Merge branch 'IntelPython:large-scale' into large-scale

Author: ethanglaser

.github/workflows/scorecard.yml

@@ -0,0 +1,73 @@
+# This workflow uses actions that are not certified by GitHub. They are provided
+# by a third-party and are governed by separate terms of service, privacy
+# policy, and support documentation.
+
+name: Scorecard supply-chain security
+on:
+  # For Branch-Protection check. Only the default branch is supported. See
+  # https://github.com/ossf/scorecard/blob/main/docs/checks.md#branch-protection
+  branch_protection_rule:
+  # To guarantee Maintained check is occasionally updated. See
+  # https://github.com/ossf/scorecard/blob/main/docs/checks.md#maintained
+  schedule:
+    - cron: '29 18 * * 4'
+  push:
+    branches: [ "main" ]
+
+# Declare default permissions as read only.
+permissions: read-all
+
+jobs:
+  analysis:
+    name: Scorecard analysis
+    runs-on: ubuntu-latest
+    permissions:
+      # Needed to upload the results to code-scanning dashboard.
+      security-events: write
+      # Needed to publish results and get a badge (see publish_results below).
+      id-token: write
+      # Uncomment the permissions below if installing in a private repository.
+      # contents: read
+      # actions: read
+
+    steps:
+      - name: "Checkout code"
+        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
+        with:
+          persist-credentials: false
+
+      - name: "Run analysis"
+        uses: ossf/scorecard-action@0864cf19026789058feabb7e87baa5f140aac736 # v2.3.1
+        with:
+          results_file: results.sarif
+          results_format: sarif
+          # (Optional) "write" PAT token. Uncomment the `repo_token` line below if:
+          # - you want to enable the Branch-Protection check on a *public* repository, or
+          # - you are installing Scorecard on a *private* repository
+          # To create the PAT, follow the steps in https://github.com/ossf/scorecard-action?tab=readme-ov-file#authentication-with-fine-grained-pat-optional.
+          # repo_token: ${{ secrets.SCORECARD_TOKEN }}
+
+          # Public repositories:
+          #   - Publish results to OpenSSF REST API for easy access by consumers
+          #   - Allows the repository to include the Scorecard badge.
+          #   - See https://github.com/ossf/scorecard-action#publishing-results.
+          # For private repositories:
+          #   - `publish_results` will always be set to `false`, regardless
+          #     of the value entered here.
+          publish_results: true
+
+      # Upload the results as artifacts (optional). Commenting out will disable uploads of run results in SARIF
+      # format to the repository Actions tab.
+      # - name: "Upload artifact"
+      #   uses: actions/upload-artifact@97a0fba1372883ab732affbe8f94b823f91727db # v3.pre.node20
+      #   with:
+      #     name: SARIF file
+      #     path: results.sarif
+      #     retention-days: 5
+
+      # # Upload the results to GitHub's code scanning dashboard (optional).
+      # # Commenting out will disable upload of results to your repo's Code Scanning dashboard
+      # - name: "Upload to code-scanning"
+      #   uses: github/codeql-action/upload-sarif@v3
+      #   with:
+      #     sarif_file: results.sarif

SECURITY.md

@@ -0,0 +1,5 @@
+# Security Policy
+Intel is committed to rapidly addressing security vulnerabilities affecting our customers and providing clear guidance on the solution, impact, severity and mitigation. 
+
+## Reporting a Vulnerability
+Please report any security vulnerabilities in this project utilizing the guidelines [here](https://www.intel.com/content/www/us/en/security-center/vulnerability-handling-guidelines.html).

configs/regular/kmeans.json

@@ -6,7 +6,7 @@
                 "estimator": "KMeans",
                 "estimator_params": {
                     "n_clusters": "[SPECIAL_VALUE]auto",
-                    "n_init": 10,
+                    "n_init": 1,
                     "max_iter": 30,
                     "tol": 1e-3,
                     "random_state": 42

configs/regular/pca.json

@@ -8,7 +8,7 @@
                     "n_components": 3,
                     "copy": true,
                     "whiten": false,
-                    "svd_solver": "full",
+                    "svd_solver": "covariance_eigh",
                     "tol": 0.0,
                     "iterated_power": 15,
                     "random_state": 42

envs/conda-env-sklearn.yml

@@ -10,7 +10,7 @@ dependencies:
   - modin-all
   - scikit-learn-intelex
   # sklbench dependencies
-  - scikit-learn<1.5
+  - scikit-learn
   - pandas
   - tabulate
   - fastparquet

envs/requirements-sklearn.txt

@@ -8,7 +8,7 @@ scikit-learn-intelex
 dpctl
 dpnp
 # sklbench dependencies
-scikit-learn<1.5
+scikit-learn
 pandas
 tabulate
 fastparquet