remove uninteresting parameter combinations for benchmarks for kmeans…

… and pca - fix pca tests

.github/workflows/test_cpu_benchmarks.yaml

@@ -139,8 +139,7 @@ jobs:
 
     - name: Run k-means benchmarks
       run: |
-        export PYTHONPATH=$PYTHONPATH:$(realpath ./kmeans_dpcpp/)
         cd benchmarks/kmeans
-        benchopt run --no-plot -l -d Simulated_correlated_data[n_samples=1000,n_features=14]
+        PYTHONPATH=$PYTHONPATH:$(realpath ./kmeans_dpcpp/) benchopt run --no-plot -l -d Simulated_correlated_data[n_samples=1000,n_features=14]
         cd ../pca
         benchopt run --no-plot -l -d Simulated_correlated_data[n_samples=100,n_features=100]

benchmarks/kmeans/datasets/simulated_blobs.py

@@ -10,7 +10,7 @@ class Dataset(BaseDataset):
 
     parameters = {
         "n_samples, n_features": [(50_000_000, 14), (10_000_000, 14), (1_000_000, 14)],
-        "dtype": ["float32", "float64"],
+        "dtype": ["float32"],
         "random_state": [123],
     }
 

benchmarks/kmeans/solvers/kmeans_dpcpp.py

@@ -66,7 +66,7 @@ class Solver(BaseSolver):
         "kmeans_dpcpp",
     ]
 
-    parameters = dict(device=["cpu", "gpu"], runtime=["level_zero", "opencl"])
+    parameters = {"device, runtime": [("cpu", "opencl"), ("gpu", "level_zero")]}
 
     stopping_criterion = SingleRunCriterion(1)
 

benchmarks/kmeans/solvers/scikit_learn_intelex.py

@@ -24,10 +24,7 @@ class Solver(BaseSolver):
     parameters = {
         "device, runtime": [
             ("cpu", "numpy"),
-            ("cpu", "level_zero"),
-            ("cpu", "opencl"),
             ("gpu", "level_zero"),
-            ("gpu", "opencl"),
         ]
     }
 

benchmarks/kmeans/solvers/sklearn_numba_dpex.py

@@ -22,7 +22,7 @@ class Solver(BaseSolver):
         "sklearn-numba-dpex",
     ]
 
-    parameters = dict(device=["cpu", "gpu"], runtime=["level_zero", "opencl"])
+    parameters = {"device, runtime": [("cpu", "opencl"), ("gpu", "level_zero")]}
 
     stopping_criterion = SingleRunCriterion(1)
 

benchmarks/pca/datasets/simulated_blobs.py

@@ -9,8 +9,8 @@ class Dataset(BaseDataset):
     name = "Simulated_correlated_data"
 
     parameters = {
-        "n_samples, n_features": [(1_000_000, 10_000), (10_000, 10_000)],
-        "dtype": ["float32", "float64"],
+        "n_samples, n_features": [(1_000_000, 100), (10_000, 10_000)],
+        "dtype": ["float32"],
         "random_state": [123],
     }
 

benchmarks/pca/objective.py

@@ -15,7 +15,6 @@ class Objective(BaseObjective):
     # solver.
     parameters = dict(
         n_components=[10],
-        whiten=[False],
         tol=[0.0],
         iterated_power=[15],
         n_oversamples=[10],
@@ -57,7 +56,6 @@ def get_objective(self):
         return dict(
             X=self.X,
             n_components=self.n_components,
-            whiten=self.whiten,
             tol=self.tol,
             iterated_power=self.iterated_power,
             n_oversamples=self.n_oversamples,

benchmarks/pca/solvers/cuml.py

@@ -39,7 +39,6 @@ def set_objective(
         self,
         X,
         n_components,
-        whiten,
         tol,
         iterated_power,
         n_oversamples,
@@ -54,22 +53,21 @@ def set_objective(
         else:
             self.X = cupy.asarray(X)
 
-        self.components = n_components
-        self.whiten = whiten
+        self.n_components = n_components
         self.tol = tol
 
