, 2, 4, 2, 2])) data_stream.has_more_samples() # Output- # True data_stream.n_remaining_samples() # Output- # 734 #####################################################################################
X_init, y_init = stream.next_sample(CHUNK_SIZE)
print(X_init)
print(y_init)
goowe.partial_fit(X_init, y_init)
accuracy = 0.0
total = 0.0
true_predictions = 0.0
for i in range(CHUNK_SIZE):
total += 1
cur = stream.next_sample()
X, y = cur[0], cur[1]
preds = goowe.predict(X)
true_predictions += np.sum(preds == y)
accuracy = true_predictions / total
print('\tData instance: {} - Accuracy: {}'.format(total, accuracy))
goowe.partial_fit(X, y)
# Now, for the remaining instances, do ITTT (Interleaved Test Then Train).
while(stream.has_more_samples()):
total += 1
cur = stream.next_sample()
X, y = cur[0], cur[1]
preds = goowe.predict(X) # Test
true_predictions += np.sum(preds == y)
accuracy = true_predictions / total
print('\tData instance: {} - Accuracy: {}'.format(int(total), round(accuracy*100.0, 3)))
goowe.partial_fit(X, y) # Then train