def ints_floats_complex_or_booleans(draw):
dtypes = (
unsigned_integer_dtypes(endianness="="),
integer_dtypes(endianness="="),
floating_dtypes(endianness="="),
# complex_number_dtypes(endianness="="),
boolean_dtypes(),
)
return draw(one_of(dtypes))
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(
st.one_of(
npst.boolean_dtypes(),
npst.integer_dtypes(endianness="="),
npst.floating_dtypes(endianness="="),
npst.complex_number_dtypes(endianness="="),
npst.datetime64_dtypes(endianness="="),
npst.timedelta64_dtypes(endianness="="),
).filter(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 one_of_supported_dtypes(draw):
# A strategy that selects a dtype that riptable is known to handle.
# dtype size 16-bit is not supported
# little endian is not supported
return one_of(
boolean_dtypes(),
integer_dtypes(endianness="=", sizes=(8, 32, 64)),
unsigned_integer_dtypes(endianness="=", sizes=(8, 32, 64)),
floating_dtypes(endianness="=", sizes=(32, 64)),
byte_string_dtypes(endianness="="),
unicode_string_dtypes(endianness="="),
# the following dtypes are not supported
# complex_number_dtypes(),
# datetime64_dtypes(),
# timedelta64_dtypes(),
)
booleans,
dictionaries,
floats,
integers,
lists,
one_of,
recursive,
text,
)
import superintendent.prioritisation
from superintendent import SemiSupervisor
primitive_strategy = text() | integers() | floats(allow_nan=False) | booleans()
guaranteed_dtypes = (boolean_dtypes()
| integer_dtypes()
| floating_dtypes()
| unicode_string_dtypes())
container_strategy = dictionaries(
text(), primitive_strategy) | lists(primitive_strategy)
nested_strategy = recursive(
container_strategy,
lambda children: lists(children) | dictionaries(text(), children),
)
container_strategy = dictionaries(
text(), primitive_strategy) | lists(primitive_strategy)
dictionaries,
floats,
integers,
lists,
one_of,
recursive,
text,
)
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_validate
from superintendent.distributed import SemiSupervisor
primitive_strategy = text() | integers() | floats(allow_nan=False) | booleans()
guaranteed_dtypes = (
boolean_dtypes()
| integer_dtypes()
| floating_dtypes()
| unicode_string_dtypes()
)
container_strategy = dictionaries(text(), primitive_strategy) | lists(
primitive_strategy
)
nested_strategy = recursive(
container_strategy,
lambda children: lists(children) | dictionaries(text(), children),
)
container_strategy = dictionaries(text(), primitive_strategy) | lists(
def generate_array_and_where(draw, shape, dtype):
arr = draw(arrays(shape=shape, dtype=dtype))
where = draw(arrays(shape=arr.shape, dtype=boolean_dtypes()))
return arr, where
from hypothesis import given
from hypothesis import strategies as st
from hypothesis.extra import numpy as nst
from oh import Config
# ints are not strictly json but they're important & supported by Python's json module
jsons = st.recursive(
st.none() | st.booleans() | st.integers() | st.floats() | st.text(),
lambda children:
(st.lists(children)
| st.dictionaries(st.text(ascii_letters, min_size=1), children)),
)
numpy_scalar_dtypes = st.one_of(
nst.boolean_dtypes(),
nst.integer_dtypes(),
nst.unsigned_integer_dtypes(),
nst.floating_dtypes(),
)
@given(jsons)
def test_json_types(value):
c = Config({"x": value})
assert isinstance(c.x, type(value))
assert c.x == value or (isinstance(c.x, float) and isnan(c.x)
and isinstance(value, float) and isnan(value))
assert_valid_json(c)
import pandas as pd
from hypothesis import given
from hypothesis.extra.pandas import column, columns, data_frames, series
from hypothesis.strategies import (
booleans,
dictionaries,
floats,
integers,
lists,
one_of,
recursive,
text,
)
from superintendent.distributed.serialization import data_dumps, data_loads
guaranteed_dtypes = (np_strategies.boolean_dtypes()
| np_strategies.integer_dtypes()
| np_strategies.floating_dtypes()
| np_strategies.unicode_string_dtypes())
json_array = recursive(
floats(allow_nan=False) | integers() | text() | booleans(), lists)
json_object = recursive(
floats(allow_nan=False) | integers() | text() | booleans(),
partial(dictionaries, text()),
)
def exact_element_match(a, b):
if isinstance(a, np.ndarray) and isinstance(b, np.ndarray):
try:
from hypothesis import given
from hypothesis.extra.pandas import column, columns, data_frames, series
from hypothesis.strategies import (
booleans,
dictionaries,
floats,
integers,
lists,
one_of,
recursive,
text,
)
from superintendent.distributed.serialization import data_dumps, data_loads
guaranteed_dtypes = (
np_strategies.boolean_dtypes()
| np_strategies.integer_dtypes()
| np_strategies.floating_dtypes()
| np_strategies.unicode_string_dtypes()
)
json_array = recursive(
floats(allow_nan=False) | integers() | text() | booleans(), lists
)
json_object = recursive(
floats(allow_nan=False) | integers() | text() | booleans(),
partial(dictionaries, text()),
)
