spaCy/spacy/tests/parser/test_nonproj.py

156 lines
5.7 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import pytest
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
from spacy.syntax.nonproj import ancestors, contains_cycle, is_nonproj_arc
from spacy.syntax.nonproj import is_nonproj_tree
from spacy.syntax import nonproj
from ..util import get_doc
@pytest.fixture
def tree():
return [1, 2, 2, 4, 5, 2, 2]
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
@pytest.fixture
def cyclic_tree():
return [1, 2, 2, 4, 5, 3, 2]
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
@pytest.fixture
def partial_tree():
return [1, 2, 2, 4, 5, None, 7, 4, 2]
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
@pytest.fixture
def nonproj_tree():
return [1, 2, 2, 4, 5, 2, 7, 4, 2]
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
@pytest.fixture
def proj_tree():
return [1, 2, 2, 4, 5, 2, 7, 5, 2]
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
@pytest.fixture
def multirooted_tree():
return [3, 2, 0, 3, 3, 7, 7, 3, 7, 10, 7, 10, 11, 12, 18, 16, 18, 17, 12, 3]
def test_parser_ancestors(tree, cyclic_tree, partial_tree, multirooted_tree):
assert [a for a in ancestors(3, tree)] == [4, 5, 2]
assert [a for a in ancestors(3, cyclic_tree)] == [4, 5, 3, 4, 5, 3, 4]
assert [a for a in ancestors(3, partial_tree)] == [4, 5, None]
assert [a for a in ancestors(17, multirooted_tree)] == []
def test_parser_contains_cycle(tree, cyclic_tree, partial_tree, multirooted_tree):
2018-11-30 19:43:08 +03:00
assert contains_cycle(tree) is None
assert contains_cycle(cyclic_tree) == set([3, 4, 5])
2018-11-30 19:43:08 +03:00
assert contains_cycle(partial_tree) is None
assert contains_cycle(multirooted_tree) is None
def test_parser_is_nonproj_arc(nonproj_tree, partial_tree, multirooted_tree):
2018-11-30 19:43:08 +03:00
assert is_nonproj_arc(0, nonproj_tree) is False
assert is_nonproj_arc(1, nonproj_tree) is False
assert is_nonproj_arc(2, nonproj_tree) is False
assert is_nonproj_arc(3, nonproj_tree) is False
assert is_nonproj_arc(4, nonproj_tree) is False
assert is_nonproj_arc(5, nonproj_tree) is False
assert is_nonproj_arc(6, nonproj_tree) is False
assert is_nonproj_arc(7, nonproj_tree) is True
assert is_nonproj_arc(8, nonproj_tree) is False
assert is_nonproj_arc(7, partial_tree) is False
assert is_nonproj_arc(17, multirooted_tree) is False
assert is_nonproj_arc(16, multirooted_tree) is True
def test_parser_is_nonproj_tree(
proj_tree, nonproj_tree, partial_tree, multirooted_tree
):
2018-11-30 19:43:08 +03:00
assert is_nonproj_tree(proj_tree) is False
assert is_nonproj_tree(nonproj_tree) is True
assert is_nonproj_tree(partial_tree) is False
assert is_nonproj_tree(multirooted_tree) is True
def test_parser_pseudoprojectivity(en_tokenizer):
def deprojectivize(proj_heads, deco_labels):
tokens = en_tokenizer("whatever " * len(proj_heads))
rel_proj_heads = [head - i for i, head in enumerate(proj_heads)]
doc = get_doc(
tokens.vocab,
words=[t.text for t in tokens],
deps=deco_labels,
heads=rel_proj_heads,
)
2017-05-22 13:39:03 +03:00
nonproj.deprojectivize(doc)
return [t.head.i for t in doc], [token.dep_ for token in doc]
# fmt: off
tree = [1, 2, 2]
nonproj_tree = [1, 2, 2, 4, 5, 2, 7, 4, 2]
nonproj_tree2 = [9, 1, 3, 1, 5, 6, 9, 8, 6, 1, 6, 12, 13, 10, 1]
labels = ["det", "nsubj", "root", "det", "dobj", "aux", "nsubj", "acl", "punct"]
labels2 = ["advmod", "root", "det", "nsubj", "advmod", "det", "dobj", "det", "nmod", "aux", "nmod", "advmod", "det", "amod", "punct"]
# fmt: on
assert nonproj.decompose("X||Y") == ("X", "Y")
assert nonproj.decompose("X") == ("X", "")
2018-11-30 19:43:08 +03:00
assert nonproj.is_decorated("X||Y") is True
assert nonproj.is_decorated("X") is False
2017-05-22 13:39:03 +03:00
nonproj._lift(0, tree)
assert tree == [2, 2, 2]
assert nonproj._get_smallest_nonproj_arc(nonproj_tree) == 7
assert nonproj._get_smallest_nonproj_arc(nonproj_tree2) == 10
# fmt: off
2017-05-22 13:39:03 +03:00
proj_heads, deco_labels = nonproj.projectivize(nonproj_tree, labels)
assert proj_heads == [1, 2, 2, 4, 5, 2, 7, 5, 2]
assert deco_labels == ["det", "nsubj", "root", "det", "dobj", "aux",
"nsubj", "acl||dobj", "punct"]
deproj_heads, undeco_labels = deprojectivize(proj_heads, deco_labels)
assert deproj_heads == nonproj_tree
assert undeco_labels == labels
2017-05-22 13:39:03 +03:00
proj_heads, deco_labels = nonproj.projectivize(nonproj_tree2, labels2)
assert proj_heads == [1, 1, 3, 1, 5, 6, 9, 8, 6, 1, 9, 12, 13, 10, 1]
assert deco_labels == ["advmod||aux", "root", "det", "nsubj", "advmod",
"det", "dobj", "det", "nmod", "aux", "nmod||dobj",
"advmod", "det", "amod", "punct"]
deproj_heads, undeco_labels = deprojectivize(proj_heads, deco_labels)
assert deproj_heads == nonproj_tree2
assert undeco_labels == labels2
# if decoration is wrong such that there is no head with the desired label
# the structure is kept and the label is undecorated
proj_heads = [1, 2, 2, 4, 5, 2, 7, 5, 2]
deco_labels = ["det", "nsubj", "root", "det", "dobj", "aux", "nsubj",
"acl||iobj", "punct"]
deproj_heads, undeco_labels = deprojectivize(proj_heads, deco_labels)
assert deproj_heads == proj_heads
assert undeco_labels == ["det", "nsubj", "root", "det", "dobj", "aux",
"nsubj", "acl", "punct"]
# if there are two potential new heads, the first one is chosen even if
# it"s wrong
proj_heads = [1, 1, 3, 1, 5, 6, 9, 8, 6, 1, 9, 12, 13, 10, 1]
deco_labels = ["advmod||aux", "root", "det", "aux", "advmod", "det",
"dobj", "det", "nmod", "aux", "nmod||dobj", "advmod",
"det", "amod", "punct"]
deproj_heads, undeco_labels = deprojectivize(proj_heads, deco_labels)
assert deproj_heads == [3, 1, 3, 1, 5, 6, 9, 8, 6, 1, 6, 12, 13, 10, 1]
assert undeco_labels == ["advmod", "root", "det", "aux", "advmod", "det",
"dobj", "det", "nmod", "aux", "nmod", "advmod",
"det", "amod", "punct"]
# fmt: on