Skip to content

Instantly share code, notes, and snippets.

@dondrake
Last active May 18, 2016 03:27
Show Gist options
  • Save dondrake/90b7e3ae93844ab72aca443a1d33bcf1 to your computer and use it in GitHub Desktop.
Save dondrake/90b7e3ae93844ab72aca443a1d33bcf1 to your computer and use it in GitHub Desktop.
import org.apache.spark.sql.Row
import org.apache.spark.sql.types.{StructType,StructField,StringType,IntegerType}
import sqlContext.implicits._
val r1 = Row(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 270, 271, 272, 273, 274, 275, 276, 277, 278, 279, 280, 281, 282, 283, 284, 285, 286, 287, 288, 289, 290, 291, 292, 293, 294, 295, 296, 297, 298, 299)
val r2 = Row(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 270, 271, 272, 273, 274, 275, 276, 277, 278, 279, 280, 281, 282, 283, 284, 285, 286, 287, 288, 289, 290, 291, 292, 293, 294, 295, 296, 297, 298, 299)
val schemaString = """_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, _14, _15, _16, _17, _18, _19, _20, _21, _22, _23, _24, _25, _26, _27, _28, _29, _30, _31, _32, _33, _34, _35, _36, _37, _38, _39, _40, _41, _42, _43, _44, _45, _46, _47, _48, _49, _50, _51, _52, _53, _54, _55, _56, _57, _58, _59, _60, _61, _62, _63, _64, _65, _66, _67, _68, _69, _70, _71, _72, _73, _74, _75, _76, _77, _78, _79, _80, _81, _82, _83, _84, _85, _86, _87, _88, _89, _90, _91, _92, _93, _94, _95, _96, _97, _98, _99, _100, _101, _102, _103, _104, _105, _106, _107, _108, _109, _110, _111, _112, _113, _114, _115, _116, _117, _118, _119, _120, _121, _122, _123, _124, _125, _126, _127, _128, _129, _130, _131, _132, _133, _134, _135, _136, _137, _138, _139, _140, _141, _142, _143, _144, _145, _146, _147, _148, _149, _150, _151, _152, _153, _154, _155, _156, _157, _158, _159, _160, _161, _162, _163, _164, _165, _166, _167, _168, _169, _170, _171, _172, _173, _174, _175, _176, _177, _178, _179, _180, _181, _182, _183, _184, _185, _186, _187, _188, _189, _190, _191, _192, _193, _194, _195, _196, _197, _198, _199, _200, _201, _202, _203, _204, _205, _206, _207, _208, _209, _210, _211, _212, _213, _214, _215, _216, _217, _218, _219, _220, _221, _222, _223, _224, _225, _226, _227, _228, _229, _230, _231, _232, _233, _234, _235, _236, _237, _238, _239, _240, _241, _242, _243, _244, _245, _246, _247, _248, _249, _250, _251, _252, _253, _254, _255, _256, _257, _258, _259, _260, _261, _262, _263, _264, _265, _266, _267, _268, _269, _270, _271, _272, _273, _274, _275, _276, _277, _278, _279, _280, _281, _282, _283, _284, _285, _286, _287, _288, _289, _290, _291, _292, _293, _294, _295, _296, _297, _298, _299"""
val schema = StructType(schemaString.split(", ").map(fieldName => StructField(fieldName, IntegerType, true)))
val rdd = sc.parallelize(Seq(r1, r2))
// df now has 300 columns and 2 rows
val df = sqlContext.createDataFrame(rdd, schema)
// subset #1 first 20 fields
case class Subset1(_0:String, _1:String, _2:String, _3:String, _4:String, _5:String, _6:String, _7:String, _8:String, _9:String, _10:String, _11:String, _12:String, _13:String, _14:String, _15:String, _16:String, _17:String, _18:String, _19:String)
case class NestedSubset1(_0:String, rows:Seq[Subset1])
val ds = df.as[Subset1]
// works
val newdf = ds.groupBy($"_0").mapGroups( (k, vals) => {
val rows = vals.toSeq
val first = rows(0)
NestedSubset1(first._0, rows)
}).toDF
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment