Last active
February 20, 2020 17:40
-
-
Save ebuildy/736ddb7160b587f6405c88c556287a17 to your computer and use it in GitHub Desktop.
Flatten Apache Spark Data Frame
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
import org.apache.spark.sql.Column | |
import org.apache.spark.sql.types.StructType | |
import org.apache.spark.sql.functions.col | |
def flattenSchema(schema: StructType, prefix: String = null) : Array[Column] = { | |
schema.fields.flatMap(f => { | |
val colName = if (prefix == null) f.name else (prefix + "." + f.name) | |
f.dataType match { | |
case st: StructType => flattenSchema(st, colName) | |
case _ => Array(col(colName)) | |
} | |
}) | |
} | |
val flattenedSchema = flattenSchema(df.schema) | |
val renamedCols = flattenedSchema.map(name => col(name.toString()).as(name.toString().replace(".","_"))) | |
val flatDF = df.select(renamedCols:_*) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment