def test_dress_rehearsal(tmp_path):
s = WilsonScanner(scale=5, eft="WET", basis="flavio")
s.set_dfunction(random_kinematics,
sampling=np.linspace(0.0, 1.0, 10),
normalize=True)
s.set_no_workers(no_workers=1)
s.set_spoints_equidist({
"CVL_bctaunutau": (-0.5, 0.5, 3),
"CSL_bctaunutau": (-0.5, 0.5, 3),
"CT_bctaunutau": (-0.1, 0.1, 3),
})
d = Data()
r = s.run(d)
r.write()
# Can remove str casting once we remove py3.5 support
d.write(str(tmp_path / "dress_rehearsal.sql"), overwrite="overwrite")
d = DataWithErrors(str(tmp_path / "dress_rehearsal.sql"))
d.add_rel_err_uncorr(0.01)
d.add_err_poisson(1000)
c = HierarchyCluster()
c.set_metric(chi2_metric)
b = Benchmark()
b.set_metric(chi2_metric)
c.set_max_d(1)
c.run(d).write()
b.run(d).write()
def test_reuse_hierarchy(_data):
d = _data.copy()
c = HierarchyCluster()
c.set_metric("euclidean")
c.set_max_d(1.5)
r = c.run(d)
r.write()
r2 = c.run(d, reuse_hierarchy_from=r)
r2.write(cluster_column="reused")
assert d.df["cluster"].tolist() == d.df["reused"].tolist()
def test_reuse_hierarchy_fail_different_data(_data):
d = _data.copy()
e = _data.copy()
c = HierarchyCluster()
c.set_metric("euclidean")
c.set_max_d(1.5)
r = c.run(d)
r.write()
with pytest.raises(ValueError, match=".*different data object.*"):
c.run(e, reuse_hierarchy_from=r)
def test_reuse_hierarchy(self):
d = self.d.copy()
c = HierarchyCluster()
c.set_metric("euclidean")
c.set_max_d(1.5)
r = c.run(d)
r.write()
r2 = c.run(d, reuse_hierarchy_from=r)
r2.write(cluster_column="reused")
self.assertListEqual(d.df["cluster"].tolist(), d.df["reused"].tolist())
def test_reuse_hierarchy_fail_different_data(self):
d = self.d.copy()
e = self.d.copy()
c = HierarchyCluster()
c.set_metric("euclidean")
c.set_max_d(1.5)
r = c.run(d)
r.write()
with self.assertRaises(ValueError) as ex:
c.run(e, reuse_hierarchy_from=r)
self.assertTrue("different data object" in str(ex.exception))
def test_cluster(_data):
d = _data.copy()
c = HierarchyCluster()
c.set_metric("euclidean")
c.set_max_d(0.75)
c.run(d).write()
c.set_max_d(1.5)
c.run(d).write(cluster_column="cluster15")
# The minimal distance between our distributions is 1, so they all
# end up in different clusters
assert len(d.clusters()) == d.n
# This is a bit unfortunate, since we have so many distribution pairs
# with equal distance (so it's up to the implementation of the algorithm
# , which clusters develop) but this is what happened so far:
assert len(d.clusters(cluster_column="cluster15")) == 6
def test_dendrogram_plot(_data, tmp_path):
c = HierarchyCluster()
c.set_metric()
c.set_max_d(0.2)
r = c.run(_data)
r.dendrogram(output=str(tmp_path / "output.pdf"))
def test_hierarchy_cluster_no_max_d(_data):
d = _data.copy()
c = HierarchyCluster()
with pytest.raises(ValueError, match=".*set_max_d.*"):
c.run(d)
def test_dendrogram_plot(self):
c = HierarchyCluster()
c.set_metric()
c.set_max_d(0.2)
r = c.run(self.d)
r.dendrogram()
def test_hierarchy_cluster_no_max_d(self):
d = self.d.copy()
c = HierarchyCluster()
with self.assertRaises(ValueError) as e:
c.run(d)
self.assertTrue("set_max_d" in str(e.exception))