File size: 17,685 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 |
import numpy as np
import pytest
from pandas.core.dtypes.dtypes import DatetimeTZDtype
import pandas as pd
from pandas import (
CategoricalIndex,
Series,
Timedelta,
Timestamp,
date_range,
)
import pandas._testing as tm
from pandas.core.arrays import (
DatetimeArray,
IntervalArray,
NumpyExtensionArray,
PeriodArray,
SparseArray,
TimedeltaArray,
)
from pandas.core.arrays.string_arrow import ArrowStringArrayNumpySemantics
class TestToIterable:
# test that we convert an iterable to python types
dtypes = [
("int8", int),
("int16", int),
("int32", int),
("int64", int),
("uint8", int),
("uint16", int),
("uint32", int),
("uint64", int),
("float16", float),
("float32", float),
("float64", float),
("datetime64[ns]", Timestamp),
("datetime64[ns, US/Eastern]", Timestamp),
("timedelta64[ns]", Timedelta),
]
@pytest.mark.parametrize("dtype, rdtype", dtypes)
@pytest.mark.parametrize(
"method",
[
lambda x: x.tolist(),
lambda x: x.to_list(),
lambda x: list(x),
lambda x: list(x.__iter__()),
],
ids=["tolist", "to_list", "list", "iter"],
)
def test_iterable(self, index_or_series, method, dtype, rdtype):
# gh-10904
# gh-13258
# coerce iteration to underlying python / pandas types
typ = index_or_series
if dtype == "float16" and issubclass(typ, pd.Index):
with pytest.raises(NotImplementedError, match="float16 indexes are not "):
typ([1], dtype=dtype)
return
s = typ([1], dtype=dtype)
result = method(s)[0]
assert isinstance(result, rdtype)
@pytest.mark.parametrize(
"dtype, rdtype, obj",
[
("object", object, "a"),
("object", int, 1),
("category", object, "a"),
("category", int, 1),
],
)
@pytest.mark.parametrize(
"method",
[
lambda x: x.tolist(),
lambda x: x.to_list(),
lambda x: list(x),
lambda x: list(x.__iter__()),
],
ids=["tolist", "to_list", "list", "iter"],
)
def test_iterable_object_and_category(
self, index_or_series, method, dtype, rdtype, obj
):
# gh-10904
# gh-13258
# coerce iteration to underlying python / pandas types
typ = index_or_series
s = typ([obj], dtype=dtype)
result = method(s)[0]
assert isinstance(result, rdtype)
@pytest.mark.parametrize("dtype, rdtype", dtypes)
def test_iterable_items(self, dtype, rdtype):
# gh-13258
# test if items yields the correct boxed scalars
# this only applies to series
s = Series([1], dtype=dtype)
_, result = next(iter(s.items()))
assert isinstance(result, rdtype)
_, result = next(iter(s.items()))
assert isinstance(result, rdtype)
@pytest.mark.parametrize(
"dtype, rdtype", dtypes + [("object", int), ("category", int)]
)
def test_iterable_map(self, index_or_series, dtype, rdtype):
# gh-13236
# coerce iteration to underlying python / pandas types
typ = index_or_series
if dtype == "float16" and issubclass(typ, pd.Index):
with pytest.raises(NotImplementedError, match="float16 indexes are not "):
typ([1], dtype=dtype)
return
s = typ([1], dtype=dtype)
result = s.map(type)[0]
if not isinstance(rdtype, tuple):
rdtype = (rdtype,)
assert result in rdtype
@pytest.mark.parametrize(
"method",
[
lambda x: x.tolist(),
lambda x: x.to_list(),
lambda x: list(x),
lambda x: list(x.__iter__()),
],
ids=["tolist", "to_list", "list", "iter"],
)
def test_categorial_datetimelike(self, method):
i = CategoricalIndex([Timestamp("1999-12-31"), Timestamp("2000-12-31")])
result = method(i)[0]
assert isinstance(result, Timestamp)
def test_iter_box_dt64(self, unit):
vals = [Timestamp("2011-01-01"), Timestamp("2011-01-02")]
ser = Series(vals).dt.as_unit(unit)
assert ser.dtype == f"datetime64[{unit}]"
