test(workflow-operator): add unit test coverage for Sklearn training NB & tree descriptors

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingBernoulliNaiveBayesOpDescSpec.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 SklearnTrainingBernoulliNaiveBayesOpDescSpec extends AnyFlatSpec with Matchers {
+
+  "SklearnTrainingBernoulliNaiveBayesOpDesc.operatorInfo" should
+    "advertise the model name, Sklearn Training group, and the single training port" in {
+    val info = (new SklearnTrainingBernoulliNaiveBayesOpDesc).operatorInfo
+    info.userFriendlyName shouldBe "Training: Bernoulli Naive Bayes"
+    info.operatorDescription shouldBe "Sklearn Training: Bernoulli Naive Bayes 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
+  }
+
+  "SklearnTrainingBernoulliNaiveBayesOpDesc" should "default its config fields" in {
+    val d = new SklearnTrainingBernoulliNaiveBayesOpDesc
+    d.countVectorizer shouldBe false
+    d.tfidfTransformer shouldBe false
+    d.target shouldBe null
+    d.text shouldBe null
+  }
+
+  "SklearnTrainingBernoulliNaiveBayesOpDesc.getOutputSchemas" should
+    "emit the model_name/model schema keyed by the declared output port" in {
+    val d = new SklearnTrainingBernoulliNaiveBayesOpDesc
+    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
+  }
+
+  "SklearnTrainingBernoulliNaiveBayesOpDesc.generatePythonCode" should "import the configured sklearn estimator" in {
+    val d = new SklearnTrainingBernoulliNaiveBayesOpDesc
+    d.target = "y"
+    val code = d.generatePythonCode()
+    code should include("from sklearn.naive_bayes import BernoulliNB")
+    code should include("make_pipeline")
+    code should include("Training: Bernoulli Naive Bayes")
+  }
+
+  "SklearnTrainingBernoulliNaiveBayesOpDesc" should "round-trip its config fields through the polymorphic base" in {
+    val d = new SklearnTrainingBernoulliNaiveBayesOpDesc
+    d.target = "label"
+    d.countVectorizer = true
+    val json = objectMapper.writeValueAsString(d)
+    json should include("\"operatorType\":\"SklearnTrainingBernoulliNaiveBayes\"")
+    val restored = objectMapper.readValue(json, classOf[LogicalOp])
+    restored shouldBe a[SklearnTrainingBernoulliNaiveBayesOpDesc]
+    val r = restored.asInstanceOf[SklearnTrainingBernoulliNaiveBayesOpDesc]
+    r.target shouldBe "label"
+    r.countVectorizer shouldBe true
+  }
+}

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingComplementNaiveBayesOpDescSpec.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 SklearnTrainingComplementNaiveBayesOpDescSpec extends AnyFlatSpec with Matchers {
+
+  "SklearnTrainingComplementNaiveBayesOpDesc.operatorInfo" should
+    "advertise the model name, Sklearn Training group, and the single training port" in {
+    val info = (new SklearnTrainingComplementNaiveBayesOpDesc).operatorInfo
+    info.userFriendlyName shouldBe "Training: Complement Naive Bayes"
+    info.operatorDescription shouldBe "Sklearn Training: Complement Naive Bayes 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
+  }
+
+  "SklearnTrainingComplementNaiveBayesOpDesc" should "default its config fields" in {
+    val d = new SklearnTrainingComplementNaiveBayesOpDesc
+    d.countVectorizer shouldBe false
+    d.tfidfTransformer shouldBe false
+    d.target shouldBe null
+    d.text shouldBe null
+  }
+
+  "SklearnTrainingComplementNaiveBayesOpDesc.getOutputSchemas" should
+    "emit the model_name/model schema keyed by the declared output port" in {
+    val d = new SklearnTrainingComplementNaiveBayesOpDesc
+    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
+  }
+
+  "SklearnTrainingComplementNaiveBayesOpDesc.generatePythonCode" should "import the configured sklearn estimator" in {
+    val d = new SklearnTrainingComplementNaiveBayesOpDesc
+    d.target = "y"
+    val code = d.generatePythonCode()
+    code should include("from sklearn.naive_bayes import ComplementNB")
+    code should include("make_pipeline")
+    code should include("Training: Complement Naive Bayes")
+  }
+
+  "SklearnTrainingComplementNaiveBayesOpDesc" should "round-trip its config fields through the polymorphic base" in {
+    val d = new SklearnTrainingComplementNaiveBayesOpDesc
+    d.target = "label"
+    d.countVectorizer = true
+    val json = objectMapper.writeValueAsString(d)
+    json should include("\"operatorType\":\"SklearnTrainingComplementNaiveBayes\"")
+    val restored = objectMapper.readValue(json, classOf[LogicalOp])
+    restored shouldBe a[SklearnTrainingComplementNaiveBayesOpDesc]
+    val r = restored.asInstanceOf[SklearnTrainingComplementNaiveBayesOpDesc]
+    r.target shouldBe "label"
+    r.countVectorizer shouldBe true
+  }
+}

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingDecisionTreeOpDescSpec.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 SklearnTrainingDecisionTreeOpDescSpec extends AnyFlatSpec with Matchers {
+
+  "SklearnTrainingDecisionTreeOpDesc.operatorInfo" should
+    "advertise the model name, Sklearn Training group, and the single training port" in {
+    val info = (new SklearnTrainingDecisionTreeOpDesc).operatorInfo
+    info.userFriendlyName shouldBe "Training: Decision Tree"
+    info.operatorDescription shouldBe "Sklearn Training: Decision Tree 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
+  }
+
+  "SklearnTrainingDecisionTreeOpDesc" should "default its config fields" in {
+    val d = new SklearnTrainingDecisionTreeOpDesc
+    d.countVectorizer shouldBe false
+    d.tfidfTransformer shouldBe false
+    d.target shouldBe null
+    d.text shouldBe null
+  }
+
+  "SklearnTrainingDecisionTreeOpDesc.getOutputSchemas" should
+    "emit the model_name/model schema keyed by the declared output port" in {
+    val d = new SklearnTrainingDecisionTreeOpDesc
+    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
+  }
+
+  "SklearnTrainingDecisionTreeOpDesc.generatePythonCode" should "import the configured sklearn estimator" in {
+    val d = new SklearnTrainingDecisionTreeOpDesc
+    d.target = "y"
+    val code = d.generatePythonCode()
+    code should include("from sklearn.tree import DecisionTreeClassifier")
+    code should include("make_pipeline")
+    code should include("Training: Decision Tree")
+  }
+
+  "SklearnTrainingDecisionTreeOpDesc" should "round-trip its config fields through the polymorphic base" in {
+    val d = new SklearnTrainingDecisionTreeOpDesc
+    d.target = "label"
+    d.countVectorizer = true
+    val json = objectMapper.writeValueAsString(d)
+    json should include("\"operatorType\":\"SklearnTrainingDecisionTree\"")
+    val restored = objectMapper.readValue(json, classOf[LogicalOp])
+    restored shouldBe a[SklearnTrainingDecisionTreeOpDesc]
+    val r = restored.asInstanceOf[SklearnTrainingDecisionTreeOpDesc]
+    r.target shouldBe "label"
+    r.countVectorizer shouldBe true
+  }
+}

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingExtraTreeOpDescSpec.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 SklearnTrainingExtraTreeOpDescSpec extends AnyFlatSpec with Matchers {
+
+  "SklearnTrainingExtraTreeOpDesc.operatorInfo" should
+    "advertise the model name, Sklearn Training group, and the single training port" in {
+    val info = (new SklearnTrainingExtraTreeOpDesc).operatorInfo
+    info.userFriendlyName shouldBe "Training: Extra Tree"
+    info.operatorDescription shouldBe "Sklearn Training: Extra Tree 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
+  }
+
+  "SklearnTrainingExtraTreeOpDesc" should "default its config fields" in {
+    val d = new SklearnTrainingExtraTreeOpDesc
+    d.countVectorizer shouldBe false
+    d.tfidfTransformer shouldBe false
+    d.target shouldBe null
+    d.text shouldBe null
+  }
+
+  "SklearnTrainingExtraTreeOpDesc.getOutputSchemas" should
+    "emit the model_name/model schema keyed by the declared output port" in {
+    val d = new SklearnTrainingExtraTreeOpDesc
+    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
+  }
+
+  "SklearnTrainingExtraTreeOpDesc.generatePythonCode" should "import the configured sklearn estimator" in {
+    val d = new SklearnTrainingExtraTreeOpDesc
+    d.target = "y"
+    val code = d.generatePythonCode()
+    code should include("from sklearn.tree import ExtraTreeClassifier")
+    code should include("make_pipeline")
+    code should include("Training: Extra Tree")
+  }
+
+  "SklearnTrainingExtraTreeOpDesc" should "round-trip its config fields through the polymorphic base" in {
+    val d = new SklearnTrainingExtraTreeOpDesc
+    d.target = "label"
+    d.countVectorizer = true
+    val json = objectMapper.writeValueAsString(d)
+    json should include("\"operatorType\":\"SklearnTrainingExtraTree\"")
+    val restored = objectMapper.readValue(json, classOf[LogicalOp])
+    restored shouldBe a[SklearnTrainingExtraTreeOpDesc]
+    val r = restored.asInstanceOf[SklearnTrainingExtraTreeOpDesc]
+    r.target shouldBe "label"
+    r.countVectorizer shouldBe true
+  }
+}

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingExtraTreesOpDescSpec.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 SklearnTrainingExtraTreesOpDescSpec extends AnyFlatSpec with Matchers {
+
+  "SklearnTrainingExtraTreesOpDesc.operatorInfo" should
+    "advertise the model name, Sklearn Training group, and the single training port" in {
+    val info = (new SklearnTrainingExtraTreesOpDesc).operatorInfo
+    info.userFriendlyName shouldBe "Training: Extra Trees"
+    info.operatorDescription shouldBe "Sklearn Training: Extra Trees 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
+  }
+
+  "SklearnTrainingExtraTreesOpDesc" should "default its config fields" in {
+    val d = new SklearnTrainingExtraTreesOpDesc
+    d.countVectorizer shouldBe false
+    d.tfidfTransformer shouldBe false
+    d.target shouldBe null
+    d.text shouldBe null
+  }
+
+  "SklearnTrainingExtraTreesOpDesc.getOutputSchemas" should
+    "emit the model_name/model schema keyed by the declared output port" in {
+    val d = new SklearnTrainingExtraTreesOpDesc
+    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
+  }
+
+  "SklearnTrainingExtraTreesOpDesc.generatePythonCode" should "import the configured sklearn estimator" in {
+    val d = new SklearnTrainingExtraTreesOpDesc
+    d.target = "y"
+    val code = d.generatePythonCode()
+    code should include("from sklearn.ensemble import ExtraTreesClassifier")
+    code should include("make_pipeline")
+    code should include("Training: Extra Trees")
+  }
+
+  "SklearnTrainingExtraTreesOpDesc" should "round-trip its config fields through the polymorphic base" in {
+    val d = new SklearnTrainingExtraTreesOpDesc
+    d.target = "label"
+    d.countVectorizer = true
+    val json = objectMapper.writeValueAsString(d)
+    json should include("\"operatorType\":\"SklearnTrainingExtraTrees\"")
+    val restored = objectMapper.readValue(json, classOf[LogicalOp])
+    restored shouldBe a[SklearnTrainingExtraTreesOpDesc]
+    val r = restored.asInstanceOf[SklearnTrainingExtraTreesOpDesc]
+    r.target shouldBe "label"
+    r.countVectorizer shouldBe true
+  }
+}