From 124680934378fa4208c3c1fba5991f1d9683ffd9 Mon Sep 17 00:00:00 2001 From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com> Date: Mon, 9 Oct 2023 12:39:48 -1000 Subject: [PATCH] Backport PR #55460: COMPAT: Update old numpy aliases --- pandas/io/stata.py | 2 +- pandas/tests/frame/constructors/test_from_records.py | 2 +- pandas/tests/frame/methods/test_select_dtypes.py | 4 +--- pandas/tests/frame/methods/test_to_records.py | 2 +- pandas/tests/indexes/base_class/test_setops.py | 10 +++++----- pandas/tests/io/json/test_pandas.py | 2 +- pandas/tests/reshape/concat/test_append.py | 4 ++-- pandas/tests/series/methods/test_astype.py | 4 ++-- 8 files changed, 14 insertions(+), 16 deletions(-) diff --git a/pandas/io/stata.py b/pandas/io/stata.py index 5b190619c4ac3..0a02da09c9e15 100644 --- a/pandas/io/stata.py +++ b/pandas/io/stata.py @@ -977,7 +977,7 @@ def __init__(self) -> None: # with a label, but the underlying variable is -127 to 100 # we're going to drop the label and cast to int self.DTYPE_MAP = dict( - list(zip(range(1, 245), [np.dtype("a" + str(i)) for i in range(1, 245)])) + [(i, np.dtype(f"S{i}")) for i in range(1, 245)] + [ (251, np.dtype(np.int8)), (252, np.dtype(np.int16)), diff --git a/pandas/tests/frame/constructors/test_from_records.py b/pandas/tests/frame/constructors/test_from_records.py index 7dffa7bb242d5..55d4a6c3b39fa 100644 --- a/pandas/tests/frame/constructors/test_from_records.py +++ b/pandas/tests/frame/constructors/test_from_records.py @@ -281,7 +281,7 @@ def test_frame_from_records_utc(self): def test_from_records_to_records(self): # from numpy documentation - arr = np.zeros((2,), dtype=("i4,f4,a10")) + arr = np.zeros((2,), dtype=("i4,f4,S10")) arr[:] = [(1, 2.0, "Hello"), (2, 3.0, "World")] DataFrame.from_records(arr) diff --git a/pandas/tests/frame/methods/test_select_dtypes.py b/pandas/tests/frame/methods/test_select_dtypes.py index 67dd5b6217187..a38d2c6fd016a 100644 --- a/pandas/tests/frame/methods/test_select_dtypes.py +++ b/pandas/tests/frame/methods/test_select_dtypes.py @@ -339,9 +339,7 @@ def test_select_dtypes_datetime_with_tz(self): expected = df3.reindex(columns=[]) tm.assert_frame_equal(result, expected) - @pytest.mark.parametrize( - "dtype", [str, "str", np.bytes_, "S1", "unicode", np.str_, "U1"] - ) + @pytest.mark.parametrize("dtype", [str, "str", np.bytes_, "S1", np.str_, "U1"]) @pytest.mark.parametrize("arg", ["include", "exclude"]) def test_select_dtypes_str_raises(self, dtype, arg): df = DataFrame( diff --git a/pandas/tests/frame/methods/test_to_records.py b/pandas/tests/frame/methods/test_to_records.py index 7df52a1fb903f..27939856503e5 100644 --- a/pandas/tests/frame/methods/test_to_records.py +++ b/pandas/tests/frame/methods/test_to_records.py @@ -253,7 +253,7 @@ def test_to_records_with_categorical(self): ), # Pass in a dtype instance. ( - {"column_dtypes": np.dtype("unicode")}, + {"column_dtypes": np.dtype(np.str_)}, np.rec.array( [("0", "1", "0.2", "a"), ("1", "2", "1.5", "bc")], dtype=[ diff --git a/pandas/tests/indexes/base_class/test_setops.py b/pandas/tests/indexes/base_class/test_setops.py