spaCy/spacy/tests/pipeline/test_spancat.py

397 lines
13 KiB
Python
Raw Normal View History

import pytest
import numpy
from numpy.testing import assert_array_equal, assert_almost_equal
from thinc.api import get_current_ops, Ragged
from spacy import util
from spacy.lang.en import English
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
from spacy.language import Language
from spacy.tokens import SpanGroup
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167) * 🚨 Ignore all existing Mypy errors * 🏗 Add Mypy check to CI * Add types-mock and types-requests as dev requirements * Add additional type ignore directives * Add types packages to dev-only list in reqs test * Add types-dataclasses for python 3.6 * Add ignore to pretrain * 🏷 Improve type annotation on `run_command` helper The `run_command` helper previously declared that it returned an `Optional[subprocess.CompletedProcess]`, but it isn't actually possible for the function to return `None`. These changes modify the type annotation of the `run_command` helper and remove all now-unnecessary `# type: ignore` directives. * 🔧 Allow variable type redefinition in limited contexts These changes modify how Mypy is configured to allow variables to have their type automatically redefined under certain conditions. The Mypy documentation contains the following example: ```python def process(items: List[str]) -> None: # 'items' has type List[str] items = [item.split() for item in items] # 'items' now has type List[List[str]] ... ``` This configuration change is especially helpful in reducing the number of `# type: ignore` directives needed to handle the common pattern of: * Accepting a filepath as a string * Overwriting the variable using `filepath = ensure_path(filepath)` These changes enable redefinition and remove all `# type: ignore` directives rendered redundant by this change. * 🏷 Add type annotation to converters mapping * 🚨 Fix Mypy error in convert CLI argument verification * 🏷 Improve type annotation on `resolve_dot_names` helper * 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors` * 🏷 Add type annotations for more `Vocab` attributes * 🏷 Add loose type annotation for gold data compilation * 🏷 Improve `_format_labels` type annotation * 🏷 Fix `get_lang_class` type annotation * 🏷 Loosen return type of `Language.evaluate` * 🏷 Don't accept `Scorer` in `handle_scores_per_type` * 🏷 Add `string_to_list` overloads * 🏷 Fix non-Optional command-line options * 🙈 Ignore redefinition of `wandb_logger` in `loggers.py` * ➕ Install `typing_extensions` in Python 3.8+ The `typing_extensions` package states that it should be used when "writing code that must be compatible with multiple Python versions". Since SpaCy needs to support multiple Python versions, it should be used when newer `typing` module members are required. One example of this is `Literal`, which is available starting with Python 3.8. Previously SpaCy tried to import `Literal` from `typing`, falling back to `typing_extensions` if the import failed. However, Mypy doesn't seem to be able to understand what `Literal` means when the initial import means. Therefore, these changes modify how `compat` imports `Literal` by always importing it from `typing_extensions`. These changes also modify how `typing_extensions` is installed, so that it is a requirement for all Python versions, including those greater than or equal to 3.8. * 🏷 Improve type annotation for `Language.pipe` These changes add a missing overload variant to the type signature of `Language.pipe`. Additionally, the type signature is enhanced to allow type checkers to differentiate between the two overload variants based on the `as_tuple` parameter. Fixes #8772 * ➖ Don't install `typing-extensions` in Python 3.8+ After more detailed analysis of how to implement Python version-specific type annotations using SpaCy, it has been determined that by branching on a comparison against `sys.version_info` can be statically analyzed by Mypy well enough to enable us to conditionally use `typing_extensions.Literal`. This means that we no longer need to install `typing_extensions` for Python versions greater than or equal to 3.8! 