def check_output(self, expr, expected):
result = expr._compute(
[self.fake_raw_data[input_] for input_ in expr.inputs],
self.mask.index,
self.mask.columns,
self.mask.values,
)
check_allclose(result, expected)
def check_output(self, expr, expected):
result = expr._compute(
[self.fake_raw_data[input_] for input_ in expr.inputs],
self.mask.index,
self.mask.columns,
self.mask.values,
)
check_allclose(result, expected)
def test_rsi(self, seed_value, expected):
rsi = RSI()
today = np.datetime64(1, "ns")
assets = np.arange(3)
out = np.empty((3, ), dtype=float)
np.random.seed(seed_value) # Seed so we get deterministic results.
test_data = np.abs(np.random.randn(15, 3))
out = np.empty((3, ), dtype=float)
rsi.compute(today, assets, out, test_data)
check_allclose(expected, out)
def test_rsi(self, seed_value, expected):
rsi = RSI()
today = np.datetime64(1, 'ns')
assets = np.arange(3)
out = np.empty((3,), dtype=float)
np.random.seed(seed_value) # Seed so we get deterministic results.
test_data = np.abs(np.random.randn(15, 3))
out = np.empty((3,), dtype=float)
rsi.compute(today, assets, out, test_data)
check_allclose(expected, out)
def test_rsi(self, seed_value, expected):
rsi = RSI()
today = datetime64(1, 'ns')
assets = arange(3)
out = empty((3, ), dtype=float)
seed(seed_value) # Seed so we get deterministic results.
test_data = abs(randn(15, 3))
out = empty((3, ), dtype=float)
rsi.compute(today, assets, out, test_data)
check_allclose(expected, out)
def test_returns(self, seed_value, window_length):
returns = Returns(window_length=window_length)
today = datetime64(1, 'ns')
assets = arange(3)
out = empty((3,), dtype=float)
seed(seed_value) # Seed so we get deterministic results.
test_data = abs(randn(window_length, 3))
# Calculate the expected returns
expected = (test_data[-1] - test_data[0]) / test_data[0]
out = empty((3,), dtype=float)
returns.compute(today, assets, out, test_data)
check_allclose(expected, out)
def test_returns(self, seed_value, window_length):
returns = Returns(window_length=window_length)
today = datetime64(1, 'ns')
assets = arange(3)
out = empty((3, ), dtype=float)
seed(seed_value) # Seed so we get deterministic results.
test_data = abs(randn(window_length, 3))
# Calculate the expected returns
expected = (test_data[-1] - test_data[0]) / test_data[0]
out = empty((3, ), dtype=float)
returns.compute(today, assets, out, test_data)
check_allclose(expected, out)
def test_normalizations_hand_computed(self):
"""
Test the hand-computed example in factor.demean.
"""
f = self.f
m = Mask()
c = C()
str_c = C(dtype=categorical_dtype, missing_value=None)
factor_data = array([[1.0, 2.0, 3.0, 4.0], [1.5, 2.5, 3.5, 1.0],
[2.0, 3.0, 4.0, 1.5], [2.5, 3.5, 1.0, 2.0]], )
filter_data = array(
[[False, True, True, True], [True, False, True, True],
[True, True, False, True], [True, True, True, False]],
dtype=bool,
)
classifier_data = array(
[[1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2]],
dtype=int64_dtype,
)
string_classifier_data = LabelArray(
classifier_data.astype(str).astype(object),
missing_value=None,
)
terms = {
'vanilla': f.demean(),
'masked': f.demean(mask=m),
'grouped': f.demean(groupby=c),
'grouped_str': f.demean(groupby=str_c),
'grouped_masked': f.demean(mask=m, groupby=c),
'grouped_masked_str': f.demean(mask=m, groupby=str_c),
}
expected = {
'vanilla':
array([[-1.500, -0.500, 0.500, 1.500],
[-0.625, 0.375, 1.375, -1.125],
[-0.625, 0.375, 1.375, -1.125],
[0.250, 1.250, -1.250, -0.250]], ),
'masked':
array(
[[nan, -1.000, 0.000, 1.000], [-0.500, nan, 1.500, -1.000],
[-0.166, 0.833, nan, -0.666], [0.166, 1.166, -1.333, nan]], ),
'grouped':
array([[-0.500, 0.500, -0.500, 0.500],
[-0.500, 0.500, 1.250, -1.250],
[-0.500, 0.500, 1.250, -1.250],
[-0.500, 0.500, -0.500, 0.500]], ),
'grouped_masked':
array([[nan, 0.000, -0.500, 0.500], [0.000, nan, 1.250, -1.250],
[-0.500, 0.500, nan, 0.000], [-0.500, 0.500, 0.000, nan]])
}
# Changing the classifier dtype shouldn't affect anything.
expected['grouped_str'] = expected['grouped']
expected['grouped_masked_str'] = expected['grouped_masked']
graph = TermGraph(terms)
results = self.run_graph(
graph,
initial_workspace={
f: factor_data,
c: classifier_data,
str_c: string_classifier_data,
m: filter_data,
},
mask=self.build_mask(self.ones_mask(shape=factor_data.shape)),
)
for key, (res, exp) in dzip_exact(results, expected).items():
check_allclose(
res,
exp,
# The hand-computed values aren't very precise (in particular,
# we truncate repeating decimals at 3 places) This is just
# asserting that the example isn't misleading by being totally
# wrong.
atol=0.001,
err_msg="Mismatch for %r" % key)
def test_normalizations_hand_computed(self):
"""
Test the hand-computed example in factor.demean.
"""
f = self.f
m = Mask()
c = C()
str_c = C(dtype=categorical_dtype, missing_value=None)
factor_data = array(
[[1.0, 2.0, 3.0, 4.0],
[1.5, 2.5, 3.5, 1.0],
[2.0, 3.0, 4.0, 1.5],
[2.5, 3.5, 1.0, 2.0]],
)
filter_data = array(
[[False, True, True, True],
[True, False, True, True],
[True, True, False, True],
[True, True, True, False]],
dtype=bool,
)
classifier_data = array(
[[1, 1, 2, 2],
[1, 1, 2, 2],
[1, 1, 2, 2],
[1, 1, 2, 2]],
dtype=int64_dtype,
)
string_classifier_data = LabelArray(
classifier_data.astype(str).astype(object),
missing_value=None,
)
terms = {
'vanilla': f.demean(),
'masked': f.demean(mask=m),
'grouped': f.demean(groupby=c),
'grouped_str': f.demean(groupby=str_c),
'grouped_masked': f.demean(mask=m, groupby=c),
'grouped_masked_str': f.demean(mask=m, groupby=str_c),
}
expected = {
'vanilla': array(
[[-1.500, -0.500, 0.500, 1.500],
[-0.625, 0.375, 1.375, -1.125],
[-0.625, 0.375, 1.375, -1.125],
[0.250, 1.250, -1.250, -0.250]],
),
'masked': array(
[[nan, -1.000, 0.000, 1.000],
[-0.500, nan, 1.500, -1.000],
[-0.166, 0.833, nan, -0.666],
[0.166, 1.166, -1.333, nan]],
),
'grouped': array(
[[-0.500, 0.500, -0.500, 0.500],
[-0.500, 0.500, 1.250, -1.250],
[-0.500, 0.500, 1.250, -1.250],
[-0.500, 0.500, -0.500, 0.500]],
),
'grouped_masked': array(
[[nan, 0.000, -0.500, 0.500],
[0.000, nan, 1.250, -1.250],
[-0.500, 0.500, nan, 0.000],
[-0.500, 0.500, 0.000, nan]]
)
}
# Changing the classifier dtype shouldn't affect anything.
expected['grouped_str'] = expected['grouped']
expected['grouped_masked_str'] = expected['grouped_masked']
graph = TermGraph(terms)
results = self.run_graph(
graph,
initial_workspace={
f: factor_data,
c: classifier_data,
str_c: string_classifier_data,
m: filter_data,
},
mask=self.build_mask(self.ones_mask(shape=factor_data.shape)),
)
for key, (res, exp) in dzip_exact(results, expected).items():
check_allclose(
res,
exp,
# The hand-computed values aren't very precise (in particular,
# we truncate repeating decimals at 3 places) This is just
# asserting that the example isn't misleading by being totally
# wrong.
atol=0.001,
err_msg="Mismatch for %r" % key
)