index 21d1630af9de2..488f79eea0d11 100644 --- a/pandas/tests/indexes/base_class/test_setops.py +++ b/pandas/tests/indexes/base_class/test_setops.py @@ -182,7 +182,7 @@ def test_symmetric_difference(self): "intersection", np.array( [(1, "A"), (2, "A"), (1, "B"), (2, "B")], - dtype=[("num", int), ("let", "a1")], + dtype=[("num", int), ("let", "S1")], ), False, ), @@ -190,7 +190,7 @@ def test_symmetric_difference(self): "intersection", np.array( [(1, "A"), (1, "B"), (2, "A"), (2, "B")], - dtype=[("num", int), ("let", "a1")], + dtype=[("num", int), ("let", "S1")], ), None, ), @@ -198,7 +198,7 @@ def test_symmetric_difference(self): "union", np.array( [(1, "A"), (1, "B"), (1, "C"), (2, "A"), (2, "B"), (2, "C")], - dtype=[("num", int), ("let", "a1")], + dtype=[("num", int), ("let", "S1")], ), None, ), @@ -208,13 +208,13 @@ def test_tuple_union_bug(self, method, expected, sort): index1 = Index( np.array( [(1, "A"), (2, "A"), (1, "B"), (2, "B")], - dtype=[("num", int), ("let", "a1")], + dtype=[("num", int), ("let", "S1")], ) ) index2 = Index( np.array( [(1, "A"), (2, "A"), (1, "B"), (2, "B"), (1, "C"), (2, "C")], - dtype=[("num", int), ("let", "a1")], + dtype=[("num", int), ("let", "S1")], ) ) diff --git a/pandas/tests/io/json/test_pandas.py b/pandas/tests/io/json/test_pandas.py index 437012d836941..663d0a195fa55 100644 --- a/pandas/tests/io/json/test_pandas.py +++ b/pandas/tests/io/json/test_pandas.py @@ -599,7 +599,7 @@ def test_blocks_compat_GH9037(self): ) # JSON deserialisation always creates unicode strings - df_mixed.columns = df_mixed.columns.astype("unicode") + df_mixed.columns = df_mixed.columns.astype(np.str_) data = StringIO(df_mixed.to_json(orient="split")) df_roundtrip = read_json(data, orient="split") tm.assert_frame_equal( diff --git a/pandas/tests/reshape/concat/test_append.py b/pandas/tests/reshape/concat/test_append.py index 386f363c81557..81ca227fb7afb 100644 --- a/pandas/tests/reshape/concat/test_append.py +++ b/pandas/tests/reshape/concat/test_append.py @@ -91,10 +91,10 @@ def test_append_length0_frame(self, sort): tm.assert_frame_equal(df5, expected) def test_append_records(self): - arr1 = np.zeros((2,), dtype=("i4,f4,a10")) + arr1 = np.zeros((2,), dtype=("i4,f4,S10")) arr1[:] = [(1, 2.0, "Hello"), (2, 3.0, "World")] - arr2 = np.zeros((3,), dtype=("i4,f4,a10")) + arr2 = np.zeros((3,), dtype=("i4,f4,S10")) arr2[:] = [(3, 4.0, "foo"), (5, 6.0, "bar"), (7.0, 8.0, "baz")] df1 = DataFrame(arr1) diff --git a/pandas/tests/series/methods/test_astype.py b/pandas/tests/series/methods/test_astype.py index b6c409397c9fb..03fc6cba2902a 100644 --- a/pandas/tests/series/methods/test_astype.py +++ b/pandas/tests/series/methods/test_astype.py @@ -403,12 +403,12 @@ def test_astype_unicode(self): # bytes with obj.decode() instead of str(obj) item = "野菜食べないとやばい" ser = Series([item.encode()]) - result = ser.astype("unicode") + result = ser.astype(np.str_) expected = Series([item]) tm.assert_series_equal(result, expected) for ser in test_series: - res = ser.astype("unicode") + res = ser.astype(np.str_) expec = ser.map(str) tm.assert_series_equal(res, expec)