mirror of
https://github.com/wassname/catalyst.git
synced 2026-06-29 04:25:37 +08:00
Scott Sanderson
8e59d12daf
- Adds `zipline.pipeline.Pipeline`, a new user-facing class for managing pipelines of Modeling API expressions. - Adds `attach_pipeline` and `drain_pipeline` as API methods - Removes `add_factor` and `add_filter` as API methods. These have been replaced two new methods on `Pipeline`: `add`, and `apply_screen`. - Adding a `Filter` as a column no longer implicitly truncates rows from the Modelling API output. It simply causes a new column, of dtype `bool` to show up in the output. Removal of rows is now handled by the new `apply_screen` method of `Pipeline`. - Refactors the existing Modeling API tests to reflect the new APIs.
195 lines
7.5 KiB
Python
195 lines
7.5 KiB
Python
"""
|
|
Tests for Factor terms.
|
|
"""
|
|
from numpy import array, eye, nan, ones
|
|
from zipline.errors import UnknownRankMethod
|
|
from zipline.modelling.factor import Factor
|
|
from zipline.modelling.filter import Filter
|
|
from zipline.modelling.graph import TermGraph
|
|
from zipline.utils.test_utils import check_arrays
|
|
|
|
from .base import BaseFFCTestCase
|
|
|
|
|
|
class F(Factor):
|
|
inputs = ()
|
|
window_length = 0
|
|
|
|
|
|
class Mask(Filter):
|
|
inputs = ()
|
|
window_length = 0
|
|
|
|
|
|
class FactorTestCase(BaseFFCTestCase):
|
|
|
|
def setUp(self):
|
|
super(FactorTestCase, self).setUp()
|
|
self.f = F()
|
|
|
|
def test_bad_input(self):
|
|
with self.assertRaises(UnknownRankMethod):
|
|
self.f.rank("not a real rank method")
|
|
|
|
def test_rank_ascending(self):
|
|
|
|
# Generated with:
|
|
# data = arange(25).reshape(5, 5).transpose() % 4
|
|
data = array([[0, 1, 2, 3, 0],
|
|
[1, 2, 3, 0, 1],
|
|
[2, 3, 0, 1, 2],
|
|
[3, 0, 1, 2, 3],
|
|
[0, 1, 2, 3, 0]], dtype=float)
|
|
expected_ranks = {
|
|
'ordinal': array([[1., 3., 4., 5., 2.],
|
|
[2., 4., 5., 1., 3.],
|
|
[3., 5., 1., 2., 4.],
|
|
[4., 1., 2., 3., 5.],
|
|
[1., 3., 4., 5., 2.]]),
|
|
'average': array([[1.5, 3., 4., 5., 1.5],
|
|
[2.5, 4., 5., 1., 2.5],
|
|
[3.5, 5., 1., 2., 3.5],
|
|
[4.5, 1., 2., 3., 4.5],
|
|
[1.5, 3., 4., 5., 1.5]]),
|
|
'min': array([[1., 3., 4., 5., 1.],
|
|
[2., 4., 5., 1., 2.],
|
|
[3., 5., 1., 2., 3.],
|
|
[4., 1., 2., 3., 4.],
|
|
[1., 3., 4., 5., 1.]]),
|
|
'max': array([[2., 3., 4., 5., 2.],
|
|
[3., 4., 5., 1., 3.],
|
|
[4., 5., 1., 2., 4.],
|
|
[5., 1., 2., 3., 5.],
|
|
[2., 3., 4., 5., 2.]]),
|
|
'dense': array([[1., 2., 3., 4., 1.],
|
|
[2., 3., 4., 1., 2.],
|
|
[3., 4., 1., 2., 3.],
|
|
[4., 1., 2., 3., 4.],
|
|
[1., 2., 3., 4., 1.]]),
|
|
}
|
|
|
|
def check(terms):
|
|
graph = TermGraph(terms)
|
|
results = self.run_graph(
|
|
graph,
|
|
initial_workspace={self.f: data},
|
|
mask=self.build_mask(ones((5, 5))),
|
|
)
|
|
for method in terms:
|
|
check_arrays(results[method], expected_ranks[method])
|
|
|
|
check({meth: self.f.rank(method=meth) for meth in expected_ranks})
|
|
check({
|
|
meth: self.f.rank(method=meth, ascending=True)
|
|
for meth in expected_ranks
|
|
})
