def test_to_integer_array_dtype_keyword(constructor):
result = constructor([1, 2], dtype="Int8")
assert result.dtype == Int8Dtype()
# if values has dtype -> override it
result = constructor(np.array([1, 2], dtype="int8"), dtype="Int32")
assert result.dtype == Int32Dtype()
def test_to_integer_array_dtype_keyword():
result = integer_array([1, 2], dtype='int8')
assert result.dtype == Int8Dtype()
# if values has dtype -> override it
result = integer_array(np.array([1, 2], dtype='int8'), dtype='int32')
assert result.dtype == Int32Dtype()
def test_to_integer_array_inferred_dtype():
# if values has dtype -> respect it
result = integer_array(np.array([1, 2], dtype='int8'))
assert result.dtype == Int8Dtype()
result = integer_array(np.array([1, 2], dtype='int32'))
assert result.dtype == Int32Dtype()
# if values have no dtype -> always int64
result = integer_array([1, 2])
assert result.dtype == Int64Dtype()
def test_to_integer_array_inferred_dtype(constructor):
# if values has dtype -> respect it
result = constructor(np.array([1, 2], dtype="int8"))
assert result.dtype == Int8Dtype()
result = constructor(np.array([1, 2], dtype="int32"))
assert result.dtype == Int32Dtype()
# if values have no dtype -> always int64
result = constructor([1, 2])
assert result.dtype == Int64Dtype()
def test_astype(self, all_data):
all_data = all_data[:10]
ints = all_data[~all_data.isna()]
mixed = all_data
dtype = Int8Dtype()
# coerce to same type - ints
s = pd.Series(ints)
result = s.astype(all_data.dtype)
expected = pd.Series(ints)
tm.assert_series_equal(result, expected)
# coerce to same other - ints
s = pd.Series(ints)
result = s.astype(dtype)
expected = pd.Series(ints, dtype=dtype)
tm.assert_series_equal(result, expected)
# coerce to same numpy_dtype - ints
s = pd.Series(ints)
result = s.astype(all_data.dtype.numpy_dtype)
expected = pd.Series(ints._data.astype(
all_data.dtype.numpy_dtype))
tm.assert_series_equal(result, expected)
# coerce to same type - mixed
s = pd.Series(mixed)
result = s.astype(all_data.dtype)
expected = pd.Series(mixed)
tm.assert_series_equal(result, expected)
# coerce to same other - mixed
s = pd.Series(mixed)
result = s.astype(dtype)
expected = pd.Series(mixed, dtype=dtype)
tm.assert_series_equal(result, expected)
# coerce to same numpy_dtype - mixed
s = pd.Series(mixed)
with pytest.raises(ValueError):
s.astype(all_data.dtype.numpy_dtype)
# coerce to object
s = pd.Series(mixed)
result = s.astype('object')
expected = pd.Series(np.asarray(mixed))
tm.assert_series_equal(result, expected)
def test_astype(all_data):
all_data = all_data[:10]
ints = all_data[~all_data.isna()]
mixed = all_data
dtype = Int8Dtype()
# coerce to same type - ints
s = pd.Series(ints)
result = s.astype(all_data.dtype)
expected = pd.Series(ints)
tm.assert_series_equal(result, expected)
# coerce to same other - ints
s = pd.Series(ints)
result = s.astype(dtype)
expected = pd.Series(ints, dtype=dtype)
tm.assert_series_equal(result, expected)
# coerce to same numpy_dtype - ints
s = pd.Series(ints)
result = s.astype(all_data.dtype.numpy_dtype)
expected = pd.Series(ints._data.astype(all_data.dtype.numpy_dtype))
tm.assert_series_equal(result, expected)
# coerce to same type - mixed
s = pd.Series(mixed)
result = s.astype(all_data.dtype)
expected = pd.Series(mixed)
tm.assert_series_equal(result, expected)
# coerce to same other - mixed
s = pd.Series(mixed)
result = s.astype(dtype)
expected = pd.Series(mixed, dtype=dtype)
tm.assert_series_equal(result, expected)
# coerce to same numpy_dtype - mixed
s = pd.Series(mixed)
msg = r"cannot convert to .*-dtype NumPy array with missing values.*"
with pytest.raises(ValueError, match=msg):
s.astype(all_data.dtype.numpy_dtype)
# coerce to object
s = pd.Series(mixed)
result = s.astype("object")
expected = pd.Series(np.asarray(mixed))
tm.assert_series_equal(result, expected)
class TestCasting(object):
pass
@pytest.mark.parametrize('dropna', [True, False])
def test_construct_index(self, all_data, dropna):
# ensure that we do not coerce to Float64Index, rather
# keep as Index
all_data = all_data[:10]
if dropna:
other = np.array(all_data[~all_data.isna()])
else:
other = all_data
result = pd.Index(integer_array(other, dtype=all_data.dtype))
expected = pd.Index(other, dtype=object)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize('dropna', [True, False])
def test_astype_index(self, all_data, dropna):
# as an int/uint index to Index
all_data = all_data[:10]
if dropna:
other = all_data[~all_data.isna()]
else:
other = all_data
dtype = all_data.dtype
idx = pd.Index(np.array(other))
assert isinstance(idx, ABCIndexClass)
result = idx.astype(dtype)
expected = idx.astype(object).astype(dtype)
tm.assert_index_equal(result, expected)
def test_astype(self, all_data):
all_data = all_data[:10]
ints = all_data[~all_data.isna()]
mixed = all_data
dtype = Int8Dtype()
# coerce to same type - ints
s = pd.Series(ints)
result = s.astype(all_data.dtype)
expected = pd.Series(ints)
tm.assert_series_equal(result, expected)
# coerce to same other - ints
s = pd.Series(ints)
result = s.astype(dtype)
expected = pd.Series(ints, dtype=dtype)
tm.assert_series_equal(result, expected)
# coerce to same numpy_dtype - ints
s = pd.Series(ints)
result = s.astype(all_data.dtype.numpy_dtype)
expected = pd.Series(ints._data.astype(all_data.dtype.numpy_dtype))
tm.assert_series_equal(result, expected)
# coerce to same type - mixed
s = pd.Series(mixed)
result = s.astype(all_data.dtype)
expected = pd.Series(mixed)
tm.assert_series_equal(result, expected)
# coerce to same other - mixed
s = pd.Series(mixed)
result = s.astype(dtype)
expected = pd.Series(mixed, dtype=dtype)
tm.assert_series_equal(result, expected)
# coerce to same numpy_dtype - mixed
s = pd.Series(mixed)
with pytest.raises(ValueError):
s.astype(all_data.dtype.numpy_dtype)
# coerce to object
s = pd.Series(mixed)
result = s.astype('object')
expected = pd.Series(np.asarray(mixed))
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize(
'dtype',
[Int8Dtype(), 'Int8', UInt32Dtype(), 'UInt32'])
def test_astype_specific_casting(self, dtype):
s = pd.Series([1, 2, 3], dtype='Int64')
result = s.astype(dtype)
expected = pd.Series([1, 2, 3], dtype=dtype)
tm.assert_series_equal(result, expected)
s = pd.Series([1, 2, 3, None], dtype='Int64')
result = s.astype(dtype)
expected = pd.Series([1, 2, 3, None], dtype=dtype)
tm.assert_series_equal(result, expected)
def test_construct_cast_invalid(self, dtype):
msg = "cannot safely"
arr = [1.2, 2.3, 3.7]
with pytest.raises(TypeError, match=msg):
integer_array(arr, dtype=dtype)
with pytest.raises(TypeError, match=msg):
pd.Series(arr).astype(dtype)
arr = [1.2, 2.3, 3.7, np.nan]
with pytest.raises(TypeError, match=msg):
integer_array(arr, dtype=dtype)
with pytest.raises(TypeError, match=msg):
pd.Series(arr).astype(dtype)
def test_dtypes(dtype):
# smoke tests on auto dtype construction
if dtype.is_signed_integer:
assert np.dtype(dtype.type).kind == "i"
else:
assert np.dtype(dtype.type).kind == "u"
assert dtype.name is not None
@pytest.mark.parametrize(
"dtype, expected",
[
(Int8Dtype(), "Int8Dtype()"),
(Int16Dtype(), "Int16Dtype()"),
(Int32Dtype(), "Int32Dtype()"),
(Int64Dtype(), "Int64Dtype()"),
(UInt8Dtype(), "UInt8Dtype()"),
(UInt16Dtype(), "UInt16Dtype()"),
(UInt32Dtype(), "UInt32Dtype()"),
(UInt64Dtype(), "UInt64Dtype()"),
],
)
def test_repr_dtype(dtype, expected):
assert repr(dtype) == expected
