mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 13:17:06 +03:00
c1ea55307b
* Add initial reproducibility tests * failing test for default_text_classifier (WIP) * track trouble to underlying tok2vec layer * add regression test for Issue 5551 * tests go green with https://github.com/explosion/thinc/pull/359 * update test * adding fixed seeds to HashEmbed layers, seems to fix the reproducility issue Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
32 lines
1.1 KiB
Python
32 lines
1.1 KiB
Python
from spacy.lang.en import English
|
|
from spacy.util import fix_random_seed
|
|
|
|
|
|
def test_issue5551():
|
|
"""Test that after fixing the random seed, the results of the pipeline are truly identical"""
|
|
component = "textcat"
|
|
pipe_cfg = {"exclusive_classes": False}
|
|
|
|
results = []
|
|
for i in range(3):
|
|
fix_random_seed(0)
|
|
nlp = English()
|
|
example = (
|
|
"Once hot, form ping-pong-ball-sized balls of the mixture, each weighing roughly 25 g.",
|
|
{"cats": {"Labe1": 1.0, "Label2": 0.0, "Label3": 0.0}},
|
|
)
|
|
nlp.add_pipe(nlp.create_pipe(component, config=pipe_cfg), last=True)
|
|
pipe = nlp.get_pipe(component)
|
|
for label in set(example[1]["cats"]):
|
|
pipe.add_label(label)
|
|
nlp.begin_training(component_cfg={component: pipe_cfg})
|
|
|
|
# Store the result of each iteration
|
|
result = pipe.model.predict([nlp.make_doc(example[0])])
|
|
results.append(list(result[0]))
|
|
|
|
# All results should be the same because of the fixed seed
|
|
assert len(results) == 3
|
|
assert results[0] == results[1]
|
|
assert results[0] == results[2]
|