def test_fit_invalid():
"""Fit the classifier with an invalid"""
clf = HMMClassifier()
with pytest.raises(TypeError) as e:
clf.fit(tuple(hmm_list))
assert str(
e.value) == 'Expected models to be a list or dict of HMM objects'
def test_fit_dict_invalid():
"""Fit the classifier using a dict of invalid types"""
clf = HMMClassifier()
with pytest.raises(TypeError) as e:
clf.fit({'a': 0, 'b': 0})
assert str(e.value) == 'Expected all models to be HMM objects'
def test_fit_dict_empty():
"""Fit the classifier using an empty dict"""
clf = HMMClassifier()
with pytest.raises(RuntimeError) as e:
clf.fit({})
assert str(e.value) == 'Must fit the classifier with at least one HMM'
def test_fit_dict():
"""Fit the classifier using a dict of HMMs"""
clf = HMMClassifier()
clf.fit(hmm_dict)
assert clf._models == list(hmm_dict.values())
def test_fit_list():
"""Fit the classifier using a list of HMMs"""
clf = HMMClassifier()
clf.fit(hmm_list)
assert clf._models == hmm_list
hmm.set_random_initial()
hmm.set_random_transitions()
with warnings.catch_warnings():
warnings.filterwarnings('ignore', category=DeprecationWarning)
hmm.fit(
[np.arange((i + j * 20) * 30).reshape(-1, 3) for j in range(2, 5)])
hmm_list.append(hmm)
hmm_dict[label] = hmm
# Create some sample test data and labels
X = [np.arange((i + 2 * 20) * 30).reshape(-1, 3) for i in range(2, 5)]
Y = ['c0', 'c1', 'c1']
x, y = X[0], 'c1'
# Fit a classifier
hmm_clf = HMMClassifier()
hmm_clf.fit(hmm_list)
# =================== #
# HMMClassifier.fit() #
# =================== #
def test_fit_list():
"""Fit the classifier using a list of HMMs"""
clf = HMMClassifier()
clf.fit(hmm_list)
assert clf._models == hmm_list
def test_fit_list_empty():
import numpy as np
from sequentia.classifiers import HMM, HMMClassifier
# Set of possible labels
labels = [f'class{i}' for i in range(5)]
# Create and fit some sample HMMs
hmms = []
for i, label in enumerate(labels):
hmm = HMM(label=label, n_states=(i + 3), topology='left-right')
hmm.set_random_initial()
hmm.set_random_transitions()
hmm.fit([np.arange((i + j * 20) * 30).reshape(-1, 3) for j in range(1, 4)])
hmms.append(hmm)
# Create some sample test data and labels
X = [np.random.random((10 * i, 3)) for i in range(1, 4)]
y = ['class0', 'class1', 'class1']
# Create a classifier and calculate predictions and evaluations
clf = HMMClassifier()
clf.fit(hmms)
predictions = clf.predict(X)
accuracy, confusion = clf.evaluate(X, y, labels=labels)