for res, exp in zip(ser, vals):
assert isinstance(res, Timestamp)
assert res.tz is None
assert res == exp
assert res.unit == unit
def test_iter_box_dt64tz(self, unit):
vals = [
Timestamp("2011-01-01", tz="US/Eastern"),
Timestamp("2011-01-02", tz="US/Eastern"),
]
ser = Series(vals).dt.as_unit(unit)
assert ser.dtype == f"datetime64[{unit}, US/Eastern]"
for res, exp in zip(ser, vals):
assert isinstance(res, Timestamp)
assert res.tz == exp.tz
assert res == exp
assert res.unit == unit
def test_iter_box_timedelta64(self, unit):
# timedelta
vals = [Timedelta("1 days"), Timedelta("2 days")]
ser = Series(vals).dt.as_unit(unit)
assert ser.dtype == f"timedelta64[{unit}]"
for res, exp in zip(ser, vals):
assert isinstance(res, Timedelta)
assert res == exp
assert res.unit == unit
def test_iter_box_period(self):
# period
vals = [pd.Period("2011-01-01", freq="M"), pd.Period("2011-01-02", freq="M")]
s = Series(vals)
assert s.dtype == "Period[M]"
for res, exp in zip(s, vals):
assert isinstance(res, pd.Period)
assert res.freq == "ME"
assert res == exp
@pytest.mark.parametrize(
"arr, expected_type, dtype",
[
(np.array([0, 1], dtype=np.int64), np.ndarray, "int64"),
(np.array(["a", "b"]), np.ndarray, "object"),
(pd.Categorical(["a", "b"]), pd.Categorical, "category"),
(
pd.DatetimeIndex(["2017", "2018"], tz="US/Central"),
DatetimeArray,
"datetime64[ns, US/Central]",
),
(
pd.PeriodIndex([2018, 2019], freq="Y"),
PeriodArray,
pd.core.dtypes.dtypes.PeriodDtype("Y-DEC"),
),
(pd.IntervalIndex.from_breaks([0, 1, 2]), IntervalArray, "interval"),
(
pd.DatetimeIndex(["2017", "2018"]),
DatetimeArray,
"datetime64[ns]",
),
(
pd.TimedeltaIndex([10**10]),
TimedeltaArray,
"m8[ns]",
),
],
)
def test_values_consistent(arr, expected_type, dtype, using_infer_string):
if using_infer_string and dtype == "object":
expected_type = ArrowStringArrayNumpySemantics
l_values = Series(arr)._values
r_values = pd.Index(arr)._values
assert type(l_values) is expected_type
assert type(l_values) is type(r_values)
tm.assert_equal(l_values, r_values)
@pytest.mark.parametrize("arr", [np.array([1, 2, 3])])
def test_numpy_array(arr):
ser = Series(arr)
result = ser.array
expected = NumpyExtensionArray(arr)
tm.assert_extension_array_equal(result, expected)
def test_numpy_array_all_dtypes(any_numpy_dtype):
ser = Series(dtype=any_numpy_dtype)
result = ser.array
if np.dtype(any_numpy_dtype).kind == "M":
assert isinstance(result, DatetimeArray)
elif np.dtype(any_numpy_dtype).kind == "m":
assert isinstance(result, TimedeltaArray)
else:
assert isinstance(result, NumpyExtensionArray)
@pytest.mark.parametrize(
"arr, attr",
[
(pd.Categorical(["a", "b"]), "_codes"),
(PeriodArray._from_sequence(["2000", "2001"], dtype="period[D]"), "_ndarray"),
(pd.array([0, np.nan], dtype="Int64"), "_data"),
(IntervalArray.from_breaks([0, 1]), "_left"),
(SparseArray([0, 1]), "_sparse_values"),
(
DatetimeArray._from_sequence(np.array([1, 2], dtype="datetime64[ns]")),
"_ndarray",
),
# tz-aware Datetime
(
DatetimeArray._from_sequence(
np.array(
["2000-01-01T12:00:00", "2000-01-02T12:00:00"], dtype="M8[ns]"
),
dtype=DatetimeTZDtype(tz="US/Central"),
),
"_ndarray",
),
],
)
def test_array(arr, attr, index_or_series, request):
box = index_or_series
result = box(arr, copy=False).array
if attr:
arr = getattr(arr, attr)
result = getattr(result, attr)
assert result is arr
def test_array_multiindex_raises():
idx = pd.MultiIndex.from_product([["A"], ["a", "b"]])
msg = "MultiIndex has no single backing array"
with pytest.raises(ValueError, match=msg):
idx.array
@pytest.mark.parametrize(
"arr, expected",
[
(np.array([1, 2], dtype=np.int64), np.array([1, 2], dtype=np.int64)),
(pd.Categorical(["a", "b"]), np.array(["a", "b"], dtype=object)),
(
pd.core.arrays.period_array(["2000", "2001"], freq="D"),
np.array([pd.Period("2000", freq="D"), pd.Period("2001", freq="D")]),
),
(pd.array([0, np.nan], dtype="Int64"), np.array([0, np.nan])),
(
IntervalArray.from_breaks([0, 1, 2]),
np.array([pd.Interval(0, 1), pd.Interval(1, 2)], dtype=object),
),
(SparseArray([0, 1]), np.array([0, 1], dtype=np.int64)),
# tz-naive datetime
(
DatetimeArray._from_sequence(np.array(["2000", "2001"], dtype="M8[ns]")),
np.array(["2000", "2001"], dtype="M8[ns]"),
),
# tz-aware stays tz`-aware
(
DatetimeArray._from_sequence(
np.array(["2000-01-01T06:00:00", "2000-01-02T06:00:00"], dtype="M8[ns]")
)
.tz_localize("UTC")
.tz_convert("US/Central"),
np.array(
[
Timestamp("2000-01-01", tz="US/Central"),
Timestamp("2000-01-02", tz="US/Central"),
]
),
),
# Timedelta
(
TimedeltaArray._from_sequence(
np.array([0, 3600000000000], dtype="i8").view("m8[ns]")
),
np.array([0, 3600000000000], dtype="m8[ns]"),
),
# GH#26406 tz is preserved in Categorical[dt64tz]
(
pd.Categorical(date_range("2016-01-01", periods=2, tz="US/Pacific")),
np.array(
[
Timestamp("2016-01-01", tz="US/Pacific"),
Timestamp("2016-01-02", tz="US/Pacific"),
]
),
),
],
)
def test_to_numpy(arr, expected, index_or_series_or_array, request):
box = index_or_series_or_array
with tm.assert_produces_warning(None):
thing = box(arr)
result = thing.to_numpy()
tm.assert_numpy_array_equal(result, expected)
result = np.asarray(thing)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize("as_series", [True, False])
@pytest.mark.parametrize(
"arr", [np.array([1, 2, 3], dtype="int64"), np.array(["a", "b", "c"], dtype=object)]
)
def test_to_numpy_copy(arr, as_series, using_infer_string):
obj = pd.Index(arr, copy=False)
if as_series:
obj = Series(obj.values, copy=False)
# no copy by default
result = obj.to_numpy()
if using_infer_string and arr.dtype == object:
assert np.shares_memory(arr, result) is False
else:
assert np.shares_memory(arr, result) is True
result = obj.to_numpy(copy=False)
if using_infer_string and arr.dtype == object:
assert np.shares_memory(arr, result) is False
else:
assert np.shares_memory(arr, result) is True
# copy=True
result = obj.to_numpy(copy=True)
assert np.shares_memory(arr, result) is False
@pytest.mark.parametrize("as_series", [True, False])
def test_to_numpy_dtype(as_series, unit):
tz = "US/Eastern"
obj = pd.DatetimeIndex(["2000", "2001"], tz=tz)
if as_series:
obj = Series(obj)
# preserve tz by default
result = obj.to_numpy()
expected = np.array(
[Timestamp("2000", tz=tz), Timestamp("2001", tz=tz)], dtype=object
)
tm.assert_numpy_array_equal(result, expected)
result = obj.to_numpy(dtype="object")
tm.assert_numpy_array_equal(result, expected)
result = obj.to_numpy(dtype="M8[ns]")
expected = np.array(["2000-01-01T05", "2001-01-01T05"], dtype="M8[ns]")
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"values, dtype, na_value, expected",
[
([1, 2, None], "float64", 0, [1.0, 2.0, 0.0]),
(
[Timestamp("2000"), Timestamp("2000"), pd.NaT],
None,
Timestamp("2000"),
[np.datetime64("2000-01-01T00:00:00.000000000")] * 3,
),
],
)
def test_to_numpy_na_value_numpy_dtype(
index_or_series, values, dtype, na_value, expected
):
obj = index_or_series(values)
result = obj.to_numpy(dtype=dtype, na_value=na_value)
expected = np.array(expected)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"data, multiindex, dtype, na_value, expected",
