Spark dataframe filter

Question

val df = sc.parallelize(Seq((1,\"Emailab\"), (2,\"Phoneab\"), (3, \"Faxab\"),(4,\"Mail\"),(5,\"Other\"),(6,\"MSL12\"),(7,\"MSL\"),(8,\"HCP\"),(9,\"HCP12\"))).toDF(\"c1\"         


        

Answer 1

df.filter(not(
    substring(col("c2"), 0, 3).isin("MSL", "HCP"))
    )