File size: 9,279 Bytes
9c6594c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 |
"""
This file contains a minimal set of tests for compliance with the extension
array interface test suite, and should contain no other tests.
The test suite for the full functionality of the array is located in
`pandas/tests/arrays/`.
The tests in this file are inherited from the BaseExtensionTests, and only
minimal tweaks should be applied to get the tests passing (by overwriting a
parent method).
Additional tests should either be added to one of the BaseExtensionTests
classes (if they are relevant for the extension interface for all dtypes), or
be added to the array-specific tests in `pandas/tests/arrays/`.
"""
from __future__ import annotations
import string
from typing import cast
import numpy as np
import pytest
from pandas.compat import HAS_PYARROW
from pandas.core.dtypes.base import StorageExtensionDtype
import pandas as pd
import pandas._testing as tm
from pandas.api.types import is_string_dtype
from pandas.core.arrays import ArrowStringArray
from pandas.core.arrays.string_ import StringDtype
from pandas.tests.extension import base
def maybe_split_array(arr, chunked):
if not chunked:
return arr
elif arr.dtype.storage != "pyarrow":
return arr
pa = pytest.importorskip("pyarrow")
arrow_array = arr._pa_array
split = len(arrow_array) // 2
arrow_array = pa.chunked_array(
[*arrow_array[:split].chunks, *arrow_array[split:].chunks]
)
assert arrow_array.num_chunks == 2
return type(arr)(arrow_array)
@pytest.fixture(params=[True, False])
def chunked(request):
return request.param
@pytest.fixture
def dtype(string_dtype_arguments):
storage, na_value = string_dtype_arguments
return StringDtype(storage=storage, na_value=na_value)
@pytest.fixture
def data(dtype, chunked):
strings = np.random.default_rng(2).choice(list(string.ascii_letters), size=100)
while strings[0] == strings[1]:
strings = np.random.default_rng(2).choice(list(string.ascii_letters), size=100)
arr = dtype.construct_array_type()._from_sequence(strings, dtype=dtype)
return maybe_split_array(arr, chunked)
@pytest.fixture
def data_missing(dtype, chunked):
"""Length 2 array with [NA, Valid]"""
arr = dtype.construct_array_type()._from_sequence([pd.NA, "A"], dtype=dtype)
return maybe_split_array(arr, chunked)
@pytest.fixture
def data_for_sorting(dtype, chunked):
arr = dtype.construct_array_type()._from_sequence(["B", "C", "A"], dtype=dtype)
return maybe_split_array(arr, chunked)
@pytest.fixture
def data_missing_for_sorting(dtype, chunked):
arr = dtype.construct_array_type()._from_sequence(["B", pd.NA, "A"], dtype=dtype)
return maybe_split_array(arr, chunked)
@pytest.fixture
def data_for_grouping(dtype, chunked):
arr = dtype.construct_array_type()._from_sequence(
["B", "B", pd.NA, pd.NA, "A", "A", "B", "C"], dtype=dtype
)
return maybe_split_array(arr, chunked)
class TestStringArray(base.ExtensionTests):
def test_eq_with_str(self, dtype):
super().test_eq_with_str(dtype)
if dtype.na_value is pd.NA:
# only the NA-variant supports parametrized string alias
assert dtype == f"string[{dtype.storage}]"
elif dtype.storage == "pyarrow":
with tm.assert_produces_warning(FutureWarning):
assert dtype == "string[pyarrow_numpy]"
def test_is_not_string_type(self, dtype):
# Different from BaseDtypeTests.test_is_not_string_type
# because StringDtype is a string type
assert is_string_dtype(dtype)
def test_is_dtype_from_name(self, dtype, using_infer_string):
if dtype.na_value is np.nan and not using_infer_string:
result = type(dtype).is_dtype(dtype.name)
assert result is False
else:
super().test_is_dtype_from_name(dtype)
def test_construct_from_string_own_name(self, dtype, using_infer_string):
if dtype.na_value is np.nan and not using_infer_string:
with pytest.raises(TypeError, match="Cannot construct a 'StringDtype'"):
dtype.construct_from_string(dtype.name)
else:
super().test_construct_from_string_own_name(dtype)
def test_view(self, data):
if data.dtype.storage == "pyarrow":
pytest.skip(reason="2D support not implemented for ArrowStringArray")
super().test_view(data)
def test_from_dtype(self, data):
# base test uses string representation of dtype
pass
def test_transpose(self, data):
if data.dtype.storage == "pyarrow":
pytest.skip(reason="2D support not implemented for ArrowStringArray")
super().test_transpose(data)
def test_setitem_preserves_views(self, data):
if data.dtype.storage == "pyarrow":
pytest.skip(reason="2D support not implemented for ArrowStringArray")
super().test_setitem_preserves_views(data)
def test_dropna_array(self, data_missing):
result = data_missing.dropna()
expected = data_missing[[1]]
tm.assert_extension_array_equal(result, expected)
def test_fillna_no_op_returns_copy(self, data):
data = data[~data.isna()]
valid = data[0]
result = data.fillna(valid)
assert result is not data
tm.assert_extension_array_equal(result, data)
result = data.fillna(method="backfill")
assert result is not data
tm.assert_extension_array_equal(result, data)
def _get_expected_exception(
self, op_name: str, obj, other
) -> type[Exception] | tuple[type[Exception], ...] | None:
if op_name in [
"__mod__",
"__rmod__",
"__divmod__",
"__rdivmod__",
"__pow__",
"__rpow__",
]:
return TypeError
elif op_name in ["__mul__", "__rmul__"]:
# Can only multiply strings by integers
return TypeError
elif op_name in [
"__truediv__",
"__rtruediv__",
"__floordiv__",
"__rfloordiv__",
"__sub__",
"__rsub__",
]:
return TypeError
return None
def _supports_reduction(self, ser: pd.Series, op_name: str) -> bool:
return (
op_name in ["min", "max", "sum"]
or ser.dtype.na_value is np.nan # type: ignore[union-attr]
and op_name in ("any", "all")
)
def _supports_accumulation(self, ser: pd.Series, op_name: str) -> bool:
assert isinstance(ser.dtype, StorageExtensionDtype)
return op_name in ["cummin", "cummax", "cumsum"]
def _cast_pointwise_result(self, op_name: str, obj, other, pointwise_result):
dtype = cast(StringDtype, tm.get_dtype(obj))
if op_name in ["__add__", "__radd__"]:
cast_to = dtype
elif dtype.na_value is np.nan:
cast_to = np.bool_ # type: ignore[assignment]
elif dtype.storage == "pyarrow":
cast_to = "boolean[pyarrow]" # type: ignore[assignment]
else:
cast_to = "boolean" # type: ignore[assignment]
return pointwise_result.astype(cast_to)
def test_compare_scalar(self, data, comparison_op):
ser = pd.Series(data)
self._compare_other(ser, data, comparison_op, "abc")
def test_combine_add(self, data_repeated, using_infer_string, request):
dtype = next(data_repeated(1)).dtype
if using_infer_string and (
(dtype.na_value is pd.NA) and dtype.storage == "python"
):
mark = pytest.mark.xfail(
reason="The pointwise operation result will be inferred to "
"string[nan, pyarrow], which does not match the input dtype"
)
request.applymarker(mark)
super().test_combine_add(data_repeated)
def test_arith_series_with_array(
self, data, all_arithmetic_operators, using_infer_string, request
):
dtype = data.dtype
if (
using_infer_string
and all_arithmetic_operators == "__radd__"
and (
(dtype.na_value is pd.NA) or (dtype.storage == "python" and HAS_PYARROW)
)
):
mark = pytest.mark.xfail(
reason="The pointwise operation result will be inferred to "
"string[nan, pyarrow], which does not match the input dtype"
)
request.applymarker(mark)
super().test_arith_series_with_array(data, all_arithmetic_operators)
class Test2DCompat(base.Dim2CompatTests):
@pytest.fixture(autouse=True)
def arrow_not_supported(self, data):
if isinstance(data, ArrowStringArray):
pytest.skip(reason="2D support not implemented for ArrowStringArray")
def test_searchsorted_with_na_raises(data_for_sorting, as_series):
# GH50447
b, c, a = data_for_sorting
arr = data_for_sorting.take([2, 0, 1]) # to get [a, b, c]
arr[-1] = pd.NA
if as_series:
arr = pd.Series(arr)
msg = (
"searchsorted requires array to be sorted, "
"which is impossible with NAs present."
)
with pytest.raises(ValueError, match=msg):
arr.searchsorted(b)
|