spaCy/website/api/doc.jade
2018-02-07 01:08:30 +01:00

796 lines
23 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

//- 💫 DOCS > API > DOC
include ../_includes/_mixins
p
| A #[code Doc] is a sequence of #[+api("token") #[code Token]] objects.
| Access sentences and named entities, export annotations to numpy arrays,
| losslessly serialize to compressed binary strings. The #[code Doc] object
| holds an array of #[code TokenC] structs. The Python-level #[code Token]
| and #[+api("span") #[code Span]] objects are views of this array, i.e.
| they don't own the data themselves.
+aside-code("Example").
# Construction 1
doc = nlp(u'Some text')
# Construction 2
from spacy.tokens import Doc
doc = Doc(nlp.vocab, words=[u'hello', u'world', u'!'],
spaces=[True, False, False])
+h(2, "init") Doc.__init__
+tag method
p
| Construct a #[code Doc] object. The most common way to get a #[code Doc]
| object is via the #[code nlp] object.
+table(["Name", "Type", "Description"])
+row
+cell #[code vocab]
+cell #[code Vocab]
+cell A storage container for lexical types.
+row
+cell #[code words]
+cell -
+cell A list of strings to add to the container.
+row
+cell #[code spaces]
+cell -
+cell
| A list of boolean values indicating whether each word has a
| subsequent space. Must have the same length as #[code words], if
| specified. Defaults to a sequence of #[code True].
+row("foot")
+cell returns
+cell #[code Doc]
+cell The newly constructed object.
+h(2, "getitem") Doc.__getitem__
+tag method
p
| Get a #[+api("token") #[code Token]] object at position #[code i], where
| #[code i] is an integer. Negative indexing is supported, and follows the
| usual Python semantics, i.e. #[code doc[-2]] is #[code doc[len(doc) - 2]].
+aside-code("Example").
doc = nlp(u'Give it back! He pleaded.')
assert doc[0].text == 'Give'
assert doc[-1].text == '.'
span = doc[1:3]
assert span.text == 'it back'
+table(["Name", "Type", "Description"])
+row
+cell #[code i]
+cell int
+cell The index of the token.
+row("foot")
+cell returns
+cell #[code Token]
+cell The token at #[code doc[i]].
p
| Get a #[+api("span") #[code Span]] object, starting at position
| #[code start] (token index) and ending at position #[code end] (token
| index).
p
| For instance, #[code doc[2:5]] produces a span consisting of tokens 2, 3
| and 4. Stepped slices (e.g. #[code doc[start : end : step]]) are not
| supported, as #[code Span] objects must be contiguous (cannot have gaps).
| You can use negative indices and open-ended ranges, which have their
| normal Python semantics.
+table(["Name", "Type", "Description"])
+row
+cell #[code start_end]
+cell tuple
+cell The slice of the document to get.
+row("foot")
+cell returns
+cell #[code Span]
+cell The span at #[code doc[start : end]].
+h(2, "iter") Doc.__iter__
+tag method
p
| Iterate over #[code Token] objects, from which the annotations can be
| easily accessed.
+aside-code("Example").
doc = nlp(u'Give it back')
assert [t.text for t in doc] == [u'Give', u'it', u'back']
p
| This is the main way of accessing #[+api("token") #[code Token]] objects,
| which are the main way annotations are accessed from Python. If
| faster-than-Python speeds are required, you can instead access the
| annotations as a numpy array, or access the underlying C data directly
| from Cython.
+table(["Name", "Type", "Description"])
+row("foot")
+cell yields
+cell #[code Token]
+cell A #[code Token] object.
+h(2, "len") Doc.__len__
+tag method
p Get the number of tokens in the document.
+aside-code("Example").
doc = nlp(u'Give it back! He pleaded.')
assert len(doc) == 7
+table(["Name", "Type", "Description"])
+row("foot")
+cell returns
+cell int
+cell The number of tokens in the document.
+h(2, "set_extension") Doc.set_extension
+tag classmethod
+tag-new(2)
p
| Define a custom attribute on the #[code Doc] which becomes available via
| #[code Doc._]. For details, see the documentation on
| #[+a("/usage/processing-pipelines#custom-components-attributes") custom attributes].
+aside-code("Example").
from spacy.tokens import Doc
city_getter = lambda doc: doc.text in ('New York', 'Paris', 'Berlin')
Doc.set_extension('has_city', getter=city_getter)
doc = nlp(u'I like New York')
assert doc._.has_city
+table(["Name", "Type", "Description"])
+row
+cell #[code name]
+cell unicode
+cell
| Name of the attribute to set by the extension. For example,
| #[code 'my_attr'] will be available as #[code doc._.my_attr].
+row
+cell #[code default]
+cell -
+cell
| Optional default value of the attribute if no getter or method
| is defined.
+row
+cell #[code method]
+cell callable
+cell
| Set a custom method on the object, for example
| #[code doc._.compare(other_doc)].
+row
+cell #[code getter]
+cell callable
+cell
| Getter function that takes the object and returns an attribute
| value. Is called when the user accesses the #[code ._] attribute.
+row
+cell #[code setter]
+cell callable
+cell
| Setter function that takes the #[code Doc] and a value, and
| modifies the object. Is called when the user writes to the
| #[code Doc._] attribute.
+h(2, "get_extension") Doc.get_extension
+tag classmethod
+tag-new(2)
p
| Look up a previously registered extension by name. Returns a 4-tuple
| #[code.u-break (default, method, getter, setter)] if the extension is
| registered. Raises a #[code KeyError] otherwise.
+aside-code("Example").
from spacy.tokens import Doc
Doc.set_extension('is_city', default=False)
extension = Doc.get_extension('is_city')
assert extension == (False, None, None, None)
+table(["Name", "Type", "Description"])
+row
+cell #[code name]
+cell unicode
+cell Name of the extension.
+row("foot")
+cell returns
+cell tuple
+cell
| A #[code.u-break (default, method, getter, setter)] tuple of the
| extension.
+h(2, "has_extension") Doc.has_extension
+tag classmethod
+tag-new(2)
p Check whether an extension has been registered on the #[code Doc] class.
+aside-code("Example").
from spacy.tokens import Doc
Doc.set_extension('is_city', default=False)
assert Doc.has_extension('is_city')
+table(["Name", "Type", "Description"])
+row
+cell #[code name]
+cell unicode
+cell Name of the extension to check.
+row("foot")
+cell returns
+cell bool
+cell Whether the extension has been registered.
+h(2, "char_span") Doc.char_span
+tag method
+tag-new(2)
p
| Create a #[code Span] object from the slice #[code doc.text[start : end]].
| Returns #[code None] if the character indices don't map to a valid span.
+aside-code("Example").
doc = nlp(u'I like New York')
span = doc.char_span(7, 15, label=u'GPE')
assert span.text == 'New York'
+table(["Name", "Type", "Description"])
+row
+cell #[code start]
+cell int
+cell The index of the first character of the span.
+row
+cell #[code end]
+cell int
+cell The index of the first character after the span.
+row
+cell #[code label]
+cell uint64 / unicode
+cell A label to attach to the Span, e.g. for named entities.
+row
+cell #[code vector]
+cell #[code.u-break numpy.ndarray[ndim=1, dtype='float32']]
+cell A meaning representation of the span.
+row("foot")
+cell returns
+cell #[code Span]
+cell The newly constructed object or #[code None].
+h(2, "similarity") Doc.similarity
+tag method
+tag-model("vectors")
p
| Make a semantic similarity estimate. The default estimate is cosine
| similarity using an average of word vectors.
+aside-code("Example").
apples = nlp(u'I like apples')
oranges = nlp(u'I like oranges')
apples_oranges = apples.similarity(oranges)
oranges_apples = oranges.similarity(apples)
assert apples_oranges == oranges_apples
+table(["Name", "Type", "Description"])
+row
+cell #[code other]
+cell -
+cell
| The object to compare with. By default, accepts #[code Doc],
| #[code Span], #[code Token] and #[code Lexeme] objects.
+row("foot")
+cell returns
+cell float
+cell A scalar similarity score. Higher is more similar.
+h(2, "count_by") Doc.count_by
+tag method
p
| Count the frequencies of a given attribute. Produces a dict of
| #[code {attr (int): count (ints)}] frequencies, keyed by the values
| of the given attribute ID.
+aside-code("Example").
from spacy.attrs import ORTH
doc = nlp(u'apple apple orange banana')
assert doc.count_by(ORTH) == {7024L: 1, 119552L: 1, 2087L: 2}
doc.to_array([attrs.ORTH])
# array([[11880], [11880], [7561], [12800]])
+table(["Name", "Type", "Description"])
+row
+cell #[code attr_id]
+cell int
+cell The attribute ID
+row("foot")
+cell returns
+cell dict
+cell A dictionary mapping attributes to integer counts.
+h(2, "get_lca_matrix") Doc.get_lca_matrix
+tag method
p
| Calculates the lowest common ancestor matrix for a given #[code Doc].
| Returns LCA matrix containing the integer index of the ancestor, or
| #[code -1] if no common ancestor is found, e.g. if span excludes a
| necessary ancestor.
+aside-code("Example").
doc = nlp(u"This is a test")
matrix = doc.get_lca_matrix()
# array([[0, 1, 1, 1], [1, 1, 1, 1], [1, 1, 2, 3], [1, 1, 3, 3]], dtype=int32)
+table(["Name", "Type", "Description"])
+row("foot")
+cell returns
+cell #[code.u-break numpy.ndarray[ndim=2, dtype='int32']]
+cell The lowest common ancestor matrix of the #[code Doc].
+h(2, "to_array") Doc.to_array
+tag method
p
| Export given token attributes to a numpy #[code ndarray].
| If #[code attr_ids] is a sequence of #[code M] attributes,
| the output array will be of shape #[code (N, M)], where #[code N]
| is the length of the #[code Doc] (in tokens). If #[code attr_ids] is
| a single attribute, the output shape will be #[code (N,)]. You can
| specify attributes by integer ID (e.g. #[code spacy.attrs.LEMMA])
| or string name (e.g. 'LEMMA' or 'lemma'). The values will be 64-bit
| integers.
+aside-code("Example").
from spacy.attrs import LOWER, POS, ENT_TYPE, IS_ALPHA
doc = nlp(text)
# All strings mapped to integers, for easy export to numpy
np_array = doc.to_array([LOWER, POS, ENT_TYPE, IS_ALPHA])
np_array = doc.to_array("POS")
+table(["Name", "Type", "Description"])
+row
+cell #[code attr_ids]
+cell list or int or string
+cell
| A list of attributes (int IDs or string names) or
| a single attribute (int ID or string name)
+row("foot")
+cell returns
+cell
| #[code.u-break numpy.ndarray[ndim=2, dtype='uint64']] or
| #[code.u-break numpy.ndarray[ndim=1, dtype='uint64']] or
+cell
| The exported attributes as a 2D numpy array, with one row per
| token and one column per attribute (when #[code attr_ids] is a
| list), or as a 1D numpy array, with one item per attribute (when
| #[code attr_ids] is a single value).
+h(2, "from_array") Doc.from_array
+tag method
p
| Load attributes from a numpy array. Write to a #[code Doc] object, from
| an #[code (M, N)] array of attributes.
+aside-code("Example").
from spacy.attrs import LOWER, POS, ENT_TYPE, IS_ALPHA
from spacy.tokens import Doc
doc = nlp("Hello world!")
np_array = doc.to_array([LOWER, POS, ENT_TYPE, IS_ALPHA])
doc2 = Doc(doc.vocab, words=[t.text for t in doc])
doc2.from_array([LOWER, POS, ENT_TYPE, IS_ALPHA], np_array)
assert doc[0].pos_ == doc2[0].pos_
+table(["Name", "Type", "Description"])
+row
+cell #[code attrs]
+cell ints
+cell A list of attribute ID ints.
+row
+cell #[code array]
+cell #[code.u-break numpy.ndarray[ndim=2, dtype='int32']]
+cell The attribute values to load.
+row("foot")
+cell returns
+cell #[code Doc]
+cell Itself.
+h(2, "to_disk") Doc.to_disk
+tag method
+tag-new(2)
p Save the current state to a directory.
+aside-code("Example").
doc.to_disk('/path/to/doc')
+table(["Name", "Type", "Description"])
+row
+cell #[code path]
+cell unicode or #[code Path]
+cell
| A path to a directory, which will be created if it doesn't exist.
| Paths may be either strings or #[code Path]-like objects.
+h(2, "from_disk") Doc.from_disk
+tag method
+tag-new(2)
p Loads state from a directory. Modifies the object in place and returns it.
+aside-code("Example").
from spacy.tokens import Doc
from spacy.vocab import Vocab
doc = Doc(Vocab()).from_disk('/path/to/doc')
+table(["Name", "Type", "Description"])
+row
+cell #[code path]
+cell unicode or #[code Path]
+cell
| A path to a directory. Paths may be either strings or
| #[code Path]-like objects.
+row("foot")
+cell returns
+cell #[code Doc]
+cell The modified #[code Doc] object.
+h(2, "to_bytes") Doc.to_bytes
+tag method
p Serialize, i.e. export the document contents to a binary string.
+aside-code("Example").
doc = nlp(u'Give it back! He pleaded.')
doc_bytes = doc.to_bytes()
+table(["Name", "Type", "Description"])
+row("foot")
+cell returns
+cell bytes
+cell
| A losslessly serialized copy of the #[code Doc], including all
| annotations.
+h(2, "from_bytes") Doc.from_bytes
+tag method
p Deserialize, i.e. import the document contents from a binary string.
+aside-code("Example").
from spacy.tokens import Doc
text = u'Give it back! He pleaded.'
doc = nlp(text)
bytes = doc.to_bytes()
doc2 = Doc(doc.vocab).from_bytes(bytes)
assert doc.text == doc2.text
+table(["Name", "Type", "Description"])
+row
+cell #[code data]
+cell bytes
+cell The string to load from.
+row("foot")
+cell returns
+cell #[code Doc]
+cell The #[code Doc] object.
+h(2, "merge") Doc.merge
+tag method
p
| Retokenize the document, such that the span at
| #[code doc.text[start_idx : end_idx]] is merged into a single token. If
| #[code start_idx] and #[code end_idx] do not mark start and end token
| boundaries, the document remains unchanged.
+aside-code("Example").
doc = nlp(u'Los Angeles start.')
doc.merge(0, len('Los Angeles'), 'NNP', 'Los Angeles', 'GPE')
assert [t.text for t in doc] == [u'Los Angeles', u'start', u'.']
+table(["Name", "Type", "Description"])
+row
+cell #[code start_idx]
+cell int
+cell The character index of the start of the slice to merge.
+row
+cell #[code end_idx]
+cell int
+cell The character index after the end of the slice to merge.
+row
+cell #[code **attributes]
+cell -
+cell
| Attributes to assign to the merged token. By default,
| attributes are inherited from the syntactic root token of
| the span.
+row("foot")
+cell returns
+cell #[code Token]
+cell
| The newly merged token, or #[code None] if the start and end
| indices did not fall at token boundaries
+h(2, "print_tree") Doc.print_tree
+tag method
+tag-model("parse")
p
| Returns the parse trees in JSON (dict) format. Especially useful for
| web applications.
+aside-code("Example").
doc = nlp('Alice ate the pizza.')
trees = doc.print_tree()
# {'modifiers': [
# {'modifiers': [], 'NE': 'PERSON', 'word': 'Alice', 'arc': 'nsubj', 'POS_coarse': 'PROPN', 'POS_fine': 'NNP', 'lemma': 'Alice'},
# {'modifiers': [{'modifiers': [], 'NE': '', 'word': 'the', 'arc': 'det', 'POS_coarse': 'DET', 'POS_fine': 'DT', 'lemma': 'the'}], 'NE': '', 'word': 'pizza', 'arc': 'dobj', 'POS_coarse': 'NOUN', 'POS_fine': 'NN', 'lemma': 'pizza'},
# {'modifiers': [], 'NE': '', 'word': '.', 'arc': 'punct', 'POS_coarse': 'PUNCT', 'POS_fine': '.', 'lemma': '.'}
# ], 'NE': '', 'word': 'ate', 'arc': 'ROOT', 'POS_coarse': 'VERB', 'POS_fine': 'VBD', 'lemma': 'eat'}
+table(["Name", "Type", "Description"])
+row
+cell #[code light]
+cell bool
+cell Don't include lemmas or entities.
+row
+cell #[code flat]
+cell bool
+cell Don't include arcs or modifiers.
+row("foot")
+cell returns
+cell dict
+cell Parse tree as dict.
+h(2, "ents") Doc.ents
+tag property
+tag-model("NER")
p
| Iterate over the entities in the document. Yields named-entity
| #[code Span] objects, if the entity recognizer has been applied to the
| document.
+aside-code("Example").
tokens = nlp(u'Mr. Best flew to New York on Saturday morning.')
ents = list(tokens.ents)
assert ents[0].label == 346
assert ents[0].label_ == 'PERSON'
assert ents[0].text == 'Mr. Best'
+table(["Name", "Type", "Description"])
+row("foot")
+cell yields
+cell #[code Span]
+cell Entities in the document.
+h(2, "noun_chunks") Doc.noun_chunks
+tag property
+tag-model("parse")
p
| Iterate over the base noun phrases in the document. Yields base
| noun-phrase #[code Span] objects, if the document has been syntactically
| parsed. A base noun phrase, or "NP chunk", is a noun phrase that does not
| permit other NPs to be nested within it so no NP-level coordination, no
| prepositional phrases, and no relative clauses.
+aside-code("Example").
doc = nlp(u'A phrase with another phrase occurs.')
chunks = list(doc.noun_chunks)
assert chunks[0].text == "A phrase"
assert chunks[1].text == "another phrase"
+table(["Name", "Type", "Description"])
+row("foot")
+cell yields
+cell #[code Span]
+cell Noun chunks in the document.
+h(2, "sents") Doc.sents
+tag property
+tag-model("parse")
p
| Iterate over the sentences in the document. Sentence spans have no label.
| To improve accuracy on informal texts, spaCy calculates sentence boundaries
| from the syntactic dependency parse. If the parser is disabled,
| the #[code sents] iterator will be unavailable.
+aside-code("Example").
doc = nlp(u"This is a sentence. Here's another...")
sents = list(doc.sents)
assert len(sents) == 2
assert [s.root.text for s in sents] == ["is", "'s"]
+table(["Name", "Type", "Description"])
+row("foot")
+cell yields
+cell #[code Span]
+cell Sentences in the document.
+h(2, "has_vector") Doc.has_vector
+tag property
+tag-model("vectors")
p
| A boolean value indicating whether a word vector is associated with the
| object.
+aside-code("Example").
doc = nlp(u'I like apples')
assert doc.has_vector
+table(["Name", "Type", "Description"])
+row("foot")
+cell returns
+cell bool
+cell Whether the document has a vector data attached.
+h(2, "vector") Doc.vector
+tag property
+tag-model("vectors")
p
| A real-valued meaning representation. Defaults to an average of the
| token vectors.
+aside-code("Example").
apples = nlp(u'I like apples')
assert doc.vector.dtype == 'float32'
assert doc.vector.shape == (300,)
+table(["Name", "Type", "Description"])
+row("foot")
+cell returns
+cell #[code.u-break numpy.ndarray[ndim=1, dtype='float32']]
+cell A 1D numpy array representing the document's semantics.
+h(2, "vector_norm") Doc.vector_norm
+tag property
+tag-model("vectors")
p
| The L2 norm of the document's vector representation.
+aside-code("Example").
doc1 = nlp(u'I like apples')
doc2 = nlp(u'I like oranges')
doc1.vector_norm # 4.54232424414368
doc2.vector_norm # 3.304373298575751
assert doc1.vector_norm != doc2.vector_norm
+table(["Name", "Type", "Description"])
+row("foot")
+cell returns
+cell float
+cell The L2 norm of the vector representation.
+h(2, "attributes") Attributes
+table(["Name", "Type", "Description"])
+row
+cell #[code text]
+cell unicode
+cell A unicode representation of the document text.
+row
+cell #[code text_with_ws]
+cell unicode
+cell
| An alias of #[code Doc.text], provided for duck-type compatibility
| with #[code Span] and #[code Token].
+row
+cell #[code mem]
+cell #[code Pool]
+cell The document's local memory heap, for all C data it owns.
+row
+cell #[code vocab]
+cell #[code Vocab]
+cell The store of lexical types.
+row
+cell #[code tensor] #[+tag-new(2)]
+cell object
+cell Container for dense vector representations.
+row
+cell #[code cats] #[+tag-new(2)]
+cell dictionary
+cell
| Maps either a label to a score for categories applied to whole
| document, or #[code (start_char, end_char, label)] to score for
| categories applied to spans. #[code start_char] and #[code end_char]
| should be character offsets, label can be either a string or an
| integer ID, and score should be a float.
+row
+cell #[code user_data]
+cell -
+cell A generic storage area, for user custom data.
+row
+cell #[code is_tagged]
+cell bool
+cell
| A flag indicating that the document has been part-of-speech
| tagged.
+row
+cell #[code is_parsed]
+cell bool
+cell A flag indicating that the document has been syntactically parsed.
+row
+cell #[code sentiment]
+cell float
+cell The document's positivity/negativity score, if available.
+row
+cell #[code user_hooks]
+cell dict
+cell
| A dictionary that allows customisation of the #[code Doc]'s
| properties.
+row
+cell #[code user_token_hooks]
+cell dict
+cell
| A dictionary that allows customisation of properties of
| #[code Token] children.
+row
+cell #[code user_span_hooks]
+cell dict
+cell
| A dictionary that allows customisation of properties of
| #[code Span] children.
+row
+cell #[code _]
+cell #[code Underscore]
+cell
| User space for adding custom
| #[+a("/usage/processing-pipelines#custom-components-attributes") attribute extensions].