spaCy/spacy/tests/test_gold.py

457 lines
16 KiB
Python
Raw Normal View History

2017-01-12 22:39:18 +00:00
# coding: utf-8
from __future__ import unicode_literals
Fix Example details for train CLI / pipeline components (#4624) * Switch to train_dataset() function in train CLI * Fixes for pipe() methods in pipeline components * Don't clobber `examples` variable with `as_example` in pipe() methods * Remove unnecessary traversals of `examples` * Update Parser.pipe() for Examples * Add `as_examples` kwarg to `pipe()` with implementation to return `Example`s * Accept `Doc` or `Example` in `pipe()` with `_get_doc()` (copied from `Pipe`) * Fixes to Example implementation in spacy.gold * Move `make_projective` from an attribute of Example to an argument of `Example.get_gold_parses()` * Head of 0 are not treated as unset * Unset heads are set to self rather than `None` (which causes problems while projectivizing) * Check for `Doc` (not just not `None`) when creating GoldParses for pre-merged example * Don't clobber `examples` variable in `iter_gold_docs()` * Add/modify gold tests for handling projectivity * In JSON roundtrip compare results from `dev_dataset` rather than `train_dataset` to avoid projectivization (and other potential modifications) * Add test for projective train vs. nonprojective dev versions of the same `Doc` * Handle ignore_misaligned as arg rather than attr Move `ignore_misaligned` from an attribute of `Example` to an argument to `Example.get_gold_parses()`, which makes it parallel to `make_projective`. Add test with old and new align that checks whether `ignore_misaligned` errors are raised as expected (only for new align). * Remove unused attrs from gold.pxd Remove `ignore_misaligned` and `make_projective` from `gold.pxd` * Refer to Example.goldparse in iter_gold_docs() Use `Example.goldparse` in `iter_gold_docs()` instead of `Example.gold` because a `None` `GoldParse` is generated with ignore_misaligned and generating it on-the-fly can raise an unwanted AlignmentError * Update test for ignore_misaligned
2019-11-23 13:32:15 +00:00
import spacy
from spacy.errors import AlignmentError
from spacy.gold import biluo_tags_from_offsets, offsets_from_biluo_tags, Example, DocAnnotation
from spacy.gold import spans_from_biluo_tags, GoldParse, iob_to_biluo
from spacy.gold import GoldCorpus, docs_to_json, align
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 20:31:31 +00:00
from spacy.lang.en import English
Fix Example details for train CLI / pipeline components (#4624) * Switch to train_dataset() function in train CLI * Fixes for pipe() methods in pipeline components * Don't clobber `examples` variable with `as_example` in pipe() methods * Remove unnecessary traversals of `examples` * Update Parser.pipe() for Examples * Add `as_examples` kwarg to `pipe()` with implementation to return `Example`s * Accept `Doc` or `Example` in `pipe()` with `_get_doc()` (copied from `Pipe`) * Fixes to Example implementation in spacy.gold * Move `make_projective` from an attribute of Example to an argument of `Example.get_gold_parses()` * Head of 0 are not treated as unset * Unset heads are set to self rather than `None` (which causes problems while projectivizing) * Check for `Doc` (not just not `None`) when creating GoldParses for pre-merged example * Don't clobber `examples` variable in `iter_gold_docs()` * Add/modify gold tests for handling projectivity * In JSON roundtrip compare results from `dev_dataset` rather than `train_dataset` to avoid projectivization (and other potential modifications) * Add test for projective train vs. nonprojective dev versions of the same `Doc` * Handle ignore_misaligned as arg rather than attr Move `ignore_misaligned` from an attribute of `Example` to an argument to `Example.get_gold_parses()`, which makes it parallel to `make_projective`. Add test with old and new align that checks whether `ignore_misaligned` errors are raised as expected (only for new align). * Remove unused attrs from gold.pxd Remove `ignore_misaligned` and `make_projective` from `gold.pxd` * Refer to Example.goldparse in iter_gold_docs() Use `Example.goldparse` in `iter_gold_docs()` instead of `Example.gold` because a `None` `GoldParse` is generated with ignore_misaligned and generating it on-the-fly can raise an unwanted AlignmentError * Update test for ignore_misaligned
2019-11-23 13:32:15 +00:00
from spacy.syntax.nonproj import is_nonproj_tree
💫 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.
2018-07-24 21:38:44 +00:00
from spacy.tokens import Doc
from spacy.util import compounding, minibatch
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 20:31:31 +00:00
from .util import make_tempdir
import pytest
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 20:31:31 +00:00
import srsly
Fix Example details for train CLI / pipeline components (#4624) * Switch to train_dataset() function in train CLI * Fixes for pipe() methods in pipeline components * Don't clobber `examples` variable with `as_example` in pipe() methods * Remove unnecessary traversals of `examples` * Update Parser.pipe() for Examples * Add `as_examples` kwarg to `pipe()` with implementation to return `Example`s * Accept `Doc` or `Example` in `pipe()` with `_get_doc()` (copied from `Pipe`) * Fixes to Example implementation in spacy.gold * Move `make_projective` from an attribute of Example to an argument of `Example.get_gold_parses()` * Head of 0 are not treated as unset * Unset heads are set to self rather than `None` (which causes problems while projectivizing) * Check for `Doc` (not just not `None`) when creating GoldParses for pre-merged example * Don't clobber `examples` variable in `iter_gold_docs()` * Add/modify gold tests for handling projectivity * In JSON roundtrip compare results from `dev_dataset` rather than `train_dataset` to avoid projectivization (and other potential modifications) * Add test for projective train vs. nonprojective dev versions of the same `Doc` * Handle ignore_misaligned as arg rather than attr Move `ignore_misaligned` from an attribute of `Example` to an argument to `Example.get_gold_parses()`, which makes it parallel to `make_projective`. Add test with old and new align that checks whether `ignore_misaligned` errors are raised as expected (only for new align). * Remove unused attrs from gold.pxd Remove `ignore_misaligned` and `make_projective` from `gold.pxd` * Refer to Example.goldparse in iter_gold_docs() Use `Example.goldparse` in `iter_gold_docs()` instead of `Example.gold` because a `None` `GoldParse` is generated with ignore_misaligned and generating it on-the-fly can raise an unwanted AlignmentError * Update test for ignore_misaligned
2019-11-23 13:32:15 +00:00
@pytest.fixture
def doc():
text = "Sarah's sister flew to Silicon Valley via London."
tags = ['NNP', 'POS', 'NN', 'VBD', 'IN', 'NNP', 'NNP', 'IN', 'NNP', '.']
# head of '.' is intentionally nonprojective for testing
heads = [2, 0, 3, 3, 3, 6, 4, 3, 7, 5]
deps = ['poss', 'case', 'nsubj', 'ROOT', 'prep', 'compound', 'pobj', 'prep', 'pobj', 'punct']
biluo_tags = ["U-PERSON", "O", "O", "O", "O", "B-LOC", "L-LOC", "O", "U-GPE", "O"]
cats = {"TRAVEL": 1.0, "BAKING": 0.0}
nlp = English()
doc = nlp(text)
for i in range(len(tags)):
doc[i].tag_ = tags[i]
doc[i].dep_ = deps[i]
doc[i].head = doc[heads[i]]
doc.ents = spans_from_biluo_tags(doc, biluo_tags)
doc.cats = cats
doc.is_tagged = True
doc.is_parsed = True
return doc
2019-08-18 13:09:16 +00:00
2017-01-12 22:39:18 +00:00
def test_gold_biluo_U(en_vocab):
words = ["I", "flew", "to", "London", "."]
spaces = [True, True, True, False, True]
doc = Doc(en_vocab, words=words, spaces=spaces)
entities = [(len("I flew to "), len("I flew to London"), "LOC")]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ["O", "O", "O", "U-LOC", "O"]
2017-01-12 22:39:18 +00:00
def test_gold_biluo_BL(en_vocab):
words = ["I", "flew", "to", "San", "Francisco", "."]
spaces = [True, True, True, True, False, True]
doc = Doc(en_vocab, words=words, spaces=spaces)
entities = [(len("I flew to "), len("I flew to San Francisco"), "LOC")]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ["O", "O", "O", "B-LOC", "L-LOC", "O"]
2017-01-12 22:39:18 +00:00
def test_gold_biluo_BIL(en_vocab):
words = ["I", "flew", "to", "San", "Francisco", "Valley", "."]
spaces = [True, True, True, True, True, False, True]
doc = Doc(en_vocab, words=words, spaces=spaces)
entities = [(len("I flew to "), len("I flew to San Francisco Valley"), "LOC")]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ["O", "O", "O", "B-LOC", "I-LOC", "L-LOC", "O"]
2019-08-18 13:09:16 +00:00
def test_gold_biluo_overlap(en_vocab):
words = ["I", "flew", "to", "San", "Francisco", "Valley", "."]
spaces = [True, True, True, True, True, False, True]
doc = Doc(en_vocab, words=words, spaces=spaces)
2019-08-18 13:09:16 +00:00
entities = [
(len("I flew to "), len("I flew to San Francisco Valley"), "LOC"),
(len("I flew to "), len("I flew to San Francisco"), "LOC"),
]
with pytest.raises(ValueError):
2019-08-18 13:09:16 +00:00
biluo_tags_from_offsets(doc, entities)
2017-01-12 22:39:18 +00:00
def test_gold_biluo_misalign(en_vocab):
words = ["I", "flew", "to", "San", "Francisco", "Valley."]
spaces = [True, True, True, True, True, False]
doc = Doc(en_vocab, words=words, spaces=spaces)
entities = [(len("I flew to "), len("I flew to San Francisco Valley"), "LOC")]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ["O", "O", "O", "-", "-", "-"]
def test_roundtrip_offsets_biluo_conversion(en_tokenizer):
text = "I flew to Silicon Valley via London."
biluo_tags = ["O", "O", "O", "B-LOC", "L-LOC", "O", "U-GPE", "O"]
offsets = [(10, 24, "LOC"), (29, 35, "GPE")]
doc = en_tokenizer(text)
biluo_tags_converted = biluo_tags_from_offsets(doc, offsets)
assert biluo_tags_converted == biluo_tags
offsets_converted = offsets_from_biluo_tags(doc, biluo_tags)
assert offsets_converted == offsets
def test_biluo_spans(en_tokenizer):
doc = en_tokenizer("I flew to Silicon Valley via London.")
biluo_tags = ["O", "O", "O", "B-LOC", "L-LOC", "O", "U-GPE", "O"]
spans = spans_from_biluo_tags(doc, biluo_tags)
assert len(spans) == 2
assert spans[0].text == "Silicon Valley"
assert spans[0].label_ == "LOC"
assert spans[1].text == "London"
assert spans[1].label_ == "GPE"
2019-02-27 13:24:55 +00:00
def test_gold_ner_missing_tags(en_tokenizer):
doc = en_tokenizer("I flew to Silicon Valley via London.")
biluo_tags = [None, "O", "O", "B-LOC", "L-LOC", "O", "U-GPE", "O"]
2019-02-27 13:24:55 +00:00
gold = GoldParse(doc, entities=biluo_tags) # noqa: F841
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 20:31:31 +00:00
def test_iob_to_biluo():
good_iob = ["O", "O", "B-LOC", "I-LOC", "O", "B-PERSON"]
good_biluo = ["O", "O", "B-LOC", "L-LOC", "O", "U-PERSON"]
2019-10-24 14:21:08 +00:00
bad_iob = ["O", "O", '"', "B-LOC", "I-LOC"]
converted_biluo = iob_to_biluo(good_iob)
assert good_biluo == converted_biluo
with pytest.raises(ValueError):
iob_to_biluo(bad_iob)
Fix Example details for train CLI / pipeline components (#4624) * Switch to train_dataset() function in train CLI * Fixes for pipe() methods in pipeline components * Don't clobber `examples` variable with `as_example` in pipe() methods * Remove unnecessary traversals of `examples` * Update Parser.pipe() for Examples * Add `as_examples` kwarg to `pipe()` with implementation to return `Example`s * Accept `Doc` or `Example` in `pipe()` with `_get_doc()` (copied from `Pipe`) * Fixes to Example implementation in spacy.gold * Move `make_projective` from an attribute of Example to an argument of `Example.get_gold_parses()` * Head of 0 are not treated as unset * Unset heads are set to self rather than `None` (which causes problems while projectivizing) * Check for `Doc` (not just not `None`) when creating GoldParses for pre-merged example * Don't clobber `examples` variable in `iter_gold_docs()` * Add/modify gold tests for handling projectivity * In JSON roundtrip compare results from `dev_dataset` rather than `train_dataset` to avoid projectivization (and other potential modifications) * Add test for projective train vs. nonprojective dev versions of the same `Doc` * Handle ignore_misaligned as arg rather than attr Move `ignore_misaligned` from an attribute of `Example` to an argument to `Example.get_gold_parses()`, which makes it parallel to `make_projective`. Add test with old and new align that checks whether `ignore_misaligned` errors are raised as expected (only for new align). * Remove unused attrs from gold.pxd Remove `ignore_misaligned` and `make_projective` from `gold.pxd` * Refer to Example.goldparse in iter_gold_docs() Use `Example.goldparse` in `iter_gold_docs()` instead of `Example.gold` because a `None` `GoldParse` is generated with ignore_misaligned and generating it on-the-fly can raise an unwanted AlignmentError * Update test for ignore_misaligned
