E-MapReduce银行员工信息查询示例

段落1创建临时表

1. %spark
2. import org.apache.commons.io.IOUtils
3. import java.net.URL
4. import java.nio.charset.Charset
6. // Zeppelin creates and injects sc (SparkContext) and sqlContext (HiveContext or SqlContext)
7. // So you don't need create them manually
8. // load bank data
9. val bankText = sc.parallelize(
10.     IOUtils.toString(
11.         new URL("http://emr-sample-projects.oss-cn-hangzhou.aliyuncs.com/bank.csv"),
12.         Charset.forName("utf8")).split("\n"))
13. case class Bank(age: Integer, job: String, marital: String, education: String, balance: Integer)
14. val bank = bankText.map(s => s.split(";")).filter(s => s(0) != "\"age\"").map(
15.     s => Bank(s(0).toInt,
16.             s(1).replaceAll("\"", ""),
17.             s(2).replaceAll("\"", ""),
18.             s(3).replaceAll("\"", ""),
19.             s(5).replaceAll("\"", "").toInt
20.         )
21. ).toDF()
22. bank.registerTempTable("bank")

1. %sql
2. desc bank

1. %sql select age, count(1) value from bank where age < 30 group by age order by age

1. %sql select * from bank where age <= 20