Merge branch 'develop' of https://github.com/explosion/spaCy into develop

This commit is contained in:
Matthew Honnibal 2020-08-27 03:22:11 +02:00
commit e1e1760fd6
8 changed files with 17 additions and 72 deletions

View File

@ -5,7 +5,7 @@ thinc>=8.0.0a30,<8.0.0a40
blis>=0.4.0,<0.5.0
ml_datasets>=0.1.1
murmurhash>=0.28.0,<1.1.0
wasabi>=0.7.1,<1.1.0
wasabi>=0.8.0,<1.1.0
srsly>=2.1.0,<3.0.0
catalogue>=0.0.7,<1.1.0
typer>=0.3.0,<0.4.0

View File

@ -42,7 +42,7 @@ install_requires =
preshed>=3.0.2,<3.1.0
thinc>=8.0.0a30,<8.0.0a40
blis>=0.4.0,<0.5.0
wasabi>=0.7.1,<1.1.0
wasabi>=0.8.0,<1.1.0
srsly>=2.1.0,<3.0.0
catalogue>=0.0.7,<1.1.0
typer>=0.3.0,<0.4.0

View File

@ -1,7 +1,7 @@
from typing import Optional, Dict, Any, Union
import platform
from pathlib import Path
from wasabi import Printer
from wasabi import Printer, MarkdownRenderer
import srsly
from ._util import app, Arg, Opt
@ -97,12 +97,13 @@ def get_markdown(data: Dict[str, Any], title: Optional[str] = None) -> str:
title (str / None): Title, will be rendered as headline 2.
RETURNS (str): The Markdown string.
"""
markdown = []
md = MarkdownRenderer()
if title:
md.add(md.title(2, title))
items = []
for key, value in data.items():
if isinstance(value, str) and Path(value).exists():
continue
markdown.append(f"* **{key}:** {value}")
result = "\n{}\n".format("\n".join(markdown))
if title:
result = f"\n## {title}\n{result}"
return result
items.append(f"{md.bold(f'{key}:')} {value}")
md.add(md.list(items))
return f"\n{md.text}\n"

View File

@ -1,6 +1,5 @@
from typing import Iterable, Optional
from pathlib import Path
from wasabi import msg
from wasabi import msg, MarkdownRenderer
from ...util import working_dir
from .._util import project_cli, Arg, Opt, PROJECT_FILE, load_project_config
@ -107,34 +106,3 @@ def project_document(
with output_file.open("w") as f:
f.write(content)
msg.good("Saved project documentation", output_file)
class MarkdownRenderer:
"""Simple helper for generating raw Markdown."""
def __init__(self, no_emoji: bool = False):
self.data = []
self.no_emoji = no_emoji
@property
def text(self):
return "\n\n".join(self.data)
def add(self, content: str) -> None:
self.data.append(content)
def table(self, data: Iterable[Iterable[str]], header: Iterable[str]) -> str:
head = f"| {' | '.join(header)} |"
divider = f"| {' | '.join('---' for _ in header)} |"
body = "\n".join(f"| {' | '.join(row)} |" for row in data)
return f"{head}\n{divider}\n{body}"
def title(self, level: int, text: str, emoji: Optional[str] = None) -> str:
prefix = f"{emoji} " if emoji and not self.no_emoji else ""
return f"{'#' * level} {prefix}{text}"
def code(self, text: str) -> str:
return f"`{text}`"
def link(self, text: str, url: str) -> str:
return f"[{text}]({url})"

View File

@ -273,10 +273,6 @@ class Errors:
"existing extension, set `force=True` on `{obj}.set_extension`.")
E091 = ("Invalid extension attribute {name}: expected callable or None, "
"but got: {value}")
E092 = ("Could not find or assign name for word vectors. Ususally, the "
"name is read from the model's meta.json in vector.name. "
"Alternatively, it is built from the 'lang' and 'name' keys in "
"the meta.json. Vector names are required to avoid issue #1660.")
E093 = ("token.ent_iob values make invalid sequence: I without B\n{seq}")
E094 = ("Error reading line {line_num} in vectors file {loc}.")
E095 = ("Can't write to frozen dictionary. This is likely an internal "

View File

@ -1538,7 +1538,6 @@ class Language:
def deserialize_vocab(path: Path) -> None:
if path.exists():
self.vocab.from_disk(path)
_fix_pretrained_vectors_name(self)
path = util.ensure_path(path)
deserializers = {}
@ -1605,14 +1604,10 @@ class Language:
# from self.vocab.vectors, so set the name directly
self.vocab.vectors.name = data.get("vectors", {}).get("name")
def deserialize_vocab(b):
self.vocab.from_bytes(b)
_fix_pretrained_vectors_name(self)
deserializers = {}
deserializers["config.cfg"] = lambda b: self.config.from_bytes(b)
deserializers["meta.json"] = deserialize_meta
deserializers["vocab"] = deserialize_vocab
deserializers["vocab"] = self.vocab.from_bytes
deserializers["tokenizer"] = lambda b: self.tokenizer.from_bytes(
b, exclude=["vocab"]
)
@ -1646,25 +1641,6 @@ class FactoryMeta:
default_score_weights: Optional[Dict[str, float]] = None # noqa: E704
def _fix_pretrained_vectors_name(nlp: Language) -> None:
# TODO: Replace this once we handle vectors consistently as static
# data
if "vectors" in nlp.meta and "name" in nlp.meta["vectors"]:
nlp.vocab.vectors.name = nlp.meta["vectors"]["name"]
elif not nlp.vocab.vectors.size:
nlp.vocab.vectors.name = None
elif "name" in nlp.meta and "lang" in nlp.meta:
vectors_name = f"{nlp.meta['lang']}_{nlp.meta['name']}.vectors"
nlp.vocab.vectors.name = vectors_name
else:
raise ValueError(Errors.E092)
for name, proc in nlp.pipeline:
if not hasattr(proc, "cfg") or not isinstance(proc.cfg, dict):
continue
proc.cfg.setdefault("deprecation_fixes", {})
proc.cfg["deprecation_fixes"]["vectors_name"] = nlp.vocab.vectors.name
class DisabledPipes(list):
"""Manager for temporary pipeline disabling."""

View File

@ -146,8 +146,12 @@ validation error with more details.
> #### Example
>
> ```cli
> $ python -m spacy init fill-config base.cfg config.cfg
> $ python -m spacy init fill-config base.cfg config.cfg --diff
> ```
>
> #### Example diff
>
> ![Screenshot of visual diff in terminal](../images/cli_init_fill-config_diff.jpg)
```cli
$ python -m spacy init fill-config [base_path] [output_file] [--diff]

Binary file not shown.

After

Width:  |  Height:  |  Size: 202 KiB