def test_generate_arbitrary_indices(data):
min_size = data.draw(st.integers(0, 10), "min_size")
max_size = data.draw(st.none() | st.integers(min_size, min_size + 10), "max_size")
unique = data.draw(st.booleans(), "unique")
dtype = data.draw(npst.scalar_dtypes(), "dtype")
assume(supported_by_pandas(dtype))
# Pandas bug: https://github.com/pandas-dev/pandas/pull/14916 until 0.20;
# then int64 indexes are inferred from uint64 values.
assume(dtype.kind != "u")
pass_elements = data.draw(st.booleans(), "pass_elements")
converted_dtype = pandas.Index([], dtype=dtype).dtype
try:
inferred_dtype = pandas.Index([data.draw(npst.from_dtype(dtype))]).dtype
if pass_elements:
elements = npst.from_dtype(dtype)
dtype = None
else:
elements = None
index = data.draw(
pdst.indexes(
elements=elements,
dtype=dtype,
min_size=min_size,
max_size=max_size,
unique=unique,
)
)
except Exception as e:
if type(e).__name__ == "OutOfBoundsDatetime":
# See https://github.com/HypothesisWorks/hypothesis-python/pull/826
reject()
else:
raise
if dtype is None:
if pandas.__version__ >= "0.19":
assert index.dtype == inferred_dtype
else:
assert index.dtype == converted_dtype
if unique:
assert len(set(index.values)) == len(index)
def column_strategy(draw):
name = draw(st.none() | st.text())
dtype = draw(npst.scalar_dtypes().filter(supported_by_pandas))
pass_dtype = not draw(st.booleans())
if pass_dtype:
pass_elements = not draw(st.booleans())
else:
pass_elements = True
if pass_elements:
elements = npst.from_dtype(dtype)
else:
elements = None
unique = draw(st.booleans())
fill = st.nothing() if draw(st.booleans()) else None
return pdst.column(
name=name, dtype=dtype, unique=unique, fill=fill, elements=elements)
def test_generate_arbitrary_indices(data):
min_size = data.draw(st.integers(0, 10), 'min_size')
max_size = data.draw(
st.none() | st.integers(min_size, min_size + 10), 'max_size')
unique = data.draw(st.booleans(), 'unique')
dtype = data.draw(npst.scalar_dtypes(), 'dtype')
assume(supported_by_pandas(dtype))
pass_elements = data.draw(st.booleans(), 'pass_elements')
converted_dtype = pandas.Index([], dtype=dtype).dtype
try:
inferred_dtype = pandas.Index(
[data.draw(npst.from_dtype(dtype))]).dtype
if pass_elements:
elements = npst.from_dtype(dtype)
dtype = None
else:
elements = None
index = data.draw(pdst.indexes(
elements=elements, dtype=dtype, min_size=min_size,
max_size=max_size, unique=unique,
))
except Exception as e:
if type(e).__name__ == 'OutOfBoundsDatetime':
# See https://github.com/HypothesisWorks/hypothesis-python/pull/826
reject()
else:
raise
if dtype is None:
assert index.dtype == inferred_dtype
else:
assert index.dtype == converted_dtype
if unique:
assert len(set(index.values)) == len(index)
def test_minimise_scalar_dtypes():
assert minimal(nps.scalar_dtypes()) == np.dtype(u'bool')
def test_minimise_scalar_dtypes():
assert minimal(nps.scalar_dtypes()) == np.dtype("bool")
import numpy as np
from hypothesis.extra.numpy import (
arrays,
array_shapes,
scalar_dtypes,
nested_dtypes,
from_dtype,
integer_dtypes,
unsigned_integer_dtypes,
)
_global_type_lookup.update({
np.dtype:
nested_dtypes(),
np.ndarray:
arrays(scalar_dtypes(), array_shapes(max_dims=2)),
})
except ImportError: # pragma: no cover
np = None
try:
import typing
except ImportError: # pragma: no cover
pass
else:
_global_type_lookup.update({
typing.ByteString:
