From aa246940b3842a8b28a677329d472f0b35911d8b Mon Sep 17 00:00:00 2001 From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com> Date: Sat, 3 Feb 2024 14:33:59 -0800 Subject: [PATCH 1/2] DEPR: Remove Index type checking attributes --- doc/source/reference/index.rst | 1 - doc/source/reference/indexing.rst | 7 - doc/source/whatsnew/v3.0.0.rst | 4 +- pandas/core/indexes/base.py | 359 -------------------------- pandas/plotting/_core.py | 11 +- pandas/plotting/_matplotlib/core.py | 17 +- pandas/tests/indexes/test_old_base.py | 55 ---- 7 files changed, 22 insertions(+), 432 deletions(-) diff --git a/doc/source/reference/index.rst b/doc/source/reference/index.rst index 7f4d05414d254..639bac4d40b70 100644 --- a/doc/source/reference/index.rst +++ b/doc/source/reference/index.rst @@ -62,7 +62,6 @@ to be stable. .. .. toctree:: - api/pandas.Index.holds_integer api/pandas.Index.nlevels api/pandas.Index.sort diff --git a/doc/source/reference/indexing.rst b/doc/source/reference/indexing.rst index fa6105761df0a..8c8e4e42c35e9 100644 --- a/doc/source/reference/indexing.rst +++ b/doc/source/reference/indexing.rst @@ -61,13 +61,6 @@ Modifying and computations Index.identical Index.insert Index.is_ - Index.is_boolean - Index.is_categorical - Index.is_floating - Index.is_integer - Index.is_interval - Index.is_numeric - Index.is_object Index.min Index.max Index.reindex diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst index 806a46c248e15..8d83a8789468f 100644 --- a/doc/source/whatsnew/v3.0.0.rst +++ b/doc/source/whatsnew/v3.0.0.rst @@ -102,13 +102,13 @@ Deprecations Removal of prior version deprecations/changes ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -- Removed :meth:`DataFrameGroupby.fillna` and :meth:`SeriesGroupBy.fillna` (:issue:`55719`) - Removed ``DataFrameGroupBy.grouper`` and ``SeriesGroupBy.grouper`` (:issue:`56521`) +- Removed ``DataFrameGroupby.fillna`` and ``SeriesGroupBy.fillna``` (:issue:`55719`) - Removed ``axis`` argument from :meth:`DataFrame.groupby`, :meth:`Series.groupby`, :meth:`DataFrame.rolling`, :meth:`Series.rolling`, :meth:`DataFrame.resample`, and :meth:`Series.resample` (:issue:`51203`) - Removed ``axis`` argument from all groupby operations (:issue:`50405`) - Removed deprecated argument ``obj`` in :meth:`.DataFrameGroupBy.get_group` and :meth:`.SeriesGroupBy.get_group` (:issue:`53545`) - Removed the ``ArrayManager`` (:issue:`55043`) -- +- Removed the ``is_boolean``, ``is_integer``, ``is_floating``, ``holds_integer``, ``is_numeric``, ``is_categorical``, ``is_object``, and ``is_interval`` attributes of :class:`Index` (:issue:`50042`) .. --------------------------------------------------------------------------- .. _whatsnew_300.performance: diff --git a/pandas/core/indexes/base.py b/pandas/core/indexes/base.py index 87135ce9e0dd0..058394c72110a 100644 --- a/pandas/core/indexes/base.py +++ b/pandas/core/indexes/base.py @@ -2387,365 +2387,6 @@ def has_duplicates(self) -> bool: """ return not self.is_unique - @final - def is_boolean(self) -> bool: - """ - Check if the Index only consists of booleans. - - .. deprecated:: 2.0.0 - Use `pandas.api.types.is_bool_dtype` instead. - - Returns - ------- - bool - Whether or not the Index only consists of booleans. - - See Also - -------- - is_integer : Check if the Index only consists of integers (deprecated). - is_floating : Check if the Index is a floating type (deprecated). - is_numeric : Check if the Index only consists of numeric data (deprecated). - is_object : Check if the Index is of the object dtype (deprecated). - is_categorical : Check if the Index holds categorical data. - is_interval : Check if the Index holds Interval objects (deprecated). - - Examples - -------- - >>> idx = pd.Index([True, False, True]) - >>> idx.is_boolean() # doctest: +SKIP - True - - >>> idx = pd.Index(["True", "False", "True"]) - >>> idx.is_boolean() # doctest: +SKIP - False - - >>> idx = pd.Index([True, False, "True"]) - >>> idx.is_boolean() # doctest: +SKIP - False - """ - warnings.warn( - f"{type(self).