2017-01-12 14:30:49 +00:00
|
|
|
# coding: utf-8
|
2015-04-07 02:52:25 +00:00
|
|
|
from __future__ import unicode_literals
|
2017-01-12 14:30:49 +00:00
|
|
|
|
|
|
|
from ..util import get_doc
|
2017-08-19 14:24:38 +00:00
|
|
|
from ...attrs import ORTH, LENGTH
|
2015-04-07 02:52:25 +00:00
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture
|
2017-01-12 14:30:49 +00:00
|
|
|
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)
|
2015-04-07 02:52:25 +00:00
|
|
|
|
|
|
|
|
2017-01-12 14:30:49 +00:00
|
|
|
def test_spans_sent_spans(doc):
|
2015-04-07 02:52:25 +00:00
|
|
|
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)
|
2015-07-09 15:30:58 +00:00
|
|
|
|
|
|
|
|
2017-01-12 14:30:49 +00:00
|
|
|
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'
|
2016-01-16 15:19:09 +00:00
|
|
|
|
2017-03-11 00:50:02 +00:00
|
|
|
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'
|
2016-01-16 15:19:09 +00:00
|
|
|
|
2017-01-12 14:30:49 +00:00
|
|
|
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'
|
2016-05-05 22:17:38 +00:00
|
|
|
|
|
|
|
|
2017-01-12 14:30:49 +00:00
|
|
|
def test_spans_span_sent(doc):
|
|
|
|
"""Test span.sent property"""
|
2016-05-05 22:17:38 +00:00
|
|
|
assert len(list(doc.sents))
|
2017-01-12 14:30:49 +00:00
|
|
|
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'
|
|
|
|
|
|
|
|
|
2017-10-20 18:28:00 +00:00
|
|
|
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[0, 0] == 0)
|
|
|
|
assert(lca[0, 1] == -1)
|
|
|
|
assert(lca[1, 0] == -1)
|
|
|
|
assert(lca[1, 1] == 1)
|
|
|
|
|
|
|
|
|
2017-01-12 14:30:49 +00:00
|
|
|
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])
|
2016-12-02 10:05:50 +00:00
|
|
|
doc.user_span_hooks['sentiment'] = lambda span: 10.0
|
2017-01-12 14:30:49 +00:00
|
|
|
assert doc[:2].sentiment == 10.0
|
|
|
|
assert doc[-2:].sentiment == 10.0
|
|
|
|
assert doc[:-1].sentiment == 10.0
|
2017-04-26 17:01:05 +00:00
|
|
|
|
|
|
|
|
|
|
|
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)
|
2017-10-24 13:27:29 +00:00
|
|
|
|
2017-08-19 14:18:23 +00:00
|
|
|
|
|
|
|
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'
|
2017-08-19 14:24:38 +00:00
|
|
|
|
|
|
|
|
|
|
|
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])
|
|
|
|
|