mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 07:57:35 +03:00
364 lines
8.9 KiB
Plaintext
364 lines
8.9 KiB
Plaintext
//- 💫 DOCS > API > SPAN
|
|
|
|
include ../../_includes/_mixins
|
|
|
|
p A slice from a #[+api("doc") #[code Doc]] object.
|
|
|
|
+h(2, "init") Span.__init__
|
|
+tag method
|
|
|
|
p Create a Span object from the #[code slice doc[start : end]].
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
span = doc[1:4]
|
|
assert [t.text for t in span] == [u'it', u'back', u'!']
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code doc]
|
|
+cell #[code Doc]
|
|
+cell The parent document.
|
|
|
|
+row
|
|
+cell #[code start]
|
|
+cell int
|
|
+cell The index of the first token of the span.
|
|
|
|
+row
|
|
+cell #[code end]
|
|
+cell int
|
|
+cell The index of the first token after the span.
|
|
|
|
+row
|
|
+cell #[code label]
|
|
+cell int
|
|
+cell A label to attach to the span, e.g. for named entities.
|
|
|
|
+row
|
|
+cell #[code vector]
|
|
+cell #[code numpy.ndarray[ndim=1, dtype='float32']]
|
|
+cell A meaning representation of the span.
|
|
|
|
+footrow
|
|
+cell returns
|
|
+cell #[code Span]
|
|
+cell The newly constructed object.
|
|
|
|
+h(2, "getitem") Span.__getitem__
|
|
+tag method
|
|
|
|
p Get a #[code Token] object.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
span = doc[1:4]
|
|
assert span[1].text == 'back'
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code i]
|
|
+cell int
|
|
+cell The index of the token within the span.
|
|
|
|
+footrow
|
|
+cell returns
|
|
+cell #[code Token]
|
|
+cell The token at #[code span[i]].
|
|
|
|
p Get a #[code Span] object.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
span = doc[1:4]
|
|
assert span[1:3].text == 'back!'
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code start_end]
|
|
+cell tuple
|
|
+cell The slice of the span to get.
|
|
|
|
+footrow
|
|
+cell returns
|
|
+cell #[code Span]
|
|
+cell The span at #[code span[start : end]].
|
|
|
|
+h(2, "iter") Span.__iter__
|
|
+tag method
|
|
|
|
p Iterate over #[code Token] objects.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
span = doc[1:4]
|
|
assert [t.text for t in span] == ['it', 'back', '!']
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+footrow
|
|
+cell yields
|
|
+cell #[code Token]
|
|
+cell A #[code Token] object.
|
|
|
|
+h(2, "len") Span.__len__
|
|
+tag method
|
|
|
|
p Get the number of tokens in the span.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
span = doc[1:4]
|
|
assert len(span) == 3
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+footrow
|
|
+cell returns
|
|
+cell int
|
|
+cell The number of tokens in the span.
|
|
|
|
+h(2, "similarity") Span.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").
|
|
doc = nlp(u'green apples and red oranges')
|
|
green_apples = doc[:2]
|
|
red_oranges = doc[3:]
|
|
apples_oranges = green_apples.similarity(red_oranges)
|
|
oranges_apples = red_oranges.similarity(green_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.
|
|
|
|
+footrow
|
|
+cell returns
|
|
+cell float
|
|
+cell A scalar similarity score. Higher is more similar.
|
|
|
|
+h(2, "merge") Span.merge
|
|
+tag method
|
|
|
|
p Retokenize the document, such that the span is merged into a single token.
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+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.
|
|
|
|
+footrow
|
|
+cell returns
|
|
+cell #[code Token]
|
|
+cell The newly merged token.
|
|
|
|
+h(2, "root") Span.root
|
|
+tag property
|
|
+tag-model("parse")
|
|
|
|
p
|
|
| The token within the span that's highest in the parse tree. If there's a
|
|
| tie, the earlist is prefered.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'I like New York in Autumn.')
|
|
i, like, new, york, in_, autumn, dot = range(len(doc))
|
|
assert doc[new].head.text == 'York'
|
|
assert doc[york].head.text == 'like'
|
|
new_york = doc[new:york+1]
|
|
assert new_york.root.text == 'York'
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+footrow
|
|
+cell returns
|
|
+cell #[code Token]
|
|
+cell The root token.
|
|
|
|
+h(2, "lefts") Span.lefts
|
|
+tag property
|
|
+tag-model("parse")
|
|
|
|
p Tokens that are to the left of the span, whose head is within the span.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'I like New York in Autumn.')
|
|
lefts = [t.text for t in doc[3:7].lefts]
|
|
assert lefts == [u'New']
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+footrow
|
|
+cell yields
|
|
+cell #[code Token]
|
|
+cell A left-child of a token of the span.
|
|
|
|
+h(2, "rights") Span.rights
|
|
+tag property
|
|
+tag-model("parse")
|
|
|
|
p Tokens that are to the right of the span, whose head is within the span.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'I like New York in Autumn.')
|
|
rights = [t.text for t in doc[2:4].rights]
|
|
assert rights == [u'in']
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+footrow
|
|
+cell yields
|
|
+cell #[code Token]
|
|
+cell A right-child of a token of the span.
|
|
|
|
+h(2, "subtree") Span.subtree
|
|
+tag property
|
|
+tag-model("parse")
|
|
|
|
p Tokens that descend from tokens in the span, but fall outside it.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'Give it back! He pleaded.')
|
|
subtree = [t.text for t in doc[:3].subtree]
|
|
assert subtree == [u'Give', u'it', u'back', u'!']
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+footrow
|
|
+cell yields
|
|
+cell #[code Token]
|
|
+cell A descendant of a token within the span.
|
|
|
|
+h(2, "has_vector") Span.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[1:].has_vector
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+footrow
|
|
+cell returns
|
|
+cell bool
|
|
+cell Whether the span has a vector data attached.
|
|
|
|
+h(2, "vector") Span.vector
|
|
+tag property
|
|
+tag-model("vectors")
|
|
|
|
p
|
|
| A real-valued meaning representation. Defaults to an average of the
|
|
| token vectors.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'I like apples')
|
|
assert doc[1:].vector.dtype == 'float32'
|
|
assert doc[1:].vector.shape == (300,)
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+footrow
|
|
+cell returns
|
|
+cell #[code numpy.ndarray[ndim=1, dtype='float32']]
|
|
+cell A 1D numpy array representing the span's semantics.
|
|
|
|
+h(2, "vector_norm") Span.vector_norm
|
|
+tag property
|
|
+tag-model("vectors")
|
|
|
|
p
|
|
| The L2 norm of the span's vector representation.
|
|
|
|
+aside-code("Example").
|
|
doc = nlp(u'I like apples')
|
|
doc[1:].vector_norm # 4.800883928527915
|
|
doc[2:].vector_norm # 6.895897646384268
|
|
assert doc[1:].vector_norm != doc[2:].vector_norm
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+footrow
|
|
+cell returns
|
|
+cell float
|
|
+cell The L2 norm of the vector representation.
|
|
|
|
+h(2, "attributes") Attributes
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code doc]
|
|
+cell #[code Doc]
|
|
+cell The parent document.
|
|
|
|
+row
|
|
+cell #[code sent]
|
|
+cell #[code Span]
|
|
+cell The sentence span that this span is a part of.
|
|
|
|
+row
|
|
+cell #[code start]
|
|
+cell int
|
|
+cell The token offset for the start of the span.
|
|
|
|
+row
|
|
+cell #[code end]
|
|
+cell int
|
|
+cell The token offset for the end of the span.
|
|
|
|
+row
|
|
+cell #[code start_char]
|
|
+cell int
|
|
+cell The character offset for the start of the span.
|
|
|
|
+row
|
|
+cell #[code end_char]
|
|
+cell int
|
|
+cell The character offset for the end of the span.
|
|
|
|
+row
|
|
+cell #[code text]
|
|
+cell unicode
|
|
+cell A unicode representation of the span text.
|
|
|
|
+row
|
|
+cell #[code text_with_ws]
|
|
+cell unicode
|
|
+cell
|
|
| The text content of the span with a trailing whitespace character
|
|
| if the last token has one.
|
|
|
|
+row
|
|
+cell #[code label]
|
|
+cell int
|
|
+cell The span's label.
|
|
|
|
+row
|
|
+cell #[code label_]
|
|
+cell unicode
|
|
+cell The span's label.
|
|
|
|
+row
|
|
+cell #[code lemma_]
|
|
+cell unicode
|
|
+cell The span's lemma.
|
|
|
|
+row
|
|
+cell #[code ent_id]
|
|
+cell int
|
|
+cell The integer ID of the named entity the token is an instance of.
|
|
|
|
+row
|
|
+cell #[code ent_id_]
|
|
+cell unicode
|
|
+cell The string ID of the named entity the token is an instance of.
|