update all test cases to work with the new structure

tests/acquisition/test_mi.py

@@ -25,6 +25,8 @@
 from gpytorch.kernels import LinearKernel
 from gpytorch.means import ConstantMean
 from scipy.stats import bernoulli, multivariate_normal, norm, pearsonr
+from aepsych.models.inducing_point_allocators import SobolAllocator
+from aepsych.models.utils import select_inducing_points
 
 
 class SingleProbitMI(unittest.TestCase):
@@ -34,8 +36,12 @@ def test_1d_monotonic_single_probit(self):
         np.random.seed(seed)
         n_init = 15
         n_opt = 1
-        lb = -4.0
-        ub = 4.0
+        lb = torch.tensor([-4.0])
+        ub = torch.tensor([4.0])
+        inducing_size = 10
+        bounds = torch.stack([lb, ub])
+        inducing_points = select_inducing_points(inducing_size=inducing_size, allocator=SobolAllocator(bounds=bounds))
+
         acqf = MonotonicBernoulliMCMutualInformation
         acqf_kwargs = {"objective": ProbitObjective()}
         model_list = [
@@ -51,8 +57,8 @@ def test_1d_monotonic_single_probit(self):
                 lb=lb,
                 ub=ub,
                 min_asks=n_opt,
-                model=MonotonicRejectionGP(lb=lb, ub=ub, dim=1, monotonic_idxs=[0]),
-                generator=MonotonicRejectionGenerator(acqf, acqf_kwargs),
+                model=MonotonicRejectionGP(inducing_points=inducing_points, dim=1, monotonic_idxs=[0]),
+                generator=MonotonicRejectionGenerator(acqf=acqf, acqf_kwargs=acqf_kwargs, lb=lb, ub=ub),
                 stimuli_per_trial=1,
                 outcome_types=["binary"],
             ),
@@ -81,8 +87,13 @@ def test_1d_single_probit(self):
         np.random.seed(seed)
         n_init = 15
         n_opt = 20
-        lb = -4.0
-        ub = 4.0
+        lb = torch.tensor([-4.0])
+        ub = torch.tensor([4.0])
+        inducing_size = 10
+        bounds = torch.stack([lb, ub])
+        inducing_points = select_inducing_points(inducing_size=inducing_size, allocator=SobolAllocator(bounds=bounds))
+
+
         acqf = BernoulliMCMutualInformation
         extra_acqf_args = {"objective": ProbitObjective()}
 
@@ -98,8 +109,8 @@ def test_1d_single_probit(self):
             Strategy(
                 lb=lb,
                 ub=ub,
-                model=GPClassificationModel(lb=lb, ub=ub, dim=1, inducing_size=10),
-                generator=OptimizeAcqfGenerator(acqf, extra_acqf_args),
+                model=GPClassificationModel(inducing_points=inducing_points, dim=1, inducing_size=10),
+                generator=OptimizeAcqfGenerator(acqf=acqf, lb=lb, ub=ub, acqf_kwargs=extra_acqf_args),
                 min_asks=n_opt,
                 stimuli_per_trial=1,
                 outcome_types=["binary"],
@@ -126,10 +137,15 @@ def test_1d_single_probit(self):
     def test_mi_acqf(self):
         mean = ConstantMean().initialize(constant=1.2)
         covar = LinearKernel().initialize(variance=1.0)
+        lb = torch.tensor([0.0])
+        ub = torch.tensor([1.0])
+        inducing_size = 10
+        bounds = torch.stack([lb, ub])
+        inducing_points = select_inducing_points(inducing_size=inducing_size, allocator=SobolAllocator(bounds=bounds))
+
         model = GPClassificationModel(
-            lb=torch.Tensor([0]),
-            ub=torch.Tensor([1]),
-            inducing_size=10,
+            inducing_points=inducing_points,
+            inducing_size=inducing_size,
             mean_module=mean,
             covar_module=covar,
         )

tests/generators/test_epsilon_greedy_generator.py

@@ -22,13 +22,17 @@ def test_epsilon_greedy(self):
         np.random.seed(seed)
         total_trials = 2000
         extra_acqf_args = {"target": 0.75, "beta": 1.96}
+        lb = torch.tensor([0.0])
+        ub = torch.tensor([1.0])
 
         for epsilon in (0.1, 0.5):
             gen = EpsilonGreedyGenerator(
                 subgenerator=MonotonicRejectionGenerator(
-                    acqf=MonotonicMCLSE, acqf_kwargs=extra_acqf_args
+                    acqf=MonotonicMCLSE, acqf_kwargs=extra_acqf_args, lb=lb, ub=ub
                 ),
                 epsilon=epsilon,
+                lb=lb, 
+                ub=ub
             )
             model = MagicMock()
             gen.subgenerator.gen = MagicMock()
@@ -44,6 +48,8 @@ def test_greedyepsilon_config(self):
         config_str = """
             [common]
             acqf = MonotonicMCLSE
+            lb = [0]
+            ub = [1]
             [EpsilonGreedyGenerator]
             subgenerator = MonotonicRejectionGenerator
             epsilon = .5

tests/generators/test_optimize_acqf_generator.py

@@ -16,7 +16,8 @@
 from aepsych.models import GPClassificationModel, PairwiseProbitModel
 from botorch.acquisition.preference import AnalyticExpectedUtilityOfBestOption
 from sklearn.datasets import make_classification
-
+from aepsych.models.inducing_point_allocators import SobolAllocator
+from aepsych.models.utils import select_inducing_points
 
 class TestOptimizeAcqfGenerator(unittest.TestCase):
     def test_time_limits(self):
@@ -33,17 +34,21 @@ def test_time_limits(self):
             n_clusters_per_class=4,
         )
         X, y = torch.Tensor(X), torch.Tensor(y)
+        lb = -3 * torch.ones(8)
+        ub = 3 * torch.ones(8)
+        inducing_size = 10
+        bounds = torch.stack([lb, ub])
+        inducing_points = select_inducing_points(inducing_size=inducing_size, allocator=SobolAllocator(bounds=bounds))
 
         model = GPClassificationModel(
-            lb=-3 * torch.ones(8),
-            ub=3 * torch.ones(8),
+            inducing_points=inducing_points,
             max_fit_time=0.5,
-            inducing_size=10,
+            inducing_size=inducing_size,
         )
 
         model.fit(X, y)
         generator = OptimizeAcqfGenerator(
-            acqf=MCLevelSetEstimation, acqf_kwargs={"beta": 1.96, "target": 0.5}
+            acqf=MCLevelSetEstimation, acqf_kwargs={"beta": 1.96, "target": 0.5}, lb=lb, ub=ub,
         )
 
         start = time.time()
@@ -54,6 +59,8 @@ def test_time_limits(self):
             acqf=MCLevelSetEstimation,
             acqf_kwargs={"beta": 1.96, "target": 0.5},
             max_gen_time=0.1,
+            lb=lb,
+            ub=ub,
         )
 
         start = time.time()
@@ -68,6 +75,10 @@ def test_time_limits(self):
 
     def test_instantiate_eubo(self):
         config = """
+        [common]
+        lb = [-1]
+        ub = [1]
+
         [OptimizeAcqfGenerator]
         acqf = AnalyticExpectedUtilityOfBestOption
         stimuli_per_trial = 2