From 558a6ef001a1e60522e4f69867c48bc8cc0d8ea4 Mon Sep 17 00:00:00 2001 From: Mario Graff Date: Thu, 2 Oct 2025 11:38:07 -0500 Subject: [PATCH] Default parameters --- dialectid/__init__.py | 2 +- dialectid/model.py | 4 ++-- dialectid/tests/test_model.py | 10 +++++----- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/dialectid/__init__.py b/dialectid/__init__.py index f9bc42d..79291f3 100644 --- a/dialectid/__init__.py +++ b/dialectid/__init__.py @@ -20,7 +20,7 @@ # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE # SOFTWARE. -__version__ = '0.1.7' +__version__ = '0.2.0' # from dialectid.text_repr import BoW, SeqTM from dialectid.model import DialectId, BoW diff --git a/dialectid/model.py b/dialectid/model.py index 23e8975..1906a02 100644 --- a/dialectid/model.py +++ b/dialectid/model.py @@ -51,12 +51,12 @@ def download(self, first: bool=True): @dataclass class DialectId(EncExpT): """DialectId""" - token_max_filter: int=int(2**19) + token_max_filter: int=2**19 del_diac: bool=True with_intercept: bool=True probability: bool=False uniform_distribution: bool=True - max_pos: int=False + max_pos: int=2**19 def identifier_filter(self, key, value): """Test default parameters""" diff --git a/dialectid/tests/test_model.py b/dialectid/tests/test_model.py index 70838f2..2552402 100644 --- a/dialectid/tests/test_model.py +++ b/dialectid/tests/test_model.py @@ -70,7 +70,7 @@ def test_DialectId_predict_2cl(): def test_DialectId_download(): """Test DialectId download""" - dialectid = DialectId(lang='es', token_max_filter=2**17) + dialectid = DialectId(lang='es') dialectid.weights assert len(dialectid.names) == 21 @@ -92,8 +92,8 @@ def test_DialectId_probability(): _ = enc._lr.predict_proba(X) assert_almost_equal(_, hy) enc2 = DialectId(lang='es', - pretrained=False, - probability=True) + pretrained=False, + probability=True) enc2.set_weights(tweet_iterator('tailored_intercept2.json.gz')) assert_almost_equal(enc._lr[1].coef_.T, enc2.proba_coefs[0]) assert_almost_equal(enc._lr[1].intercept_, enc2.proba_coefs[1]) @@ -121,8 +121,8 @@ def test_DialectId_probability_2cl(): assert_almost_equal(_, hy) assert_almost_equal(hy[0].sum(), 1) enc2 = DialectId(lang='es', - pretrained=False, - probability=True) + pretrained=False, + probability=True) enc2.set_weights(tweet_iterator('tailored_intercept2.json.gz')) assert_almost_equal(enc._lr[1].coef_[0], enc2.proba_coefs[0]) assert_almost_equal(enc._lr[1].intercept_, enc2.proba_coefs[1])