CLN: More tests/window/* (#37959)

* Move tests to appripriate locations, use less pd.

* Consolidate fixtures and use frame_or_series

* Rename test

* Add TestRolling and TestExpanding to groupby tests

Co-authored-by: Matt Roeschke <[email protected]>

Author: mroeschke

pandas/tests/window/conftest.py

@@ -275,40 +275,24 @@ def consistency_data(request):
     return request.param
 
 
-def _create_series():
-    """Internal function to mock Series."""
-    arr = np.random.randn(100)
-    locs = np.arange(20, 40)
-    arr[locs] = np.NaN
-    series = Series(arr, index=bdate_range(datetime(2009, 1, 1), periods=100))
-    return series
-
-
-def _create_frame():
-    """Internal function to mock DataFrame."""
+@pytest.fixture
+def frame():
+    """Make mocked frame as fixture."""
     return DataFrame(
         np.random.randn(100, 10),
         index=bdate_range(datetime(2009, 1, 1), periods=100),
         columns=np.arange(10),
     )
 
 
-@pytest.fixture
-def frame():
-    """Make mocked frame as fixture."""
-    return _create_frame()
-
-
 @pytest.fixture
 def series():
     """Make mocked series as fixture."""
-    return _create_series()
-
-
-@pytest.fixture(params=[_create_series(), _create_frame()])
-def which(request):
-    """Turn parametrized which as fixture for series and frame"""
-    return request.param
+    arr = np.random.randn(100)
+    locs = np.arange(20, 40)
+    arr[locs] = np.NaN
+    series = Series(arr, index=bdate_range(datetime(2009, 1, 1), periods=100))
+    return series
 
 
 @pytest.fixture(params=["1 day", timedelta(days=1)])

pandas/tests/window/test_api.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-import pandas.util._test_decorators as td
-
 import pandas as pd
 from pandas import DataFrame, Index, Series, Timestamp, concat
 import pandas._testing as tm
@@ -238,30 +236,6 @@ def test_count_nonnumeric_types():
     tm.assert_frame_equal(result, expected)
 
 
-@td.skip_if_no_scipy
-@pytest.mark.filterwarnings("ignore:can't resolve:ImportWarning")
-def test_window_with_args():
-    # make sure that we are aggregating window functions correctly with arg
-    r = Series(np.random.randn(100)).rolling(
-        window=10, min_periods=1, win_type="gaussian"
-    )
-    expected = concat([r.mean(std=10), r.mean(std=0.01)], axis=1)
-    expected.columns = ["<lambda>", "<lambda>"]
-    result = r.aggregate([lambda x: x.mean(std=10), lambda x: x.mean(std=0.01)])
-    tm.assert_frame_equal(result, expected)
-
-    def a(x):
-        return x.mean(std=10)
-
-    def b(x):
-        return x.mean(std=0.01)
-
-    expected = concat([r.mean(std=10), r.mean(std=0.01)], axis=1)
-    expected.columns = ["a", "b"]
-    result = r.aggregate([a, b])
-    tm.assert_frame_equal(result, expected)
-
-
 def test_preserve_metadata():
     # GH 10565
     s = Series(np.arange(100), name="foo")

pandas/tests/window/test_apply.py

@@ -1,9 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas.errors import NumbaUtilError
-import pandas.util._test_decorators as td
-
 from pandas import DataFrame, Index, MultiIndex, Series, Timestamp, date_range
 import pandas._testing as tm
 
@@ -133,14 +130,6 @@ def test_invalid_raw_numba():
         Series(range(1)).rolling(1).apply(lambda x: x, raw=False, engine="numba")
 
 
-@td.skip_if_no("numba")
-def test_invalid_kwargs_nopython():
-    with pytest.raises(NumbaUtilError, match="numba does not support kwargs with"):
-        Series(range(1)).rolling(1).apply(
-            lambda x: x, kwargs={"a": 1}, engine="numba", raw=True
-        )
-
-
 @pytest.mark.parametrize("args_kwargs", [[None, {"par": 10}], [(10,), None]])
 def test_rolling_apply_args_kwargs(args_kwargs):
     # GH 33433

pandas/tests/window/test_ewm.py

@@ -15,9 +15,9 @@ def test_doc_string():
     df.ewm(com=0.5).mean()
 
 
-def test_constructor(which):
+def test_constructor(frame_or_series):
 
-    c = which.ewm
+    c = frame_or_series(range(5)).ewm
 
     # valid
     c(com=0.5)

pandas/tests/window/test_expanding.py

@@ -19,10 +19,10 @@ def test_doc_string():
 @pytest.mark.filterwarnings(
     "ignore:The `center` argument on `expanding` will be removed in the future"
 )
-def test_constructor(which):
+def test_constructor(frame_or_series):
     # GH 12669
 
-    c = which.expanding
+    c = frame_or_series(range(5)).expanding
 
     # valid
     c(min_periods=1)
@@ -34,10 +34,10 @@ def test_constructor(which):
 @pytest.mark.filterwarnings(
     "ignore:The `center` argument on `expanding` will be removed in the future"
 )
-def test_constructor_invalid(which, w):
+def test_constructor_invalid(frame_or_series, w):
     # not valid
 
-    c = which.expanding
+    c = frame_or_series(range(5)).expanding
     msg = "min_periods must be an integer"
     with pytest.raises(ValueError, match=msg):
         c(min_periods=w)
@@ -118,30 +118,27 @@ def test_expanding_axis(axis_frame):
     tm.assert_frame_equal(result, expected)
 
 
-@pytest.mark.parametrize("constructor", [Series, DataFrame])
-def test_expanding_count_with_min_periods(constructor):
+def test_expanding_count_with_min_periods(frame_or_series):
     # GH 26996
-    result = constructor(range(5)).expanding(min_periods=3).count()
-    expected = constructor([np.nan, np.nan, 3.0, 4.0, 5.0])
+    result = frame_or_series(range(5)).expanding(min_periods=3).count()
+    expected = frame_or_series([np.nan, np.nan, 3.0, 4.0, 5.0])
     tm.assert_equal(result, expected)
 
 
-@pytest.mark.parametrize("constructor", [Series, DataFrame])
-def test_expanding_count_default_min_periods_with_null_values(constructor):
+def test_expanding_count_default_min_periods_with_null_values(frame_or_series):
     # GH 26996
     values = [1, 2, 3, np.nan, 4, 5, 6]
     expected_counts = [1.0, 2.0, 3.0, 3.0, 4.0, 5.0, 6.0]
 
-    result = constructor(values).expanding().count()
-    expected = constructor(expected_counts)
+    result = frame_or_series(values).expanding().count()
+    expected = frame_or_series(expected_counts)
     tm.assert_equal(result, expected)
 
 
-@pytest.mark.parametrize("constructor", [Series, DataFrame])
-def test_expanding_count_with_min_periods_exceeding_series_length(constructor):
+def test_expanding_count_with_min_periods_exceeding_series_length(frame_or_series):
     # GH 25857
-    result = constructor(range(5)).expanding(min_periods=6).count()
-    expected = constructor([np.nan, np.nan, np.nan, np.nan, np.nan])
+    result = frame_or_series(range(5)).expanding(min_periods=6).count()
+    expected = frame_or_series([np.nan, np.nan, np.nan, np.nan, np.nan])
     tm.assert_equal(result, expected)
 
 
@@ -246,10 +243,9 @@ def test_center_deprecate_warning():
         df.expanding()
 
 
-@pytest.mark.parametrize("constructor", ["DataFrame", "Series"])
-def test_expanding_sem(constructor):
+def test_expanding_sem(frame_or_series):
     # GH: 26476
-    obj = getattr(pd, constructor)([0, 1, 2])
+    obj = frame_or_series([0, 1, 2])
     result = obj.expanding().sem()
     if isinstance(result, DataFrame):
         result = Series(result[0].values)

pandas/tests/window/test_groupby.py

@@ -7,9 +7,8 @@
 from pandas.core.groupby.groupby import get_groupby
 
 
-class TestGrouperGrouping:
+class TestRolling:
     def setup_method(self):
-        self.series = Series(np.arange(10))
         self.frame = DataFrame({"A": [1] * 20 + [2] * 12 + [3] * 8, "B": np.arange(40)})
 
     def test_mutated(self):
@@ -152,68 +151,6 @@ def test_rolling_apply_mutability(self):
         result = g.rolling(window=2).sum()
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.parametrize(
-        "f", ["sum", "mean", "min", "max", "count", "kurt", "skew"]
-    )
-    def test_expanding(self, f):
-        g = self.frame.groupby("A")
-        r = g.expanding()
-
-        result = getattr(r, f)()
-        expected = g.apply(lambda x: getattr(x.expanding(), f)())
-        tm.assert_frame_equal(result, expected)
-
-    @pytest.mark.parametrize("f", ["std", "var"])
-    def test_expanding_ddof(self, f):
-        g = self.frame.groupby("A")
-        r = g.expanding()
-
-        result = getattr(r, f)(ddof=0)
-        expected = g.apply(lambda x: getattr(x.expanding(), f)(ddof=0))
-        tm.assert_frame_equal(result, expected)
-
-    @pytest.mark.parametrize(
-        "interpolation", ["linear", "lower", "higher", "midpoint", "nearest"]
-    )
-    def test_expanding_quantile(self, interpolation):
-        g = self.frame.groupby("A")
-        r = g.expanding()
-        result = r.quantile(0.4, interpolation=interpolation)
-        expected = g.apply(
-            lambda x: x.expanding().quantile(0.4, interpolation=interpolation)
-        )
-        tm.assert_frame_equal(result, expected)
-
-    @pytest.mark.parametrize("f", ["corr", "cov"])
-    def test_expanding_corr_cov(self, f):
-        g = self.frame.groupby("A")
-        r = g.expanding()
-
-        result = getattr(r, f)(self.frame)
-
-        def func(x):
-            return getattr(x.expanding(), f)(self.frame)
-
-        expected = g.apply(func)
-        tm.assert_frame_equal(result, expected)
-
-        result = getattr(r.B, f)(pairwise=True)
-
-        def func(x):
-            return getattr(x.B.expanding(), f)(pairwise=True)
-
-        expected = g.apply(func)
-        tm.assert_series_equal(result, expected)
-
-    def test_expanding_apply(self, raw):
-        g = self.frame.groupby("A")
-        r = g.expanding()
-
-        # reduction
-        result = r.apply(lambda x: x.sum(), raw=raw)
-        expected = g.apply(lambda x: x.expanding().apply(lambda y: y.sum(), raw=raw))
-        tm.assert_frame_equal(result, expected)
-
     @pytest.mark.parametrize("expected_value,raw_value", [[1.0, True], [0.0, False]])
     def test_groupby_rolling(self, expected_value, raw_value):
         # GH 31754
@@ -633,6 +570,73 @@ def test_groupby_rolling_index_level_and_column_label(self):
         tm.assert_frame_equal(result, expected)
 
 
+class TestExpanding:
+    def setup_method(self):
+        self.frame = DataFrame({"A": [1] * 20 + [2] * 12 + [3] * 8, "B": np.arange(40)})
+
+    @pytest.mark.parametrize(
+        "f", ["sum", "mean", "min", "max", "count", "kurt", "skew"]
+    )
+    def test_expanding(self, f):
+        g = self.frame.groupby("A")
+        r = g.expanding()
+
+        result = getattr(r, f)()
+        expected = g.apply(lambda x: getattr(x.expanding(), f)())
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("f", ["std", "var"])
+    def test_expanding_ddof(self, f):
+        g = self.frame.groupby("A")
+        r = g.expanding()
+
+        result = getattr(r, f)(ddof=0)
+        expected = g.apply(lambda x: getattr(x.expanding(), f)(ddof=0))
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "interpolation", ["linear", "lower", "higher", "midpoint", "nearest"]
+    )
+    def test_expanding_quantile(self, interpolation):
+        g = self.frame.groupby("A")
+        r = g.expanding()
+        result = r.quantile(0.4, interpolation=interpolation)
+        expected = g.apply(
+            lambda x: x.expanding().quantile(0.4, interpolation=interpolation)
+        )
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("f", ["corr", "cov"])
+    def test_expanding_corr_cov(self, f):
+        g = self.frame.groupby("A")
+        r = g.expanding()
+
+        result = getattr(r, f)(self.frame)
+
+        def func(x):
+            return getattr(x.expanding(), f)(self.frame)
+
+        expected = g.apply(func)
+        tm.assert_frame_equal(result, expected)
+
+        result = getattr(r.B, f)(pairwise=True)
+
+        def func(x):
+            return getattr(x.B.expanding(), f)(pairwise=True)
+
+        expected = g.apply(func)
+        tm.assert_series_equal(result, expected)
+
+    def test_expanding_apply(self, raw):
+        g = self.frame.groupby("A")
+        r = g.expanding()
+
+        # reduction
+        result = r.apply(lambda x: x.sum(), raw=raw)
+        expected = g.apply(lambda x: x.expanding().apply(lambda y: y.sum(), raw=raw))
+        tm.assert_frame_equal(result, expected)
+
+
 class TestEWM:
     @pytest.mark.parametrize(
         "method, expected_data",

pandas/tests/window/test_numba.py

@@ -1,6 +1,7 @@
 import numpy as np
 import pytest
 
+from pandas.errors import NumbaUtilError
 import pandas.util._test_decorators as td
 
 from pandas import DataFrame, Series, option_context
@@ -112,3 +113,11 @@ def f(x):
         result = s.rolling(2).apply(f, engine=None, raw=True)
     expected = s.rolling(2).apply(f, engine="numba", raw=True)
     tm.assert_series_equal(expected, result)
+
+
+@td.skip_if_no("numba", "0.46.0")
+def test_invalid_kwargs_nopython():
+    with pytest.raises(NumbaUtilError, match="numba does not support kwargs with"):
+        Series(range(1)).rolling(1).apply(
+            lambda x: x, kwargs={"a": 1}, engine="numba", raw=True
+        )