def check_classifiers_classes(name, classifier_orig):
X_multiclass, y_multiclass = make_blobs(n_samples=30,
random_state=0,
cluster_std=0.1)
X_multiclass, y_multiclass = shuffle(X_multiclass,
y_multiclass,
random_state=7)
X_multiclass = StandardScaler().fit_transform(X_multiclass)
# We need to make sure that we have non negative data, for things
# like NMF
X_multiclass -= X_multiclass.min() - .1
X_binary = X_multiclass[y_multiclass != 2]
y_binary = y_multiclass[y_multiclass != 2]
X_binary = pairwise_estimator_convert_X(X_binary, classifier_orig)
labels_binary = ["one", "two"]
y_names_binary = np.take(labels_binary, y_binary)
for X, y, y_names in [(X_binary, y_binary, y_names_binary)]:
for y_names_i in [y_names, y_names.astype('O')]:
y_ = choose_check_classifiers_labels(name, y, y_names_i)
check_classifiers_predictions(X, y_, name, classifier_orig)
labels_binary = [-1, 1]
y_names_binary = np.take(labels_binary, y_binary)
y_binary = choose_check_classifiers_labels(name, y_binary, y_names_binary)
check_classifiers_predictions(X_binary, y_binary, name, classifier_orig)
def check_classifiers_classes(name, classifier_orig):
# Case of shapelet models
if name == 'SerializableShapeletModel':
raise SkipTest('Skipping check_classifiers_classes for shapelets'
' due to convergence issues...')
elif name == 'ShapeletModel':
X_multiclass, y_multiclass = _create_large_ts_dataset()
classifier_orig = clone(classifier_orig)
classifier_orig.max_iter = 1000
else:
X_multiclass, y_multiclass = _create_small_ts_dataset()
X_multiclass, y_multiclass = shuffle(X_multiclass,
y_multiclass,
random_state=7)
scaler = TimeSeriesScalerMeanVariance()
X_multiclass = scaler.fit_transform(X_multiclass)
X_multiclass = np.reshape(X_multiclass,
(X_multiclass.shape[0], X_multiclass.shape[1]))
X_binary = X_multiclass[y_multiclass != 2]
y_binary = y_multiclass[y_multiclass != 2]
X_multiclass = pairwise_estimator_convert_X(X_multiclass, classifier_orig)
X_binary = pairwise_estimator_convert_X(X_binary, classifier_orig)
labels_multiclass = ["one", "two", "three"]
labels_binary = ["one", "two"]
y_names_multiclass = np.take(labels_multiclass, y_multiclass)
y_names_binary = np.take(labels_binary, y_binary)
problems = [(X_binary, y_binary, y_names_binary)]
if not classifier_orig._get_tags()['binary_only']:
problems.append((X_multiclass, y_multiclass, y_names_multiclass))
for X, y, y_names in problems:
for y_names_i in [y_names, y_names.astype('O')]:
y_ = choose_check_classifiers_labels(name, y, y_names_i)
check_classifiers_predictions(X, y_, name, classifier_orig)
labels_binary = [-1, 1]
y_names_binary = np.take(labels_binary, y_binary)
y_binary = choose_check_classifiers_labels(name, y_binary, y_names_binary)
check_classifiers_predictions(X_binary, y_binary, name, classifier_orig)