all code files updated

PacktPublishing · Jun 4, 2020 · b61704d · b61704d
1 parent c364faa
commit b61704d
Show file tree

Hide file tree

Showing 1,132 changed files with 197,378 additions and 66,870 deletions.
diff --git a/...xploring_data_structures-checkpoint.ipynb → ...xploring_data_structures-checkpoint.ipynb b/...xploring_data_structures-checkpoint.ipynb → ...xploring_data_structures-checkpoint.ipynb
diff --git a/...oints/Chapter_2_ALL_CODE-checkpoint.ipynb → ...oints/Chapter_2_ALL_CODE-checkpoint.ipynb b/...oints/Chapter_2_ALL_CODE-checkpoint.ipynb → ...oints/Chapter_2_ALL_CODE-checkpoint.ipynb
diff --git a/Chapter2/Chapter_2_ALL_CODE.ipynb → Chapter02/Chapter_2_ALL_CODE.ipynb b/Chapter2/Chapter_2_ALL_CODE.ipynb → Chapter02/Chapter_2_ALL_CODE.ipynb
diff --git a/...oints/Chapter_3_ALL_CODE-checkpoint.ipynb → ...oints/Chapter_3_ALL_CODE-checkpoint.ipynb b/...oints/Chapter_3_ALL_CODE-checkpoint.ipynb → ...oints/Chapter_3_ALL_CODE-checkpoint.ipynb
diff --git a/Chapter3/Chapter_3_ALL_CODE.ipynb → Chapter03/Chapter_3_ALL_CODE.ipynb b/Chapter3/Chapter_3_ALL_CODE.ipynb → Chapter03/Chapter_3_ALL_CODE.ipynb
diff --git a/...oints/CHAPTER_4_ALL_CODE-checkpoint.ipynb → ...oints/CHAPTER_4_ALL_CODE-checkpoint.ipynb b/...oints/CHAPTER_4_ALL_CODE-checkpoint.ipynb → ...oints/CHAPTER_4_ALL_CODE-checkpoint.ipynb
diff --git a/Chapter04/.ipynb_checkpoints/CHAPTER_4_Divide_and_conquer-checkpoint.ipynb b/Chapter04/.ipynb_checkpoints/CHAPTER_4_Divide_and_conquer-checkpoint.ipynb
@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/Chapter4/CHAPTER_4_ALL_CODE.ipynb → Chapter04/CHAPTER_4_ALL_CODE.ipynb b/Chapter4/CHAPTER_4_ALL_CODE.ipynb → Chapter04/CHAPTER_4_ALL_CODE.ipynb
diff --git a/Chapter04/CHAPTER_4_Divide_and_conquer.ipynb b/Chapter04/CHAPTER_4_Divide_and_conquer.ipynb
@@ -0,0 +1,139 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import findspark\n",
+    "findspark.init()\n",
+    "from pyspark.sql import SparkSession\n",
+    "spark = SparkSession.builder.master(\"local[*]\").getOrCreate()\n",
+    "sc = spark.sparkContext"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "        <div>\n",
+       "            <p><b>SparkContext</b></p>\n",
+       "\n",
+       "            <p><a href=\"http://07c60a334272:4040\">Spark UI</a></p>\n",
+       "\n",
+       "            <dl>\n",
+       "              <dt>Version</dt>\n",
+       "                <dd><code>v2.4.4</code></dd>\n",
+       "              <dt>Master</dt>\n",
+       "                <dd><code>local[*]</code></dd>\n",
+       "              <dt>AppName</dt>\n",
+       "                <dd><code>pyspark-shell</code></dd>\n",
+       "            </dl>\n",
+       "        </div>\n",
+       "        "
+      ],
+      "text/plain": [
+       "<SparkContext master=local[*] appName=pyspark-shell>"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sc"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['python', 'java', 'ottawa', 'ottawa', 'java', 'news']\n"
+     ]
+    }
+   ],
+   "source": [
+    "wordsList = ['python', 'java', 'ottawa', 'ottawa', 'java','news']\n",
+    "wordsRDD = sc.parallelize(wordsList, 4)\n",
+    "# Print out the type of wordsRDD\n",
+    "print (wordsRDD.collect())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[('python', 1), ('java', 1), ('ottawa', 1), ('ottawa', 1), ('java', 1), ('news', 1)]\n"
+     ]
+    }
+   ],
+   "source": [
+    "wordPairs = wordsRDD.map(lambda w: (w, 1))\n",
+    "print (wordPairs.collect())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[('python', 1), ('java', 2), ('ottawa', 2), ('news', 1)]\n"
+     ]
+    }
+   ],
+   "source": [
+    "wordCountsCollected = wordPairs.reduceByKey(lambda x,y: x+y)\n",
+    "print(wordCountsCollected.collect())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "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": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}