This is an automated email from the ASF dual-hosted git repository. github-merge-queue[bot] pushed a commit to branch gh-readonly-queue/main/pr-5951-e17de6fd622daa340594dd268b6d74632cfb08c8 in repository https://gitbox.apache.org/repos/asf/texera.git
commit 588a9d7831012882cc314aa3b0520973cd07ee23 Author: Xinyuan Lin <[email protected]> AuthorDate: Fri Jun 26 01:41:01 2026 -0700 test(workflow-operator): add unit test coverage for Sklearn MLP and probability-calibration descriptors (#5951) ### What changes were proposed in this PR? Pin behavior of two previously-untested Sklearn classifier descriptors (multi-layer perceptron and probability calibration) in `common/workflow-operator`. No production-code changes. This completes unit coverage of the concrete `SklearnClassifierOpDesc` classifier family. | Spec | Source class | Tests | | --- | --- | --- | | `SklearnMultiLayerPerceptronOpDescSpec` | `SklearnMultiLayerPerceptronOpDesc` | 5 | | `SklearnProbabilityCalibrationOpDescSpec` | `SklearnProbabilityCalibrationOpDesc` | 5 | **Behavior pinned** | Surface | Contract | | --- | --- | | `operatorInfo` | exact model name + `Sklearn <name> Operator` description; Sklearn group; training/testing input ports + one blocking output | | field defaults | `countVectorizer`/`tfidfTransformer` `false`; `target`/`text` `null` | | `getOutputSchemas` | `model_name` (STRING) + `model` (BINARY) keyed by the declared output port | | `generatePythonCode` | imports the matching sklearn estimator (`MLPClassifier`/`CalibratedClassifierCV`) and builds the `make_pipeline` model | | Round-trip | config fields preserved through the polymorphic `LogicalOp` base, with the correct `operatorType` discriminator | ### Any related issues, documentation, discussions? Part of the ongoing `workflow-operator` unit-test coverage effort (follow-up to the Sklearn classifier coverage in #5925, #5939, #5940, #5941, #5945, #5946). ### How was this PR tested? - `sbt "WorkflowOperator/testOnly *SklearnMultiLayerPerceptronOpDescSpec *SklearnProbabilityCalibrationOpDescSpec"` — 10 tests, all green - `sbt "WorkflowOperator/Test/scalafmtCheck"` and `sbt "WorkflowOperator/scalafixAll --check"` — clean - CI to confirm ### Was this PR authored or co-authored using generative AI tooling? Generated-by: Claude Code (Opus 4.8 [1M context]) --- .../SklearnMultiLayerPerceptronOpDescSpec.scala | 79 ++++++++++++++++++++++ .../SklearnProbabilityCalibrationOpDescSpec.scala | 79 ++++++++++++++++++++++ 2 files changed, 158 insertions(+) diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnMultiLayerPerceptronOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnMultiLayerPerceptronOpDescSpec.scala new file mode 100644 index 0000000000..592f577956 --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnMultiLayerPerceptronOpDescSpec.scala @@ -0,0 +1,79 @@ +/* + * 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.texera.amber.operator.sklearn + +import org.apache.texera.amber.core.tuple.AttributeType +import org.apache.texera.amber.operator.LogicalOp +import org.apache.texera.amber.operator.metadata.OperatorGroupConstants +import org.apache.texera.amber.util.JSONUtils.objectMapper +import org.scalatest.flatspec.AnyFlatSpec +import org.scalatest.matchers.should.Matchers + +class SklearnMultiLayerPerceptronOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnMultiLayerPerceptronOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnMultiLayerPerceptronOpDesc).operatorInfo + info.userFriendlyName shouldBe "Multi-layer Perceptron" + info.operatorDescription shouldBe "Sklearn Multi-layer Perceptron Operator" + info.operatorGroupName shouldBe OperatorGroupConstants.SKLEARN_GROUP + info.inputPorts.map(_.displayName) shouldBe List("training", "testing") + info.outputPorts should have length 1 + info.outputPorts.head.blocking shouldBe true + } + + "SklearnMultiLayerPerceptronOpDesc" should "default its config fields" in { + val d = new SklearnMultiLayerPerceptronOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnMultiLayerPerceptronOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnMultiLayerPerceptronOpDesc + val schema = d.getOutputSchemas(Map.empty)(d.operatorInfo.outputPorts.head.id) + schema.getAttribute("model_name").getType shouldBe AttributeType.STRING + schema.getAttribute("model").getType shouldBe AttributeType.BINARY + } + + "SklearnMultiLayerPerceptronOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnMultiLayerPerceptronOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.neural_network import MLPClassifier") + code should include("make_pipeline") + code should include("Multi-layer Perceptron") + } + + "SklearnMultiLayerPerceptronOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnMultiLayerPerceptronOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnMultiLayerPerceptron\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnMultiLayerPerceptronOpDesc] + val r = restored.asInstanceOf[SklearnMultiLayerPerceptronOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +} diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnProbabilityCalibrationOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnProbabilityCalibrationOpDescSpec.scala new file mode 100644 index 0000000000..2eab3102cb --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnProbabilityCalibrationOpDescSpec.scala @@ -0,0 +1,79 @@ +/* + * 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.texera.amber.operator.sklearn + +import org.apache.texera.amber.core.tuple.AttributeType +import org.apache.texera.amber.operator.LogicalOp +import org.apache.texera.amber.operator.metadata.OperatorGroupConstants +import org.apache.texera.amber.util.JSONUtils.objectMapper +import org.scalatest.flatspec.AnyFlatSpec +import org.scalatest.matchers.should.Matchers + +class SklearnProbabilityCalibrationOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnProbabilityCalibrationOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnProbabilityCalibrationOpDesc).operatorInfo + info.userFriendlyName shouldBe "Probability Calibration" + info.operatorDescription shouldBe "Sklearn Probability Calibration Operator" + info.operatorGroupName shouldBe OperatorGroupConstants.SKLEARN_GROUP + info.inputPorts.map(_.displayName) shouldBe List("training", "testing") + info.outputPorts should have length 1 + info.outputPorts.head.blocking shouldBe true + } + + "SklearnProbabilityCalibrationOpDesc" should "default its config fields" in { + val d = new SklearnProbabilityCalibrationOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnProbabilityCalibrationOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnProbabilityCalibrationOpDesc + val schema = d.getOutputSchemas(Map.empty)(d.operatorInfo.outputPorts.head.id) + schema.getAttribute("model_name").getType shouldBe AttributeType.STRING + schema.getAttribute("model").getType shouldBe AttributeType.BINARY + } + + "SklearnProbabilityCalibrationOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnProbabilityCalibrationOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.calibration import CalibratedClassifierCV") + code should include("make_pipeline") + code should include("Probability Calibration") + } + + "SklearnProbabilityCalibrationOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnProbabilityCalibrationOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnProbabilityCalibration\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnProbabilityCalibrationOpDesc] + val r = restored.asInstanceOf[SklearnProbabilityCalibrationOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +}
