Merge remote-tracking branch 'upstream/master' into fix_convert_dtypes_bool

Merge remote-tracking branch 'upstream/master' into fix_convert_dtypes_bool

Author: AnnaDaglis

doc/source/whatsnew/v1.1.0.rst

@@ -234,7 +234,7 @@ Numeric
 Conversion
 ^^^^^^^^^^
 - Bug in :class:`Series` construction from NumPy array with big-endian ``datetime64`` dtype (:issue:`29684`)
--
+- Bug in :class:`Timedelta` construction with large nanoseconds keyword value (:issue:`32402`)
 -
 
 Strings
@@ -327,6 +327,7 @@ Reshaping
 - Bug in :func:`crosstab` when inputs are two Series and have tuple names, the output will keep dummy MultiIndex as columns. (:issue:`18321`)
 - :meth:`DataFrame.pivot` can now take lists for ``index`` and ``columns`` arguments (:issue:`21425`)
 - Bug in :func:`concat` where the resulting indices are not copied when ``copy=True`` (:issue:`29879`)
+- :meth:`Series.append` will now raise a ``TypeError`` when passed a DataFrame or a sequence containing Dataframe (:issue:`31413`)
 - :meth:`DataFrame.replace` and :meth:`Series.replace` will raise a ``TypeError`` if ``to_replace`` is not an expected type. Previously the ``replace`` would fail silently (:issue:`18634`)
 
 
@@ -349,7 +350,6 @@ Other
   instead of ``TypeError: Can only append a Series if ignore_index=True or if the Series has a name`` (:issue:`30871`)
 - Set operations on an object-dtype :class:`Index` now always return object-dtype results (:issue:`31401`)
 - Bug in :meth:`AbstractHolidayCalendar.holidays` when no rules were defined (:issue:`31415`)
--
 
 .. ---------------------------------------------------------------------------
 

pandas/_libs/tslibs/timedeltas.pyx

@@ -1198,7 +1198,7 @@ class Timedelta(_Timedelta):
 
             kwargs = {key: _to_py_int_float(kwargs[key]) for key in kwargs}
 
-            nano = np.timedelta64(kwargs.pop('nanoseconds', 0), 'ns')
+            nano = convert_to_timedelta64(kwargs.pop('nanoseconds', 0), 'ns')
             try:
                 value = nano + convert_to_timedelta64(timedelta(**kwargs),
                                                       'ns')

pandas/_testing.py

@@ -706,11 +706,11 @@ def _get_ilevel_values(index, level):
     if isinstance(left, pd.PeriodIndex) or isinstance(right, pd.PeriodIndex):
         assert_attr_equal("freq", left, right, obj=obj)
     if isinstance(left, pd.IntervalIndex) or isinstance(right, pd.IntervalIndex):
-        assert_interval_array_equal(left.values, right.values)
+        assert_interval_array_equal(left._values, right._values)
 
     if check_categorical:
         if is_categorical_dtype(left) or is_categorical_dtype(right):
-            assert_categorical_equal(left.values, right.values, obj=f"{obj} category")
+            assert_categorical_equal(left._values, right._values, obj=f"{obj} category")
 
 
 def assert_class_equal(left, right, exact: Union[bool, str] = True, obj="Input"):
@@ -883,7 +883,7 @@ def assert_interval_array_equal(left, right, exact="equiv", obj="IntervalArray")
 def assert_period_array_equal(left, right, obj="PeriodArray"):
     _check_isinstance(left, right, PeriodArray)
 
-    assert_numpy_array_equal(left._data, right._data, obj=f"{obj}.values")
+    assert_numpy_array_equal(left._data, right._data, obj=f"{obj}._data")
     assert_attr_equal("freq", left, right, obj=obj)
 
 
@@ -1170,10 +1170,10 @@ def assert_series_equal(
 
             # datetimelike may have different objects (e.g. datetime.datetime
             # vs Timestamp) but will compare equal
-            if not Index(left.values).equals(Index(right.values)):
+            if not Index(left._values).equals(Index(right._values)):
                 msg = (
-                    f"[datetimelike_compat=True] {left.values} "
-                    f"is not equal to {right.values}."
+                    f"[datetimelike_compat=True] {left._values} "
+                    f"is not equal to {right._values}."
                 )
                 raise AssertionError(msg)
         else:
@@ -1212,8 +1212,8 @@ def assert_series_equal(
     if check_categorical:
         if is_categorical_dtype(left) or is_categorical_dtype(right):
             assert_categorical_equal(
-                left.values,
-                right.values,
+                left._values,
+                right._values,
                 obj=f"{obj} category",
                 check_category_order=check_category_order,
             )

pandas/core/algorithms.py

@@ -313,8 +313,8 @@ def unique(values):
 
     See Also
     --------
-    Index.unique
-    Series.unique
+    Index.unique : Return unique values from an Index.
+    Series.unique : Return unique values of Series object.
 
     Examples
     --------
@@ -1515,7 +1515,7 @@ def take(arr, indices, axis: int = 0, allow_fill: bool = False, fill_value=None)
 
     See Also
     --------
-    numpy.take
+    numpy.take : Take elements from an array along an axis.
 
     Examples
     --------

pandas/core/base.py

@@ -927,16 +927,17 @@ def max(self, axis=None, skipna=True, *args, **kwargs):
         nv.validate_max(args, kwargs)
         return nanops.nanmax(self._values, skipna=skipna)
 
+    @doc(op="max", oppose="min", value="largest")
     def argmax(self, axis=None, skipna=True, *args, **kwargs):
         """
-        Return int position of the largest value in the Series.
+        Return int position of the {value} value in the Series.
 
-        If the maximum is achieved in multiple locations,
+        If the {op}imum is achieved in multiple locations,
         the first row position is returned.
 
         Parameters
         ----------
-        axis : {None}
+        axis : {{None}}
             Dummy argument for consistency with Series.
         skipna : bool, default True
             Exclude NA/null values when showing the result.
@@ -946,21 +947,22 @@ def argmax(self, axis=None, skipna=True, *args, **kwargs):
         Returns
         -------
         int
-            Row position of the maximum values.
+            Row position of the {op}imum value.
 
         See Also
         --------
-        numpy.ndarray.argmax : Equivalent method for numpy arrays.
-        Series.argmin : Similar method, but returning the minimum.
+        Series.arg{op} : Return position of the {op}imum value.
+        Series.arg{oppose} : Return position of the {oppose}imum value.
+        numpy.ndarray.arg{op} : Equivalent method for numpy arrays.
         Series.idxmax : Return index label of the maximum values.
         Series.idxmin : Return index label of the minimum values.
 
         Examples
         --------
         Consider dataset containing cereal calories
 
-        >>> s = pd.Series({'Corn Flakes': 100.0, 'Almond Delight': 110.0,
-        ...                'Cinnamon Toast Crunch': 120.0, 'Cocoa Puff': 110.0})
+        >>> s = pd.Series({{'Corn Flakes': 100.0, 'Almond Delight': 110.0,
+        ...                'Cinnamon Toast Crunch': 120.0, 'Cocoa Puff': 110.0}})
         >>> s
         Corn Flakes              100.0
         Almond Delight           110.0
@@ -970,8 +972,11 @@ def argmax(self, axis=None, skipna=True, *args, **kwargs):
 
         >>> s.argmax()
         2
+        >>> s.argmin()
+        0
 
-        The maximum cereal calories is in the third element,
+        The maximum cereal calories is the third element and
+        the minimum cereal calories is the first element,
         since series is zero-indexed.
         """
         nv.validate_minmax_axis(axis)
@@ -1019,25 +1024,8 @@ def min(self, axis=None, skipna=True, *args, **kwargs):
         nv.validate_min(args, kwargs)
         return nanops.nanmin(self._values, skipna=skipna)
 
+    @doc(argmax, op="min", oppose="max", value="smallest")
     def argmin(self, axis=None, skipna=True, *args, **kwargs):
-        """
-        Return a ndarray of the minimum argument indexer.
-
-        Parameters
-        ----------
-        axis : {None}
-            Dummy argument for consistency with Series.
-        skipna : bool, default True
-
-        Returns
-        -------
-        numpy.ndarray
-
-        See Also
-        --------
-        numpy.ndarray.argmin : Return indices of the minimum values along
-            the given axis.
-        """
         nv.validate_minmax_axis(axis)
         nv.validate_argmax_with_skipna(skipna, args, kwargs)
         return nanops.nanargmin(self._values, skipna=skipna)

pandas/core/dtypes/cast.py

@@ -1184,9 +1184,11 @@ def try_timedelta(v):
         from pandas import to_timedelta
 
         try:
-            return to_timedelta(v)._ndarray_values.reshape(shape)
+            td_values = to_timedelta(v)
         except ValueError:
             return v.reshape(shape)
+        else:
+            return np.asarray(td_values).reshape(shape)
 
     inferred_type = lib.infer_datetimelike_array(ensure_object(v))
 

pandas/core/frame.py

@@ -94,10 +94,8 @@
 )
 from pandas.core.dtypes.generic import (
     ABCDataFrame,
-    ABCDatetimeIndex,
     ABCIndexClass,
     ABCMultiIndex,
-    ABCPeriodIndex,
     ABCSeries,
 )
 from pandas.core.dtypes.missing import isna, notna
@@ -358,9 +356,9 @@ class DataFrame(NDFrame):
     --------
     DataFrame.from_records : Constructor from tuples, also record arrays.
     DataFrame.from_dict : From dicts of Series, arrays, or dicts.
-    read_csv
-    read_table
-    read_clipboard
+    read_csv : Read a comma-separated values (csv) file into DataFrame.
+    read_table : Read general delimited file into DataFrame.
+    read_clipboard : Read text from clipboard into DataFrame.
 
     Examples
     --------
@@ -892,7 +890,7 @@ def style(self) -> "Styler":
         """
 
     @Appender(_shared_docs["items"])
-    def items(self) -> Iterable[Tuple[Optional[Hashable], Series]]:
+    def items(self) -> Iterable[Tuple[Label, Series]]:
         if self.columns.is_unique and hasattr(self, "_item_cache"):
             for k in self.columns:
                 yield k, self._get_item_cache(k)
@@ -901,10 +899,10 @@ def items(self) -> Iterable[Tuple[Optional[Hashable], Series]]:
                 yield k, self._ixs(i, axis=1)
 
     @Appender(_shared_docs["items"])
-    def iteritems(self) -> Iterable[Tuple[Optional[Hashable], Series]]:
+    def iteritems(self) -> Iterable[Tuple[Label, Series]]:
         yield from self.items()
 
-    def iterrows(self) -> Iterable[Tuple[Optional[Hashable], Series]]:
+    def iterrows(self) -> Iterable[Tuple[Label, Series]]:
         """
         Iterate over DataFrame rows as (index, Series) pairs.
 
@@ -4045,7 +4043,7 @@ def set_index(
             "one-dimensional arrays."
         )
 
-        missing: List[Optional[Hashable]] = []
+        missing: List[Label] = []
         for col in keys:
             if isinstance(
                 col, (ABCIndexClass, ABCSeries, np.ndarray, list, abc.Iterator)
@@ -4084,7 +4082,7 @@ def set_index(
             else:
                 arrays.append(self.index)
 
-        to_remove: List[Optional[Hashable]] = []
+        to_remove: List[Label] = []
         for col in keys:
             if isinstance(col, ABCMultiIndex):
                 for n in range(col.nlevels):
@@ -4139,7 +4137,7 @@ def reset_index(
         drop: bool = False,
         inplace: bool = False,
         col_level: Hashable = 0,
-        col_fill: Optional[Hashable] = "",
+        col_fill: Label = "",
     ) -> Optional["DataFrame"]:
         """
         Reset the index, or a level of it.
@@ -4582,7 +4580,7 @@ def drop_duplicates(
         duplicated = self.duplicated(subset, keep=keep)
 
         if inplace:
-            (inds,) = (-duplicated)._ndarray_values.nonzero()
+            (inds,) = np.asarray(-duplicated).nonzero()
             new_data = self._data.take(inds)
 
             if ignore_index:
@@ -7393,8 +7391,9 @@ def corr(self, method="pearson", min_periods=1) -> "DataFrame":
 
         See Also
         --------
-        DataFrame.corrwith
-        Series.corr
+        DataFrame.corrwith : Compute pairwise correlation with another
+            DataFrame or Series.
+        Series.corr : Compute the correlation between two Series.
 
         Examples
         --------
@@ -7596,7 +7595,7 @@ def corrwith(self, other, axis=0, drop=False, method="pearson") -> Series:
 
         See Also
         --------
-        DataFrame.corr
+        DataFrame.corr : Compute pairwise correlation of columns.
         """
         axis = self._get_axis_number(axis)
         this = self._get_numeric_data()
@@ -8001,7 +8000,7 @@ def idxmin(self, axis=0, skipna=True) -> Series:
 
         See Also
         --------
-        Series.idxmin
+        Series.idxmin : Return index of the minimum element.
 
         Notes
         -----
@@ -8039,7 +8038,7 @@ def idxmax(self, axis=0, skipna=True) -> Series:
 
         See Also
         --------
-        Series.idxmax
+        Series.idxmax : Return index of the maximum element.
 
         Notes
         -----
@@ -8245,7 +8244,9 @@ def quantile(self, q=0.5, axis=0, numeric_only=True, interpolation="linear"):
 
         return result
 
-    def to_timestamp(self, freq=None, how="start", axis=0, copy=True) -> "DataFrame":
+    def to_timestamp(
+        self, freq=None, how: str = "start", axis: Axis = 0, copy: bool = True
+    ) -> "DataFrame":
         """
         Cast to DatetimeIndex of timestamps, at *beginning* of period.
 
@@ -8265,23 +8266,16 @@ def to_timestamp(self, freq=None, how="start", axis=0, copy=True) -> "DataFrame"
         -------
         DataFrame with DatetimeIndex
         """
-        new_data = self._data
-        if copy:
-            new_data = new_data.copy()
+        new_obj = self.copy(deep=copy)
 
-        axis = self._get_axis_number(axis)
-        if axis == 0:
-            assert isinstance(self.index, (ABCDatetimeIndex, ABCPeriodIndex))
-            new_data.set_axis(1, self.index.to_timestamp(freq=freq, how=how))
-        elif axis == 1:
-            assert isinstance(self.columns, (ABCDatetimeIndex, ABCPeriodIndex))
-            new_data.set_axis(0, self.columns.to_timestamp(freq=freq, how=how))
-        else:  # pragma: no cover
-            raise AssertionError(f"Axis must be 0 or 1. Got {axis}")
+        axis_name = self._get_axis_name(axis)
+        old_ax = getattr(self, axis_name)
+        new_ax = old_ax.to_timestamp(freq=freq, how=how)
 
-        return self._constructor(new_data)
+        setattr(new_obj, axis_name, new_ax)
+        return new_obj
 
-    def to_period(self, freq=None, axis=0, copy=True) -> "DataFrame":
+    def to_period(self, freq=None, axis: Axis = 0, copy: bool = True) -> "DataFrame":
         """
         Convert DataFrame from DatetimeIndex to PeriodIndex.
 
@@ -8299,23 +8293,16 @@ def to_period(self, freq=None, axis=0, copy=True) -> "DataFrame":
 
         Returns
         -------
-        TimeSeries with PeriodIndex
+        DataFrame with PeriodIndex
         """
-        new_data = self._data
-        if copy:
-            new_data = new_data.copy()
+        new_obj = self.copy(deep=copy)
 
-        axis = self._get_axis_number(axis)
-        if axis == 0:
-            assert isinstance(self.index, ABCDatetimeIndex)
-            new_data.set_axis(1, self.index.to_period(freq=freq))
-        elif axis == 1:
-            assert isinstance(self.columns, ABCDatetimeIndex)
-            new_data.set_axis(0, self.columns.to_period(freq=freq))
-        else:  # pragma: no cover
-            raise AssertionError(f"Axis must be 0 or 1. Got {axis}")
+        axis_name = self._get_axis_name(axis)
+        old_ax = getattr(self, axis_name)
+        new_ax = old_ax.to_period(freq=freq)
 
-        return self._constructor(new_data)
+        setattr(new_obj, axis_name, new_ax)
+        return new_obj
 
     def isin(self, values) -> "DataFrame":
         """