def calculate_class_metrics(y_true: List[List[int]], y_pred: List[List[int]],
labels: Dictionary) -> List[Metric]:
"""
Calculates the metrics for the individual classes for the given predictions.
The labels should be converted into a one-hot-list.
:param y_true: list of true labels
:param y_pred: list of predicted labels
:param labels: the label dictionary
:return: the metrics for every class
"""
metrics = []
for label in labels.get_items():
metric = Metric(label)
label_idx = labels.get_idx_for_item(label)
for true, pred in zip(y_true, y_pred):
if true[label_idx] == 1 and pred[label_idx] == 1:
metric.tp()
elif true[label_idx] == 1 and pred[label_idx] == 0:
metric.fn()
elif true[label_idx] == 0 and pred[label_idx] == 1:
metric.fp()
elif true[label_idx] == 0 and pred[label_idx] == 0:
metric.tn()
metrics.append(metric)
return metrics
def test_training():
# get default dictionary
dictionary: Dictionary = Dictionary.load('chars')
# init forward LM with 128 hidden states and 1 layer
language_model: LanguageModel = LanguageModel(dictionary,
is_forward_lm=True,
hidden_size=128,
nlayers=1)
# get the example corpus and process at character level in forward direction
corpus: TextCorpus = TextCorpus('resources/corpora/lorem_ipsum',
dictionary,
language_model.is_forward_lm,
character_level=True)
# train the language model
trainer: LanguageModelTrainer = LanguageModelTrainer(
language_model, corpus)
trainer.train('./results',
sequence_length=10,
mini_batch_size=10,
max_epochs=5)
# use the character LM as embeddings to embed the example sentence 'I love Berlin'
char_lm_embeddings = CharLMEmbeddings('./results/best-lm.pt')
sentence = Sentence('I love Berlin')
char_lm_embeddings.embed(sentence)
print(sentence[1].embedding.size())
# clean up results directory
shutil.rmtree('./results')
def test_dictionary_get_item_for_index():
dictionary: Dictionary = Dictionary(add_unk=False)
dictionary.add_item('class_1')
dictionary.add_item('class_2')
dictionary.add_item('class_3')
item = dictionary.get_item_for_index(0)
assert ('class_1' == item)
def test_dictionary_get_idx_for_item():
dictionary: Dictionary = Dictionary(add_unk=False)
dictionary.add_item('class_1')
dictionary.add_item('class_2')
dictionary.add_item('class_3')
idx = dictionary.get_idx_for_item('class_2')
assert (1 == idx)
def test_dictionary_get_items_without_unk():
dictionary: Dictionary = Dictionary(add_unk=False)
dictionary.add_item('class_1')
dictionary.add_item('class_2')
dictionary.add_item('class_3')
items = dictionary.get_items()
assert (3 == len(items))
assert ('class_1' == items[0])
assert ('class_2' == items[1])
assert ('class_3' == items[2])
def test_dictionary_get_items_with_unk():
dictionary: Dictionary = Dictionary()
dictionary.add_item('class_1')
dictionary.add_item('class_2')
dictionary.add_item('class_3')
items = dictionary.get_items()
assert (4 == len(items))
assert ('<unk>' == items[0])
assert ('class_1' == items[1])
assert ('class_2' == items[2])
assert ('class_3' == items[3])
def init():
y_true = [[0, 1, 1], [0, 0, 1], [1, 1, 0]]
y_pred = [[0, 1, 1], [0, 0, 0], [1, 0, 0]]
labels = Dictionary(add_unk=False)
labels.add_item('class-1')
labels.add_item('class-2')
labels.add_item('class-3')
return y_true, y_pred, labels
def test_dictionary_save_and_load():
dictionary: Dictionary = Dictionary(add_unk=False)
dictionary.add_item('class_1')
dictionary.add_item('class_2')
dictionary.add_item('class_3')
file_path = 'dictionary.txt'
dictionary.save(file_path)
loaded_dictionary = dictionary.load_from_file(file_path)
assert (len(dictionary) == len(loaded_dictionary))
assert (len(dictionary.get_items()) == len(loaded_dictionary.get_items()))
# clean up file
os.remove(file_path)
def convert_labels_to_one_hot(label_list: List[List[str]],
label_dict: Dictionary) -> List[List[int]]:
"""
Convert list of labels (strings) to a one hot list.
:param label_list: list of labels
:param label_dict: label dictionary
:return: converted label list
"""
converted_label_list = []
for labels in label_list:
arr = np.empty(len(label_dict))
arr.fill(0)
for label in labels:
arr[label_dict.get_idx_for_item(label)] = 1
converted_label_list.append(arr.tolist())
return converted_label_list