spaCy/website/docs/api/lexeme.jade

240 lines
5.5 KiB
Plaintext

//- 💫 DOCS > API > LEXEME
include ../../_includes/_mixins
p An entry in the vocabulary.
+h(2, "attributes") Attributes
+table(["Name", "Type", "Description"])
+row
+cell #[code vocab]
+cell #[code Vocab]
+cell
+row
+cell #[code lower]
+cell int
+cell Lower-case form of the word.
+row
+cell #[code lower_]
+cell unicode
+cell Lower-case form of the word.
+row
+cell #[code shape]
+cell int
+cell Transform of the word's string, to show orthographic features.
+row
+cell #[code shape_]
+cell unicode
+cell Transform of the word's string, to show orthographic features.
+row
+cell #[code prefix]
+cell int
+cell Length-N substring from the start of the word. Defaults to #[code N=1].
+row
+cell #[code prefix_]
+cell unicode
+cell Length-N substring from the start of the word. Defaults to #[code N=1].
+row
+cell #[code suffix]
+cell int
+cell Length-N substring from the end of the word. Defaults to #[code N=3].
+row
+cell #[code suffix_]
+cell unicode
+cell Length-N substring from the start of the word. Defaults to #[code N=3].
+row
+cell #[code is_alpha]
+cell bool
+cell Equivalent to #[code word.orth_.isalpha()].
+row
+cell #[code is_ascii]
+cell bool
+cell Equivalent to #[code [any(ord(c) >= 128 for c in word.orth_)]].
+row
+cell #[code is_digit]
+cell bool
+cell Equivalent to #[code word.orth_.isdigit()].
+row
+cell #[code is_lower]
+cell bool
+cell Equivalent to #[code word.orth_.islower()].
+row
+cell #[code is_title]
+cell bool
+cell Equivalent to #[code word.orth_.istitle()].
+row
+cell #[code is_punct]
+cell bool
+cell Equivalent to #[code word.orth_.ispunct()].
+row
+cell #[code is_space]
+cell bool
+cell Equivalent to #[code word.orth_.isspace()].
+row
+cell #[code like_url]
+cell bool
+cell Does the word resemble a URL?
+row
+cell #[code like_num]
+cell bool
+cell Does the word represent a number? e.g. “10.9”, “10”, “ten”, etc.
+row
+cell #[code like_email]
+cell bool
+cell Does the word resemble an email address?
+row
+cell #[code is_oov]
+cell bool
+cell Is the word out-of-vocabulary?
+row
+cell #[code is_stop]
+cell bool
+cell Is the word part of a "stop list"?
+row
+cell #[code lang]
+cell int
+cell Language of the parent vocabulary.
+row
+cell #[code lang_]
+cell unicode
+cell Language of the parent vocabulary.
+row
+cell #[code prob]
+cell float
+cell Smoothed log probability estimate of token's type.
+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.
+row
+cell #[code text]
+cell unicode
+cell Verbatim text content.
+h(2, "init") Lexeme.__init__
+tag method
p Create a #[code Lexeme] object.
+table(["Name", "Type", "Description"])
+row
+cell #[code vocab]
+cell #[code Vocab]
+cell The parent vocabulary.
+row
+cell #[code orth]
+cell int
+cell The orth id of the lexeme.
+footrow
+cell returns
+cell #[code Lexeme]
+cell The newly constructed object.
+h(2, "set_flag") Lexeme.set_flag
+tag method
p Change the value of a boolean flag.
+table(["Name", "Type", "Description"])
+row
+cell #[code flag_id]
+cell int
+cell The attribute ID of the flag to set.
+row
+cell #[code value]
+cell bool
+cell The new value of the flag.
+footrow
+cell returns
+cell #[code None]
+cell -
+h(2, "check_flag") Lexeme.check_flag
+tag method
p Check the value of a boolean flag.
+table(["Name", "Type", "Description"])
+row
+cell #[code flag_id]
+cell int
+cell The attribute ID of the flag to query.
+footrow
+cell returns
+cell bool
+cell The value of the flag.
+h(2, "similarity") Lexeme.similarity
+tag method
p Compute a semantic similarity estimate. Defaults to cosine over vectors.
+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, "vector") Lexeme.vector
+tag property
p A real-valued meaning representation.
+table(["Name", "Type", "Description"])
+footrow
+cell returns
+cell #[code numpy.ndarray[ndim=1, dtype='float32']]
+cell A real-valued meaning representation.
+h(2, "has_vector") Lexeme.has_vector
+tag property
p A boolean value indicating whether a word vector is associated with the object.
+table(["Name", "Type", "Description"])
+footrow
+cell returns
+cell bool
+cell Whether a word vector is associated with the object.