How to create a DataFrame from a text file in Spark

Question

I have a text file on HDFS and I want to convert it to a Data Frame in Spark.

I am using the Spark Context to load the file and then try to generate individual columns f

Answer 1

I have given different ways to create DataFrame from text file

val conf = new SparkConf().setAppName(appName).setMaster("local")
val sc = SparkContext(conf)

raw text file

val file = sc.textFile("C:\\vikas\\spark\\Interview\\text.txt")
val fileToDf = file.map(_.split(",")).map{case Array(a,b,c) => 
(a,b.toInt,c)}.toDF("name","age","city")
fileToDf.foreach(println(_))

spark session without schema

import org.apache.spark.sql.SparkSession
val sparkSess = 
SparkSession.builder().appName("SparkSessionZipsExample")
.config(conf).getOrCreate()

val df = sparkSess.read.option("header", 
"false").csv("C:\\vikas\\spark\\Interview\\text.txt")
df.show()

spark session with schema

import org.apache.spark.sql.types._
val schemaString = "name age city"
val fields = schemaString.split(" ").map(fieldName => StructField(fieldName, 
StringType, nullable=true))
val schema = StructType(fields)

val dfWithSchema = sparkSess.read.option("header", 
"false").schema(schema).csv("C:\\vikas\\spark\\Interview\\text.txt")
dfWithSchema.show()

using sql context

import org.apache.spark.sql.SQLContext

val fileRdd = 
sc.textFile("C:\\vikas\\spark\\Interview\\text.txt").map(_.split(",")).map{x 
=> org.apache.spark.sql.Row(x:_*)}
val sqlDf = sqlCtx.createDataFrame(fileRdd,schema)
sqlDf.show()