🎉 These changes revert previous changes installing `typing-extensions` regardless of Python version and modify how we import the `Literal` type to ensure that Mypy treats it properly. * resolve mypy errors for Strict pydantic types * refactor code to avoid missing return statement * fix types of convert CLI command * avoid list-set confustion in debug_data * fix typo and formatting * small fixes to avoid type ignores * fix types in profile CLI command and make it more efficient * type fixes in projects CLI * put one ignore back * type fixes for render * fix render types - the sequel * fix BaseDefault in language definitions * fix type of noun_chunks iterator - yields tuple instead of span * fix types in language-specific modules * 🏷 Expand accepted inputs of `get_string_id` `get_string_id` accepts either a string (in which case it returns its ID) or an ID (in which case it immediately returns the ID). These changes extend the type annotation of `get_string_id` to indicate that it can accept either strings or IDs. * 🏷 Handle override types in `combine_score_weights` The `combine_score_weights` function allows users to pass an `overrides` mapping to override data extracted from the `weights` argument. Since it allows `Optional` dictionary values, the return value may also include `Optional` dictionary values. These changes update the type annotations for `combine_score_weights` to reflect this fact. * 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer` * 🏷 Fix redefinition of `wandb_logger` These changes fix the redefinition of `wandb_logger` by giving a separate name to each `WandbLogger` version. For backwards-compatibility, `spacy.train` still exports `wandb_logger_v3` as `wandb_logger` for now. * more fixes for typing in language * type fixes in model definitions * 🏷 Annotate `_RandomWords.probs` as `NDArray` * 🏷 Annotate `tok2vec` layers to help Mypy * 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6 Also remove an import that I forgot to move to the top of the module 😅 * more fixes for matchers and other pipeline components * quick fix for entity linker * fixing types for spancat, textcat, etc * bugfix for tok2vec * type annotations for scorer * add runtime_checkable for Protocol * type and import fixes in tests * mypy fixes for training utilities * few fixes in util * fix import * 🐵 Remove unused `# type: ignore` directives * 🏷 Annotate `Language._components` * 🏷 Annotate `spacy.pipeline.Pipe` * add doc as property to span.pyi * small fixes and cleanup * explicit type annotations instead of via comment Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 16:21:40 +03:00
from spacy.tokens._dict_proxies import SpanGroups
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
from spacy.training import Example
from spacy.util import fix_random_seed, registry, make_tempdir
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
OPS = get_current_ops()
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
SPAN_KEY = "labeled_spans"
TRAIN_DATA = [
("Who is Shaka Khan?", {"spans": {SPAN_KEY: [(7, 17, "PERSON")]}}),
(
"I like London and Berlin.",
{"spans": {SPAN_KEY: [(7, 13, "LOC"), (18, 24, "LOC")]}},
),
]
TRAIN_DATA_OVERLAPPING = [
("Who is Shaka Khan?", {"spans": {SPAN_KEY: [(7, 17, "PERSON")]}}),
(
"I like London and Berlin",
{"spans": {SPAN_KEY: [(7, 13, "LOC"), (18, 24, "LOC"), (7, 24, "DOUBLE_LOC")]}},
),
("", {"spans": {SPAN_KEY: []}}),
]
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
def make_examples(nlp, data=TRAIN_DATA):
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
train_examples = []
for t in data:
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
eg = Example.from_dict(nlp.make_doc(t[0]), t[1])
train_examples.append(eg)
return train_examples
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
def test_no_label():
nlp = Language()
nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
with pytest.raises(ValueError):
nlp.initialize()
def test_no_resize():
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
spancat.add_label("Thing")
spancat.add_label("Phrase")
assert spancat.labels == ("Thing", "Phrase")
nlp.initialize()
assert spancat.model.get_dim("nO") == 2
# this throws an error because the spancat can't be resized after initialization
with pytest.raises(ValueError):
spancat.add_label("Stuff")
def test_implicit_labels():
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
assert len(spancat.labels) == 0
train_examples = make_examples(nlp)
nlp.initialize(get_examples=lambda: train_examples)
assert spancat.labels == ("PERSON", "LOC")
def test_explicit_labels():
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
assert len(spancat.labels) == 0
spancat.add_label("PERSON")
spancat.add_label("LOC")
nlp.initialize()
assert spancat.labels == ("PERSON", "LOC")
def test_doc_gc():
# If the Doc object is garbage collected, the spans won't be functional afterwards
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
spancat.add_label("PERSON")
nlp.initialize()
texts = [
"Just a sentence.",
"I like London and Berlin",
"I like Berlin",
"I eat ham.",
]
all_spans = [doc.spans for doc in nlp.pipe(texts)]
for text, spangroups in zip(texts, all_spans):
assert isinstance(spangroups, SpanGroups)
for key, spangroup in spangroups.items():
assert isinstance(spangroup, SpanGroup)
assert len(spangroup) > 0
with pytest.raises(RuntimeError):
span = spangroup[0]
@pytest.mark.parametrize(
"max_positive,nr_results", [(None, 4), (1, 2), (2, 3), (3, 4), (4, 4)]
)
def test_make_spangroup(max_positive, nr_results):
fix_random_seed(0)
nlp = Language()
spancat = nlp.add_pipe(
"spancat",
config={"spans_key": SPAN_KEY, "threshold": 0.5, "max_positive": max_positive},
)
doc = nlp.make_doc("Greater London")
ngram_suggester = registry.misc.get("spacy.ngram_suggester.v1")(sizes=[1, 2])
indices = ngram_suggester([doc])[0].dataXd
assert_array_equal(OPS.to_numpy(indices), numpy.asarray([[0, 1], [1, 2], [0, 2]]))
labels = ["Thing", "City", "Person", "GreatCity"]
scores = numpy.asarray(
[[0.2, 0.4, 0.3, 0.1], [0.1, 0.6, 0.2, 0.4], [0.8, 0.7, 0.3, 0.9]], dtype="f"
)
spangroup = spancat._make_span_group(doc, indices, scores, labels)
assert len(spangroup) == nr_results
# first span is always the second token "London"
assert spangroup[0].text == "London"
assert spangroup[0].label_ == "City"
assert_almost_equal(0.6, spangroup.attrs["scores"][0], 5)
# second span depends on the number of positives that were allowed
assert spangroup[1].text == "Greater London"
if max_positive == 1:
assert spangroup[1].label_ == "GreatCity"
assert_almost_equal(0.9, spangroup.attrs["scores"][1], 5)
else:
assert spangroup[1].label_ == "Thing"
assert_almost_equal(0.8, spangroup.attrs["scores"][1], 5)
if nr_results > 2:
assert spangroup[2].text == "Greater London"
if max_positive == 2:
assert spangroup[2].label_ == "GreatCity"
assert_almost_equal(0.9, spangroup.attrs["scores"][2], 5)
else:
assert spangroup[2].label_ == "City"
assert_almost_equal(0.7, spangroup.attrs["scores"][2], 5)
assert spangroup[-1].text == "Greater London"
assert spangroup[-1].label_ == "GreatCity"
assert_almost_equal(0.9, spangroup.attrs["scores"][-1], 5)
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
def test_ngram_suggester(en_tokenizer):
# test different n-gram lengths
for size in [1, 2, 3]:
ngram_suggester = registry.misc.get("spacy.ngram_suggester.v1")(sizes=[size])
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
docs = [
en_tokenizer(text)
for text in [
"a",
"a b",
"a b c",
"a b c d",
"a b c d e",
"a " * 100,
]
]
ngrams = ngram_suggester(docs)
# span sizes are correct
for s in ngrams.data:
assert s[1] - s[0] == size
# spans are within docs
offset = 0
for i, doc in enumerate(docs):
spans = ngrams.dataXd[offset : offset + ngrams.lengths[i]]
spans_set = set()
for span in spans:
assert 0 <= span[0] < len(doc)
assert 0 < span[1] <= len(doc)
spans_set.add((int(span[0]), int(span[1])))
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
# spans are unique
assert spans.shape[0] == len(spans_set)
offset += ngrams.lengths[i]
# the number of spans is correct
assert_array_equal(
OPS.to_numpy(ngrams.lengths),
[max(0, len(doc) - (size - 1)) for doc in docs],
)
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
# test 1-3-gram suggestions
ngram_suggester = registry.misc.get("spacy.ngram_suggester.v1")(sizes=[1, 2, 3])
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
docs = [
en_tokenizer(text) for text in ["a", "a b", "a b c", "a b c d", "a b c d e"]
]
ngrams = ngram_suggester(docs)
assert_array_equal(OPS.to_numpy(ngrams.lengths), [1, 3, 6, 9, 12])
assert_array_equal(
OPS.to_numpy(ngrams.data),
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
[
# doc 0
[0, 1],
# doc 1
[0, 1],
[1, 2],
[0, 2],
# doc 2
[0, 1],
[1, 2],
[2, 3],
[0, 2],
[1, 3],
[0, 3],
# doc 3
[0, 1],
[1, 2],
[2, 3],
[3, 4],
[0, 2],
[1, 3],
[2, 4],
[0, 3],
[1, 4],
# doc 4
[0, 1],
[1, 2],
[2, 3],
[3, 4],
[4, 5],
[0, 2],
[1, 3],
[2, 4],
[3, 5],
[0, 3],
[1, 4],
[2, 5],
],
)
# test some empty docs
ngram_suggester = registry.misc.get("spacy.ngram_suggester.v1")(sizes=[1])
