dycw-utilities 0.159.7__py3-none-any.whl → 0.160.0__py3-none-any.whl

{dycw_utilities-0.159.7.dist-info → dycw_utilities-0.160.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dycw-utilities
-Version: 0.159.7
+Version: 0.160.0
 Author-email: Derek Wan <d.wan@icloud.com>
 License-File: LICENSE
 Requires-Python: >=3.12

{dycw_utilities-0.159.7.dist-info → dycw_utilities-0.160.0.dist-info}/RECORD

@@ -1,4 +1,4 @@
-utilities/__init__.py,sha256=56_sf0hO601aZOcezRa7sifQnNq2J9UBn2u-2N4z3x0,60
+utilities/__init__.py,sha256=KzM9quB3tnVvjnkbcK8xcoFUxydORZMj9PxkQWDPRDo,60
 utilities/altair.py,sha256=92E2lCdyHY4Zb-vCw6rEJIsWdKipuu-Tu2ab1ufUfAk,9079
 utilities/asyncio.py,sha256=PUedzQ5deqlSECQ33sam9cRzI9TnygHz3FdOqWJWPTM,15288
 utilities/atomicwrites.py,sha256=tPo6r-Rypd9u99u66B9z86YBPpnLrlHtwox_8Z7T34Y,5790
@@ -45,7 +45,7 @@ utilities/parse.py,sha256=JcJn5yXKhIWXBCwgBdPsyu7Hvcuw6kyEdqvaebCaI9k,17951
 utilities/pathlib.py,sha256=qGuU8XPmdgGpy8tOMUgelfXx3kxI8h9IaV3TI_06QGE,8428
 utilities/pickle.py,sha256=MBT2xZCsv0pH868IXLGKnlcqNx2IRVKYNpRcqiQQqxw,653
 utilities/platform.py,sha256=pTn7gw6N4T6LdKrf0virwarof_mze9WtoQlrGMzhGVI,2798
-utilities/polars.py,sha256=sPi-h2G-Nv6nykgK4_4Gg4lYEpy1F3F3KWswEASu6zw,79756
+utilities/polars.py,sha256=z1A4Uqqbccu1rSYmymMq6Ku5mLxEFpRhPGgoQ41WLyA,79912
 utilities/polars_ols.py,sha256=Uc9V5kvlWZ5cU93lKZ-cfAKdVFFw81tqwLW9PxtUvMs,5618
 utilities/postgres.py,sha256=ynCTTaF-bVEOSW-KEAR-dlLh_hYjeVVjm__-4pEU8Zk,12269
 utilities/pottery.py,sha256=ggMN72Y7wx7Js8VN6eyNyodpm8TIYqZHGghkDPXIVWk,3949
@@ -87,8 +87,8 @@ utilities/zoneinfo.py,sha256=FBMcUQ4662Aq8SsuCL1OAhDQiyANmVjtb-C30DRrWoE,1966
 utilities/pytest_plugins/__init__.py,sha256=U4S_2y3zgLZVfMenHRaJFBW8yqh2mUBuI291LGQVOJ8,35
 utilities/pytest_plugins/pytest_randomly.py,sha256=B1qYVlExGOxTywq2r1SMi5o7btHLk2PNdY_b1p98dkE,409
 utilities/pytest_plugins/pytest_regressions.py,sha256=9v8kAXDM2ycIXJBimoiF4EgrwbUvxTycFWJiGR_GHhM,1466
-dycw_utilities-0.159.7.dist-info/METADATA,sha256=iitOcQmUpaHfUZKp0sZ7xCjberrrfy1KUdA02FD72y4,1643
-dycw_utilities-0.159.7.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-dycw_utilities-0.159.7.dist-info/entry_points.txt,sha256=BOD_SoDxwsfJYOLxhrSXhHP_T7iw-HXI9f2WVkzYxvQ,135
-dycw_utilities-0.159.7.dist-info/licenses/LICENSE,sha256=gppZp16M6nSVpBbUBrNL6JuYfvKwZiKgV7XoKKsHzqo,1066
-dycw_utilities-0.159.7.dist-info/RECORD,,
+dycw_utilities-0.160.0.dist-info/METADATA,sha256=uNm9eVdsStvpIIDOUkcqxeyAqHAdEDZTHTQ_4FJt8EQ,1643
+dycw_utilities-0.160.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+dycw_utilities-0.160.0.dist-info/entry_points.txt,sha256=BOD_SoDxwsfJYOLxhrSXhHP_T7iw-HXI9f2WVkzYxvQ,135
+dycw_utilities-0.160.0.dist-info/licenses/LICENSE,sha256=gppZp16M6nSVpBbUBrNL6JuYfvKwZiKgV7XoKKsHzqo,1066
+dycw_utilities-0.160.0.dist-info/RECORD,,

utilities/__init__.py

@@ -1,3 +1,3 @@
 from __future__ import annotations
 
-__version__ = "0.159.7"
+__version__ = "0.160.0"

utilities/polars.py

@@ -1325,18 +1325,6 @@ class _FiniteEWMWeightsError(Exception):
 ##
 
 
-@overload
-def first_true_horizontal(column: Series, /) -> Series: ...
-@overload
-def first_true_horizontal(column1: Series, column2: Series, /) -> Series: ...
-@overload
-def first_true_horizontal(
-    column1: Series, column2: Series, column3: Series, /
-) -> Series: ...
-@overload
-def first_true_horizontal(
-    column1: Series, column2: Series, column3: Series, column4: Series, /
-) -> Series: ...
 @overload
 def first_true_horizontal(*columns: Series) -> Series: ...
 @overload
@@ -1931,27 +1919,17 @@ def nan_sum_agg(column: str | Expr, /, *, dtype: PolarsDataType | None = None) -
 ##
 
 
-def nan_sum_cols(
-    column: str | Expr, *columns: str | Expr, dtype: PolarsDataType | None = None
-) -> Expr:
+@overload
+def nan_sum_horizonal(*columns: Series) -> Series: ...
+@overload
+def nan_sum_horizonal(*columns: IntoExprColumn) -> ExprOrSeries: ...
+def nan_sum_horizonal(*columns: IntoExprColumn) -> ExprOrSeries:
     """Nan sum across columns."""
-    all_columns = chain([column], columns)
-    all_exprs = (
-        col(column) if isinstance(column, str) else column for column in all_columns
+    columns2 = ensure_expr_or_series_many(*columns)
+    expr = when(any_horizontal(*(c.is_not_null() for c in columns2))).then(
+        sum_horizontal(*columns2)
     )
-
-    def func(x: Expr, y: Expr, /) -> Expr:
-        return (
-            when(x.is_not_null() & y.is_not_null())
-            .then(x + y)
-            .when(x.is_not_null() & y.is_null())
-            .then(x)
-            .when(x.is_null() & y.is_not_null())
-            .then(y)
-            .otherwise(lit(None, dtype=dtype))
-        )
-
-    return reduce(func, all_exprs)
+    return try_reify_expr(expr, *columns2)
 
 
 ##
@@ -2446,6 +2424,31 @@ class RoundToFloatError(Exception):
 ##
 
 
+def select_exact(
+    df: DataFrame, /, *columns: IntoExprColumn, drop: MaybeIterable[str] | None = None
+) -> DataFrame:
+    """Select an exact set of columns from a DataFrame."""
+    names = [get_expr_name(df, c) for c in columns]
+    drop = set() if drop is None else set(always_iterable(drop))
+    union = set(names) | drop
+    extra = [c for c in df.columns if c not in union]
+    if len(extra) >= 1:
+        raise SelectExactError(columns=extra)
+    return df.select(*columns)
+
+
+@dataclass(kw_only=True, slots=True)
+class SelectExactError(Exception):
+    columns: list[str]
+
+    @override
+    def __str__(self) -> str:
+        return f"All columns must be selected; got {get_repr(self.columns)} remaining"
+
+
+##
+
+
 def set_first_row_as_columns(df: DataFrame, /) -> DataFrame:
     """Set the first row of a DataFrame as its columns."""
     try:
@@ -2654,6 +2657,7 @@ __all__ = [
     "OneColumnError",
     "OneColumnNonUniqueError",
     "RoundToFloatError",
+    "SelectExactError",
     "SetFirstRowAsColumnsError",
     "TimePeriodDType",
     "acf",
@@ -2698,7 +2702,7 @@ __all__ = [
     "join_into_periods",
     "map_over_columns",
     "nan_sum_agg",
-    "nan_sum_cols",
+    "nan_sum_horizonal",
     "normal",
     "number_of_decimals",
     "offset_datetime",
@@ -2709,6 +2713,7 @@ __all__ = [
     "read_series",
     "replace_time_zone",
     "round_to_float",
+    "select_exact",
     "serialize_dataframe",
     "set_first_row_as_columns",
     "struct_dtype",