Github user yanboliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/15212#discussion_r93874272
--- Diff:
mllib/src/test/scala/org/apache/spark/mllib/feature/ChiSqSelectorSuite.scala ---
@@ -27,60 +27,143 @@ class ChiSqSelectorSuite extends SparkFunSuite with
MLlibTestSparkContext {
/*
* Contingency tables
- * feature0 = {8.0, 0.0}
+ * feature0 = {6.0, 0.0, 8.0}
* class 0 1 2
- * 8.0||1|0|1|
- * 0.0||0|2|0|
+ * 6.0||1|0|0|
+ * 0.0||0|3|0|
+ * 8.0||0|0|2|
+ * degree of freedom = 4, statistic = 12, pValue = 0.017
*
* feature1 = {7.0, 9.0}
* class 0 1 2
* 7.0||1|0|0|
- * 9.0||0|2|1|
+ * 9.0||0|3|2|
+ * degree of freedom = 2, statistic = 6, pValue = 0.049
*
- * feature2 = {0.0, 6.0, 8.0, 5.0}
+ * feature2 = {0.0, 6.0, 3.0, 8.0}
* class 0 1 2
* 0.0||1|0|0|
- * 6.0||0|1|0|
+ * 6.0||0|1|2|
+ * 3.0||0|1|0|
* 8.0||0|1|0|
- * 5.0||0|0|1|
+ * degree of freedom = 6, statistic = 8.66, pValue = 0.193
+ *
+ * feature3 = {7.0, 0.0, 5.0, 4.0}
+ * class 0 1 2
+ * 7.0||1|0|0|
+ * 0.0||0|2|0|
+ * 5.0||0|1|1|
+ * 4.0||0|0|1|
+ * degree of freedom = 6, statistic = 9.5, pValue = 0.147
+ *
+ * feature4 = {6.0, 5.0, 4.0, 0.0}
+ * class 0 1 2
+ * 6.0||1|1|0|
+ * 5.0||0|2|0|
+ * 4.0||0|0|1|
+ * 0.0||0|0|1|
+ * degree of freedom = 6, statistic = 8.0, pValue = 0.238
+ *
+ * feature5 = {0.0, 9.0, 5.0, 4.0}
+ * class 0 1 2
+ * 0.0||1|0|1|
+ * 9.0||0|1|0|
+ * 5.0||0|1|0|
+ * 4.0||0|1|1|
+ * degree of freedom = 6, statistic = 5, pValue = 0.54
*
* Use chi-squared calculator from Internet
*/
- test("ChiSqSelector transform test (sparse & dense vector)") {
- val labeledDiscreteData = sc.parallelize(
- Seq(LabeledPoint(0.0, Vectors.sparse(3, Array((0, 8.0), (1, 7.0)))),
- LabeledPoint(1.0, Vectors.sparse(3, Array((1, 9.0), (2, 6.0)))),
- LabeledPoint(1.0, Vectors.dense(Array(0.0, 9.0, 8.0))),
- LabeledPoint(2.0, Vectors.dense(Array(8.0, 9.0, 5.0)))), 2)
+ lazy val labeledDiscreteData = sc.parallelize(
+ Seq(LabeledPoint(0.0, Vectors.sparse(6, Array((0, 6.0), (1, 7.0), (3,
7.0), (4, 6.0)))),
+ LabeledPoint(1.0, Vectors.sparse(6, Array((1, 9.0), (2, 6.0), (4,
5.0), (5, 9.0)))),
+ LabeledPoint(1.0, Vectors.sparse(6, Array((1, 9.0), (2, 3.0), (4,
5.0), (5, 5.0)))),
+ LabeledPoint(1.0, Vectors.dense(Array(0.0, 9.0, 8.0, 5.0, 6.0,
4.0))),
+ LabeledPoint(2.0, Vectors.dense(Array(8.0, 9.0, 6.0, 5.0, 4.0,
4.0))),
+ LabeledPoint(2.0, Vectors.dense(Array(8.0, 9.0, 6.0, 4.0, 0.0,
0.0)))), 2)
+
+ test("ChiSqSelector transform by numTopFeatures test (sparse & dense
vector)") {
+ val preFilteredData =
+ Set(LabeledPoint(0.0, Vectors.dense(Array(6.0, 7.0, 7.0))),
+ LabeledPoint(1.0, Vectors.dense(Array(0.0, 9.0, 0.0))),
+ LabeledPoint(1.0, Vectors.dense(Array(0.0, 9.0, 0.0))),
+ LabeledPoint(1.0, Vectors.dense(Array(0.0, 9.0, 5.0))),
+ LabeledPoint(2.0, Vectors.dense(Array(8.0, 9.0, 5.0))),
+ LabeledPoint(2.0, Vectors.dense(Array(8.0, 9.0, 4.0))))
+
+ val model = new ChiSqSelector(3).fit(labeledDiscreteData)
+ val filteredData = labeledDiscreteData.map { lp =>
+ LabeledPoint(lp.label, model.transform(lp.features))
+ }.collect().toSet
+ assert(filteredData === preFilteredData)
+ }
+
+ test("ChiSqSelector transform by Percentile test (sparse & dense
vector)") {
+ val preFilteredData =
+ Set(LabeledPoint(0.0, Vectors.dense(Array(6.0, 7.0, 7.0))),
+ LabeledPoint(1.0, Vectors.dense(Array(0.0, 9.0, 0.0))),
+ LabeledPoint(1.0, Vectors.dense(Array(0.0, 9.0, 0.0))),
+ LabeledPoint(1.0, Vectors.dense(Array(0.0, 9.0, 5.0))),
+ LabeledPoint(2.0, Vectors.dense(Array(8.0, 9.0, 5.0))),
+ LabeledPoint(2.0, Vectors.dense(Array(8.0, 9.0, 4.0))))
+
+ val model = new
ChiSqSelector().setSelectorType("percentile").setPercentile(0.5)
+ .fit(labeledDiscreteData)
+ val filteredData = labeledDiscreteData.map { lp =>
+ LabeledPoint(lp.label, model.transform(lp.features))
+ }.collect().toSet
+ assert(filteredData == preFilteredData)
--- End diff --
Use ```===```, see the difference at
http://stackoverflow.com/questions/10489548/what-is-the-triple-equals-operator-in-scala-koans
.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
