This is an automated email from the ASF dual-hosted git repository. github-merge-queue[bot] pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/texera.git
commit 2779df91c44418eed60ec257f5f7b77653a8552c Author: Xinyuan Lin <[email protected]> AuthorDate: Thu Jun 25 00:19:44 2026 -0700 test(workflow-operator): add unit test coverage for Sklearn linear classifier descriptors (#5941) ### What changes were proposed in this PR? Pin behavior of four previously-untested Sklearn linear classifier descriptors in `common/workflow-operator`. No production-code changes. | Spec | Source class | Tests | | --- | --- | --- | | `SklearnLogisticRegressionOpDescSpec` | `SklearnLogisticRegressionOpDesc` | 5 | | `SklearnLogisticRegressionCVOpDescSpec` | `SklearnLogisticRegressionCVOpDesc` | 5 | | `SklearnPerceptronOpDescSpec` | `SklearnPerceptronOpDesc` | 5 | | `SklearnPassiveAggressiveOpDescSpec` | `SklearnPassiveAggressiveOpDesc` | 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 *SklearnLogisticRegressionOpDescSpec *SklearnLogisticRegressionCVOpDescSpec *SklearnPerceptronOpDescSpec *SklearnPassiveAggressiveOpDescSpec"` — 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]) --- .../SklearnLogisticRegressionCVOpDescSpec.scala | 79 ++++++++++++++++++++++ .../SklearnLogisticRegressionOpDescSpec.scala | 79 ++++++++++++++++++++++ .../SklearnPassiveAggressiveOpDescSpec.scala | 79 ++++++++++++++++++++++ .../sklearn/SklearnPerceptronOpDescSpec.scala | 79 ++++++++++++++++++++++ 4 files changed, 316 insertions(+) diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLogisticRegressionCVOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLogisticRegressionCVOpDescSpec.scala new file mode 100644 index 0000000000..24589453ed --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLogisticRegressionCVOpDescSpec.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 SklearnLogisticRegressionCVOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnLogisticRegressionCVOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnLogisticRegressionCVOpDesc).operatorInfo + info.userFriendlyName shouldBe "Logistic Regression Cross Validation" + info.operatorDescription shouldBe "Sklearn Logistic Regression Cross Validation 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 + } + + "SklearnLogisticRegressionCVOpDesc" should "default its config fields" in { + val d = new SklearnLogisticRegressionCVOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnLogisticRegressionCVOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnLogisticRegressionCVOpDesc + 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 + } + + "SklearnLogisticRegressionCVOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnLogisticRegressionCVOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.linear_model import LogisticRegressionCV") + code should include("make_pipeline") + code should include("Logistic Regression Cross Validation") + } + + "SklearnLogisticRegressionCVOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnLogisticRegressionCVOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnLogisticRegressionCV\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnLogisticRegressionCVOpDesc] + val r = restored.asInstanceOf[SklearnLogisticRegressionCVOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +} diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLogisticRegressionOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLogisticRegressionOpDescSpec.scala new file mode 100644 index 0000000000..077ecb9ac4 --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLogisticRegressionOpDescSpec.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 SklearnLogisticRegressionOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnLogisticRegressionOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnLogisticRegressionOpDesc).operatorInfo + info.userFriendlyName shouldBe "Logistic Regression" + info.operatorDescription shouldBe "Sklearn Logistic Regression 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 + } + + "SklearnLogisticRegressionOpDesc" should "default its config fields" in { + val d = new SklearnLogisticRegressionOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnLogisticRegressionOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnLogisticRegressionOpDesc + 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 + } + + "SklearnLogisticRegressionOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnLogisticRegressionOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.linear_model import LogisticRegression") + code should include("make_pipeline") + code should include("Logistic Regression") + } + + "SklearnLogisticRegressionOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnLogisticRegressionOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnLogisticRegression\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnLogisticRegressionOpDesc] + val r = restored.asInstanceOf[SklearnLogisticRegressionOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +} diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnPassiveAggressiveOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnPassiveAggressiveOpDescSpec.scala new file mode 100644 index 0000000000..d184eb4367 --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnPassiveAggressiveOpDescSpec.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 SklearnPassiveAggressiveOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnPassiveAggressiveOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnPassiveAggressiveOpDesc).operatorInfo + info.userFriendlyName shouldBe "Passive Aggressive" + info.operatorDescription shouldBe "Sklearn Passive Aggressive 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 + } + + "SklearnPassiveAggressiveOpDesc" should "default its config fields" in { + val d = new SklearnPassiveAggressiveOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnPassiveAggressiveOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnPassiveAggressiveOpDesc + 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 + } + + "SklearnPassiveAggressiveOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnPassiveAggressiveOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.linear_model import PassiveAggressiveClassifier") + code should include("make_pipeline") + code should include("Passive Aggressive") + } + + "SklearnPassiveAggressiveOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnPassiveAggressiveOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnPassiveAggressive\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnPassiveAggressiveOpDesc] + val r = restored.asInstanceOf[SklearnPassiveAggressiveOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +} diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnPerceptronOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnPerceptronOpDescSpec.scala new file mode 100644 index 0000000000..b28a57c582 --- /dev/null +++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnPerceptronOpDescSpec.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 SklearnPerceptronOpDescSpec extends AnyFlatSpec with Matchers { + + "SklearnPerceptronOpDesc.operatorInfo" should + "advertise the model name, Sklearn group, and the training/testing port shape" in { + val info = (new SklearnPerceptronOpDesc).operatorInfo + info.userFriendlyName shouldBe "Linear Perceptron" + info.operatorDescription shouldBe "Sklearn Linear 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 + } + + "SklearnPerceptronOpDesc" should "default its config fields" in { + val d = new SklearnPerceptronOpDesc + d.countVectorizer shouldBe false + d.tfidfTransformer shouldBe false + d.target shouldBe null + d.text shouldBe null + } + + "SklearnPerceptronOpDesc.getOutputSchemas" should + "emit the model_name/model schema keyed by the declared output port" in { + val d = new SklearnPerceptronOpDesc + 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 + } + + "SklearnPerceptronOpDesc.generatePythonCode" should "import the configured sklearn estimator" in { + val d = new SklearnPerceptronOpDesc + d.target = "y" + val code = d.generatePythonCode() + code should include("from sklearn.linear_model import Perceptron") + code should include("make_pipeline") + code should include("Linear Perceptron") + } + + "SklearnPerceptronOpDesc" should "round-trip its config fields through the polymorphic base" in { + val d = new SklearnPerceptronOpDesc + d.target = "label" + d.countVectorizer = true + val json = objectMapper.writeValueAsString(d) + json should include("\"operatorType\":\"SklearnPerceptron\"") + val restored = objectMapper.readValue(json, classOf[LogicalOp]) + restored shouldBe a[SklearnPerceptronOpDesc] + val r = restored.asInstanceOf[SklearnPerceptronOpDesc] + r.target shouldBe "label" + r.countVectorizer shouldBe true + } +}
