Λ θΛ€h*γσX—ddlmZddlmZddlmZddlmZerddlm Z Gd„d«Z y) ι)Ϊ annotations)Ϊ TYPE_CHECKING)Ϊqualified_type_name)Ϊ wrap_expr)ΪExprcσN—eZdZdZdZd d„Zd d„Zd d„Zd d„Zd d„Z dd„Z ddd „Z y )ΪExprCatNameSpacez.Namespace for categorical related expressions.Ϊcatcσ&—|j|_y©N)Ϊ_pyexpr)ΪselfΪexprs ϊs/var/www/html/wine-match-dev/backend/winematch-backend/venv/lib/python3.12/site-packages/polars/expr/categorical.pyΪ__init__zExprCatNameSpace.__init__s €Ψ—|‘|ˆ σcσH—t|jj««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) 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 Ϊcat_get_categories©rs rΪget_categorieszExprCatNameSpace.get_categoriess€τ*˜Ÿ™Χ8Ρ8Σ:Σ;Π;rcσH—t|jj««S)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 Ϊ cat_len_bytesrs rΪ len_byteszExprCatNameSpace.len_bytes+s€τR˜Ÿ™Χ3Ρ3Σ5Σ6Π6rcσH—t|jj««S)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 Ϊ cat_len_charsrs rΪ len_charszExprCatNameSpace.len_charsVs€τ\˜Ÿ™Χ3Ρ3Σ5Σ6Π6rcσœ—t|t«sdt|«›}t|«‚t |j 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) 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 isinstanceΪstrrΪ TypeErrorrr Ϊcat_starts_with)rΪprefixΪmsgs rΪ starts_withzExprCatNameSpace.starts_with†sF€τd˜&€#Τ&Ψ5Τ6IΘ&Σ6QΠ5TΠUˆCά˜C“.Π ά˜Ÿ™Χ5Ρ5°fΣ=Σ>Π>rcσœ—t|t«sdt|«›}t|«‚t |j 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) 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 )rrrr rr Ϊ cat_ends_with)rΪsuffixr#s rΪ ends_withzExprCatNameSpace.ends_with½sF€τ`˜&€#Τ&Ψ5Τ6IΘ&Σ6QΠ5TΠUˆCά˜C“.Π ά˜Ÿ™Χ3Ρ3°FΣ;Σ<Π>> 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 Ϊ cat_slice)rΪoffsetΪlengths rΪslicezExprCatNameSpace.sliceςs!€τ@˜Ÿ™Χ/Ρ/°ΈΣ?Σ@Π@r)rrΪreturnΪNone)r.r)r"rr.r)r'rr.rr )r+Ϊintr,z int | Noner.r) Ϊ__name__Ϊ __module__Ϊ __qualname__Ϊ__doc__Ϊ _accessorrrrrr$r(r-©rrr r s3„Ω8ΰ€Iσ$σ<σ.)7σV.7σ`5?σn3=υj@Arr N) Ϊ __future__rΪtypingrΪpolars._utils.variousrΪpolars._utils.wraprΪpolarsrr r6rrϊr<s%πέ"ε ε5έ(αέχfAςfAr