|
|
# Not passing a method should default to ordinal.
|
|
check({'ordinal': self.f.rank()})
|
|
check({'ordinal': self.f.rank(ascending=True)})
|
|
|
|
def test_rank_descending(self):
|
|
|
|
# Generated with:
|
|
# data = arange(25).reshape(5, 5).transpose() % 4
|
|
data = array([[0, 1, 2, 3, 0],
|
|
[1, 2, 3, 0, 1],
|
|
[2, 3, 0, 1, 2],
|
|
[3, 0, 1, 2, 3],
|
|
[0, 1, 2, 3, 0]], dtype=float)
|
|
expected_ranks = {
|
|
'ordinal': array([[4., 3., 2., 1., 5.],
|
|
[3., 2., 1., 5., 4.],
|
|
[2., 1., 5., 4., 3.],
|
|
[1., 5., 4., 3., 2.],
|
|
[4., 3., 2., 1., 5.]]),
|
|
'average': array([[4.5, 3., 2., 1., 4.5],
|
|
[3.5, 2., 1., 5., 3.5],
|
|
[2.5, 1., 5., 4., 2.5],
|
|
[1.5, 5., 4., 3., 1.5],
|
|
[4.5, 3., 2., 1., 4.5]]),
|
|
'min': array([[4., 3., 2., 1., 4.],
|
|
[3., 2., 1., 5., 3.],
|
|
[2., 1., 5., 4., 2.],
|
|
[1., 5., 4., 3., 1.],
|
|
[4., 3., 2., 1., 4.]]),
|
|
'max': array([[5., 3., 2., 1., 5.],
|
|
[4., 2., 1., 5., 4.],
|
|
[3., 1., 5., 4., 3.],
|
|
[2., 5., 4., 3., 2.],
|
|
[5., 3., 2., 1., 5.]]),
|
|
'dense': array([[4., 3., 2., 1., 4.],
|
|
[3., 2., 1., 4., 3.],
|
|
[2., 1., 4., 3., 2.],
|
|
[1., 4., 3., 2., 1.],
|
|
[4., 3., 2., 1., 4.]]),
|
|
}
|
|
|
|
def check(terms):
|
|
graph = TermGraph(terms)
|
|
results = self.run_graph(
|
|
graph,
|
|
initial_workspace={self.f: data},
|
|
mask=self.build_mask(ones((5, 5))),
|
|
)
|
|
for method in terms:
|
|
check_arrays(results[method], expected_ranks[method])
|
|
|
|
check({
|
|
meth: self.f.rank(method=meth, ascending=False)
|
|
for meth in expected_ranks
|
|
})
|
|
# Not passing a method should default to ordinal.
|
|
check({'ordinal': self.f.rank(ascending=False)})
|
|
|
|
def test_rank_after_mask(self):
|
|
# data = arange(25).reshape(5, 5).transpose() % 4
|
|
data = array([[0, 1, 2, 3, 0],
|
|
[1, 2, 3, 0, 1],
|
|
[2, 3, 0, 1, 2],
|
|
[3, 0, 1, 2, 3],
|
|
[0, 1, 2, 3, 0]], dtype=float)
|
|
mask_data = ~eye(5, dtype=bool)
|
|
initial_workspace = {self.f: data, Mask(): mask_data}
|
|
|
|
graph = TermGraph(
|
|
{
|
|
"ascending_nomask": self.f.rank(ascending=True),
|
|
"ascending_mask": self.f.rank(ascending=True, mask=Mask()),
|
|
"descending_nomask": self.f.rank(ascending=False),
|
|
"descending_mask": self.f.rank(ascending=False, mask=Mask()),
|
|
}
|
|
)
|
|
|
|
expected = {
|
|
"ascending_nomask": array([[1., 3., 4., 5., 2.],
|
|
[2., 4., 5., 1., 3.],
|
|
[3., 5., 1., 2., 4.],
|
|
[4., 1., 2., 3., 5.],
|
|
[1., 3., 4., 5., 2.]]),
|
|
"descending_nomask": array([[4., 3., 2., 1., 5.],
|
|
[3., 2., 1., 5., 4.],
|
|
[2., 1., 5., 4., 3.],
|
|
[1., 5., 4., 3., 2.],
|
|
[4., 3., 2., 1., 5.]]),
|
|
# Diagonal should be all nans, and anything whose rank was less
|
|
# than the diagonal in the unmasked calc should go down by 1.
|
|
"ascending_mask": array([[nan, 2., 3., 4., 1.],
|
|
[2., nan, 4., 1., 3.],
|
|
[2., 4., nan, 1., 3.],
|
|
[3., 1., 2., nan, 4.],
|
|
[1., 2., 3., 4., nan]]),
|
|
"descending_mask": array([[nan, 3., 2., 1., 4.],
|
|
[2., nan, 1., 4., 3.],
|
|
[2., 1., nan, 4., 3.],
|
|
[1., 4., 3., nan, 2.],
|
|
[4., 3., 2., 1., nan]]),
|
|
}
|
|
|
|
results = self.run_graph(
|
|
graph,
|
|
initial_workspace,
|
|
mask=self.build_mask(ones((5, 5))),
|
|
)
|
|
for method in results:
|
|
check_arrays(expected[method], results[method])
|