CODEWITHSUNDEEP
scalaapache-spark
navicore
navicore

Reputation: 2109

filter spark dataframe with row field that is an array of strings

Using Spark 1.5 and Scala 2.10.6

I'm trying to filter a dataframe via a field "tags" that is an array of strings. Looking for all rows that have the tag 'private'.

val report = df.select("*")
  .where(df("tags").contains("private"))

getting:

Exception in thread "main" org.apache.spark.sql.AnalysisException: cannot resolve 'Contains(tags, private)' due to data type mismatch: argument 1 requires string type, however, 'tags' is of array type.;

Is the filter method better suited?

UPDATED:

the data is coming from cassandra adapter but a minimal example that shows what I'm trying to do and also gets the above error is:

  def testData (sc: SparkContext): DataFrame = {
    val stringRDD = sc.parallelize(Seq("""
      { "name": "ed",
        "tags": ["red", "private"]
      }""",
      """{ "name": "fred",
        "tags": ["public", "blue"]
      }""")
    )
    val sqlContext = new org.apache.spark.sql.SQLContext(sc)
    import sqlContext.implicits._
    sqlContext.read.json(stringRDD)
  }
  def run(sc: SparkContext) {
    val df1 = testData(sc)
    df1.show()
    val report = df1.select("*")
      .where(df1("tags").contains("private"))
    report.show()
  }

UPDATED: the tags array can be any length and the 'private' tag can be in any position

UPDATED: one solution that works: UDF

val filterPriv = udf {(tags: mutable.WrappedArray[String]) => tags.contains("private")}
val report = df1.filter(filterPriv(df1("tags")))

Upvotes: 19

Views: 46816

Answers (2)

Robert Dodier
Robert Dodier

Reputation: 17576

I think if you use where(array_contains(...)) it will work. Here's my result:

scala> import org.apache.spark.SparkContext
import org.apache.spark.SparkContext

scala> import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.DataFrame

scala> def testData (sc: SparkContext): DataFrame = {
     |     val stringRDD = sc.parallelize(Seq
     |      ("""{ "name": "ned", "tags": ["blue", "big", "private"] }""",
     |       """{ "name": "albert", "tags": ["private", "lumpy"] }""",
     |       """{ "name": "zed", "tags": ["big", "private", "square"] }""",
     |       """{ "name": "jed", "tags": ["green", "small", "round"] }""",
     |       """{ "name": "ed", "tags": ["red", "private"] }""",
     |       """{ "name": "fred", "tags": ["public", "blue"] }"""))
     |     val sqlContext = new org.apache.spark.sql.SQLContext(sc)
     |     import sqlContext.implicits._
     |     sqlContext.read.json(stringRDD)
     |   }
testData: (sc: org.apache.spark.SparkContext)org.apache.spark.sql.DataFrame

scala>   
     | val df = testData (sc)
df: org.apache.spark.sql.DataFrame = [name: string, tags: array<string>]

scala> val report = df.select ("*").where (array_contains (df("tags"), "private"))
report: org.apache.spark.sql.DataFrame = [name: string, tags: array<string>]

scala> report.show
+------+--------------------+
|  name|                tags|
+------+--------------------+
|   ned|[blue, big, private]|
|albert|    [private, lumpy]|
|   zed|[big, private, sq...|
|    ed|      [red, private]|
+------+--------------------+

Note that it works if you write where(array_contains(df("tags"), "private")), but if you write where(df("tags").array_contains("private")) (more directly analogous to what you wrote originally) it fails with array_contains is not a member of org.apache.spark.sql.Column. Looking at the source code for Column, I see there's some stuff to handle contains (constructing a Contains instance for that) but not array_contains. Maybe that's an oversight.

Upvotes: 32

Aravind Yarram
Aravind Yarram

Reputation: 80186

You can use ordinal to refer to the json array's for e.g. in your case df("tags")(0). Here is a working sample

scala> val stringRDD = sc.parallelize(Seq("""
     |       { "name": "ed",
     |         "tags": ["private"]
     |       }""",
     |       """{ "name": "fred",
     |         "tags": ["public"]
     |       }""")
     |     )
stringRDD: org.apache.spark.rdd.RDD[String] = ParallelCollectionRDD[87] at parallelize at <console>:22

scala> import sqlContext.implicits._
import sqlContext.implicits._

scala> sqlContext.read.json(stringRDD)
res28: org.apache.spark.sql.DataFrame = [name: string, tags: array<string>]

scala> val df=sqlContext.read.json(stringRDD)
df: org.apache.spark.sql.DataFrame = [name: string, tags: array<string>]

scala> df.columns
res29: Array[String] = Array(name, tags)

scala> df.dtypes
res30: Array[(String, String)] = Array((name,StringType), (tags,ArrayType(StringType,true)))

scala> val report = df.select("*").where(df("tags")(0).contains("private"))
report: org.apache.spark.sql.DataFrame = [name: string, tags: array<string>]

scala> report.show
+----+-------------+
|name|         tags|
+----+-------------+
|  ed|List(private)|
+----+-------------+

Upvotes: 1

Related Questions