GH-33697: [CI][Python] Nightly test for PySpark 3.2.0 fail with Attri…

…buteError on numpy.bool (#33714)

### Rationale for this change
Fix for nightly integration tests with PySpark 3.2.0 failure.

### What changes are included in this PR?
NumPy version pin in `docker-compose.yml`.

### Are these changes tested?
Will test on the open PR with the CI.

### Are there any user-facing changes?
No.
* Closes: #33697

Lead-authored-by: Alenka Frim <frim.alenka@gmail.com>
Co-authored-by: Alenka Frim <AlenkaF@users.noreply.github.com>
Co-authored-by: Sutou Kouhei <kou@cozmixng.org>
Signed-off-by: Raúl Cumplido <raulcumplido@gmail.com>

ci/docker/conda-python-spark.dockerfile

@@ -23,11 +23,16 @@ FROM ${repo}:${arch}-conda-python-${python}
 ARG jdk=8
 ARG maven=3.5
 
+ARG numpy=latest
+COPY ci/scripts/install_numpy.sh /arrow/ci/scripts/
+
 RUN mamba install -q -y \
  openjdk=${jdk} \
  maven=${maven} \
  pandas && \
- mamba clean --all
+ mamba clean --all && \
+ mamba uninstall -q -y numpy && \
+ /arrow/ci/scripts/install_numpy.sh ${numpy}
 
 # installing specific version of spark
 ARG spark=master

ci/scripts/install_numpy.sh

@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+set -e
+
+if [ $# -gt 1 ]; then
+ echo "Usage: $0 <optional numpy version = latest>"
+ exit 1
+fi
+
+numpy=${1:-"latest"}
+
+if [ "${numpy}" = "latest" ]; then
+ pip install numpy
+else
+ pip install numpy==${numpy}
+fi

dev/tasks/tasks.yml

@@ -1589,9 +1589,9 @@ tasks:
  image: conda-python-hdfs
 {% endfor %}
 
-{% for python_version, spark_version, test_pyarrow_only in [("3.7", "v3.1.2", "false"),
- ("3.8", "v3.2.0", "false"),
- ("3.9", "master", "false")] %}
+{% for python_version, spark_version, test_pyarrow_only, numpy_version in [("3.7", "v3.1.2", "false", "latest"),
+  ("3.8", "v3.2.0", "false", "1.23"),
+  ("3.9", "master", "false", "latest")] %}
  test-conda-python-{{ python_version }}-spark-{{ spark_version }}:
  ci: github
  template: docker-tests/github.linux.yml
@@ -1600,6 +1600,7 @@ tasks:
  PYTHON: "{{ python_version }}"
  SPARK: "{{ spark_version }}"
  TEST_PYARROW_ONLY: "{{ test_pyarrow_only }}"
+ NUMPY: "{{ numpy_version }}"
  # use the branch-3.0 of spark, so prevent reusing any layers
  flags: --no-leaf-cache
  image: conda-python-spark

docker-compose.yml

@@ -1788,6 +1788,7 @@ services:
  # be set to ${MAVEN}
  maven: 3.5
  spark: ${SPARK}
+ numpy: ${NUMPY}
  shm_size: *shm-size
  environment:
  <<: *ccache