WIP: add benchmark setup for Ridge

.github/workflows/run_benchmark_results_file_sanity_checks.yaml

@@ -19,3 +19,4 @@ jobs:
       run: |
         python ./benchmarks/kmeans/consolidate_result_csv.py ./benchmarks/kmeans/results.csv --check-csv
         python ./benchmarks/pca/consolidate_result_csv.py ./benchmarks/pca/results.csv --check-csv
+        python ./benchmarks/ridge/consolidate_result_csv.py ./benchmarks/ridge/results.csv --check-csv

.github/workflows/sync_benchmark_files_to_gsheet.yaml

@@ -24,8 +24,11 @@ jobs:
       run: |
         python ./benchmarks/kmeans/consolidate_result_csv.py ./benchmarks/kmeans/results.csv --check-csv
         python ./benchmarks/pca/consolidate_result_csv.py ./benchmarks/pca/results.csv --check-csv
+        python ./benchmarks/ridge/consolidate_result_csv.py ./benchmarks/pca/results.csv --check-csv
         echo "$GSPREAD_SERVICE_ACCOUNT_AUTH_KEY" > service_account.json
         python ./benchmarks/kmeans/consolidate_result_csv.py ./benchmarks/kmeans/results.csv \
           --sync-to-gspread --gspread-url $GSPREAD_URL --gspread-auth-key ./service_account.json
         python ./benchmarks/pca/consolidate_result_csv.py ./benchmarks/pca/results.csv \
           --sync-to-gspread --gspread-url $GSPREAD_URL --gspread-auth-key ./service_account.json
+        python ./benchmarks/ridge/consolidate_result_csv.py ./benchmarks/pca/results.csv \
+          --sync-to-gspread --gspread-url $GSPREAD_URL --gspread-auth-key ./service_account.json

.github/workflows/test_cpu_benchmarks.yaml

@@ -143,3 +143,5 @@ jobs:
         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]
+        cd ../ridge
+        benchopt run --no-plot -l -d Simulated_correlated_data[n_samples=100,n_features=100]  # TODO add relevant parameters

README.md

@@ -18,6 +18,7 @@ hardware.
 Benchmarks are currently available for the following algorithms:
 - [k-means](https://github.com/soda-inria/sklearn-engine-benchmarks/tree/main/benchmarks/kmeans)
 - [PCA](https://github.com/soda-inria/sklearn-engine-benchmarks/tree/main/benchmarks/pca)
+- [Ridge](https://github.com/soda-inria/sklearn-engine-benchmarks/tree/main/benchmarks/pca)
 
 Here is a (non-exhaustive) list of libraries that are compared in the benchmarks:
 - [scikit-learn](https://scikit-learn.org/stable/index.html)

benchmarks/kmeans/objective.py

@@ -32,24 +32,25 @@ def set_data(self, X, **dataset_parameters):
         self.X = X
         dtype = X.dtype
 
-        if self.init == "random" or self.sample_weight == "random":
-            rng = np.random.default_rng(self.random_state)
-
         if self.sample_weight == "None":
             sample_weight = None
         elif self.sample_weight == "unary":
             sample_weight = np.ones(len(X), dtype=dtype)
         elif self.sample_weight == "random":
-            sample_weight = rng.random(size=len(X)).astype(dtype)
+            rng_sample_weight = np.random.default_rng(
+                dataset_parameters["sample_weight"] + 1
+            )
+            sample_weight = rng_sample_weight.random(size=len(X)).astype(dtype)
         else:
             raise ValueError(
                 "Expected 'sample_weight' parameter to be either equal to 'None', "
                 f"'unary' or 'random', but got {sample_weight}."
             )
 
         if self.init == "random":
+            rng_init = np.random.default_rng(self.random_state)
             init = np.array(
-                rng.choice(X, self.n_clusters, replace=False), dtype=X.dtype
+                rng_init.choice(X, self.n_clusters, replace=False), dtype=X.dtype
             )
         elif self.init == "k-means++":
             init = self.init