explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-01 00:17:44 +03:00
Code Issues Packages Projects Releases Wiki Activity

rm unclear uniqueness check

Browse Source
This commit is contained in:
Peter Baumgartner 2023-01-23 09:35:38 -05:00
parent 4c45dfabae
commit 6ea2b3524b
2 changed files with 0 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
spacy/cli/debug_data.py
View File

@ -693,18 +693,6 @@ def debug_data(
# and we might actually want a warning?
msg.info("All trees in dev data present in training data.")
if gold_train_data["n_low_cardinality_lemmas"] > 0:
n = gold_train_data["n_low_cardinality_lemmas"]
msg.warn(f"{n} docs with 1 or 0 unique lemmas.")
else:
msg.good("All training docs meet lemma uniqueness requirements.")
if gold_dev_data["n_low_cardinality_lemmas"] > 0:
n = gold_dev_data["n_low_cardinality_lemmas"]
msg.warn(f"{n} docs with 1 or 0 unique lemmas.")
else:
msg.good("All dev docs meet lemma uniqueness requirements.")
if gold_train_data["no_lemma_annotations"] > 0:
n = gold_train_data["no_lemma_annotations"]
msg.warn(f"{n} docs with no lemma annotations.")
@ -793,7 +781,6 @@ def _compile_gold(
"lemmatizer_trees": set(),
"no_lemma_annotations": 0,
"partial_lemma_annotations": 0,
"n_low_cardinality_lemmas": 0,
}
if "trainable_lemmatizer" in factory_names:
trees = EditTrees(nlp.vocab.strings)
@ -933,18 +920,11 @@ def _compile_gold(
continue
if any(token.lemma == 0 for token in gold):
data["partial_lemma_annotations"] += 1
lemma_set = set()
for token in gold:
if token.lemma != 0:
lemma_set.add(token.lemma)
tree_id = trees.add(token.text, token.lemma_)
tree_str = trees.tree_to_str(tree_id)
data["lemmatizer_trees"].add(tree_str)
# We want to identify cases where lemmas aren't assigned
# or are all assigned the same value, as this would indicate
# an issue since we're expecting a large set of lemmas
if len(lemma_set) < 2 and len(gold) > 1:
data["n_low_cardinality_lemmas"] += 1
return data

13
spacy/tests/test_cli.py
View File

@ -1244,19 +1244,6 @@ def test_debug_data_trainable_lemmatizer_partial():
data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
assert data["partial_lemma_annotations"] == 2
def test_debug_data_trainable_lemmatizer_low_cardinality():
low_cardinality_examples = [
("She likes green eggs", {"lemmas": ["no", "no", "no", "no"]}),
("Eat blue ham", {"lemmas": ["no", "no", "no"]}),
]
nlp = Language()
train_examples = []
for t in low_cardinality_examples:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
assert data["n_low_cardinality_lemmas"] == 2
def test_debug_data_trainable_lemmatizer_not_annotated():
unannotated_examples = [
("She likes green eggs", {}),