test(workflow-operator): add unit test coverage for Sklearn training ensemble & linear descriptors

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingAdaptiveBoostingOpDescSpec.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.training
+
+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 SklearnTrainingAdaptiveBoostingOpDescSpec extends AnyFlatSpec with Matchers {
+
+  "SklearnTrainingAdaptiveBoostingOpDesc.operatorInfo" should
+    "advertise the model name, Sklearn Training group, and the single training port" in {
+    val info = (new SklearnTrainingAdaptiveBoostingOpDesc).operatorInfo
+    info.userFriendlyName shouldBe "Training: Adaptive Boosting"
+    info.operatorDescription shouldBe "Sklearn Training: Adaptive Boosting Operator"
+    info.operatorGroupName shouldBe OperatorGroupConstants.SKLEARN_TRAINING_GROUP
+    info.inputPorts.map(_.displayName) shouldBe List("training")
+    info.outputPorts should have length 1
+    info.outputPorts.head.blocking shouldBe true
+  }
+
+  "SklearnTrainingAdaptiveBoostingOpDesc" should "default its config fields" in {
+    val d = new SklearnTrainingAdaptiveBoostingOpDesc
+    d.countVectorizer shouldBe false
+    d.tfidfTransformer shouldBe false
+    d.target shouldBe null
+    d.text shouldBe null
+  }
+
+  "SklearnTrainingAdaptiveBoostingOpDesc.getOutputSchemas" should
+    "emit the model_name/model schema keyed by the declared output port" in {
+    val d = new SklearnTrainingAdaptiveBoostingOpDesc
+    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
+  }
+
+  "SklearnTrainingAdaptiveBoostingOpDesc.generatePythonCode" should "import the configured sklearn estimator" in {
+    val d = new SklearnTrainingAdaptiveBoostingOpDesc
+    d.target = "y"
+    val code = d.generatePythonCode()
+    code should include("from sklearn.ensemble import AdaBoostClassifier")
+    code should include("make_pipeline")
+    code should include("Training: Adaptive Boosting")
+  }
+
+  "SklearnTrainingAdaptiveBoostingOpDesc" should "round-trip its config fields through the polymorphic base" in {
+    val d = new SklearnTrainingAdaptiveBoostingOpDesc
+    d.target = "label"
+    d.countVectorizer = true
+    val json = objectMapper.writeValueAsString(d)
+    json should include("\"operatorType\":\"SklearnTrainingAdaptiveBoosting\"")
+    val restored = objectMapper.readValue(json, classOf[LogicalOp])
+    restored shouldBe a[SklearnTrainingAdaptiveBoostingOpDesc]
+    val r = restored.asInstanceOf[SklearnTrainingAdaptiveBoostingOpDesc]
+    r.target shouldBe "label"
+    r.countVectorizer shouldBe true
+  }
+}

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingBaggingOpDescSpec.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.training
+
+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 SklearnTrainingBaggingOpDescSpec extends AnyFlatSpec with Matchers {
+
+  "SklearnTrainingBaggingOpDesc.operatorInfo" should
+    "advertise the model name, Sklearn Training group, and the single training port" in {
+    val info = (new SklearnTrainingBaggingOpDesc).operatorInfo
+    info.userFriendlyName shouldBe "Training: Bagging"
+    info.operatorDescription shouldBe "Sklearn Training: Bagging Operator"
+    info.operatorGroupName shouldBe OperatorGroupConstants.SKLEARN_TRAINING_GROUP
+    info.inputPorts.map(_.displayName) shouldBe List("training")
+    info.outputPorts should have length 1
+    info.outputPorts.head.blocking shouldBe true
+  }
+
+  "SklearnTrainingBaggingOpDesc" should "default its config fields" in {
+    val d = new SklearnTrainingBaggingOpDesc
+    d.countVectorizer shouldBe false
+    d.tfidfTransformer shouldBe false
+    d.target shouldBe null
+    d.text shouldBe null
+  }
+
+  "SklearnTrainingBaggingOpDesc.getOutputSchemas" should
+    "emit the model_name/model schema keyed by the declared output port" in {
+    val d = new SklearnTrainingBaggingOpDesc
+    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
+  }
+
+  "SklearnTrainingBaggingOpDesc.generatePythonCode" should "import the configured sklearn estimator" in {
+    val d = new SklearnTrainingBaggingOpDesc
+    d.target = "y"
+    val code = d.generatePythonCode()
+    code should include("from sklearn.ensemble import BaggingClassifier")
+    code should include("make_pipeline")
+    code should include("Training: Bagging")
+  }
+
+  "SklearnTrainingBaggingOpDesc" should "round-trip its config fields through the polymorphic base" in {
+    val d = new SklearnTrainingBaggingOpDesc
+    d.target = "label"
+    d.countVectorizer = true
+    val json = objectMapper.writeValueAsString(d)
+    json should include("\"operatorType\":\"SklearnTrainingBagging\"")
+    val restored = objectMapper.readValue(json, classOf[LogicalOp])
+    restored shouldBe a[SklearnTrainingBaggingOpDesc]
+    val r = restored.asInstanceOf[SklearnTrainingBaggingOpDesc]
+    r.target shouldBe "label"
+    r.countVectorizer shouldBe true
+  }
+}

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingGradientBoostingOpDescSpec.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.training
+
+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 SklearnTrainingGradientBoostingOpDescSpec extends AnyFlatSpec with Matchers {
+
+  "SklearnTrainingGradientBoostingOpDesc.operatorInfo" should
+    "advertise the model name, Sklearn Training group, and the single training port" in {
+    val info = (new SklearnTrainingGradientBoostingOpDesc).operatorInfo
+    info.userFriendlyName shouldBe "Training: Gradient Boosting"
+    info.operatorDescription shouldBe "Sklearn Training: Gradient Boosting Operator"
+    info.operatorGroupName shouldBe OperatorGroupConstants.SKLEARN_TRAINING_GROUP
+    info.inputPorts.map(_.displayName) shouldBe List("training")
+    info.outputPorts should have length 1
+    info.outputPorts.head.blocking shouldBe true
+  }
+
+  "SklearnTrainingGradientBoostingOpDesc" should "default its config fields" in {
+    val d = new SklearnTrainingGradientBoostingOpDesc
+    d.countVectorizer shouldBe false
+    d.tfidfTransformer shouldBe false
+    d.target shouldBe null
+    d.text shouldBe null
+  }
+
+  "SklearnTrainingGradientBoostingOpDesc.getOutputSchemas" should
+    "emit the model_name/model schema keyed by the declared output port" in {
+    val d = new SklearnTrainingGradientBoostingOpDesc
+    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
+  }
+
+  "SklearnTrainingGradientBoostingOpDesc.generatePythonCode" should "import the configured sklearn estimator" in {
+    val d = new SklearnTrainingGradientBoostingOpDesc
+    d.target = "y"
+    val code = d.generatePythonCode()
+    code should include("from sklearn.ensemble import GradientBoostingClassifier")
+    code should include("make_pipeline")
+    code should include("Training: Gradient Boosting")
+  }
+
+  "SklearnTrainingGradientBoostingOpDesc" should "round-trip its config fields through the polymorphic base" in {
+    val d = new SklearnTrainingGradientBoostingOpDesc
+    d.target = "label"
+    d.countVectorizer = true
+    val json = objectMapper.writeValueAsString(d)
+    json should include("\"operatorType\":\"SklearnTrainingGradientBoosting\"")
+    val restored = objectMapper.readValue(json, classOf[LogicalOp])
+    restored shouldBe a[SklearnTrainingGradientBoostingOpDesc]
+    val r = restored.asInstanceOf[SklearnTrainingGradientBoostingOpDesc]
+    r.target shouldBe "label"
+    r.countVectorizer shouldBe true
+  }
+}

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingLinearRegressionOpDescSpec.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.training
+
+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 SklearnTrainingLinearRegressionOpDescSpec extends AnyFlatSpec with Matchers {
+
+  "SklearnTrainingLinearRegressionOpDesc.operatorInfo" should
+    "advertise the model name, Sklearn Training group, and the single training port" in {
+    val info = (new SklearnTrainingLinearRegressionOpDesc).operatorInfo
+    info.userFriendlyName shouldBe "Training: Linear Regression"
+    info.operatorDescription shouldBe "Sklearn Training: Linear Regression Operator"
+    info.operatorGroupName shouldBe OperatorGroupConstants.SKLEARN_TRAINING_GROUP
+    info.inputPorts.map(_.displayName) shouldBe List("training")
+    info.outputPorts should have length 1
+    info.outputPorts.head.blocking shouldBe true
+  }
+
+  "SklearnTrainingLinearRegressionOpDesc" should "default its config fields" in {
+    val d = new SklearnTrainingLinearRegressionOpDesc
+    d.countVectorizer shouldBe false
+    d.tfidfTransformer shouldBe false
+    d.target shouldBe null
+    d.text shouldBe null
+  }
+
+  "SklearnTrainingLinearRegressionOpDesc.getOutputSchemas" should
+    "emit the model_name/model schema keyed by the declared output port" in {
+    val d = new SklearnTrainingLinearRegressionOpDesc
+    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
+  }
+
+  "SklearnTrainingLinearRegressionOpDesc.generatePythonCode" should "import the configured sklearn estimator" in {
+    val d = new SklearnTrainingLinearRegressionOpDesc
+    d.target = "y"
+    val code = d.generatePythonCode()
+    code should include("from sklearn.linear_model import LinearRegression")
+    code should include("make_pipeline")
+    code should include("Training: Linear Regression")
+  }
+
+  "SklearnTrainingLinearRegressionOpDesc" should "round-trip its config fields through the polymorphic base" in {
+    val d = new SklearnTrainingLinearRegressionOpDesc
+    d.target = "label"
+    d.countVectorizer = true
+    val json = objectMapper.writeValueAsString(d)
+    json should include("\"operatorType\":\"SklearnTrainingLinearRegression\"")
+    val restored = objectMapper.readValue(json, classOf[LogicalOp])
+    restored shouldBe a[SklearnTrainingLinearRegressionOpDesc]
+    val r = restored.asInstanceOf[SklearnTrainingLinearRegressionOpDesc]
+    r.target shouldBe "label"
+    r.countVectorizer shouldBe true
+  }
+}

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingLogisticRegressionCVOpDescSpec.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.training
+
+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 SklearnTrainingLogisticRegressionCVOpDescSpec extends AnyFlatSpec with Matchers {
+
+  "SklearnTrainingLogisticRegressionCVOpDesc.operatorInfo" should
+    "advertise the model name, Sklearn Training group, and the single training port" in {
+    val info = (new SklearnTrainingLogisticRegressionCVOpDesc).operatorInfo
+    info.userFriendlyName shouldBe "Training: Logistic Regression Cross Validation"
+    info.operatorDescription shouldBe "Sklearn Training: Logistic Regression Cross Validation Operator"
+    info.operatorGroupName shouldBe OperatorGroupConstants.SKLEARN_TRAINING_GROUP
+    info.inputPorts.map(_.displayName) shouldBe List("training")
+    info.outputPorts should have length 1
+    info.outputPorts.head.blocking shouldBe true
+  }
+
+  "SklearnTrainingLogisticRegressionCVOpDesc" should "default its config fields" in {
+    val d = new SklearnTrainingLogisticRegressionCVOpDesc
+    d.countVectorizer shouldBe false
+    d.tfidfTransformer shouldBe false
+    d.target shouldBe null
+    d.text shouldBe null
+  }
+
+  "SklearnTrainingLogisticRegressionCVOpDesc.getOutputSchemas" should
+    "emit the model_name/model schema keyed by the declared output port" in {
+    val d = new SklearnTrainingLogisticRegressionCVOpDesc
+    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
+  }
+
+  "SklearnTrainingLogisticRegressionCVOpDesc.generatePythonCode" should "import the configured sklearn estimator" in {
+    val d = new SklearnTrainingLogisticRegressionCVOpDesc
+    d.target = "y"
+    val code = d.generatePythonCode()
+    code should include("from sklearn.linear_model import LogisticRegressionCV")
+    code should include("make_pipeline")
+    code should include("Training: Logistic Regression Cross Validation")
+  }
+
+  "SklearnTrainingLogisticRegressionCVOpDesc" should "round-trip its config fields through the polymorphic base" in {
+    val d = new SklearnTrainingLogisticRegressionCVOpDesc
+    d.target = "label"
+    d.countVectorizer = true
+    val json = objectMapper.writeValueAsString(d)
+    json should include("\"operatorType\":\"SklearnTrainingLogisticRegressionCV\"")
+    val restored = objectMapper.readValue(json, classOf[LogicalOp])
+    restored shouldBe a[SklearnTrainingLogisticRegressionCVOpDesc]
+    val r = restored.asInstanceOf[SklearnTrainingLogisticRegressionCVOpDesc]
+    r.target shouldBe "label"
+    r.countVectorizer shouldBe true
+  }
+}