def test_fit_and_predict_with_new_labels_set_via_method(self):
# Initialize model
invalid_entities = {"PAD": 0, "BACKGROUND": 1, "test3": 2}
cnn_model = CharacterLevelCnnModel(invalid_entities)
cnn_model._construct_model()
invalid_entities2 = {"PAD": 0, "BACKGROUND": 1}
cnn_model.set_label_mapping(invalid_entities2)
cnn_model._reconstruct_model()
cnn_model.set_label_mapping(self.label_mapping)
# data for model
data_gen = [[
np.array([['test']]), # x_data
np.zeros((1, 3400, max(self.label_mapping.values()) + 1))
]
# y_data
]
cv_gen = data_gen
cnn_model._construct_model()
# set different labels
cnn_model.set_label_mapping(self.label_mapping)
history, f1, f1_report = cnn_model.fit(data_gen, cv_gen)
# test predict on just the text
cnn_model.predict(data_gen[0][0])
def test_set_label_mapping(self, *mocks):
# load default
cnn_model = CharacterLevelCnnModel(self.label_mapping)
# test not dict
label_mapping = None
with self.assertRaisesRegex(
TypeError, "Labels must either be a non-empty encoding dict "
"which maps labels to index encodings or a list."):
cnn_model.set_label_mapping(label_mapping)
# test raise error for setting non PAD to 0
label_mapping = {'TEST': 0}
with self.assertRaisesRegex(ValueError,
"`PAD` must map to index zero."):
cnn_model.set_label_mapping(label_mapping)
# test raise error for setting PAD other than 0
label_mapping = {'PAD': 1}
with self.assertRaisesRegex(ValueError,
"`PAD` must map to index zero."):
cnn_model.set_label_mapping(label_mapping)
# test raise error if default label not in mapping
label_mapping = {'PAD': 0}
with self.assertRaisesRegex(
ValueError, "The `default_label` of BACKGROUND must "
"exist in the label mapping."):
cnn_model.set_label_mapping(label_mapping)
# test label_mapping without PAD
label_mapping = {
'CITY': 1, # SAME AS BACKGROUND
'BACKGROUND': 1,
'ADDRESS': 2,
}
cnn_model.set_label_mapping(label_mapping)
self.assertNotEqual(label_mapping, cnn_model.label_mapping)
label_mapping['PAD'] = 0
self.assertDictEqual(label_mapping, cnn_model.label_mapping)
# test label_mapping with PAD: 0
label_mapping = {
'PAD': 0,
'CITY': 1, # SAME AS BACKGROUND
'BACKGROUND': 1,
'ADDRESS': 2,
}
cnn_model.set_label_mapping(label_mapping)
self.assertDictEqual(label_mapping, cnn_model.label_mapping)