Merge pull request #12192 from adrianeboyd/chore/update-v4-from-master-5

Update v4 from master, format, update CI
This commit is contained in:
Sofie Van Landeghem 2023-01-27 14:59:26 +01:00 committed by GitHub
commit 1678a98449
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
120 changed files with 1518 additions and 465 deletions

10
.gitignore vendored
View File

@ -10,16 +10,6 @@ spacy/tests/package/setup.cfg
spacy/tests/package/pyproject.toml
spacy/tests/package/requirements.txt
# Website
website/.cache/
website/public/
website/node_modules
website/.npm
website/logs
*.log
npm-debug.log*
quickstart-training-generator.js
# Cython / C extensions
cythonize.json
spacy/*.html

View File

@ -16,7 +16,7 @@ production-ready [**training system**](https://spacy.io/usage/training) and easy
model packaging, deployment and workflow management. spaCy is commercial
open-source software, released under the [MIT license](https://github.com/explosion/spaCy/blob/master/LICENSE).
💫 **Version 3.4 out now!**
💫 **Version 3.5 out now!**
[Check out the release notes here.](https://github.com/explosion/spaCy/releases)
[![Azure Pipelines](https://img.shields.io/azure-devops/build/explosion-ai/public/8/master.svg?logo=azure-pipelines&style=flat-square&label=build)](https://dev.azure.com/explosion-ai/public/_build?definitionId=8)

View File

@ -11,18 +11,28 @@ trigger:
exclude:
- "website/*"
- "*.md"
- "*.mdx"
- ".github/workflows/*"
pr:
paths:
exclude:
- "*.md"
- "*.mdx"
- "website/docs/*"
- "website/src/*"
- "website/meta/*.tsx"
- "website/meta/*.mjs"
- "website/meta/languages.json"
- "website/meta/site.json"
- "website/meta/sidebars.json"
- "website/meta/type-annotations.json"
- "website/pages/*"
- ".github/workflows/*"
jobs:
# Perform basic checks for most important errors (syntax etc.) Uses the config
# defined in .flake8 and overwrites the selected codes.
# Check formatting and linting. Perform basic checks for most important errors
# (syntax etc.) Uses the config defined in setup.cfg and overwrites the
# selected codes.
- job: "Validate"
pool:
vmImage: "ubuntu-latest"
@ -30,6 +40,10 @@ jobs:
- task: UsePythonVersion@0
inputs:
versionSpec: "3.7"
- script: |
pip install black==22.3.0
python -m black spacy --check
displayName: "black"
- script: |
pip install flake8==5.0.4
python -m flake8 spacy --count --select=E901,E999,F821,F822,F823,W605 --show-source --statistics

View File

@ -22,7 +22,7 @@ langcodes>=3.2.0,<4.0.0
# Official Python utilities
setuptools
packaging>=20.0
typing_extensions>=3.7.4.1,<4.2.0; python_version < "3.8"
typing_extensions>=3.7.4.1,<4.5.0; python_version < "3.8"
# Development dependencies
pre-commit>=2.13.0
cython>=0.25,<3.0

View File

@ -55,7 +55,7 @@ install_requires =
# Official Python utilities
setuptools
packaging>=20.0
typing_extensions>=3.7.4,<4.2.0; python_version < "3.8"
typing_extensions>=3.7.4.1,<4.5.0; python_version < "3.8"
langcodes>=3.2.0,<4.0.0
[options.entry_points]

View File

@ -4,6 +4,7 @@ from ._util import app, setup_cli # noqa: F401
# These are the actual functions, NOT the wrapped CLI commands. The CLI commands
# are registered automatically and won't have to be imported here.
from .benchmark_speed import benchmark_speed_cli # noqa: F401
from .download import download # noqa: F401
from .info import info # noqa: F401
from .package import package # noqa: F401

View File

@ -46,6 +46,7 @@ DEBUG_HELP = """Suite of helpful commands for debugging and profiling. Includes
commands to check and validate your config files, training and evaluation data,
and custom model implementations.
"""
BENCHMARK_HELP = """Commands for benchmarking pipelines."""
INIT_HELP = """Commands for initializing configs and pipeline packages."""
# Wrappers for Typer's annotations. Initially created to set defaults and to
@ -54,12 +55,14 @@ Arg = typer.Argument
Opt = typer.Option
app = typer.Typer(name=NAME, help=HELP)
benchmark_cli = typer.Typer(name="benchmark", help=BENCHMARK_HELP, no_args_is_help=True)
project_cli = typer.Typer(name="project", help=PROJECT_HELP, no_args_is_help=True)
debug_cli = typer.Typer(name="debug", help=DEBUG_HELP, no_args_is_help=True)
init_cli = typer.Typer(name="init", help=INIT_HELP, no_args_is_help=True)
app.add_typer(project_cli)
app.add_typer(debug_cli)
app.add_typer(benchmark_cli)
app.add_typer(init_cli)

View File

@ -0,0 +1,174 @@
from typing import Iterable, List, Optional
import random
from itertools import islice
import numpy
from pathlib import Path
import time
from tqdm import tqdm
import typer
from wasabi import msg
from .. import util
from ..language import Language
from ..tokens import Doc
from ..training import Corpus
from ._util import Arg, Opt, benchmark_cli, setup_gpu
@benchmark_cli.command(
"speed",
context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
)
def benchmark_speed_cli(
# fmt: off
ctx: typer.Context,
model: str = Arg(..., help="Model name or path"),
data_path: Path = Arg(..., help="Location of binary evaluation data in .spacy format", exists=True),
batch_size: Optional[int] = Opt(None, "--batch-size", "-b", min=1, help="Override the pipeline batch size"),
no_shuffle: bool = Opt(False, "--no-shuffle", help="Do not shuffle benchmark data"),
use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
n_batches: int = Opt(50, "--batches", help="Minimum number of batches to benchmark", min=30,),
warmup_epochs: int = Opt(3, "--warmup", "-w", min=0, help="Number of iterations over the data for warmup"),
# fmt: on
):
"""
Benchmark a pipeline. Expects a loadable spaCy pipeline and benchmark
data in the binary .spacy format.
"""
setup_gpu(use_gpu=use_gpu, silent=False)
nlp = util.load_model(model)
batch_size = batch_size if batch_size is not None else nlp.batch_size
corpus = Corpus(data_path)
docs = [eg.predicted for eg in corpus(nlp)]
if len(docs) == 0:
msg.fail("Cannot benchmark speed using an empty corpus.", exits=1)
print(f"Warming up for {warmup_epochs} epochs...")
warmup(nlp, docs, warmup_epochs, batch_size)
print()
print(f"Benchmarking {n_batches} batches...")
wps = benchmark(nlp, docs, n_batches, batch_size, not no_shuffle)
print()
print_outliers(wps)
print_mean_with_ci(wps)
# Lowercased, behaves as a context manager function.
class time_context:
"""Register the running time of a context."""
def __enter__(self):
self.start = time.perf_counter()
return self
def __exit__(self, type, value, traceback):
self.elapsed = time.perf_counter() - self.start
class Quartiles:
"""Calculate the q1, q2, q3 quartiles and the inter-quartile range (iqr)
of a sample."""
q1: float
q2: float
q3: float
iqr: float
def __init__(self, sample: numpy.ndarray) -> None:
self.q1 = numpy.quantile(sample, 0.25)
self.q2 = numpy.quantile(sample, 0.5)
self.q3 = numpy.quantile(sample, 0.75)
self.iqr = self.q3 - self.q1
def annotate(
nlp: Language, docs: List[Doc], batch_size: Optional[int]
) -> numpy.ndarray:
docs = nlp.pipe(tqdm(docs, unit="doc"), batch_size=batch_size)
wps = []
while True:
with time_context() as elapsed:
batch_docs = list(
islice(docs, batch_size if batch_size else nlp.batch_size)
)
if len(batch_docs) == 0:
break
n_tokens = count_tokens(batch_docs)
wps.append(n_tokens / elapsed.elapsed)
return numpy.array(wps)
def benchmark(
nlp: Language,
docs: List[Doc],
n_batches: int,
batch_size: int,
shuffle: bool,
) -> numpy.ndarray:
if shuffle:
bench_docs = [
nlp.make_doc(random.choice(docs).text)
for _ in range(n_batches * batch_size)
]
else:
bench_docs = [
nlp.make_doc(docs[i % len(docs)].text)
for i in range(n_batches * batch_size)
]
return annotate(nlp, bench_docs, batch_size)
def bootstrap(x, statistic=numpy.mean, iterations=10000) -> numpy.ndarray:
"""Apply a statistic to repeated random samples of an array."""
return numpy.fromiter(
(
statistic(numpy.random.choice(x, len(x), replace=True))
for _ in range(iterations)
),
numpy.float64,
)
def count_tokens(docs: Iterable[Doc]) -> int:
return sum(len(doc) for doc in docs)
def print_mean_with_ci(sample: numpy.ndarray):
mean = numpy.mean(sample)
bootstrap_means = bootstrap(sample)
bootstrap_means.sort()
# 95% confidence interval
low = bootstrap_means[int(len(bootstrap_means) * 0.025)]
high = bootstrap_means[int(len(bootstrap_means) * 0.975)]
print(f"Mean: {mean:.1f} words/s (95% CI: {low-mean:.1f} +{high-mean:.1f})")
def print_outliers(sample: numpy.ndarray):
quartiles = Quartiles(sample)
n_outliers = numpy.sum(
(sample < (quartiles.q1 - 1.5 * quartiles.iqr))
| (sample > (quartiles.q3 + 1.5 * quartiles.iqr))
)
n_extreme_outliers = numpy.sum(
(sample < (quartiles.q1 - 3.0 * quartiles.iqr))
| (sample > (quartiles.q3 + 3.0 * quartiles.iqr))
)
print(
f"Outliers: {(100 * n_outliers) / len(sample):.1f}%, extreme outliers: {(100 * n_extreme_outliers) / len(sample)}%"
)
def warmup(
nlp: Language, docs: List[Doc], warmup_epochs: int, batch_size: Optional[int]
) -> numpy.ndarray:
docs = warmup_epochs * docs
return annotate(nlp, docs, batch_size)

View File

@ -17,6 +17,7 @@ from ..pipeline import TrainablePipe
from ..pipeline._parser_internals import nonproj
from ..pipeline._parser_internals.nonproj import DELIMITER
from ..pipeline import Morphologizer, SpanCategorizer
from ..pipeline._edit_tree_internals.edit_trees import EditTrees
from ..morphology import Morphology
from ..language import Language
from ..util import registry, resolve_dot_names
@ -671,6 +672,59 @@ def debug_data(
f"Found {gold_train_data['n_cycles']} projectivized train sentence(s) with cycles"
)
if "trainable_lemmatizer" in factory_names:
msg.divider("Trainable Lemmatizer")
trees_train: Set[str] = gold_train_data["lemmatizer_trees"]
trees_dev: Set[str] = gold_dev_data["lemmatizer_trees"]
# This is necessary context when someone is attempting to interpret whether the
# number of trees exclusively in the dev set is meaningful.
msg.info(f"{len(trees_train)} lemmatizer trees generated from training data")
msg.info(f"{len(trees_dev)} lemmatizer trees generated from dev data")
dev_not_train = trees_dev - trees_train
if len(dev_not_train) != 0:
pct = len(dev_not_train) / len(trees_dev)
msg.info(
f"{len(dev_not_train)} lemmatizer trees ({pct*100:.1f}% of dev trees)"
" were found exclusively in the dev data."
)
else:
# Would we ever expect this case? It seems like it would be pretty rare,
# and we might actually want a warning?
msg.info("All trees in dev data present in training data.")
if gold_train_data["n_low_cardinality_lemmas"] > 0:
n = gold_train_data["n_low_cardinality_lemmas"]
msg.warn(f"{n} training docs with 0 or 1 unique lemmas.")
if gold_dev_data["n_low_cardinality_lemmas"] > 0:
n = gold_dev_data["n_low_cardinality_lemmas"]
msg.warn(f"{n} dev docs with 0 or 1 unique lemmas.")
if gold_train_data["no_lemma_annotations"] > 0:
n = gold_train_data["no_lemma_annotations"]
msg.warn(f"{n} training docs with no lemma annotations.")
else:
msg.good("All training docs have lemma annotations.")
if gold_dev_data["no_lemma_annotations"] > 0:
n = gold_dev_data["no_lemma_annotations"]
msg.warn(f"{n} dev docs with no lemma annotations.")
else:
msg.good("All dev docs have lemma annotations.")
if gold_train_data["partial_lemma_annotations"] > 0:
n = gold_train_data["partial_lemma_annotations"]
msg.info(f"{n} training docs with partial lemma annotations.")
else:
msg.good("All training docs have complete lemma annotations.")
if gold_dev_data["partial_lemma_annotations"] > 0:
n = gold_dev_data["partial_lemma_annotations"]
msg.info(f"{n} dev docs with partial lemma annotations.")
else:
msg.good("All dev docs have complete lemma annotations.")
msg.divider("Summary")
good_counts = msg.counts[MESSAGES.GOOD]
warn_counts = msg.counts[MESSAGES.WARN]
@ -732,7 +786,13 @@ def _compile_gold(
"n_cats_multilabel": 0,
"n_cats_bad_values": 0,
"texts": set(),
"lemmatizer_trees": set(),
"no_lemma_annotations": 0,
"partial_lemma_annotations": 0,
"n_low_cardinality_lemmas": 0,
}
if "trainable_lemmatizer" in factory_names:
trees = EditTrees(nlp.vocab.strings)
for eg in examples:
gold = eg.reference
doc = eg.predicted
@ -862,6 +922,25 @@ def _compile_gold(
data["n_nonproj"] += 1
if nonproj.contains_cycle(aligned_heads):
data["n_cycles"] += 1
if "trainable_lemmatizer" in factory_names:
# from EditTreeLemmatizer._labels_from_data
if all(token.lemma == 0 for token in gold):
data["no_lemma_annotations"] += 1
continue
if any(token.lemma == 0 for token in gold):
data["partial_lemma_annotations"] += 1
lemma_set = set()
for token in gold:
if token.lemma != 0:
lemma_set.add(token.lemma)
tree_id = trees.add(token.text, token.lemma_)
tree_str = trees.tree_to_str(tree_id)
data["lemmatizer_trees"].add(tree_str)
# We want to identify cases where lemmas aren't assigned
# or are all assigned the same value, as this would indicate
# an issue since we're expecting a large set of lemmas
if len(lemma_set) < 2 and len(gold) > 1:
data["n_low_cardinality_lemmas"] += 1
return data

View File

@ -7,12 +7,15 @@ from thinc.api import fix_random_seed
from ..training import Corpus
from ..tokens import Doc
from ._util import app, Arg, Opt, setup_gpu, import_code
from ._util import app, Arg, Opt, setup_gpu, import_code, benchmark_cli
from ..scorer import Scorer
from .. import util
from .. import displacy
@benchmark_cli.command(
"accuracy",
)
@app.command("evaluate")
def evaluate_cli(
# fmt: off
@ -36,7 +39,7 @@ def evaluate_cli(
dependency parses in a HTML file, set as output directory as the
displacy_path argument.
DOCS: https://spacy.io/api/cli#evaluate
DOCS: https://spacy.io/api/cli#benchmark-accuracy
"""
import_code(code_path)
evaluate(

View File

@ -106,9 +106,7 @@ def serve(
if is_in_jupyter():
warnings.warn(Warnings.W011)
render(
docs, style=style, page=page, minify=minify, options=options, manual=manual
)
render(docs, style=style, page=page, minify=minify, options=options, manual=manual)
httpd = simple_server.make_server(host, port, app)
print(f"\nUsing the '{style}' visualizer")
print(f"Serving on http://{host}:{port} ...\n")

View File

@ -949,8 +949,8 @@ class Errors(metaclass=ErrorsWithCodes):
E1047 = ("`find_threshold()` only supports components with a `scorer` attribute.")
E1048 = ("Got '{unexpected}' as console progress bar type, but expected one of the following: {expected}")
E1049 = ("No available port found for displaCy on host {host}. Please specify an available port "
"with `displacy.serve(doc, port)`")
E1050 = ("Port {port} is already in use. Please specify an available port with `displacy.serve(doc, port)` "
"with `displacy.serve(doc, port=port)`")
E1050 = ("Port {port} is already in use. Please specify an available port with `displacy.serve(doc, port=port)` "
"or use `auto_switch_port=True` to pick an available port automatically.")
# v4 error strings

View File

@ -25,7 +25,7 @@ cdef class InMemoryLookupKB(KnowledgeBase):
"""An `InMemoryLookupKB` instance stores unique identifiers for entities and their textual aliases,
to support entity linking of named entities to real-world concepts.
DOCS: https://spacy.io/api/kb_in_memory
DOCS: https://spacy.io/api/inmemorylookupkb
"""
def __init__(self, Vocab vocab, entity_vector_length):

View File

@ -22,7 +22,7 @@ cpdef bint levenshtein_compare(input_text: str, pattern_text: str, fuzzy: int =
max_edits = fuzzy
else:
# allow at least two edits (to allow at least one transposition) and up
# to 20% of the pattern string length
# to 30% of the pattern string length
max_edits = max(2, round(0.3 * len(pattern_text)))
return levenshtein(input_text, pattern_text, max_edits) <= max_edits

View File

@ -5,8 +5,12 @@ from ..vocab import Vocab
from ..tokens import Doc, Span
class Matcher:
def __init__(self, vocab: Vocab, validate: bool = ...,
fuzzy_compare: Callable[[str, str, int], bool] = ...) -> None: ...
def __init__(
self,
vocab: Vocab,
validate: bool = ...,
fuzzy_compare: Callable[[str, str, int], bool] = ...,
) -> None: ...
def __reduce__(self) -> Any: ...
def __len__(self) -> int: ...
def __contains__(self, key: str) -> bool: ...

View File

@ -5,7 +5,7 @@ from itertools import islice
import numpy as np
import srsly
from thinc.api import Config, Model
from thinc.api import Config, Model, SequenceCategoricalCrossentropy, NumpyOps
from thinc.types import ArrayXd, Floats2d, Ints1d
from thinc.legacy import LegacySequenceCategoricalCrossentropy
@ -22,6 +22,8 @@ from .. import util
ActivationsT = Dict[str, Union[List[Floats2d], List[Ints1d]]]
# The cutoff value of *top_k* above which an alternative method is used to process guesses.
TOP_K_GUARDRAIL = 20
default_model_config = """
@ -125,6 +127,7 @@ class EditTreeLemmatizer(TrainablePipe):
self.cfg: Dict[str, Any] = {"labels": []}
self.scorer = scorer
self.save_activations = save_activations
self.numpy_ops = NumpyOps()
def get_loss(
self, examples: Iterable[Example], scores: List[Floats2d]
@ -140,7 +143,7 @@ class EditTreeLemmatizer(TrainablePipe):
for (predicted, gold_lemma) in zip(
eg.predicted, eg.get_aligned("LEMMA", as_string=True)
):
if gold_lemma is None:
if gold_lemma is None or gold_lemma == "":
label = -1
else:
tree_id = self.trees.add(predicted.text, gold_lemma)
@ -165,7 +168,7 @@ class EditTreeLemmatizer(TrainablePipe):
student_scores: Scores representing the student model's predictions.
RETURNS (Tuple[float, float]): The loss and the gradient.
DOCS: https://spacy.io/api/edittreelemmatizer#get_teacher_student_loss
"""
loss_func = LegacySequenceCategoricalCrossentropy(normalize=False)
@ -175,6 +178,18 @@ class EditTreeLemmatizer(TrainablePipe):
return float(loss), d_scores
def predict(self, docs: Iterable[Doc]) -> ActivationsT:
if self.top_k == 1:
scores2guesses = self._scores2guesses_top_k_equals_1
elif self.top_k <= TOP_K_GUARDRAIL:
scores2guesses = self._scores2guesses_top_k_greater_1
else:
scores2guesses = self._scores2guesses_top_k_guardrail
# The behaviour of *_scores2guesses_top_k_greater_1()* is efficient for values
# of *top_k>1* that are likely to be useful when the edit tree lemmatizer is used
# for its principal purpose of lemmatizing tokens. However, the code could also
# be used for other purposes, and with very large values of *top_k* the method
# becomes inefficient. In such cases, *_scores2guesses_top_k_guardrail()* is used
# instead.
n_docs = len(list(docs))
if not any(len(doc) for doc in docs):
# Handle cases where there are no tokens in any docs.
@ -189,20 +204,52 @@ class EditTreeLemmatizer(TrainablePipe):
return {"probabilities": scores, "tree_ids": guesses}
scores = self.model.predict(docs)
assert len(scores) == n_docs
guesses = self._scores2guesses(docs, scores)
guesses = scores2guesses(docs, scores)
assert len(guesses) == n_docs
return {"probabilities": scores, "tree_ids": guesses}
def _scores2guesses(self, docs, scores):
def _scores2guesses_top_k_equals_1(self, docs, scores):
guesses = []
for doc, doc_scores in zip(docs, scores):
if self.top_k == 1:
doc_guesses = doc_scores.argmax(axis=1).reshape(-1, 1)
else:
doc_guesses = np.argsort(doc_scores)[..., : -self.top_k - 1 : -1]
doc_guesses = doc_scores.argmax(axis=1)
doc_guesses = self.numpy_ops.asarray(doc_guesses)
if not isinstance(doc_guesses, np.ndarray):
doc_guesses = doc_guesses.get()
doc_compat_guesses = []
for i, token in enumerate(doc):
tree_id = self.cfg["labels"][doc_guesses[i]]
if self.trees.apply(tree_id, token.text) is not None:
doc_compat_guesses.append(tree_id)
else:
doc_compat_guesses.append(-1)
guesses.append(np.array(doc_compat_guesses))
return guesses
def _scores2guesses_top_k_greater_1(self, docs, scores):
guesses = []
top_k = min(self.top_k, len(self.labels))
for doc, doc_scores in zip(docs, scores):
doc_scores = self.numpy_ops.asarray(doc_scores)
doc_compat_guesses = []
for i, token in enumerate(doc):
for _ in range(top_k):
candidate = int(doc_scores[i].argmax())
candidate_tree_id = self.cfg["labels"][candidate]
if self.trees.apply(candidate_tree_id, token.text) is not None:
doc_compat_guesses.append(candidate_tree_id)
break
doc_scores[i, candidate] = np.finfo(np.float32).min
else:
doc_compat_guesses.append(-1)
guesses.append(np.array(doc_compat_guesses))
return guesses
def _scores2guesses_top_k_guardrail(self, docs, scores):
guesses = []
for doc, doc_scores in zip(docs, scores):
doc_guesses = np.argsort(doc_scores)[..., : -self.top_k - 1 : -1]
doc_guesses = self.numpy_ops.asarray(doc_guesses)
doc_compat_guesses = []
for token, candidates in zip(doc, doc_guesses):

View File

@ -453,7 +453,11 @@ class EntityLinker(TrainablePipe):
docs_ents: List[Ragged] = []
docs_scores: List[Ragged] = []
if not docs:
return {KNOWLEDGE_BASE_IDS: final_kb_ids, "ents": docs_ents, "scores": docs_scores}
return {
KNOWLEDGE_BASE_IDS: final_kb_ids,
"ents": docs_ents,
"scores": docs_scores,
}
if isinstance(docs, Doc):
docs = [docs]
for doc in docs:
@ -585,7 +589,11 @@ class EntityLinker(TrainablePipe):
method="predict", msg="result variables not of equal length"
)
raise RuntimeError(err)
return {KNOWLEDGE_BASE_IDS: final_kb_ids, "ents": docs_ents, "scores": docs_scores}
return {
KNOWLEDGE_BASE_IDS: final_kb_ids,
"ents": docs_ents,
"scores": docs_scores,
}
def set_annotations(self, docs: Iterable[Doc], activations: ActivationsT) -> None:
"""Modify a batch of documents, using pre-computed scores.

View File

@ -252,8 +252,11 @@ class EntityRecognizer(Parser):
def labels(self):
# Get the labels from the model by looking at the available moves, e.g.
# B-PERSON, I-PERSON, L-PERSON, U-PERSON
labels = set(remove_bilu_prefix(move) for move in self.move_names
if move[0] in ("B", "I", "L", "U"))
labels = set(
remove_bilu_prefix(move)
for move in self.move_names
if move[0] in ("B", "I", "L", "U")
)
return tuple(sorted(labels))
def scored_ents(self, beams):

View File

@ -163,15 +163,33 @@ class TokenPatternString(BaseModel):
IS_SUPERSET: Optional[List[StrictStr]] = Field(None, alias="is_superset")
INTERSECTS: Optional[List[StrictStr]] = Field(None, alias="intersects")
FUZZY: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy")
FUZZY1: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy1")
FUZZY2: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy2")
FUZZY3: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy3")
FUZZY4: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy4")
FUZZY5: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy5")
FUZZY6: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy6")
FUZZY7: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy7")
FUZZY8: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy8")
FUZZY9: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy9")
FUZZY1: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
None, alias="fuzzy1"
)
FUZZY2: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
None, alias="fuzzy2"
)
FUZZY3: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
None, alias="fuzzy3"
)
FUZZY4: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
None, alias="fuzzy4"
)
FUZZY5: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
None, alias="fuzzy5"
)
FUZZY6: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
None, alias="fuzzy6"
)
FUZZY7: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
None, alias="fuzzy7"
)
FUZZY8: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
None, alias="fuzzy8"
)
FUZZY9: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
None, alias="fuzzy9"
)
class Config:
extra = "forbid"

View File

@ -103,14 +103,15 @@ def test_initialize_from_labels():
}
def test_no_data():
@pytest.mark.parametrize("top_k", (1, 5, 30))
def test_no_data(top_k):
# Test that the lemmatizer provides a nice error when there's no tagging data / labels
TEXTCAT_DATA = [
("I'm so happy.", {"cats": {"POSITIVE": 1.0, "NEGATIVE": 0.0}}),
("I'm so angry", {"cats": {"POSITIVE": 0.0, "NEGATIVE": 1.0}}),
]
nlp = English()
nlp.add_pipe("trainable_lemmatizer")
nlp.add_pipe("trainable_lemmatizer", config={"top_k": top_k})
nlp.add_pipe("textcat")
train_examples = []
@ -121,10 +122,11 @@ def test_no_data():
nlp.initialize(get_examples=lambda: train_examples)
def test_incomplete_data():
@pytest.mark.parametrize("top_k", (1, 5, 30))
def test_incomplete_data(top_k):
# Test that the lemmatizer works with incomplete information
nlp = English()
lemmatizer = nlp.add_pipe("trainable_lemmatizer")
lemmatizer = nlp.add_pipe("trainable_lemmatizer", config={"top_k": top_k})
lemmatizer.min_tree_freq = 1
train_examples = []
for t in PARTIAL_DATA:
@ -141,10 +143,25 @@ def test_incomplete_data():
assert doc[1].lemma_ == "like"
assert doc[2].lemma_ == "blue"
# Check that incomplete annotations are ignored.
scores, _ = lemmatizer.model([eg.predicted for eg in train_examples], is_train=True)
_, dX = lemmatizer.get_loss(train_examples, scores)
xp = lemmatizer.model.ops.xp
def test_overfitting_IO():
# Missing annotations.
assert xp.count_nonzero(dX[0][0]) == 0
assert xp.count_nonzero(dX[0][3]) == 0
assert xp.count_nonzero(dX[1][0]) == 0
assert xp.count_nonzero(dX[1][3]) == 0
# Misaligned annotations.
assert xp.count_nonzero(dX[1][1]) == 0
@pytest.mark.parametrize("top_k", (1, 5, 30))
def test_overfitting_IO(top_k):
nlp = English()
lemmatizer = nlp.add_pipe("trainable_lemmatizer")
lemmatizer = nlp.add_pipe("trainable_lemmatizer", config={"top_k": top_k})
lemmatizer.min_tree_freq = 1
train_examples = []
for t in TRAIN_DATA:
@ -177,7 +194,7 @@ def test_overfitting_IO():
# Check model after a {to,from}_bytes roundtrip
nlp_bytes = nlp.to_bytes()
nlp3 = English()
nlp3.add_pipe("trainable_lemmatizer")
nlp3.add_pipe("trainable_lemmatizer", config={"top_k": top_k})
nlp3.from_bytes(nlp_bytes)
doc3 = nlp3(test_text)
assert doc3[0].lemma_ == "she"

View File

@ -618,7 +618,6 @@ def test_string_to_list_intify(value):
assert string_to_list(value, intify=True) == [1, 2, 3]
@pytest.mark.skip(reason="Temporarily skip for dev version")
def test_download_compatibility():
spec = SpecifierSet("==" + about.__version__)
spec.prereleases = False
@ -629,7 +628,6 @@ def test_download_compatibility():
assert get_minor_version(about.__version__) == get_minor_version(version)
@pytest.mark.skip(reason="Temporarily skip for dev version")
def test_validate_compatibility_table():
spec = SpecifierSet("==" + about.__version__)
spec.prereleases = False
@ -1076,7 +1074,7 @@ def test_cli_find_threshold(capsys):
)
with make_tempdir() as nlp_dir:
nlp.to_disk(nlp_dir)
res = find_threshold(
best_threshold, best_score, res = find_threshold(
model=nlp_dir,
data_path=docs_dir / "docs.spacy",
pipe_name="tc_multi",
@ -1084,10 +1082,10 @@ def test_cli_find_threshold(capsys):
scores_key="cats_macro_f",
silent=True,
)
assert res[0] != thresholds[0]
assert thresholds[0] < res[0] < thresholds[9]
assert res[1] == 1.0
assert res[2][1.0] == 0.0
assert best_threshold != thresholds[0]
assert thresholds[0] < best_threshold < thresholds[9]
assert best_score == max(res.values())
assert res[1.0] == 0.0
# Test with spancat.
nlp, _ = init_nlp((("spancat", {}),))
@ -1209,3 +1207,69 @@ def test_walk_directory():
assert (len(walk_directory(d, suffix="iob"))) == 2
assert (len(walk_directory(d, suffix="conll"))) == 3
assert (len(walk_directory(d, suffix="pdf"))) == 0
def test_debug_data_trainable_lemmatizer_basic():
examples = [
("She likes green eggs", {"lemmas": ["she", "like", "green", "egg"]}),
("Eat blue ham", {"lemmas": ["eat", "blue", "ham"]}),
]
nlp = Language()
train_examples = []
for t in examples:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
# ref test_edit_tree_lemmatizer::test_initialize_from_labels
# this results in 4 trees
assert len(data["lemmatizer_trees"]) == 4
def test_debug_data_trainable_lemmatizer_partial():
partial_examples = [
# partial annotation
("She likes green eggs", {"lemmas": ["", "like", "green", ""]}),
# misaligned partial annotation
(
"He hates green eggs",
{
"words": ["He", "hat", "es", "green", "eggs"],
"lemmas": ["", "hat", "e", "green", ""],
},
),
]
nlp = Language()
train_examples = []
for t in partial_examples:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
assert data["partial_lemma_annotations"] == 2
def test_debug_data_trainable_lemmatizer_low_cardinality():
low_cardinality_examples = [
("She likes green eggs", {"lemmas": ["no", "no", "no", "no"]}),
("Eat blue ham", {"lemmas": ["no", "no", "no"]}),
]
nlp = Language()
train_examples = []
for t in low_cardinality_examples:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
assert data["n_low_cardinality_lemmas"] == 2
def test_debug_data_trainable_lemmatizer_not_annotated():
unannotated_examples = [
("She likes green eggs", {}),
("Eat blue ham", {}),
]
nlp = Language()
train_examples = []
for t in unannotated_examples:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
assert data["no_lemma_annotations"] == 2

View File

@ -1,6 +1,7 @@
import os
from pathlib import Path
from typer.testing import CliRunner
from spacy.tokens import DocBin, Doc
from spacy.cli._util import app
from .util import make_tempdir
@ -31,3 +32,60 @@ def test_convert_auto_conflict():
assert "All input files must be same type" in result.stdout
out_files = os.listdir(d_out)
assert len(out_files) == 0
def test_benchmark_accuracy_alias():
# Verify that the `evaluate` alias works correctly.
result_benchmark = CliRunner().invoke(app, ["benchmark", "accuracy", "--help"])
result_evaluate = CliRunner().invoke(app, ["evaluate", "--help"])
assert result_benchmark.stdout == result_evaluate.stdout.replace(
"spacy evaluate", "spacy benchmark accuracy"
)
def test_debug_data_trainable_lemmatizer_cli(en_vocab):
train_docs = [
Doc(en_vocab, words=["I", "like", "cats"], lemmas=["I", "like", "cat"]),
Doc(
en_vocab,
words=["Dogs", "are", "great", "too"],
lemmas=["dog", "be", "great", "too"],
),
]
dev_docs = [
Doc(en_vocab, words=["Cats", "are", "cute"], lemmas=["cat", "be", "cute"]),
Doc(en_vocab, words=["Pets", "are", "great"], lemmas=["pet", "be", "great"]),
]
with make_tempdir() as d_in:
train_bin = DocBin(docs=train_docs)
train_bin.to_disk(d_in / "train.spacy")
dev_bin = DocBin(docs=dev_docs)
dev_bin.to_disk(d_in / "dev.spacy")
# `debug data` requires an input pipeline config
CliRunner().invoke(
app,
[
"init",
"config",
f"{d_in}/config.cfg",
"--lang",
"en",
"--pipeline",
"trainable_lemmatizer",
],
)
result_debug_data = CliRunner().invoke(
app,
[
"debug",
"data",
f"{d_in}/config.cfg",
"--paths.train",
f"{d_in}/train.spacy",
"--paths.dev",
f"{d_in}/dev.spacy",
],
)
# Instead of checking specific wording of the output, which may change,
# we'll check that this section of the debug output is present.
assert "= Trainable Lemmatizer =" in result_debug_data.stdout

View File

@ -0,0 +1,78 @@
from typing import IO, Generator, Iterable, List, TextIO, Tuple
from contextlib import contextmanager
from pathlib import Path
import pytest
import tempfile
from spacy.lang.en import English
from spacy.training import Example, PlainTextCorpus
from spacy.util import make_tempdir
# Intentional newlines to check that they are skipped.
PLAIN_TEXT_DOC = """
This is a doc. It contains two sentences.
This is another doc.
A third doc.
"""
PLAIN_TEXT_DOC_TOKENIZED = [
[
"This",
"is",
"a",
"doc",
".",
"It",
"contains",
"two",
"sentences",
".",
],
["This", "is", "another", "doc", "."],
["A", "third", "doc", "."],
]
@pytest.mark.parametrize("min_length", [0, 5])
@pytest.mark.parametrize("max_length", [0, 5])
def test_plain_text_reader(min_length, max_length):
nlp = English()
with _string_to_tmp_file(PLAIN_TEXT_DOC) as file_path:
corpus = PlainTextCorpus(
file_path, min_length=min_length, max_length=max_length
)
check = [
doc
for doc in PLAIN_TEXT_DOC_TOKENIZED
if len(doc) >= min_length and (max_length == 0 or len(doc) <= max_length)
]
reference, predicted = _examples_to_tokens(corpus(nlp))
assert reference == check
assert predicted == check
@contextmanager
def _string_to_tmp_file(s: str) -> Generator[Path, None, None]:
with make_tempdir() as d:
file_path = Path(d) / "string.txt"
with open(file_path, "w", encoding="utf-8") as f:
f.write(s)
yield file_path
def _examples_to_tokens(
examples: Iterable[Example],
) -> Tuple[List[List[str]], List[List[str]]]:
reference = []
predicted = []
for eg in examples:
reference.append([t.text for t in eg.reference])
predicted.append([t.text for t in eg.predicted])
return reference, predicted

View File

@ -1,4 +1,4 @@
from .corpus import Corpus, JsonlCorpus # noqa: F401
from .corpus import Corpus, JsonlCorpus, PlainTextCorpus # noqa: F401
from .example import Example, validate_examples, validate_get_examples # noqa: F401
from .example import validate_distillation_examples # noqa: F401
from .alignment import Alignment # noqa: F401

View File

@ -58,6 +58,28 @@ def read_labels(path: Path, *, require: bool = False):
return srsly.read_json(path)
@util.registry.readers("spacy.PlainTextCorpus.v1")
def create_plain_text_reader(
path: Optional[Path],
min_length: int = 0,
max_length: int = 0,
) -> Callable[["Language"], Iterable[Doc]]:
"""Iterate Example objects from a file or directory of plain text
UTF-8 files with one line per doc.
path (Path): The directory or filename to read from.
min_length (int): Minimum document length (in tokens). Shorter documents
will be skipped. Defaults to 0, which indicates no limit.
max_length (int): Maximum document length (in tokens). Longer documents will
be skipped. Defaults to 0, which indicates no limit.
DOCS: https://spacy.io/api/corpus#plaintextcorpus
"""
if path is None:
raise ValueError(Errors.E913)
return PlainTextCorpus(path, min_length=min_length, max_length=max_length)
def walk_corpus(path: Union[str, Path], file_type) -> List[Path]:
path = util.ensure_path(path)
if not path.is_dir() and path.parts[-1].endswith(file_type):
@ -257,3 +279,52 @@ class JsonlCorpus:
# We don't *need* an example here, but it seems nice to
# make it match the Corpus signature.
yield Example(doc, Doc(nlp.vocab, words=words, spaces=spaces))
class PlainTextCorpus:
"""Iterate Example objects from a file or directory of plain text
UTF-8 files with one line per doc.
path (Path): The directory or filename to read from.
min_length (int): Minimum document length (in tokens). Shorter documents
will be skipped. Defaults to 0, which indicates no limit.
max_length (int): Maximum document length (in tokens). Longer documents will
be skipped. Defaults to 0, which indicates no limit.
DOCS: https://spacy.io/api/corpus#plaintextcorpus
"""
file_type = "txt"
def __init__(
self,
path: Optional[Union[str, Path]],
*,
min_length: int = 0,
max_length: int = 0,
) -> None:
self.path = util.ensure_path(path)
self.min_length = min_length
self.max_length = max_length
def __call__(self, nlp: "Language") -> Iterator[Example]:
"""Yield examples from the data.
nlp (Language): The current nlp object.
YIELDS (Example): The example objects.
DOCS: https://spacy.io/api/corpus#plaintextcorpus-call
"""
for loc in walk_corpus(self.path, ".txt"):
with open(loc, encoding="utf-8") as f:
for text in f:
text = text.rstrip("\r\n")
if len(text):
doc = nlp.make_doc(text)
if self.min_length >= 1 and len(doc) < self.min_length:
continue
elif self.max_length >= 1 and len(doc) > self.max_length:
continue
# We don't *need* an example here, but it seems nice to
# make it match the Corpus signature.
yield Example(doc, doc.copy())

9
website/.dockerignore Normal file
View File

@ -0,0 +1,9 @@
.cache/
.next/
public/
node_modules
.npm
logs
*.log
npm-debug.log*
quickstart-training-generator.js

4
website/.gitignore vendored
View File

@ -1,5 +1,7 @@
# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
quickstart-training-generator.js
# dependencies
/node_modules
/.pnp
@ -41,4 +43,4 @@ next-env.d.ts
public/robots.txt
public/sitemap*
public/sw.js*
public/workbox*
public/workbox*

View File

@ -1,16 +1,14 @@
FROM node:11.15.0
FROM node:18
WORKDIR /spacy-io
RUN npm install -g gatsby-cli@2.7.4
COPY package.json .
COPY package-lock.json .
RUN npm install
USER node
# This is so the installed node_modules will be up one directory
# from where a user mounts files, so that they don't accidentally mount
# their own node_modules from a different build
# https://nodejs.org/api/modules.html#modules_loading_from_node_modules_folders
WORKDIR /spacy-io/website/
WORKDIR /home/node
COPY --chown=node package.json .
COPY --chown=node package-lock.json .
RUN npm install
WORKDIR /home/node/website/

View File

@ -41,33 +41,27 @@ If you'd like to do this, **be sure you do _not_ include your local
`node_modules` folder**, since there are some dependencies that need to be built
for the image system. Rename it before using.
```bash
docker run -it \
-v $(pwd):/spacy-io/website \
-p 8000:8000 \
ghcr.io/explosion/spacy-io \
gatsby develop -H 0.0.0.0
```
This will allow you to access the built website at http://0.0.0.0:8000/ in your
browser, and still edit code in your editor while having the site reflect those
changes.
**Note**: If you're working on a Mac with an M1 processor, you might see
segfault errors from `qemu` if you use the default image. To fix this use the
`arm64` tagged image in the `docker run` command
(ghcr.io/explosion/spacy-io:arm64).
### Building the Docker image
If you'd like to build the image locally, you can do so like this:
First build the Docker image. This only needs to be done on the first run
or when changes are made to `Dockerfile` or the website dependencies:
```bash
docker build -t spacy-io .
```
This will take some time, so if you want to use the prebuilt image you'll save a
bit of time.
You can then build and run the website with:
```bash
docker run -it \
--rm \
-v $(pwd):/home/node/website \
-p 3000:3000 \
spacy-io \
npm run dev -- -H 0.0.0.0
```
This will allow you to access the built website at http://0.0.0.0:3000/ in your
browser, and still edit code in your editor while having the site reflect those
changes.
## Project structure

View File

@ -12,6 +12,7 @@ menu:
- ['train', 'train']
- ['pretrain', 'pretrain']
- ['evaluate', 'evaluate']
- ['benchmark', 'benchmark']
- ['apply', 'apply']
- ['find-threshold', 'find-threshold']
- ['assemble', 'assemble']
@ -269,10 +270,10 @@ $ python -m spacy convert [input_file] [output_dir] [--converter] [--file-type]
| `--file-type`, `-t` | Type of file to create. Either `spacy` (default) for binary [`DocBin`](/api/docbin) data or `json` for v2.x JSON format. ~~str (option)~~ |
| `--n-sents`, `-n` | Number of sentences per document. Supported for: `conll`, `conllu`, `iob`, `ner` ~~int (option)~~ |
| `--seg-sents`, `-s` | Segment sentences. Supported for: `conll`, `ner` ~~bool (flag)~~ |
| `--base`, `-b`, `--model` | Trained spaCy pipeline for sentence segmentation to use as base (for `--seg-sents`). ~~Optional[str](option)~~ |
| `--base`, `-b`, `--model` | Trained spaCy pipeline for sentence segmentation to use as base (for `--seg-sents`). ~~Optional[str] (option)~~ |
| `--morphology`, `-m` | Enable appending morphology to tags. Supported for: `conllu` ~~bool (flag)~~ |
| `--merge-subtokens`, `-T` | Merge CoNLL-U subtokens ~~bool (flag)~~ |
| `--ner-map`, `-nm` | NER tag mapping (as JSON-encoded dict of entity types). Supported for: `conllu` ~~Optional[Path](option)~~ |
| `--ner-map`, `-nm` | NER tag mapping (as JSON-encoded dict of entity types). Supported for: `conllu` ~~Optional[Path] (option)~~ |
| `--lang`, `-l` | Language code (if tokenizer required). ~~Optional[str] \(option)~~ |
| `--concatenate`, `-C` | Concatenate output to a single file ~~bool (flag)~~ |
| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ |
@ -1135,8 +1136,19 @@ $ python -m spacy pretrain [config_path] [output_dir] [--code] [--resume-path] [
## evaluate {id="evaluate",version="2",tag="command"}
Evaluate a trained pipeline. Expects a loadable spaCy pipeline (package name or
path) and evaluation data in the
The `evaluate` subcommand is superseded by
[`spacy benchmark accuracy`](#benchmark-accuracy). `evaluate` is provided as an
alias to `benchmark accuracy` for compatibility.
## benchmark {id="benchmark", version="3.5"}
The `spacy benchmark` CLI includes commands for benchmarking the accuracy and
speed of your spaCy pipelines.
### accuracy {id="benchmark-accuracy", version="3.5", tag="command"}
Evaluate the accuracy of a trained pipeline. Expects a loadable spaCy pipeline
(package name or path) and evaluation data in the
[binary `.spacy` format](/api/data-formats#binary-training). The
`--gold-preproc` option sets up the evaluation examples with gold-standard
sentences and tokens for the predictions. Gold preprocessing helps the
@ -1147,7 +1159,7 @@ skew. To render a sample of dependency parses in a HTML file using the
`--displacy-path` argument.
```bash
$ python -m spacy evaluate [model] [data_path] [--output] [--code] [--gold-preproc] [--gpu-id] [--displacy-path] [--displacy-limit]
$ python -m spacy benchmark accuracy [model] [data_path] [--output] [--code] [--gold-preproc] [--gpu-id] [--displacy-path] [--displacy-limit]
```
| Name | Description |
@ -1163,6 +1175,29 @@ $ python -m spacy evaluate [model] [data_path] [--output] [--code] [--gold-prepr
| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ |
| **CREATES** | Training results and optional metrics and visualizations. |
### speed {id="benchmark-speed", version="3.5", tag="command"}
Benchmark the speed of a trained pipeline with a 95% confidence interval.
Expects a loadable spaCy pipeline (package name or path) and benchmark data in
the [binary `.spacy` format](/api/data-formats#binary-training). The pipeline is
warmed up before any measurements are taken.
```cli
$ python -m spacy benchmark speed [model] [data_path] [--batch_size] [--no-shuffle] [--gpu-id] [--batches] [--warmup]
```
| Name | Description |
| -------------------- | -------------------------------------------------------------------------------------------------------- |
| `model` | Pipeline to benchmark the speed of. Can be a package or a path to a data directory. ~~str (positional)~~ |
| `data_path` | Location of benchmark data in spaCy's [binary format](/api/data-formats#training). ~~Path (positional)~~ |
| `--batch-size`, `-b` | Set the batch size. If not set, the pipeline's batch size is used. ~~Optional[int] \(option)~~ |
| `--no-shuffle` | Do not shuffle documents in the benchmark data. ~~bool (flag)~~ |
| `--gpu-id`, `-g` | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~ |
| `--batches` | Number of batches to benchmark on. Defaults to `50`. ~~Optional[int] \(option)~~ |
| `--warmup`, `-w` | Iterations over the benchmark data for warmup. Defaults to `3` ~~Optional[int] \(option)~~ |
| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ |
| **PRINTS** | Pipeline speed in words per second with a 95% confidence interval. |
## apply {id="apply", version="3.5", tag="command"}
Applies a trained pipeline to data and stores the resulting annotated documents
@ -1176,24 +1211,23 @@ input formats are:
When a directory is provided it is traversed recursively to collect all files.
```cli
```bash
$ python -m spacy apply [model] [data-path] [output-file] [--code] [--text-key] [--force-overwrite] [--gpu-id] [--batch-size] [--n-process]
```
| Name | Description |
| ----------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `model` | Pipeline to apply to the data. Can be a package or a path to a data directory. ~~str (positional)~~ |
| `data_path` | Location of data to be evaluated in spaCy's [binary format](/api/data-formats#training), jsonl, or plain text. ~~Path (positional)~~ |
| `output-file`, `-o` | Output `DocBin` path. ~~str (positional)~~ |
| `--code`, `-c` <Tag variant="new">3</Tag> | Path to Python file with additional code to be imported. Allows [registering custom functions](/usage/training#custom-functions) for new architectures. ~~Optional[Path] \(option)~~ |
| `--text-key`, `-tk` | The key for `.jsonl` files to use to grab the texts from. Defaults to `text`. ~~Optional[str] \(option)~~ |
| `--force-overwrite`, `-F` | If the provided `output-file` already exists, then force `apply` to overwrite it. If this is `False` (default) then quits with a warning instead. ~~bool (flag)~~ |
| `--gpu-id`, `-g` | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~ |
| `--batch-size`, `-b` | Batch size to use for prediction. Defaults to `1`. ~~int (option)~~ |
| `--n-process`, `-n` | Number of processes to use for prediction. Defaults to `1`. ~~int (option)~~ |
| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ |
| **CREATES** | A `DocBin` with the annotations from the `model` for all the files found in `data-path`. |
| Name | Description |
| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `model` | Pipeline to apply to the data. Can be a package or a path to a data directory. ~~str (positional)~~ |
| `data_path` | Location of data to be evaluated in spaCy's [binary format](/api/data-formats#training), jsonl, or plain text. ~~Path (positional)~~ |
| `output-file`, `-o` | Output `DocBin` path. ~~str (positional)~~ |
| `--code`, `-c` | Path to Python file with additional code to be imported. Allows [registering custom functions](/usage/training#custom-functions) for new architectures. ~~Optional[Path] \(option)~~ |
| `--text-key`, `-tk` | The key for `.jsonl` files to use to grab the texts from. Defaults to `text`. ~~Optional[str] \(option)~~ |
| `--force-overwrite`, `-F` | If the provided `output-file` already exists, then force `apply` to overwrite it. If this is `False` (default) then quits with a warning instead. ~~bool (flag)~~ |
| `--gpu-id`, `-g` | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~ |
| `--batch-size`, `-b` | Batch size to use for prediction. Defaults to `1`. ~~int (option)~~ |
| `--n-process`, `-n` | Number of processes to use for prediction. Defaults to `1`. ~~int (option)~~ |
| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ |
| **CREATES** | A `DocBin` with the annotations from the `model` for all the files found in `data-path`. |
## find-threshold {id="find-threshold",version="3.5",tag="command"}

View File

@ -175,3 +175,68 @@ Yield examples from the data.
| ---------- | -------------------------------------- |
| `nlp` | The current `nlp` object. ~~Language~~ |
| **YIELDS** | The examples. ~~Example~~ |
## PlainTextCorpus {id="plaintextcorpus",tag="class",version="3.5.1"}
Iterate over documents from a plain text file. Can be used to read the raw text
corpus for language model
[pretraining](/usage/embeddings-transformers#pretraining). The expected file
format is:
- UTF-8 encoding
- One document per line
- Blank lines are ignored.
```text {title="Example"}
Can I ask where you work now and what you do, and if you enjoy it?
They may just pull out of the Seattle market completely, at least until they have autonomous vehicles.
My cynical view on this is that it will never be free to the public. Reason: what would be the draw of joining the military? Right now their selling point is free Healthcare and Education. Ironically both are run horribly and most, that I've talked to, come out wishing they never went in.
```
### PlainTextCorpus.\_\_init\_\_ {id="plaintextcorpus-init",tag="method"}
Initialize the reader.
> #### Example
>
> ```python
> from spacy.training import PlainTextCorpus
>
> corpus = PlainTextCorpus("./data/docs.txt")
> ```
>
> ```ini
> ### Example config
> [corpora.pretrain]
> @readers = "spacy.PlainTextCorpus.v1"
> path = "corpus/raw_text.txt"
> min_length = 0
> max_length = 0
> ```
| Name | Description |
| -------------- | -------------------------------------------------------------------------------------------------------------------------- |
| `path` | The directory or filename to read from. Expects newline-delimited documents in UTF8 format. ~~Union[str, Path]~~ |
| _keyword-only_ | |
| `min_length` | Minimum document length (in tokens). Shorter documents will be skipped. Defaults to `0`, which indicates no limit. ~~int~~ |
| `max_length` | Maximum document length (in tokens). Longer documents will be skipped. Defaults to `0`, which indicates no limit. ~~int~~ |
### PlainTextCorpus.\_\_call\_\_ {id="plaintextcorpus-call",tag="method"}
Yield examples from the data.
> #### Example
>
> ```python
> from spacy.training import PlainTextCorpus
> import spacy
>
> corpus = PlainTextCorpus("./docs.txt")
> nlp = spacy.blank("en")
> data = corpus(nlp)
> ```
| Name | Description |
| ---------- | -------------------------------------- |
| `nlp` | The current `nlp` object. ~~Language~~ |
| **YIELDS** | The examples. ~~Example~~ |

View File

@ -15,7 +15,7 @@ world". It requires a `KnowledgeBase`, as well as a function to generate
plausible candidates from that `KnowledgeBase` given a certain textual mention,
and a machine learning model to pick the right candidate, given the local
context of the mention. `EntityLinker` defaults to using the
[`InMemoryLookupKB`](/api/kb_in_memory) implementation.
[`InMemoryLookupKB`](/api/inmemorylookupkb) implementation.
## Assigned Attributes {id="assigned-attributes"}

View File

@ -43,7 +43,7 @@ The length of the fixed-size entity vectors in the knowledge base.
Add an entity to the knowledge base, specifying its corpus frequency and entity
vector, which should be of length
[`entity_vector_length`](/api/kb_in_memory#entity_vector_length).
[`entity_vector_length`](/api/inmemorylookupkb#entity_vector_length).
> #### Example
>
@ -79,8 +79,9 @@ frequency and entity vector for each entity.
Add an alias or mention to the knowledge base, specifying its potential KB
identifiers and their prior probabilities. The entity identifiers should refer
to entities previously added with [`add_entity`](/api/kb_in_memory#add_entity)
or [`set_entities`](/api/kb_in_memory#set_entities). The sum of the prior
to entities previously added with
[`add_entity`](/api/inmemorylookupkb#add_entity) or
[`set_entities`](/api/inmemorylookupkb#set_entities). The sum of the prior
probabilities should not exceed 1. Note that an empty string can not be used as
alias.
@ -156,7 +157,7 @@ Get a list of all aliases in the knowledge base.
Given a certain textual mention as input, retrieve a list of candidate entities
of type [`Candidate`](/api/kb#candidate). Wraps
[`get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates).
[`get_alias_candidates()`](/api/inmemorylookupkb#get_alias_candidates).
> #### Example
>
@ -174,7 +175,7 @@ of type [`Candidate`](/api/kb#candidate). Wraps
## InMemoryLookupKB.get_candidates_batch {id="get_candidates_batch",tag="method"}
Same as [`get_candidates()`](/api/kb_in_memory#get_candidates), but for an
Same as [`get_candidates()`](/api/inmemorylookupkb#get_candidates), but for an
arbitrary number of mentions. The [`EntityLinker`](/api/entitylinker) component
will call `get_candidates_batch()` instead of `get_candidates()`, if the config
parameter `candidates_batch_size` is greater or equal than 1.
@ -231,7 +232,7 @@ Given a certain entity ID, retrieve its pretrained entity vector.
## InMemoryLookupKB.get_vectors {id="get_vectors",tag="method"}
Same as [`get_vector()`](/api/kb_in_memory#get_vector), but for an arbitrary
Same as [`get_vector()`](/api/inmemorylookupkb#get_vector), but for an arbitrary
number of entity IDs.
The default implementation of `get_vectors()` executes `get_vector()` in a loop.

View File

@ -21,8 +21,8 @@ functions called by the [`EntityLinker`](/api/entitylinker) component.
<Infobox variant="warning">
This class was not abstract up to spaCy version 3.5. The `KnowledgeBase`
implementation up to that point is available as `InMemoryLookupKB` from 3.5
onwards.
implementation up to that point is available as
[`InMemoryLookupKB`](/api/inmemorylookupkb) from 3.5 onwards.
</Infobox>
@ -110,14 +110,15 @@ to you.
</Infobox>
From spaCy 3.5 on `KnowledgeBase` is an abstract class (with
[`InMemoryLookupKB`](/api/kb_in_memory) being a drop-in replacement) to allow
more flexibility in customizing knowledge bases. Some of its methods were moved
to [`InMemoryLookupKB`](/api/kb_in_memory) during this refactoring, one of those
being `get_alias_candidates()`. This method is now available as
[`InMemoryLookupKB.get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates).
Note: [`InMemoryLookupKB.get_candidates()`](/api/kb_in_memory#get_candidates)
[`InMemoryLookupKB`](/api/inmemorylookupkb) being a drop-in replacement) to
allow more flexibility in customizing knowledge bases. Some of its methods were
moved to [`InMemoryLookupKB`](/api/inmemorylookupkb) during this refactoring,
one of those being `get_alias_candidates()`. This method is now available as
[`InMemoryLookupKB.get_alias_candidates()`](/api/inmemorylookupkb#get_alias_candidates).
Note:
[`InMemoryLookupKB.get_candidates()`](/api/inmemorylookupkb#get_candidates)
defaults to
[`InMemoryLookupKB.get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates).
[`InMemoryLookupKB.get_alias_candidates()`](/api/inmemorylookupkb#get_alias_candidates).
## KnowledgeBase.get_vector {id="get_vector",tag="method"}

View File

@ -236,17 +236,17 @@ browser. Will run a simple web server.
> displacy.serve([doc1, doc2], style="dep")
> ```
| Name | Description |
| ------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `docs` | Document(s) or span(s) to visualize. ~~Union[Iterable[Union[Doc, Span]], Doc, Span]~~ |
| `style` | Visualization style, `"dep"`, `"ent"` or `"span"` <Tag variant="new">3.3</Tag>. Defaults to `"dep"`. ~~str~~ |
| `page` | Render markup as full HTML page. Defaults to `True`. ~~bool~~ |
| `minify` | Minify HTML markup. Defaults to `False`. ~~bool~~ |
| `options` | [Visualizer-specific options](#displacy_options), e.g. colors. ~~Dict[str, Any]~~ |
| `manual` | Don't parse `Doc` and instead expect a dict or list of dicts. [See here](/usage/visualizers#manual-usage) for formats and examples. Defaults to `False`. ~~bool~~ |
| `port` | Port to serve visualization. Defaults to `5000`. ~~int~~ |
| `host` | Host to serve visualization. Defaults to `"0.0.0.0"`. ~~str~~ |
| `auto_select_port` | If `True`, automatically switch to a different port if the specified port is already in use. Defaults to `False`. ~~bool~~ |
| Name | Description |
| ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `docs` | Document(s) or span(s) to visualize. ~~Union[Iterable[Union[Doc, Span]], Doc, Span]~~ |
| `style` <Tag variant="new">3.3</Tag> | Visualization style, `"dep"`, `"ent"` or `"span"`. Defaults to `"dep"`. ~~str~~ |
| `page` | Render markup as full HTML page. Defaults to `True`. ~~bool~~ |
| `minify` | Minify HTML markup. Defaults to `False`. ~~bool~~ |
| `options` | [Visualizer-specific options](#displacy_options), e.g. colors. ~~Dict[str, Any]~~ |
| `manual` | Don't parse `Doc` and instead expect a dict or list of dicts. [See here](/usage/visualizers#manual-usage) for formats and examples. Defaults to `False`. ~~bool~~ |
| `port` | Port to serve visualization. Defaults to `5000`. ~~int~~ |
| `host` | Host to serve visualization. Defaults to `"0.0.0.0"`. ~~str~~ |
| `auto_select_port` <Tag variant="new">3.5</Tag> | If `True`, automatically switch to a different port if the specified port is already in use. Defaults to `False`. ~~bool~~ |
### displacy.render {id="displacy.render",tag="method",version="2"}

View File

@ -81,7 +81,7 @@ operates on a `Doc` and gives you access to the matched tokens **in context**.
| ------------------------------------------------ | -------------------------------------------------------------------------------------------------- |
| [`Corpus`](/api/corpus) | Class for managing annotated corpora for training and evaluation data. |
| [`KnowledgeBase`](/api/kb) | Abstract base class for storage and retrieval of data for entity linking. |
| [`InMemoryLookupKB`](/api/kb_in_memory) | Implementation of `KnowledgeBase` storing all data in memory. |
| [`InMemoryLookupKB`](/api/inmemorylookupkb) | Implementation of `KnowledgeBase` storing all data in memory. |
| [`Candidate`](/api/kb#candidate) | Object associating a textual mention with a specific entity contained in a `KnowledgeBase`. |
| [`Lookups`](/api/lookups) | Container for convenient access to large lookup tables and dictionaries. |
| [`MorphAnalysis`](/api/morphology#morphanalysis) | A morphological analysis. |

View File

@ -134,6 +134,7 @@ useful for your purpose. Here are some important considerations to keep in mind:
<Image
src="/images/sense2vec.jpg"
href="https://github.com/explosion/sense2vec"
alt="sense2vec Screenshot"
/>
[`sense2vec`](https://github.com/explosion/sense2vec) is a library developed by

View File

@ -113,6 +113,7 @@ code.
<Image
src="/images/thinc_mypy.jpg"
href="https://thinc.ai/docs/usage-type-checking#linting"
alt="Screenshot of Thinc type checking in VSCode with mypy"
/>
</Accordion>

View File

@ -943,7 +943,7 @@ full embedded visualizer, as well as individual components.
> $ pip install spacy-streamlit --pre
> ```
![](/images/spacy-streamlit.png)
![Screenshot of the spacy-streamlit package in Streamlit](/images/spacy-streamlit.png)
Using [`spacy-streamlit`](https://github.com/explosion/spacy-streamlit), your
projects can easily define their own scripts that spin up an interactive

View File

@ -384,14 +384,14 @@ the more specific attributes `FUZZY1`..`FUZZY9` you can specify the maximum
allowed edit distance directly.
```python
# Match lowercase with fuzzy matching (allows 2 edits)
# Match lowercase with fuzzy matching (allows 3 edits)
pattern = [{"LOWER": {"FUZZY": "definitely"}}]
# Match custom attribute values with fuzzy matching (allows 2 edits)
# Match custom attribute values with fuzzy matching (allows 3 edits)
pattern = [{"_": {"country": {"FUZZY": "Kyrgyzstan"}}}]
# Match with exact Levenshtein edit distance limits (allows 3 edits)
pattern = [{"_": {"country": {"FUZZY3": "Kyrgyzstan"}}}]
# Match with exact Levenshtein edit distance limits (allows 4 edits)
pattern = [{"_": {"country": {"FUZZY4": "Kyrgyzstan"}}}]
```
#### Regex and fuzzy matching with lists {id="regex-fuzzy-lists", version="3.5"}

View File

@ -304,6 +304,28 @@ installed in the same environment that's it.
| `spacy_lookups` | Group of entry points for custom [`Lookups`](/api/lookups), including lemmatizer data. Used by spaCy's [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data) package. |
| [`spacy_displacy_colors`](#entry-points-displacy) | Group of entry points of custom label colors for the [displaCy visualizer](/usage/visualizers#ent). The key name doesn't matter, but it should point to a dict of labels and color values. Useful for custom models that predict different entity types. |
### Loading probability tables into existing models
You can load a probability table from [spacy-lookups-data](https://github.com/explosion/spacy-lookups-data) into an existing spaCy model like `en_core_web_sm`.
```python
# Requirements: pip install spacy-lookups-data
import spacy
from spacy.lookups import load_lookups
nlp = spacy.load("en_core_web_sm")
lookups = load_lookups("en", ["lexeme_prob"])
nlp.vocab.lookups.add_table("lexeme_prob", lookups.get_table("lexeme_prob"))
```
When training a model from scratch you can also specify probability tables in the `config.cfg`.
```ini {title="config.cfg (excerpt)"}
[initialize.lookups]
@misc = "spacy.LookupsDataLoader.v1"
lang = ${nlp.lang}
tables = ["lexeme_prob"]
```
### Custom components via entry points {id="entry-points-components"}
When you load a pipeline, spaCy will generally use its `config.cfg` to set up
@ -684,10 +706,15 @@ If your pipeline includes
[custom components](/usage/processing-pipelines#custom-components), model
architectures or other [code](/usage/training#custom-code), those functions need
to be registered **before** your pipeline is loaded. Otherwise, spaCy won't know
how to create the objects referenced in the config. The
[`spacy package`](/api/cli#package) command lets you provide one or more paths
to Python files containing custom registered functions using the `--code`
argument.
how to create the objects referenced in the config. If you're loading your own
pipeline in Python, you can make custom components available just by importing
the code that defines them before calling
[`spacy.load`](/api/top-level#spacy.load). This is also how the `--code`
argument to CLI commands works.
With the [`spacy package`](/api/cli#package) command, you can provide one or
more paths to Python files containing custom registered functions using the
`--code` argument.
> #### \_\_init\_\_.py (excerpt)
>

View File

@ -567,7 +567,10 @@ If you would like to use the spaCy logo on your site, please get in touch and
ask us first. However, if you want to show support and tell others that your
project is using spaCy, you can grab one of our **spaCy badges** here:
<img src={`https://img.shields.io/badge/built%20with-spaCy-09a3d5.svg`} />
<img
src={`https://img.shields.io/badge/built%20with-spaCy-09a3d5.svg`}
alt="Built with spaCy"
/>
```markdown
[![Built with spaCy](https://img.shields.io/badge/built%20with-spaCy-09a3d5.svg)](https://spacy.io)
@ -575,8 +578,9 @@ project is using spaCy, you can grab one of our **spaCy badges** here:
<img
src={`https://img.shields.io/badge/made%20with%20❤%20and-spaCy-09a3d5.svg`}
alt="Made with love and spaCy"
/>
```markdown
[![Built with spaCy](https://img.shields.io/badge/made%20with%20❤%20and-spaCy-09a3d5.svg)](https://spacy.io)
[![Made with love and spaCy](https://img.shields.io/badge/made%20with%20❤%20and-spaCy-09a3d5.svg)](https://spacy.io)
```

215
website/docs/usage/v3-5.mdx Normal file
View File

@ -0,0 +1,215 @@
---
title: What's New in v3.5
teaser: New features and how to upgrade
menu:
- ['New Features', 'features']
- ['Upgrading Notes', 'upgrading']
---
## New features {id="features",hidden="true"}
spaCy v3.5 introduces three new CLI commands, `apply`, `benchmark` and
`find-threshold`, adds fuzzy matching, provides improvements to our entity
linking functionality, and includes a range of language updates and bug fixes.
### New CLI commands {id="cli"}
#### apply CLI
The [`apply` CLI](/api/cli#apply) can be used to apply a pipeline to one or more
`.txt`, `.jsonl` or `.spacy` input files, saving the annotated docs in a single
`.spacy` file.
```bash
$ spacy apply en_core_web_sm my_texts/ output.spacy
```
#### benchmark CLI
The [`benchmark` CLI](/api/cli#benchmark) has been added to extend the existing
`evaluate` functionality with a wider range of profiling subcommands.
The `benchmark accuracy` CLI is introduced as an alias for `evaluate`. The new
`benchmark speed` CLI performs warmup rounds before measuring the speed in words
per second on batches of randomly shuffled documents from the provided data.
```bash
$ spacy benchmark speed my_pipeline data.spacy
```
The output is the mean performance using batches (`nlp.pipe`) with a 95%
confidence interval, e.g., profiling `en_core_web_sm` on CPU:
```none
Outliers: 2.0%, extreme outliers: 0.0%
Mean: 18904.1 words/s (95% CI: -256.9 +244.1)
```
#### find-threshold CLI
The [`find-threshold` CLI](/api/cli#find-threshold) runs a series of trials
across threshold values from `0.0` to `1.0` and identifies the best threshold
for the provided score metric.
The following command runs 20 trials for the `spancat` component in
`my_pipeline`, recording the `spans_sc_f` score for each value of the threshold
`[components.spancat.threshold]` from `0.0` to `1.0`:
```bash
$ spacy find-threshold my_pipeline data.spacy spancat threshold spans_sc_f --n_trials 20
```
The `find-threshold` CLI can be used with `textcat_multilabel`, `spancat` and
custom components with thresholds that are applied while predicting or scoring.
### Fuzzy matching {id="fuzzy"}
New `FUZZY` operators support [fuzzy matching](/usage/rule-based-matching#fuzzy)
with the `Matcher`. By default, the `FUZZY` operator allows a Levenshtein edit
distance of 2 and up to 30% of the pattern string length. `FUZZY1`..`FUZZY9` can
be used to specify the exact number of allowed edits.
```python
# Match lowercase with fuzzy matching (allows up to 3 edits)
pattern = [{"LOWER": {"FUZZY": "definitely"}}]
# Match custom attribute values with fuzzy matching (allows up to 3 edits)
pattern = [{"_": {"country": {"FUZZY": "Kyrgyzstan"}}}]
# Match with exact Levenshtein edit distance limits (allows up to 4 edits)
pattern = [{"_": {"country": {"FUZZY4": "Kyrgyzstan"}}}]
```
Note that `FUZZY` uses Levenshtein edit distance rather than Damerau-Levenshtein
edit distance, so a transposition like `teh` for `the` counts as two edits, one
insertion and one deletion.
If you'd prefer an alternate fuzzy matching algorithm, you can provide your own
custom method to the `Matcher` or as a config option for an entity ruler and
span ruler.
### FUZZY and REGEX with lists {id="fuzzy-regex-lists"}
The `FUZZY` and `REGEX` operators are also now supported for lists with `IN` and
`NOT_IN`:
```python
pattern = [{"TEXT": {"FUZZY": {"IN": ["awesome", "cool", "wonderful"]}}}]
pattern = [{"TEXT": {"REGEX": {"NOT_IN": ["^awe(some)?$", "^wonder(ful)?"]}}}]
```
### Entity linking generalization {id="el"}
The knowledge base used for entity linking is now easier to customize and has a
new default implementation [`InMemoryLookupKB`](/api/inmemorylookupkb).
### Additional features and improvements {id="additional-features-and-improvements"}
- Language updates:
- Extended support for Slovenian
- Fixed lookup fallback for French and Catalan lemmatizers
- Switch Russian and Ukrainian lemmatizers to `pymorphy3`
- Support for editorial punctuation in Ancient Greek
- Update to Russian tokenizer exceptions
- Small fix for Dutch stop words
- Allow up to `typer` v0.7.x, `mypy` 0.990 and `typing_extensions` v4.4.x.
- New `spacy.ConsoleLogger.v3` with expanded progress
[tracking](/api/top-level#ConsoleLogger).
- Improved scoring behavior for `textcat` with `spacy.textcat_scorer.v2` and
`spacy.textcat_multilabel_scorer.v2`.
- Updates so that downstream components can train properly on a frozen `tok2vec`
or `transformer` layer.
- Allow interpolation of variables in directory names in projects.
- Support for local file system [remotes](/usage/projects#remote) for projects.
- Improve UX around `displacy.serve` when the default port is in use.
- Optional `before_update` callback that is invoked at the start of each
[training step](/api/data-formats#config-training).
- Improve performance of `SpanGroup` and fix typing issues for `SpanGroup` and
`Span` objects.
- Patch a
[security vulnerability](https://github.com/advisories/GHSA-gw9q-c7gh-j9vm) in
extracting tar files.
- Add equality definition for `Vectors`.
- Ensure `Vocab.to_disk` respects the exclude setting for `lookups` and
`vectors`.
- Correctly handle missing annotations in the edit tree lemmatizer.
### Trained pipeline updates {id="pipelines"}
- The CNN pipelines add `IS_SPACE` as a `tok2vec` feature for `tagger` and
`morphologizer` components to improve tagging of non-whitespace vs. whitespace
tokens.
- The transformer pipelines require `spacy-transformers` v1.2, which uses the
exact alignment from `tokenizers` for fast tokenizers instead of the heuristic
alignment from `spacy-alignments`. For all trained pipelines except
`ja_core_news_trf`, the alignments between spaCy tokens and transformer tokens
may be slightly different. More details about the `spacy-transformers` changes
in the
[v1.2.0 release notes](https://github.com/explosion/spacy-transformers/releases/tag/v1.2.0).
## Notes about upgrading from v3.4 {id="upgrading"}
### Validation of textcat values {id="textcat-validation"}
An error is now raised when unsupported values are given as input to train a
`textcat` or `textcat_multilabel` model - ensure that values are `0.0` or `1.0`
as explained in the [docs](/api/textcategorizer#assigned-attributes).
### Updated scorers for tokenization and textcat {id="scores"}
We fixed a bug that inflated the `token_acc` scores in v3.0-v3.4. The reported
`token_acc` will drop from v3.4 to v3.5, but if `token_p/r/f` stay the same,
your tokenization performance has not changed from v3.4.
For new `textcat` or `textcat_multilabel` configs, the new default `v2` scorers:
- ignore `threshold` for `textcat`, so the reported `cats_p/r/f` may increase
slightly in v3.5 even though the underlying predictions are unchanged
- report the performance of only the **final** `textcat` or `textcat_multilabel`
component in the pipeline by default
- allow custom scorers to be used to score multiple `textcat` and
`textcat_multilabel` components with `Scorer.score_cats` by restricting the
evaluation to the component's provided labels
### Pipeline package version compatibility {id="version-compat"}
> #### Using legacy implementations
>
> In spaCy v3, you'll still be able to load and reference legacy implementations
> via [`spacy-legacy`](https://github.com/explosion/spacy-legacy), even if the
> components or architectures change and newer versions are available in the
> core library.
When you're loading a pipeline package trained with an earlier version of spaCy
v3, you will see a warning telling you that the pipeline may be incompatible.
This doesn't necessarily have to be true, but we recommend running your
pipelines against your test suite or evaluation data to make sure there are no
unexpected results.
If you're using one of the [trained pipelines](/models) we provide, you should
run [`spacy download`](/api/cli#download) to update to the latest version. To
see an overview of all installed packages and their compatibility, you can run
[`spacy validate`](/api/cli#validate).
If you've trained your own custom pipeline and you've confirmed that it's still
working as expected, you can update the spaCy version requirements in the
[`meta.json`](/api/data-formats#meta):
```diff
- "spacy_version": ">=3.4.0,<3.5.0",
+ "spacy_version": ">=3.4.0,<3.6.0",
```
### Updating v3.4 configs
To update a config from spaCy v3.4 with the new v3.5 settings, run
[`init fill-config`](/api/cli#init-fill-config):
```cli
$ python -m spacy init fill-config config-v3.4.cfg config-v3.5.cfg
```
In many cases ([`spacy train`](/api/cli#train),
[`spacy.load`](/api/top-level#spacy.load)), the new defaults will be filled in
automatically, but you'll need to fill in the new settings to run
[`debug config`](/api/cli#debug) and [`debug data`](/api/cli#debug-data).

View File

@ -437,6 +437,6 @@ Alternatively, if you're using [Streamlit](https://streamlit.io), check out the
helps you integrate spaCy visualizations into your apps. It includes a full
embedded visualizer, as well as individual components.
![](/images/spacy-streamlit.png)
![Screenshot of the spacy-streamlit package in Streamlit](/images/spacy-streamlit.png)
</Grid>

View File

@ -13,7 +13,8 @@
{ "text": "New in v3.1", "url": "/usage/v3-1" },
{ "text": "New in v3.2", "url": "/usage/v3-2" },
{ "text": "New in v3.3", "url": "/usage/v3-3" },
{ "text": "New in v3.4", "url": "/usage/v3-4" }
{ "text": "New in v3.4", "url": "/usage/v3-4" },
{ "text": "New in v3.5", "url": "/usage/v3-5" }
]
},
{
@ -129,6 +130,7 @@
"items": [
{ "text": "Attributes", "url": "/api/attributes" },
{ "text": "Corpus", "url": "/api/corpus" },
{ "text": "InMemoryLookupKB", "url": "/api/inmemorylookupkb" },
{ "text": "KnowledgeBase", "url": "/api/kb" },
{ "text": "Lookups", "url": "/api/lookups" },
{ "text": "MorphAnalysis", "url": "/api/morphology#morphanalysis" },

View File

@ -27,7 +27,7 @@
"indexName": "spacy"
},
"binderUrl": "explosion/spacy-io-binder",
"binderVersion": "3.4",
"binderVersion": "3.5",
"sections": [
{ "id": "usage", "title": "Usage Documentation", "theme": "blue" },
{ "id": "models", "title": "Models Documentation", "theme": "blue" },

View File

@ -2381,7 +2381,7 @@
"author": "Nikita Kitaev",
"author_links": {
"github": "nikitakit",
"website": " http://kitaev.io"
"website": "http://kitaev.io"
},
"category": ["research", "pipeline"]
},

View File

@ -17,7 +17,7 @@ export default function App({ Component, pageProps }: AppProps) {
<link rel="manifest" href="/manifest.webmanifest" />
<meta
name="viewport"
content="width=device-width, initial-scale=1.0, minimum-scale=1 maximum-scale=1.0, user-scalable=0, shrink-to-fit=no, viewport-fit=cover"
content="width=device-width, initial-scale=1.0, minimum-scale=1, maximum-scale=5.0, shrink-to-fit=no, viewport-fit=cover"
/>
<meta name="theme-color" content="#09a3d5" />
<link rel="apple-touch-icon" sizes="192x192" href="/icons/icon-192x192.png" />

View File

@ -13,7 +13,7 @@ import {
LandingBanner,
} from '../src/components/landing'
import { H2 } from '../src/components/typography'
import { InlineCode } from '../src/components/code'
import { InlineCode } from '../src/components/inlineCode'
import { Ul, Li } from '../src/components/list'
import Button from '../src/components/button'
import Link from '../src/components/link'
@ -89,8 +89,8 @@ const Landing = () => {
</LandingCard>
<LandingCard title="Awesome ecosystem" url="/usage/projects" button="Read more">
In the five years since its release, spaCy has become an industry standard with
a huge ecosystem. Choose from a variety of plugins, integrate with your machine
Since its release in 2015, spaCy has become an industry standard with a huge
ecosystem. Choose from a variety of plugins, integrate with your machine
learning stack and build custom components and workflows.
</LandingCard>
</LandingGrid>
@ -162,7 +162,7 @@ const Landing = () => {
small
>
<p>
<Link to="https://prodi.gy" hidden>
<Link to="https://prodi.gy" noLinkLayout>
<ImageFill
image={prodigyImage}
alt="Prodigy: Radically efficient machine teaching"
@ -206,7 +206,10 @@ const Landing = () => {
<LandingGrid cols={2}>
<LandingCol>
<Link to="/usage/projects" hidden>
<ImageFill image={projectsImage} />
<ImageFill
image={projectsImage}
alt="Illustration of project workflow and commands"
/>
</Link>
<br />
<br />

View File

@ -33,7 +33,7 @@ export default function Accordion({ title, id, expanded = false, spaced = false,
<Link
to={`#${id}`}
className={classes.anchor}
hidden
noLinkLayout
onClick={(event) => event.stopPropagation()}
>
&para;

View File

@ -1,6 +1,7 @@
import React from 'react'
import PropTypes from 'prop-types'
import classNames from 'classnames'
import ImageNext from 'next/image'
import Link from './link'
import { H5 } from './typography'
@ -10,7 +11,7 @@ export default function Card({ title, to, image, header, small, onClick, childre
return (
<div className={classNames(classes.root, { [classes.small]: !!small })}>
{header && (
<Link to={to} onClick={onClick} hidden>
<Link to={to} onClick={onClick} noLinkLayout>
{header}
</Link>
)}
@ -18,18 +19,17 @@ export default function Card({ title, to, image, header, small, onClick, childre
<H5 className={classes.title}>
{image && (
<div className={classes.image}>
{/* eslint-disable-next-line @next/next/no-img-element */}
<img src={image} width={35} alt="" />
<ImageNext src={image} height={35} width={35} alt={`${title} Logo`} />
</div>
)}
{title && (
<Link to={to} onClick={onClick} hidden>
<Link to={to} onClick={onClick} noLinkLayout>
{title}
</Link>
)}
</H5>
)}
<Link to={to} onClick={onClick} hidden>
<Link to={to} onClick={onClick} noLinkLayout>
{children}
</Link>
</div>

View File

@ -14,96 +14,16 @@ import 'prismjs/components/prism-markdown.min.js'
import 'prismjs/components/prism-python.min.js'
import 'prismjs/components/prism-yaml.min.js'
import CUSTOM_TYPES from '../../meta/type-annotations.json'
import { isString, htmlToReact } from './util'
import { isString } from './util'
import Link, { OptionalLink } from './link'
import GitHubCode from './github'
import Juniper from './juniper'
import classes from '../styles/code.module.sass'
import siteMetadata from '../../meta/site.json'
import { binderBranch } from '../../meta/dynamicMeta.mjs'
import dynamic from 'next/dynamic'
const WRAP_THRESHOLD = 30
const CLI_GROUPS = ['init', 'debug', 'project', 'ray', 'huggingface-hub']
const CodeBlock = (props) => (
<Pre>
<Code {...props} />
</Pre>
)
export default CodeBlock
export const Pre = (props) => {
return <pre className={classes['pre']}>{props.children}</pre>
}
export const InlineCode = ({ wrap = false, className, children, ...props }) => {
const codeClassNames = classNames(classes['inline-code'], className, {
[classes['wrap']]: wrap || (isString(children) && children.length >= WRAP_THRESHOLD),
})
return (
<code className={codeClassNames} {...props}>
{children}
</code>
)
}
InlineCode.propTypes = {
wrap: PropTypes.bool,
className: PropTypes.string,
children: PropTypes.node,
}
function linkType(el, showLink = true) {
if (!isString(el) || !el.length) return el
const elStr = el.trim()
if (!elStr) return el
const typeUrl = CUSTOM_TYPES[elStr]
const url = typeUrl == true ? DEFAULT_TYPE_URL : typeUrl
const ws = el[0] == ' '
return url && showLink ? (
<Fragment>
{ws && ' '}
<Link to={url} hideIcon>
{elStr}
</Link>
</Fragment>
) : (
el
)
}
export const TypeAnnotation = ({ lang = 'python', link = true, children }) => {
// Hacky, but we're temporarily replacing a dot to prevent it from being split during highlighting
const TMP_DOT = '۔'
const code = Array.isArray(children) ? children.join('') : children || ''
const [rawText, meta] = code.split(/(?= \(.+\)$)/)
const rawStr = rawText.replace(/\./g, TMP_DOT)
const rawHtml =
lang === 'none' || !code ? code : Prism.highlight(rawStr, Prism.languages[lang], lang)
const html = rawHtml.replace(new RegExp(TMP_DOT, 'g'), '.').replace(/\n/g, ' ')
const result = htmlToReact(html)
const elements = Array.isArray(result) ? result : [result]
const annotClassNames = classNames(
'type-annotation',
`language-${lang}`,
classes['inline-code'],
classes['type-annotation'],
{
[classes['wrap']]: code.length >= WRAP_THRESHOLD,
}
)
return (
<span className={annotClassNames} role="code" aria-label="Type annotation">
{elements.map((el, i) => (
<Fragment key={i}>{linkType(el, !!link)}</Fragment>
))}
{meta && <span className={classes['type-annotation-meta']}>{meta}</span>}
</span>
)
}
const splitLines = (children) => {
const listChildrenPerLine = []
@ -235,7 +155,7 @@ const handlePromot = ({ lineFlat, prompt }) => {
<Fragment key={j}>
{j !== 0 && ' '}
<span className={itemClassNames}>
<OptionalLink hidden hideIcon to={url}>
<OptionalLink noLinkLayout hideIcon to={url}>
{text}
</OptionalLink>
</span>
@ -288,7 +208,7 @@ const addLineHighlight = (children, highlight) => {
})
}
export const CodeHighlighted = ({ children, highlight, lang }) => {
const CodeHighlighted = ({ children, highlight, lang }) => {
const [html, setHtml] = useState()
useEffect(
@ -305,7 +225,7 @@ export const CodeHighlighted = ({ children, highlight, lang }) => {
return <>{html}</>
}
export class Code extends React.Component {
export default class Code extends React.Component {
static defaultProps = {
lang: 'none',
executable: null,
@ -354,6 +274,8 @@ export class Code extends React.Component {
}
}
const JuniperDynamic = dynamic(() => import('./juniper'))
const JuniperWrapper = ({ title, lang, children }) => {
const { binderUrl, binderVersion } = siteMetadata
const juniperTitle = title || 'Editable Code'
@ -363,13 +285,13 @@ const JuniperWrapper = ({ title, lang, children }) => {
{juniperTitle}
<span className={classes['juniper-meta']}>
spaCy v{binderVersion} &middot; Python 3 &middot; via{' '}
<Link to="https://mybinder.org/" hidden>
<Link to="https://mybinder.org/" noLinkLayout>
Binder
</Link>
</span>
</h4>
<Juniper
<JuniperDynamic
repo={binderUrl}
branch={binderBranch}
lang={lang}
@ -381,7 +303,7 @@ const JuniperWrapper = ({ title, lang, children }) => {
}}
>
{children}
</Juniper>
</JuniperDynamic>
</div>
)
}

View File

@ -0,0 +1,14 @@
import React from 'react'
import Code from './codeDynamic'
import classes from '../styles/code.module.sass'
export const Pre = (props) => {
return <pre className={classes['pre']}>{props.children}</pre>
}
const CodeBlock = (props) => (
<Pre>
<Code {...props} />
</Pre>
)
export default CodeBlock

View File

@ -0,0 +1,5 @@
import dynamic from 'next/dynamic'
export default dynamic(() => import('./code'), {
loading: () => <div style={{ color: 'white', padding: '1rem' }}>Loading...</div>,
})

View File

@ -14,7 +14,7 @@ export function copyToClipboard(ref, callback) {
}
}
export default function CopyInput({ text, prefix }) {
export default function CopyInput({ text, description, prefix }) {
const isClient = typeof window !== 'undefined'
const [supportsCopy, setSupportsCopy] = useState(false)
@ -41,6 +41,7 @@ export default function CopyInput({ text, prefix }) {
defaultValue={text}
rows={1}
onClick={selectText}
aria-label={description}
/>
{supportsCopy && (
<button title="Copy to clipboard" onClick={onClick}>

View File

@ -5,8 +5,8 @@ import ImageNext from 'next/image'
import Link from './link'
import Button from './button'
import { InlineCode } from './code'
import { MarkdownToReact } from './util'
import { InlineCode } from './inlineCode'
import MarkdownToReact from './markdownToReactDynamic'
import classes from '../styles/embed.module.sass'
@ -88,10 +88,16 @@ const Image = ({ src, alt, title, href, ...props }) => {
const markdownComponents = { code: InlineCode, p: Fragment, a: Link }
return (
<figure className="gatsby-resp-image-figure">
<Link className={linkClassNames} href={href ?? src} hidden forceExternal>
{/* eslint-disable-next-line @next/next/no-img-element */}
{href ? (
<Link className={linkClassNames} href={href} noLinkLayout forceExternal>
{/* eslint-disable-next-line @next/next/no-img-element */}
<img className={classes.image} src={src} alt={alt} width={650} height="auto" />
</Link>
) : (
/* eslint-disable-next-line @next/next/no-img-element */
<img className={classes.image} src={src} alt={alt} width={650} height="auto" />
</Link>
)}
{title && (
<figcaption className="gatsby-resp-image-figcaption">
<MarkdownToReact markdown={title} />
@ -104,7 +110,7 @@ const Image = ({ src, alt, title, href, ...props }) => {
const ImageFill = ({ image, ...props }) => {
return (
<span
class={classes['figure-fill']}
className={classes['figure-fill']}
style={{ paddingBottom: `${(image.height / image.width) * 100}%` }}
>
<ImageNext src={image.src} {...props} fill />

View File

@ -21,7 +21,7 @@ export default function Footer({ wide = false }) {
<li className={classes.label}>{label}</li>
{items.map(({ text, url }, j) => (
<li key={j}>
<Link to={url} hidden>
<Link to={url} noLinkLayout>
{text}
</Link>
</li>
@ -42,14 +42,14 @@ export default function Footer({ wide = false }) {
<div className={classNames(classes.content, classes.copy)}>
<span>
&copy; 2016-{new Date().getFullYear()}{' '}
<Link to={companyUrl} hidden>
<Link to={companyUrl} noLinkLayout>
{company}
</Link>
</span>
<Link to={companyUrl} aria-label={company} hidden className={classes.logo}>
<Link to={companyUrl} aria-label={company} noLinkLayout className={classes.logo}>
<SVG src={explosionLogo.src} width={45} height={45} />
</Link>
<Link to={`${companyUrl}/legal`} hidden>
<Link to={`${companyUrl}/legal`} noLinkLayout>
Legal / Imprint
</Link>
</div>

View File

@ -5,7 +5,7 @@ import classNames from 'classnames'
import Icon from './icon'
import Link from './link'
import classes from '../styles/code.module.sass'
import { Code } from './code'
import Code from './codeDynamic'
const defaultErrorMsg = `Can't fetch code example from GitHub :(
@ -42,7 +42,7 @@ const GitHubCode = ({ url, lang, errorMsg = defaultErrorMsg, className }) => {
return (
<>
<header className={classes.header}>
<Link to={url} hidden>
<Link to={url} noLinkLayout>
<Icon name="github" width={16} inline />
<code
className={classNames(classes['inline-code'], classes['inline-code-dark'])}

View File

@ -0,0 +1,12 @@
import { Parser as HtmlToReactParser } from 'html-to-react'
const htmlToReactParser = new HtmlToReactParser()
/**
* Convert raw HTML to React elements
* @param {string} html - The HTML markup to convert.
* @returns {Node} - The converted React elements.
*/
export default function HtmlToReact(props) {
return htmlToReactParser.parse(props.children)
}

View File

@ -0,0 +1,23 @@
import React from 'react'
import PropTypes from 'prop-types'
import classNames from 'classnames'
import { isString } from './util'
import classes from '../styles/code.module.sass'
const WRAP_THRESHOLD = 30
export const InlineCode = ({ wrap = false, className, children, ...props }) => {
const codeClassNames = classNames(classes['inline-code'], className, {
[classes['wrap']]: wrap || (isString(children) && children.length >= WRAP_THRESHOLD),
})
return (
<code className={codeClassNames} {...props}>
{children}
</code>
)
}
InlineCode.propTypes = {
wrap: PropTypes.bool,
className: PropTypes.string,
children: PropTypes.node,
}

View File

@ -12,17 +12,17 @@ const spacyTheme = createTheme({
theme: 'dark',
settings: {
background: 'var(--color-front)',
foreground: 'var(--color-subtle)',
foreground: 'var(--color-subtle-on-dark)',
caret: 'var(--color-theme-dark)',
selection: 'var(--color-theme)',
selectionMatch: 'var(--color-theme)',
selection: 'var(--color-theme-dark)',
selectionMatch: 'var(--color-theme-dark)',
gutterBackground: 'var(--color-front)',
gutterForeground: 'var(--color-subtle)',
gutterForeground: 'var(--color-subtle-on-dark)',
fontFamily: 'var(--font-code)',
},
styles: [
{ tag: t.comment, color: 'var(--syntax-comment)' },
{ tag: t.variableName, color: 'var(--color-subtle)' },
{ tag: t.variableName, color: 'var(--color-subtle-on-dark)' },
{ tag: [t.string, t.special(t.brace)], color: '#fff' },
{ tag: t.number, color: 'var(--syntax-number)' },
{ tag: t.string, color: 'var(--syntax-selector)' },

View File

@ -1,17 +1,17 @@
import React from 'react'
import classNames from 'classnames'
import patternDefault from '../images/pattern_blue.jpg'
import patternNightly from '../images/pattern_nightly.jpg'
import patternLegacy from '../images/pattern_legacy.jpg'
import overlayDefault from '../images/pattern_landing.jpg'
import overlayNightly from '../images/pattern_landing_nightly.jpg'
import overlayLegacy from '../images/pattern_landing_legacy.jpg'
import patternDefault from '../images/pattern_blue.png'
import patternNightly from '../images/pattern_nightly.png'
import patternLegacy from '../images/pattern_legacy.png'
import overlayDefault from '../images/pattern_landing.png'
import overlayNightly from '../images/pattern_landing_nightly.png'
import overlayLegacy from '../images/pattern_landing_legacy.png'
import Grid from './grid'
import { Content } from './main'
import Button from './button'
import CodeBlock from './code'
import CodeBlock from './codeBlock'
import { H1, H2, H3 } from './typography'
import Link from './link'
import classes from '../styles/landing.module.sass'
@ -110,6 +110,7 @@ export const LandingBanner = ({
})
const style = {
'--color-theme': background,
'--color-theme-dark': background,
'--color-back': color,
backgroundImage: backgroundImage ? `url(${backgroundImage})` : null,
}
@ -124,7 +125,7 @@ export const LandingBanner = ({
<span className={classes['label']}>{label}</span>
</div>
)}
<Link to={to} hidden>
<Link to={to} noLinkLayout>
{title}
</Link>
</Heading>

View File

@ -26,7 +26,7 @@ export default function Link({
to,
href,
onClick,
hidden = false,
noLinkLayout = false,
hideIcon = false,
ws = false,
forceExternal = false,
@ -36,10 +36,10 @@ export default function Link({
const dest = to || href
const external = forceExternal || /(http(s?)):\/\//gi.test(dest)
const icon = getIcon(dest)
const withIcon = !hidden && !hideIcon && !!icon && !isImage(children)
const withIcon = !noLinkLayout && !hideIcon && !!icon && !isImage(children)
const sourceWithText = withIcon && isString(children)
const linkClassNames = classNames(classes.root, className, {
[classes.hidden]: hidden,
[classes['no-link-layout']]: noLinkLayout,
[classes.nowrap]: (withIcon && !sourceWithText) || icon === 'network',
[classes['with-icon']]: withIcon,
})
@ -97,7 +97,7 @@ Link.propTypes = {
to: PropTypes.string,
href: PropTypes.string,
onClick: PropTypes.func,
hidden: PropTypes.bool,
noLinkLayout: PropTypes.bool,
hideIcon: PropTypes.bool,
ws: PropTypes.bool,
className: PropTypes.string,

View File

@ -2,11 +2,11 @@ import React from 'react'
import PropTypes from 'prop-types'
import classNames from 'classnames'
import patternBlue from '../images/pattern_blue.jpg'
import patternGreen from '../images/pattern_green.jpg'
import patternPurple from '../images/pattern_purple.jpg'
import patternNightly from '../images/pattern_nightly.jpg'
import patternLegacy from '../images/pattern_legacy.jpg'
import patternBlue from '../images/pattern_blue.png'
import patternGreen from '../images/pattern_green.png'
import patternPurple from '../images/pattern_purple.png'
import patternNightly from '../images/pattern_nightly.png'
import patternLegacy from '../images/pattern_legacy.png'
import classes from '../styles/main.module.sass'
const patterns = {

View File

@ -0,0 +1,32 @@
import React, { useEffect, useState } from 'react'
import { serialize } from 'next-mdx-remote/serialize'
import { MDXRemote } from 'next-mdx-remote'
import remarkPlugins from '../../plugins/index.mjs'
/**
* Convert raw Markdown to React
* @param {String} markdown - The Markdown markup to convert.
* @param {Object} [remarkReactComponents] - Optional React components to use
* for HTML elements.
* @returns {Node} - The converted React elements.
*/
export default function MarkdownToReact({ markdown }) {
const [mdx, setMdx] = useState(null)
useEffect(() => {
const getMdx = async () => {
setMdx(
await serialize(markdown, {
parseFrontmatter: false,
mdxOptions: {
remarkPlugins,
},
})
)
}
getMdx()
}, [markdown])
return mdx ? <MDXRemote {...mdx} /> : <></>
}

View File

@ -0,0 +1,5 @@
import dynamic from 'next/dynamic'
export default dynamic(() => import('./markdownToReact'), {
loading: () => <p>Loading...</p>,
})

View File

@ -30,7 +30,7 @@ const NavigationDropdown = ({ items = [], section }) => {
export default function Navigation({ title, items = [], section, search, alert, children }) {
const logo = (
<Link to="/" aria-label={title} hidden>
<Link to="/" aria-label={title} noLinkLayout>
<h1 className={classes.title}>{title}</h1>
<SVG src={logoSpacy.src} className={classes.logo} width={300} height={96} />
</Link>
@ -57,7 +57,7 @@ export default function Navigation({ title, items = [], section, search, alert,
})
return (
<li key={i} className={itemClassNames}>
<Link to={url} tabIndex={isActive ? '-1' : null} hidden>
<Link to={url} tabIndex={isActive ? '-1' : null} noLinkLayout>
{text}
</Link>
</li>

View File

@ -251,7 +251,12 @@ const Quickstart = ({
</menu>
</pre>
{showCopy && (
<textarea ref={copyAreaRef} className={classes['copy-area']} rows={1} />
<textarea
ref={copyAreaRef}
className={classes['copy-area']}
rows={1}
aria-label={`Interactive code example for ${title}`}
/>
)}
</div>
</Container>

View File

@ -9,15 +9,15 @@ import classes from '../styles/readnext.module.sass'
export default function ReadNext({ title, to }) {
return (
<div className={classes.root}>
<Link to={to} hidden>
<Link to={to} noLinkLayout className={classes.root}>
<span>
<Label>Read next</Label>
{title}
</Link>
<Link to={to} hidden className={classes.icon} aria-hidden="true">
<Icon name="arrowright" />
</Link>
</div>
</span>
<span className={classes.icon}>
<Icon name="arrowright" aria-hidden="true" />
</span>
</Link>
)
}

View File

@ -9,6 +9,8 @@ import socialImageLegacy from '../images/social_legacy.jpg'
import siteMetadata from '../../meta/site.json'
import Head from 'next/head'
import { siteUrl } from '../../meta/dynamicMeta.mjs'
function getPageTitle(title, sitename, slogan, sectionTitle, nightly, legacy) {
if (sectionTitle && title) {
const suffix = nightly ? ' (nightly)' : legacy ? ' (legacy)' : ''
@ -25,7 +27,7 @@ function getImage(section, nightly, legacy) {
if (legacy) return socialImageLegacy
if (section === 'api') return socialImageApi
if (section === 'universe') return socialImageUniverse
return socialImageDefault
return `${siteUrl}${socialImageDefault.src}`
}
export default function SEO({
@ -46,7 +48,7 @@ export default function SEO({
nightly,
legacy
)
const socialImage = getImage(section, nightly, legacy).src
const socialImage = getImage(section, nightly, legacy)
const meta = [
{
name: 'description',

View File

@ -5,7 +5,7 @@ import classNames from 'classnames'
import Button from './button'
import Tag from './tag'
import { OptionalLink } from './link'
import { InlineCode } from './code'
import { InlineCode } from './inlineCode'
import { H1, Label, InlineList, Help } from './typography'
import Icon from './icon'
@ -51,8 +51,7 @@ export default function Title({
{image && (
<div className={classes.image}>
{/* eslint-disable-next-line @next/next/no-img-element */}
<img src={image} width={100} height={100} alt="" />
<Image src={image} width={100} height={100} alt={`${title} Logo`} />
</div>
)}
</div>

View File

@ -0,0 +1,51 @@
import React from 'react'
import classNames from 'classnames'
import CUSTOM_TYPES from '../../meta/type-annotations.json'
import Link from './link'
import classes from '../styles/code.module.sass'
export const WRAP_THRESHOLD = 30
const specialCharacterList = ['[', ']', ',', ', ']
const highlight = (element) =>
specialCharacterList.includes(element) ? (
<span className={classes['cli-arg-subtle']}>{element}</span>
) : (
element
)
function linkType(el, showLink = true, key) {
if (!el.length) return el
const elStr = el.trim()
if (!elStr) return el
const typeUrl = CUSTOM_TYPES[elStr]
const url = typeUrl == true ? DEFAULT_TYPE_URL : typeUrl
return url && showLink ? (
<Link to={url} hideIcon key={key}>
{elStr}
</Link>
) : (
highlight(el)
)
}
export const TypeAnnotation = ({ lang = 'python', link = true, children }) => {
const code = Array.isArray(children) ? children.join('') : children || ''
const [rawText, meta] = code.split(/(?= \(.+\)$)/)
const annotClassNames = classNames(
'type-annotation',
`language-${lang}`,
classes['inline-code'],
classes['type-annotation'],
{
[classes['wrap']]: code.length >= WRAP_THRESHOLD,
}
)
return (
<span className={annotClassNames} role="code" aria-label="Type annotation">
{rawText.split(/(\[|\]|,)/).map((el, i) => linkType(el, !!link, i))}
{meta && <span className={classes['type-annotation-meta']}>{meta}</span>}
</span>
)
}

View File

@ -1,12 +1,6 @@
import React, { Fragment, useEffect, useState } from 'react'
import { Parser as HtmlToReactParser } from 'html-to-react'
import React, { Fragment } from 'react'
import siteMetadata from '../../meta/site.json'
import { domain } from '../../meta/dynamicMeta.mjs'
import remarkPlugins from '../../plugins/index.mjs'
import { serialize } from 'next-mdx-remote/serialize'
import { MDXRemote } from 'next-mdx-remote'
const htmlToReactParser = new HtmlToReactParser()
const isNightly = siteMetadata.nightlyBranches.includes(domain)
export const DEFAULT_BRANCH = isNightly ? 'develop' : 'master'
@ -70,43 +64,6 @@ export function isEmptyObj(obj) {
return Object.entries(obj).length === 0 && obj.constructor === Object
}
/**
* Convert raw HTML to React elements
* @param {string} html - The HTML markup to convert.
* @returns {Node} - The converted React elements.
*/
export function htmlToReact(html) {
return htmlToReactParser.parse(html)
}
/**
* Convert raw Markdown to React
* @param {String} markdown - The Markdown markup to convert.
* @param {Object} [remarkReactComponents] - Optional React components to use
* for HTML elements.
* @returns {Node} - The converted React elements.
*/
export function MarkdownToReact({ markdown }) {
const [mdx, setMdx] = useState(null)
useEffect(() => {
const getMdx = async () => {
setMdx(
await serialize(markdown, {
parseFrontmatter: false,
mdxOptions: {
remarkPlugins,
},
})
)
}
getMdx()
}, [markdown])
return mdx ? <MDXRemote {...mdx} /> : <></>
}
/**
* Join an array of nodes with a given string delimiter, like Array.join for React
* @param {Array} arr - The elements to join.

View File

@ -1,3 +1,3 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 500 500" width="200" height="200">
<path fill="currentColor" d="M111.7 74.9L91.2 93.1l9.1 10.2 17.8-15.8 7.4 8.4-17.8 15.8 10.1 11.4 20.6-18.2 7.7 8.7-30.4 26.9-41.9-47.3 30.3-26.9 7.6 8.6zM190.8 59.6L219 84.3l-14.4 4.5-20.4-18.2-6.4 26.6-14.4 4.5 8.9-36.4-26.9-24.1 14.3-4.5L179 54.2l5.7-25.2 14.3-4.5-8.2 35.1zM250.1 21.2l27.1 3.4c6.1.8 10.8 3.1 14 7.2 3.2 4.1 4.5 9.2 3.7 15.5-.8 6.3-3.2 11-7.4 14.1-4.1 3.1-9.2 4.3-15.3 3.5L258 63.2l-2.8 22.3-13-1.6 7.9-62.7zm11.5 13l-2.2 17.5 12.6 1.6c5.1.6 9.1-2 9.8-7.6.7-5.6-2.5-9.2-7.6-9.9l-12.6-1.6zM329.1 95.4l23.8 13.8-5.8 10L312 98.8l31.8-54.6 11.3 6.6-26 44.6zM440.5 145c-1.3 8.4-5.9 15.4-13.9 21.1s-16.2 7.7-24.6 6.1c-8.4-1.6-15.3-6.3-20.8-14.1-5.5-7.9-7.6-16-6.4-24.4 1.3-8.5 6-15.5 14-21.1 8-5.6 16.2-7.7 24.5-6 8.4 1.6 15.4 6.3 20.9 14.2 5.5 7.6 7.6 15.7 6.3 24.2zM412 119c-5.1-.8-10.3.6-15.6 4.4-5.2 3.7-8.4 8.1-9.4 13.2-1 5.2.2 10.1 3.5 14.8 3.4 4.8 7.5 7.5 12.7 8.2 5.2.8 10.4-.7 15.6-4.4 5.3-3.7 8.4-8.1 9.4-13.2 1.1-5.1-.1-9.9-3.4-14.7-3.4-4.8-7.6-7.6-12.8-8.3zM471.5 237.9c-2.8 4.8-7.1 7.6-13 8.7l-2.6-13.1c5.3-.9 8.1-5 7.2-11-.9-5.8-4.3-8.8-8.9-8.2-2.3.3-3.7 1.4-4.5 3.3-.7 1.9-1.4 5.2-1.7 10.1-.8 7.5-2.2 13.1-4.3 16.9-2.1 3.9-5.7 6.2-10.9 7-6.3.9-11.3-.5-15.2-4.4-3.9-3.8-6.3-9-7.3-15.7-1.1-7.4-.2-13.7 2.6-18.8 2.8-5.1 7.4-8.2 13.7-9.2l2.6 13c-5.6 1.1-8.7 6.6-7.7 13.4 1 6.6 3.9 9.5 8.6 8.8 4.4-.7 5.7-4.5 6.7-14.1.3-3.5.7-6.2 1.1-8.4.4-2.2 1.2-4.4 2.2-6.8 2.1-4.7 6-7.2 11.8-8.1 5.4-.8 10.3.4 14.5 3.7 4.2 3.3 6.9 8.5 8 15.6.9 6.9-.1 12.6-2.9 17.3zM408.6 293.5l2.4-12.9 62 11.7-2.4 12.9-62-11.7zM419.6 396.9c-8.3 2-16.5.3-24.8-5-8.2-5.3-13.2-12.1-14.9-20.5-1.6-8.4.1-16.6 5.3-24.6 5.2-8.1 11.9-13.1 20.2-15.1 8.4-1.9 16.6-.3 24.9 5 8.2 5.3 13.2 12.1 14.8 20.5 1.7 8.4 0 16.6-5.2 24.7-5.2 8-12 13-20.3 15zm13.4-36.3c-1.2-5.1-4.5-9.3-9.9-12.8s-10.6-4.7-15.8-3.7-9.3 4-12.4 8.9-4.1 9.8-2.8 14.8c1.2 5.1 4.5 9.3 9.9 12.8 5.5 3.5 10.7 4.8 15.8 3.7 5.1-.9 9.2-3.8 12.3-8.7s4.1-9.9 2.9-15zM303.6 416.5l9.6-5.4 43.3 20.4-19.2-34 11.4-6.4 31 55-9.6 5.4-43.4-20.5 19.2 34.1-11.3 6.4-31-55zM238.2 468.8c-49 0-96.9-17.4-134.8-49-38.3-32-64-76.7-72.5-125.9-2-11.9-3.1-24-3.1-35.9 0-36.5 9.6-72.6 27.9-104.4 2.1-3.6 6.7-4.9 10.3-2.8 3.6 2.1 4.9 6.7 2.8 10.3-16.9 29.5-25.9 63.1-25.9 96.9 0 11.1 1 22.3 2.9 33.4 7.9 45.7 31.8 87.2 67.3 116.9 35.2 29.3 79.6 45.5 125.1 45.5 11.1 0 22.3-1 33.4-2.9 4.1-.7 8 2 8.7 6.1.7 4.1-2 8-6.1 8.7-11.9 2-24 3.1-36 3.1z" />
</svg>
<svg height="100" viewBox="0 0 100 100" width="100" xmlns="http://www.w3.org/2000/svg">
<path d="M22.8 11.9l1.5 1.7-4.4 3.8 1.8 2 4-3.5 1.4 1.6-4 3.5 1.9 2.2 4.4-3.8 1.5 1.7-6.3 5.5-8-9.3 6.2-5.4zm17.1-1.2l5.9 4.8-2.8.8-4-3.3-1.5 4.9-2.7.8 2.3-7.2-5.6-4.6 2.8-.8 3.7 3 1.5-4.6 2.7-.8-2.3 7zm14.1.9l-.6 4.2-2.5-.4 1.8-12.1 4.9.7c2.6.4 4.1 2 3.7 4.6s-2.3 3.7-4.9 3.3l-2.4-.3zm3.2-5.4l-2.3-.3-.5 3.6 2.3.3c1.3.2 2.1-.5 2.2-1.5.1-1.1-.4-1.9-1.7-2.1zm14.5 2.4l2.2 1.4-5.4 8.4 4.8 3.1-1.2 1.9-7-4.5 6.6-10.3zm6.8 22.8c-1.9-2.9-.9-6.3 2.1-8.3 3.1-2 6.6-1.5 8.5 1.4s1 6.3-2.1 8.3c-3 2-6.6 1.4-8.5-1.4zm8.7-5.7c-1.1-1.6-3.1-1.8-5.1-.5s-2.7 3.3-1.6 4.9 3.2 1.8 5.2.5c1.9-1.3 2.6-3.3 1.5-4.9zm-.1 17c-1 .5-1.4 1.4-1.2 2.6s.8 2 1.8 1.8c.7-.1 1.1-.6 1.2-1.7l.2-2.2c.2-1.8.9-3.3 2.9-3.5 2.2-.3 4 1.3 4.3 3.9.4 2.8-.9 4.6-2.9 5.2l-.3-2.5c.8-.4 1.3-1.2 1.2-2.4-.2-1.1-.8-1.8-1.7-1.7-.7.1-1 .6-1.1 1.5l-.3 2.3c-.2 2-1.2 3.4-3 3.6-2.4.3-4-1.4-4.4-4-.4-2.7.7-4.8 3-5.5l.3 2.6zm-3.8 15.6l.5-2.5 12 2.5-.5 2.5-12-2.5zm-4.7 10.3c1.9-2.9 5.4-3.4 8.5-1.4s4 5.5 2.1 8.3-5.4 3.4-8.5 1.4-4-5.5-2.1-8.3zm8.7 5.6c1.1-1.6.4-3.6-1.7-4.9-2-1.3-4.1-1.2-5.1.5-1.1 1.6-.4 3.6 1.6 4.9 2 1.4 4.1 1.2 5.2-.5zm-24.7 8.1l1.8-1 9.1 4.2-4.1-7.1 2.1-1.2 6.1 10.6-2 1.2-8.6-4 3.9 6.7-2.1 1.2-6.2-10.6zM50 92.2C26.7 92.2 7.8 73.3 7.8 50c0-7.2 1.8-14.3 5.3-20.5.4-.7 1.3-1 2-.6s1 1.3.6 2a39.53 39.53 0 0 0-4.9 19c0 21.6 17.6 39.2 39.2 39.2 2.2 0 4.4-.2 6.6-.5.8-.1 1.6.4 1.7 1.2s-.4 1.6-1.2 1.7c-2.4.5-4.7.7-7.1.7z"/>
</svg>

Before

Width:  |  Height:  |  Size: 2.4 KiB

After

Width:  |  Height:  |  Size: 1.4 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 114 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 119 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 101 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 7.8 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 86 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 7.9 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 126 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 7.9 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 106 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 157 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 112 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

View File

@ -1,7 +1,10 @@
import Link from './components/link'
import Section, { Hr } from './components/section'
import { Table, Tr, Th, Tx, Td } from './components/table'
import CodeBlock, { Pre, Code, InlineCode, TypeAnnotation } from './components/code'
import Code from './components/codeDynamic'
import { TypeAnnotation } from './components/typeAnnotation'
import { InlineCode } from './components/inlineCode'
import CodeBlock, { Pre } from './components/codeBlock'
import { Ol, Ul, Li } from './components/list'
import { H2, H3, H4, H5, P, Abbr, Help, Label } from './components/typography'
import Accordion from './components/accordion'

View File

@ -31,7 +31,7 @@
width: $width
height: $width
flex: 0 0 $width
background: var(--color-theme)
background: var(--color-theme-dark)
color: var(--color-back)
border-radius: 50%
padding: 0.35rem

View File

@ -10,7 +10,7 @@
padding: 1rem
box-shadow: var(--box-shadow)
border-top: 2px solid
color: var(--color-theme)
color: var(--color-theme-dark)
.warning
--alert-bg: var(--color-yellow-light)

View File

@ -77,7 +77,7 @@ $border-radius: 6px
padding: 1.5rem 2.5rem 2.5rem 2rem
a, a:hover
color: var(--color-subtle)
color: var(--color-subtle-on-dark)
& > *:last-child
margin-bottom: 0

View File

@ -2,7 +2,7 @@
display: inline-block
padding: 0.65rem 1.1rem 0.825rem
margin-bottom: 1px
border: 2px solid var(--color-theme)
border: 2px solid var(--color-theme-dark)
border-radius: 2em
text-align: center
transition: background-color, color 0.25s ease
@ -18,7 +18,7 @@
padding: 0.8em 1.1em 1em
.primary
background: var(--color-theme)
background: var(--color-theme-dark)
color: var(--color-back)
&:hover
@ -27,7 +27,7 @@
.secondary
background: var(--color-back)
color: var(--color-theme)
color: var(--color-theme-dark)
&:hover
color: var(--color-theme-dark)

View File

@ -1,7 +1,7 @@
.pre
position: relative
background: var(--color-front)
color: var(--color-subtle)
color: var(--color-subtle-on-dark)
border-radius: var(--border-radius)
overflow: auto
width: 100%
@ -152,7 +152,7 @@
.juniper-button
transition: background-color 0.15s ease
background: var(--color-theme)
background: var(--color-theme-dark)
margin: 0.5rem 0 1rem 2rem
&:hover
@ -182,8 +182,8 @@
color: inherit !important
.cli-arg-highlight
background: var(--color-theme)
border-color: var(--color-theme)
background: var(--color-theme-dark)
border-color: var(--color-theme-dark)
color: var(--color-back) !important
.cli-arg-subtle

View File

@ -32,7 +32,7 @@
.copy
border-top: 1px dotted var(--color-subtle)
font-size: var(--font-size-xs)
color: var(--color-subtle-dark)
color: var(--color-front-dark)
text-align: center
width: 100%
@ -42,4 +42,4 @@
vertical-align: middle
&:hover
color: var(--color-theme)
color: var(--color-theme-dark)

View File

@ -31,7 +31,7 @@
.title
font-weight: bold
color: var(--color-theme)
color: var(--color-theme-dark)
display: block
margin-bottom: var(--spacing-xs)
font-size: var(--font-size-md)
@ -41,7 +41,7 @@
color: inherit
.icon
color: var(--color-theme)
color: var(--color-theme-dark)
vertical-align: baseline
position: relative
bottom: -2px

View File

@ -2,22 +2,25 @@
.header
background: var(--color-theme)
padding-top: calc(var(--height-nav) * 1.5)
padding-top: var(--height-nav)
width: 100%
text-align: center
--header-top-margin: 27px
.header-wrapper
background: var(--color-theme)
background-position: top center
background-position: center var(--header-top-margin)
background-repeat: repeat
width: 100%
background-size: 799px 643px
.header-content
background: transparent
background-position: center -138px
background-position: center calc(-138px + var(--header-top-margin))
background-repeat: no-repeat
width: 100%
min-height: 573px
min-height: calc(573px + var(--header-top-margin))
background-size: 1444px 573px
padding-top: var(--header-top-margin)
.title
font: normal 600 7rem/#{1} var(--font-secondary)

View File

@ -65,9 +65,10 @@
--color-dark: hsl(214, 15%, 32%)
--color-dark-secondary: hsl(214, 14%, 22%)
--color-subtle-opaque: hsla(0, 0%, 96%, 0.56)
--color-subtle: hsl(0, 0%, 87%)
--color-subtle-light: hsl(0, 0%, 96%)
--color-subtle-dark: hsl(162, 5%, 60%)
--color-subtle: hsla(0, 0%, 0%, 0.13)
--color-subtle-light: hsla(0, 0%, 0%, 0.04)
--color-subtle-dark: hsla(162, 5%, 0%, 0.55)
--color-subtle-on-dark: hsla(0, 0%, 100%, 0.87)
--color-green-medium: hsl(108, 66%, 63%)
--color-green-transparent: hsla(108, 66%, 63%, 0.12)
@ -301,13 +302,13 @@ p
margin-bottom: 0
a:focus
outline: 1px dotted var(--color-theme)
outline: 1px dotted var(--color-theme-dark)
body [id]:target
padding-top: calc(var(--height-nav) * 1.25) !important
::selection
background: var(--color-theme)
background: var(--color-theme-dark)
color: var(--color-back)
text-shadow: none
@ -387,7 +388,7 @@ body [id]:target
[class*="language-bash"] .token
&.function
color: var(--color-subtle)
color: var(--color-subtle-on-dark)
&.operator, &.variable
color: var(--syntax-comment)
@ -397,7 +398,7 @@ body [id]:target
color: var(--syntax-comment)
.token
color: var(--color-subtle)
color: var(--color-subtle-on-dark)
.gatsby-highlight-code-line
background-color: var(--color-dark-secondary)
@ -524,7 +525,7 @@ body [id]:target
display: block
font: bold var(--font-size-lg)/var(--line-height-md) var(--font-secondary)
text-transform: uppercase
color: var(--color-theme)
color: var(--color-theme-dark)
.algolia-autocomplete .algolia-docsearch-suggestion--subcategory-column
color: var(--color-dark)

Some files were not shown because too many files have changed in this diff Show More