st.binary() | st.binary().map(bytearray),
# Reversible is somehow a subclass of Hashable, so we tuplize it.
# See also the discussion at https://bugs.python.org/issue39046
typing.Reversible:
@given(array_shapes())
def test_can_generate_array_shapes(shape):
assert isinstance(shape, tuple)
assert all(isinstance(i, int) for i in shape)
@given(st.integers(1, 10), st.integers(0, 9), st.integers(1), st.integers(0))
def test_minimise_array_shapes(min_dims, dim_range, min_side, side_range):
smallest = minimal(array_shapes(min_dims, min_dims + dim_range,
min_side, min_side + side_range))
assert len(smallest) == min_dims and all(k == min_side for k in smallest)
@given(scalar_dtypes())
def test_can_generate_scalar_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@given(nested_dtypes())
def test_can_generate_compound_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@given(nested_dtypes(max_itemsize=settings.default.buffer_size // 10),
st.data())
def test_infer_strategy_from_dtype(dtype, data):
# Given a dtype
assert isinstance(dtype, np.dtype)
# We can infer a strategy
@given(nps.array_shapes())
def test_can_generate_array_shapes(shape):
assert isinstance(shape, tuple)
assert all(isinstance(i, int) for i in shape)
@settings(deadline=None)
@given(st.integers(1, 10), st.integers(0, 9), st.integers(1), st.integers(0))
def test_minimise_array_shapes(min_dims, dim_range, min_side, side_range):
smallest = minimal(nps.array_shapes(min_dims, min_dims + dim_range,
min_side, min_side + side_range))
assert len(smallest) == min_dims and all(k == min_side for k in smallest)
@given(nps.scalar_dtypes())
def test_can_generate_scalar_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@given(nps.nested_dtypes())
def test_can_generate_compound_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@given(nps.nested_dtypes(max_itemsize=settings.default.buffer_size // 10),
st.data())
def test_infer_strategy_from_dtype(dtype, data):
# Given a dtype
assert isinstance(dtype, np.dtype)
# We can infer a strategy
smallest = minimal(
nps.array_shapes(
min_dims, min_dims + dim_range, min_side, min_side + side_range
)
)
assert len(smallest) == min_dims and all(k == min_side for k in smallest)
@pytest.mark.parametrize(
"kwargs", [dict(min_side=100), dict(min_dims=15), dict(min_dims=32)]
)
def test_interesting_array_shapes_argument(kwargs):
nps.array_shapes(**kwargs).example()
@given(nps.scalar_dtypes())
def test_can_generate_scalar_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@given(
nps.nested_dtypes(
subtype_strategy=st.one_of(
nps.scalar_dtypes(), nps.byte_string_dtypes(), nps.unicode_string_dtypes()
)
)
)
def test_can_generate_compound_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@given(lists(_st_shape, min_size=0, max_size=5), real_scalar_dtypes(), data())
def test_elements_tuple_of_arrays(shapes, dtype, data):
choices = data.draw(real_from_dtype(dtype))
elements = sampled_from(choices)
S = gu._tuple_of_arrays(shapes, dtype, elements=elements)
X = data.draw(S)
validate_elements(X, choices=choices, dtype=dtype)
@given(
gu.gufunc_args(
"(1),(1),(1),()->()",
dtype=["object", "object", "object", "bool"],
elements=[_st_shape, scalar_dtypes(), just(None), booleans()],
min_side=1,
max_dims_extra=1,
),
data(),
)
def test_bcast_tuple_of_arrays(args, data):
"""Now testing broadcasting of tuple_of_arrays, kind of crazy since it uses
gufuncs to test itself. Some awkwardness here since there are a lot of
corner cases when dealing with object types in the numpy extension.
For completeness, should probably right a function like this for the other
functions, but there always just pass dtype, elements, unique to
`_tuple_of_arrays` anyway, so this should be pretty good.
"""
shapes, dtype, elements, unique = args
#
# This Source Code Form is subject to the terms of the Mozilla Public License,
# v. 2.0. If a copy of the MPL was not distributed with this file, You can
# obtain one at http://mozilla.org/MPL/2.0/.
#
# END HEADER
from __future__ import division, print_function, absolute_import
from hypothesis import given
from hypothesis.extra import numpy as npst
from tests.common.utils import checks_deprecated_behaviour
from hypothesis.strategies import data, sampled_from
@given(data(), npst.arrays(
dtype=npst.scalar_dtypes(),
shape=npst.array_shapes(max_dims=1)
))
def test_can_sample_1D_numpy_array_without_warning(data, arr):
data.draw(sampled_from(arr))
@checks_deprecated_behaviour
@given(data(), npst.arrays(
dtype=npst.scalar_dtypes(),
shape=npst.array_shapes(min_dims=2, max_dims=5)
))
def test_sampling_multi_dimensional_arrays_is_deprecated(data, arr):
data.draw(sampled_from(arr))
@given(nps.array_shapes())
def test_can_generate_array_shapes(shape):
assert isinstance(shape, tuple)
assert all(isinstance(i, int) for i in shape)
@given(st.integers(1, 10), st.integers(0, 9), st.integers(1), st.integers(0))
def test_minimise_array_shapes(min_dims, dim_range, min_side, side_range):
smallest = minimal(nps.array_shapes(min_dims, min_dims + dim_range,
min_side, min_side + side_range))
assert len(smallest) == min_dims and all(k == min_side for k in smallest)
@given(nps.scalar_dtypes())
def test_can_generate_scalar_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@given(nps.nested_dtypes())
def test_can_generate_compound_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@given(nps.nested_dtypes(max_itemsize=settings.default.buffer_size // 10),
st.data())
def test_infer_strategy_from_dtype(dtype, data):
# Given a dtype
assert isinstance(dtype, np.dtype)
# We can infer a strategy
# obtain one at http://mozilla.org/MPL/2.0/.
#
# END HEADER
from __future__ import division, print_function, absolute_import
import numpy as np
from hypothesis import given, assume
from hypothesis.extra import numpy as npst
from tests.common.utils import checks_deprecated_behaviour
from hypothesis.strategies import data, sampled_from
@given(data(), npst.arrays(
dtype=npst.scalar_dtypes(),
shape=npst.array_shapes(max_dims=1)
))
def test_can_sample_1D_numpy_array_without_warning(data, arr):
elem = data.draw(sampled_from(arr))
try:
assume(not np.isnan(elem))
except TypeError:
pass
assert elem in arr
@checks_deprecated_behaviour
@given(data(), npst.arrays(
dtype=npst.scalar_dtypes(),
shape=npst.array_shapes(min_dims=2, max_dims=5)
# v. 2.0. If a copy of the MPL was not distributed with this file, You can
# obtain one at https://mozilla.org/MPL/2.0/.
#
# END HEADER
from __future__ import absolute_import, division, print_function
from hypothesis import given
from hypothesis.errors import InvalidArgument
from hypothesis.extra import numpy as npst
from hypothesis.strategies import data, sampled_from
from tests.common.utils import fails_with
@given(
data(), npst.arrays(dtype=npst.scalar_dtypes(), shape=npst.array_shapes(max_dims=1))
)
def test_can_sample_1D_numpy_array_without_warning(data, arr):
data.draw(sampled_from(arr))
@fails_with(InvalidArgument)
@given(
data(),
npst.arrays(
dtype=npst.scalar_dtypes(), shape=npst.array_shapes(min_dims=2, max_dims=5)
),
)
def test_sampling_multi_dimensional_arrays_is_deprecated(data, arr):
data.draw(sampled_from(arr))
import pytest
from hypothesis import given
import hypothesis.strategies as st
import hypothesis.extra.numpy as st_np
import numpy as np
import pyarrow as pa
from ..context import serialization_context
# Fails, most concerningly, on:
# array([1], dtype=uint16)
# array([256], dtype=uint16)
@pytest.mark.xfail
@given(
st_np.arrays(dtype=st_np.scalar_dtypes(),
shape=st.one_of(st.just(0), st_np.array_shapes())))
def test_plain_roundtrip(arr):
cereal = pa.serialize(arr, context=serialization_context)
buf = cereal.to_buffer()
decereal = pa.deserialize(buf, context=serialization_context)
assert arr.dtype == decereal.dtype.newbyteorder(
arr.dtype.byteorder) # arrow may change endianness
np.testing.assert_array_equal(arr, decereal)
def test_can_draw_arrays_from_scalars(data):
dt = data.draw(nps.scalar_dtypes())
result = data.draw(nps.arrays(dtype=dt, shape=()))
assert isinstance(result, np.ndarray)
assert result.dtype == dt
def test_can_create_a_series_of_any_dtype(data):
dtype = np.dtype(data.draw(npst.scalar_dtypes()))
assume(supported_by_pandas(dtype))
series = data.draw(pdst.series(dtype=dtype))
assert series.dtype == pandas.Series([], dtype=dtype).dtype
def test_can_draw_shapeless_from_scalars(data):
dt = data.draw(nps.scalar_dtypes())
result = data.draw(nps.arrays(dtype=dt, shape=()))
assert isinstance(result, dt.type)
df = pd.DataFrame({
'key': np.arange(0, 5000),
'count': rng.integers(0, 1000, 5000),
'score': rng.normal(10, 2, 5000)
})
dump(df, file)
df2 = load(file)
assert all(df2.columns == df.columns)
for c in df2.columns:
assert all(df2[c] == df[c])
@given(arrays(scalar_dtypes(), st.integers(500, 10000)))
def test_compress_many_arrays(a):
"Pickle random NumPy arrays"
assume(not any(np.isnan(a)))
with TemporaryDirectory('.test', 'binpickle') as path:
file = Path(path) / 'data.bpk'
with BinPickler.compressed(file) as w:
w.dump(a)
with BinPickleFile(file) as bpf:
assert not bpf.find_errors()
assert len(bpf.entries) in (1, 2)
a2 = bpf.load()
assert len(a2) == len(a)
def test_minimise_scalar_dtypes():
assert minimal(scalar_dtypes()) == np.dtype(u'bool')
_global_type_lookup[type] = st.sampled_from(
[type(None)] + sorted(_global_type_lookup, key=str))
if sys.version_info[:2] >= (3, 9): # pragma: no cover
# subclass of MutableMapping, and in Python 3.9 we resolve to a union
# which includes this... but we don't actually ever want to build one.
_global_type_lookup[os._Environ] = st.just(os.environ)
try: # pragma: no cover
import numpy as np
from hypothesis.extra.numpy import array_dtypes, array_shapes, arrays, scalar_dtypes
_global_type_lookup[np.dtype] = array_dtypes()
_global_type_lookup[np.ndarray] = arrays(scalar_dtypes(),
array_shapes(max_dims=2))
except ImportError:
pass
_global_type_lookup.update({
typing.ByteString:
st.binary() | st.binary().map(bytearray),
# Reversible is somehow a subclass of Hashable, so we tuplize it.
# See also the discussion at https://bugs.python.org/issue39046
typing.Reversible:
st.lists(st.integers()).map(tuple),
# TODO: SupportsAbs and SupportsRound should be covariant, ie have functions.
typing.SupportsAbs:
st.one_of(
st.booleans(),
))
assert len(smallest) == min_dims and all(k == min_side for k in smallest)
@pytest.mark.parametrize("kwargs", [{
"min_side": 100
}, {
"min_dims": 15
}, {
"min_dims": 32
}])
def test_interesting_array_shapes_argument(kwargs):
nps.array_shapes(**kwargs).example()
@given(nps.scalar_dtypes())
def test_can_generate_scalar_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@settings(max_examples=100)
@given(
nps.nested_dtypes(subtype_strategy=st.one_of(nps.scalar_dtypes(
), nps.byte_string_dtypes(), nps.unicode_string_dtypes())))
def test_can_generate_compound_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@settings(max_examples=100)
@given(
nps.nested_dtypes(subtype_strategy=st.one_of(nps.scalar_dtypes(
def posvel_arrays(draw):
s = draw(array_shapes())
dtype = draw(scalar_dtypes())
pos = draw(arrays(dtype=dtype, shape=(3, ) + s))
vel = draw(arrays(dtype=dtype, shape=(3, ) + s))
return pos, vel
@given(nps.array_shapes())
def test_can_generate_array_shapes(shape):
assert isinstance(shape, tuple)
assert all(isinstance(i, int) for i in shape)
@settings(deadline=None)
@given(st.integers(1, 10), st.integers(0, 9), st.integers(1), st.integers(0))
def test_minimise_array_shapes(min_dims, dim_range, min_side, side_range):
smallest = minimal(nps.array_shapes(min_dims, min_dims + dim_range,
min_side, min_side + side_range))
assert len(smallest) == min_dims and all(k == min_side for k in smallest)
@given(nps.scalar_dtypes())
def test_can_generate_scalar_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@given(nps.nested_dtypes())
def test_can_generate_compound_dtypes(dtype):
assert isinstance(dtype, np.dtype)
@given(nps.nested_dtypes(max_itemsize=settings.default.buffer_size // 10),
st.data())
def test_infer_strategy_from_dtype(dtype, data):
# Given a dtype
assert isinstance(dtype, np.dtype)
# We can infer a strategy
def posvel_arrays_broadcastable(draw):
s, s_pos, s_vel = draw(broadcastable_subshapes(array_shapes()))
dtype = draw(scalar_dtypes())
pos = draw(arrays(dtype=dtype, shape=(3, ) + tuple(s_pos)))
vel = draw(arrays(dtype=dtype, shape=(3, ) + tuple(s_vel)))
return pos, vel, (3, ) + s
def test_can_draw_shapeless_from_scalars(data):
dt = data.draw(nps.scalar_dtypes())
result = data.draw(nps.arrays(dtype=dt, shape=()))
assert isinstance(result, dt.type)
# consult the git log if you need to determine who owns an individual
# contribution.
#
# This Source Code Form is subject to the terms of the Mozilla Public License,
# v. 2.0. If a copy of the MPL was not distributed with this file, You can
# obtain one at http://mozilla.org/MPL/2.0/.
#
# END HEADER
from __future__ import division, print_function, absolute_import
from hypothesis import given
from hypothesis.extra import numpy as npst
from tests.common.utils import checks_deprecated_behaviour
from hypothesis.strategies import data, sampled_from
@given(data(),
npst.arrays(dtype=npst.scalar_dtypes(),
shape=npst.array_shapes(max_dims=1)))
def test_can_sample_1D_numpy_array_without_warning(data, arr):
data.draw(sampled_from(arr))
@checks_deprecated_behaviour
@given(data(),
npst.arrays(dtype=npst.scalar_dtypes(),
shape=npst.array_shapes(min_dims=2, max_dims=5)))
def test_sampling_multi_dimensional_arrays_is_deprecated(data, arr):
data.draw(sampled_from(arr))
int: st.integers().filter(lambda x: isinstance(x, int)),
long: st.integers().map(long) # noqa
})
try:
from hypothesis.extra.pytz import timezones
_global_type_lookup[datetime.tzinfo] = timezones()
except ImportError: # pragma: no cover
pass
try: # pragma: no cover
import numpy as np
from hypothesis.extra.numpy import \
arrays, array_shapes, scalar_dtypes, nested_dtypes
_global_type_lookup.update({
np.dtype: nested_dtypes(),
np.ndarray: arrays(scalar_dtypes(), array_shapes(max_dims=2)),
})
except ImportError: # pragma: no cover
pass
try:
import typing
except ImportError: # pragma: no cover
pass
else:
_global_type_lookup.update({
typing.ByteString: st.binary(),
typing.io.BinaryIO: st.builds(io.BytesIO, st.binary()), # type: ignore
typing.io.TextIO: st.builds(io.StringIO, st.text()), # type: ignore
typing.Reversible: st.lists(st.integers()),
typing.SupportsAbs: st.complex_numbers(),
from hypothesis.extra.numpy import (
arrays,
scalar_dtypes,
unsigned_integer_dtypes,
datetime64_dtypes,
floating_dtypes,
integer_dtypes,
)
from hypothesis import HealthCheck
from superintendent.queueing import _features_to_array
guaranteed_dtypes = one_of(
scalar_dtypes(),
unsigned_integer_dtypes(),
datetime64_dtypes(),
floating_dtypes(),
integer_dtypes(),
)
@composite
def dataframe(draw):
n_cols = draw(integers(min_value=1, max_value=20))
dtypes = draw(
lists(
sampled_from([float, int, str]), min_size=n_cols, max_size=n_cols
)
)
def test_can_create_a_series_of_any_dtype(data):
dtype = np.dtype(data.draw(npst.scalar_dtypes()))
assume(supported_by_pandas(dtype))
series = data.draw(pdst.series(dtype=dtype))
assert series.dtype == pandas.Series([], dtype=dtype).dtype
from hypothesis.extra.pandas import column, data_frames
from hypothesis.strategies import (
booleans,
composite,
floats,
integers,
lists,
one_of,
text,
tuples,
)
from superintendent.distributed.queueing import DatabaseQueue
guaranteed_dtypes = one_of(
np_strategies.scalar_dtypes(),
np_strategies.unsigned_integer_dtypes(),
np_strategies.datetime64_dtypes(),
np_strategies.floating_dtypes(),
np_strategies.integer_dtypes(),
)
@composite
def dataframe(draw):
n_cols = draw(integers(min_value=1, max_value=20))
dtypes = draw(
lists(
one_of(
np_strategies.floating_dtypes(),
np_strategies.integer_dtypes(),
