From 7a39ed0a8c782f28bc472f310aab69739f3d3eca Mon Sep 17 00:00:00 2001 From: heibaiying <31504331+heibaiying@users.noreply.github.com> Date: Mon, 22 Apr 2019 22:39:25 +0800 Subject: [PATCH] Update Hadoop-MapReduce.md --- notes/Hadoop-MapReduce.md | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/notes/Hadoop-MapReduce.md b/notes/Hadoop-MapReduce.md index f329682..6dc9ff5 100644 --- a/notes/Hadoop-MapReduce.md +++ b/notes/Hadoop-MapReduce.md @@ -110,6 +110,8 @@ Merge是怎样的?如“aaa”从某个map task读取过来时值是5,从另 ## 四、MapReduce 词频统计案例 +> 源码下载地址:[hadoop-word-count](https://github.com/heibaiying/BigData-Notes/tree/master/code/Hadoop/hadoop-word-count) + ### 4.1 项目简介 这里给出一个经典的案例:词频统计。统计如下样本数据中每个单词出现的次数。 @@ -132,12 +134,8 @@ HBase Hive 为方便大家开发,我在项目源码中放置了一个工具类`WordCountDataUtils`,用于产生词频统计样本文件: -> 本篇文章所有源码下载地址:[hadoop-word-count](https://github.com/heibaiying/BigData-Notes/tree/master/code/Hadoop/hadoop-word-count) ```java -/** - * 产生词频统计模拟数据 - */ public class WordCountDataUtils { public static final List WORD_LIST = Arrays.asList("Spark", "Hadoop", "HBase", @@ -231,7 +229,6 @@ public class WordCountMapper extends Mapper