spaCy/spacy/tests/doc/test_span.py
Álvaro Abella Bascarán e03e1eee92 Bugfix/get lca matrix (#3110)
This PR adds a test for an untested case of `Span.get_lca_matrix`, and fixes a bug for that scenario, which I introduced in [this PR](https://github.com/explosion/spaCy/pull/3089) (sorry!).

## Description
The previous implementation of get_lca_matrix was failing for the case `doc[j:k].get_lca_matrix()` where `j > 0`. A test has been added for this case and the bug has been fixed.

### Types of change
Bug fix

## Checklist

- [x] I have submitted the spaCy Contributor Agreement.
- [x] I ran the tests, and all new and existing tests passed.
- [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
2019-01-06 19:07:50 +01:00

178 lines
5.8 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
from ..util import get_doc
from ...attrs import ORTH, LENGTH
from ...tokens import Doc
from ...vocab import Vocab
import pytest
@pytest.fixture
def doc(en_tokenizer):
text = "This is a sentence. This is another sentence. And a third."
heads = [1, 0, 1, -2, -3, 1, 0, 1, -2, -3, 0, 1, -2, -1]
deps = ['nsubj', 'ROOT', 'det', 'attr', 'punct', 'nsubj', 'ROOT', 'det',
'attr', 'punct', 'ROOT', 'det', 'npadvmod', 'punct']
tokens = en_tokenizer(text)
return get_doc(tokens.vocab, [t.text for t in tokens], heads=heads, deps=deps)
def test_spans_sent_spans(doc):
sents = list(doc.sents)
assert sents[0].start == 0
assert sents[0].end == 5
assert len(sents) == 3
assert sum(len(sent) for sent in sents) == len(doc)
def test_spans_root(doc):
span = doc[2:4]
assert len(span) == 2
assert span.text == 'a sentence'
assert span.root.text == 'sentence'
assert span.root.head.text == 'is'
def test_spans_string_fn(doc):
span = doc[0:4]
assert len(span) == 4
assert span.text == 'This is a sentence'
assert span.upper_ == 'THIS IS A SENTENCE'
assert span.lower_ == 'this is a sentence'
def test_spans_root2(en_tokenizer):
text = "through North and South Carolina"
heads = [0, 3, -1, -2, -4]
tokens = en_tokenizer(text)
doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads)
assert doc[-2:].root.text == 'Carolina'
def test_spans_span_sent(doc):
"""Test span.sent property"""
assert len(list(doc.sents))
assert doc[:2].sent.root.text == 'is'
assert doc[:2].sent.text == 'This is a sentence .'
assert doc[6:7].sent.root.left_edge.text == 'This'
def test_spans_lca_matrix(en_tokenizer):
"""Test span's lca matrix generation"""
tokens = en_tokenizer('the lazy dog slept')
doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=[2, 1, 1, 0])
lca = doc[:2].get_lca_matrix()
assert lca.shape == (2, 2)
assert lca[0, 0] == 0 # the & the -> the
assert lca[0, 1] == -1 # the & lazy -> dog (out of span)
assert lca[1, 0] == -1 # lazy & the -> dog (out of span)
assert lca[1, 1] == 1 # lazy & lazy -> lazy
lca = doc[1:].get_lca_matrix()
assert lca.shape == (3, 3)
assert lca[0, 0] == 0 # lazy & lazy -> lazy
assert lca[0, 1] == 1 # lazy & dog -> dog
assert lca[0, 2] == 2 # lazy & slept -> slept
lca = doc[2:].get_lca_matrix()
assert lca.shape == (2, 2)
assert lca[0, 0] == 0 # dog & dog -> dog
assert lca[0, 1] == 1 # dog & slept -> slept
assert lca[1, 0] == 1 # slept & dog -> slept
assert lca[1, 1] == 1 # slept & slept -> slept
def test_span_similarity_match():
doc = Doc(Vocab(), words=['a', 'b', 'a', 'b'])
span1 = doc[:2]
span2 = doc[2:]
assert span1.similarity(span2) == 1.0
assert span1.similarity(doc) == 0.0
assert span1[:1].similarity(doc.vocab['a']) == 1.0
def test_spans_default_sentiment(en_tokenizer):
"""Test span.sentiment property's default averaging behaviour"""
text = "good stuff bad stuff"
tokens = en_tokenizer(text)
tokens.vocab[tokens[0].text].sentiment = 3.0
tokens.vocab[tokens[2].text].sentiment = -2.0
doc = get_doc(tokens.vocab, [t.text for t in tokens])
assert doc[:2].sentiment == 3.0 / 2
assert doc[-2:].sentiment == -2. / 2
assert doc[:-1].sentiment == (3.+-2) / 3.
def test_spans_override_sentiment(en_tokenizer):
"""Test span.sentiment property's default averaging behaviour"""
text = "good stuff bad stuff"
tokens = en_tokenizer(text)
tokens.vocab[tokens[0].text].sentiment = 3.0
tokens.vocab[tokens[2].text].sentiment = -2.0
doc = get_doc(tokens.vocab, [t.text for t in tokens])
doc.user_span_hooks['sentiment'] = lambda span: 10.0
assert doc[:2].sentiment == 10.0
assert doc[-2:].sentiment == 10.0
assert doc[:-1].sentiment == 10.0
def test_spans_are_hashable(en_tokenizer):
"""Test spans can be hashed."""
text = "good stuff bad stuff"
tokens = en_tokenizer(text)
span1 = tokens[:2]
span2 = tokens[2:4]
assert hash(span1) != hash(span2)
span3 = tokens[0:2]
assert hash(span3) == hash(span1)
def test_spans_by_character(doc):
span1 = doc[1:-2]
span2 = doc.char_span(span1.start_char, span1.end_char, label='GPE')
assert span1.start_char == span2.start_char
assert span1.end_char == span2.end_char
assert span2.label_ == 'GPE'
def test_span_to_array(doc):
span = doc[1:-2]
arr = span.to_array([ORTH, LENGTH])
assert arr.shape == (len(span), 2)
assert arr[0, 0] == span[0].orth
assert arr[0, 1] == len(span[0])
def test_span_as_doc(doc):
span = doc[4:10]
span_doc = span.as_doc()
assert span.text == span_doc.text.strip()
def test_span_ents_property(doc):
"""Test span.ents for the """
doc.ents = [
(doc.vocab.strings['PRODUCT'], 0, 1),
(doc.vocab.strings['PRODUCT'], 7, 8),
(doc.vocab.strings['PRODUCT'], 11, 14)
]
assert len(list(doc.ents)) == 3
sentences = list(doc.sents)
assert len(sentences) == 3
assert len(sentences[0].ents) == 1
# First sentence, also tests start of sentence
assert sentences[0].ents[0].text == "This"
assert sentences[0].ents[0].label_ == "PRODUCT"
assert sentences[0].ents[0].start == 0
assert sentences[0].ents[0].end == 1
# Second sentence
assert len(sentences[1].ents) == 1
assert sentences[1].ents[0].text == "another"
assert sentences[1].ents[0].label_ == "PRODUCT"
assert sentences[1].ents[0].start == 7
assert sentences[1].ents[0].end == 8
# Third sentence ents, Also tests end of sentence
assert sentences[2].ents[0].text == "a third ."
assert sentences[2].ents[0].label_ == "PRODUCT"
assert sentences[2].ents[0].start == 11
assert sentences[2].ents[0].end == 14