§ q-Ph*ãó`—ddlmZddlmZddlmZddlmZerddlm Z Gd„d¦«Z dS) é)Ú annotations)Ú TYPE_CHECKING)Úqualified_type_name)Ú wrap_expr)ÚExprcóP—eZdZdZdZdd„Zdd„Zdd „Zdd „Zdd „Z dd„Z ddd„Z dS)ÚExprCatNameSpacez.Namespace for categorical related expressions.ÚcatÚexprrÚreturnÚNonecó—|j|_dS©N)Ú_pyexpr)Úselfr s úW/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/polars/expr/categorical.pyÚ__init__zExprCatNameSpace.__init__s€Ø”|ˆŒ ˆ ˆ ócóN—t|j ¦«¦«S)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()) shape: (3, 1) ┌──────┠│ cats │ │ --- │ │ str │ â•žâ•â•â•â•â•â•â•¡ │ foo │ │ bar │ │ ham │ └──────┘ )rrÚcat_get_categories©rs rÚget_categorieszExprCatNameSpace.get_categoriess €õ*˜œ×8Ò8Ñ:Ô:Ñ;Ô;Ð;rcóN—t|j ¦«¦«S)uÔ 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(["Café", "345", "æ±äº¬", 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) ┌──────┬─────────┬─────────┠│ a ┆ n_bytes ┆ n_chars │ │ --- ┆ --- ┆ --- │ │ cat ┆ u32 ┆ u32 │ â•žâ•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•¡ │ Café ┆ 5 ┆ 4 │ │ 345 ┆ 3 ┆ 3 │ │ æ±äº¬ ┆ 6 ┆ 2 │ │ null ┆ null ┆ null │ └──────┴─────────┴─────────┘ )rrÚ cat_len_bytesrs rÚ len_byteszExprCatNameSpace.len_bytes+s!€õR˜œ×3Ò3Ñ5Ô5Ñ6Ô6Ð6rcóN—t|j ¦«¦«S)uÅ 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(["Café", "345", "æ±äº¬", 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) ┌──────┬─────────┬─────────┠│ a ┆ n_chars ┆ n_bytes │ │ --- ┆ --- ┆ --- │ │ cat ┆ u32 ┆ u32 │ â•žâ•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•¡ │ Café ┆ 4 ┆ 5 │ │ 345 ┆ 3 ┆ 3 │ │ æ±äº¬ ┆ 2 ┆ 6 │ │ null ┆ null ┆ null │ └──────┴─────────┴─────────┘ )rrÚ cat_len_charsrs rÚ len_charszExprCatNameSpace.len_charsVs!€õ\˜œ×3Ò3Ñ5Ô5Ñ6Ô6Ð6rÚprefixÚstrcó¼—t|t¦«s!dt|¦«›}t|¦«‚t |j |¦«¦«S)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) ┌────────┬────────────┠│ fruits ┆ has_prefix │ │ --- ┆ --- │ │ cat ┆ bool │ â•žâ•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•¡ │ apple ┆ true │ │ mango ┆ false │ │ null ┆ null │ └────────┴────────────┘ Using `starts_with` as a filter condition: >>> df.filter(pl.col("fruits").cat.starts_with("app")) shape: (1, 1) ┌────────┠│ fruits │ │ --- │ │ cat │ â•žâ•â•â•â•â•â•â•â•â•¡ │ apple │ └────────┘ z!'prefix' must be a string; found )Ú isinstancer rÚ TypeErrorrrÚcat_starts_with)rrÚmsgs rÚ starts_withzExprCatNameSpace.starts_with†sW€õd˜&¥#Ñ&Ô&ð !ØUÕ6IÈ&Ñ6QÔ6QÐUÐUˆCݘC‘.”.Рݘœ×5Ò5°fÑ=Ô=Ñ>Ô>Ð>rÚsuffixcó¼—t|t¦«s!dt|¦«›}t|¦«‚t |j |¦«¦«S)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) ┌────────┬────────────┠│ fruits ┆ has_suffix │ │ --- ┆ --- │ │ cat ┆ bool │ â•žâ•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•¡ │ apple ┆ false │ │ mango ┆ true │ │ null ┆ null │ └────────┴────────────┘ Using `ends_with` as a filter condition: >>> df.filter(pl.col("fruits").cat.ends_with("go")) shape: (1, 1) ┌────────┠│ fruits │ │ --- │ │ cat │ â•žâ•â•â•â•â•â•â•â•â•¡ │ mango │ └────────┘ z!'suffix' must be a string; found )r"r rr#rrÚ cat_ends_with)rr'r%s rÚ ends_withzExprCatNameSpace.ends_with½sW€õ`˜&¥#Ñ&Ô&ð !ØUÕ6IÈ&Ñ6QÔ6QÐUÐUˆCݘC‘.”.Рݘœ×3Ò3°FÑ;Ô;Ñ<Ô<Ð>> 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) ┌─────────────┬───────┠│ s ┆ slice │ │ --- ┆ --- │ │ cat ┆ str │ â•žâ•â•â•â•â•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•¡ │ pear ┆ ear │ │ null ┆ null │ │ papaya ┆ aya │ │ dragonfruit ┆ uit │ └─────────────┴───────┘ Using the optional `length` parameter >>> df.with_columns(pl.col("s").cat.slice(4, length=3).alias("slice")) shape: (4, 2) ┌─────────────┬───────┠│ s ┆ slice │ │ --- ┆ --- │ │ cat ┆ str │ â•žâ•â•â•â•â•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•¡ │ pear ┆ │ │ null ┆ null │ │ papaya ┆ ya │ │ dragonfruit ┆ onf │ └─────────────┴───────┘ )rrÚ cat_slice)rr+r-s rÚslicezExprCatNameSpace.sliceòs%€õ@˜œ×/Ò/°¸Ñ?Ô?Ñ@Ô@Ð@r)r rr r )r r)rr r r)r'r r rr)r+r,r-r.r r) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú _accessorrrrrr&r*r1©rrr r s€€€€€Ø8Ð8à€Ið$ð$ð$ð$ð<ð<ð<ð<ð.)7ð)7ð)7ð)7ðV.7ð.7ð.7ð.7ð`5?ð5?ð5?ð5?ðn3=ð3=ð3=ð3=ðj@Að@Að@Að@Að@Að@Að@Arr N) Ú __future__rÚtypingrÚpolars._utils.variousrÚpolars._utils.wraprÚpolarsrr r7rrúr=s­ðØ"Ð"Ð"Ð"Ð"Ð"à Ð Ð Ð Ð Ð à5Ð5Ð5Ð5Ð5Ð5Ø(Ð(Ð(Ð(Ð(Ð(àðØÐÐÐÐÐðfAðfAðfAðfAðfAñfAôfAðfAðfAðfAr