Merge branch 'master' of https://github.com/pandas-dev/pandas into fuse_kh

Author: jbrockmendel

pandas/_libs/tslibs/period.pyx

@@ -1709,14 +1709,14 @@ cdef class _Period:
 
     def asfreq(self, freq, how='E'):
         """
-        Convert Period to desired frequency, either at the start or end of the
-        interval.
+        Convert Period to desired frequency, at the start or end of the interval.
 
         Parameters
         ----------
-        freq : string
+        freq : str
+            The desired frequency.
         how : {'E', 'S', 'end', 'start'}, default 'end'
-            Start or end of the timespan
+            Start or end of the timespan.
 
         Returns
         -------
@@ -1776,17 +1776,19 @@ cdef class _Period:
 
     def to_timestamp(self, freq=None, how='start', tz=None):
         """
-        Return the Timestamp representation of the Period at the target
-        frequency at the specified end (how) of the Period.
+        Return the Timestamp representation of the Period.
+
+        Uses the target frequency specified at the part of the period specified
+        by `how`, which is either `Start` or `Finish`.
 
         Parameters
         ----------
-        freq : string or DateOffset
+        freq : str or DateOffset
             Target frequency. Default is 'D' if self.freq is week or
-            longer and 'S' otherwise
+            longer and 'S' otherwise.
         how : str, default 'S' (start)
-            'S', 'E'. Can be aliased as case insensitive
-            'Start', 'Finish', 'Begin', 'End'
+            One of 'S', 'E'. Can be aliased as case insensitive
+            'Start', 'Finish', 'Begin', 'End'.
 
         Returns
         -------
@@ -2385,16 +2387,25 @@ class Period(_Period):
     Parameters
     ----------
     value : Period or str, default None
-        The time period represented (e.g., '4Q2005')
+        The time period represented (e.g., '4Q2005').
     freq : str, default None
-        One of pandas period strings or corresponding objects
+        One of pandas period strings or corresponding objects.
+    ordinal : int, default None
+        The period offset from the gregorian proleptic epoch.
     year : int, default None
+        Year value of the period.
     month : int, default 1
+        Month value of the period.
     quarter : int, default None
+        Quarter value of the period.
     day : int, default 1
+        Day value of the period.
     hour : int, default 0
+        Hour value of the period.
     minute : int, default 0
+        Minute value of the period.
     second : int, default 0
+        Second value of the period.
     """
 
     def __new__(cls, value=None, freq=None, ordinal=None,

pandas/core/dtypes/dtypes.py

@@ -793,7 +793,7 @@ class PeriodDtype(PandasExtensionDtype):
     Parameters
     ----------
     freq : str or DateOffset
-        The frequency of this PeriodDtype
+        The frequency of this PeriodDtype.
 
     Attributes
     ----------

pandas/core/groupby/ops.py

@@ -672,7 +672,13 @@ def agg_series(self, obj, func):
                 pass
             else:
                 raise
-            return self._aggregate_series_pure_python(obj, func)
+        except TypeError as err:
+            if "ndarray" in str(err):
+                # raised in libreduction if obj's values is no ndarray
+                pass
+            else:
+                raise
+        return self._aggregate_series_pure_python(obj, func)
 
     def _aggregate_series_fast(self, obj, func):
         func = self._is_builtin_func(func)

pandas/tests/extension/decimal/test_decimal.py

@@ -426,3 +426,55 @@ def test_array_ufunc_series_defer():
 
     tm.assert_series_equal(r1, expected)
     tm.assert_series_equal(r2, expected)
+
+
+def test_groupby_agg():
+    # Ensure that the result of agg is inferred to be decimal dtype
+    # https://github.com/pandas-dev/pandas/issues/29141
+
+    data = make_data()[:5]
+    df = pd.DataFrame(
+        {"id1": [0, 0, 0, 1, 1], "id2": [0, 1, 0, 1, 1], "decimals": DecimalArray(data)}
+    )
+
+    # single key, selected column
+    expected = pd.Series(to_decimal([data[0], data[3]]))
+    result = df.groupby("id1")["decimals"].agg(lambda x: x.iloc[0])
+    tm.assert_series_equal(result, expected, check_names=False)
+    result = df["decimals"].groupby(df["id1"]).agg(lambda x: x.iloc[0])
+    tm.assert_series_equal(result, expected, check_names=False)
+
+    # multiple keys, selected column
+    expected = pd.Series(
+        to_decimal([data[0], data[1], data[3]]),
+        index=pd.MultiIndex.from_tuples([(0, 0), (0, 1), (1, 1)]),
+    )
+    result = df.groupby(["id1", "id2"])["decimals"].agg(lambda x: x.iloc[0])
+    tm.assert_series_equal(result, expected, check_names=False)
+    result = df["decimals"].groupby([df["id1"], df["id2"]]).agg(lambda x: x.iloc[0])
+    tm.assert_series_equal(result, expected, check_names=False)
+
+    # multiple columns
+    expected = pd.DataFrame({"id2": [0, 1], "decimals": to_decimal([data[0], data[3]])})
+    result = df.groupby("id1").agg(lambda x: x.iloc[0])
+    tm.assert_frame_equal(result, expected, check_names=False)
+
+
+def test_groupby_agg_ea_method(monkeypatch):
+    # Ensure that the result of agg is inferred to be decimal dtype
+    # https://github.com/pandas-dev/pandas/issues/29141
+
+    def DecimalArray__my_sum(self):
+        return np.sum(np.array(self))
+
+    monkeypatch.setattr(DecimalArray, "my_sum", DecimalArray__my_sum, raising=False)
+
+    data = make_data()[:5]
+    df = pd.DataFrame({"id": [0, 0, 0, 1, 1], "decimals": DecimalArray(data)})
+    expected = pd.Series(to_decimal([data[0] + data[1] + data[2], data[3] + data[4]]))
+
+    result = df.groupby("id")["decimals"].agg(lambda x: x.values.my_sum())
+    tm.assert_series_equal(result, expected, check_names=False)
+    s = pd.Series(DecimalArray(data))
+    result = s.groupby(np.array([0, 0, 0, 1, 1])).agg(lambda x: x.values.my_sum())
+    tm.assert_series_equal(result, expected, check_names=False)