mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 05:37:03 +03:00
576 lines
14 KiB
Plaintext
576 lines
14 KiB
Plaintext
//- 💫 DOCS > API > TOKEN
|
|
|
|
include ../_includes/_mixins
|
|
|
|
p An individual token — i.e. a word, punctuation symbol, whitespace, etc.
|
|
|
|
+h(2, "init") Token.__init__
|
|
+tag method
|
|
|
|
p Construct a #[code Token] object.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
token = doc[0]
|
|
assert token.text == u'Give'
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code vocab]
|
|
+cell #[code Vocab]
|
|
+cell A storage container for lexical types.
|
|
|
|
+row
|
|
+cell #[code doc]
|
|
+cell #[code Doc]
|
|
+cell The parent document.
|
|
|
|
+row
|
|
+cell #[code offset]
|
|
+cell int
|
|
+cell The index of the token within the document.
|
|
|
|
+row("foot")
|
|
+cell returns
|
|
+cell #[code Token]
|
|
+cell The newly constructed object.
|
|
|
|
+h(2, "len") Token.__len__
|
|
+tag method
|
|
|
|
p The number of unicode characters in the token, i.e. #[code token.text].
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
token = doc[0]
|
|
assert len(token) == 4
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row("foot")
|
|
+cell returns
|
|
+cell int
|
|
+cell The number of unicode characters in the token.
|
|
|
|
+h(2, "check_flag") Token.check_flag
|
|
+tag method
|
|
|
|
p Check the value of a boolean flag.
|
|
|
|
+aside-code("Example").
|
|
from spacy.attrs import IS_TITLE
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
token = doc[0]
|
|
assert token.check_flag(IS_TITLE) == True
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code flag_id]
|
|
+cell int
|
|
+cell The attribute ID of the flag to check.
|
|
|
|
+row("foot")
|
|
+cell returns
|
|
+cell bool
|
|
+cell Whether the flag is set.
|
|
|
|
+h(2, "similarity") Token.similarity
|
|
+tag method
|
|
+tag-model("vectors")
|
|
|
|
p Compute a semantic similarity estimate. Defaults to cosine over vectors.
|
|
|
|
+aside-code("Example").
|
|
apples, _, oranges = nlp(u'apples and oranges')
|
|
apples_oranges = apples.similarity(oranges)
|
|
oranges_apples = oranges.similarity(apples)
|
|
assert apples_oranges == oranges_apples
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell 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, "nbor") Token.nbor
|
|
+tag method
|
|
|
|
p Get a neighboring token.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
give_nbor = doc[0].nbor()
|
|
assert give_nbor.text == u'it'
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code i]
|
|
+cell int
|
|
+cell The relative position of the token to get. Defaults to #[code 1].
|
|
|
|
+row("foot")
|
|
+cell returns
|
|
+cell #[code Token]
|
|
+cell The token at position #[code self.doc[self.i+i]].
|
|
|
|
+h(2, "is_ancestor") Token.is_ancestor
|
|
+tag method
|
|
+tag-model("parse")
|
|
|
|
p
|
|
| Check whether this token is a parent, grandparent, etc. of another
|
|
| in the dependency tree.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
give = doc[0]
|
|
it = doc[1]
|
|
assert give.is_ancestor(it)
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell descendant
|
|
+cell #[code Token]
|
|
+cell Another token.
|
|
|
|
+row("foot")
|
|
+cell returns
|
|
+cell bool
|
|
+cell Whether this token is the ancestor of the descendant.
|
|
|
|
+h(2, "ancestors") Token.ancestors
|
|
+tag property
|
|
+tag-model("parse")
|
|
|
|
p The rightmost token of this token's syntactic descendants.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
it_ancestors = doc[1].ancestors
|
|
assert [t.text for t in it_ancestors] == [u'Give']
|
|
he_ancestors = doc[4].ancestors
|
|
assert [t.text for t in he_ancestors] == [u'pleaded']
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row("foot")
|
|
+cell yields
|
|
+cell #[code Token]
|
|
+cell
|
|
| A sequence of ancestor tokens such that
|
|
| #[code ancestor.is_ancestor(self)].
|
|
|
|
+h(2, "conjuncts") Token.conjuncts
|
|
+tag property
|
|
+tag-model("parse")
|
|
|
|
p A sequence of coordinated tokens, including the token itself.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'I like apples and oranges')
|
|
apples_conjuncts = doc[2].conjuncts
|
|
assert [t.text for t in apples_conjuncts] == [u'oranges']
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row("foot")
|
|
+cell yields
|
|
+cell #[code Token]
|
|
+cell A coordinated token.
|
|
|
|
+h(2, "children") Token.children
|
|
+tag property
|
|
+tag-model("parse")
|
|
|
|
p A sequence of the token's immediate syntactic children.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
give_children = doc[0].children
|
|
assert [t.text for t in give_children] == [u'it', u'back', u'!']
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row("foot")
|
|
+cell yields
|
|
+cell #[code Token]
|
|
+cell A child token such that #[code child.head==self].
|
|
|
|
+h(2, "subtree") Token.subtree
|
|
+tag property
|
|
+tag-model("parse")
|
|
|
|
p A sequence of all the token's syntactic descendents.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
give_subtree = doc[0].subtree
|
|
assert [t.text for t in give_subtree] == [u'Give', u'it', u'back', u'!']
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row("foot")
|
|
+cell yields
|
|
+cell #[code Token]
|
|
+cell A descendant token such that #[code self.is_ancestor(descendant)].
|
|
|
|
+h(2, "has_vector") Token.has_vector
|
|
+tag property
|
|
+tag-model("vectors")
|
|
|
|
p
|
|
| A boolean value indicating whether a word vector is associated with the
|
|
| token.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'I like apples')
|
|
apples = doc[2]
|
|
assert apples.has_vector
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row("foot")
|
|
+cell returns
|
|
+cell bool
|
|
+cell Whether the token has a vector data attached.
|
|
|
|
+h(2, "vector") Token.vector
|
|
+tag property
|
|
+tag-model("vectors")
|
|
|
|
p A real-valued meaning representation.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'I like apples')
|
|
apples = doc[2]
|
|
assert apples.vector.dtype == 'float32'
|
|
assert apples.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 token's semantics.
|
|
|
|
+h(2, "vector_norm") Span.vector_norm
|
|
+tag property
|
|
+tag-model("vectors")
|
|
|
|
p The L2 norm of the token's vector representation.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'I like apples and pasta')
|
|
apples = doc[2]
|
|
pasta = doc[4]
|
|
apples.vector_norm # 6.89589786529541
|
|
pasta.vector_norm # 7.759851932525635
|
|
assert apples.vector_norm != pasta.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 Verbatim text content.
|
|
|
|
+row
|
|
+cell #[code text_with_ws]
|
|
+cell unicode
|
|
+cell Text content, with trailing space character if present.
|
|
|
|
+row
|
|
+cell #[code whitespace_]
|
|
+cell unicode
|
|
+cell Trailing space character if present.
|
|
|
|
+row
|
|
+cell #[code orth]
|
|
+cell int
|
|
+cell ID of the verbatim text content.
|
|
|
|
+row
|
|
+cell #[code orth_]
|
|
+cell unicode
|
|
+cell
|
|
| Verbatim text content (identical to #[code Token.text]). Existst
|
|
| mostly for consistency with the other attributes.
|
|
|
|
+row
|
|
+cell #[code vocab]
|
|
+cell #[code Vocab]
|
|
+cell The vocab object of the parent #[code Doc].
|
|
|
|
+row
|
|
+cell #[code doc]
|
|
+cell #[code Doc]
|
|
+cell The parent document.
|
|
|
|
+row
|
|
+cell #[code head]
|
|
+cell #[code Token]
|
|
+cell The syntactic parent, or "governor", of this token.
|
|
|
|
+row
|
|
+cell #[code left_edge]
|
|
+cell #[code Token]
|
|
+cell The leftmost token of this token's syntactic descendants.
|
|
|
|
+row
|
|
+cell #[code right_edge]
|
|
+cell #[code Token]
|
|
+cell The rightmost token of this token's syntactic descendents.
|
|
|
|
+row
|
|
+cell #[code i]
|
|
+cell int
|
|
+cell The index of the token within the parent document.
|
|
|
|
+row
|
|
+cell #[code ent_type]
|
|
+cell int
|
|
+cell Named entity type.
|
|
|
|
+row
|
|
+cell #[code ent_type_]
|
|
+cell unicode
|
|
+cell Named entity type.
|
|
|
|
+row
|
|
+cell #[code ent_iob]
|
|
+cell int
|
|
+cell
|
|
| IOB code of named entity tag. #[code "B"]
|
|
| means the token begins an entity, #[code "I"] means it is inside
|
|
| an entity, #[code "O"] means it is outside an entity, and
|
|
| #[code ""] means no entity tag is set.
|
|
|
|
+row
|
|
+cell #[code ent_iob_]
|
|
+cell unicode
|
|
+cell
|
|
| IOB code of named entity tag. #[code "B"]
|
|
| means the token begins an entity, #[code "I"] means it is inside
|
|
| an entity, #[code "O"] means it is outside an entity, and
|
|
| #[code ""] means no entity tag is set.
|
|
|
|
+row
|
|
+cell #[code ent_id]
|
|
+cell int
|
|
+cell
|
|
| ID of the entity the token is an instance of, if any. Usually
|
|
| assigned by patterns in the Matcher.
|
|
|
|
+row
|
|
+cell #[code ent_id_]
|
|
+cell unicode
|
|
+cell
|
|
| ID of the entity the token is an instance of, if any. Usually
|
|
| assigned by patterns in the Matcher.
|
|
|
|
+row
|
|
+cell #[code lemma]
|
|
+cell int
|
|
+cell
|
|
| Base form of the token, with no inflectional suffixes.
|
|
|
|
+row
|
|
+cell #[code lemma_]
|
|
+cell unicode
|
|
+cell Base form of the token, with no inflectional suffixes.
|
|
|
|
+row
|
|
+cell #[code lower]
|
|
+cell int
|
|
+cell Lower-case form of the token.
|
|
|
|
+row
|
|
+cell #[code lower_]
|
|
+cell unicode
|
|
+cell Lower-case form of the token.
|
|
|
|
+row
|
|
+cell #[code shape]
|
|
+cell int
|
|
+cell
|
|
| Transform of the tokens's string, to show orthographic features.
|
|
| For example, "Xxxx" or "dd".
|
|
|
|
+row
|
|
+cell #[code shape_]
|
|
+cell unicode
|
|
+cell
|
|
| Transform of the tokens's string, to show orthographic features.
|
|
| For example, "Xxxx" or "dd".
|
|
|
|
+row
|
|
+cell #[code prefix]
|
|
+cell int
|
|
+cell
|
|
| Hash value of a length-N substring from the start of the
|
|
| token. Defaults to #[code N=1].
|
|
|
|
+row
|
|
+cell #[code prefix_]
|
|
+cell unicode
|
|
+cell
|
|
| A length-N substring from the start of the token. Defaults to
|
|
| #[code N=1].
|
|
|
|
+row
|
|
+cell #[code suffix]
|
|
+cell int
|
|
+cell
|
|
| Hash value of a length-N substring from the end of the token.
|
|
| Defaults to #[code N=3].
|
|
|
|
+row
|
|
+cell #[code suffix_]
|
|
+cell unicode
|
|
+cell Length-N substring from the end of the token. Defaults to #[code N=3].
|
|
|
|
+row
|
|
+cell #[code is_alpha]
|
|
+cell bool
|
|
+cell
|
|
| Does the token consist of alphabetic characters? Equivalent to
|
|
| #[code token.text.isalpha()].
|
|
|
|
+row
|
|
+cell #[code is_ascii]
|
|
+cell bool
|
|
+cell
|
|
| Does the token consist of ASCII characters? Equivalent to
|
|
| #[code [any(ord(c) >= 128 for c in token.text)]].
|
|
|
|
+row
|
|
+cell #[code is_digit]
|
|
+cell bool
|
|
+cell
|
|
| Does the token consist of digits? Equivalent to
|
|
| #[code token.text.isdigit()].
|
|
|
|
+row
|
|
+cell #[code is_lower]
|
|
+cell bool
|
|
+cell
|
|
| Is the token in lowercase? Equivalent to
|
|
| #[code token.text.islower()].
|
|
|
|
+row
|
|
+cell #[code is_upper]
|
|
+cell bool
|
|
+cell
|
|
| Is the token in uppercase? Equivalent to
|
|
| #[code token.text.isupper()].
|
|
|
|
+row
|
|
+cell #[code is_title]
|
|
+cell bool
|
|
+cell
|
|
| Is the token in titlecase? Equivalent to
|
|
| #[code token.text.istitle()].
|
|
|
|
+row
|
|
+cell #[code is_punct]
|
|
+cell bool
|
|
+cell Is the token punctuation?
|
|
|
|
+row
|
|
+cell #[code is_space]
|
|
+cell bool
|
|
+cell
|
|
| Does the token consist of whitespace characters? Equivalent to
|
|
| #[code token.text.isspace()].
|
|
|
|
+row
|
|
+cell #[code like_url]
|
|
+cell bool
|
|
+cell Does the token resemble a URL?
|
|
|
|
+row
|
|
+cell #[code like_num]
|
|
+cell bool
|
|
+cell Does the token represent a number? e.g. "10.9", "10", "ten", etc.
|
|
|
|
+row
|
|
+cell #[code like_email]
|
|
+cell bool
|
|
+cell Does the token resemble an email address?
|
|
|
|
+row
|
|
+cell #[code is_oov]
|
|
+cell bool
|
|
+cell Is the token out-of-vocabulary?
|
|
|
|
+row
|
|
+cell #[code is_stop]
|
|
+cell bool
|
|
+cell Is the token part of a "stop list"?
|
|
|
|
+row
|
|
+cell #[code pos]
|
|
+cell int
|
|
+cell Coarse-grained part-of-speech.
|
|
|
|
+row
|
|
+cell #[code pos_]
|
|
+cell unicode
|
|
+cell Coarse-grained part-of-speech.
|
|
|
|
+row
|
|
+cell #[code tag]
|
|
+cell int
|
|
+cell Fine-grained part-of-speech.
|
|
|
|
+row
|
|
+cell #[code tag_]
|
|
+cell unicode
|
|
+cell Fine-grained part-of-speech.
|
|
|
|
+row
|
|
+cell #[code dep]
|
|
+cell int
|
|
+cell Syntactic dependency relation.
|
|
|
|
+row
|
|
+cell #[code dep_]
|
|
+cell unicode
|
|
+cell Syntactic dependency relation.
|
|
|
|
+row
|
|
+cell #[code lang]
|
|
+cell int
|
|
+cell Language of the parent document's vocabulary.
|
|
+row
|
|
+cell #[code lang_]
|
|
+cell unicode
|
|
+cell Language of the parent document's vocabulary.
|
|
|
|
+row
|
|
+cell #[code prob]
|
|
+cell float
|
|
+cell Smoothed log probability estimate of token's type.
|
|
|
|
+row
|
|
+cell #[code idx]
|
|
+cell int
|
|
+cell The character offset of the token within the parent document.
|
|
|
|
+row
|
|
+cell #[code sentiment]
|
|
+cell float
|
|
+cell A scalar value indicating the positivity or negativity of the token.
|
|
|
|
+row
|
|
+cell #[code lex_id]
|
|
+cell int
|
|
+cell ID of the token's lexical type.
|