def check_terms(self, terms, expected, initial_workspace, mask):
"""
Compile the given terms into a TermGraph, compute it with
initial_workspace, and compare the results with ``expected``.
"""
graph = TermGraph(terms)
results = self.run_graph(graph, initial_workspace, mask)
for key, (res, exp) in dzip_exact(results, expected).items():
check_arrays(res, exp)
def check_terms(self, terms, expected, initial_workspace, mask):
"""
Compile the given terms into a TermGraph, compute it with
initial_workspace, and compare the results with ``expected``.
"""
graph = TermGraph(terms)
results = self.run_graph(graph, initial_workspace, mask)
for key, (res, exp) in dzip_exact(results, expected).items():
check_arrays(res, exp)
def assert_dict_equal(result, expected, path=(), msg="", **kwargs):
_check_sets(viewkeys(result), viewkeys(expected), msg, path + (".%s()" % ("viewkeys" if PY2 else "keys"),), "key")
failures = []
for k, (resultv, expectedv) in iteritems(dzip_exact(result, expected)):
try:
assert_equal(resultv, expectedv, path=path + ("[%r]" % k,), msg=msg, **kwargs)
except AssertionError as e:
failures.append(str(e))
if failures:
raise AssertionError("\n".join(failures))
def assert_dict_equal(result, expected, path=(), msg='', **kwargs):
if path is None:
path = ()
result_keys = viewkeys(result)
expected_keys = viewkeys(expected)
if result_keys != expected_keys:
if result_keys > expected_keys:
diff = result_keys - expected_keys
msg = 'extra %s in result: %r' % (_s('key', diff), diff)
elif result_keys < expected_keys:
diff = expected_keys - result_keys
msg = 'result is missing %s: %r' % (_s('key', diff), diff)
else:
sym = result_keys ^ expected_keys
in_result = sym - expected_keys
in_expected = sym - result_keys
msg = '%s only in result: %s\n%s only in expected: %s' % (
_s('key', in_result),
in_result,
_s('key', in_expected),
in_expected,
)
raise AssertionError(
'%sdict keys do not match\n%s' % (
_fmt_msg(msg),
_fmt_path(path + ('.%s()' % ('viewkeys' if PY2 else 'keys'),)),
),
)
failures = []
for k, (resultv, expectedv) in iteritems(dzip_exact(result, expected)):
try:
assert_equal(
resultv,
expectedv,
path=path + ('[%r]' % k,),
msg=msg,
**kwargs
)
except AssertionError as e:
failures.append(str(e))
if failures:
raise AssertionError('\n'.join(failures))
def assert_dict_equal(result, expected, path=(), msg='', **kwargs):
if path is None:
path = ()
result_keys = viewkeys(result)
expected_keys = viewkeys(expected)
if result_keys != expected_keys:
if result_keys > expected_keys:
diff = result_keys - expected_keys
msg = 'extra %s in result: %r' % (_s('key', diff), diff)
elif result_keys < expected_keys:
diff = expected_keys - result_keys
msg = 'result is missing %s: %r' % (_s('key', diff), diff)
else:
sym = result_keys ^ expected_keys
in_result = sym - expected_keys
in_expected = sym - result_keys
msg = '%s only in result: %s\n%s only in expected: %s' % (
_s('key', in_result),
in_result,
_s('key', in_expected),
in_expected,
)
raise AssertionError(
'%sdict keys do not match\n%s' % (
_fmt_msg(msg),
_fmt_path(path + ('.%s()' % ('viewkeys' if PY2 else 'keys'),)),
),
)
failures = []
for k, (resultv, expectedv) in iteritems(dzip_exact(result, expected)):
try:
assert_equal(
resultv,
expectedv,
path=path + ('[%r]' % k,),
msg=msg,
**kwargs
)
except AssertionError as e:
failures.append(str(e))
if failures:
raise AssertionError('\n'.join(failures))
def assert_dict_equal(result, expected, path=(), msg='', **kwargs):
_check_sets(
viewkeys(result),
viewkeys(expected),
msg,
path + ('.%s()' % ('viewkeys' if PY2 else 'keys'), ),
'key',
)
failures = []
for k, (resultv, expectedv) in iteritems(dzip_exact(result, expected)):
try:
assert_equal(resultv,
expectedv,
path=path + ('[%r]' % (k, ), ),
msg=msg,
**kwargs)
except AssertionError as e:
failures.append(str(e))
if failures:
raise AssertionError('\n===\n'.join(failures))
def assert_dict_equal(result, expected, path=(), msg="", **kwargs):
_check_sets(
result.keys(),
expected.keys(),
msg,
path + (".keys()", ),
"key",
)
failures = []
for k, (resultv, expectedv) in dzip_exact(result, expected).items():
try:
assert_equal(resultv,
expectedv,
path=path + ("[%r]" % (k, ), ),
msg=msg,
**kwargs)
except AssertionError as e:
failures.append(str(e))
if failures:
raise AssertionError("\n===\n".join(failures))
def check_terms(self,
terms,
expected,
initial_workspace,
mask,
check=check_arrays):
"""
Compile the given terms into a TermGraph, compute it with
initial_workspace, and compare the results with ``expected``.
"""
start_date, end_date = mask.index[[0, -1]]
graph = ExecutionPlan(
domain=US_EQUITIES,
terms=terms,
start_date=start_date,
end_date=end_date,
)
results = self.run_graph(graph, initial_workspace, mask)
for key, (res, exp) in dzip_exact(results, expected).items():
check(res, exp)
return results
def assert_dict_equal(result, expected, path=(), msg='', **kwargs):
_check_sets(
viewkeys(result),
viewkeys(expected),
msg,
path + ('.%s()' % ('viewkeys' if PY2 else 'keys'),),
'key',
)
failures = []
for k, (resultv, expectedv) in iteritems(dzip_exact(result, expected)):
try:
assert_equal(
resultv,
expectedv,
path=path + ('[%r]' % (k,),),
msg=msg,
**kwargs
)
except AssertionError as e:
failures.append(str(e))
if failures:
raise AssertionError('\n'.join(failures))
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
)
