读取CSV文件创建dataFrame的写法:
val df1 = spark.read
.format("csv")
.option("header","true")
.option("inferSchema","true")
.load("src/test/resource/1.csv")
完整写法:
import org.apache.spark.{SparkConf,SparkContext}
import org.apache.spark.sql.SparkSession
object readDataFrame {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setMaster("local").setAppName("readDataFrame")
val sc = new SparkContext(conf)
val spark = SparkSession.builder().appName("readDF").getOrCreate()
val df = spark.read.format("csv").option("header",true).load("src/test/resource/1.csv")
df.printSchema()
df.show()
}
}