用MR和Hive对sougou.500w.utf8进行数据分析

[{"title":"（ 49 个子文件 2.84MB ） 用MR和Hive对sougou.500w.utf8进行数据分析","children":[{"title":"sougou.500w.utf8数据分析","children":[{"title":"java 代码","children":[{"title":"One.java <span style='color:#111;'> 1.68KB </span>","children":null,"spread":false},{"title":"Two.java <span style='color:#111;'> 2.33KB </span>","children":null,"spread":false},{"title":"Five.java <span style='color:#111;'> 3.21KB </span>","children":null,"spread":false},{"title":"Ten.java <span style='color:#111;'> 2.64KB </span>","children":null,"spread":false},{"title":"Seven.java <span style='color:#111;'> 3.69KB </span>","children":null,"spread":false},{"title":"Eight.java <span style='color:#111;'> 1.61KB </span>","children":null,"spread":false},{"title":"HBaseImport.java <span style='color:#111;'> 3.75KB </span>","children":null,"spread":false},{"title":"Nine.java <span style='color:#111;'> 1.77KB </span>","children":null,"spread":false},{"title":"Four.java <span style='color:#111;'> 2.37KB </span>","children":null,"spread":false},{"title":"Three.java <span style='color:#111;'> 2.43KB </span>","children":null,"spread":false},{"title":"Six.java <span style='color:#111;'> 3.31KB </span>","children":null,"spread":false}],"spread":false},{"title":"截图","children":[{"title":"非空.png <span style='color:#111;'> 41.47KB </span>","children":null,"spread":false},{"title":"sougou.png <span style='color:#111;'> 5.65KB </span>","children":null,"spread":false},{"title":"javasix.png <span style='color:#111;'> 49.24KB </span>","children":null,"spread":false},{"title":"word.png <span style='color:#111;'> 100.23KB </span>","children":null,"spread":false},{"title":"占比.png <span style='color:#111;'> 43.97KB </span>","children":null,"spread":false},{"title":"数据加载到hdfs上.png <span style='color:#111;'> 6.42KB </span>","children":null,"spread":false},{"title":"javatwo.png <span style='color:#111;'> 44.54KB </span>","children":null,"spread":false},{"title":"gong.png <span style='color:#111;'> 46.20KB </span>","children":null,"spread":false},{"title":"javanine.png <span style='color:#111;'> 60.94KB </span>","children":null,"spread":false},{"title":"灌输.png <span style='color:#111;'> 34.45KB </span>","children":null,"spread":false},{"title":"频度.png <span style='color:#111;'> 35.57KB </span>","children":null,"spread":false},{"title":"2用户.png <span style='color:#111;'> 55.27KB </span>","children":null,"spread":false},{"title":"javafour.png <span style='color:#111;'> 33.84KB </span>","children":null,"spread":false},{"title":"xxxxxx.png <span style='color:#111;'> 48.06KB </span>","children":null,"spread":false},{"title":"javaten.png <span style='color:#111;'> 49.13KB </span>","children":null,"spread":false},{"title":"java.png <span style='color:#111;'> 46.33KB </span>","children":null,"spread":false},{"title":"five.png <span style='color:#111;'> 35.83KB </span>","children":null,"spread":false},{"title":"1.png <span style='color:#111;'> 54.04KB </span>","children":null,"spread":false},{"title":"2.png <span style='color:#111;'> 58.52KB </span>","children":null,"spread":false},{"title":"年月日.png <span style='color:#111;'> 68.87KB </span>","children":null,"spread":false},{"title":"uid.png <span style='color:#111;'> 49.34KB </span>","children":null,"spread":false},{"title":"hbase shell.png <span style='color:#111;'> 71.39KB </span>","children":null,"spread":false},{"title":"javaone.png <span style='color:#111;'> 54.39KB </span>","children":null,"spread":false},{"title":"11.png <span style='color:#111;'> 47.81KB </span>","children":null,"spread":false},{"title":"javathree.png <span style='color:#111;'> 52.84KB </span>","children":null,"spread":false},{"title":"javaeight.png <span style='color:#111;'> 51.77KB </span>","children":null,"spread":false},{"title":".sh.png <span style='color:#111;'> 2.35KB </span>","children":null,"spread":false},{"title":"数据过滤.png <span style='color:#111;'> 2.69KB </span>","children":null,"spread":false},{"title":"创建表1.png <span style='color:#111;'> 15.09KB </span>","children":null,"spread":false},{"title":"创建分区表.png <span style='color:#111;'> 19.06KB </span>","children":null,"spread":false},{"title":"xianjian.png <span style='color:#111;'> 54.94KB </span>","children":null,"spread":false},{"title":"总条数.png <span style='color:#111;'> 38.55KB </span>","children":null,"spread":false},{"title":"保存到hdfs中.png <span style='color:#111;'> 25.35KB </span>","children":null,"spread":false}],"spread":false},{"title":"需求分析描述.doc <span style='color:#111;'> 158.50KB </span>","children":null,"spread":false},{"title":"任务书.doc <span style='color:#111;'> 13.00KB </span>","children":null,"spread":false},{"title":"系统结构设计.docx <span style='color:#111;'> 51.95KB </span>","children":null,"spread":false},{"title":"分布式计算应用开发课程设计.docx <span style='color:#111;'> 1.34MB </span>","children":null,"spread":false},{"title":"参考文献.txt <span style='color:#111;'> 229B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]