2019-11-23 13:32:15 +00:00
def test_roundtrip_docs_to_json(doc):
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 20:31:31 +00:00
nlp = English()
Fix Example details for train CLI / pipeline components (#4624) * Switch to train_dataset() function in train CLI * Fixes for pipe() methods in pipeline components * Don't clobber `examples` variable with `as_example` in pipe() methods * Remove unnecessary traversals of `examples` * Update Parser.pipe() for Examples * Add `as_examples` kwarg to `pipe()` with implementation to return `Example`s * Accept `Doc` or `Example` in `pipe()` with `_get_doc()` (copied from `Pipe`) * Fixes to Example implementation in spacy.gold * Move `make_projective` from an attribute of Example to an argument of `Example.get_gold_parses()` * Head of 0 are not treated as unset * Unset heads are set to self rather than `None` (which causes problems while projectivizing) * Check for `Doc` (not just not `None`) when creating GoldParses for pre-merged example * Don't clobber `examples` variable in `iter_gold_docs()` * Add/modify gold tests for handling projectivity * In JSON roundtrip compare results from `dev_dataset` rather than `train_dataset` to avoid projectivization (and other potential modifications) * Add test for projective train vs. nonprojective dev versions of the same `Doc` * Handle ignore_misaligned as arg rather than attr Move `ignore_misaligned` from an attribute of `Example` to an argument to `Example.get_gold_parses()`, which makes it parallel to `make_projective`. Add test with old and new align that checks whether `ignore_misaligned` errors are raised as expected (only for new align). * Remove unused attrs from gold.pxd Remove `ignore_misaligned` and `make_projective` from `gold.pxd` * Refer to Example.goldparse in iter_gold_docs() Use `Example.goldparse` in `iter_gold_docs()` instead of `Example.gold` because a `None` `GoldParse` is generated with ignore_misaligned and generating it on-the-fly can raise an unwanted AlignmentError * Update test for ignore_misaligned
2019-11-23 13:32:15 +00:00
text = doc.text
tags = [t.tag_ for t in doc]
deps = [t.dep_ for t in doc]
heads = [t.head.i for t in doc]
biluo_tags = iob_to_biluo([t.ent_iob_ + "-" + t.ent_type_ if t.ent_type_ else "O" for t in doc])
cats = doc.cats
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 20:31:31 +00:00
# roundtrip to JSON
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 20:31:31 +00:00
with make_tempdir() as tmpdir:
json_file = tmpdir / "roundtrip.json"
srsly.write_json(json_file, [docs_to_json(doc)])
goldcorpus = GoldCorpus(train=str(json_file), dev=str(json_file))
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 20:31:31 +00:00
Fix Example details for train CLI / pipeline components (#4624) * Switch to train_dataset() function in train CLI * Fixes for pipe() methods in pipeline components * Don't clobber `examples` variable with `as_example` in pipe() methods * Remove unnecessary traversals of `examples` * Update Parser.pipe() for Examples * Add `as_examples` kwarg to `pipe()` with implementation to return `Example`s * Accept `Doc` or `Example` in `pipe()` with `_get_doc()` (copied from `Pipe`) * Fixes to Example implementation in spacy.gold * Move `make_projective` from an attribute of Example to an argument of `Example.get_gold_parses()` * Head of 0 are not treated as unset * Unset heads are set to self rather than `None` (which causes problems while projectivizing) * Check for `Doc` (not just not `None`) when creating GoldParses for pre-merged example * Don't clobber `examples` variable in `iter_gold_docs()` * Add/modify gold tests for handling projectivity * In JSON roundtrip compare results from `dev_dataset` rather than `train_dataset` to avoid projectivization (and other potential modifications) * Add test for projective train vs. nonprojective