spaCy/spacy/tests/regression/test_issue3611.py
Ines Montani db55577c45
Drop Python 2.7 and 3.5 (#4828)
* Remove unicode declarations

* Remove Python 3.5 and 2.7 from CI

* Don't require pathlib

* Replace compat helpers

* Remove OrderedDict

* Use f-strings

* Set Cython compiler language level

* Fix typo

* Re-add OrderedDict for Table

* Update setup.cfg

* Revert CONTRIBUTING.md

* Revert lookups.md

* Revert top-level.md

* Small adjustments and docs [ci skip]
2019-12-22 01:53:56 +01:00

47 lines
1.4 KiB
Python

import spacy
from spacy.util import minibatch, compounding
def test_issue3611():
""" Test whether adding n-grams in the textcat works even when n > token length of some docs """
unique_classes = ["offensive", "inoffensive"]
x_train = [
"This is an offensive text",
"This is the second offensive text",
"inoff",
]
y_train = ["offensive", "offensive", "inoffensive"]
# preparing the data
pos_cats = list()
for train_instance in y_train:
pos_cats.append({label: label == train_instance for label in unique_classes})
train_data = list(zip(x_train, [{"cats": cats} for cats in pos_cats]))
# set up the spacy model with a text categorizer component
nlp = spacy.blank("en")
textcat = nlp.create_pipe(
"textcat",
config={"exclusive_classes": True, "architecture": "bow", "ngram_size": 2},
)
for label in unique_classes:
textcat.add_label(label)
nlp.add_pipe(textcat, last=True)
# training the network
with nlp.disable_pipes([p for p in nlp.pipe_names if p != "textcat"]):
optimizer = nlp.begin_training()
for i in range(3):
losses = {}
batches = minibatch(train_data, size=compounding(4.0, 32.0, 1.001))
for batch in batches:
nlp.update(
examples=batch,
sgd=optimizer,
drop=0.1,
losses=losses,
)