o Ή­§i)*γ@sRddlmZddlmZddlmZddlmZer ddlm Z Gdd„dƒZ dS) ι)Ϊ annotations)Ϊ TYPE_CHECKING)Ϊqualified_type_name)Ϊ wrap_expr)ΪExprc@s\eZdZdZdZddd„Zdd d „Zdd d „Zdd d„Zddd„Z d dd„Z d!d"dd„Z dS)#ΪExprCatNameSpacez.Namespace for categorical related expressions.ΪcatΪexprrΪreturnΪNonecCs |j|_dS©N)Ϊ_pyexpr)Ϊselfr ©rϊN/home/app/Keep/.python/lib/python3.10/site-packages/polars/expr/categorical.pyΪ__init__s zExprCatNameSpace.__init__cCσt|j ‘ƒS)u, Get the categories stored in this data type. Examples -------- >>> df = pl.Series( ... "cats", ["foo", "bar", "foo", "foo", "ham"], dtype=pl.Categorical ... ).to_frame() >>> df.select(pl.col("cats").cat.get_categories()) # doctest: +SKIP shape: (3, 1) β”Œβ”€β”€β”€β”€β”€β”€β” β”‚ cats β”‚ β”‚ --- β”‚ β”‚ str β”‚ β•žβ•β•β•β•β•β•β•‘ β”‚ foo β”‚ β”‚ bar β”‚ β”‚ ham β”‚ β””β”€β”€β”€β”€β”€β”€β”˜ )rr Zcat_get_categories©rrrrΪget_categoriesszExprCatNameSpace.get_categoriescCr)uΤ Return the byte-length of the string representation of each value. Returns ------- Expr Expression 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 -------- >>> df = pl.DataFrame( ... {"a": pl.Series(["CafΓ©", "345", "東京", None], dtype=pl.Categorical)} ... ) >>> df.with_columns( ... pl.col("a").cat.len_bytes().alias("n_bytes"), ... pl.col("a").cat.len_chars().alias("n_chars"), ... ) shape: (4, 3) β”Œβ”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚ a ┆ n_bytes ┆ n_chars β”‚ β”‚ --- ┆ --- ┆ --- β”‚ β”‚ cat ┆ u32 ┆ u32 β”‚ β•žβ•β•β•β•β•β•β•ͺ═════════β•ͺ═════════║ β”‚ CafΓ© ┆ 5 ┆ 4 β”‚ β”‚ 345 ┆ 3 ┆ 3 β”‚ β”‚ 東京 ┆ 6 ┆ 2 β”‚ β”‚ null ┆ null ┆ null β”‚ β””β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ )rr Z cat_len_bytesrrrrΪ len_bytes+s)zExprCatNameSpace.len_bytescCr)uΕ Return the number of characters of the string representation of each value. Returns ------- Expr Expression 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 -------- >>> df = pl.DataFrame( ... {"a": pl.Series(["CafΓ©", "345", "東京", None], dtype=pl.Categorical)} ... ) >>> df.with_columns( ... pl.col("a").cat.len_chars().alias("n_chars"), ... pl.col("a").cat.len_bytes().alias("n_bytes"), ... ) shape: (4, 3) β”Œβ”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚ a ┆ n_chars ┆ n_bytes β”‚ β”‚ --- ┆ --- ┆ --- β”‚ β”‚ cat ┆ u32 ┆ u32 β”‚ β•žβ•β•β•β•β•β•β•ͺ═════════β•ͺ═════════║ β”‚ CafΓ© ┆ 4 ┆ 5 β”‚ β”‚ 345 ┆ 3 ┆ 3 β”‚ β”‚ 東京 ┆ 2 ┆ 6 β”‚ β”‚ null ┆ null ┆ null β”‚ β””β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ )rr Z cat_len_charsrrrrΪ len_charsVs.zExprCatNameSpace.len_charsΪprefixΪstrcCσ0t|tƒsdt|ƒ›}t|ƒ‚t|j |‘ƒS)uO Check if string representations of values start with a substring. Parameters ---------- prefix Prefix substring. See Also -------- contains : Check if string repr contains a substring that matches a pattern. ends_with : Check if string repr end with a substring. Notes ----- Whereas `str.starts_with` allows expression inputs, `cat.starts_with` requires a literal string value. Examples -------- >>> df = pl.DataFrame( ... {"fruits": pl.Series(["apple", "mango", None], dtype=pl.Categorical)} ... ) >>> df.with_columns( ... pl.col("fruits").cat.starts_with("app").alias("has_prefix"), ... ) shape: (3, 2) β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚ fruits ┆ has_prefix β”‚ β”‚ --- ┆ --- β”‚ β”‚ cat ┆ bool β”‚ β•žβ•β•β•β•β•β•β•β•β•ͺ════════════║ β”‚ apple ┆ true β”‚ β”‚ mango ┆ false β”‚ β”‚ null ┆ null β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ Using `starts_with` as a filter condition: >>> df.filter(pl.col("fruits").cat.starts_with("app")) shape: (1, 1) β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β” β”‚ fruits β”‚ β”‚ --- β”‚ β”‚ cat β”‚ β•žβ•β•β•β•β•β•β•β•β•‘ β”‚ apple β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”˜ z!'prefix' must be a string; found )Ϊ isinstancerrΪ TypeErrorrr Zcat_starts_with)rrΪmsgrrrΪ starts_with†s 2zExprCatNameSpace.starts_withΪsuffixcCr)u( Check if string representations of values end with a substring. Parameters ---------- suffix Suffix substring. See Also -------- contains : Check if string reprs contains a substring that matches a pattern. starts_with : Check if string reprs start with a substring. Notes ----- Whereas `str.ends_with` allows expression inputs, `cat.ends_with` requires a literal string value. Examples -------- >>> df = pl.DataFrame( ... {"fruits": pl.Series(["apple", "mango", None], dtype=pl.Categorical)} ... ) >>> df.with_columns(pl.col("fruits").cat.ends_with("go").alias("has_suffix")) shape: (3, 2) β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚ fruits ┆ has_suffix β”‚ β”‚ --- ┆ --- β”‚ β”‚ cat ┆ bool β”‚ β•žβ•β•β•β•β•β•β•β•β•ͺ════════════║ β”‚ apple ┆ false β”‚ β”‚ mango ┆ true β”‚ β”‚ null ┆ null β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ Using `ends_with` as a filter condition: >>> df.filter(pl.col("fruits").cat.ends_with("go")) shape: (1, 1) β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β” β”‚ fruits β”‚ β”‚ --- β”‚ β”‚ cat β”‚ β•žβ•β•β•β•β•β•β•β•β•‘ β”‚ mango β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”˜ z!'suffix' must be a string; found )rrrrrr Z cat_ends_with)rrrrrrΪ ends_with½s 0zExprCatNameSpace.ends_withNΪoffsetΪintΪlengthϊ int | NonecCst|j ||‘ƒS)uN Extract a substring from the string representation of each 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 ------- Expr Expression 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 -------- >>> df = pl.DataFrame( ... { ... "s": pl.Series( ... ["pear", None, "papaya", "dragonfruit"], ... dtype=pl.Categorical, ... ) ... } ... ) >>> df.with_columns(pl.col("s").cat.slice(-3).alias("slice")) shape: (4, 2) β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β” β”‚ s ┆ slice β”‚ β”‚ --- ┆ --- β”‚ β”‚ cat ┆ str β”‚ β•žβ•β•β•β•β•β•β•β•β•β•β•β•β•β•ͺ═══════║ β”‚ pear ┆ ear β”‚ β”‚ null ┆ null β”‚ β”‚ papaya ┆ aya β”‚ β”‚ dragonfruit ┆ uit β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”˜ Using the optional `length` parameter >>> df.with_columns(pl.col("s").cat.slice(4, length=3).alias("slice")) shape: (4, 2) β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β” β”‚ s ┆ slice β”‚ β”‚ --- ┆ --- β”‚ β”‚ cat ┆ str β”‚ β•žβ•β•β•β•β•β•β•β•β•β•β•β•β•β•ͺ═══════║ β”‚ pear ┆ β”‚ β”‚ null ┆ null β”‚ β”‚ papaya ┆ ya β”‚ β”‚ dragonfruit ┆ onf β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”˜ )rr Z cat_slice)rr r"rrrΪsliceςs@zExprCatNameSpace.slice)r rr r )r r)rrr r)rrr rr )r r!r"r#r r) Ϊ__name__Ϊ __module__Ϊ __qualname__Ϊ__doc__Ϊ _accessorrrrrrrr$rrrrr s    + 0 75rN) Ϊ __future__rΪtypingrZpolars._utils.variousrZpolars._utils.wraprZpolarsrrrrrrΪs