dev versions of the same `Doc` * Handle ignore_misaligned as arg rather than attr Move `ignore_misaligned` from an attribute of `Example` to an argument to `Example.get_gold_parses()`, which makes it parallel to `make_projective`. Add test with old and new align that checks whether `ignore_misaligned` errors are raised as expected (only for new align). * Remove unused attrs from gold.pxd Remove `ignore_misaligned` and `make_projective` from `gold.pxd` * Refer to Example.goldparse in iter_gold_docs() Use `Example.goldparse` in `iter_gold_docs()` instead of `Example.gold` because a `None` `GoldParse` is generated with ignore_misaligned and generating it on-the-fly can raise an unwanted AlignmentError * Update test for ignore_misaligned
2019-11-23 13:32:15 +00:00
reloaded_example = next(goldcorpus.dev_dataset(nlp))
goldparse = reloaded_example.gold
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 20:31:31 +00:00
assert len(doc) == goldcorpus.count_train()
assert text == reloaded_example.text
assert tags == goldparse.tags
assert deps == goldparse.labels
assert heads == goldparse.heads
assert biluo_tags == goldparse.ner
assert "TRAVEL" in goldparse.cats
assert "BAKING" in goldparse.cats
assert cats["TRAVEL"] == goldparse.cats["TRAVEL"]
assert cats["BAKING"] == goldparse.cats["BAKING"]
# roundtrip to JSONL train dicts
with make_tempdir() as tmpdir:
jsonl_file = tmpdir / "roundtrip.jsonl"
srsly.write_jsonl(jsonl_file, [docs_to_json(doc)])
goldcorpus = GoldCorpus(str(jsonl_file), str(jsonl_file))
Fix Example details for train CLI / pipeline components (#4624) * Switch to train_dataset() function in train CLI * Fixes for pipe() methods in pipeline components * Don't clobber `examples` variable with `as_example` in pipe() methods * Remove unnecessary traversals of `examples` * Update Parser.pipe() for Examples * Add `as_examples` kwarg to `pipe()` with implementation to return `Example`s * Accept `Doc` or `Example` in `pipe()` with `_get_doc()` (copied from `Pipe`) * Fixes to Example implementation in spacy.gold * Move `make_projective` from an attribute of Example to an argument of `Example.get_gold_parses()` * Head of 0 are not treated as unset * Unset heads are set to self rather than `None` (which causes problems while projectivizing) * Check for `Doc` (not just not `None`) when creating GoldParses for pre-merged example * Don't clobber `examples` variable in `iter_gold_docs()` * Add/modify gold tests for handling projectivity * In JSON roundtrip compare results from `dev_dataset` rather than `train_dataset` to avoid projectivization (and other potential modifications) * Add test for projective train vs. nonprojective dev versions of the same `Doc` * Handle ignore_misaligned as arg rather than attr Move `ignore_misaligned` from an attribute of `Example` to an argument to `Example.get_gold_parses()`, which makes it parallel to `make_projective`. Add test with old and new align that checks whether `ignore_misaligned` errors are raised as expected (only for new align). * Remove unused attrs from gold.pxd Remove `ignore_misaligned` and `make_projective` from `gold.pxd` * Refer to Example.goldparse in iter_gold_docs() Use `Example.goldparse` in `iter_gold_docs()` instead of `Example.gold` because a `None` `GoldParse` is generated with ignore_misaligned and generating it on-the-fly can raise an unwanted AlignmentError * Update test for ignore_misaligned
2019-11-23 13:32:15 +00:00
reloaded_example = next(goldcorpus.dev_dataset(nlp))
goldparse = reloaded_example.gold
assert len(doc) == goldcorpus.count_train()
assert text == reloaded_example.text
assert tags == goldparse.tags
assert deps == goldparse.labels
assert heads == goldparse.heads
assert biluo_tags == goldparse.ner
assert "TRAVEL" in goldparse.cats
assert "BAKING" in goldparse.cats
assert cats["TRAVEL"] == goldparse.cats["TRAVEL"]
assert cats["BAKING"] == goldparse.cats["BAKING"]
# roundtrip to JSONL tuples
with make_tempdir() as tmpdir:
jsonl_file = tmpdir / "roundtrip.jsonl"
# write to JSONL train dicts
srsly.write_jsonl(jsonl_file, [docs_to_json(doc)])
goldcorpus = GoldCorpus(str(jsonl_file), str(jsonl_file))
# load and rewrite as JSONL tuples
srsly.write_jsonl(jsonl_file, goldcorpus.train_examples)
goldcorpus = GoldCorpus(str(jsonl_file), str(jsonl_file))
Fix Example details for train CLI / pipeline components (#4624) * Switch to train_dataset() function in train CLI * Fixes for pipe() methods in pipeline components * Don't clobber `examples` variable with `as_example` in pipe() methods * Remove unnecessary traversals of `examples` * Update Parser.pipe() for Examples * Add `as_examples` kwarg to `pipe()` with implementation to return `Example`s * Accept `Doc` or `Example` in `pipe()` with `_get_doc()` (copied from `Pipe`) * Fixes to Example implementation in spacy.gold * Move `make_projective` from an attribute of Example to an argument of `Example.get_gold_parses()` * Head of 0 are not treated as unset * Unset heads are set to self rather than `None` (which causes problems while projectivizing) * Check for `Doc` (not just not `None`) when creating GoldParses for pre-merged example * Don't clobber `examples` variable in `iter_gold_docs()` * Add/modify gold tests for handling projectivity * In JSON roundtrip compare results from `dev_dataset` rather than `train_dataset` to avoid projectivization (and other potential modifications) * Add test for projective train vs. nonprojective dev versions of the same `Doc` * Handle ignore_misaligned as arg rather than attr Move `ignore_misaligned` from an attribute of `Example` to an argument to `Example.get_gold_parses()`, which makes it parallel to `make_projective`. Add test with old and new align that checks whether `ignore_misaligned` errors are raised as expected (only for new align). * Remove unused attrs from gold.pxd Remove `ignore_misaligned` and `make_projective` from `gold.pxd` * Refer to Example.goldparse in iter_gold_docs() Use `Example.goldparse` in `iter_gold_docs()` instead of `Example.gold` because a `None` `GoldParse` is generated with ignore_misaligned and generating it on-the-fly can raise an unwanted AlignmentError * Update test for ignore_misaligned
2019-11-23 13:32:15 +00:00
reloaded_example = next(goldcorpus.dev_dataset(nlp))
goldparse = reloaded_example.gold
assert len(doc) == goldcorpus.count_train()
assert text == reloaded_example.text
assert tags == goldparse.tags
assert deps == goldparse.labels
assert heads == goldparse.heads
assert biluo_tags == goldparse.ner
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 20:31:31 +00:00
assert "TRAVEL" in goldparse.cats
assert "BAKING" in goldparse.cats
assert cats["TRAVEL"] == goldparse.cats["TRAVEL"]
assert cats["BAKING"] == goldparse.cats["BAKING"]
Fix Example details for train CLI / pipeline components (#4624) * Switch to train_dataset() function in train CLI * Fixes for pipe() methods in pipeline components * Don't clobber `examples` variable with `as_example` in pipe() methods * Remove unnecessary traversals of `examples` * Update Parser.pipe() for Examples * Add `as_examples` kwarg to `pipe()` with implementation to return `Example`s * Accept `Doc` or `Example` in `pipe()` with `_get_doc()` (copied from `Pipe`) * Fixes to Example implementation in spacy.gold * Move `make_projective` from an attribute of Example to an argument of `Example.get_gold_parses()` * Head of 0 are not treated as unset * Unset heads are set to self rather than `None` (which causes problems while projectivizing) * Check for `Doc` (not just not `None`) when creating GoldParses for pre-merged example * Don't clobber `examples` variable in `iter_gold_docs()` * Add/modify gold tests for handling projectivity * In JSON roundtrip compare results from `dev_dataset` rather than `train_dataset` to avoid projectivization (and other potential modifications) * Add test for projective train vs. nonprojective dev versions of the same `Doc` * Handle ignore_misaligned as arg rather than attr Move `ignore_misaligned` from an attribute of `Example` to an argument to `Example.get_gold_parses()`, which makes it parallel to `make_projective`. Add test with old and new align that checks whether `ignore_misaligned` errors are raised as expected (only for new align). * Remove unused attrs from gold.pxd Remove `ignore_misaligned` and `make_projective` from `gold.pxd` * Refer to Example.goldparse in iter_gold_docs() Use `Example.goldparse` in `iter_gold_docs()` instead of `Example.gold` because a `None` `GoldParse` is generated with ignore_misaligned and generating it on-the-fly can raise an unwanted AlignmentError * Update test for ignore_misaligned
2019-11-23 13:32:15 +00:00
def test_projective_train_vs_nonprojective_dev(doc):
nlp = English()
text = doc.text
deps = [t.dep_ for t in doc]
heads = [t.head.i for t in doc]
with make_tempdir() as tmpdir:
jsonl_file = tmpdir / "test.jsonl"
# write to JSONL train dicts
srsly.write_jsonl(jsonl_file, [docs_to_json(doc)])
goldcorpus = GoldCorpus(str(jsonl_file), str(jsonl_file))
train_reloaded_example = next(goldcorpus.train_dataset(nlp))
train_goldparse = train_reloaded_example.gold
dev_reloaded_example = next(goldcorpus.dev_dataset(nlp))
dev_goldparse = dev_reloaded_example.gold
assert is_nonproj_tree([t.head.i for t in doc]) is True
assert is_nonproj_tree(train_goldparse.heads) is False
assert heads[:-1] == train_goldparse.heads[:-1]
assert heads[-1] != train_goldparse.heads[-1]
assert deps[:-1] == train_goldparse.labels[:-1]
assert deps[-1] != train_goldparse.labels[-1]
assert heads == dev_goldparse.heads
assert deps == dev_goldparse.labels
def test_ignore_misaligned(doc):
nlp = English()
text = doc.text
deps = [t.dep_ for t in doc]
heads = [t.head.i for t in doc]
use_new_align = spacy.gold.USE_NEW_ALIGN
spacy.gold.USE_NEW_ALIGN = False
with make_tempdir() as tmpdir:
jsonl_file = tmpdir / "test.jsonl"
data = [docs_to_json(doc)]
data[0]["paragraphs"][0]["raw"] = text.replace("Sarah", "Jane")
# write to JSONL train dicts
srsly.write_jsonl(jsonl_file, data)
goldcorpus = GoldCorpus(str(jsonl_file), str(jsonl_file))
train_reloaded_example = next(goldcorpus.train_dataset(nlp))
spacy.gold.USE_NEW_ALIGN = True
with make_tempdir() as tmpdir:
jsonl_file = tmpdir / "test.jsonl"
data = [docs_to_json(doc)]
data[0]["paragraphs"][0]["raw"] = text.replace("Sarah", "Jane")
# write to JSONL train dicts
srsly.write_jsonl(jsonl_file, data)
goldcorpus = GoldCorpus(str(jsonl_file), str(jsonl_file))
with pytest.raises(AlignmentError):
train_reloaded_example = next(goldcorpus.train_dataset(nlp))
with make_tempdir() as tmpdir:
jsonl_file = tmpdir / "test.jsonl"
data = [docs_to_json(doc)]
data[0]["paragraphs"][0]["raw"] = text.replace("Sarah", "Jane")
# write to JSONL train dicts
srsly.write_jsonl(jsonl_file, data)
goldcorpus = GoldCorpus(str(jsonl_file), str(jsonl_file))
# doesn't raise an AlignmentError, but there is nothing to iterate over
# because the only example can't be aligned
train_reloaded_example = list(goldcorpus.train_dataset(nlp,
ignore_misaligned=True))
assert len(train_reloaded_example) == 0
spacy.gold.USE_NEW_ALIGN = use_new_align
# xfail while we have backwards-compatible alignment
@pytest.mark.xfail
@pytest.mark.parametrize(
"tokens_a,tokens_b,expected",
[
(["a", "b", "c"], ["ab", "c"], (3, [-1, -1, 1], [-1, 2], {0: 0, 1: 0}, {})),
(
["a", "b", "``", "c"],
['ab"', "c"],
(4, [-1, -1, -1, 1], [-1, 3], {0: 0, 1: 0, 2: 0}, {}),
),
(["a", "bc"], ["ab", "c"], (4, [-1, -1], [-1, -1], {0: 0}, {1: 1})),
(
["ab", "c", "d"],
["a", "b", "cd"],
(6, [-1, -1, -1], [-1, -1, -1], {1: 2, 2: 2}, {0: 0, 1: 0}),
),
(
["a", "b", "cd"],
["a", "b", "c", "d"],
(3, [0, 1, -1], [0, 1, -1, -1], {}, {2: 2, 3: 2}),
),
([" ", "a"], ["a"], (1, [-1, 0], [1], {}, {})),
],
)
def test_align(tokens_a, tokens_b, expected):
cost, a2b, b2a, a2b_multi, b2a_multi = align(tokens_a, tokens_b)
assert (cost, list(a2b), list(b2a), a2b_multi, b2a_multi) == expected
# check symmetry
cost, a2b, b2a, a2b_multi, b2a_multi = align(tokens_b, tokens_a)
assert (cost, list(b2a), list(a2b), b2a_multi, a2b_multi) == expected
def test_goldparse_startswith_space(en_tokenizer):
text = " a"
doc = en_tokenizer(text)
g = GoldParse(doc, words=["a"], entities=["U-DATE"], deps=["ROOT"], heads=[0])
assert g.words == [" ", "a"]
assert g.ner == [None, "U-DATE"]
assert g.labels == [None, "ROOT"]
def test_gold_constructor():
"""Test that the GoldParse constructor works fine"""
nlp = English()
doc = nlp("This is a sentence")
gold = GoldParse(doc, cats={"cat1": 1.0, "cat2": 0.0})
assert gold.cats["cat1"]
assert not gold.cats["cat2"]
assert gold.words == ["This", "is", "a", "sentence"]
def test_gold_orig_annot():
nlp = English()
doc = nlp("This is a sentence")
gold = GoldParse(doc, cats={"cat1": 1.0, "cat2": 0.0})
assert gold.orig.words == ["This", "is", "a", "sentence"]
assert gold.cats["cat1"]
doc_annotation = DocAnnotation(cats={"cat1": 0.0, "cat2": 1.0})
gold2 = GoldParse.from_annotation(doc, doc_annotation, gold.orig)
assert gold2.orig.words == ["This", "is", "a", "sentence"]
assert not gold2.cats["cat1"]
def test_tuple_format_implicit():
"""Test tuple format with implicit GoldParse creation"""
train_data = [
("Uber blew through $1 million a week", {"entities": [(0, 4, "ORG")]}),
(
"Spotify steps up Asia expansion",
{"entities": [(0, 8, "ORG"), (17, 21, "LOC")]},
),
("Google rebrands its business apps", {"entities": [(0, 6, "ORG")]}),
]
_train(train_data)
def test_tuple_format_implicit_invalid():
"""Test that an error is thrown for an implicit invalid GoldParse field"""
train_data = [
("Uber blew through $1 million a week", {"frumble": [(0, 4, "ORG")]}),
(
"Spotify steps up Asia expansion",
{"entities": [(0, 8, "ORG"), (17, 21, "LOC")]},
),
("Google rebrands its business apps", {"entities": [(0, 6, "ORG")]}),
]
with pytest.raises(TypeError):
_train(train_data)
def _train(train_data):
nlp = English()
ner = nlp.create_pipe("ner")
ner.add_label("ORG")
ner.add_label("LOC")
nlp.add_pipe(ner)
optimizer = nlp.begin_training()
for i in range(5):
losses = {}
batches = minibatch(train_data, size=compounding(4.0, 32.0, 1.001))
for batch in batches:
nlp.update(batch, sgd=optimizer, losses=losses)
tokens_1 = {
"ids": [1, 2, 3],
"words": ["Hi", "there", "everyone"],
"tags": ["INTJ", "ADV", "PRON"],
}
tokens_2 = {
"ids": [1, 2, 3, 4],
"words": ["It", "is", "just", "me"],
"tags": ["PRON", "AUX", "ADV", "PRON"],
}
text0 = "Hi there everyone It is just me"
def test_merge_sents():
nlp = English()
example = Example()
example.add_token_annotation(**tokens_1)
example.add_token_annotation(**tokens_2)
assert len(example.get_gold_parses(merge=False, vocab=nlp.vocab)) == 2
assert len(example.get_gold_parses(merge=True, vocab=nlp.vocab)) == 1 # this shouldn't change the original object
merged_example = example.merge_sents()
token_annotation_1 = example.token_annotations[0]
assert token_annotation_1.ids == [1, 2, 3]
assert token_annotation_1.words == ["Hi", "there", "everyone"]
assert token_annotation_1.tags == ["INTJ", "ADV", "PRON"]
token_annotation_m = merged_example.token_annotations[0]
assert token_annotation_m.ids == [1, 2, 3, 4, 5, 6, 7]
assert token_annotation_m.words == ["Hi", "there", "everyone", "It", "is", "just", "me"]
assert token_annotation_m.tags == ["INTJ", "ADV", "PRON", "PRON", "AUX", "ADV", "PRON"]
def test_tuples_to_example():
ex = Example()
ex.add_token_annotation(**tokens_1)
ex.add_token_annotation(**tokens_2)
ex.add_doc_annotation(cats={"TRAVEL": 1.0, "BAKING": 0.0})
ex_dict = ex.to_dict()
token_dicts = [
{
"ids": [1, 2, 3],
"words": ["Hi", "there", "everyone"],
"tags": ["INTJ", "ADV", "PRON"],
"heads": [],
"deps": [],
"entities": [],
"morphology": [],
"brackets": [],
},
{
"ids": [1, 2, 3, 4],
"words": ["It", "is", "just", "me"],
"tags": ["PRON", "AUX", "ADV", "PRON"],
"heads": [],
"deps": [],
"entities": [],
"morphology": [],
"brackets": [],
},
]
doc_dict = {"cats": {"TRAVEL": 1.0, "BAKING": 0.0}, "links": {}}
assert ex_dict == {"token_annotations": token_dicts, "doc_annotation": doc_dict}