def test_text_classifier_param_selector(results_base_path, tasks_base_path):
corpus = NLPTaskDataFetcher.load_corpus(u'imdb', base_path=tasks_base_path)
glove_embedding = WordEmbeddings(u'en-glove')
search_space = SearchSpace()
search_space.add(Parameter.EMBEDDINGS,
hp.choice,
options=[[glove_embedding]])
search_space.add(Parameter.HIDDEN_SIZE,
hp.choice,
options=[64, 128, 256, 512])
search_space.add(Parameter.RNN_LAYERS, hp.choice, options=[1, 2])
search_space.add(Parameter.REPROJECT_WORDS,
hp.choice,
options=[True, False])
search_space.add(Parameter.REPROJECT_WORD_DIMENSION,
hp.choice,
options=[64, 128])
search_space.add(Parameter.BIDIRECTIONAL, hp.choice, options=[True, False])
search_space.add(Parameter.DROPOUT, hp.uniform, low=0.25, high=0.75)
search_space.add(Parameter.WORD_DROPOUT, hp.uniform, low=0.25, high=0.75)
search_space.add(Parameter.LOCKED_DROPOUT, hp.uniform, low=0.25, high=0.75)
search_space.add(Parameter.LEARNING_RATE, hp.uniform, low=0, high=1)
search_space.add(Parameter.MINI_BATCH_SIZE,
hp.choice,
options=[4, 8, 16, 32])
search_space.add(Parameter.ANNEAL_FACTOR, hp.uniform, low=0, high=0.75)
search_space.add(Parameter.PATIENCE, hp.choice, options=[3, 5])
param_selector = TextClassifierParamSelector(
corpus,
False,
results_base_path,
document_embedding_type=u'lstm',
max_epochs=2)
param_selector.optimize(search_space, max_evals=2)
shutil.rmtree(results_base_path)
def test_text_classifier_param_selector(results_base_path, tasks_base_path):
corpus = flair.datasets.ClassificationCorpus(tasks_base_path / "imdb")
search_space = SearchSpace()
# document embeddings parameter
search_space.add(Parameter.EMBEDDINGS, hp.choice, options=[[glove_embedding]])
search_space.add(Parameter.HIDDEN_SIZE, hp.choice, options=[64, 128, 256, 512])
search_space.add(Parameter.RNN_LAYERS, hp.choice, options=[1, 2])
search_space.add(Parameter.REPROJECT_WORDS, hp.choice, options=[True, False])
search_space.add(Parameter.REPROJECT_WORD_DIMENSION, hp.choice, options=[64, 128])
search_space.add(Parameter.BIDIRECTIONAL, hp.choice, options=[True, False])
search_space.add(Parameter.DROPOUT, hp.uniform, low=0.25, high=0.75)
search_space.add(Parameter.WORD_DROPOUT, hp.uniform, low=0.25, high=0.75)
search_space.add(Parameter.LOCKED_DROPOUT, hp.uniform, low=0.25, high=0.75)
# training parameter
search_space.add(Parameter.LEARNING_RATE, hp.uniform, low=0, high=1)
search_space.add(Parameter.MINI_BATCH_SIZE, hp.choice, options=[4, 8, 16, 32])
search_space.add(Parameter.ANNEAL_FACTOR, hp.uniform, low=0, high=0.75)
search_space.add(Parameter.PATIENCE, hp.choice, options=[3, 5])
param_selector = TextClassifierParamSelector(
corpus, False, results_base_path, document_embedding_type="lstm", max_epochs=2
)
param_selector.optimize(search_space, max_evals=2)
# clean up results directory
shutil.rmtree(results_base_path)
del param_selector, search_space
def test_text_classifier_param_selector(results_base_path, tasks_base_path):
corpus = flair.datasets.ClassificationCorpus(tasks_base_path / "imdb")
label_type = "sentiment"
search_space = SearchSpace()
# document embeddings parameter
search_space.add(Parameter.TRANSFORMER_MODEL,
hp.choice,
options=["albert-base-v1"])
search_space.add(Parameter.LAYERS, hp.choice, options=["-1", "-2"])
# training parameter
search_space.add(Parameter.LEARNING_RATE, hp.uniform, low=0, high=1)
search_space.add(Parameter.MINI_BATCH_SIZE,
hp.choice,
options=[4, 8, 16, 32])
search_space.add(Parameter.ANNEAL_FACTOR, hp.uniform, low=0, high=0.75)
search_space.add(Parameter.PATIENCE, hp.choice, options=[3, 5])
param_selector = TextClassifierParamSelector(corpus,
label_type,
False,
results_base_path,
max_epochs=2)
param_selector.optimize(search_space, max_evals=2)
# clean up results directory
shutil.rmtree(results_base_path)
del param_selector, search_space