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
docs = [en_tokenizer(text) for text in ["", "a", ""]]
ngrams = ngram_suggester(docs)
assert_array_equal(OPS.to_numpy(ngrams.lengths), [len(doc) for doc in docs])
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
# test all empty docs
ngram_suggester = registry.misc.get("spacy.ngram_suggester.v1")(sizes=[1])
Add SpanCategorizer component (#6747) * Draft spancat model * Add spancat model * Add test for extract_spans * Add extract_spans layer * Upd extract_spans * Add spancat model * Add test for spancat model * Upd spancat model * Update spancat component * Upd spancat * Update spancat model * Add quick spancat test * Import SpanCategorizer * Fix SpanCategorizer component * Import SpanGroup * Fix span extraction * Fix import * Fix import * Upd model * Update spancat models * Add scoring, update defaults * Update and add docs * Fix type * Update spacy/ml/extract_spans.py * Auto-format and fix import * Fix comment * Fix type * Fix type * Update website/docs/api/spancategorizer.md * Fix comment Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Better defense Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix labels list Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/extract_spans.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/pipeline/spancat.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Set annotations during update * Set annotations in spancat * fix imports in test * Update spacy/pipeline/spancat.py * replace MaxoutLogistic with LinearLogistic * fix config * various small fixes * remove set_annotations parameter in update * use our beloved tupley format with recent support for doc.spans * bugfix to allow renaming the default span_key (scores weren't showing up) * use different key in docs example * change defaults to better-working parameters from project (WIP) * register spacy.extract_spans.v1 for legacy purposes * Upd dev version so can build wheel * layers instead of architectures for smaller building blocks * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Update website/docs/api/spancategorizer.md Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Include additional scores from overrides in combined score weights * Parameterize spans key in scoring Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so that it's possible to evaluate multiple `spancat` components in the same pipeline. * Use the (intentionally very short) default spans key `sc` in the `SpanCategorizer` * Adjust the default score weights to include the default key * Adjust the scorer to use `spans_{spans_key}` as the prefix for the returned score * Revert addition of `attr_name` argument to `score_spans` and adjust the key in the `getter` instead. Note that for `spancat` components with a custom `span_key`, the score weights currently need to be modified manually in `[training.score_weights]` for them to be available during training. To suppress the default score weights `spans_sc_p/r/f` during training, set them to `null` in `[training.score_weights]`. * Update website/docs/api/scorer.md * Fix scorer for spans key containing underscore * Increment version * Add Spans to Evaluate CLI (#8439) * Add Spans to Evaluate CLI * Change to spans_key * Add spans per_type output Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Fix spancat GPU issues (#8455) * Fix GPU issues * Require thinc >=8.0.6 * Switch to glorot_uniform_init * Fix and test ngram suggester * Include final ngram in doc for all sizes * Fix ngrams for docs of the same length as ngram size * Handle batches of docs that result in no ngrams * Add tests Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>
2021-06-24 13:35:27 +03:00
docs = [en_tokenizer(text) for text in ["", "", ""]]
ngrams = ngram_suggester(docs)
assert_array_equal(OPS.to_numpy(ngrams.lengths), [len(doc) for doc in docs])
2021-07-15 11:01:22 +03:00
def test_ngram_sizes(en_tokenizer):
# test that the range suggester works well
size_suggester = registry.misc.get("spacy.ngram_suggester.v1")(sizes=[1, 2, 3])
2021-07-17 03:49:13 +03:00
suggester_factory = registry.misc.get("spacy.ngram_range_suggester.v1")
range_suggester = suggester_factory(min_size=1, max_size=3)
2021-07-15 11:01:22 +03:00
docs = [
en_tokenizer(text) for text in ["a", "a b", "a b c", "a b c d", "a b c d e"]
]
ngrams_1 = size_suggester(docs)
ngrams_2 = range_suggester(docs)
assert_array_equal(OPS.to_numpy(ngrams_1.lengths), [1, 3, 6, 9, 12])
assert_array_equal(OPS.to_numpy(ngrams_1.lengths), OPS.to_numpy(ngrams_2.lengths))
assert_array_equal(OPS.to_numpy(ngrams_1.data), OPS.to_numpy(ngrams_2.data))
2021-07-15 11:01:22 +03:00
# one more variation
2021-07-17 03:49:13 +03:00
suggester_factory = registry.misc.get("spacy.ngram_range_suggester.v1")
range_suggester = suggester_factory(min_size=2, max_size=4)
2021-07-15 11:01:22 +03:00
ngrams_3 = range_suggester(docs)
assert_array_equal(OPS.to_numpy(ngrams_3.lengths), [0, 1, 3, 6, 9])
def test_overfitting_IO():
# Simple test to try and quickly overfit the spancat component - ensuring the ML models work correctly
fix_random_seed(0)
nlp = English()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
train_examples = make_examples(nlp)
optimizer = nlp.initialize(get_examples=lambda: train_examples)
assert spancat.model.get_dim("nO") == 2
assert set(spancat.labels) == {"LOC", "PERSON"}
for i in range(50):
losses = {}
nlp.update(train_examples, sgd=optimizer, losses=losses)
assert losses["spancat"] < 0.01
# test the trained model
test_text = "I like London and Berlin"
doc = nlp(test_text)
assert doc.spans[spancat.key] == doc.spans[SPAN_KEY]
spans = doc.spans[SPAN_KEY]
assert len(spans) == 2
assert len(spans.attrs["scores"]) == 2
assert min(spans.attrs["scores"]) > 0.9
assert set([span.text for span in spans]) == {"London", "Berlin"}
assert set([span.label_ for span in spans]) == {"LOC"}
# Also test the results are still the same after IO
with make_tempdir() as tmp_dir:
nlp.to_disk(tmp_dir)
nlp2 = util.load_model_from_path(tmp_dir)
doc2 = nlp2(test_text)
spans2 = doc2.spans[SPAN_KEY]
assert len(spans2) == 2
assert len(spans2.attrs["scores"]) == 2
assert min(spans2.attrs["scores"]) > 0.9
assert set([span.text for span in spans2]) == {"London", "Berlin"}
assert set([span.label_ for span in spans2]) == {"LOC"}
# Test scoring
scores = nlp.evaluate(train_examples)
assert f"spans_{SPAN_KEY}_f" in scores
assert scores[f"spans_{SPAN_KEY}_p"] == 1.0
assert scores[f"spans_{SPAN_KEY}_r"] == 1.0
assert scores[f"spans_{SPAN_KEY}_f"] == 1.0
# also test that the spancat works for just a single entity in a sentence
doc = nlp("London")
assert len(doc.spans[spancat.key]) == 1
def test_overfitting_IO_overlapping():
# Test for overfitting on overlapping entities
fix_random_seed(0)
nlp = English()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
train_examples = make_examples(nlp, data=TRAIN_DATA_OVERLAPPING)
optimizer = nlp.initialize(get_examples=lambda: train_examples)
assert spancat.model.get_dim("nO") == 3
assert set(spancat.labels) == {"PERSON", "LOC", "DOUBLE_LOC"}
for i in range(50):
losses = {}
nlp.update(train_examples, sgd=optimizer, losses=losses)
assert losses["spancat"] < 0.01
# test the trained model
test_text = "I like London and Berlin"
doc = nlp(test_text)
spans = doc.spans[SPAN_KEY]
assert len(spans) == 3
assert len(spans.attrs["scores"]) == 3
assert min(spans.attrs["scores"]) > 0.9
assert set([span.text for span in spans]) == {
"London",
"Berlin",
"London and Berlin",
}
assert set([span.label_ for span in spans]) == {"LOC", "DOUBLE_LOC"}
# Also test the results are still the same after IO
with make_tempdir() as tmp_dir:
nlp.to_disk(tmp_dir)
nlp2 = util.load_model_from_path(tmp_dir)
doc2 = nlp2(test_text)
spans2 = doc2.spans[SPAN_KEY]
assert len(spans2) == 3
assert len(spans2.attrs["scores"]) == 3
assert min(spans2.attrs["scores"]) > 0.9
assert set([span.text for span in spans2]) == {
"London",
"Berlin",
"London and Berlin",
}
assert set([span.label_ for span in spans2]) == {"LOC", "DOUBLE_LOC"}
def test_zero_suggestions():
# Test with a suggester that returns 0 suggestions
@registry.misc("test_zero_suggester")
def make_zero_suggester():
def zero_suggester(docs, *, ops=None):
if ops is None:
ops = get_current_ops()
return Ragged(
ops.xp.zeros((0, 0), dtype="i"), ops.xp.zeros((len(docs),), dtype="i")
)
return zero_suggester
fix_random_seed(0)
nlp = English()
spancat = nlp.add_pipe(
"spancat",
config={"suggester": {"@misc": "test_zero_suggester"}, "spans_key": SPAN_KEY},
)
train_examples = make_examples(nlp)
optimizer = nlp.initialize(get_examples=lambda: train_examples)
assert spancat.model.get_dim("nO") == 2
assert set(spancat.labels) == {"LOC", "PERSON"}
nlp.update(train_examples, sgd=optimizer)