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-5945-abbe7a30244d6e50bc5ce7a89befcbc7a9d31c28 in repository https://gitbox.apache.org/repos/asf/texera.git
commit 0c179ce6af7129442091fdda8d76ab3dc1e08fb7 Author: Xinyuan Lin <[email protected]> AuthorDate: Thu Jun 25 09:28:56 2026 -0700 test(workflow-operator): add unit test coverage for Sklearn SVM and neighbor classifier descriptors (#5945) ### What changes were proposed in this PR? Pin behavior of four previously-untested Sklearn support-vector and neighbor classifier descriptors in `common/workflow-operator`. No production-code changes. | Spec | Source class | Tests | | --- | --- | --- | | `SklearnSVMOpDescSpec` | `SklearnSVMOpDesc` | 5 | | `SklearnLinearSVMOpDescSpec` | `SklearnLinearSVMOpDesc` | 5 | | `SklearnKNNOpDescSpec` | `SklearnKNNOpDesc` | 5 | | `SklearnNearestCentroidOpDescSpec` | `SklearnNearestCentroidOpDesc` | 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 classifier coverage in #5925, #5939, #5940, #5941). ### How was this PR tested? - `sbt "WorkflowOperator/testOnly *SklearnSVMOpDescSpec *SklearnLinearSVMOpDescSpec *SklearnKNNOpDescSpec *SklearnNearestCentroidOpDescSpec"` — 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]) --- .../operator/sklearn/SklearnKNNOpDescSpec.scala | 79 ++++++++++++++++++++++ .../sklearn/SklearnLinearSVMOpDescSpec.scala | 79 ++++++++++++++++++++++ .../sklearn/SklearnNearestCentroidOpDescSpec.scala | 79 ++++++++++++++++++++++ .../operator/sklearn/SklearnSVMOpDescSpec.scala | 79 ++++++++++++++++++++++ 4 files changed, 316 insertions(+) diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnKNNOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnKNNOpDescSpec.scala new file mode 100644 index 0000000000..57dcc06be4 --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnKNNOpDescSpec.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 SklearnKNNOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnKNNOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnKNNOpDesc).operatorInfo + info.userFriendlyName shouldBe "K-nearest Neighbors" + info.operatorDescription shouldBe "Sklearn K-nearest Neighbors 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 + } + + "SklearnKNNOpDesc" should "default its config fields" in { + val d = new SklearnKNNOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnKNNOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnKNNOpDesc + 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 + } + + "SklearnKNNOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnKNNOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.neighbors import KNeighborsClassifier") + code should include("make_pipeline") + code should include("K-nearest Neighbors") + } + + "SklearnKNNOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnKNNOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnKNN\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnKNNOpDesc] + val r = restored.asInstanceOf[SklearnKNNOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +} diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearSVMOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearSVMOpDescSpec.scala new file mode 100644 index 0000000000..d0153ae37f --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearSVMOpDescSpec.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 SklearnLinearSVMOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnLinearSVMOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnLinearSVMOpDesc).operatorInfo + info.userFriendlyName shouldBe "Linear Support Vector Machine" + info.operatorDescription shouldBe "Sklearn Linear Support Vector Machine 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 + } + + "SklearnLinearSVMOpDesc" should "default its config fields" in { + val d = new SklearnLinearSVMOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnLinearSVMOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnLinearSVMOpDesc + 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 + } + + "SklearnLinearSVMOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnLinearSVMOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.svm import LinearSVC") + code should include("make_pipeline") + code should include("Linear Support Vector Machine") + } + + "SklearnLinearSVMOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnLinearSVMOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnLinearSVM\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnLinearSVMOpDesc] + val r = restored.asInstanceOf[SklearnLinearSVMOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +} diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnNearestCentroidOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnNearestCentroidOpDescSpec.scala new file mode 100644 index 0000000000..db61804a79 --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnNearestCentroidOpDescSpec.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 SklearnNearestCentroidOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnNearestCentroidOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnNearestCentroidOpDesc).operatorInfo + info.userFriendlyName shouldBe "Nearest Centroid" + info.operatorDescription shouldBe "Sklearn Nearest Centroid 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 + } + + "SklearnNearestCentroidOpDesc" should "default its config fields" in { + val d = new SklearnNearestCentroidOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnNearestCentroidOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnNearestCentroidOpDesc + 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 + } + + "SklearnNearestCentroidOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnNearestCentroidOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.neighbors import NearestCentroid") + code should include("make_pipeline") + code should include("Nearest Centroid") + } + + "SklearnNearestCentroidOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnNearestCentroidOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnNearestCentroid\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnNearestCentroidOpDesc] + val r = restored.asInstanceOf[SklearnNearestCentroidOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +} diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnSVMOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnSVMOpDescSpec.scala new file mode 100644 index 0000000000..b1a7e9f3b0 --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnSVMOpDescSpec.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 SklearnSVMOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnSVMOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnSVMOpDesc).operatorInfo + info.userFriendlyName shouldBe "Support Vector Machine" + info.operatorDescription shouldBe "Sklearn Support Vector Machine 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 + } + + "SklearnSVMOpDesc" should "default its config fields" in { + val d = new SklearnSVMOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnSVMOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnSVMOpDesc + 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 + } + + "SklearnSVMOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnSVMOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.svm import SVC") + code should include("make_pipeline") + code should include("Support Vector Machine") + } + + "SklearnSVMOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnSVMOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnSVM\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnSVMOpDesc] + val r = restored.asInstanceOf[SklearnSVMOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +}
