FEA ridge benchmarks (#18)

Add benchmarks for Ridge. --------- Co-authored-by: Olivier Grisel <[email protected]>
soda-inria · Feb 21, 2024 · bd405f0 · bd405f0
1 parent 6101c27
commit bd405f0
Show file tree

Hide file tree

Showing 18 changed files with 1,500 additions and 10 deletions.
diff --git a/.github/workflows/run_benchmark_results_file_sanity_checks.yaml b/.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
diff --git a/.github/workflows/sync_benchmark_files_to_gsheet.yaml b/.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/ridge/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/ridge/results.csv \
+          --sync-to-gspread --gspread-url $GSPREAD_URL --gspread-auth-key ./service_account.json
diff --git a/.github/workflows/test_cpu_benchmarks.yaml b/.github/workflows/test_cpu_benchmarks.yaml
@@ -143,3 +143,5 @@ jobs:
         PYTHONPATH=$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,n_targets=2]
diff --git a/README.md b/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)

diff --git a/benchmarks/kmeans/consolidate_result_csv.py b/benchmarks/kmeans/consolidate_result_csv.py
@@ -2,7 +2,6 @@
 from functools import partial
 from io import BytesIO
 from itertools import zip_longest
-from operator import attrgetter
 
 import numpy as np
 import pandas as pd
@@ -393,17 +392,18 @@ def _gspread_sync(source, gspread_url, gspread_auth_key):
         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))
+        reset_format = dict(
+            backgroundColorStyle=dict(rgbColor=dict(red=1, green=1, blue=1, alpha=1)),
+            textFormat=dict(bold=False),
         )
-        worksheet.format(global_range, white_background)
+        worksheet.format(global_range, reset_format)
     except gspread.WorksheetNotFound:
         worksheet = sheet.add_worksheet(
             GOOGLE_WORKSHEET_NAME, rows=n_rows + 1, cols=n_cols
         )
         # ensure worksheets are sorted anti-alphabetically
         sheet.reorder_worksheets(
-            sorted(sheet.worksheets(), key=attrgetter("title"), reverse=True)
+            sorted(sheet.worksheets(), key=lambda worksheet: worksheet.title.lower())
         )
 
     # upload all values

diff --git a/benchmarks/pca/consolidate_result_csv.py b/benchmarks/pca/consolidate_result_csv.py
@@ -2,7 +2,6 @@
 from functools import partial
 from io import BytesIO
 from itertools import zip_longest
-from operator import attrgetter
 
 import numpy as np
 import pandas as pd
@@ -391,17 +390,18 @@ def _gspread_sync(source, gspread_url, gspread_auth_key):
         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))
+        reset_format = dict(
+            backgroundColorStyle=dict(rgbColor=dict(red=1, green=1, blue=1, alpha=1)),
+            textFormat=dict(bold=False),
         )
-        worksheet.format(global_range, white_background)
+        worksheet.format(global_range, reset_format)
     except gspread.WorksheetNotFound:
         worksheet = sheet.add_worksheet(
             GOOGLE_WORKSHEET_NAME, rows=n_rows + 1, cols=n_cols
         )
         # ensure worksheets are sorted anti-alphabetically
         sheet.reorder_worksheets(
-            sorted(sheet.worksheets(), key=attrgetter("title"), reverse=True)
+            sorted(sheet.worksheets(), key=lambda worksheet: worksheet.title.lower())
         )
 
     # upload all values