add notebook container

.gitignore

@@ -0,0 +1,170 @@
+### Example user template template
+### Example user template
+
+# IntelliJ project files
+.idea
+*.iml
+out
+gen
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+

Dockerfile

@@ -28,7 +28,7 @@ ENV PYTHON_VER=python3.11
 RUN apt update && \
 	apt-get install -y software-properties-common && \
 	add-apt-repository ppa:deadsnakes/ppa && \
-	apt install -y $PYTHON_VER python3-pip && \
+	apt install -y $PYTHON_VER python3-pip gcc $PYTHON_VER-dev && \
 	apt install -y r-base r-base-dev && \
 	rm -rf /var/lib/apt/lists/*
 
@@ -46,6 +46,10 @@ COPY --from=build /opt/$SPARK_VER/ /opt/spark/
 # this doesn't seem to actually work
 RUN echo "spark.pyspark.python /usr/bin/$PYTHON_VER" > /opt/spark/conf/spark-defaults.conf
 
+RUN /usr/bin/$PYTHON_VER -m pip install --upgrade pip && \
+    /usr/bin/$PYTHON_VER -m pip install --force-reinstall psutil==5.9.8 && \
+    /usr/bin/$PYTHON_VER -m pip install jupyterlab==4.2.0 pyspark==3.5.1 findspark==2.0.1
+
 COPY entrypoint.sh /opt/
 RUN chmod a+x /opt/entrypoint.sh
 

README.md

@@ -5,6 +5,7 @@ Rancher.
 
 ## Submit example
 
+### Submitting a job in Rancher
 Open a shell in a container in rancher with spark installed in `/opt/spark` (as of this writing,
 the `ci-core-cdm-prototype-spark-bash` container is appropriate and has environment variables set up
 for the necessary host and port configurations).
@@ -24,6 +25,52 @@ root@f058c872158d:/opt/spark# bin/spark-submit --master spark://10.58.1.104:7077
 Pi is roughly 3.144080
 ```
 
+### Submitting a Spark Job via Jupyter Notebook
+
+After launching the Jupyter Notebook, establish a Spark context or session with the master set to 
+`spark://spark-master:7077` and proceed to submit your job. Once the job is submitted, you can monitor 
+the job status and logs in the Spark UI.
+
+Sample code to calculate Pi using `SparkContext`:
+```python
+import findspark
+findspark.init()
+from pyspark import SparkConf, SparkContext
+import random
+
+conf = SparkConf().setMaster("spark://spark-master:7077").setAppName("Pi")
+sc = SparkContext(conf=conf)
+
+num_samples = 100000000
+def inside(p):     
+  x, y = random.random(), random.random()
+  return x*x + y*y < 1
+count = sc.parallelize(range(0, num_samples)).filter(inside).count()
+pi = 4 * count / num_samples
+print(pi)
+sc.stop()
+```
+
+Sample code to create a DataFrame and display the contents with `SparkSession`:
+```python
+import findspark
+findspark.init()
+from pyspark.sql import SparkSession
+
+spark = SparkSession.builder \
+    .master("spark://spark-master:7077") \
+    .appName("TestSparkJob") \
+    .getOrCreate()
+
+data = [("Alice", 34), ("Bob", 45), ("Charlie", 56)]
+df = spark.createDataFrame(data, ["Name", "Age"])
+
+df.show()
+
+spark.stop()
+```
+
+
 ## Notes
 
 * When we switch to Rancher 2 should probably switch from the standalone scheduler to the k8s

docker-compose.yaml

@@ -15,7 +15,7 @@ services:
       - MODE=master
       - PORT=7077
       - WEBPORT=8080
-      
+
   spark-worker1:
     build:
       context: .
@@ -47,3 +47,16 @@ services:
       - CORES=2
       - MEM=1G
       - SPARK_MASTER_URL=spark://spark-master:7077
+
+  notebook:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    ports:
+      - "4040:4040"
+      - "4041:4041"
+    depends_on:
+      - spark-master
+    environment:
+      - MODE=notebook
+      - PORT=4041

entrypoint.sh

@@ -27,6 +27,18 @@ elif [ "$MODE" == "worker" ] ; then
     /opt/spark/sbin/start-worker.sh --cores "$CORES" --memory "$MEM" "$SPARK_MASTER_URL"
 elif [ "$MODE" == "bash" ] ; then
     bash
+elif [ "$MODE" == "notebook" ] ; then
+    echo "starting jupyter notebook"
+    WORKSPACE_DIR="/cdm_shared_workspace"
+    mkdir -p "$WORKSPACE_DIR" || { echo "Error: Failed to create workspace directory"; exit 1; }
+    cd "$WORKSPACE_DIR" || { echo "Error: Failed to navigate to workspace directory"; exit 1; }
+    jupyter lab --ip=0.0.0.0 \
+                --port=$PORT \
+                --no-browser \
+                --allow-root \
+                --notebook-dir="$WORKSPACE_DIR" \
+                --ServerApp.token='' \
+                --ServerApp.password=''
 else
     echo "Unrecognized MODE env var: [$MODE]"
 fi