__name__}.is_boolean is deprecated. " - "Use pandas.api.types.is_bool_type instead.", - FutureWarning, - stacklevel=find_stack_level(), - ) - return self.inferred_type in ["boolean"] - - @final - def is_integer(self) -> bool: - """ - Check if the Index only consists of integers. - - .. deprecated:: 2.0.0 - Use `pandas.api.types.is_integer_dtype` instead. - - Returns - ------- - bool - Whether or not the Index only consists of integers. - - See Also - -------- - is_boolean : Check if the Index only consists of booleans (deprecated). - is_floating : Check if the Index is a floating type (deprecated). - is_numeric : Check if the Index only consists of numeric data (deprecated). - is_object : Check if the Index is of the object dtype. (deprecated). - is_categorical : Check if the Index holds categorical data (deprecated). - is_interval : Check if the Index holds Interval objects (deprecated). - - Examples - -------- - >>> idx = pd.Index([1, 2, 3, 4]) - >>> idx.is_integer() # doctest: +SKIP - True - - >>> idx = pd.Index([1.0, 2.0, 3.0, 4.0]) - >>> idx.is_integer() # doctest: +SKIP - False - - >>> idx = pd.Index(["Apple", "Mango", "Watermelon"]) - >>> idx.is_integer() # doctest: +SKIP - False - """ - warnings.warn( - f"{type(self).__name__}.is_integer is deprecated. " - "Use pandas.api.types.is_integer_dtype instead.", - FutureWarning, - stacklevel=find_stack_level(), - ) - return self.inferred_type in ["integer"] - - @final - def is_floating(self) -> bool: - """ - Check if the Index is a floating type. - - .. deprecated:: 2.0.0 - Use `pandas.api.types.is_float_dtype` instead - - The Index may consist of only floats, NaNs, or a mix of floats, - integers, or NaNs. - - Returns - ------- - bool - Whether or not the Index only consists of only consists of floats, NaNs, or - a mix of floats, integers, or NaNs. - - See Also - -------- - is_boolean : Check if the Index only consists of booleans (deprecated). - is_integer : Check if the Index only consists of integers (deprecated). - is_numeric : Check if the Index only consists of numeric data (deprecated). - is_object : Check if the Index is of the object dtype. (deprecated). - is_categorical : Check if the Index holds categorical data (deprecated). - is_interval : Check if the Index holds Interval objects (deprecated). - - Examples - -------- - >>> idx = pd.Index([1.0, 2.0, 3.0, 4.0]) - >>> idx.is_floating() # doctest: +SKIP - True - - >>> idx = pd.Index([1.0, 2.0, np.nan, 4.0]) - >>> idx.is_floating() # doctest: +SKIP - True - - >>> idx = pd.Index([1, 2, 3, 4, np.nan]) - >>> idx.is_floating() # doctest: +SKIP - True - - >>> idx = pd.Index([1, 2, 3, 4]) - >>> idx.is_floating() # doctest: +SKIP - False - """ - warnings.warn( - f"{type(self).__name__}.is_floating is deprecated. " - "Use pandas.api.types.is_float_dtype instead.", - FutureWarning, - stacklevel=find_stack_level(), - ) - return self.inferred_type in ["floating", "mixed-integer-float", "integer-na"] - - @final - def is_numeric(self) -> bool: - """ - Check if the Index only consists of numeric data. - - .. deprecated:: 2.0.0 - Use `pandas.api.types.is_numeric_dtype` instead. - - Returns - ------- - bool - Whether or not the Index only consists of numeric data. - - See Also - -------- - is_boolean : Check if the Index only consists of booleans (deprecated). - is_integer : Check if the Index only consists of integers (deprecated). - is_floating : Check if the Index is a floating type (deprecated). - is_object : Check if the Index is of the object dtype. (deprecated). - is_categorical : Check if the Index holds categorical data (deprecated). - is_interval : Check if the Index holds Interval objects (deprecated). - - Examples - -------- - >>> idx = pd.Index([1.0, 2.0, 3.0, 4.0]) - >>> idx.is_numeric() # doctest: +SKIP - True - - >>> idx = pd.Index([1, 2, 3, 4.0]) - >>> idx.is_numeric() # doctest: +SKIP - True - - >>> idx = pd.Index([1, 2, 3, 4]) - >>> idx.is_numeric() # doctest: +SKIP - True - - >>> idx = pd.Index([1, 2, 3, 4.0, np.nan]) - >>> idx.is_numeric() # doctest: +SKIP - True - - >>> idx = pd.Index([1, 2, 3, 4.0, np.nan, "Apple"]) - >>> idx.is_numeric() # doctest: +SKIP - False - """ - warnings.warn( - f"{type(self).__name__}.is_numeric is deprecated. " - "Use pandas.api.types.is_any_real_numeric_dtype instead", - FutureWarning, - stacklevel=find_stack_level(), - ) - return self.inferred_type in ["integer", "floating"] - - @final - def is_object(self) -> bool: - """ - Check if the Index is of the object dtype. - - .. deprecated:: 2.0.0 - Use `pandas.api.types.is_object_dtype` instead. - - Returns - ------- - bool - Whether or not the Index is of the object dtype. - - See Also - -------- - is_boolean : Check if the Index only consists of booleans (deprecated). - is_integer : Check if the Index only consists of integers (deprecated). - is_floating : Check if the Index is a floating type (deprecated). - is_numeric : Check if the Index only consists of numeric data (deprecated). - is_categorical : Check if the Index holds categorical data (deprecated). - is_interval : Check if the Index holds Interval objects (deprecated). - - Examples - -------- - >>> idx = pd.Index(["Apple", "Mango", "Watermelon"]) - >>> idx.is_object() # doctest: +SKIP - True - - >>> idx = pd.Index(["Apple", "Mango", 2.0]) - >>> idx.is_object() # doctest: +SKIP - True - - >>> idx = pd.Index(["Watermelon", "Orange", "Apple", - ... "Watermelon"]).astype("category") - >>> idx.is_object() # doctest: +SKIP - False - - >>> idx = pd.Index([1.0, 2.0, 3.0, 4.0]) - >>> idx.is_object() # doctest: +SKIP - False - """ - warnings.warn( - f"{type(self).__name__}.is_object is deprecated." - "Use pandas.api.types.is_object_dtype instead", - FutureWarning, - stacklevel=find_stack_level(), - ) - return is_object_dtype(self.dtype) - - @final - def is_categorical(self) -> bool: - """ - Check if the Index holds categorical data. - - .. deprecated:: 2.0.0 - Use `isinstance(index.dtype, pd.CategoricalDtype)` instead. - - Returns - ------- - bool - True if the Index is categorical. - - See Also - -------- - CategoricalIndex : Index for categorical data. - is_boolean : Check if the Index only consists of booleans (deprecated). - is_integer : Check if the Index only consists of integers (deprecated). - is_floating : Check if the Index is a floating type (deprecated). - is_numeric : Check if the Index only consists of numeric data (deprecated). - is_object : Check if the Index is of the object dtype. (deprecated). - is_interval : Check if the Index holds Interval objects (deprecated). - - Examples - -------- - >>> idx = pd.Index(["Watermelon", "Orange", "Apple", - ... "Watermelon"]).astype("category") - >>> idx.is_categorical() # doctest: +SKIP - True - - >>> idx = pd.Index([1, 3, 5, 7]) - >>> idx.is_categorical() # doctest: +SKIP - False - - >>> s = pd.Series(["Peter", "Victor", "Elisabeth", "Mar"]) - >>> s - 0 Peter - 1 Victor - 2 Elisabeth - 3 Mar - dtype: object - >>> s.index.is_categorical() # doctest: +SKIP - False - """ - warnings.warn( - f"{type(self).__name__}.is_categorical is deprecated." - "Use pandas.api.types.is_categorical_dtype instead", - FutureWarning, - stacklevel=find_stack_level(), - ) - - return self.inferred_type in ["categorical"] - - @final - def is_interval(self) -> bool: - """ - Check if the Index holds Interval objects. - - .. deprecated:: 2.0.0 - Use `isinstance(index.dtype, pd.IntervalDtype)` instead. - - Returns - ------- - bool - Whether or not the Index holds Interval objects. - - See Also - -------- - IntervalIndex : Index for Interval objects. - is_boolean : Check if the Index only consists of booleans (deprecated). - is_integer : Check if the Index only consists of integers (deprecated). - is_floating : Check if the Index is a floating type (deprecated). - is_numeric : Check if the Index only consists of numeric data (deprecated). - is_object : Check if the Index is of the object dtype. (deprecated). - is_categorical : Check if the Index holds categorical data (deprecated). - - Examples - -------- - >>> idx = pd.Index([pd.Interval(left=0, right=5), - ... pd.Interval(left=5, right=10)]) - >>> idx.is_interval() # doctest: +SKIP - True - - >>> idx = pd.Index([1, 3, 5, 7]) - >>> idx.is_interval() # doctest: +SKIP - False - """ - warnings.warn( - f"{type(self).__name__}.is_interval is deprecated." - "Use pandas.api.types.is_interval_dtype instead", - FutureWarning, - stacklevel=find_stack_level(), - ) - return self.inferred_type in ["interval"] - - @final - def _holds_integer(self) -> bool: - """ - Whether the type is an integer type. - """ - return self.inferred_type in ["integer", "mixed-integer"] - - @final - def holds_integer(self) -> bool: - """ - Whether the type is an integer type. - - .. deprecated:: 2.0.0 - Use `pandas.api.types.infer_dtype` instead - """ - warnings.warn( - f"{type(self).__name__}.holds_integer is deprecated. " - "Use pandas.api.types.infer_dtype instead.", - FutureWarning, - stacklevel=find_stack_level(), - ) - return self._holds_integer() - @cache_readonly def inferred_type(self) -> str_t: """ diff --git a/pandas/plotting/_core.py b/pandas/plotting/_core.py index e8675a6d74746..a755806aa45c6 100644 --- a/pandas/plotting/_core.py +++ b/pandas/plotting/_core.py @@ -39,11 +39,16 @@ from pandas import ( DataFrame, + Index, Series, ) from pandas.core.groupby.generic import DataFrameGroupBy +def holds_integer(column: Index) -> bool: + return column.inferred_type in {"integer", "mixed-integer"} + + def hist_series( self: Series, by=None, @@ -982,7 +987,7 @@ def __call__(self, *args, **kwargs): f"{kind} requires either y column or 'subplots=True'" ) if y is not None: - if is_integer(y) and not data.columns._holds_integer(): + if is_integer(y) and not holds_integer(self.data.columns): y = data.columns[y] # converted to series actually. copy to not modify data = data[y].copy() @@ -990,7 +995,7 @@ def __call__(self, *args, **kwargs): elif isinstance(data, ABCDataFrame): data_cols = data.columns if x is not None: - if is_integer(x) and not data.columns._holds_integer(): + if is_integer(x) and not holds_integer(self.data.columns): x = data_cols[x] elif not isinstance(data[x], ABCSeries): raise ValueError("x must be a label or position") @@ -999,7 +1004,7 @@ def __call__(self, *args, **kwargs): # check if we have y as int or list of ints int_ylist = is_list_like(y) and all(is_integer(c) for c in y) int_y_arg = is_integer(y) or int_ylist - if int_y_arg and not data.columns._holds_integer(): + if int_y_arg and not holds_integer(self.data.columns): y = data_cols[y] label_kw = kwargs["label"] if "label" in kwargs else False diff --git a/pandas/plotting/_matplotlib/core.py b/pandas/plotting/_matplotlib/core.py index 6fa75ba5fb12d..30ecc83b2f222 100644 --- a/pandas/plotting/_matplotlib/core.py +++ b/pandas/plotting/_matplotlib/core.py @@ -93,7 +93,14 @@ npt, ) - from pandas import Series + from pandas import ( + Index, + Series, + ) + + +def holds_integer(column: Index) -> bool: + return column.inferred_type in {"integer", "mixed-integer"} def _color_in_style(style: str) -> bool: @@ -1246,9 +1253,9 @@ def __init__(self, data, x, y, **kwargs) -> None: MPLPlot.__init__(self, data, **kwargs) if x is None or y is None: raise ValueError(self._kind + " requires an x and y column") - if is_integer(x) and not self.data.columns._holds_integer(): + if is_integer(x) and not holds_integer(self.data.columns): x = self.data.columns[x] - if is_integer(y) and not self.data.columns._holds_integer(): + if is_integer(y) and not holds_integer(self.data.columns): y = self.data.columns[y] self.x = x @@ -1318,7 +1325,7 @@ def __init__( self.norm = norm super().__init__(data, x, y, **kwargs) - if is_integer(c) and not self.data.columns._holds_integer(): + if is_integer(c) and not holds_integer(self.data.columns): c = self.data.columns[c] self.c = c @@ -1434,7 +1441,7 @@ def _kind(self) -> Literal["hexbin"]: def __init__(self, data, x, y, C=None, *, colorbar: bool = True, **kwargs) -> None: super().__init__(data, x, y, **kwargs) - if is_integer(C) and not self.data.columns._holds_integer(): + if is_integer(C) and not holds_integer(self.data.columns): C = self.data.columns[C] self.C = C diff --git a/pandas/tests/indexes/test_old_base.py b/pandas/tests/indexes/test_old_base.py index 1787379b0faee..d944c204f33ec 100644 --- a/pandas/tests/indexes/test_old_base.py +++ b/pandas/tests/indexes/test_old_base.py @@ -876,61 +876,6 @@ def test_inv(self, simple_index, using_infer_string): with pytest.raises(err, match=msg): ~Series(idx) - def test_is_boolean_is_deprecated(self, simple_index): - # GH50042 - idx = simple_index - with tm.assert_produces_warning(FutureWarning): - idx.is_boolean() - - def test_is_floating_is_deprecated(self, simple_index): - # GH50042 - idx = simple_index - with tm.assert_produces_warning(FutureWarning): - idx.is_floating() - - def test_is_integer_is_deprecated(self, simple_index): - # GH50042 - idx = simple_index - with tm.assert_produces_warning(FutureWarning): - idx.is_integer() - - def test_holds_integer_deprecated(self, simple_index): - # GH50243 - idx = simple_index - msg = f"{type(idx).__name__}.holds_integer is deprecated. " - with tm.assert_produces_warning(FutureWarning, match=msg): - idx.holds_integer() - - def test_is_numeric_is_deprecated(self, simple_index): - # GH50042 - idx = simple_index - with tm.assert_produces_warning( - FutureWarning, - match=f"{type(idx).__name__}.is_numeric is deprecated. ", - ): - idx.is_numeric() - - def test_is_categorical_is_deprecated(self, simple_index): - # GH50042 - idx = simple_index - with tm.assert_produces_warning( - FutureWarning, - match=r"Use pandas\.api\.types\.is_categorical_dtype instead", - ): - idx.is_categorical() - - def test_is_interval_is_deprecated(self, simple_index): - # GH50042 - idx = simple_index - with tm.assert_produces_warning(FutureWarning): - idx.is_interval() - - def test_is_object_is_deprecated(self, simple_index): - # GH50042 - idx = simple_index - with tm.assert_produces_warning(FutureWarning): - idx.is_object() - class TestNumericBase: @pytest.fixture( From 7a18dcf46fe201cb8f22b07dd8aa81f8cfebfe20 Mon Sep 17 00:00:00 2001 From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com> Date: Sat, 3 Feb 2024 18:42:07 -0800 Subject: [PATCH 2/2] Remove is_floating usage --- pandas/io/formats/format.py | 36 +++++++++--------------------------- pandas/plotting/_core.py | 6 +++--- 2 files changed, 12 insertions(+), 30 deletions(-) diff --git a/pandas/io/formats/format.py b/pandas/io/formats/format.py index 65124f97459cd..3c86b8f224fc6 100644 --- a/pandas/io/formats/format.py +++ b/pandas/io/formats/format.py @@ -780,38 +780,20 @@ def _get_formatted_column_labels(self, frame: DataFrame) -> list[list[str]]: if isinstance(columns, MultiIndex): fmt_columns = columns._format_multi(sparsify=False, include_names=False) - fmt_columns = list(zip(*fmt_columns)) - dtypes = self.frame.dtypes._values - - # if we have a Float level, they don't use leading space at all - restrict_formatting = any(level.is_floating for level in columns.levels) - need_leadsp = dict(zip(fmt_columns, map(is_numeric_dtype, dtypes))) - - def space_format(x, y): - if ( - y not in self.formatters - and need_leadsp[x] - and not restrict_formatting - ): - return " " + y - return y - - str_columns_tuple = list( - zip(*([space_format(x, y) for y in x] for x in fmt_columns)) - ) - if self.sparsify and len(str_columns_tuple): - str_columns_tuple = sparsify_labels(str_columns_tuple) + if self.sparsify and len(fmt_columns): + fmt_columns = sparsify_labels(fmt_columns) - str_columns = [list(x) for x in zip(*str_columns_tuple)] + str_columns = [list(x) for x in zip(*fmt_columns)] else: fmt_columns = columns._format_flat(include_name=False) - dtypes = self.frame.dtypes - need_leadsp = dict(zip(fmt_columns, map(is_numeric_dtype, dtypes))) str_columns = [ - [" " + x if not self._get_formatter(i) and need_leadsp[x] else x] - for i, x in enumerate(fmt_columns) + [ + " " + x + if not self._get_formatter(i) and is_numeric_dtype(dtype) + else x + ] + for i, (x, dtype) in enumerate(zip(fmt_columns, self.frame.dtypes)) ] - # self.str_columns = str_columns return str_columns def _get_formatted_index(self, frame: DataFrame) -> list[str]: diff --git a/pandas/plotting/_core.py b/pandas/plotting/_core.py index a755806aa45c6..f5c6cd1f76724 100644 --- a/pandas/plotting/_core.py +++ b/pandas/plotting/_core.py @@ -987,7 +987,7 @@ def __call__(self, *args, **kwargs): f"{kind} requires either y column or 'subplots=True'" ) if y is not None: - if is_integer(y) and not holds_integer(self.data.columns): + if is_integer(y) and not holds_integer(data.columns): y = data.columns[y] # converted to series actually. copy to not modify data = data[y].copy() @@ -995,7 +995,7 @@ def __call__(self, *args, **kwargs): elif isinstance(data, ABCDataFrame): data_cols = data.columns if x is not None: - if is_integer(x) and not holds_integer(self.data.columns): + if is_integer(x) and not holds_integer(data.columns): x = data_cols[x] elif not isinstance(data[x], ABCSeries): raise ValueError("x must be a label or position") @@ -1004,7 +1004,7 @@ def __call__(self, *args, **kwargs): # check if we have y as int or list of ints int_ylist = is_list_like(y) and all(is_integer(c) for c in y) int_y_arg = is_integer(y) or int_ylist - if int_y_arg and not holds_integer(self.data.columns): + if int_y_arg and not holds_integer(data.columns): y = data_cols[y] label_kw = kwargs["label"] if "label" in kwargs else False