[
(
[1, 2, None, 4],
[(0, "a"), (0, "b"), (1, "b"), (1, "c")],
float,
None,
[1.0, 2.0, np.nan, 4.0],
),
(
[1, 2, None, 4],
[(0, "a"), (0, "b"), (1, "b"), (1, "c")],
float,
np.nan,
[1.0, 2.0, np.nan, 4.0],
),
(
[1.0, 2.0, np.nan, 4.0],
[("a", 0), ("a", 1), ("a", 2), ("b", 0)],
int,
0,
[1, 2, 0, 4],
),
(
[Timestamp("2000"), Timestamp("2000"), pd.NaT],
[(0, Timestamp("2021")), (0, Timestamp("2022")), (1, Timestamp("2000"))],
None,
Timestamp("2000"),
[np.datetime64("2000-01-01T00:00:00.000000000")] * 3,
),
],
)
def test_to_numpy_multiindex_series_na_value(
data, multiindex, dtype, na_value, expected
):
index = pd.MultiIndex.from_tuples(multiindex)
series = Series(data, index=index)
result = series.to_numpy(dtype=dtype, na_value=na_value)
expected = np.array(expected)
tm.assert_numpy_array_equal(result, expected)
def test_to_numpy_kwargs_raises():
# numpy
s = Series([1, 2, 3])
msg = r"to_numpy\(\) got an unexpected keyword argument 'foo'"
with pytest.raises(TypeError, match=msg):
s.to_numpy(foo=True)
# extension
s = Series([1, 2, 3], dtype="Int64")
with pytest.raises(TypeError, match=msg):
s.to_numpy(foo=True)
@pytest.mark.parametrize(
"data",
[
{"a": [1, 2, 3], "b": [1, 2, None]},
{"a": np.array([1, 2, 3]), "b": np.array([1, 2, np.nan])},
{"a": pd.array([1, 2, 3]), "b": pd.array([1, 2, None])},
],
)
@pytest.mark.parametrize("dtype, na_value", [(float, np.nan), (object, None)])
def test_to_numpy_dataframe_na_value(data, dtype, na_value):
# https://github.com/pandas-dev/pandas/issues/33820
df = pd.DataFrame(data)
result = df.to_numpy(dtype=dtype, na_value=na_value)
expected = np.array([[1, 1], [2, 2], [3, na_value]], dtype=dtype)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"data, expected",
[
(
{"a": pd.array([1, 2, None])},
np.array([[1.0], [2.0], [np.nan]], dtype=float),
),
(
{"a": [1, 2, 3], "b": [1, 2, 3]},
np.array([[1, 1], [2, 2], [3, 3]], dtype=float),
),
],
)
def test_to_numpy_dataframe_single_block(data, expected):
# https://github.com/pandas-dev/pandas/issues/33820
df = pd.DataFrame(data)
result = df.to_numpy(dtype=float, na_value=np.nan)
tm.assert_numpy_array_equal(result, expected)
def test_to_numpy_dataframe_single_block_no_mutate():
# https://github.com/pandas-dev/pandas/issues/33820
result = pd.DataFrame(np.array([1.0, 2.0, np.nan]))
expected = pd.DataFrame(np.array([1.0, 2.0, np.nan]))
result.to_numpy(na_value=0.0)
tm.assert_frame_equal(result, expected)
class TestAsArray:
@pytest.mark.parametrize("tz", [None, "US/Central"])
def test_asarray_object_dt64(self, tz):
ser = Series(date_range("2000", periods=2, tz=tz))
with tm.assert_produces_warning(None):
# Future behavior (for tzaware case) with no warning
result = np.asarray(ser, dtype=object)
expected = np.array(
[Timestamp("2000-01-01", tz=tz), Timestamp("2000-01-02", tz=tz)]
)
tm.assert_numpy_array_equal(result, expected)
def test_asarray_tz_naive(self):
# This shouldn't produce a warning.
ser = Series(date_range("2000", periods=2))
expected = np.array(["2000-01-01", "2000-01-02"], dtype="M8[ns]")
result = np.asarray(ser)
tm.assert_numpy_array_equal(result, expected)
def test_asarray_tz_aware(self):
tz = "US/Central"
ser = Series(date_range("2000", periods=2, tz=tz))
expected = np.array(["2000-01-01T06", "2000-01-02T06"], dtype="M8[ns]")
result = np.asarray(ser, dtype="datetime64[ns]")
tm.assert_numpy_array_equal(result, expected)
# Old behavior with no warning
result = np.asarray(ser, dtype="M8[ns]")
tm.assert_numpy_array_equal(result, expected)
|