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-5939-2779df91c44418eed60ec257f5f7b77653a8552c in repository https://gitbox.apache.org/repos/asf/texera.git
commit abbe7a30244d6e50bc5ce7a89befcbc7a9d31c28 Author: Xinyuan Lin <[email protected]> AuthorDate: Thu Jun 25 00:19:56 2026 -0700 test(workflow-operator): add unit test coverage for Sklearn tree-based classifier descriptors (#5939) ### What changes were proposed in this PR? Pin behavior of four previously-untested Sklearn tree-based classifier descriptors in `common/workflow-operator`. No production-code changes. | Spec | Source class | Tests | | --- | --- | --- | | `SklearnDecisionTreeOpDescSpec` | `SklearnDecisionTreeOpDesc` | 5 | | `SklearnExtraTreeOpDescSpec` | `SklearnExtraTreeOpDesc` | 5 | | `SklearnExtraTreesOpDescSpec` | `SklearnExtraTreesOpDesc` | 5 | | `SklearnRandomForestOpDescSpec` | `SklearnRandomForestOpDesc` | 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 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 Naive Bayes coverage in #5925). ### How was this PR tested? - `sbt "WorkflowOperator/testOnly *SklearnDecisionTreeOpDescSpec *SklearnExtraTreeOpDescSpec *SklearnExtraTreesOpDescSpec *SklearnRandomForestOpDescSpec"` — 20 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]) --- .../sklearn/SklearnDecisionTreeOpDescSpec.scala | 79 ++++++++++++++++++++++ .../sklearn/SklearnExtraTreeOpDescSpec.scala | 79 ++++++++++++++++++++++ .../sklearn/SklearnExtraTreesOpDescSpec.scala | 79 ++++++++++++++++++++++ .../sklearn/SklearnRandomForestOpDescSpec.scala | 79 ++++++++++++++++++++++ 4 files changed, 316 insertions(+) diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnDecisionTreeOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnDecisionTreeOpDescSpec.scala new file mode 100644 index 0000000000..44fbf1aeed --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnDecisionTreeOpDescSpec.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 SklearnDecisionTreeOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnDecisionTreeOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnDecisionTreeOpDesc).operatorInfo + info.userFriendlyName shouldBe "Decision Tree" + info.operatorDescription shouldBe "Sklearn Decision Tree 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 + } + + "SklearnDecisionTreeOpDesc" should "default its config fields" in { + val d = new SklearnDecisionTreeOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnDecisionTreeOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnDecisionTreeOpDesc + 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 + } + + "SklearnDecisionTreeOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnDecisionTreeOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.tree import DecisionTreeClassifier") + code should include("make_pipeline") + code should include("Decision Tree") + } + + "SklearnDecisionTreeOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnDecisionTreeOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnDecisionTree\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnDecisionTreeOpDesc] + val r = restored.asInstanceOf[SklearnDecisionTreeOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +} diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnExtraTreeOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnExtraTreeOpDescSpec.scala new file mode 100644 index 0000000000..96b9ec470b --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnExtraTreeOpDescSpec.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 SklearnExtraTreeOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnExtraTreeOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnExtraTreeOpDesc).operatorInfo + info.userFriendlyName shouldBe "Extra Tree" + info.operatorDescription shouldBe "Sklearn Extra Tree 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 + } + + "SklearnExtraTreeOpDesc" should "default its config fields" in { + val d = new SklearnExtraTreeOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnExtraTreeOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnExtraTreeOpDesc + 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 + } + + "SklearnExtraTreeOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnExtraTreeOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.tree import ExtraTreeClassifier") + code should include("make_pipeline") + code should include("Extra Tree") + } + + "SklearnExtraTreeOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnExtraTreeOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnExtraTree\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnExtraTreeOpDesc] + val r = restored.asInstanceOf[SklearnExtraTreeOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +} diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnExtraTreesOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnExtraTreesOpDescSpec.scala new file mode 100644 index 0000000000..332bee1ee3 --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnExtraTreesOpDescSpec.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 SklearnExtraTreesOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnExtraTreesOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnExtraTreesOpDesc).operatorInfo + info.userFriendlyName shouldBe "Extra Trees" + info.operatorDescription shouldBe "Sklearn Extra Trees 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 + } + + "SklearnExtraTreesOpDesc" should "default its config fields" in { + val d = new SklearnExtraTreesOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnExtraTreesOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnExtraTreesOpDesc + 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 + } + + "SklearnExtraTreesOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnExtraTreesOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.ensemble import ExtraTreesClassifier") + code should include("make_pipeline") + code should include("Extra Trees") + } + + "SklearnExtraTreesOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnExtraTreesOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnExtraTrees\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnExtraTreesOpDesc] + val r = restored.asInstanceOf[SklearnExtraTreesOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +} diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnRandomForestOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnRandomForestOpDescSpec.scala new file mode 100644 index 0000000000..2f19aff0ad --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnRandomForestOpDescSpec.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 SklearnRandomForestOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnRandomForestOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnRandomForestOpDesc).operatorInfo + info.userFriendlyName shouldBe "Random Forest" + info.operatorDescription shouldBe "Sklearn Random Forest 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 + } + + "SklearnRandomForestOpDesc" should "default its config fields" in { + val d = new SklearnRandomForestOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnRandomForestOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnRandomForestOpDesc + 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 + } + + "SklearnRandomForestOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnRandomForestOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.ensemble import RandomForestClassifier") + code should include("make_pipeline") + code should include("Random Forest") + } + + "SklearnRandomForestOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnRandomForestOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnRandomForest\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnRandomForestOpDesc] + val r = restored.asInstanceOf[SklearnRandomForestOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +}
