q-PhddlmZddlmZddlmZddlmZddlm Z er ddl m Z ddl m Z e Gdd Zd S) ) annotations) TYPE_CHECKING)unstable)wrap_s) expr_dispatch)Series)PySeriesceZdZdZdZddZddZdd Zdd Ze dd Z dd Z ddZ ddZ ddZdd dZdS)! CatNameSpacez)Namespace for categorical related series.catseriesrreturnNonec|j|_dSN)_s)selfr s Y/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/polars/series/categorical.py__init__zCatNameSpace.__init__s"IcdS)aP Get the categories stored in this data type. Examples -------- >>> s = pl.Series(["foo", "bar", "foo", "foo", "ham"], dtype=pl.Categorical) >>> s.cat.get_categories() shape: (3,) Series: '' [str] [ "foo" "bar" "ham" ] Nrs rget_categorieszCatNameSpace.get_categoriesrboolc4|jS)a Return whether or not the column is a local categorical. Examples -------- Categoricals constructed without a string cache are considered local. >>> s = pl.Series(["a", "b", "a"], dtype=pl.Categorical) >>> s.cat.is_local() True Categoricals constructed with a string cache are considered global. >>> with pl.StringCache(): ... s = pl.Series(["a", "b", "a"], dtype=pl.Categorical) >>> s.cat.is_local() False )r cat_is_localrs ris_localzCatNameSpace.is_local(s&w##%%%rcNt|jS)a Convert a categorical column to its local representation. This may change the underlying physical representation of the column. See the documentation of :func:`StringCache` for more information on the difference between local and global categoricals. Examples -------- Compare the global and local representations of a categorical. >>> with pl.StringCache(): ... _ = pl.Series("x", ["a", "b", "a"], dtype=pl.Categorical) ... s = pl.Series("y", ["c", "b", "d"], dtype=pl.Categorical) >>> s.to_physical() shape: (3,) Series: 'y' [u32] [ 2 1 3 ] >>> s.cat.to_local().to_physical() shape: (3,) Series: 'y' [u32] [ 0 1 2 ] )rr cat_to_localrs rto_localzCatNameSpace.to_local=s!Bdg**,,---rc4|jS)a Indicate whether the Series uses lexical ordering. .. warning:: This functionality is considered **unstable**. It may be changed at any point without it being considered a breaking change. Examples -------- >>> s = pl.Series(["b", "a", "b"]).cast(pl.Categorical) >>> s.cat.uses_lexical_ordering() False >>> s = s.cast(pl.Categorical("lexical")) >>> s.cat.uses_lexical_ordering() True )rcat_uses_lexical_orderingrs ruses_lexical_orderingz"CatNameSpace.uses_lexical_ordering`s$w00222rcdS)u& Return the byte-length of the string representation of each value. Returns ------- Series Series of data type :class:`UInt32`. See Also -------- len_chars Notes ----- When working with non-ASCII text, the length in bytes is not the same as the length in characters. You may want to use :func:`len_chars` instead. Note that :func:`len_bytes` is much more performant (_O(1)_) than :func:`len_chars` (_O(n)_). Examples -------- >>> s = pl.Series(["Café", "345", "東京", None], dtype=pl.Categorical) >>> s.cat.len_bytes() shape: (4,) Series: '' [u32] [ 5 3 6 null ] Nrrs r len_byteszCatNameSpace.len_bytestrrcdS)u Return the number of characters of the string representation of each value. Returns ------- Series Series of data type :class:`UInt32`. See Also -------- len_bytes Notes ----- When working with ASCII text, use :func:`len_bytes` instead to achieve equivalent output with much better performance: :func:`len_bytes` runs in _O(1)_, while :func:`len_chars` runs in (_O(n)_). A character is defined as a `Unicode scalar value`_. A single character is represented by a single byte when working with ASCII text, and a maximum of 4 bytes otherwise. .. _Unicode scalar value: https://www.unicode.org/glossary/#unicode_scalar_value Examples -------- >>> s = pl.Series(["Café", "345", "東京", None], dtype=pl.Categorical) >>> s.cat.len_chars() shape: (4,) Series: '' [u32] [ 4 3 2 null ] Nrrs r len_charszCatNameSpace.len_charsrrprefixstrcdS)a{ Check if string representations of values start with a substring. Parameters ---------- prefix Prefix substring. See Also -------- contains : Check if the string repr contains a substring that matches a pattern. ends_with : Check if string repr ends with a substring. Examples -------- >>> s = pl.Series("fruits", ["apple", "mango", None], dtype=pl.Categorical) >>> s.cat.starts_with("app") shape: (3,) Series: 'fruits' [bool] [ true false null ] Nr)rr*s r starts_withzCatNameSpace.starts_withrrsuffixcdS)az Check if string representations of values end with a substring. Parameters ---------- suffix Suffix substring. See Also -------- contains : Check if the string repr contains a substring that matches a pattern. starts_with : Check if string repr starts with a substring. Examples -------- >>> s = pl.Series("fruits", ["apple", "mango", None], dtype=pl.Categorical) >>> s.cat.ends_with("go") shape: (3,) Series: 'fruits' [bool] [ false true null ] Nr)rr.s r ends_withzCatNameSpace.ends_withrrNoffsetintlength int | NonecdS)aV Extract a substring from the string representation of each string value. Parameters ---------- offset Start index. Negative indexing is supported. length Length of the slice. If set to `None` (default), the slice is taken to the end of the string. Returns ------- Series Series of data type :class:`String`. Notes ----- Both the `offset` and `length` inputs are defined in terms of the number of characters in the (UTF8) string. A character is defined as a `Unicode scalar value`_. A single character is represented by a single byte when working with ASCII text, and a maximum of 4 bytes otherwise. .. _Unicode scalar value: https://www.unicode.org/glossary/#unicode_scalar_value Examples -------- >>> s = pl.Series(["pear", None, "papaya", "dragonfruit"], dtype=pl.Categorical) >>> s.cat.slice(-3) shape: (4,) Series: '' [str] [ "ear" null "aya" "uit" ] Using the optional `length` parameter >>> s.cat.slice(4, length=3) shape: (4,) Series: '' [str] [ "" null "ya" "onf" ] Nr)rr1r3s rslicezCatNameSpace.slicerr)r rrr)rr)rr)r*r+rr)r.r+rrr)r1r2r3r4rr)__name__ __module__ __qualname____doc__ _accessorrrrr"rr%r'r)r-r0r6rrrr r s33I&&&&    "&&&&*!.!.!.!.FXZZ333Z3&     D% % % % N    6    62 2 2 2 2 2 2 rr N) __future__rtypingrpolars._utils.unstablerpolars._utils.wraprpolars.series.utilsrpolarsr polars.polarsr r rrrrCs"""""" ++++++%%%%%%------'&&&&&&V V V V V V V V V V r