Created
February 19, 2018 03:45
-
-
Save Arnold1/9ca288ebe38ad3c99b49a4b1b3095bdc to your computer and use it in GitHub Desktop.
copy schema from one dataframe to another dataframe
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// reference: https://stackoverflow.com/questions/36795680/copy-schema-from-one-dataframe-to-another-dataframe?rq=1 | |
case class Person(Dummy: String, Name: String, Timestamp: String, Age: Int) | |
val personDF = spark.sparkContext.parallelize(Seq(Person("dummy", "Ray", "12345", 23), Person("dummy", "John", "12345", 44))).toDF() | |
val personSchema = StructType( | |
Seq(StructField("Name", StringType, true), | |
StructField("Age", IntegerType, true))) | |
var dataRDD = spark.sparkContext.emptyRDD[Row] | |
val perschonDFSchema = spark.createDataFrame(dataRDD, personSchema) | |
val exprs = perschonDFSchema.schema.fields.map { f => | |
if (personDF.schema.fields.contains(f)) col(f.name) | |
else lit(null).cast(f.dataType).alias(f.name) | |
} | |
val finalDF = personDF.select(exprs: _*) | |
finalDF.show(false) | |
finalDF.printSchema |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment