spaCy/website/docs/api/top-level.md

title	menu
Top-level Functions	spacy spacy displacy displacy registry registry Readers & Batchers readers-batchers Data & Alignment gold Utility Functions util

spaCy

spacy.load

Load a model using the name of an installed model package, a string path or a Path-like object. spaCy will try resolving the load argument in this order. If a model is loaded from a model name, spaCy will assume it's a Python package and import it and call the model's own load() method. If a model is loaded from a path, spaCy will assume it's a data directory, read the language and pipeline settings off the meta.json and initialize the Language class. The data will be loaded in via Language.from_disk.

Example

nlp = spacy.load("en_core_web_sm") # package
nlp = spacy.load("/path/to/en") # string path
nlp = spacy.load(Path("/path/to/en")) # pathlib Path

nlp = spacy.load("en_core_web_sm", disable=["parser", "tagger"])

Name	Type	Description
name	str / Path	Model to load, i.e. package name or path.
keyword-only
disable	List[str]	Names of pipeline components to disable.
config 3	Dict[str, Any] / Config	Optional config overrides, either as nested dict or dict keyed by section value in dot notation, e.g. "components.name.value".
RETURNS	Language	A Language object with the loaded model.

Essentially, spacy.load() is a convenience wrapper that reads the language ID and pipeline components from a model's meta.json, initializes the Language class, loads in the model data and returns it.

### Abstract example
cls = util.get_lang_class(lang)         #  get language for ID, e.g. "en"
nlp = cls()                             #  initialize the language
for name in pipeline:
    nlp.add_pipe(name)                  #  add component to pipeline
nlp.from_disk(model_data_path)          #  load in model data

spacy.blank

Create a blank model of a given language class. This function is the twin of spacy.load().

Example

nlp_en = spacy.blank("en")   # equivalent to English()
nlp_de = spacy.blank("de")   # equivalent to German()

Name	Type	Description
name	str	ISO code of the language class to load.
RETURNS	Language	An empty Language object of the appropriate subclass.

spacy.info

The same as the info command. Pretty-print information about your installation, models and local setup from within spaCy. To get the model meta data as a dictionary instead, you can use the meta attribute on your nlp object with a loaded model, e.g. nlp.meta.

Example

spacy.info()
spacy.info("en_core_web_sm")
markdown = spacy.info(markdown=True, silent=True)

Name	Type	Description
model	str	A model, i.e. a package name or path (optional).
keyword-only
markdown	bool	Print information as Markdown.
silent	bool	Don't print anything, just return.

spacy.explain

Get a description for a given POS tag, dependency label or entity type. For a list of available terms, see glossary.py.

Example

spacy.explain("NORP")
# Nationalities or religious or political groups

doc = nlp("Hello world")
for word in doc:
   print(word.text, word.tag_, spacy.explain(word.tag_))
# Hello UH interjection
# world NN noun, singular or mass

Name	Type	Description
term	str	Term to explain.
RETURNS	str	The explanation, or None if not found in the glossary.

spacy.prefer_gpu

Allocate data and perform operations on GPU, if available. If data has already been allocated on CPU, it will not be moved. Ideally, this function should be called right after importing spaCy and before loading any models.

Example

import spacy
activated = spacy.prefer_gpu()
nlp = spacy.load("en_core_web_sm")

Name	Type	Description
RETURNS	bool	Whether the GPU was activated.

spacy.require_gpu

Allocate data and perform operations on GPU. Will raise an error if no GPU is available. If data has already been allocated on CPU, it will not be moved. Ideally, this function should be called right after importing spaCy and before loading any models.

Example

import spacy
spacy.require_gpu()
nlp = spacy.load("en_core_web_sm")

Name	Type	Description
RETURNS	bool	True

displaCy

As of v2.0, spaCy comes with a built-in visualization suite. For more info and examples, see the usage guide on visualizing spaCy.

displacy.serve

Serve a dependency parse tree or named entity visualization to view it in your browser. Will run a simple web server.

Example

import spacy
from spacy import displacy
nlp = spacy.load("en_core_web_sm")
doc1 = nlp("This is a sentence.")
doc2 = nlp("This is another sentence.")
displacy.serve([doc1, doc2], style="dep")

Name	Type	Description	Default
docs	list, Doc, Span	Document(s) to visualize.
style	str	Visualization style, 'dep' or 'ent'.	'dep'
page	bool	Render markup as full HTML page.	True
minify	bool	Minify HTML markup.	False
options	dict	Visualizer-specific options, e.g. colors.	{}
manual	bool	Don't parse Doc and instead, expect a dict or list of dicts. See here for formats and examples.	False
port	int	Port to serve visualization.	5000
host	str	Host to serve visualization.	'0.0.0.0'

displacy.render

Render a dependency parse tree or named entity visualization.

Example

import spacy
from spacy import displacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("This is a sentence.")
html = displacy.render(doc, style="dep")

Name	Type	Description	Default
docs	list, Doc, Span	Document(s) to visualize.
style	str	Visualization style, 'dep' or 'ent'.	'dep'
page	bool	Render markup as full HTML page.	False
minify	bool	Minify HTML markup.	False
jupyter	bool	Explicitly enable or disable "Jupyter mode" to return markup ready to be rendered in a notebook. Detected automatically if None.	None
options	dict	Visualizer-specific options, e.g. colors.	{}
manual	bool	Don't parse Doc and instead, expect a dict or list of dicts. See here for formats and examples.	False
RETURNS	str	Rendered HTML markup.

Visualizer options

The options argument lets you specify additional settings for each visualizer. If a setting is not present in the options, the default value will be used.

Dependency Visualizer options

Example

options = {"compact": True, "color": "blue"}
displacy.serve(doc, style="dep", options=options)

Name	Type	Description	Default
fine_grained	bool	Use fine-grained part-of-speech tags (Token.tag_) instead of coarse-grained tags (Token.pos_).	False
add_lemma 2.2.4	bool	Print the lemma's in a separate row below the token texts.	False
collapse_punct	bool	Attach punctuation to tokens. Can make the parse more readable, as it prevents long arcs to attach punctuation.	True
collapse_phrases	bool	Merge noun phrases into one token.	False
compact	bool	"Compact mode" with square arrows that takes up less space.	False
color	str	Text color (HEX, RGB or color names).	'#000000'
bg	str	Background color (HEX, RGB or color names).	'#ffffff'
font	str	Font name or font family for all text.	'Arial'
offset_x	int	Spacing on left side of the SVG in px.	50
arrow_stroke	int	Width of arrow path in px.	2
arrow_width	int	Width of arrow head in px.	10 / 8 (compact)
arrow_spacing	int	Spacing between arrows in px to avoid overlaps.	20 / 12 (compact)
word_spacing	int	Vertical spacing between words and arcs in px.	45
distance	int	Distance between words in px.	175 / 150 (compact)

Named Entity Visualizer options

Example

options = {"ents": ["PERSON", "ORG", "PRODUCT"],
           "colors": {"ORG": "yellow"}}
displacy.serve(doc, style="ent", options=options)

Name	Type	Description	Default
ents	list	Entity types to highlight (None for all types).	None
colors	dict	Color overrides. Entity types in uppercase should be mapped to color names or values.	{}
template 2.2	str	Optional template to overwrite the HTML used to render entity spans. Should be a format string and can use {bg}, {text} and {label}.	see templates.py

By default, displaCy comes with colors for all entity types used by spaCy models. If you're using custom entity types, you can use the colors setting to add your own colors for them. Your application or model package can also expose a spacy_displacy_colors entry point to add custom labels and their colors automatically.

registry

spaCy's function registry extends Thinc's registry and allows you to map strings to functions. You can register functions to create architectures, optimizers, schedules and more, and then refer to them and set their arguments in your config file. Python type hints are used to validate the inputs. See the Thinc docs for details on the registry methods and our helper library catalogue for some background on the concept of function registries. spaCy also uses the function registry for language subclasses, model architecture, lookups and pipeline component factories.

Example

import spacy
from thinc.api import Model

@spacy.registry.architectures("CustomNER.v1")
def custom_ner(n0: int) -> Model:
    return Model("custom", forward, dims={"nO": nO})

Registry name	Description
architectures	Registry for functions that create model architectures. Can be used to register custom model architectures and reference them in the config.cfg.
factories	Registry for functions that create pipeline components. Added automatically when you use the @spacy.component decorator and also reads from entry points
languages	Registry for language-specific Language subclasses. Automatically reads from entry points.
lookups	Registry for large lookup tables available via vocab.lookups.
displacy_colors	Registry for custom color scheme for the displacy NER visualizer. Automatically reads from entry points.
assets
callbacks	Registry for custom callbacks to modify the nlp object before training.
readers	Registry for training and evaluation data readers.
batchers	Registry for training and evaluation data batchers.
optimizers	Registry for functions that create optimizers.
schedules	Registry for functions that create schedules.
layers	Registry for functions that create layers.
losses	Registry for functions that create losses.
initializers	Registry for functions that create initializers.

spacy-transformers registry

The following registries are added by the spacy-transformers package. See the Transformer API reference and usage docs for details.

Example

import spacy_transformers

@spacy_transformers.registry.annotation_setters("my_annotation_setter.v1")
def configure_custom_annotation_setter():
    def annotation_setter(docs, trf_data) -> None:
       # Set annotations on the docs

    return annotation_sette

Registry name	Description
span_getters	Registry for functions that take a batch of Doc objects and return a list of Span objects to process by the transformer, e.g. sentences.
annotation_setters	Registry for functions that create annotation setters. Annotation setters are functions that take a batch of Doc objects and a FullTransformerBatch and can set additional annotations on the Doc.

Data readers and batchers

spacy.Corpus.v1

Registered function that creates a Corpus of training or evaluation data. It takes the same arguments as the Corpus class and returns a callable that yields Example objects. You can replace it with your own registered function in the @readers registry to customize the data loading and streaming.

Example config

[paths]
train = "corpus/train.spacy"

[training.train_corpus]
@readers = "spacy.Corpus.v1"
path = ${paths:train}
gold_preproc = false
max_length = 0
limit = 0

Name	Type	Description
path	Path	The directory or filename to read from. Expects data in spaCy's binary .spacy format.
gold_preproc	bool	Whether to set up the Example object with gold-standard sentences and tokens for the predictions. See Corpus for details.
max_length	int	Maximum document length. Longer documents will be split into sentences, if sentence boundaries are available. Defaults to 0 for no limit.
limit	int	Limit corpus to a subset of examples, e.g. for debugging. Defaults to 0 for no limit.

Batchers

batch_by_words.v1

Create minibatches of roughly a given number of words. If any examples are longer than the specified batch length, they will appear in a batch by themselves, or be discarded if discard_oversize is set to True. The argument docs can be a list of strings, Doc objects or Example objects.

Example config

[training.batcher]
@batchers = "batch_by_words.v1"
size = 100
tolerance = 0.2
discard_oversize = false
get_length = null

Name	Type	Description
size	Iterable[int] / int	The batch size. Can also be a block referencing a schedule, e.g. compounding.
tolerance	float
discard_oversize	bool	Discard items that are longer than the specified batch length.
get_length	Callable[[Any], int]	Optional function that receives a sequence and returns its length. Defaults to the built-in len() if not set.

batch_by_sequence.v1

Example config

[training.batcher]
@batchers = "batch_by_sequence.v1"
size = 32
get_length = null

Name	Type	Description
size	Iterable[int] / int	The batch size. Can also be a block referencing a schedule, e.g. compounding.
get_length	Callable[[Any], int]	Optional function that receives a sequence and returns its length. Defaults to the built-in len() if not set.

batch_by_padded.v1

Example config

[training.batcher]
@batchers = "batch_by_words.v1"
size = 100
buffer = TODO:
discard_oversize = false
get_length = null

Name	Type	Description
size	Iterable[int] / int	The batch size. Can also be a block referencing a schedule, e.g. compounding.
buffer	int
discard_oversize	bool	Discard items that are longer than the specified batch length.
get_length	Callable[[Any], int]	Optional function that receives a sequence and returns its length. Defaults to the built-in len() if not set.

Training data and alignment

gold.docs_to_json

Convert a list of Doc objects into the JSON-serializable format used by the spacy train command. Each input doc will be treated as a 'paragraph' in the output doc.

Example

from spacy.gold import docs_to_json

doc = nlp("I like London")
json_data = docs_to_json([doc])

Name	Type	Description
docs	iterable / Doc	The Doc object(s) to convert.
id	int	ID to assign to the JSON. Defaults to 0.
RETURNS	dict	The data in spaCy's JSON format.

gold.align

Calculate alignment tables between two tokenizations, using the Levenshtein algorithm. The alignment is case-insensitive.

The current implementation of the alignment algorithm assumes that both tokenizations add up to the same string. For example, you'll be able to align ["I", "'", "m"] and ["I", "'m"], which both add up to "I'm", but not ["I", "'m"] and ["I", "am"].

Example

from spacy.gold import align

bert_tokens = ["obama", "'", "s", "podcast"]
spacy_tokens = ["obama", "'s", "podcast"]
alignment = align(bert_tokens, spacy_tokens)
cost, a2b, b2a, a2b_multi, b2a_multi = alignment

Name	Type	Description
tokens_a	list	String values of candidate tokens to align.
tokens_b	list	String values of reference tokens to align.
RETURNS	tuple	A (cost, a2b, b2a, a2b_multi, b2a_multi) tuple describing the alignment.

The returned tuple contains the following alignment information:

Example

a2b = array([0, -1, -1, 2])
b2a = array([0, 2, 3])
a2b_multi = {1: 1, 2: 1}
b2a_multi = {}

If a2b[3] == 2, that means that tokens_a[3] aligns to tokens_b[2]. If there's no one-to-one alignment for a token, it has the value -1.

Name	Type	Description
cost	int	The number of misaligned tokens.
a2b	numpy.ndarray[ndim=1, dtype='int32']	One-to-one mappings of indices in tokens_a to indices in tokens_b.
b2a	numpy.ndarray[ndim=1, dtype='int32']	One-to-one mappings of indices in tokens_b to indices in tokens_a.
a2b_multi	dict	A dictionary mapping indices in tokens_a to indices in tokens_b, where multiple tokens of tokens_a align to the same token of tokens_b.
b2a_multi	dict	A dictionary mapping indices in tokens_b to indices in tokens_a, where multiple tokens of tokens_b align to the same token of tokens_a.

gold.biluo_tags_from_offsets

Encode labelled spans into per-token tags, using the BILUO scheme (Begin, In, Last, Unit, Out). Returns a list of strings, describing the tags. Each tag string will be of the form of either "", "O" or "{action}-{label}", where action is one of "B", "I", "L", "U". The string "-" is used where the entity offsets don't align with the tokenization in the Doc object. The training algorithm will view these as missing values. O denotes a non-entity token. B denotes the beginning of a multi-token entity, I the inside of an entity of three or more tokens, and L the end of an entity of two or more tokens. U denotes a single-token entity.

Example

from spacy.gold import biluo_tags_from_offsets

doc = nlp("I like London.")
entities = [(7, 13, "LOC")]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ["O", "O", "U-LOC", "O"]

Name	Type	Description
doc	Doc	The document that the entity offsets refer to. The output tags will refer to the token boundaries within the document.
entities	iterable	A sequence of (start, end, label) triples. start and end should be character-offset integers denoting the slice into the original string.
RETURNS	list	str strings, describing the BILUO tags.

gold.offsets_from_biluo_tags

Encode per-token tags following the BILUO scheme into entity offsets.

Example

from spacy.gold import offsets_from_biluo_tags

doc = nlp("I like London.")
tags = ["O", "O", "U-LOC", "O"]
entities = offsets_from_biluo_tags(doc, tags)
assert entities == [(7, 13, "LOC")]

Name	Type	Description
doc	Doc	The document that the BILUO tags refer to.
entities	iterable	A sequence of BILUO tags with each tag describing one token. Each tag string will be of the form of either "", "O" or "{action}-{label}", where action is one of "B", "I", "L", "U".
RETURNS	list	A sequence of (start, end, label) triples. start and end will be character-offset integers denoting the slice into the original string.

gold.spans_from_biluo_tags

Encode per-token tags following the BILUO scheme into Span objects. This can be used to create entity spans from token-based tags, e.g. to overwrite the doc.ents.

Example

from spacy.gold import spans_from_biluo_tags

doc = nlp("I like London.")
tags = ["O", "O", "U-LOC", "O"]
doc.ents = spans_from_biluo_tags(doc, tags)

Name	Type	Description
doc	Doc	The document that the BILUO tags refer to.
entities	iterable	A sequence of BILUO tags with each tag describing one token. Each tag string will be of the form of either "", "O" or "{action}-{label}", where action is one of "B", "I", "L", "U".
RETURNS	list	A sequence of Span objects with added entity labels.

Utility functions

spaCy comes with a small collection of utility functions located in spacy/util.py. Because utility functions are mostly intended for internal use within spaCy, their behavior may change with future releases. The functions documented on this page should be safe to use and we'll try to ensure backwards compatibility. However, we recommend having additional tests in place if your application depends on any of spaCy's utilities.

util.get_lang_class

Import and load a Language class. Allows lazy-loading language data and importing languages using the two-letter language code. To add a language code for a custom language class, you can use the set_lang_class helper.

Example

for lang_id in ["en", "de"]:
    lang_class = util.get_lang_class(lang_id)
    lang = lang_class()

Name	Type	Description
lang	str	Two-letter language code, e.g. 'en'.
RETURNS	Language	Language class.

util.set_lang_class

Set a custom Language class name that can be loaded via get_lang_class. If your model uses a custom language, this is required so that spaCy can load the correct class from the two-letter language code.

Example

from spacy.lang.xy import CustomLanguage

util.set_lang_class('xy', CustomLanguage)
lang_class = util.get_lang_class('xy')
nlp = lang_class()

Name	Type	Description
name	str	Two-letter language code, e.g. 'en'.
cls	Language	The language class, e.g. English.

util.lang_class_is_loaded

Check whether a Language class is already loaded. Language classes are loaded lazily, to avoid expensive setup code associated with the language data.

Example

lang_cls = util.get_lang_class("en")
assert util.lang_class_is_loaded("en") is True
assert util.lang_class_is_loaded("de") is False

Name	Type	Description
name	str	Two-letter language code, e.g. 'en'.
RETURNS	bool	Whether the class has been loaded.

util.load_model

Load a model from a package or data path. If called with a package name, spaCy will assume the model is a Python package and import and call its load() method. If called with a path, spaCy will assume it's a data directory, read the language and pipeline settings from the meta.json and initialize a Language class. The model data will then be loaded in via Language.from_disk().

Example

nlp = util.load_model("en_core_web_sm")
nlp = util.load_model("en_core_web_sm", disable=["ner"])
nlp = util.load_model("/path/to/data")

Name	Type	Description
name	str	Package name or model path.
**overrides	-	Specific overrides, like pipeline components to disable.
RETURNS	Language	Language class with the loaded model.

util.load_model_from_path

Load a model from a data directory path. Creates the Language class and pipeline based on the directory's meta.json and then calls from_disk() with the path. This function also makes it easy to test a new model that you haven't packaged yet.

Example

nlp = load_model_from_path("/path/to/data")

Name	Type	Description
model_path	str	Path to model data directory.
meta	dict	Model meta data. If False, spaCy will try to load the meta from a meta.json in the same directory.
**overrides	-	Specific overrides, like pipeline components to disable.
RETURNS	Language	Language class with the loaded model.

util.load_model_from_init_py

A helper function to use in the load() method of a model package's __init__.py.

Example

from spacy.util import load_model_from_init_py

def load(**overrides):
    return load_model_from_init_py(__file__, **overrides)

Name	Type	Description
init_file	str	Path to model's __init__.py, i.e. __file__.
**overrides	-	Specific overrides, like pipeline components to disable.
RETURNS	Language	Language class with the loaded model.

util.get_model_meta

Get a model's meta.json from a directory path and validate its contents.

Example

meta = util.get_model_meta("/path/to/model")

Name	Type	Description
path	str / Path	Path to model directory.
RETURNS	dict	The model's meta data.

util.is_package

Check if string maps to a package installed via pip. Mainly used to validate model packages.

Example

util.is_package("en_core_web_sm") # True
util.is_package("xyz") # False

Name	Type	Description
name	str	Name of package.
RETURNS	bool	True if installed package, False if not.

util.get_package_path

Get path to an installed package. Mainly used to resolve the location of model packages. Currently imports the package to find its path.

Example

util.get_package_path("en_core_web_sm")
# /usr/lib/python3.6/site-packages/en_core_web_sm

Name	Type	Description
package_name	str	Name of installed package.
RETURNS	Path	Path to model package directory.

util.is_in_jupyter

Check if user is running spaCy from a Jupyter notebook by detecting the IPython kernel. Mainly used for the displacy visualizer.

Example

html = "<h1>Hello world!</h1>"
if util.is_in_jupyter():
    from IPython.core.display import display, HTML
    display(HTML(html))

Name	Type	Description
RETURNS	bool	True if in Jupyter, False if not.

util.compile_prefix_regex

Compile a sequence of prefix rules into a regex object.

Example

prefixes = ("§", "%", "=", r"\+")
prefix_regex = util.compile_prefix_regex(prefixes)
nlp.tokenizer.prefix_search = prefix_regex.search

Name	Type	Description
entries	tuple	The prefix rules, e.g. lang.punctuation.TOKENIZER_PREFIXES.
RETURNS	regex	The regex object. to be used for Tokenizer.prefix_search.

util.compile_suffix_regex

Compile a sequence of suffix rules into a regex object.

Example

suffixes = ("'s", "'S", r"(?<=[0-9])\+")
suffix_regex = util.compile_suffix_regex(suffixes)
nlp.tokenizer.suffix_search = suffix_regex.search

Name	Type	Description
entries	tuple	The suffix rules, e.g. lang.punctuation.TOKENIZER_SUFFIXES.
RETURNS	regex	The regex object. to be used for Tokenizer.suffix_search.

util.compile_infix_regex

Compile a sequence of infix rules into a regex object.

Example

infixes = ("…", "-", "—", r"(?<=[0-9])[+\-\*^](?=[0-9-])")
infix_regex = util.compile_infix_regex(infixes)
nlp.tokenizer.infix_finditer = infix_regex.finditer

Name	Type	Description
entries	tuple	The infix rules, e.g. lang.punctuation.TOKENIZER_INFIXES.
RETURNS	regex	The regex object. to be used for Tokenizer.infix_finditer.

util.minibatch

Iterate over batches of items. size may be an iterator, so that batch-size can vary on each step.

Example

batches = minibatch(train_data)
for batch in batches:
    nlp.update(batch)

Name	Type	Description
items	iterable	The items to batch up.
size	int / iterable	The batch size(s).
YIELDS	list	The batches.

util.filter_spans

Filter a sequence of Span objects and remove duplicates or overlaps. Useful for creating named entities (where one token can only be part of one entity) or when merging spans with Retokenizer.merge. When spans overlap, the (first) longest span is preferred over shorter spans.

Example

doc = nlp("This is a sentence.")
spans = [doc[0:2], doc[0:2], doc[0:4]]
filtered = filter_spans(spans)

Name	Type	Description
spans	iterable	The spans to filter.
RETURNS	list	The filtered spans.

util.get_words_and_spaces

Name	Type	Description
words	list
text	str
RETURNS	tuple