多了不说 少了不唠 直接上代码
import org.apache.spark.sql.{DataFrame, SQLContext}
import org.apache.spark.{SparkConf, SparkContext}
/**
* Created by ll on 2018/5/17.
*/
object SparkReadFileCsv {
def main(args: Array[String]) {
val localpath="F:\\1.csv"
val conf = new SparkConf()
conf.setAppName("SparkReadFile")
conf.setMaster("local")
val sparkContext = new SparkContext(conf)
val sqlContext = new SQLContext(sparkContext)
//读csv文件
val data: DataFrame = sqlContext.read.format("com.databricks.spark.csv")
.option("header", "true") //在csv第一行有属性"true",没有就是"false"
.option("inferSchema", true.toString) //这是自动推断属性列的数据类型
.load(localpath)
data.show()
}
}
pom.xml
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.10</artifactId>
<version>1.6.1</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.10</artifactId>
<version>1.6.1</version>
</dependency>
<dependency>
<groupId>com.databricks</groupId>
<artifactId>spark-csv_2.10</artifactId>
<version>1.4.0</version>
<scope>compile</scope>
</dependency>
</dependencies>