         # if tol == 0:
         #     tol = 1e-16
         # self.tol = tol
 
-        self.iterated_power = self.iterated_power
+        self.iterated_power = iterated_power
         self.n_oversamples = n_oversamples
         self.random_state = random_state
         self.verbose = verbose
 
     def run(self, _):
         estimator = cuml.PCA(
-            copy=False,
+            copy=True,
             iterated_power=self.iterated_power,
             n_components=self.n_components,
             random_state=self.random_state,

benchmarks/pca/solvers/scikit_learn.py

@@ -11,30 +11,21 @@ class Solver(BaseSolver):
     name = "scikit-learn"
     requirements = ["scikit-learn"]
 
-    parameters = dict(
-        svd_solver=["full", "arpack", "randomized"],
-        power_iteration_normalizer=["QR", "LU", "none"],
-    )
+    parameters = {
+        "svd_solver, power_iteration_normalizer": [
+            (svd_solver, power_iteration_normalizer)
+            for svd_solver in ["full", "randomized"]
+            for power_iteration_normalizer in ["LU"]
+        ]
+        + [("arpack", "none")]
+    }
 
     stopping_criterion = SingleRunCriterion(1)
 
-    def skip(self, **objective_dict):
-        svd_solver = objective_dict["svd_solver"]
-        power_iteration_normalizer = objective_dict["power_iteration_normalizer"]
-
-        if (svd_solver == "arpack") and power_iteration_normalizer != "none":
-            return True, (
-                "arpack solver expect power iteration normalizer parameter set to "
-                "'none'"
-            )
-
-        return False, None
-
     def set_objective(
         self,
         X,
         n_components,
-        whiten,
         tol,
         iterated_power,
         n_oversamples,
@@ -45,19 +36,18 @@ def set_objective(
         # effects can happen
         self.X = X.copy()
 
-        self.components = n_components
-        self.whiten = whiten
+        self.n_components = n_components
         self.tol = tol
-        self.iterated_power = self.iterated_power
+        self.iterated_power = iterated_power
         self.n_oversamples = n_oversamples
         self.random_state = random_state
         self.verbose = verbose
 
     def run(self, _):
         estimator = PCA(
             n_components=self.n_components,
-            copy=False,
-            whiten=self.whiten,
+            copy=True,
+            whiten=False,
             svd_solver=self.svd_solver,
             tol=self.tol,
             iterated_power=self.iterated_power,

benchmarks/pca/solvers/scikit_learn_intelex.py

@@ -24,13 +24,14 @@ class Solver(BaseSolver):
     parameters = {
         "device, runtime": [
             ("cpu", "numpy"),
-            ("cpu", "level_zero"),
-            ("cpu", "opencl"),
             ("gpu", "level_zero"),
-            ("gpu", "opencl"),
         ],
-        "svd_solver": ["full", "arpack", "randomized"],
-        "power_iteration_normalizer": ["QR", "LU", "none"],
+        "svd_solver, power_iteration_normalizer": [
+            (svd_solver, power_iteration_normalizer)
+            for svd_solver in ["full", "randomized"]
+            for power_iteration_normalizer in ["LU"]
+        ]
+        + [("arpack", "none")],
     }
 
     stopping_criterion = SingleRunCriterion(1)
@@ -51,22 +52,12 @@ def skip(self, **objective_dict):
                     f"This {self.device} device has no support for float64 compute"
                 )
 
-        svd_solver = objective_dict["svd_solver"]
-        power_iteration_normalizer = objective_dict["power_iteration_normalizer"]
-
-        if (svd_solver == "arpack") and power_iteration_normalizer != "none":
-            return True, (
-                "arpack solver expect power iteration normalizer parameter set to "
-                "'none'"
-            )
-
         return False, None
 
     def set_objective(
         self,
         X,
         n_components,
-        whiten,
         tol,
         iterated_power,
         n_oversamples,
@@ -83,19 +74,18 @@ def set_objective(
         else:
             self.X = X.copy()
 
-        self.components = n_components
-        self.whiten = whiten
+        self.n_components = n_components
         self.tol = tol
-        self.iterated_power = self.iterated_power
+        self.iterated_power = iterated_power
         self.n_oversamples = n_oversamples
         self.random_state = random_state
         self.verbose = verbose
 
     def run(self, _):
         estimator = PCA(
             n_components=self.n_components,
-            copy=False,
-            whiten=self.whiten,
+            copy=True,
+            whiten=False,
             svd_solver=self.svd_solver,
             tol=self.tol,
             iterated_power=self.iterated_power,