Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

updated string indexer enum to match spark #93

Merged
merged 5 commits into from
Aug 27, 2018
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@ package com.salesforce.op.stages.impl.feature

import com.salesforce.op.UID
import com.salesforce.op.features.types._
import com.salesforce.op.stages.impl.feature.StringIndexerHandleInvalid.{Keep, Skip}
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think you can do import com.salesforce.op.stages.impl.feature.StringIndexerHandleInvalid._
then assert(Seq(Skip, Error, Keep).contains(value), ...)

import com.salesforce.op.stages.sparkwrappers.specific.OpEstimatorWrapper
import enumeratum._
import org.apache.spark.ml.feature.{StringIndexer, StringIndexerModel}
Expand Down Expand Up @@ -62,6 +63,8 @@ class OpStringIndexer[T <: Text]
* @return this stage
*/
def setHandleInvalid(value: StringIndexerHandleInvalid): this.type = {
assert(Seq(StringIndexerHandleInvalid.Skip, StringIndexerHandleInvalid.Error, StringIndexerHandleInvalid.Keep)
.contains(value), "OpStringIndexer only supports Skip, Error, and Keep for handle invalid")
getSparkMlStage().get.setHandleInvalid(value.entryName.toLowerCase)
this
}
Expand All @@ -73,5 +76,6 @@ object StringIndexerHandleInvalid extends Enum[StringIndexerHandleInvalid] {
val values = findValues
case object Skip extends StringIndexerHandleInvalid
case object Error extends StringIndexerHandleInvalid
case object Keep extends StringIndexerHandleInvalid
case object NoFilter extends StringIndexerHandleInvalid
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,57 @@
/*
* Copyright (c) 2017, Salesforce.com, Inc.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer.
*
* * Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* * Neither the name of the copyright holder nor the names of its
* contributors may be used to endorse or promote products derived from
* this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
package com.salesforce.op.stages.impl.feature

import com.salesforce.op.features.types.Text
import com.salesforce.op.test.TestSparkContext
import org.apache.spark.ml.feature.StringIndexer
import org.junit.runner.RunWith
import org.scalatest.FlatSpec
import org.scalatest.junit.JUnitRunner

@RunWith(classOf[JUnitRunner])
class OpStringIndexerTest extends FlatSpec with TestSparkContext{

Spec[OpStringIndexer[_]] should "correctly set the wrapped spark stage params" in {
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

please move OpStringIndexer test portion from OpStringIndexerNoFilterTest to here as well

val indexer = new OpStringIndexer[Text]()
indexer.setHandleInvalid(StringIndexerHandleInvalid.Skip)
indexer.getSparkMlStage().get.getHandleInvalid shouldBe StringIndexerHandleInvalid.Skip.entryName.toLowerCase
indexer.setHandleInvalid(StringIndexerHandleInvalid.Error)
indexer.getSparkMlStage().get.getHandleInvalid shouldBe StringIndexerHandleInvalid.Error.entryName.toLowerCase
indexer.setHandleInvalid(StringIndexerHandleInvalid.Keep)
indexer.getSparkMlStage().get.getHandleInvalid shouldBe StringIndexerHandleInvalid.Keep.entryName.toLowerCase
}

it should "throw an error if you try to set noFilter as the indexer" in {
val indexer = new OpStringIndexer[Text]()
intercept[AssertionError](indexer.setHandleInvalid(StringIndexerHandleInvalid.NoFilter))
}

}