Fix benchmark image. (#14376)

Fixes benchmark image and benchmark diff.

I will revert the CI/build changes in a follow-up PR.

Authors:
   - Bradley Dice (https://github.com/bdice)

Approvers:
   - Ray Douglass (https://github.com/raydouglass)

.github/workflows/build.yaml

@@ -55,7 +55,7 @@ jobs:
       skip_upload_pkgs: libcudf-example
   docs-build:
     if: github.ref_type == 'branch'
-    needs: python-build
+    #needs: python-build
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:

.github/workflows/pr.yaml

@@ -12,85 +12,85 @@ concurrency:
 jobs:
   pr-builder:
     needs:
-      - checks
-      - conda-cpp-build
-      - conda-cpp-tests
-      - conda-python-build
-      - conda-python-cudf-tests
-      - conda-python-other-tests
-      - conda-java-tests
-      - conda-notebook-tests
+      #- checks
+      #- conda-cpp-build
+      #- conda-cpp-tests
+      #- conda-python-build
+      #- conda-python-cudf-tests
+      #- conda-python-other-tests
+      #- conda-java-tests
+      #- conda-notebook-tests
       - docs-build
-      - wheel-build-cudf
-      - wheel-tests-cudf
-      - wheel-build-dask-cudf
-      - wheel-tests-dask-cudf
-      - unit-tests-cudf-pandas
-      - pandas-tests
+      #- wheel-build-cudf
+      #- wheel-tests-cudf
+      #- wheel-build-dask-cudf
+      #- wheel-tests-dask-cudf
+      #- unit-tests-cudf-pandas
+      #- pandas-tests
       #- pandas-tests-diff
       #- pandas-tests-diff-comment
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-  checks:
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      enable_check_generated_files: false
-  conda-cpp-build:
-    needs: checks
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      build_type: pull-request
-  conda-cpp-tests:
-    needs: conda-cpp-build
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      build_type: pull-request
-  conda-python-build:
-    needs: conda-cpp-build
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      build_type: pull-request
-  conda-python-cudf-tests:
-    needs: conda-python-build
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      build_type: pull-request
-      test_script: "ci/test_python_cudf.sh"
-  conda-python-other-tests:
-    # Tests for dask_cudf, custreamz, cudf_kafka are separated for CI parallelism
-    needs: conda-python-build
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      build_type: pull-request
-      test_script: "ci/test_python_other.sh"
-  conda-java-tests:
-    needs: conda-cpp-build
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      build_type: pull-request
-      node_type: "gpu-v100-latest-1"
-      arch: "amd64"
-      container_image: "rapidsai/ci-conda:latest"
-      run_script: "ci/test_java.sh"
-  conda-notebook-tests:
-    needs: conda-python-build
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      build_type: pull-request
-      node_type: "gpu-v100-latest-1"
-      arch: "amd64"
-      container_image: "rapidsai/ci-conda:latest"
-      run_script: "ci/test_notebooks.sh"
+# checks:
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     enable_check_generated_files: false
+# conda-cpp-build:
+#   needs: checks
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     build_type: pull-request
+# conda-cpp-tests:
+#   needs: conda-cpp-build
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     build_type: pull-request
+# conda-python-build:
+#   needs: conda-cpp-build
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     build_type: pull-request
+# conda-python-cudf-tests:
+#   needs: conda-python-build
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     build_type: pull-request
+#     test_script: "ci/test_python_cudf.sh"
+# conda-python-other-tests:
+#   # Tests for dask_cudf, custreamz, cudf_kafka are separated for CI parallelism
+#   needs: conda-python-build
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     build_type: pull-request
+#     test_script: "ci/test_python_other.sh"
+# conda-java-tests:
+#   needs: conda-cpp-build
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     build_type: pull-request
+#     node_type: "gpu-v100-latest-1"
+#     arch: "amd64"
+#     container_image: "rapidsai/ci-conda:latest"
+#     run_script: "ci/test_java.sh"
+# conda-notebook-tests:
+#   needs: conda-python-build
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     build_type: pull-request
+#     node_type: "gpu-v100-latest-1"
+#     arch: "amd64"
+#     container_image: "rapidsai/ci-conda:latest"
+#     run_script: "ci/test_notebooks.sh"
   docs-build:
-    needs: conda-python-build
+    #needs: conda-python-build
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
@@ -99,53 +99,53 @@ jobs:
       arch: "amd64"
       container_image: "rapidsai/ci-conda:latest"
       run_script: "ci/build_docs.sh"
-  wheel-build-cudf:
-    needs: checks
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      build_type: pull-request
-      script: "ci/build_wheel_cudf.sh"
-  wheel-tests-cudf:
-    needs: wheel-build-cudf
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      build_type: pull-request
-      script: ci/test_wheel_cudf.sh
-  wheel-build-dask-cudf:
-    needs: wheel-tests-cudf
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      matrix_filter: map(select(.ARCH == "amd64" and .PY_VER == "3.10" and (.CUDA_VER == "11.8.0" or .CUDA_VER == "12.0.1")))
-      build_type: pull-request
-      script: "ci/build_wheel_dask_cudf.sh"
-  wheel-tests-dask-cudf:
-    needs: wheel-build-dask-cudf
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      matrix_filter: map(select(.ARCH == "amd64" and .PY_VER == "3.10" and (.CUDA_VER == "11.8.0" or .CUDA_VER == "12.0.1")))
-      build_type: pull-request
-      script: ci/test_wheel_dask_cudf.sh
-  unit-tests-cudf-pandas:
-    needs: wheel-build-cudf
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      matrix_filter: map(select(.ARCH == "amd64" and .PY_VER == "3.10" and (.CUDA_VER == "11.8.0" or .CUDA_VER == "12.0.1")))
-      build_type: pull-request
-      script: ci/cudf_pandas_scripts/run_tests.sh
-  pandas-tests:
-    # run the Pandas unit tests using PR branch
-    needs: wheel-build-cudf
-    secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      matrix_filter: map(select(.ARCH == "amd64")) | max_by(.CUDA_VER) | [.]
-      build_type: pull-request
-      script: ci/cudf_pandas_scripts/pandas-tests/run.sh pr
+# wheel-build-cudf:
+#   needs: checks
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     build_type: pull-request
+#     script: "ci/build_wheel_cudf.sh"
+# wheel-tests-cudf:
+#   needs: wheel-build-cudf
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     build_type: pull-request
+#     script: ci/test_wheel_cudf.sh
+# wheel-build-dask-cudf:
+#   needs: wheel-tests-cudf
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     matrix_filter: map(select(.ARCH == "amd64" and .PY_VER == "3.10" and (.CUDA_VER == "11.8.0" or .CUDA_VER == "12.0.1")))
+#     build_type: pull-request
+#     script: "ci/build_wheel_dask_cudf.sh"
+# wheel-tests-dask-cudf:
+#   needs: wheel-build-dask-cudf
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     matrix_filter: map(select(.ARCH == "amd64" and .PY_VER == "3.10" and (.CUDA_VER == "11.8.0" or .CUDA_VER == "12.0.1")))
+#     build_type: pull-request
+#     script: ci/test_wheel_dask_cudf.sh
+# unit-tests-cudf-pandas:
+#   needs: wheel-build-cudf
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     matrix_filter: map(select(.ARCH == "amd64" and .PY_VER == "3.10" and (.CUDA_VER == "11.8.0" or .CUDA_VER == "12.0.1")))
+#     build_type: pull-request
+#     script: ci/cudf_pandas_scripts/run_tests.sh
+# pandas-tests:
+#   # run the Pandas unit tests using PR branch
+#   needs: wheel-build-cudf
+#   secrets: inherit
+#   uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+#   with:
+#     matrix_filter: map(select(.ARCH == "amd64")) | max_by(.CUDA_VER) | [.]
+#     build_type: pull-request
+#     script: ci/cudf_pandas_scripts/pandas-tests/run.sh pr
   #pandas-tests-diff:
   #  # diff the results of running the Pandas unit tests and publish a job summary
   #  needs: [pandas-tests-main, pandas-tests-pr]

