def test_can_create_a_series_of_any_dtype(data):
dtype = np.dtype(data.draw(npst.scalar_dtypes()))
assume(supported_by_pandas(dtype))
# Use raw data to work around pandas bug in repr. See
# https://github.com/pandas-dev/pandas/issues/27484
series = data.conjecture_data.draw(pdst.series(dtype=dtype))
assert series.dtype == pandas.Series([], dtype=dtype).dtype
def series_strategy(
pandas_dtype: PandasDtype,
strategy: Optional[SearchStrategy] = None,
*,
checks: Optional[Sequence] = None,
nullable: Optional[bool] = False,
allow_duplicates: Optional[bool] = True,
name: Optional[str] = None,
size: Optional[int] = None,
):
"""Strategy to generate a pandas Series.
:param pandas_dtype: :class:`pandera.dtypes.PandasDtype` instance.
:param strategy: an optional hypothesis strategy. If specified, the
pandas dtype strategy will be chained onto this strategy.
:param checks: sequence of :class:`~pandera.checks.Check` s to constrain
the values of the data in the column/index.
:param nullable: whether or not generated Series contains null values.
:param allow_duplicates: whether or not generated Series contains
duplicates.
:param name: name of the Series.
:param size: number of elements in the Series.
:returns: ``hypothesis`` strategy.
"""
elements = field_element_strategy(pandas_dtype, strategy, checks=checks)
strategy = (
pdst.series(
elements=elements,
dtype=pandas_dtype.numpy_dtype,
index=pdst.range_indexes(
min_size=0 if size is None else size, max_size=size
),
unique=not allow_duplicates,
)
.filter(lambda x: x.shape[0] > 0)
.map(lambda x: x.rename(name))
.map(lambda x: x.astype(pandas_dtype.str_alias))
)
if nullable:
strategy = null_field_masks(strategy)
def undefined_check_strategy(strategy, check):
"""Strategy for checks with undefined strategies."""
warnings.warn(
"Vectorized check doesn't have a defined strategy."
"Falling back to filtering drawn values based on the check "
"definition. This can considerably slow down data-generation."
)
def _check_fn(series):
return check(series).check_passed
return strategy.filter(_check_fn)
for check in checks if checks is not None else []:
if not hasattr(check, "strategy") and not check.element_wise:
strategy = undefined_check_strategy(strategy, check)
return strategy
def two_equal_size_series(draw):
series_strategy = series(
dtype=np.float64, elements=float_strategy, index=range_indexes(min_size=1)
)
s1 = draw(series_strategy)
s2 = draw(series_strategy)
assume(len(s1) == len(s2))
return s1, s2
import pandas as pd
import pytz
from hypothesis import given, settings
from hypothesis.extra.pandas import columns, indexes, series
from liualgotrader.fincalcs.support_resistance import get_local_maxima
est = pytz.timezone("US/Eastern")
@settings(deadline=None, max_examples=100)
@given(
series(
index=indexes(
elements=st.datetimes(min_value=datetime(2000, 1, 1),
max_value=datetime(2040, 1, 1)),
dtype=pd.DatetimeIndex,
),
elements=st.floats(),
dtype=float,
), )
def test_get_local_maxima(series: pd.Series):
print(series)
r = get_local_maxima(series)
if r.empty:
assert r.empty # nosec
else:
assert not r.empty # nosec
print("result", r)
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
dates(min_value=datetime.date(2019, 1, 1),
max_value=datetime.date.today()),
nats,
),
)
])
opleverstatus_st = data_frames([
column("opleverstatus",
dtype="object",
elements=sampled_from(br.opleverstatussen))
])
date_series_st = series(
dates(min_value=datetime.date(2019, 1, 1),
max_value=datetime.date.today()),
dtype="datetime64[ns]",
)
@given(date_series_st, integers(min_value=-10, max_value=10))
def test_is_date_set(test_series: pd.Series, time_delta_days: int):
opgeleverd = br.is_date_set(test_series, time_delta_days)
time_point = datetime.date.today() - datetime.timedelta(
days=time_delta_days)
assert len(test_series) == len(opgeleverd)
if not test_series.empty:
assert ((~test_series.isna() &
(test_series <= time_point)) == opgeleverd).all()
def test_can_fill_series():
nan_backed = pdst.series(
elements=st.floats(allow_nan=False), fill=st.just(float("nan"))
)
find_any(nan_backed, lambda x: np.isnan(x).any())
import hypothesis.extra.pandas as pdst
import hypothesis.strategies as st
from hypothesis import assume, given
from tests.common.debug import find_any
from tests.pandas.helpers import supported_by_pandas
@given(st.data())
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
@given(pdst.series(dtype=float, index=pdst.range_indexes(min_size=2, max_size=5)))
def test_series_respects_size_bounds(s):
assert 2 <= len(s) <= 5
def test_can_fill_series():
nan_backed = pdst.series(
elements=st.floats(allow_nan=False), fill=st.just(float("nan"))
)
find_any(nan_backed, lambda x: np.isnan(x).any())
@given(pdst.series(dtype=int))
def test_can_generate_integral_series(s):
assert s.dtype == np.dtype(int)
def test_can_fill_series():
nan_backed = pdst.series(elements=st.floats(allow_nan=False),
fill=st.just(np.nan))
find_any(nan_backed, lambda x: np.isnan(x).any())
print('The best AMS Score is {:.3f} at a Cut Parameter of {:.2f}'.format(
max(y), x[np.argmax(y)]))
#TESTING "NN_OUTPUT_TO_AMS":
from hypothesis import given, settings
import hypothesis.strategies as st
import hypothesis.extra
from hypothesis.extra.numpy import arrays
from hypothesis.extra.pandas import series, range_indexes
@given(x=st.floats(0.5, 1),
y=arrays(np.float64, (1, 100000),
elements=st.floats(0, 1),
fill=None,
unique=False),
z=arrays(np.int8, (1, 100000), elements=None, fill=None, unique=False),
t=series(elements=None,
dtype=np.float64,
index=range_indexes(min_size=1, max_size=1),
fill=None,
unique=False))
@settings(deadline=None)
def test_NN_output_to_AMS(x, y, z, t):
b_reg = 10
s = sum(t[(y[:, 1] > x) & (z[:, 1] == 1)])
b = sum(t[(y[:, 1] > x) & (z[:, 1] == 0)])
AMS = np.sqrt(2 * ((s + b + b_reg) * np.log(1 + s / (b + b_reg)) - s))
assert NN_output_to_AMS(x, y, z, t) == AMS
df, seasonalities = td.sample_n_gaussian_ts_as_df(10, '2019-01-01',
'2020-01-01', Interval.D)
assert df.shape == (366, 10)
# globals for tests
index_len = 100
train_size_min = 0.1
train_size_max = 0.9
@given(features=data_frames(columns(['feat1', 'feat2', 'feat3'], dtype=float),
index=range_indexes(min_size=index_len,
max_size=index_len)),
labels=series(elements=st.integers(min_value=0, max_value=3),
index=range_indexes(min_size=index_len,
max_size=index_len)),
time_stamps=st.integers(min_value=1, max_value=10),
train_size=st.floats(min_value=train_size_min,
max_value=train_size_max,
allow_infinity=False,
allow_nan=False))
def test_split_categorical_time_series_labels(features: pd.DataFrame,
labels: pd.Series,
time_stamps: int,
train_size: float):
assume(train_size == round(train_size,
2)) # limit to only 2 digits after comma
assume(features.isnull().any(1).sum() == 0) # forbid nans
features_train, features_test, labels_train, labels_test = \
tu.split_categorical_time_series_labels(features, labels, time_stamps, train_size)
lst_text = lists(elements=text(alphabet=list(string.printable),
min_size=4,
max_size=10),
min_size=1).example()
@given(text(min_size=3))
@example(' BAD label ')
@example(' BAD label !@#$!%!%')
def test_make_good_label(s):
print(type(make_good_label(s)))
assert isinstance(make_good_label(s), str)
assert make_good_label(' BAD label ') == 'bad_label'
@given(series(dtype=np.unicode_))
@example(series(dtype=np.int_).example())
@example(series(dtype=float).example())
@example(series(dtype=bool).example())
def test_completeness(srs_t):
print(srs_t, srs_t.dtype.kind)
assert np.isclose(completeness(df_l['flt_1']), 0.833333)
assert isinstance(completeness(srs_t), float)
def test_mash():
df_result = mash(df_l, 'flt_1')
assert df_result.shape[0] == 5
df_result = mash(df_l, 'int_1')
assert df_result.shape[0] == 5
df_result = mash(df_l, 'int_1', keep_zeros=True)
@given(
input_=np_strategies.arrays(
guaranteed_dtypes, np_strategies.array_shapes()
)
)
def test_numpy_array_serialisation(input_):
serialised = data_dumps(input_)
assert isinstance(serialised, str)
deserialised = data_loads(serialised)
assert isinstance(deserialised, type(input_))
assert pytest.helpers.exact_element_match(input_, deserialised)
@given(
input_=one_of(series(dtype=int), series(dtype=float), series(dtype=str))
)
def test_pandas_series_serialisation(input_):
serialised = data_dumps(input_)
assert isinstance(serialised, str)
deserialised = data_loads(serialised)
assert isinstance(deserialised, type(input_))
assert pytest.helpers.exact_element_match(input_, deserialised)
@given(
input_=one_of(
data_frames(columns(3, dtype=int)),
data_frames(columns(3, dtype=float)),
data_frames(columns(3, dtype=str)),
data_frames(
#
# split_at = split_at.sort()
# if 0 not in split_at:
# split_at = [0].extend(split_at)
#
# new_text = []
# for i in split_at[1:]:
# new_text.append(text[i-1:i])
#
# new_text.append(text[i[-1]:len(text)])
@settings(verbosity=Verbosity.verbose)
@given(data=expd.series(elements=st.text(
u'abcdefghijklmnopqrstuvwxyz0123456789-_/ ', min_size=25, max_size=500),
dtype=None,
index=None,
fill=None,
unique=True),
upper=expd.series(elements=st.text(u'ABCDEFGHIJKLMNOPQRSTUVWXYZ',
min_size=25,
max_size=500),
dtype=None,
index=None,
fill=None,
unique=True),
non_ascii=expd.series(elements=st.text(st.characters(
min_codepoint=256, max_codepoint=1000),
min_size=25,
max_size=500),
dtype=None,
index=None,
class TestUtilsModule(unittest.TestCase):
@given(s=st.text())
def test_belongs1(self, s):
l1 = ['apples', 'oranges', 'pears']
with pytest.raises(ValueError):
assert utils.belongs(s, l1)
def test_belongs2(self):
l1 = ['apples', 'oranges', 'pears']
assert utils.belongs("apples", l1)
def test_instance_check(self):
# single example
x = ['abba', 'father', 'cross']
assert utils.instance_check(x, list)
y = np.array([1, 2, 3], dtype=float)
assert utils.instance_check(y, np.ndarray)
# multiples given a tuple
ij = True
ji = False
assert utils.instance_check((ij, ji), bool)
@given(st.integers(min_value=0))
def test_nonnegative1(self, x):
assert utils.nonnegative(x, int)
@given(st.integers(max_value=-1))
def test_nonnegative2(self, x):
with pytest.raises(AttributeError):
assert utils.nonnegative(x, int)
def test_bounds_check(self):
assert utils.bounds_check(math.pi, math.pi - 0.00001,
math.pi + 0.00001)
assert utils.bounds_check(5, 5 - 1, 5 + 1)
@given(numpy.arrays(float, (100, 2)), numpy.arrays(float, (100, 2)))
def test_arrays_equal_size(self, x, y):
assert utils.arrays_equal_size(x, y)
@given(numpy.arrays(float, (100, 2)), st.text())
def test_arrays_dimension(self, array, s):
with pytest.raises(ValueError):
assert utils.arrays_dimension(array, s)
def test_check_list_type(self):
x = [1, 2, 3]
assert utils.check_list_type(x, int)
y = ['a', 'b', 'c']
assert utils.check_list_type(y, str)
with pytest.raises(TypeError):
assert utils.check_list_type(x, str)
@given(st.integers(min_value=1, max_value=150),
st.sampled_from(["square", "diag"]),
st.integers(min_value=1, max_value=15),
st.integers(min_value=1, max_value=15),
st.floats(min_value=0.01, max_value=10.))
def test_nearest_factors1(self, n, shape, cut, sr, wvar):
# returns a tuple
res = utils.nearest_factors(n, shape, cut, sr, wvar)
assert type(res) == tuple
assert isinstance(res[0], (np.int, np.int32, np.int64))
assert isinstance(res[1], (np.int, np.int32, np.int64))
diff = np.abs(res[0] * res[1] - sr)
assert diff - 10 < diff < diff + 10
@given(st.lists(st.text(), min_size=1))
def test_zipe1(self, x):
z = utils.zipe(x)
assert type(z) == list
assert len(z) == len(x)
assert z[0] == x[0]
@given(st.lists(st.text(), min_size=1), st.lists(st.integers(),
min_size=1))
def test_zipe2(self, x, y):
z = utils.zipe(x, y)
assert type(z) == list
assert len(z) == max(len(x), len(y))
assert z[0][0] == x[0]
assert z[0][1] == y[0]
def test_zipe3(self):
x = [1, 2, 3]
assert utils.zipe(x) == x
def test_umap(self):
"""A mapping function"""
def _f(x):
"""Blank."""
return x**2
assert utils.umap(_f, [2, 4, 6]) == [4, 16, 36]
def _g(x, y):
"""Blank."""
return x / y
assert utils.umap(_g, [3, 6, 9], [1, 2, 3]) == [3, 3, 3]
def test_umapc(self):
"""mapping w cache"""
def _f(x):
"""Blank."""
return x**2
assert utils.umapc("test.pkl", _f, [2, 4, 6]) == [4, 16, 36]
# re-run to load from file
assert utils.umapc("test.pkl", _f, [2, 4, 6]) == [4, 16, 36]
assert os.path.isfile("test.pkl")
os.remove("test.pkl")
def test_umapp(self):
def _f(x):
"""Blank."""
return x**2
assert utils.umapp(_f, [2, 4, 6]) == [4, 16, 36]
def _g(x, y):
"""Blank."""
return x / y
assert utils.umapp(_g, [3, 6, 9], [1, 2, 3]) == [3, 3, 3]
def test_umappc(self):
"""mapping w cache"""
def _f(x):
"""Blank."""
return x**2
assert utils.umappc("test.pkl", _f, [2, 4, 6]) == [4, 16, 36]
# re-run to load from file
assert utils.umappc("test.pkl", _f, [2, 4, 6]) == [4, 16, 36]
assert os.path.isfile("test.pkl")
os.remove("test.pkl")
def _g(x, y):
"""Blank."""
return x / y
assert utils.umappc("test2.pkl", _g, [3, 6, 9], [1, 2, 3]) == [3, 3, 3]
assert utils.umappc("test2.pkl", _g, [3, 6, 9], [1, 2, 3]) == [3, 3, 3]
assert os.path.isfile("test2.pkl")
os.remove("test2.pkl")
@given(pandas.series(dtype=int))
def test_panderfy(self, ser):
# make a copy
cpy = ser.copy()
pd.testing.assert_series_equal(ser, utils.transform_copy(ser, cpy))
@given(pandas.indexes(dtype=int))
def test_panderfy2(self, ser):
# make a copy
cpy = ser.copy()
pd.testing.assert_index_equal(ser, utils.transform_copy(ser, cpy))
@given(
pandas.data_frames(
[pandas.column("A", dtype=int),
pandas.column("B", dtype=float)]))
def test_panderfy3(self, ser):
# make a copy
cpy = ser.copy()
pd.testing.assert_frame_equal(ser, utils.transform_copy(ser, cpy))
@given(numpy.arrays(int, (100, )))
def test_remove_na(self, x):
np.testing.assert_array_almost_equal(x, utils.remove_na(x))
def test_dict_to_tuple(self):
d = {"a": 1, "b": 2, "c": 3}
assert utils.dict_to_tuple(d) == (("a", 1), ("b", 2), ("c", 3))
def test_dictsplit(self):
d = {"a": 1, "b": 2, "c": 3}
assert utils.dictsplit(d) == (tuple(d.keys()), tuple(d.values()))
def test_dictzip(self):
x = [1, 2, 3]
y = ['a', 'b', 'c']
assert utils.dictzip(x, y) == dict(zip(x, y))
