def setUp(self):
"""
Constructs the data and reads in the embeddings from the example data in the test_data directory
"""
test_data_dir = Path(__file__).resolve().parents[1]
embeddings_file = str(
test_data_dir.joinpath("test_data").joinpath("embeddings.txt"))
train_dataset = str(
test_data_dir.joinpath("test_data").joinpath("train_data.txt"))
self._unknown_word_key = "<unk>"
word_embeddings = data.read_word_embeddings(embeddings_file,
self._unknown_word_key)
self._word_index = word_embeddings.wv.vocab
self._db = data.generate_instances(
batch_size=3,
file_path=train_dataset,
word_index=self._word_index,
unknown_word_key=self._unknown_word_key,
separator=" ")
self._mh_index_map, self._unk_matrix_id = matrix_mapping.create_matrix_mapping(
train_mh=self._db.mh_set, unk_vec_id=self._db.unk_vector_id)
self._lookup = word_embeddings.wv.syn0
tf.set_random_seed(1)
def setUp(self):
test_data_dir = Path(__file__).resolve().parents[1]
embeddings_file = str(test_data_dir.joinpath("test_data").joinpath("embeddings.txt"))
self._predictions_file = str(test_data_dir.joinpath("test_data").joinpath("gold_standard.txt"))
self._unknown_word_key = "<unk>"
self._word_embeddings = data.read_word_embeddings(embeddings_file, self._unknown_word_key)
def setUp(self):
test_data_dir = Path(__file__).resolve().parents[1]
embeddings_file = str(
test_data_dir.joinpath("test_data").joinpath("embeddings.txt"))
self._train_dataset = str(
test_data_dir.joinpath("test_data").joinpath("train_data.txt"))
self._validation_dataset = str(
test_data_dir.joinpath("test_data").joinpath("valid_data.txt"))
self._unknown_word_key = "<unk>"
self._separator = " "
gensim_model = data.read_word_embeddings(embeddings_file,
self._unknown_word_key)
self._word_index = gensim_model.wv.vocab
def setUp(self):
"""
This sets up the data and properties (e.g. embedding dimension, batch size) all models are built on. These properties
are fixed and the same for all test classes inheriting from this class.
"""
self._test_data_dir = Path(__file__).resolve().parents[1]
embeddings_file = str(
self._test_data_dir.joinpath("test_data").joinpath(
"embeddings.txt"))
train_dataset = str(
self._test_data_dir.joinpath("test_data").joinpath(
"train_data.txt"))
validation_dataset = str(
self._test_data_dir.joinpath("test_data").joinpath(
"valid_data.txt"))
self._unknown_word_key = "<unk>"
self._embedding_model = data.read_word_embeddings(
embeddings_file, self._unknown_word_key)
self._word_index = self._embedding_model.wv.vocab
self._lookup = self._embedding_model.wv.syn0
self._embedding_dim = self._lookup.shape[1]
self._batch_size = 3
self._db = data.generate_instances(
batch_size=self._batch_size,
file_path=train_dataset,
word_index=self._word_index,
unknown_word_key=self._unknown_word_key,
separator=" ")
self._vd = data.generate_instances(
batch_size=self._batch_size,
file_path=validation_dataset,
word_index=self._word_index,
unknown_word_key=self._unknown_word_key,
separator=" ")
self._comp_model = None
"--unknown_word_key",
type=str,
help=
"string corresponding to the unknown word embedding in the embedding file",
default="<unk>")
parser.add_argument("--max_rank",
type=int,
help="maximum rank",
default=1000)
parser.add_argument("--batch_size",
type=int,
help="how many instances per batch",
default=500)
args = parser.parse_args()
embeddings = data.read_word_embeddings(args.embeddings,
args.unknown_word_key)
ranks = get_all_ranks(predictions_file=args.predictions,
word_embeddings=embeddings,
max_rank=args.max_rank,
batch_size=args.batch_size,
path_to_ranks=args.ranks)
print("ranks\n")
print(sorted(ranks))
print("quartiles\n")
print(evaluation.calculate_quartiles(ranks))
tf.enable_eager_execution()
loss = evaluation.get_loss(predictions_file=args.predictions, word_embeddings=embeddings, \
batch_size=args.batch_size)
print("loss %.5f\n" % loss)