explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-15 10:42:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

formatting

Browse Source
This commit is contained in:
vinit 2023-02-17 10:26:29 +05:30
parent d7406fffb0
commit e48a662e46
2 changed files with 12 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/cli/debug_data.py
View File

@ -526,8 +526,8 @@ def debug_data(
msg.info(f"{len(label_list)} label(s) in train data")
p = np.array(counts)
p = p / p.sum()
entropy = np.round((-p*np.log2(p)).sum(), 2)
msg.info(f"{entropy} is the train data label entropy")
norm_entropy = (-p * np.log2(p)).sum() / np.log2(len(label_list))
msg.info(f"{norm_entropy} is the normalised label entropy")
model_labels = _get_labels_from_model(nlp, "tagger")
labels = set(label_list)
missing_labels = model_labels - labels

13
spacy/tests/pipeline/test_tagger.py
View File

@ -70,8 +70,12 @@ PARTIAL_DATA = [
def test_label_smoothing():
util.fix_random_seed()
nlp = Language()
tagger_no_ls = nlp.add_pipe("tagger", "no_label_smoothing", config=dict(label_smoothing=False))
tagger_ls = nlp.add_pipe("tagger", "label_smoothing", config=dict(label_smoothing=True))
tagger_no_ls = nlp.add_pipe(
"tagger", "no_label_smoothing", config=dict(label_smoothing=False)
)
tagger_ls = nlp.add_pipe(
"tagger", "label_smoothing", config=dict(label_smoothing=True)
)
train_examples = []
losses = {}
for tag in TAGS:
@ -83,7 +87,10 @@ def test_label_smoothing():
for i in range(5):
losses = {}
nlp.update(train_examples, sgd=optimizer, losses=losses)
assert losses == {'no_label_smoothing': 1.4892945885658264, 'label_smoothing': 1.1432453989982605}
assert losses == {
"no_label_smoothing": 1.4892945885658264,
"label_smoothing": 1.1432453989982605,
}
def test_no_label():