Merge remote-tracking branch 'upstream/main' into implementation-pdep-4

Author: MarcoGorelli

.github/workflows/python-dev.yml

@@ -54,7 +54,7 @@ jobs:
         os: [ubuntu-latest, macOS-latest, windows-latest]
 
     name: actions-311-dev
-    timeout-minutes: 80
+    timeout-minutes: 120
 
     concurrency:
       #https://github.community/t/concurrecy-not-work-for-push/183068/7
@@ -75,7 +75,7 @@ jobs:
       run: |
         python --version
         python -m pip install --upgrade pip setuptools wheel
-        python -m pip install git+https://github.com/numpy/numpy.git
+        python -m pip install -i https://pypi.anaconda.org/scipy-wheels-nightly/simple numpy
         python -m pip install git+https://github.com/nedbat/coveragepy.git
         python -m pip install python-dateutil pytz cython hypothesis==6.52.1 pytest>=6.2.5 pytest-xdist pytest-cov pytest-asyncio>=0.17
         python -m pip list
@@ -84,7 +84,7 @@ jobs:
     - name: Build Pandas
       run: |
         python setup.py build_ext -q -j1
-        python -m pip install -e . --no-build-isolation --no-use-pep517
+        python -m pip install -e . --no-build-isolation --no-use-pep517 --no-index
 
     - name: Build Version
       run: |

README.md

@@ -128,8 +128,6 @@ or for installing in [development mode](https://pip.pypa.io/en/latest/cli/pip_in
 python -m pip install -e . --no-build-isolation --no-use-pep517
 ```
 
-If you have `make`, you can also use `make develop` to run the same command.
-
 or alternatively
 
 ```sh

pandas/core/arrays/datetimelike.py

@@ -1275,7 +1275,8 @@ def _add_timedeltalike_scalar(self, other):
 
         # PeriodArray overrides, so we only get here with DTA/TDA
         self = cast("DatetimeArray | TimedeltaArray", self)
-        other = Timedelta(other)._as_unit(self._unit)
+        other = Timedelta(other)
+        self, other = self._ensure_matching_resos(other)
         return self._add_timedeltalike(other)
 
     def _add_timedelta_arraylike(self, other: TimedeltaArray):

pandas/core/construction.py

@@ -45,7 +45,6 @@
     maybe_convert_platform,
     maybe_infer_to_datetimelike,
     maybe_upcast,
-    sanitize_to_nanoseconds,
 )
 from pandas.core.dtypes.common import (
     is_datetime64_ns_dtype,
@@ -782,7 +781,9 @@ def _try_cast(
         if is_ndarray:
             arr = cast(np.ndarray, arr)
             if arr.dtype != object:
-                return sanitize_to_nanoseconds(arr, copy=copy)
+                if copy:
+                    return arr.copy()
+                return arr
 
             out = maybe_infer_to_datetimelike(arr)
             if out is arr and copy:

pandas/core/dtypes/cast.py

@@ -1423,12 +1423,7 @@ def maybe_cast_to_datetime(
             return astype_nansafe(value, dtype)  # type: ignore[arg-type]
 
     elif isinstance(value, np.ndarray):
-        if value.dtype.kind in ["M", "m"]:
-            # catch a datetime/timedelta that is not of ns variety
-            # and no coercion specified
-            value = sanitize_to_nanoseconds(value)
-
-        elif value.dtype == _dtype_obj:
+        if value.dtype == _dtype_obj:
             value = maybe_infer_to_datetimelike(value)
 
     elif isinstance(value, list):

pandas/core/generic.py

@@ -5878,7 +5878,7 @@ def pipe(
 
         If you have a function that takes the data as (say) the second
         argument, pass a tuple indicating which keyword expects the
-        data. For example, suppose ``f`` takes its data as ``arg2``:
+        data. For example, suppose ``func`` takes its data as ``arg2``:
 
         >>> (df.pipe(h)
         ...    .pipe(g, arg1=a)

pandas/core/groupby/grouper.py

@@ -26,7 +26,6 @@
 from pandas.util._decorators import cache_readonly
 from pandas.util._exceptions import find_stack_level
 
-from pandas.core.dtypes.cast import sanitize_to_nanoseconds
 from pandas.core.dtypes.common import (
     is_categorical_dtype,
     is_list_like,
@@ -558,9 +557,12 @@ def __init__(
                 raise AssertionError(errmsg)
 
         if isinstance(self.grouping_vector, np.ndarray):
-            # if we have a date/time-like grouper, make sure that we have
-            # Timestamps like
-            self.grouping_vector = sanitize_to_nanoseconds(self.grouping_vector)
+            if self.grouping_vector.dtype.kind in ["m", "M"]:
+                # if we have a date/time-like grouper, make sure that we have
+                # Timestamps like
+                # TODO 2022-10-08 we only have one test that gets here and
+                #  values are already in nanoseconds in that case.
+                self.grouping_vector = Series(self.grouping_vector).to_numpy()
 
     def __repr__(self) -> str:
         return f"Grouping({self.name})"

pandas/core/internals/blocks.py

@@ -1983,7 +1983,7 @@ def _catch_deprecated_value_error(err: Exception) -> None:
             # IntervalDtype mismatched 'closed'
             pass
         elif "Timezones don't match" not in str(err):
-            raise
+            raise err
 
 
 class DatetimeLikeBlock(NDArrayBackedExtensionBlock):

pandas/tests/frame/test_query_eval.py

@@ -36,45 +36,48 @@ def skip_if_no_pandas_parser(parser):
 
 
 class TestCompat:
-    def setup_method(self):
-        self.df = DataFrame({"A": [1, 2, 3]})
-        self.expected1 = self.df[self.df.A > 0]
-        self.expected2 = self.df.A + 1
+    @pytest.fixture
+    def df(self):
+        return DataFrame({"A": [1, 2, 3]})
+
+    @pytest.fixture
+    def expected1(self, df):
+        return df[df.A > 0]
+
+    @pytest.fixture
+    def expected2(self, df):
+        return df.A + 1
 
-    def test_query_default(self):
+    def test_query_default(self, df, expected1, expected2):
 
         # GH 12749
         # this should always work, whether NUMEXPR_INSTALLED or not
-        df = self.df
         result = df.query("A>0")
-        tm.assert_frame_equal(result, self.expected1)
+        tm.assert_frame_equal(result, expected1)
         result = df.eval("A+1")
-        tm.assert_series_equal(result, self.expected2, check_names=False)
+        tm.assert_series_equal(result, expected2, check_names=False)
 
-    def test_query_None(self):
+    def test_query_None(self, df, expected1, expected2):
 
-        df = self.df
         result = df.query("A>0", engine=None)
-        tm.assert_frame_equal(result, self.expected1)
+        tm.assert_frame_equal(result, expected1)
         result = df.eval("A+1", engine=None)
-        tm.assert_series_equal(result, self.expected2, check_names=False)
+        tm.assert_series_equal(result, expected2, check_names=False)
 
-    def test_query_python(self):
+    def test_query_python(self, df, expected1, expected2):
 
-        df = self.df
         result = df.query("A>0", engine="python")
-        tm.assert_frame_equal(result, self.expected1)
+        tm.assert_frame_equal(result, expected1)
         result = df.eval("A+1", engine="python")
-        tm.assert_series_equal(result, self.expected2, check_names=False)
+        tm.assert_series_equal(result, expected2, check_names=False)
 
-    def test_query_numexpr(self):
+    def test_query_numexpr(self, df, expected1, expected2):
 
-        df = self.df
         if NUMEXPR_INSTALLED:
             result = df.query("A>0", engine="numexpr")
-            tm.assert_frame_equal(result, self.expected1)
+            tm.assert_frame_equal(result, expected1)
             result = df.eval("A+1", engine="numexpr")
-            tm.assert_series_equal(result, self.expected2, check_names=False)
+            tm.assert_series_equal(result, expected2, check_names=False)
         else:
             msg = (
                 r"'numexpr' is not installed or an unsupported version. "

pandas/tests/io/json/test_json_table_schema_ext_dtype.py

@@ -111,23 +111,36 @@ def test_as_json_table_type_ext_integer_dtype(self):
 
 
 class TestTableOrient:
-    def setup_method(self):
-        self.da = DateArray([dt.date(2021, 10, 10)])
-        self.dc = DecimalArray([decimal.Decimal(10)])
-        self.sa = array(["pandas"], dtype="string")
-        self.ia = array([10], dtype="Int64")
-        self.df = DataFrame(
+    @pytest.fixture
+    def da(self):
+        return DateArray([dt.date(2021, 10, 10)])
+
+    @pytest.fixture
+    def dc(self):
+        return DecimalArray([decimal.Decimal(10)])
+
+    @pytest.fixture
+    def sa(self):
+        return array(["pandas"], dtype="string")
+
+    @pytest.fixture
+    def ia(self):
+        return array([10], dtype="Int64")
+
+    @pytest.fixture
+    def df(self, da, dc, sa, ia):
+        return DataFrame(
             {
-                "A": self.da,
-                "B": self.dc,
-                "C": self.sa,
-                "D": self.ia,
+                "A": da,
+                "B": dc,
+                "C": sa,
+                "D": ia,
             }
         )
 
-    def test_build_date_series(self):
+    def test_build_date_series(self, da):
 
-        s = Series(self.da, name="a")
+        s = Series(da, name="a")
         s.index.name = "id"
         result = s.to_json(orient="table", date_format="iso")
         result = json.loads(result, object_pairs_hook=OrderedDict)
@@ -151,9 +164,9 @@ def test_build_date_series(self):
 
         assert result == expected
 
-    def test_build_decimal_series(self):
+    def test_build_decimal_series(self, dc):
 
-        s = Series(self.dc, name="a")
+        s = Series(dc, name="a")
         s.index.name = "id"
         result = s.to_json(orient="table", date_format="iso")
         result = json.loads(result, object_pairs_hook=OrderedDict)
@@ -177,8 +190,8 @@ def test_build_decimal_series(self):
 
         assert result == expected
 
-    def test_build_string_series(self):
-        s = Series(self.sa, name="a")
+    def test_build_string_series(self, sa):
+        s = Series(sa, name="a")
         s.index.name = "id"
         result = s.to_json(orient="table", date_format="iso")
         result = json.loads(result, object_pairs_hook=OrderedDict)
@@ -202,8 +215,8 @@ def test_build_string_series(self):
 
         assert result == expected
 
-    def test_build_int64_series(self):
-        s = Series(self.ia, name="a")
+    def test_build_int64_series(self, ia):
+        s = Series(ia, name="a")
         s.index.name = "id"
         result = s.to_json(orient="table", date_format="iso")
         result = json.loads(result, object_pairs_hook=OrderedDict)
@@ -227,9 +240,9 @@ def test_build_int64_series(self):
 
         assert result == expected
 
-    def test_to_json(self):
+    def test_to_json(self, df):
 
-        df = self.df.copy()
+        df = df.copy()
         df.index.name = "idx"
         result = df.to_json(orient="table", date_format="iso")
         result = json.loads(result, object_pairs_hook=OrderedDict)

pandas/tests/plotting/test_converter.py

@@ -287,66 +287,70 @@ def test_convert_nested(self, dtc):
 
 
 class TestPeriodConverter:
-    def setup_method(self):
-        self.pc = converter.PeriodConverter()
+    @pytest.fixture
+    def pc(self):
+        return converter.PeriodConverter()
 
+    @pytest.fixture
+    def axis(self):
         class Axis:
             pass
 
-        self.axis = Axis()
-        self.axis.freq = "D"
+        axis = Axis()
+        axis.freq = "D"
+        return axis
 
-    def test_convert_accepts_unicode(self):
-        r1 = self.pc.convert("2012-1-1", None, self.axis)
-        r2 = self.pc.convert("2012-1-1", None, self.axis)
+    def test_convert_accepts_unicode(self, pc, axis):
+        r1 = pc.convert("2012-1-1", None, axis)
+        r2 = pc.convert("2012-1-1", None, axis)
         assert r1 == r2
 
-    def test_conversion(self):
-        rs = self.pc.convert(["2012-1-1"], None, self.axis)[0]
+    def test_conversion(self, pc, axis):
+        rs = pc.convert(["2012-1-1"], None, axis)[0]
         xp = Period("2012-1-1").ordinal
         assert rs == xp
 
-        rs = self.pc.convert("2012-1-1", None, self.axis)
+        rs = pc.convert("2012-1-1", None, axis)
         assert rs == xp
 
-        rs = self.pc.convert([date(2012, 1, 1)], None, self.axis)[0]
+        rs = pc.convert([date(2012, 1, 1)], None, axis)[0]
         assert rs == xp
 
-        rs = self.pc.convert(date(2012, 1, 1), None, self.axis)
+        rs = pc.convert(date(2012, 1, 1), None, axis)
         assert rs == xp
 
-        rs = self.pc.convert([Timestamp("2012-1-1")], None, self.axis)[0]
+        rs = pc.convert([Timestamp("2012-1-1")], None, axis)[0]
         assert rs == xp
 
-        rs = self.pc.convert(Timestamp("2012-1-1"), None, self.axis)
+        rs = pc.convert(Timestamp("2012-1-1"), None, axis)
         assert rs == xp
 
-        rs = self.pc.convert("2012-01-01", None, self.axis)
+        rs = pc.convert("2012-01-01", None, axis)
         assert rs == xp
 
-        rs = self.pc.convert("2012-01-01 00:00:00+0000", None, self.axis)
+        rs = pc.convert("2012-01-01 00:00:00+0000", None, axis)
         assert rs == xp
 
-        rs = self.pc.convert(
+        rs = pc.convert(
             np.array(
                 ["2012-01-01 00:00:00", "2012-01-02 00:00:00"],
                 dtype="datetime64[ns]",
             ),
             None,
-            self.axis,
+            axis,
         )
         assert rs[0] == xp
 
-    def test_integer_passthrough(self):
+    def test_integer_passthrough(self, pc, axis):
         # GH9012
-        rs = self.pc.convert([0, 1], None, self.axis)
+        rs = pc.convert([0, 1], None, axis)
         xp = [0, 1]
         assert rs == xp
 
-    def test_convert_nested(self):
+    def test_convert_nested(self, pc, axis):
         data = ["2012-1-1", "2012-1-2"]
-        r1 = self.pc.convert([data, data], None, self.axis)
-        r2 = [self.pc.convert(data, None, self.axis) for _ in range(2)]
+        r1 = pc.convert([data, data], None, axis)
+        r2 = [pc.convert(data, None, axis) for _ in range(2)]
         assert r1 == r2