DEPR: Replacing builtin and NumPy funcs in agg/apply/transform (#53974)

* DEPR: Replacing builtin and NumPy funcs in agg/apply/transform

* mypy fixup

Author: rhshadrach

doc/source/getting_started/comparison/comparison_with_r.rst

@@ -246,7 +246,7 @@ In pandas we may use :meth:`~pandas.pivot_table` method to handle this:
        }
    )
 
-   baseball.pivot_table(values="batting avg", columns="team", aggfunc=np.max)
+   baseball.pivot_table(values="batting avg", columns="team", aggfunc="max")
 
 For more details and examples see :ref:`the reshaping documentation
 <reshaping.pivot>`.
@@ -359,7 +359,7 @@ In pandas the equivalent expression, using the
    )
 
    grouped = df.groupby(["month", "week"])
-   grouped["x"].agg([np.mean, np.std])
+   grouped["x"].agg(["mean", "std"])
 
 
 For more details and examples see :ref:`the groupby documentation
@@ -482,7 +482,7 @@ In Python the best way is to make use of :meth:`~pandas.pivot_table`:
        values="value",
        index=["variable", "week"],
        columns=["month"],
-       aggfunc=np.mean,
+       aggfunc="mean",
    )
 
 Similarly for ``dcast`` which uses a data.frame called ``df`` in R to

doc/source/getting_started/comparison/comparison_with_sql.rst

@@ -198,7 +198,7 @@ to your grouped DataFrame, indicating which functions to apply to specific colum
 
 .. ipython:: python
 
-    tips.groupby("day").agg({"tip": np.mean, "day": np.size})
+    tips.groupby("day").agg({"tip": "mean", "day": "size"})
 
 Grouping by more than one column is done by passing a list of columns to the
 :meth:`~pandas.DataFrame.groupby` method.
@@ -222,7 +222,7 @@ Grouping by more than one column is done by passing a list of columns to the
 
 .. ipython:: python
 
-    tips.groupby(["smoker", "day"]).agg({"tip": [np.size, np.mean]})
+    tips.groupby(["smoker", "day"]).agg({"tip": ["size", "mean"]})
 
 .. _compare_with_sql.join:
 

doc/source/user_guide/basics.rst

@@ -881,8 +881,8 @@ statistics methods, takes an optional ``axis`` argument:
 
 .. ipython:: python
 
-   df.apply(np.mean)
-   df.apply(np.mean, axis=1)
+   df.apply(lambda x: np.mean(x))
+   df.apply(lambda x: np.mean(x), axis=1)
    df.apply(lambda x: x.max() - x.min())
    df.apply(np.cumsum)
    df.apply(np.exp)
@@ -986,7 +986,7 @@ output:
 
 .. ipython:: python
 
-   tsdf.agg(np.sum)
+   tsdf.agg(lambda x: np.sum(x))
 
    tsdf.agg("sum")
 

doc/source/user_guide/cookbook.rst

@@ -530,7 +530,7 @@ Unlike agg, apply's callable is passed a sub-DataFrame which gives you access to
 
    code_groups = df.groupby("code")
 
-   agg_n_sort_order = code_groups[["data"]].transform(sum).sort_values(by="data")
+   agg_n_sort_order = code_groups[["data"]].transform("sum").sort_values(by="data")
 
    sorted_df = df.loc[agg_n_sort_order.index]
 
@@ -549,7 +549,7 @@ Unlike agg, apply's callable is passed a sub-DataFrame which gives you access to
            return x.iloc[1] * 1.234
        return pd.NaT
 
-   mhc = {"Mean": np.mean, "Max": np.max, "Custom": MyCust}
+   mhc = {"Mean": "mean", "Max": "max", "Custom": MyCust}
    ts.resample("5min").apply(mhc)
    ts
 
@@ -685,7 +685,7 @@ The :ref:`Pivot <reshaping.pivot>` docs.
        values=["Sales"],
        index=["Province"],
        columns=["City"],
-       aggfunc=np.sum,
+       aggfunc="sum",
        margins=True,
    )
    table.stack("City")

doc/source/user_guide/reshaping.rst

@@ -402,12 +402,12 @@ We can produce pivot tables from this data very easily:
 .. ipython:: python
 
    pd.pivot_table(df, values="D", index=["A", "B"], columns=["C"])
-   pd.pivot_table(df, values="D", index=["B"], columns=["A", "C"], aggfunc=np.sum)
+   pd.pivot_table(df, values="D", index=["B"], columns=["A", "C"], aggfunc="sum")
    pd.pivot_table(
        df, values=["D", "E"],
        index=["B"],
        columns=["A", "C"],
-       aggfunc=np.sum,
+       aggfunc="sum",
    )
 
 The result object is a :class:`DataFrame` having potentially hierarchical indexes on the
@@ -451,7 +451,7 @@ rows and columns:
        columns="C",
        values=["D", "E"],
        margins=True,
-       aggfunc=np.std
+       aggfunc="std"
    )
    table
 
@@ -552,7 +552,7 @@ each group defined by the first two :class:`Series`:
 
 .. ipython:: python
 
-   pd.crosstab(df["A"], df["B"], values=df["C"], aggfunc=np.sum)
+   pd.crosstab(df["A"], df["B"], values=df["C"], aggfunc="sum")
 
 Adding margins
 ~~~~~~~~~~~~~~
@@ -562,7 +562,7 @@ Finally, one can also add margins or normalize this output.
 .. ipython:: python
 
    pd.crosstab(
-       df["A"], df["B"], values=df["C"], aggfunc=np.sum, normalize=True, margins=True
+       df["A"], df["B"], values=df["C"], aggfunc="sum", normalize=True, margins=True
    )
 
 .. _reshaping.tile:

doc/source/user_guide/timeseries.rst

@@ -1801,22 +1801,22 @@ You can pass a list or dict of functions to do aggregation with, outputting a ``
 
 .. ipython:: python
 
-   r["A"].agg([np.sum, np.mean, np.std])
+   r["A"].agg(["sum", "mean", "std"])
 
 On a resampled ``DataFrame``, you can pass a list of functions to apply to each
 column, which produces an aggregated result with a hierarchical index:
 
 .. ipython:: python
 
-   r.agg([np.sum, np.mean])
+   r.agg(["sum", "mean"])
 
 By passing a dict to ``aggregate`` you can apply a different aggregation to the
 columns of a ``DataFrame``:
 
 .. ipython:: python
    :okexcept:
 
-   r.agg({"A": np.sum, "B": lambda x: np.std(x, ddof=1)})
+   r.agg({"A": "sum", "B": lambda x: np.std(x, ddof=1)})
 
 The function names can also be strings. In order for a string to be valid it
 must be implemented on the resampled object:

doc/source/user_guide/window.rst

@@ -140,7 +140,7 @@ of multiple aggregations applied to a window.
 .. ipython:: python
 
    df = pd.DataFrame({"A": range(5), "B": range(10, 15)})
-   df.expanding().agg([np.sum, np.mean, np.std])
+   df.expanding().agg(["sum", "mean", "std"])
 
 
 .. _window.generic:

doc/source/whatsnew/v0.14.0.rst

@@ -846,7 +846,7 @@ Enhancements
      df.pivot_table(values='Quantity',
                     index=pd.Grouper(freq='M', key='Date'),
                     columns=pd.Grouper(freq='M', key='PayDay'),
-                    aggfunc=np.sum)
+                    aggfunc="sum")
 
 - Arrays of strings can be wrapped to a specified width (``str.wrap``) (:issue:`6999`)
 - Add :meth:`~Series.nsmallest` and :meth:`Series.nlargest` methods to Series, See :ref:`the docs <basics.nsorted>` (:issue:`3960`)

doc/source/whatsnew/v0.20.0.rst

@@ -984,7 +984,7 @@ Previous behavior:
      75%    3.750000
      max    4.000000
 
-   In [3]: df.groupby('A').agg([np.mean, np.std, np.min, np.max])
+   In [3]: df.groupby('A').agg(["mean", "std", "min", "max"])
    Out[3]:
         B
      mean       std amin amax
@@ -1000,7 +1000,7 @@ New behavior:
 
    df.groupby('A').describe()
 
-   df.groupby('A').agg([np.mean, np.std, np.min, np.max])
+   df.groupby('A').agg(["mean", "std", "min", "max"])
 
 .. _whatsnew_0200.api_breaking.rolling_pairwise:
 
@@ -1163,7 +1163,7 @@ Previous behavior:
 
 .. code-block:: ipython
 
-   In [2]: df.pivot_table('col1', index=['col3', 'col2'], aggfunc=np.sum)
+   In [2]: df.pivot_table('col1', index=['col3', 'col2'], aggfunc="sum")
    Out[2]:
    col3  col2
    1     C       3
@@ -1175,7 +1175,7 @@ New behavior:
 
 .. ipython:: python
 
-   df.pivot_table('col1', index=['col3', 'col2'], aggfunc=np.sum)
+   df.pivot_table('col1', index=['col3', 'col2'], aggfunc="sum")
 
 .. _whatsnew_0200.api:
 

doc/source/whatsnew/v0.25.0.rst

@@ -48,7 +48,7 @@ output columns when applying multiple aggregation functions to specific columns
    animals.groupby("kind").agg(
        min_height=pd.NamedAgg(column='height', aggfunc='min'),
        max_height=pd.NamedAgg(column='height', aggfunc='max'),
-       average_weight=pd.NamedAgg(column='weight', aggfunc=np.mean),
+       average_weight=pd.NamedAgg(column='weight', aggfunc="mean"),
    )
 
 Pass the desired columns names as the ``**kwargs`` to ``.agg``. The values of ``**kwargs``
@@ -61,7 +61,7 @@ what the arguments to the function are, but plain tuples are accepted as well.
    animals.groupby("kind").agg(
        min_height=('height', 'min'),
        max_height=('height', 'max'),
-       average_weight=('weight', np.mean),
+       average_weight=('weight', 'mean'),
    )
 
 Named aggregation is the recommended replacement for the deprecated "dict-of-dicts"