def pre(cfg):
name = cfg["method"]
sigma = cfg["sigma"]
scale = cfg["scale"]
K = cfg["K"]
kernel = RBFKernel(sigma=sigma,scale=scale)
fastLogDet = FastIVM(K, kernel, 1.0)
if name == "Greedy":
opt = Greedy(K, fastLogDet)
if name == "IndependentSetImprovement":
opt = IndependentSetImprovement(K, fastLogDet)
elif name == "Random":
opt = Random(K, fastLogDet, cfg["run_id"])
elif name == "SieveStreaming":
e = cfg["epsilon"]
opt = SieveStreaming(K, fastLogDet, 1.0, e)
elif name == "SieveStreaming++":
e = cfg["epsilon"]
opt = SieveStreamingPP(K, fastLogDet, 1.0, e)
elif name == "Salsa":
e = cfg["epsilon"]
opt = Salsa(K, fastLogDet, 1.0, e)
elif name == "ThreeSieves":
e = cfg["epsilon"]
T = cfg["T"]
opt = ThreeSieves(K, fastLogDet, 1.0, e, "sieve", T)
return opt
### SieveStreamingPP ###
optimizers["SieveStreamingPP with IVM + RBF"] = SieveStreamingPP(K, ivm_rbf, 1.0, 0.1)
optimizers["SieveStreamingPP with IVM + poly kernel class"] = SieveStreamingPP(K, ivm_custom_kernel_class, 1.0, 0.1)
optimizers["SieveStreamingPP with IVM + poly kernel function"] = SieveStreamingPP(K, ivm_custom_kernel_function, 1.0, 0.1)
optimizers["SieveStreamingPP with custom IVM class"] = SieveStreamingPP(K, ivm_custom_class, 1.0, 0.1)
optimizers["SieveStreamingPP with custom IVM function"] = SieveStreamingPP(K, ivm_custom_function, 1.0, 0.1)
### Salsa ###
optimizers["Salsa with IVM + RBF"] = Salsa(K, ivm_rbf, 1.0, 0.1)
optimizers["Salsa with IVM + poly kernel class"] = Salsa(K, ivm_custom_kernel_class, 1.0, 0.1)
optimizers["Salsa with IVM + poly kernel function"] = Salsa(K, ivm_custom_kernel_function, 1.0, 0.1)
optimizers["Salsa with custom IVM class"] = Salsa(K, ivm_custom_class, 1.0, 0.1)
optimizers["Salsa with custom IVM function"] = Salsa(K, ivm_custom_function, 1.0, 0.1)
### ThreeSieves ###
optimizers["ThreeSieves with IVM + RBF"] = ThreeSieves(K, ivm_rbf, 1.0, 0.1, "sieve",5)
optimizers["ThreeSieves with IVM + poly kernel class"] = ThreeSieves(K, ivm_custom_kernel_class, 1.0, 0.01, "sieve",1)
optimizers["ThreeSieves with IVM + poly kernel function"] = ThreeSieves(K, ivm_custom_kernel_function, 1.0, 0.01, "sieve",1)
optimizers["ThreeSieves with custom IVM class"] = ThreeSieves(K, ivm_custom_class, 1.0, 0.1, "sieve",5)
optimizers["ThreeSieves with custom IVM function"] = ThreeSieves(K, ivm_custom_function, 1.0, 0.1, "sieve",5)
failed = False
for name, opt in optimizers.items():
opt.fit(X)
fval = opt.get_fval()
solution = np.array(sorted(opt.get_solution()))
print("Testing {}".format(name))
print("\tfval is {}".format(fval))
if "poly" in name: