lec 24 starter

lec/24-spark/Dockerfile

+FROM ubuntu:24.04
+RUN apt-get update; apt-get install -y wget curl openjdk-11-jdk python3-pip nano
+
+# SPARK
+#RUN wget https://archive.apache.org/dist/spark/spark-3.5.5/spark-3.5.5-bin-hadoop3.tgz && tar -xf spark-3.5.5-bin-hadoop3.tgz && rm spark-3.5.5-bin-hadoop3.tgz
+RUN wget https://dlcdn.apache.org/spark/spark-3.5.5/spark-3.5.5-bin-hadoop3.tgz && tar -xf spark-3.5.5-bin-hadoop3.tgz && rm spark-3.5.5-bin-hadoop3.tgz
+
+# HDFS
+RUN wget https://dlcdn.apache.org/hadoop/common/hadoop-3.3.6/hadoop-3.3.6.tar.gz && tar -xf hadoop-3.3.6.tar.gz && rm hadoop-3.3.6.tar.gz
+
+# Jupyter
+RUN pip3 install jupyterlab==4.3.5 pandas==2.2.3 pyspark==3.5.5 matplotlib==3.10.1 --break-system-packages
+
+ENV JAVA_HOME=/usr/lib/jvm/java-11-openjdk-amd64
+ENV PATH="${PATH}:/hadoop-3.3.6/bin"
+ENV HADOOP_HOME=/hadoop-3.3.6

lec/24-spark/docker-compose.yml

+services:
+    nb:
+        image: spark-demo
+        ports:
+        - "127.0.0.1:5000:5000"
+        - "127.0.0.1:4040:4040"
+        volumes:
+        - "./nb:/nb"
+        command: python3 -m jupyterlab --no-browser --ip=0.0.0.0 --port=5000 --allow-root --NotebookApp.token=''
+
+    nn:
+        image: spark-demo
+        hostname: nn
+        command: sh -c "hdfs namenode -format -force && hdfs namenode -D dfs.replication=1 -fs hdfs://nn:9000"
+
+    dn:
+        image: spark-demo
+        command: hdfs datanode -fs hdfs://nn:9000
+
+    spark-boss:
+        image: spark-demo
+        hostname: boss
+        command: sh -c "/spark-3.5.5-bin-hadoop3/sbin/start-master.sh && sleep infinity"
+
+    spark-worker:
+        image: spark-demo
+        command: sh -c "/spark-3.5.5-bin-hadoop3/sbin/start-worker.sh spark://boss:7077 -c 2 -m 2g && sleep infinity"
+        deploy:
+                replicas: 2

lec/24-spark/nb/starter.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "595b2e04-3312-4c06-a0fd-9c147076f0f9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Setting default log level to \"WARN\".\n",
+      "To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n",
+      "25/03/15 18:51:29 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n"
+     ]
+    }
+   ],
+   "source": [
+    "from pyspark.sql import SparkSession\n",
+    "spark = (SparkSession.builder.appName(\"cs544\")\n",
+    "         .master(\"spark://boss:7077\")\n",
+    "         .config(\"spark.executor.memory\", \"2G\")\n",
+    "         .config(\"spark.sql.warehouse.dir\", \"hdfs://nn:9000/user/hive/warehouse\")\n",
+    "         .enableHiveSupport()\n",
+    "         .getOrCreate())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "d8efc653-d8cf-4fb2-a982-fb2f93a8630f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>x1</th>\n",
+       "      <th>x2</th>\n",
+       "      <th>y</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3.262734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>6.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>6.347860</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.134057</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    x1   x2         y\n",
+       "0  2.0  1.0  3.262734\n",
+       "1  6.0  0.0  6.347860\n",
+       "2  3.0  0.0  3.134057"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "df = pd.DataFrame({\"x1\": np.random.randint(0, 10, 100).astype(float), \n",
+    "                   \"x2\": np.random.randint(0, 3, 100).astype(float)})\n",
+    "df[\"y\"] = df[\"x1\"] + df[\"x2\"] + np.random.rand(len(df))\n",
+    "df = spark.createDataFrame(df)\n",
+    "df.limit(3).toPandas()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}