Merge pull request #2 from soda-inria/fea/add_pca_benchmarks

Add PCA benchmarks
Adds a new tab "PCA" to the spreadsheet.

.github/workflows/run_benchmark_results_file_sanity_checks.yaml

@@ -18,3 +18,4 @@ jobs:
     - name: Check sanity of benchmark files
       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

.github/workflows/sync_benchmark_files_to_gsheet.yaml

@@ -5,7 +5,7 @@ on:
     branches: main
 
 jobs:
-  sync_kmeans_benchmark_result_file_with_gsheet:
+  sync_benchmark_result_file_with_gsheet:
     name: Run synchronization script
     runs-on: ubuntu-latest
     environment: Publish
@@ -23,6 +23,9 @@ jobs:
         GSPREAD_URL: ${{vars.GSPREAD_URL}}
       run: |
         python ./benchmarks/kmeans/consolidate_result_csv.py ./benchmarks/kmeans/results.csv --check-csv
+        python ./benchmarks/pca/consolidate_result_csv.py ./benchmarks/pca/results.csv --check-csv
         echo "$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

.github/workflows/test_cpu_benchmarks.yaml

@@ -137,7 +137,9 @@ jobs:
     - name: Check oneapi default device
       run: python -c "import dpctl; dpctl.select_default_device().print_device_info()"
 
-    - name: Run k-means benchmarks
+    - name: Run benchmarks
       run: |
         cd benchmarks/kmeans
         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]

README.md

@@ -17,6 +17,7 @@ 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)
 
 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/consolidate_result_csv.py

@@ -381,18 +381,30 @@ def _gspread_sync(source, gspread_url, gspread_auth_key):
     gs = gspread.service_account(gspread_auth_key)
     sheet = gs.open_by_url(gspread_url)
 
+    global_range = (
+        f"{gspread.utils.rowcol_to_a1(1, 1)}:"
+        f"{gspread.utils.rowcol_to_a1(n_rows + 1, n_cols)}"
+    )
+
     try:
         worksheet = sheet.worksheet(GOOGLE_WORKSHEET_NAME)
         worksheet.clear()
         worksheet.clear_basic_filter()
         worksheet.freeze(0, 0)
         worksheet.resize(rows=n_rows + 1, cols=n_cols)
+        worksheet.clear_notes(global_range)
+        white_background = dict(
+            backgroundColorStyle=dict(rgbColor=dict(red=1, green=1, blue=1, alpha=1))
+        )
+        worksheet.format(global_range, white_background)
     except gspread.WorksheetNotFound:
         worksheet = sheet.add_worksheet(
             GOOGLE_WORKSHEET_NAME, rows=n_rows + 1, cols=n_cols
         )
-        # ensure worksheets are sorted alphabetically
-        sheet.reorder_worksheets(sorted(sheet.worksheets(), key=attrgetter("title")))
+        # ensure worksheets are sorted anti-alphabetically
+        sheet.reorder_worksheets(
+            sorted(sheet.worksheets(), key=attrgetter("title"), reverse=True)
+        )
 
     # upload all values
     worksheet.update(
@@ -413,10 +425,6 @@ def _gspread_sync(source, gspread_url, gspread_auth_key):
         verticalAlignment="MIDDLE",
         wrapStrategy="WRAP",
     )
-    global_range = (
-        f"{gspread.utils.rowcol_to_a1(1, 1)}:"
-        f"{gspread.utils.rowcol_to_a1(n_rows + 1, n_cols)}"
-    )
     format_queries.append(dict(range=global_range, format=global_format))
 
     # benchmark_id and walltime columns are bold

benchmarks/kmeans/solvers/sklearn_pytorch_engine.py

@@ -54,7 +54,7 @@ def set_objective(
         device = self.device
         # Copy the data before running the benchmark to ensure that no unfortunate side
         # effects can happen
-        self.X = torch.asarray(X, copy=True, device=self.device)
+        self.X = torch.asarray(X, copy=True, device=device)
 
         if hasattr(sample_weight, "copy"):
             sample_weight = torch.asarray(sample_weight, copy=True, device=device)