def test_repr_array():
result = repr(integer_array([1, None, 3]))
def test_astype_to_larger_numpy():
a = pd.array([1, 2], dtype="Int32")
result = a.astype("int64")
expected = np.array([1, 2], dtype="int64")
tm.assert_numpy_array_equal(result, expected)
a = pd.array([1, 2], dtype="UInt32")
result = a.astype("uint64")
expected = np.array([1, 2], dtype="uint64")
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"dtype",
[Int8Dtype(), "Int8", UInt32Dtype(), "UInt32"])
def test_astype_specific_casting(dtype):
s = pd.Series([1, 2, 3], dtype="Int64")
result = s.astype(dtype)
expected = pd.Series([1, 2, 3], dtype=dtype)
tm.assert_series_equal(result, expected)
s = pd.Series([1, 2, 3, None], dtype="Int64")
result = s.astype(dtype)
expected = pd.Series([1, 2, 3, None], dtype=dtype)
tm.assert_series_equal(result, expected)
def test_astype_floating():
arr = pd.array([1, 2, None], dtype="Int64")
result = arr.astype("Float64")
elif request.param == 'data_missing':
return data_missing
def test_dtypes(dtype):
# smoke tests on auto dtype construction
if dtype.is_signed_integer:
assert np.dtype(dtype.type).kind == 'i'
else:
assert np.dtype(dtype.type).kind == 'u'
assert dtype.name is not None
@pytest.mark.parametrize('dtype, expected', [
(Int8Dtype(), 'Int8Dtype()'),
(Int16Dtype(), 'Int16Dtype()'),
(Int32Dtype(), 'Int32Dtype()'),
(Int64Dtype(), 'Int64Dtype()'),
(UInt8Dtype(), 'UInt8Dtype()'),
(UInt16Dtype(), 'UInt16Dtype()'),
(UInt32Dtype(), 'UInt32Dtype()'),
(UInt64Dtype(), 'UInt64Dtype()'),
])
def test_repr_dtype(dtype, expected):
assert repr(dtype) == expected
def test_repr_array():
result = repr(integer_array([1, None, 3]))
expected = (
class TestCasting:
@pytest.mark.parametrize("dropna", [True, False])
def test_construct_index(self, all_data, dropna):
# ensure that we do not coerce to Float64Index, rather
# keep as Index
all_data = all_data[:10]
if dropna:
other = np.array(all_data[~all_data.isna()])
else:
other = all_data
result = pd.Index(integer_array(other, dtype=all_data.dtype))
expected = pd.Index(other, dtype=object)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize("dropna", [True, False])
def test_astype_index(self, all_data, dropna):
# as an int/uint index to Index
all_data = all_data[:10]
if dropna:
other = all_data[~all_data.isna()]
else:
other = all_data
dtype = all_data.dtype
idx = pd.Index(np.array(other))
assert isinstance(idx, ABCIndexClass)
result = idx.astype(dtype)
expected = idx.astype(object).astype(dtype)
tm.assert_index_equal(result, expected)
def test_astype(self, all_data):
all_data = all_data[:10]
ints = all_data[~all_data.isna()]
mixed = all_data
dtype = Int8Dtype()
# coerce to same type - ints
s = pd.Series(ints)
result = s.astype(all_data.dtype)
expected = pd.Series(ints)
tm.assert_series_equal(result, expected)
# coerce to same other - ints
s = pd.Series(ints)
result = s.astype(dtype)
expected = pd.Series(ints, dtype=dtype)
tm.assert_series_equal(result, expected)
# coerce to same numpy_dtype - ints
s = pd.Series(ints)
result = s.astype(all_data.dtype.numpy_dtype)
expected = pd.Series(ints._data.astype(all_data.dtype.numpy_dtype))
tm.assert_series_equal(result, expected)
# coerce to same type - mixed
s = pd.Series(mixed)
result = s.astype(all_data.dtype)
expected = pd.Series(mixed)
tm.assert_series_equal(result, expected)
# coerce to same other - mixed
s = pd.Series(mixed)
result = s.astype(dtype)
expected = pd.Series(mixed, dtype=dtype)
tm.assert_series_equal(result, expected)
# coerce to same numpy_dtype - mixed
s = pd.Series(mixed)
msg = r"cannot convert to .*-dtype NumPy array with missing values.*"
with pytest.raises(ValueError, match=msg):
s.astype(all_data.dtype.numpy_dtype)
# coerce to object
s = pd.Series(mixed)
result = s.astype("object")
expected = pd.Series(np.asarray(mixed))
tm.assert_series_equal(result, expected)
def test_astype_to_larger_numpy(self):
a = pd.array([1, 2], dtype="Int32")
result = a.astype("int64")
expected = np.array([1, 2], dtype="int64")
tm.assert_numpy_array_equal(result, expected)
a = pd.array([1, 2], dtype="UInt32")
result = a.astype("uint64")
expected = np.array([1, 2], dtype="uint64")
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"dtype",
[Int8Dtype(), "Int8", UInt32Dtype(), "UInt32"])
def test_astype_specific_casting(self, dtype):
s = pd.Series([1, 2, 3], dtype="Int64")
result = s.astype(dtype)
expected = pd.Series([1, 2, 3], dtype=dtype)
tm.assert_series_equal(result, expected)
s = pd.Series([1, 2, 3, None], dtype="Int64")
result = s.astype(dtype)
expected = pd.Series([1, 2, 3, None], dtype=dtype)
tm.assert_series_equal(result, expected)
def test_construct_cast_invalid(self, dtype):
msg = "cannot safely"
arr = [1.2, 2.3, 3.7]
with pytest.raises(TypeError, match=msg):
integer_array(arr, dtype=dtype)
with pytest.raises(TypeError, match=msg):
pd.Series(arr).astype(dtype)
arr = [1.2, 2.3, 3.7, np.nan]
with pytest.raises(TypeError, match=msg):
integer_array(arr, dtype=dtype)
with pytest.raises(TypeError, match=msg):
pd.Series(arr).astype(dtype)
@pytest.mark.parametrize("in_series", [True, False])
def test_to_numpy_na_nan(self, in_series):
a = pd.array([0, 1, None], dtype="Int64")
if in_series:
a = pd.Series(a)
result = a.to_numpy(dtype="float64", na_value=np.nan)
expected = np.array([0.0, 1.0, np.nan], dtype="float64")
tm.assert_numpy_array_equal(result, expected)
result = a.to_numpy(dtype="int64", na_value=-1)
expected = np.array([0, 1, -1], dtype="int64")
tm.assert_numpy_array_equal(result, expected)
result = a.to_numpy(dtype="bool", na_value=False)
expected = np.array([False, True, False], dtype="bool")
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize("in_series", [True, False])
@pytest.mark.parametrize("dtype", ["int32", "int64", "bool"])
def test_to_numpy_dtype(self, dtype, in_series):
a = pd.array([0, 1], dtype="Int64")
if in_series:
a = pd.Series(a)
result = a.to_numpy(dtype=dtype)
expected = np.array([0, 1], dtype=dtype)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize("dtype", ["float64", "int64", "bool"])
def test_to_numpy_na_raises(self, dtype):
a = pd.array([0, 1, None], dtype="Int64")
with pytest.raises(ValueError, match=dtype):
a.to_numpy(dtype=dtype)
def test_astype_str(self):
a = pd.array([1, 2, None], dtype="Int64")
expected = np.array(["1", "2", "<NA>"], dtype=object)
tm.assert_numpy_array_equal(a.astype(str), expected)
tm.assert_numpy_array_equal(a.astype("str"), expected)
def test_astype_boolean(self):
# https://github.com/pandas-dev/pandas/issues/31102
a = pd.array([1, 0, -1, 2, None], dtype="Int64")
result = a.astype("boolean")
expected = pd.array([True, False, True, True, None], dtype="boolean")
tm.assert_extension_array_equal(result, expected)
tm.assert_series_equal(result, expected)
def test_astype_to_larger_numpy():
a = pd.array([1, 2], dtype="Int32")
result = a.astype("int64")
expected = np.array([1, 2], dtype="int64")
tm.assert_numpy_array_equal(result, expected)
a = pd.array([1, 2], dtype="UInt32")
result = a.astype("uint64")
expected = np.array([1, 2], dtype="uint64")
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize("dtype", [Int8Dtype(), "Int8", UInt32Dtype(), "UInt32"])
def test_astype_specific_casting(dtype):
s = pd.Series([1, 2, 3], dtype="Int64")
result = s.astype(dtype)
expected = pd.Series([1, 2, 3], dtype=dtype)
tm.assert_series_equal(result, expected)
s = pd.Series([1, 2, 3, None], dtype="Int64")
result = s.astype(dtype)
expected = pd.Series([1, 2, 3, None], dtype=dtype)
tm.assert_series_equal(result, expected)
def test_astype_dt64():
# GH#32435
arr = pd.array([1, 2, 3, pd.NA]) * 10 ** 9
class TestCasting:
@pytest.mark.parametrize("dropna", [True, False])
def test_construct_index(self, all_data, dropna):
# ensure that we do not coerce to Float64Index, rather
# keep as Index
all_data = all_data[:10]
if dropna:
other = np.array(all_data[~all_data.isna()])
else:
other = all_data
result = pd.Index(integer_array(other, dtype=all_data.dtype))
expected = pd.Index(other, dtype=object)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize("dropna", [True, False])
def test_astype_index(self, all_data, dropna):
# as an int/uint index to Index
all_data = all_data[:10]
if dropna:
other = all_data[~all_data.isna()]
else:
other = all_data
dtype = all_data.dtype
idx = pd.Index(np.array(other))
assert isinstance(idx, ABCIndexClass)
result = idx.astype(dtype)
expected = idx.astype(object).astype(dtype)
tm.assert_index_equal(result, expected)
def test_astype(self, all_data):
all_data = all_data[:10]
ints = all_data[~all_data.isna()]
mixed = all_data
dtype = Int8Dtype()
# coerce to same type - ints
s = pd.Series(ints)
result = s.astype(all_data.dtype)
expected = pd.Series(ints)
tm.assert_series_equal(result, expected)
# coerce to same other - ints
s = pd.Series(ints)
result = s.astype(dtype)
expected = pd.Series(ints, dtype=dtype)
tm.assert_series_equal(result, expected)
# coerce to same numpy_dtype - ints
s = pd.Series(ints)
result = s.astype(all_data.dtype.numpy_dtype)
expected = pd.Series(ints._data.astype(all_data.dtype.numpy_dtype))
tm.assert_series_equal(result, expected)
# coerce to same type - mixed
s = pd.Series(mixed)
result = s.astype(all_data.dtype)
expected = pd.Series(mixed)
tm.assert_series_equal(result, expected)
# coerce to same other - mixed
s = pd.Series(mixed)
result = s.astype(dtype)
expected = pd.Series(mixed, dtype=dtype)
tm.assert_series_equal(result, expected)
# coerce to same numpy_dtype - mixed
s = pd.Series(mixed)
with pytest.raises(ValueError):
s.astype(all_data.dtype.numpy_dtype)
# coerce to object
s = pd.Series(mixed)
result = s.astype("object")
expected = pd.Series(np.asarray(mixed))
tm.assert_series_equal(result, expected)
def test_astype_to_larger_numpy(self):
a = pd.array([1, 2], dtype="Int32")
result = a.astype("int64")
expected = np.array([1, 2], dtype="int64")
tm.assert_numpy_array_equal(result, expected)
a = pd.array([1, 2], dtype="UInt32")
result = a.astype("uint64")
expected = np.array([1, 2], dtype="uint64")
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"dtype",
[Int8Dtype(), "Int8", UInt32Dtype(), "UInt32"])
def test_astype_specific_casting(self, dtype):
s = pd.Series([1, 2, 3], dtype="Int64")
result = s.astype(dtype)
expected = pd.Series([1, 2, 3], dtype=dtype)
tm.assert_series_equal(result, expected)
s = pd.Series([1, 2, 3, None], dtype="Int64")
result = s.astype(dtype)
expected = pd.Series([1, 2, 3, None], dtype=dtype)
tm.assert_series_equal(result, expected)
def test_construct_cast_invalid(self, dtype):
msg = "cannot safely"
arr = [1.2, 2.3, 3.7]
with pytest.raises(TypeError, match=msg):
integer_array(arr, dtype=dtype)
with pytest.raises(TypeError, match=msg):
pd.Series(arr).astype(dtype)
arr = [1.2, 2.3, 3.7, np.nan]
with pytest.raises(TypeError, match=msg):
integer_array(arr, dtype=dtype)
with pytest.raises(TypeError, match=msg):
pd.Series(arr).astype(dtype)
def test_coerce_to_ndarray_float_NA_rasies(self):
a = pd.array([0, 1, 2], dtype="Int64")
with pytest.raises(TypeError, match="NAType"):
a._coerce_to_ndarray(dtype="float", na_value=pd.NA)
