feat(spark): convert spark job example to Jupyter notebook

.gitignore

@@ -4,6 +4,7 @@ __debug_bin
 .idea/
 .DS_Store
 .swp
+.venv
 *~
 
 # Python cache files

examples/spark/spark_job.ipynb

@@ -0,0 +1,190 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "04811973",
+   "metadata": {},
+   "source": [
+    "<!--\n",
+    "Copyright The Kubeflow Authors.\n",
+    "\n",
+    "Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+    "you may not use this file except in compliance with the License.\n",
+    "You may obtain a copy of the License at\n",
+    "\n",
+    "http://www.apache.org/licenses/LICENSE-2.0\n",
+    "\n",
+    "Unless required by applicable law or agreed to in writing, software\n",
+    "distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+    "WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+    "-->"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a9138435",
+   "metadata": {},
+   "source": [
+    "# Spark Batch Job Example\n",
+    "\n",
+    "The notebook walks through the following steps:\n",
+    "\n",
+    "- Create a Spark session.\n",
+    "- Create a sample DataFrame.\n",
+    "- Apply a simple transformation.\n",
+    "- Display the results.\n",
+    "- Compute summary statistics.\n",
+    "- Stop the Spark session."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "425cb2b5",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from pyspark.sql import SparkSession\n",
+    "from pyspark.sql.functions import col"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b556d547",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "source": [
+    "## Create a Spark Session\n",
+    "\n",
+    "Create a Spark session that will be used to execute the example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "edc8006e",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "spark = SparkSession.builder.appName(\n",
+    "    \"KubeflowSparkExample\"\n",
+    ").getOrCreate()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "beb30ac6",
+   "metadata": {},
+   "source": [
+    "## Create a DataFrame\n",
+    "\n",
+    "Create a small DataFrame containing integers and compute the square of each value."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1a5e19e1",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "df = spark.range(10).withColumn(\"square\", col(\"id\") * col(\"id\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fb926d44",
+   "metadata": {},
+   "source": [
+    "## Display the DataFrame"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "acd0752d",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "print(\"Input DataFrame:\")\n",
+    "df.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9d53ba9",
+   "metadata": {},
+   "source": [
+    "## Compute Summary Statistics"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d1eb8438",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "count = df.count()\n",
+    "total = df.agg({\"square\": \"sum\"}).collect()[0][0]\n",
+    "\n",
+    "print(f\"Row count: {count}\")\n",
+    "print(f\"Sum of squares: {total}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "df932d3d",
+   "metadata": {},
+   "source": [
+    "## Stop the Spark Session\n",
+    "\n",
+    "Release the Spark resources after the example finishes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "802518dd",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "spark.stop()"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}