ci[rust,python]: Improve benchmark workflow (#4800)

.github/workflows/benchmark.yaml

@@ -12,42 +12,71 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  test:
+  main:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - name: Set up Rust
-        uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: nightly-2022-08-22
+
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
           python-version: '3.10'
           cache: 'pip'
           cache-dependency-path: 'py-polars/requirements-dev.txt'
+
+      - name: Create virtual environment
+        working-directory: py-polars
+        run: |
+          python -m venv venv
+          echo "$GITHUB_WORKSPACE/py-polars/venv/bin" >> $GITHUB_PATH
+
+      - name: Install Python dependencies
+        working-directory: py-polars
+        run: |
+          pip install --upgrade pip
+          pip install -r requirements-dev.txt
+
       - name: Set up R
-        uses: r-lib/actions/setup-r@v1
+        uses: r-lib/actions/setup-r@v2
         with:
           r-version: '3.5.3'
-      - name: Run benchmark tests
+
+      - name: Generate data
+        working-directory: py-polars/tests/db-benchmark
+        run: |
+          Rscript -e 'install.packages("data.table", repos="https://Rdatatable.github.io/data.table")'
+          Rscript groupby-datagen.R 1e7 1e2 5 0
+
+      - name: Set up Rust
+        uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: nightly-2022-08-22
+
+      - name: Cache Rust
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: py-polars
+
+      - name: Install Polars
         env:
           RUSTFLAGS: -C embed-bitcode
+        working-directory: py-polars
         run: |
-          pip install --upgrade pip
-          python -m venv venv
-          source venv/bin/activate
-          pip install -r py-polars/requirements-dev.txt
-          cd py-polars
+          source activate
           maturin develop --release -- -C codegen-units=8 -C lto=thin -C target-cpu=native
-          cd tests/db-benchmark
-          Rscript -e 'install.packages("data.table", repos="https://Rdatatable.github.io/data.table")'
-          Rscript groupby-datagen.R 1e7 1e2 5 0
-          echo "LAZY vs EAGER tests"
-          python lazy_vs_eager.py
-          echo "run various.py tests"
-          python various.py
-          echo "ON STRINGS"
-          python main.py on_strings
-          echo "ON CATEGORICALS"
-          python main.py
+
+      - name: Run benchmark tests - lazy versus eager
+        working-directory: py-polars/tests/db-benchmark
+        run: python lazy_vs_eager.py
+
+      - name: Run benchmark tests - various
+        working-directory: py-polars/tests/db-benchmark
+        run: python various.py
+
+      - name: Run benchmark tests - on strings
+        working-directory: py-polars/tests/db-benchmark
+        run: python main.py on_strings
+
+      - name: Run benchmark tests - on categoricals
+        working-directory: py-polars/tests/db-benchmark
+        run: python main.py