removing redundant files not used in lessons

Author: matthew-mcateer

1_getting_started_with_spark_streaming/1_0_Apache Spark Tutorial.pptx

@@ -0,0 +1,132 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# First Spark Streaming Example\n",
+    "_____"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Simple Local Example\n",
+    "\n",
+    "This demonstration will contain two parts. The first will be a "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import findspark"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "findspark.init('/home/matthew/spark-2.1.0-bin-hadoop2.7')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pyspark import SparkContext\n",
+    "from pyspark.streaming import StreamingContext\n",
+    "\n",
+    "# Create a local StreamingContext with two working thread and batch interval of 1 second\n",
+    "sc = SparkContext(\"local[2]\", \"LocalWordCount\")\n",
+    "ssc = StreamingContext(sc, 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a DStream that will connect to hostname:port, like localhost:9999\n",
+    "# Firewalls might block this!\n",
+    "lines = ssc.socketTextStream(\"localhost\", 9999)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Split each line into words\n",
+    "words = lines.flatMap(lambda line: line.split(\" \"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Count each word in each batch\n",
+    "pairs = words.map(lambda word: (word, 1))\n",
+    "wordCounts = pairs.reduceByKey(lambda x, y: x + y)\n",
+    "\n",
+    "# Print the first ten elements of each RDD generated in this DStream to the console\n",
+    "wordCounts.pprint()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now we open up a Unix terminal and type:\n",
+    "\n",
+    "         $ nc -lk 9999\n",
+    "     $ hello world any text you want\n",
+    "     \n",
+    "With this running run the line below, then type Ctrl+C to terminate it."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ssc.start()             # Start the computation\n",
+    "ssc.awaitTermination()  # Wait for the computation to terminate"
+   ]
+  }
+ ],
+ "metadata": {
+  "anaconda-cloud": {},
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.5.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}