ci/build_docs.sh

@@ -16,14 +16,16 @@ conda activate docs
 
 rapids-print-env
 
-rapids-logger "Downloading artifacts from previous jobs"
-CPP_CHANNEL=$(rapids-download-conda-from-s3 cpp)
-PYTHON_CHANNEL=$(rapids-download-conda-from-s3 python)
-
+#rapids-logger "Downloading artifacts from previous jobs"
+#CPP_CHANNEL=$(rapids-download-conda-from-s3 cpp)
+#PYTHON_CHANNEL=$(rapids-download-conda-from-s3 python)
+#
+#rapids-mamba-retry install \
+#  --channel "${CPP_CHANNEL}" \
+#  --channel "${PYTHON_CHANNEL}" \
+#  libcudf cudf dask-cudf
 rapids-mamba-retry install \
-  --channel "${CPP_CHANNEL}" \
-  --channel "${PYTHON_CHANNEL}" \
-  libcudf cudf dask-cudf
+  libcudf=23.10 cudf=23.10 dask-cudf=23.10
 
 export RAPIDS_VERSION_NUMBER="23.10"
 export RAPIDS_DOCS_DIR="$(mktemp -d)"

docs/cudf/source/cudf_pandas/benchmarks.md

@@ -6,9 +6,9 @@ We reproduced the [Database-like ops benchmark](https://duckdblabs.github.io/db-
 including a solution using `cudf.pandas`. Here are the results:
 
