stanza 1.6.0 failing IT on linux
RichJackson opened this issue · comments
Richard Jackson commented
...although passing on Mac.
kazu/utils/stanza_pipeline.py:19: in simple_stanza_init
stanza_pipeline = stanza.Pipeline(
/tmp/kazu-env/lib/python3.9/site-packages/stanza/pipeline/core.py:235: in __init__
self.load_list = maintain_processor_list(resources, lang, package, processors, maybe_add_mwt=(not kwargs.get("tokenize_pretokenized")))
/tmp/kazu-env/lib/python3.9/site-packages/stanza/resources/common.py:208: in maintain_processor_list
add_mwt(processors, resources, lang)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
processors = {'tokenize': 'genia'}
resources = {'af': {'backward_charlm': {'oscar': {'md5': 'af65d719157609173ed04bd6208fc2ae'}}, 'default_dependencies': {'depparse'...b4d7ab922', 'default_processors': {'depparse': 'padt', 'lemma': 'padt', 'mwt': 'padt', 'ner': 'aqmar', ...}, ...}, ...}
lang = 'en'
def add_mwt(processors, resources, lang):
"""Add mwt if tokenize is passed without mwt.
If tokenize is in the list, but mwt is not, and there is a corresponding
tokenize and mwt pair in the resources file, mwt is added so no missing
mwt errors are raised.
TODO: how does this handle EWT in English?
"""
value = processors[TOKENIZE]
> if value in resources[lang][PACKAGES] and MWT in resources[lang][PACKAGES][value]:
E KeyError: 'packages'
/tmp/kazu-env/lib/python3.9/site-packages/stanza/resources/common.py:184: KeyError
The above exception was the direct cause of the following exception:
kazu_test_config = {'ray': {'init': {'_target_': 'ray.init', 'address': None, 'namespace': 'serve', 'num_cpus': None, 'object_store_memor.../github/runner/kazu/kazu/temp_model_pack_test_dir_16816/kazu_model_pack_public/ontologies/global_parser_actions.json'}}
@requires_model_pack
def test_equivalent_to_explosion_for_simple_sents(kazu_test_config):
> st_step: Step = instantiate(kazu_test_config.StanzaStep)
kazu/tests/test_sentence_segmentation.py:53: