DEPR: DataFrameGroupBy.corrwith (#58732)

doc/source/whatsnew/v3.0.0.rst

@@ -263,6 +263,7 @@ starting with 3.0, so it can be safely removed from your code.
 Other Deprecations
 ^^^^^^^^^^^^^^^^^^
 
+- Deprecated :meth:`.DataFrameGroupby.corrwith` (:issue:`57158`)
 - Deprecated :meth:`Timestamp.utcfromtimestamp`, use ``Timestamp.fromtimestamp(ts, "UTC")`` instead (:issue:`56680`)
 - Deprecated :meth:`Timestamp.utcnow`, use ``Timestamp.now("UTC")`` instead (:issue:`56680`)
 - Deprecated allowing non-keyword arguments in :meth:`DataFrame.all`, :meth:`DataFrame.min`, :meth:`DataFrame.max`, :meth:`DataFrame.sum`, :meth:`DataFrame.prod`, :meth:`DataFrame.mean`, :meth:`DataFrame.median`, :meth:`DataFrame.sem`, :meth:`DataFrame.var`, :meth:`DataFrame.std`, :meth:`DataFrame.skew`, :meth:`DataFrame.kurt`, :meth:`Series.all`,  :meth:`Series.min`, :meth:`Series.max`, :meth:`Series.sum`, :meth:`Series.prod`, :meth:`Series.mean`, :meth:`Series.median`, :meth:`Series.sem`, :meth:`Series.var`, :meth:`Series.std`, :meth:`Series.skew`, and :meth:`Series.kurt`. (:issue:`57087`)

pandas/conftest.py

@@ -150,6 +150,7 @@ def pytest_collection_modifyitems(items, config) -> None:
         ("is_categorical_dtype", "is_categorical_dtype is deprecated"),
         ("is_sparse", "is_sparse is deprecated"),
         ("DataFrameGroupBy.fillna", "DataFrameGroupBy.fillna is deprecated"),
+        ("DataFrameGroupBy.corrwith", "DataFrameGroupBy.corrwith is deprecated"),
         ("NDFrame.replace", "Series.replace without 'value'"),
         ("NDFrame.clip", "Downcasting behavior in Series and DataFrame methods"),
         ("Series.idxmin", "The behavior of Series.idxmin"),

pandas/core/groupby/generic.py

@@ -21,6 +21,7 @@
     Union,
     cast,
 )
+import warnings
 
 import numpy as np
 
@@ -32,6 +33,7 @@
     Substitution,
     doc,
 )
+from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.common import (
     ensure_int64,
@@ -2726,6 +2728,8 @@ def corrwith(
         """
         Compute pairwise correlation.
 
+        .. deprecated:: 3.0.0
+
         Pairwise correlation is computed between rows or columns of
         DataFrame with rows or columns of Series or DataFrame. DataFrames
         are first aligned along both axes before computing the
@@ -2785,6 +2789,11 @@ def corrwith(
         2    0.755929  NaN
         3    0.576557  NaN
         """
+        warnings.warn(
+            "DataFrameGroupBy.corrwith is deprecated",
+            FutureWarning,
+            stacklevel=find_stack_level(),
+        )
         result = self._op_via_apply(
             "corrwith",
             other=other,

pandas/tests/groupby/test_all_methods.py

@@ -25,9 +25,12 @@ def test_multiindex_group_all_columns_when_empty(groupby_func):
     gb = df.groupby(["a", "b", "c"], group_keys=False)
     method = getattr(gb, groupby_func)
     args = get_groupby_method_args(groupby_func, df)
-
-    warn = FutureWarning if groupby_func == "fillna" else None
-    warn_msg = "DataFrameGroupBy.fillna is deprecated"
+    if groupby_func == "corrwith":
+        warn = FutureWarning
+        warn_msg = "DataFrameGroupBy.corrwith is deprecated"
+    else:
+        warn = None
+        warn_msg = ""
     with tm.assert_produces_warning(warn, match=warn_msg):
         result = method(*args).index
     expected = df.index
@@ -42,18 +45,12 @@ def test_duplicate_columns(request, groupby_func, as_index):
     df = DataFrame([[1, 3, 6], [1, 4, 7], [2, 5, 8]], columns=list("abb"))
     args = get_groupby_method_args(groupby_func, df)
     gb = df.groupby("a", as_index=as_index)
-    warn = FutureWarning if groupby_func == "fillna" else None
-    warn_msg = "DataFrameGroupBy.fillna is deprecated"
-    with tm.assert_produces_warning(warn, match=warn_msg):
-        result = getattr(gb, groupby_func)(*args)
+    result = getattr(gb, groupby_func)(*args)
 
     expected_df = df.set_axis(["a", "b", "c"], axis=1)
     expected_args = get_groupby_method_args(groupby_func, expected_df)
     expected_gb = expected_df.groupby("a", as_index=as_index)
-    warn = FutureWarning if groupby_func == "fillna" else None
-    warn_msg = "DataFrameGroupBy.fillna is deprecated"
-    with tm.assert_produces_warning(warn, match=warn_msg):
-        expected = getattr(expected_gb, groupby_func)(*expected_args)
+    expected = getattr(expected_gb, groupby_func)(*expected_args)
     if groupby_func not in ("size", "ngroup", "cumcount"):
         expected = expected.rename(columns={"c": "b"})
     tm.assert_equal(result, expected)
@@ -74,8 +71,12 @@ def test_dup_labels_output_shape(groupby_func, idx):
     grp_by = df.groupby([0])
 
     args = get_groupby_method_args(groupby_func, df)
-    warn = FutureWarning if groupby_func == "fillna" else None
-    warn_msg = "DataFrameGroupBy.fillna is deprecated"
+    if groupby_func == "corrwith":
+        warn = FutureWarning
+        warn_msg = "DataFrameGroupBy.corrwith is deprecated"
+    else:
+        warn = None
+        warn_msg = ""
     with tm.assert_produces_warning(warn, match=warn_msg):
         result = getattr(grp_by, groupby_func)(*args)
 

pandas/tests/groupby/test_apply.py

@@ -1197,7 +1197,14 @@ def test_apply_is_unchanged_when_other_methods_are_called_first(reduction_func):
     # Check output when another method is called before .apply()
     grp = df.groupby(by="a")
     args = get_groupby_method_args(reduction_func, df)
-    _ = getattr(grp, reduction_func)(*args)
+    if reduction_func == "corrwith":
+        warn = FutureWarning
+        msg = "DataFrameGroupBy.corrwith is deprecated"
+    else:
+        warn = None
+        msg = ""
+    with tm.assert_produces_warning(warn, match=msg):
+        _ = getattr(grp, reduction_func)(*args)
     result = grp.apply(np.sum, axis=0, include_groups=False)
     tm.assert_frame_equal(result, expected)
 

pandas/tests/groupby/test_categorical.py

@@ -1473,7 +1473,14 @@ def test_dataframe_groupby_on_2_categoricals_when_observed_is_true(reduction_fun
     df_grp = df.groupby(["cat_1", "cat_2"], observed=True)
 
     args = get_groupby_method_args(reduction_func, df)
-    res = getattr(df_grp, reduction_func)(*args)
+    if reduction_func == "corrwith":
+        warn = FutureWarning
+        warn_msg = "DataFrameGroupBy.corrwith is deprecated"
+    else:
+        warn = None
+        warn_msg = ""
+    with tm.assert_produces_warning(warn, match=warn_msg):
+        res = getattr(df_grp, reduction_func)(*args)
 
     for cat in unobserved_cats:
         assert cat not in res.index
@@ -1512,7 +1519,14 @@ def test_dataframe_groupby_on_2_categoricals_when_observed_is_false(
             getattr(df_grp, reduction_func)(*args)
         return
 
-    res = getattr(df_grp, reduction_func)(*args)
+    if reduction_func == "corrwith":
+        warn = FutureWarning
+        warn_msg = "DataFrameGroupBy.corrwith is deprecated"
+    else:
+        warn = None
+        warn_msg = ""
+    with tm.assert_produces_warning(warn, match=warn_msg):
+        res = getattr(df_grp, reduction_func)(*args)
 
     expected = _results_for_groupbys_with_missing_categories[reduction_func]
 
@@ -1904,8 +1918,14 @@ def test_category_order_reducer(
         ):
             getattr(gb, reduction_func)(*args)
         return
-
-    op_result = getattr(gb, reduction_func)(*args)
+    if reduction_func == "corrwith":
+        warn = FutureWarning
+        warn_msg = "DataFrameGroupBy.corrwith is deprecated"
+    else:
+        warn = None
+        warn_msg = ""
+    with tm.assert_produces_warning(warn, match=warn_msg):
+        op_result = getattr(gb, reduction_func)(*args)
     if as_index:
         result = op_result.index.get_level_values("a").categories
     else:

pandas/tests/groupby/test_groupby_dropna.py

@@ -543,7 +543,14 @@ def test_categorical_reducers(reduction_func, observed, sort, as_index, index_ki
         return
 
     gb_filled = df_filled.groupby(keys, observed=observed, sort=sort, as_index=True)
-    expected = getattr(gb_filled, reduction_func)(*args_filled).reset_index()
+    if reduction_func == "corrwith":
+        warn = FutureWarning
+        msg = "DataFrameGroupBy.corrwith is deprecated"
+    else:
+        warn = None
+        msg = ""
+    with tm.assert_produces_warning(warn, match=msg):
+        expected = getattr(gb_filled, reduction_func)(*args_filled).reset_index()
     expected["x"] = expected["x"].cat.remove_categories([4])
     if index_kind == "multi":
         expected["x2"] = expected["x2"].cat.remove_categories([4])
@@ -567,7 +574,14 @@ def test_categorical_reducers(reduction_func, observed, sort, as_index, index_ki
         if as_index:
             expected = expected["size"].rename(None)
 
-    result = getattr(gb_keepna, reduction_func)(*args)
+    if reduction_func == "corrwith":
+        warn = FutureWarning
+        msg = "DataFrameGroupBy.corrwith is deprecated"
+    else:
+        warn = None
+        msg = ""
+    with tm.assert_produces_warning(warn, match=msg):
+        result = getattr(gb_keepna, reduction_func)(*args)
 
     # size will return a Series, others are DataFrame
     tm.assert_equal(result, expected)

pandas/tests/groupby/test_numeric_only.py

@@ -256,7 +256,14 @@ def test_numeric_only(kernel, has_arg, numeric_only, keys):
     method = getattr(gb, kernel)
     if has_arg and numeric_only is True:
         # Cases where b does not appear in the result
-        result = method(*args, **kwargs)
+        if kernel == "corrwith":
+            warn = FutureWarning
+            msg = "DataFrameGroupBy.corrwith is deprecated"
+        else:
+            warn = None
+            msg = ""
+        with tm.assert_produces_warning(warn, match=msg):
+            result = method(*args, **kwargs)
         assert "b" not in result.columns
     elif (
         # kernels that work on any dtype and have numeric_only arg
@@ -296,7 +303,14 @@ def test_numeric_only(kernel, has_arg, numeric_only, keys):
         elif kernel == "idxmax":
             msg = "'>' not supported between instances of 'type' and 'type'"
         with pytest.raises(exception, match=msg):
-            method(*args, **kwargs)
+            if kernel == "corrwith":
+                warn = FutureWarning
+                msg = "DataFrameGroupBy.corrwith is deprecated"
+            else:
+                warn = None
+                msg = ""
+            with tm.assert_produces_warning(warn, match=msg):
+                method(*args, **kwargs)
     elif not has_arg and numeric_only is not lib.no_default:
         with pytest.raises(
             TypeError, match="got an unexpected keyword argument 'numeric_only'"

pandas/tests/groupby/test_raises.py

@@ -183,6 +183,8 @@ def test_groupby_raises_string(
     if groupby_func == "fillna":
         kind = "Series" if groupby_series else "DataFrame"
         warn_msg = f"{kind}GroupBy.fillna is deprecated"
+    elif groupby_func == "corrwith":
+        warn_msg = "DataFrameGroupBy.corrwith is deprecated"
     else:
         warn_msg = ""
     _call_and_check(klass, msg, how, gb, groupby_func, args, warn_msg)
@@ -288,6 +290,8 @@ def test_groupby_raises_datetime(
     if groupby_func == "fillna":
         kind = "Series" if groupby_series else "DataFrame"
         warn_msg = f"{kind}GroupBy.fillna is deprecated"
+    elif groupby_func == "corrwith":
+        warn_msg = "DataFrameGroupBy.corrwith is deprecated"
     else:
         warn_msg = ""
     _call_and_check(klass, msg, how, gb, groupby_func, args, warn_msg=warn_msg)
@@ -485,6 +489,8 @@ def test_groupby_raises_category(
     if groupby_func == "fillna":
         kind = "Series" if groupby_series else "DataFrame"
         warn_msg = f"{kind}GroupBy.fillna is deprecated"
+    elif groupby_func == "corrwith":
+        warn_msg = "DataFrameGroupBy.corrwith is deprecated"
     else:
         warn_msg = ""
     _call_and_check(klass, msg, how, gb, groupby_func, args, warn_msg)
@@ -658,6 +664,8 @@ def test_groupby_raises_category_on_category(
     if groupby_func == "fillna":
         kind = "Series" if groupby_series else "DataFrame"
         warn_msg = f"{kind}GroupBy.fillna is deprecated"
+    elif groupby_func == "corrwith":
+        warn_msg = "DataFrameGroupBy.corrwith is deprecated"
     else:
         warn_msg = ""
     _call_and_check(klass, msg, how, gb, groupby_func, args, warn_msg)

pandas/tests/groupby/transform/test_transform.py

@@ -1104,7 +1104,14 @@ def test_transform_agg_by_name(request, reduction_func, frame_or_series):
         return
 
     args = get_groupby_method_args(reduction_func, obj)
-    result = g.transform(func, *args)
+    if func == "corrwith":
+        warn = FutureWarning
+        msg = "DataFrameGroupBy.corrwith is deprecated"
+    else:
+        warn = None
+        msg = ""
+    with tm.assert_produces_warning(warn, match=msg):
+        result = g.transform(func, *args)
 
     # this is the *definition* of a transformation
     tm.assert_index_equal(result.index, obj.index)
@@ -1468,8 +1475,12 @@ def test_as_index_no_change(keys, df, groupby_func):
     args = get_groupby_method_args(groupby_func, df)
     gb_as_index_true = df.groupby(keys, as_index=True)
     gb_as_index_false = df.groupby(keys, as_index=False)
-    warn = FutureWarning if groupby_func == "fillna" else None
-    msg = "DataFrameGroupBy.fillna is deprecated"
+    if groupby_func == "corrwith":
+        warn = FutureWarning
+        msg = "DataFrameGroupBy.corrwith is deprecated"
+    else:
+        warn = None
+        msg = ""
     with tm.assert_produces_warning(warn, match=msg):
         result = gb_as_index_true.transform(groupby_func, *args)
     with tm.assert_produces_warning(warn, match=msg):