读取数据只读取一行,在没有表头的情况下,读取不到文件的属性(string,age)
1:最基本的在表头写入属性
id,name,age,province,score
1,张飞,21,北京,80.0
2,关羽,23,北京,82.0
3,赵云,20,上海,88.6
4,刘备,26,上海,83.0
5,曹操,30,深圳,90.0
val spark = SparkSession.builder().appName(this.getClass.getSimpleName).master("local[*]").getOrCreate()
//option("header" ,true)读取第一行数据
//.option("inferSchema",true推断类型
val df = spark.read.option("header" ,true).option("inferSchema",true).csv("bigdata\\user.txt")
df.printSchema()
df.show()
spark.stop()
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.types.{DoubleType, IntegerType, StringType, StructField, StructType}
object CreateDataFrameFromCSV {
def main(args: Array[String]): Unit = {
val spark = SparkSession.builder().appName(this.getClass.getSimpleName).master("local[*]").getOrCreate()
val schema: StructType