File size: 15,075 Bytes
7885a28 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 |
import numpy as np
import pytest
import pandas as pd
import pandas._testing as tm
class BaseSetitemTests:
@pytest.fixture(
params=[
lambda x: x.index,
lambda x: list(x.index),
lambda x: slice(None),
lambda x: slice(0, len(x)),
lambda x: range(len(x)),
lambda x: list(range(len(x))),
lambda x: np.ones(len(x), dtype=bool),
],
ids=[
"index",
"list[index]",
"null_slice",
"full_slice",
"range",
"list(range)",
"mask",
],
)
def full_indexer(self, request):
"""
Fixture for an indexer to pass to obj.loc to get/set the full length of the
object.
In some cases, assumes that obj.index is the default RangeIndex.
"""
return request.param
@pytest.fixture(autouse=True)
def skip_if_immutable(self, dtype, request):
if dtype._is_immutable:
node = request.node
if node.name.split("[")[0] == "test_is_immutable":
# This fixture is auto-used, but we want to not-skip
# test_is_immutable.
return
# When BaseSetitemTests is mixed into ExtensionTests, we only
# want this fixture to operate on the tests defined in this
# class/file.
defined_in = node.function.__qualname__.split(".")[0]
if defined_in == "BaseSetitemTests":
pytest.skip("__setitem__ test not applicable with immutable dtype")
def test_is_immutable(self, data):
if data.dtype._is_immutable:
with pytest.raises(TypeError):
data[0] = data[0]
else:
data[0] = data[1]
assert data[0] == data[1]
def test_setitem_scalar_series(self, data, box_in_series):
if box_in_series:
data = pd.Series(data)
data[0] = data[1]
assert data[0] == data[1]
def test_setitem_sequence(self, data, box_in_series):
if box_in_series:
data = pd.Series(data)
original = data.copy()
data[[0, 1]] = [data[1], data[0]]
assert data[0] == original[1]
assert data[1] == original[0]
def test_setitem_sequence_mismatched_length_raises(self, data, as_array):
ser = pd.Series(data)
original = ser.copy()
value = [data[0]]
if as_array:
value = data._from_sequence(value, dtype=data.dtype)
xpr = "cannot set using a {} indexer with a different length"
with pytest.raises(ValueError, match=xpr.format("list-like")):
ser[[0, 1]] = value
# Ensure no modifications made before the exception
tm.assert_series_equal(ser, original)
with pytest.raises(ValueError, match=xpr.format("slice")):
ser[slice(3)] = value
tm.assert_series_equal(ser, original)
def test_setitem_empty_indexer(self, data, box_in_series):
if box_in_series:
data = pd.Series(data)
original = data.copy()
data[np.array([], dtype=int)] = []
tm.assert_equal(data, original)
def test_setitem_sequence_broadcasts(self, data, box_in_series):
if box_in_series:
data = pd.Series(data)
data[[0, 1]] = data[2]
assert data[0] == data[2]
assert data[1] == data[2]
@pytest.mark.parametrize("setter", ["loc", "iloc"])
def test_setitem_scalar(self, data, setter):
arr = pd.Series(data)
setter = getattr(arr, setter)
setter[0] = data[1]
assert arr[0] == data[1]
def test_setitem_loc_scalar_mixed(self, data):
df = pd.DataFrame({"A": np.arange(len(data)), "B": data})
df.loc[0, "B"] = data[1]
assert df.loc[0, "B"] == data[1]
def test_setitem_loc_scalar_single(self, data):
df = pd.DataFrame({"B": data})
df.loc[10, "B"] = data[1]
assert df.loc[10, "B"] == data[1]
def test_setitem_loc_scalar_multiple_homogoneous(self, data):
df = pd.DataFrame({"A": data, "B": data})
df.loc[10, "B"] = data[1]
assert df.loc[10, "B"] == data[1]
def test_setitem_iloc_scalar_mixed(self, data):
df = pd.DataFrame({"A": np.arange(len(data)), "B": data})
df.iloc[0, 1] = data[1]
assert df.loc[0, "B"] == data[1]
def test_setitem_iloc_scalar_single(self, data):
df = pd.DataFrame({"B": data})
df.iloc[10, 0] = data[1]
assert df.loc[10, "B"] == data[1]
def test_setitem_iloc_scalar_multiple_homogoneous(self, data):
df = pd.DataFrame({"A": data, "B": data})
df.iloc[10, 1] = data[1]
assert df.loc[10, "B"] == data[1]
@pytest.mark.parametrize(
"mask",
[
np.array([True, True, True, False, False]),
pd.array([True, True, True, False, False], dtype="boolean"),
pd.array([True, True, True, pd.NA, pd.NA], dtype="boolean"),
],
ids=["numpy-array", "boolean-array", "boolean-array-na"],
)
def test_setitem_mask(self, data, mask, box_in_series):
arr = data[:5].copy()
expected = arr.take([0, 0, 0, 3, 4])
if box_in_series:
arr = pd.Series(arr)
expected = pd.Series(expected)
arr[mask] = data[0]
tm.assert_equal(expected, arr)
def test_setitem_mask_raises(self, data, box_in_series):
# wrong length
mask = np.array([True, False])
if box_in_series:
data = pd.Series(data)
with pytest.raises(IndexError, match="wrong length"):
data[mask] = data[0]
mask = pd.array(mask, dtype="boolean")
with pytest.raises(IndexError, match="wrong length"):
data[mask] = data[0]
def test_setitem_mask_boolean_array_with_na(self, data, box_in_series):
mask = pd.array(np.zeros(data.shape, dtype="bool"), dtype="boolean")
mask[:3] = True
mask[3:5] = pd.NA
if box_in_series:
data = pd.Series(data)
data[mask] = data[0]
assert (data[:3] == data[0]).all()
@pytest.mark.parametrize(
"idx",
[[0, 1, 2], pd.array([0, 1, 2], dtype="Int64"), np.array([0, 1, 2])],
ids=["list", "integer-array", "numpy-array"],
)
def test_setitem_integer_array(self, data, idx, box_in_series):
arr = data[:5].copy()
expected = data.take([0, 0, 0, 3, 4])
if box_in_series:
arr = pd.Series(arr)
expected = pd.Series(expected)
arr[idx] = arr[0]
tm.assert_equal(arr, expected)
@pytest.mark.parametrize(
"idx, box_in_series",
[
([0, 1, 2, pd.NA], False),
pytest.param(
[0, 1, 2, pd.NA], True, marks=pytest.mark.xfail(reason="GH-31948")
),
(pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
(pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
],
ids=["list-False", "list-True", "integer-array-False", "integer-array-True"],
)
def test_setitem_integer_with_missing_raises(self, data, idx, box_in_series):
arr = data.copy()
# TODO(xfail) this raises KeyError about labels not found (it tries label-based)
# for list of labels with Series
if box_in_series:
arr = pd.Series(data, index=[chr(100 + i) for i in range(len(data))])
msg = "Cannot index with an integer indexer containing NA values"
with pytest.raises(ValueError, match=msg):
arr[idx] = arr[0]
@pytest.mark.parametrize("as_callable", [True, False])
@pytest.mark.parametrize("setter", ["loc", None])
def test_setitem_mask_aligned(self, data, as_callable, setter):
ser = pd.Series(data)
mask = np.zeros(len(data), dtype=bool)
mask[:2] = True
if as_callable:
mask2 = lambda x: mask
else:
mask2 = mask
if setter:
# loc
target = getattr(ser, setter)
else:
# Series.__setitem__
target = ser
target[mask2] = data[5:7]
ser[mask2] = data[5:7]
assert ser[0] == data[5]
assert ser[1] == data[6]
@pytest.mark.parametrize("setter", ["loc", None])
def test_setitem_mask_broadcast(self, data, setter):
ser = pd.Series(data)
mask = np.zeros(len(data), dtype=bool)
mask[:2] = True
if setter: # loc
target = getattr(ser, setter)
else: # __setitem__
target = ser
target[mask] = data[10]
assert ser[0] == data[10]
assert ser[1] == data[10]
def test_setitem_expand_columns(self, data):
df = pd.DataFrame({"A": data})
result = df.copy()
result["B"] = 1
expected = pd.DataFrame({"A": data, "B": [1] * len(data)})
tm.assert_frame_equal(result, expected)
result = df.copy()
result.loc[:, "B"] = 1
tm.assert_frame_equal(result, expected)
# overwrite with new type
result["B"] = data
expected = pd.DataFrame({"A": data, "B": data})
tm.assert_frame_equal(result, expected)
def test_setitem_expand_with_extension(self, data):
df = pd.DataFrame({"A": [1] * len(data)})
result = df.copy()
result["B"] = data
expected = pd.DataFrame({"A": [1] * len(data), "B": data})
tm.assert_frame_equal(result, expected)
result = df.copy()
result.loc[:, "B"] = data
tm.assert_frame_equal(result, expected)
def test_setitem_frame_invalid_length(self, data):
df = pd.DataFrame({"A": [1] * len(data)})
xpr = (
rf"Length of values \({len(data[:5])}\) "
rf"does not match length of index \({len(df)}\)"
)
with pytest.raises(ValueError, match=xpr):
df["B"] = data[:5]
def test_setitem_tuple_index(self, data):
ser = pd.Series(data[:2], index=[(0, 0), (0, 1)])
expected = pd.Series(data.take([1, 1]), index=ser.index)
ser[(0, 0)] = data[1]
tm.assert_series_equal(ser, expected)
def test_setitem_slice(self, data, box_in_series):
arr = data[:5].copy()
expected = data.take([0, 0, 0, 3, 4])
if box_in_series:
arr = pd.Series(arr)
expected = pd.Series(expected)
arr[:3] = data[0]
tm.assert_equal(arr, expected)
def test_setitem_loc_iloc_slice(self, data):
arr = data[:5].copy()
s = pd.Series(arr, index=["a", "b", "c", "d", "e"])
expected = pd.Series(data.take([0, 0, 0, 3, 4]), index=s.index)
result = s.copy()
result.iloc[:3] = data[0]
tm.assert_equal(result, expected)
result = s.copy()
result.loc[:"c"] = data[0]
tm.assert_equal(result, expected)
def test_setitem_slice_mismatch_length_raises(self, data):
arr = data[:5]
with pytest.raises(ValueError):
arr[:1] = arr[:2]
def test_setitem_slice_array(self, data):
arr = data[:5].copy()
arr[:5] = data[-5:]
tm.assert_extension_array_equal(arr, data[-5:])
def test_setitem_scalar_key_sequence_raise(self, data):
arr = data[:5].copy()
with pytest.raises(ValueError):
arr[0] = arr[[0, 1]]
def test_setitem_preserves_views(self, data):
# GH#28150 setitem shouldn't swap the underlying data
view1 = data.view()
view2 = data[:]
data[0] = data[1]
assert view1[0] == data[1]
assert view2[0] == data[1]
def test_setitem_with_expansion_dataframe_column(self, data, full_indexer):
# https://github.com/pandas-dev/pandas/issues/32395
df = expected = pd.DataFrame({0: pd.Series(data)})
result = pd.DataFrame(index=df.index)
key = full_indexer(df)
result.loc[key, 0] = df[0]
tm.assert_frame_equal(result, expected)
def test_setitem_with_expansion_row(self, data, na_value):
df = pd.DataFrame({"data": data[:1]})
df.loc[1, "data"] = data[1]
expected = pd.DataFrame({"data": data[:2]})
tm.assert_frame_equal(df, expected)
# https://github.com/pandas-dev/pandas/issues/47284
df.loc[2, "data"] = na_value
expected = pd.DataFrame(
{"data": pd.Series([data[0], data[1], na_value], dtype=data.dtype)}
)
tm.assert_frame_equal(df, expected)
def test_setitem_series(self, data, full_indexer):
# https://github.com/pandas-dev/pandas/issues/32395
ser = pd.Series(data, name="data")
result = pd.Series(index=ser.index, dtype=object, name="data")
# because result has object dtype, the attempt to do setting inplace
# is successful, and object dtype is retained
key = full_indexer(ser)
result.loc[key] = ser
expected = pd.Series(
data.astype(object), index=ser.index, name="data", dtype=object
)
tm.assert_series_equal(result, expected)
def test_setitem_frame_2d_values(self, data):
# GH#44514
df = pd.DataFrame({"A": data})
# Avoiding using_array_manager fixture
# https://github.com/pandas-dev/pandas/pull/44514#discussion_r754002410
using_array_manager = isinstance(df._mgr, pd.core.internals.ArrayManager)
using_copy_on_write = pd.options.mode.copy_on_write
blk_data = df._mgr.arrays[0]
orig = df.copy()
df.iloc[:] = df.copy()
tm.assert_frame_equal(df, orig)
df.iloc[:-1] = df.iloc[:-1].copy()
tm.assert_frame_equal(df, orig)
df.iloc[:] = df.values
tm.assert_frame_equal(df, orig)
if not using_array_manager and not using_copy_on_write:
# GH#33457 Check that this setting occurred in-place
# FIXME(ArrayManager): this should work there too
assert df._mgr.arrays[0] is blk_data
df.iloc[:-1] = df.values[:-1]
tm.assert_frame_equal(df, orig)
def test_delitem_series(self, data):
# GH#40763
ser = pd.Series(data, name="data")
taker = np.arange(len(ser))
taker = np.delete(taker, 1)
expected = ser[taker]
del ser[1]
tm.assert_series_equal(ser, expected)
def test_setitem_invalid(self, data, invalid_scalar):
msg = "" # messages vary by subclass, so we do not test it
with pytest.raises((ValueError, TypeError), match=msg):
data[0] = invalid_scalar
with pytest.raises((ValueError, TypeError), match=msg):
data[:] = invalid_scalar
def test_setitem_2d_values(self, data):
# GH50085
original = data.copy()
df = pd.DataFrame({"a": data, "b": data})
df.loc[[0, 1], :] = df.loc[[1, 0], :].values
assert (df.loc[0, :] == original[1]).all()
assert (df.loc[1, :] == original[0]).all()
|