 <figure>
-<img src="../_static/duckdb-benchmark-groupby-join.png"
-class="align-center" width="750"
-alt="_static/duckdb-benchmark-groupby-join.png" />
+
+![duckdb-benchmark-groupby-join](../_static/duckdb-benchmark-groupby-join.png)
+
 <figcaption style="text-align: center;">Results of the <a
 href="https://duckdblabs.github.io/db-benchmark/">Database-like ops
 benchmark</a> including <span
@@ -46,7 +46,7 @@ source pandas/py-pandas/bin/activate
 pip install --extra-index-url=https://pypi.nvidia.com cudf-cu12  # or cudf-cu11
 ```
 
-5. Modify pandas join/group code to use `cudf.pandas`:
+5. Modify pandas join/group code to use `cudf.pandas` and be compatible with pandas 1.5 APIs:
 
 ```bash
 diff --git a/pandas/groupby-pandas.py b/pandas/groupby-pandas.py
@@ -59,15 +59,46 @@ index 58eeb26..2ddb209 100755
 
  print("# groupby-pandas.py", flush=True)
 
- diff --git a/pandas/join-pandas.py b/pandas/join-pandas.py
- index f39beb0..655dd82 100755
- --- a/pandas/join-pandas.py
- +++ b/pandas/join-pandas.py
- @@ -1,4 +1,4 @@
- -#!/usr/bin/env python3
- +#!/usr/bin/env -S python3 -m cudf.pandas
+diff --git a/pandas/join-pandas.py b/pandas/join-pandas.py
+index f39beb0..a9ad651 100755
+--- a/pandas/join-pandas.py
++++ b/pandas/join-pandas.py
+@@ -1,4 +1,4 @@
+-#!/usr/bin/env python3
++#!/usr/bin/env -S python3 -m cudf.pandas
 
-  print("# join-pandas.py", flush=True)
+ print("# join-pandas.py", flush=True)
+
+@@ -26,7 +26,7 @@ if len(src_jn_y) != 3:
+
+ print("loading datasets " + data_name + ", " + y_data_name[0] + ", " + y_data_name[1] + ", " + y_data_name[2], flush=True)
+
+-x = pd.read_csv(src_jn_x, engine='pyarrow', dtype_backend='pyarrow')
++x = pd.read_csv(src_jn_x, engine='pyarrow')
+
+ # x['id1'] = x['id1'].astype('Int32')
+ # x['id2'] = x['id2'].astype('Int32')
+@@ -35,17 +35,17 @@ x['id4'] = x['id4'].astype('category') # remove after datatable#1691
+ x['id5'] = x['id5'].astype('category')
+ x['id6'] = x['id6'].astype('category')
+
+-small = pd.read_csv(src_jn_y[0], engine='pyarrow', dtype_backend='pyarrow')
++small = pd.read_csv(src_jn_y[0], engine='pyarrow')
+ # small['id1'] = small['id1'].astype('Int32')
+ small['id4'] = small['id4'].astype('category')
+ # small['v2'] = small['v2'].astype('float64')
+-medium = pd.read_csv(src_jn_y[1], engine='pyarrow', dtype_backend='pyarrow')
++medium = pd.read_csv(src_jn_y[1], engine='pyarrow')
+ # medium['id1'] = medium['id1'].astype('Int32')
+ # medium['id2'] = medium['id2'].astype('Int32')
+ medium['id4'] = medium['id4'].astype('category')
+ medium['id5'] = medium['id5'].astype('category')
+ # medium['v2'] = medium['v2'].astype('float64')
+-big = pd.read_csv(src_jn_y[2], engine='pyarrow', dtype_backend='pyarrow')
++big = pd.read_csv(src_jn_y[2], engine='pyarrow')
+ # big['id1'] = big['id1'].astype('Int32')
+ # big['id2'] = big['id2'].astype('Int32')
+ # big['id3'] = big['id3'].astype('Int32')
 ```
 
 6. Run Modified pandas benchmarks: