forked from apache/spark
-
Notifications
You must be signed in to change notification settings - Fork 0
/
DataFrameStatSuite.scala
63 lines (52 loc) · 2.28 KB
/
DataFrameStatSuite.scala
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
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.sql
import org.scalatest.FunSuite
import org.scalatest.Matchers._
import org.apache.spark.sql.test.TestSQLContext
import org.apache.spark.sql.test.TestSQLContext.implicits._
class DataFrameStatSuite extends FunSuite {
import TestData._
val sqlCtx = TestSQLContext
def toLetter(i: Int): String = (i + 97).toChar.toString
test("Frequent Items") {
val rows = Array.tabulate(1000) { i =>
if (i % 3 == 0) (1, toLetter(1), -1.0) else (i, toLetter(i), i * -1.0)
}
val df = sqlCtx.sparkContext.parallelize(rows).toDF("numbers", "letters", "negDoubles")
val results = df.stat.freqItems(Array("numbers", "letters"), 0.1)
val items = results.collect().head
items.getSeq[Int](0) should contain (1)
items.getSeq[String](1) should contain (toLetter(1))
val singleColResults = df.stat.freqItems(Array("negDoubles"), 0.1)
val items2 = singleColResults.collect().head
items2.getSeq[Double](0) should contain (-1.0)
}
test("covariance") {
val rows = Array.tabulate(10)(i => (i, 2.0 * i, toLetter(i)))
val df = sqlCtx.sparkContext.parallelize(rows).toDF("singles", "doubles", "letters")
df.show()
val results = df.stat.cov("singles", "doubles")
println(results)
assert(math.abs(results - 16.5) < 1e-6)
intercept[IllegalArgumentException] {
df.stat.cov("singles", "letters") // doesn't accept non-numerical dataTypes
}
val decimalRes = decimalData.stat.cov("a", "b")
assert(math.abs(decimalRes) < 1e-6)
}
}