mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 07:57:35 +03:00
155 lines
3.7 KiB
Plaintext
155 lines
3.7 KiB
Plaintext
//- 💫 DOCS > API > LANGUAGE
|
|
|
|
include ../../_includes/_mixins
|
|
|
|
p A text processing pipeline.
|
|
|
|
+h(2, "attributes") Attributes
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code vocab]
|
|
+cell #[code Vocab]
|
|
+cell A container for the lexical types.
|
|
|
|
+row
|
|
+cell #[code tokenizer]
|
|
+cell #[code Tokenizer]
|
|
+cell Find word boundaries and create #[code Doc] object.
|
|
|
|
+row
|
|
+cell #[code tagger]
|
|
+cell #[code Tagger]
|
|
+cell Annotate #[code Doc] objects with POS tags.
|
|
|
|
+row
|
|
+cell #[code parser]
|
|
+cell #[code DependencyParser]
|
|
+cell Annotate #[code Doc] objects with syntactic dependencies.
|
|
|
|
+row
|
|
+cell #[code entity]
|
|
+cell #[code EntityRecognizer]
|
|
+cell Annotate #[code Doc] objects with named entities.
|
|
|
|
+row
|
|
+cell #[code matcher]
|
|
+cell #[code Matcher]
|
|
+cell Rule-based sequence matcher.
|
|
|
|
+row
|
|
+cell #[code make_doc]
|
|
+cell #[code lambda text: Doc]
|
|
+cell Create a #[code Doc] object from unicode text.
|
|
|
|
+row
|
|
+cell #[code pipeline]
|
|
+cell -
|
|
+cell Sequence of annotation functions.
|
|
|
|
|
|
+h(2, "init") Language.__init__
|
|
+tag method
|
|
|
|
p Create or load the pipeline.
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code **overrides]
|
|
+cell -
|
|
+cell Keyword arguments indicating which defaults to override.
|
|
|
|
+footrow
|
|
+cell return
|
|
+cell #[code Language]
|
|
+cell The newly constructed object.
|
|
|
|
+h(2, "call") Language.__call__
|
|
+tag method
|
|
|
|
p Apply the pipeline to a single text.
|
|
|
|
+aside-code("Example").
|
|
from spacy.en import English
|
|
nlp = English()
|
|
doc = nlp('An example sentence. Another example sentence.')
|
|
doc[0].orth_, doc[0].head.tag_
|
|
# ('An', 'NN')
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code text]
|
|
+cell unicode
|
|
+cell The text to be processed.
|
|
|
|
+row
|
|
+cell #[code tag]
|
|
+cell bool
|
|
+cell Whether to apply the part-of-speech tagger.
|
|
|
|
+row
|
|
+cell #[code parse]
|
|
+cell bool
|
|
+cell Whether to apply the syntactic dependency parser.
|
|
|
|
+row
|
|
+cell #[code entity]
|
|
+cell bool
|
|
+cell Whether to apply the named entity recognizer.
|
|
|
|
+footrow
|
|
+cell return
|
|
+cell #[code Doc]
|
|
+cell A container for accessing the linguistic annotations.
|
|
|
|
+h(2, "pipe") Language.pipe
|
|
+tag method
|
|
|
|
p
|
|
| Process texts as a stream, and yield #[code Doc] objects in order.
|
|
| Supports GIL-free multi-threading.
|
|
|
|
+aside-code("Example").
|
|
texts = [u'One document.', u'...', u'Lots of documents']
|
|
for doc in nlp.pipe(texts, batch_size=50, n_threads=4):
|
|
assert doc.is_parsed
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code texts]
|
|
+cell -
|
|
+cell A sequence of unicode objects.
|
|
|
|
+row
|
|
+cell #[code n_threads]
|
|
+cell int
|
|
+cell
|
|
| The number of worker threads to use. If #[code -1], OpenMP will
|
|
| decide how many to use at run time. Default is #[code 2].
|
|
|
|
+row
|
|
+cell #[code batch_size]
|
|
+cell int
|
|
+cell The number of texts to buffer.
|
|
|
|
+footrow
|
|
+cell yield
|
|
+cell #[code Doc]
|
|
+cell Containers for accessing the linguistic annotations.
|
|
|
|
+h(2, "save_to_directory") Language.save_to_directory
|
|
+tag method
|
|
|
|
p Save the #[code Vocab], #[code StringStore] and pipeline to a directory.
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code path]
|
|
+cell string or pathlib path
|
|
+cell Path to save the model.
|
|
|
|
+footrow
|
|
+cell return
|
|
+cell #[code None]
|
|
+cell -
|