Fixed deploy pipeline and random source

.github/workflows/publish.yml

@@ -59,37 +59,3 @@ jobs:
         with:
           token: ${{ secrets.PYPI_TOKEN }}
           python-version: '3.10.9'
-
-  build:
-    # Need to deploy a PyPi version first to make sure we do not overwrite an old Docker version
-    needs: [build-and-publish-py-package]
-    if: github.event_name == 'push'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Setup Docker Buildx
-        uses: docker/setup-buildx-action@v2
-
-      - name: Login to the GitHub Container Registry
-        uses: docker/login-action@v2
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Define docker image tags
-        id: tags
-        run: |
-          version=$(cat pyproject.toml | grep version | head -n 1 | sed -e 's/version = "\(.*\)"/\1/')
-          tags="matsmoll/aligned-ml:${version},matsmoll/aligned-ml:latest"
-          echo ::set-output name=tags::$tags
-
-      - uses: docker/build-push-action@v4
-        with:
-          context: .
-          platforms: linux/amd64
-          file: Dockerfile
-          push: true
-          tags: ${{ steps.tags.outputs.tags }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max

aligned/sources/random_source.py

@@ -235,6 +235,13 @@ def multi_source_features_for(  # type: ignore
         source, _ = requests[0]
 
         async def random_features_for(facts: RetrivalJob, request: RetrivalRequest) -> pl.LazyFrame:
+
+            if source.partial_data.is_empty():
+                df = await facts.to_polars()
+                random = (await data_for_request(request, df.height)).lazy()
+                join_columns = set(request.all_returned_columns) - set(df.columns)
+                return df.hstack(random.select(pl.col(join_columns)).collect()).lazy()
+
             join_columns = set(request.all_returned_columns) - set(source.partial_data.columns)
             if not join_columns:
                 return source.partial_data.lazy()

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "aligned"
-version = "0.0.103"
+version = "0.0.104"
 description = "A data managment and lineage tool for ML applications."
 authors = ["Mats E. Mollestad <[email protected]>"]
 license = "Apache-2.0"