TST/REF: collect tests by method (#37589)

* TST/REF: move remaining setitem tests from test_timeseries

* TST/REF: rehome test_timezones test

* move misplaced arithmetic test

* collect tests by method

* move misplaced file

Author: jbrockmendel

pandas/tests/frame/indexing/test_setitem.py

@@ -185,6 +185,53 @@ def test_setitem_extension_types(self, obj, dtype):
 
         tm.assert_frame_equal(df, expected)
 
+    def test_setitem_dt64_ndarray_with_NaT_and_diff_time_units(self):
+        # GH#7492
+        data_ns = np.array([1, "nat"], dtype="datetime64[ns]")
+        result = Series(data_ns).to_frame()
+        result["new"] = data_ns
+        expected = DataFrame({0: [1, None], "new": [1, None]}, dtype="datetime64[ns]")
+        tm.assert_frame_equal(result, expected)
+
+        # OutOfBoundsDatetime error shouldn't occur
+        data_s = np.array([1, "nat"], dtype="datetime64[s]")
+        result["new"] = data_s
+        expected = DataFrame({0: [1, None], "new": [1e9, None]}, dtype="datetime64[ns]")
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("unit", ["h", "m", "s", "ms", "D", "M", "Y"])
+    def test_frame_setitem_datetime64_col_other_units(self, unit):
+        # Check that non-nano dt64 values get cast to dt64 on setitem
+        #  into a not-yet-existing column
+        n = 100
+
+        dtype = np.dtype(f"M8[{unit}]")
+        vals = np.arange(n, dtype=np.int64).view(dtype)
+        ex_vals = vals.astype("datetime64[ns]")
+
+        df = DataFrame({"ints": np.arange(n)}, index=np.arange(n))
+        df[unit] = vals
+
+        assert df[unit].dtype == np.dtype("M8[ns]")
+        assert (df[unit].values == ex_vals).all()
+
+    @pytest.mark.parametrize("unit", ["h", "m", "s", "ms", "D", "M", "Y"])
+    def test_frame_setitem_existing_datetime64_col_other_units(self, unit):
+        # Check that non-nano dt64 values get cast to dt64 on setitem
+        #  into an already-existing dt64 column
+        n = 100
+
+        dtype = np.dtype(f"M8[{unit}]")
+        vals = np.arange(n, dtype=np.int64).view(dtype)
+        ex_vals = vals.astype("datetime64[ns]")
+
+        df = DataFrame({"ints": np.arange(n)}, index=np.arange(n))
+        df["dates"] = np.arange(n, dtype=np.int64).view("M8[ns]")
+
+        # We overwrite existing dt64 column with new, non-nano dt64 vals
+        df["dates"] = vals
+        assert (df["dates"].values == ex_vals).all()
+
     def test_setitem_dt64tz(self, timezone_frame):
 
         df = timezone_frame

pandas/tests/frame/test_add_prefix_suffix.py renamed to pandas/tests/frame/methods/test_add_prefix_suffix.py

@@ -71,6 +71,15 @@ def test_reset_index_tz(self, tz_aware_fixture):
         expected["idx"] = expected["idx"].apply(lambda d: Timestamp(d, tz=tz))
         tm.assert_frame_equal(df.reset_index(), expected)
 
+    @pytest.mark.parametrize("tz", ["US/Eastern", "dateutil/US/Eastern"])
+    def test_frame_reset_index_tzaware_index(self, tz):
+        dr = date_range("2012-06-02", periods=10, tz=tz)
+        df = DataFrame(np.random.randn(len(dr)), dr)
+        roundtripped = df.reset_index().set_index("index")
+        xp = df.index.tz
+        rs = roundtripped.index.tz
+        assert xp == rs
+
     def test_reset_index_with_intervals(self):
         idx = IntervalIndex.from_breaks(np.arange(11), name="x")
         original = DataFrame({"x": idx, "y": np.arange(10)})[["x", "y"]]

pandas/tests/frame/methods/test_reset_index.py

@@ -1,53 +1,63 @@
 import numpy as np
+import pytest
 
-import pandas as pd
+from pandas import DataFrame, date_range
 import pandas._testing as tm
 
 
 class TestTranspose:
     def test_transpose_tzaware_1col_single_tz(self):
         # GH#26825
-        dti = pd.date_range("2016-04-05 04:30", periods=3, tz="UTC")
+        dti = date_range("2016-04-05 04:30", periods=3, tz="UTC")
 
-        df = pd.DataFrame(dti)
+        df = DataFrame(dti)
         assert (df.dtypes == dti.dtype).all()
         res = df.T
         assert (res.dtypes == dti.dtype).all()
 
     def test_transpose_tzaware_2col_single_tz(self):
         # GH#26825
-        dti = pd.date_range("2016-04-05 04:30", periods=3, tz="UTC")
+        dti = date_range("2016-04-05 04:30", periods=3, tz="UTC")
 
-        df3 = pd.DataFrame({"A": dti, "B": dti})
+        df3 = DataFrame({"A": dti, "B": dti})
         assert (df3.dtypes == dti.dtype).all()
         res3 = df3.T
         assert (res3.dtypes == dti.dtype).all()
 
     def test_transpose_tzaware_2col_mixed_tz(self):
         # GH#26825
-        dti = pd.date_range("2016-04-05 04:30", periods=3, tz="UTC")
+        dti = date_range("2016-04-05 04:30", periods=3, tz="UTC")
         dti2 = dti.tz_convert("US/Pacific")
 
-        df4 = pd.DataFrame({"A": dti, "B": dti2})
+        df4 = DataFrame({"A": dti, "B": dti2})
         assert (df4.dtypes == [dti.dtype, dti2.dtype]).all()
         assert (df4.T.dtypes == object).all()
         tm.assert_frame_equal(df4.T.T, df4)
 
+    @pytest.mark.parametrize("tz", [None, "America/New_York"])
+    def test_transpose_preserves_dtindex_equality_with_dst(self, tz):
+        # GH#19970
+        idx = date_range("20161101", "20161130", freq="4H", tz=tz)
+        df = DataFrame({"a": range(len(idx)), "b": range(len(idx))}, index=idx)
+        result = df.T == df.T
+        expected = DataFrame(True, index=list("ab"), columns=idx)
+        tm.assert_frame_equal(result, expected)
+
     def test_transpose_object_to_tzaware_mixed_tz(self):
         # GH#26825
-        dti = pd.date_range("2016-04-05 04:30", periods=3, tz="UTC")
+        dti = date_range("2016-04-05 04:30", periods=3, tz="UTC")
         dti2 = dti.tz_convert("US/Pacific")
 
         # mixed all-tzaware dtypes
-        df2 = pd.DataFrame([dti, dti2])
+        df2 = DataFrame([dti, dti2])
         assert (df2.dtypes == object).all()
         res2 = df2.T
         assert (res2.dtypes == [dti.dtype, dti2.dtype]).all()
 
     def test_transpose_uint64(self, uint64_frame):
 
         result = uint64_frame.T
-        expected = pd.DataFrame(uint64_frame.values.T)
+        expected = DataFrame(uint64_frame.values.T)
         expected.index = ["A", "B"]
         tm.assert_frame_equal(result, expected)
 
@@ -63,7 +73,7 @@ def test_transpose_float(self, float_frame):
 
         # mixed type
         index, data = tm.getMixedTypeDict()
-        mixed = pd.DataFrame(data, index=index)
+        mixed = DataFrame(data, index=index)
 
         mixed_T = mixed.T
         for col, s in mixed_T.items():

pandas/tests/frame/methods/test_transpose.py

@@ -2737,6 +2737,35 @@ def test_constructor_list_str_na(self, string_dtype):
 
 
 class TestDataFrameConstructorWithDatetimeTZ:
+    @pytest.mark.parametrize("tz", ["US/Eastern", "dateutil/US/Eastern"])
+    def test_construction_preserves_tzaware_dtypes(self, tz):
+        # after GH#7822
+        # these retain the timezones on dict construction
+        dr = date_range("2011/1/1", "2012/1/1", freq="W-FRI")
+        dr_tz = dr.tz_localize(tz)
+        df = DataFrame({"A": "foo", "B": dr_tz}, index=dr)
+        tz_expected = DatetimeTZDtype("ns", dr_tz.tzinfo)
+        assert df["B"].dtype == tz_expected
+
+        # GH#2810 (with timezones)
+        datetimes_naive = [ts.to_pydatetime() for ts in dr]
+        datetimes_with_tz = [ts.to_pydatetime() for ts in dr_tz]
+        df = DataFrame({"dr": dr})
+        df["dr_tz"] = dr_tz
+        df["datetimes_naive"] = datetimes_naive
+        df["datetimes_with_tz"] = datetimes_with_tz
+        result = df.dtypes
+        expected = Series(
+            [
+                np.dtype("datetime64[ns]"),
+                DatetimeTZDtype(tz=tz),
+                np.dtype("datetime64[ns]"),
+                DatetimeTZDtype(tz=tz),
+            ],
+            index=["dr", "dr_tz", "datetimes_naive", "datetimes_with_tz"],
+        )
+        tm.assert_series_equal(result, expected)
+
     def test_constructor_data_aware_dtype_naive(self, tz_aware_fixture):
         # GH#25843
         tz = tz_aware_fixture

pandas/tests/frame/test_constructors.py

@@ -400,29 +400,6 @@ def check(result, expected=None):
         result = z.loc[["a", "c", "a"]]
         check(result, expected)
 
-    def test_column_dups_indexing2(self):
-
-        # GH 8363
-        # datetime ops with a non-unique index
-        df = DataFrame(
-            {"A": np.arange(5, dtype="int64"), "B": np.arange(1, 6, dtype="int64")},
-            index=[2, 2, 3, 3, 4],
-        )
-        result = df.B - df.A
-        expected = Series(1, index=[2, 2, 3, 3, 4])
-        tm.assert_series_equal(result, expected)
-
-        df = DataFrame(
-            {
-                "A": date_range("20130101", periods=5),
-                "B": date_range("20130101 09:00:00", periods=5),
-            },
-            index=[2, 2, 3, 3, 4],
-        )
-        result = df.B - df.A
-        expected = Series(pd.Timedelta("9 hours"), index=[2, 2, 3, 3, 4])
-        tm.assert_series_equal(result, expected)
-
     def test_columns_with_dups(self):
         # GH 3468 related
 

pandas/tests/frame/test_nonunique_indexes.py

@@ -271,6 +271,21 @@ def test_getitem_boolean_different_order(self, string_series):
         exp = string_series[string_series > 0]
         tm.assert_series_equal(sel, exp)
 
+    def test_getitem_boolean_contiguous_preserve_freq(self):
+        rng = date_range("1/1/2000", "3/1/2000", freq="B")
+
+        mask = np.zeros(len(rng), dtype=bool)
+        mask[10:20] = True
+
+        masked = rng[mask]
+        expected = rng[10:20]
+        assert expected.freq == rng.freq
+        tm.assert_index_equal(masked, expected)
+
+        mask[22] = True
+        masked = rng[mask]
+        assert masked.freq is None
+
 
 class TestGetitemCallable:
     def test_getitem_callable(self):

pandas/tests/frame/test_timeseries.py

@@ -0,0 +1,25 @@
+import numpy as np
+
+from pandas import Series, date_range
+
+
+class TestIsMonotonic:
+    def test_is_monotonic_numeric(self):
+
+        ser = Series(np.random.randint(0, 10, size=1000))
+        assert not ser.is_monotonic
+        ser = Series(np.arange(1000))
+        assert ser.is_monotonic is True
+        assert ser.is_monotonic_increasing is True
+        ser = Series(np.arange(1000, 0, -1))
+        assert ser.is_monotonic_decreasing is True
+
+    def test_is_monotonic_dt64(self):
+
+        ser = Series(date_range("20130101", periods=10))
+        assert ser.is_monotonic is True
+        assert ser.is_monotonic_increasing is True
+
+        ser = Series(list(reversed(ser)))
+        assert ser.is_monotonic is False
+        assert ser.is_monotonic_decreasing is True