def test_set_like1(self):
x = ['a', 'b', 'a', 'c']
assert np.all(utils.set_like(x) == pd.Index(['a', 'b', 'c']))
def test_union(self):
x = ["fi", "fo", "fum"]
y = ["fi", "yo", "sum"]
z = ["fi", "fe", "sun"]
assert np.all(
utils.union(x, y) == pd.Index(["fi", "fo", "fum", "sum", "yo"]))
assert np.all(
utils.union(x, y, z) == pd.Index(
["fe", "fi", "fo", "fum", "sum", "sun", "yo"]))
def test_intersect(self):
x = ["fi", "fo", "sun"]
y = ["fi", "yo", "sum"]
z = ["fi", "fe", "sun"]
assert np.all(utils.intersect(x, z) == pd.Index(["fi", "sun"]))
assert np.all(utils.intersect(x, y, z) == pd.Index(["fi"]))
def test_difference(self):
x = ["fi", "fo", "sun"]
z = ["fi", "yo", "sum"]
assert np.all(
utils.difference(x, z) == pd.Index(["fo", "sum", "sun", "yo"]))
def test_absdifference(self):
x = ["fi", "fo", "sun"]
z = ["fi", "yo", "sum"]
assert np.all(utils.absdifference(x, z) == pd.Index(["fo", "sun"]))
def test_pairwise(self):
x = [1, 2, 3]
f = lambda i, j: i * j
np.testing.assert_array_equal(np.array(utils.pairwise(f, x)),
np.array([2, 3, 6]))
)
def test_minmax_scaler_np(array):
scaler = MinMaxScaler()
scaler.fit(array)
assert (scaler.transform(array).min(axis=0) >= 0).all()
assert (scaler.transform(array).max(axis=0) <= 1).all()
np.testing.assert_allclose(scaler.fit(array).transform(array), scaler.fit_transform(array))
np.testing.assert_allclose(array, scaler.inv_transform(scaler.transform(array)))
@given(
series(
unique=True,
elements=st.floats(
max_value=1e8, min_value=-1e8, allow_nan=False, allow_infinity=False
),
index=range_indexes(min_size=2)
)
)
def test_minmax_scaler_series(series):
scaler = MinMaxScaler()
scaler.fit(series)
assert scaler.transform(series).min() >= 0
assert scaler.transform(series).max() <= 1
np.testing.assert_allclose(scaler.fit(series).transform(series), scaler.fit_transform(series))
np.testing.assert_allclose(series, scaler.inv_transform(scaler.transform(series)), rtol=1e-06)
from tests.common.debug import find_any
from tests.pandas.helpers import supported_by_pandas
@given(st.data())
def test_can_create_a_series_of_any_dtype(data):
dtype = np.dtype(data.draw(npst.scalar_dtypes()))
assume(supported_by_pandas(dtype))
# Use raw data to work around pandas bug in repr. See
# https://github.com/pandas-dev/pandas/issues/27484
series = data.conjecture_data.draw(pdst.series(dtype=dtype))
assert series.dtype == pandas.Series([], dtype=dtype).dtype
@given(
pdst.series(dtype=float, index=pdst.range_indexes(min_size=2, max_size=5)))
def test_series_respects_size_bounds(s):
assert 2 <= len(s) <= 5
def test_can_fill_series():
nan_backed = pdst.series(elements=st.floats(allow_nan=False),
fill=st.just(np.nan))
find_any(nan_backed, lambda x: np.isnan(x).any())
@given(pdst.series(dtype=int))
def test_can_generate_integral_series(s):
assert s.dtype == np.dtype(int)
else:
return all(a_ == b_ or (np.isnan(a_) and np.isnan(b_))
for a_, b_ in zip(a, b))
@given(input_=np_strategies.arrays(guaranteed_dtypes,
np_strategies.array_shapes()))
def test_numpy_array_serialisation(input_):
serialised = data_dumps(input_)
assert isinstance(serialised, str)
deserialised = data_loads(serialised)
assert isinstance(deserialised, type(input_))
assert pytest.helpers.exact_element_match(input_, deserialised)
@given(input_=one_of(series(dtype=int), series(dtype=float),
series(dtype=str)))
def test_pandas_series_serialisation(input_):
serialised = data_dumps(input_)
assert isinstance(serialised, str)
deserialised = data_loads(serialised)
assert isinstance(deserialised, type(input_))
assert pytest.helpers.exact_element_match(input_, deserialised)
@given(input_=one_of(
data_frames(columns(3, dtype=int)),
data_frames(columns(3, dtype=float)),
data_frames(columns(3, dtype=str)),
data_frames([column(dtype=str),
column(dtype=float),
import numpy as np
import pandas as pd
import pytest
import xarray as xr
pytest.importorskip("hypothesis")
import hypothesis.extra.numpy as npst # isort:skip
import hypothesis.extra.pandas as pdst # isort:skip
import hypothesis.strategies as st # isort:skip
from hypothesis import given # isort:skip
numeric_dtypes = st.one_of(npst.unsigned_integer_dtypes(),
npst.integer_dtypes(), npst.floating_dtypes())
numeric_series = numeric_dtypes.flatmap(lambda dt: pdst.series(dtype=dt))
an_array = npst.arrays(
dtype=numeric_dtypes,
shape=npst.array_shapes(max_dims=2), # can only convert 1D/2D to pandas
)
@st.composite
def datasets_1d_vars(draw) -> xr.Dataset:
"""Generate datasets with only 1D variables
Suitable for converting to pandas dataframes.
"""
# Generate an index for the dataset
idx = draw(pdst.indexes(dtype="u8", min_size=0, max_size=100))
class TestStringModule(unittest.TestCase):
def test_common_substrings(self):
t = ['hello there!', 'hey there', 'well hello there', 'there is a disturbance']
x1 = turb.str.common_substrings("high tower", "low tower")
assert type(x1) == np.str
assert x1 == " tower"
x2 = turb.str.common_substrings(t)
# should return a series
assert type(x2) == pd.Series
assert len(x2) == 2
assert x2.index[0] == 'there'
assert x2.iloc[0] == 3
@given(s1=st.one_of(
st.text(), st.lists(st.text())),
s2=st.one_of(
st.text(), st.lists(st.text())))
def test_common_substrings2(self, s1, s2):
x1 = turb.str.common_substrings(s1, s2)
note(x1)
if type(s1) == str and type(s2) == str:
assert type(x1) == str
else:
assert type(x1) == pd.Series
def test_pattern(self):
_in = ["hello", "bellow", "mellow", "swellow"]
x1 = turb.str.pattern("ellow", _in)
assert type(x1) == pd.Index
assert len(x1) == 3
assert np.all(x1, pd.Index(['bellow', 'mellow', 'swellow']))
x2 = turb.str.pattern("^he | ^b", _in)
assert type(x2) == pd.Index
assert len(x2) == 2
assert np.all(x2, pd.Index(['hello', 'bellow']))
_in2 = int_dataframe_example()
x3 = turb.str.pattern("^he | ^b", _in2)
assert type(x3) == pd.Index
assert len(x3) == 2
assert np.all(x3, pd.Index(['hello', 'bellow']))
@given(words=st.one_of(
st.lists(random_or_regex, unique=True),
pandas.series(elements=random_or_regex, dtype=str, unique=True),
pandas.indexes(elements=random_or_regex, dtype=str, unique=True),
))
def test_pattern2(self, words):
res = list(turb.str.pattern("ellow", words))
# select all that conform to the pattern..?
actual = [x for x in words if re.search("ellow", x)]
self.assertEqual(res, actual)
def test_patproduct(self):
x1 = turb.str.patproduct("%s%d", ("x", "y"), range(100))
assert type(x1) == list
assert len(x1) == 200
assert x1[0] == 'x0'
assert x1[-1] == 'y99'
# second example
x2 = turb.str.patproduct("%s_%s", ("repl", "quality"), ("sum", "prod"))
assert type(x2) == list
assert len(x2) == 4
assert x2[0] == 'repl_sum'
assert x2[-1] == "quality_prod"
@given(a=st.tuples(st.text(min_size=1), st.text(min_size=1)),
b=st.lists(st.text(min_size=1)))
def test_patproduct2(self, a, b):
x1 = turb.str.patproduct("%s%s", a, b)
self.assertListEqual(x1, ["%s%s" % item for item in it.product(a, b)])
@given(s=st.text(max_size=50),
strat=st.sampled_from(['middle', 'end']))
def test_shorten(self, s, strat):
ns = turb.str.shorten(s, strategy=strat)
note(ns)
assert type(ns) == np.str
if len(s) < 15:
assert len(s) == len(ns)
else:
assert len(ns) <= 15
@given(st.lists(st.text(max_size=70)))
def test_shorten2(self, ls):
nls = turb.str.shorten(ls)
assert type(nls) == list
def test_string_replace(self):
t = ['hello', 'i am', 'pleased']
r = ['hello', 'u am', 'pleased']
x1 = turb.str.string_replace(t, ('i', 'u'))
assert type(x1) == list
assert len(x1) == 3
self.assertEqual(x1, r)
@given(st.text(min_size=1))
def test_string_replace2(self, s):
op1 = ('u', 'i')
res = s.replace(*op1)
assert turb.str.string_replace(s, op1) == res
@given(st.lists(st.text(min_size=1), min_size=1))
def test_string_replace3(self, s):
ops = [('u', 'i'), ('a', 'e')]
res = s[0].replace(*ops[0]).replace(*ops[1])
assert turb.str.string_replace(s, *ops)[0] == res
def test_reformat(self):
df = str_dataframe_example()
x1 = turb.str.reformat("{hello}{bellow}", df)
assert type(x1) == pd.Series
pd.testing.assert_series_equal(x1, pd.Series(['carrotsbird', "applesshark", "pearsdragon"], dtype=object))
@given(df=pandas.data_frames([pandas.column("A", st.text(min_size=1),
dtype=str, unique=True),
pandas.column("B", st.text(min_size=1),
dtype=str, unique=True)]))
def test_reformat2(self, df):
x1 = turb.str.reformat("{A}{B}", df)
note(x1)
pd.testing.assert_series_equal(x1, df['A'] + df['B'])
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_confusing_object_dtype_aliases():
pdst.series(elements=st.tuples(st.integers()), dtype=tuple).example()
nested_strategy = recursive(
container_strategy,
lambda children: lists(children) | dictionaries(text(), children),
)
container_strategy = dictionaries(
text(), primitive_strategy) | lists(primitive_strategy)
nested_strategy = recursive(
container_strategy,
lambda children: lists(children) | dictionaries(text(), children),
)
numpy_strategy = arrays(guaranteed_dtypes, array_shapes())
pandas_series = series(dtype=int) | series(dtype=float) | series(dtype=str)
pandas_dfs = (data_frames(columns(3, dtype=int))
| data_frames(columns(3, dtype=float))
| data_frames(columns(3, dtype=str))
| data_frames(
[column(dtype=str),
column(dtype=float),
column(dtype=int)]))
possible_input_data = one_of(
lists(primitive_strategy),
numpy_strategy,
pandas_series,
# pandas_dfs
)
from datetime import datetime
import hypothesis.strategies as st
import pandas as pd
import pytz
from hypothesis import given, settings
from hypothesis.extra.pandas import indexes, series
from liualgotrader.fincalcs.trends import SeriesTrendType, get_series_trend
@settings(max_examples=200)
@given(
series(
index=indexes(
elements=st.datetimes(min_value=datetime(2000, 1, 1),
max_value=datetime(2040, 1, 1)),
dtype=pd.DatetimeIndex,
),
elements=st.floats(
allow_nan=False,
allow_infinity=False,
),
dtype=float,
), )
def test_get_series_trend(serie: pd.Series):
print(serie)
r, t = get_series_trend(serie)
print("result", r, t)
