feat(operator): reject Count Vectorizer on the Gaussian Naive Bayes operators

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnGaussianNaiveBayesOpDesc.scala

@@ -22,4 +22,10 @@ package org.apache.texera.amber.operator.sklearn
 class SklearnGaussianNaiveBayesOpDesc extends SklearnClassifierOpDesc {
   override def getImportStatements = "from sklearn.naive_bayes import GaussianNB"
   override def getUserFriendlyModelName = "Gaussian Naive Bayes"
+
+  // GaussianNB estimates a mean and a variance for every feature, which reads the
+  // zeros as well, so scikit-learn validates its input without accept_sparse. The
+  // refusal is deliberate: densifying a text matrix is what would exhaust memory.
+  override protected def countVectorizerAlternatives: Option[String] =
+    Some("Multinomial, Bernoulli or Complement Naive Bayes")
 }

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnModelOpDesc.scala

@@ -85,9 +85,27 @@ abstract class SklearnModelOpDesc extends PythonOperatorDescriptor {
   @JsonIgnore
   def getUserFriendlyModelName: String
 
+  /** An estimator that cannot be fitted on the sparse matrix `CountVectorizer`
+    * produces names here what to reach for instead, and turning the switch on
+    * stops the workflow at compile time rather than inside scikit-learn.
+    *
+    * The switch is declared on this base, so every estimator in both families
+    * inherits it whether or not its own can use it.
+    */
+  @JsonIgnore
+  protected def countVectorizerAlternatives: Option[String] = None
+
   override def getOutputSchemas(
       inputSchemas: Map[PortIdentity, Schema]
   ): Map[PortIdentity, Schema] = {
+    if (countVectorizer) {
+      countVectorizerAlternatives.foreach { alternatives =>
+        throw new RuntimeException(
+          s"$getUserFriendlyModelName cannot be trained on the sparse matrix Count Vectorizer" +
+            s" produces. Turn Count Vectorizer off, or use $alternatives."
+        )
+      }
+    }
     Map(
       operatorInfo.outputPorts.head.id -> Schema()
         .add("model_name", AttributeType.STRING)

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingGaussianNaiveBayesOpDesc.scala

@@ -22,4 +22,9 @@ package org.apache.texera.amber.operator.sklearn.training
 class SklearnTrainingGaussianNaiveBayesOpDesc extends SklearnTrainingOpDesc {
   override def getImportStatements = "from sklearn.naive_bayes import GaussianNB"
   override def getUserFriendlyModelName = "Training: Gaussian Naive Bayes"
+
+  // The same estimator as the classifier family's, with the same limitation: a mean
+  // and a variance per feature cannot be read off a sparse matrix without densifying.
+  override protected def countVectorizerAlternatives: Option[String] =
+    Some("Multinomial, Bernoulli or Complement Naive Bayes")
 }

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnGaussianNaiveBayesOpDescSpec.scala

@@ -78,4 +78,19 @@ class SklearnGaussianNaiveBayesOpDescSpec extends AnyFlatSpec with Matchers {
     r.target shouldBe "label"
     r.countVectorizer shouldBe true
   }
+
+  "SklearnGaussianNaiveBayesOpDesc.getOutputSchemas" should
+    "reject Count Vectorizer, naming the estimator and what accepts it instead" in {
+    // GaussianNB is fitted on a mean and a variance per feature, which a sparse
+    // matrix cannot supply without being densified, so this used to end the run
+    // from inside scikit-learn. It stops at compile time now.
+    val d = new SklearnGaussianNaiveBayesOpDesc
+    d.target = "y"
+    d.text = "note"
+    d.countVectorizer = true
+    val thrown = intercept[RuntimeException](d.getOutputSchemas(Map.empty))
+    thrown.getMessage should include("Gaussian Naive Bayes")
+    thrown.getMessage should include("Count Vectorizer")
+    thrown.getMessage should include("Multinomial, Bernoulli or Complement Naive Bayes")
+  }
 }

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnModelOpDescSpec.scala

@@ -75,4 +75,32 @@ class SklearnModelOpDescSpec extends AnyFlatSpec with Matchers {
     )
     d.getOutputSchemas(arbitraryInput) shouldBe fromEmpty
   }
+
+  it should "let Count Vectorizer through for an estimator that named no alternative" in {
+    // The default, and what every estimator but GaussianNB relies on: the sparse
+    // matrix is what the others accept.
+    val d = new TestSklearnModelOpDesc
+    d.countVectorizer = true
+    d.getOutputSchemas(Map.empty).keySet shouldBe Set(d.operatorInfo.outputPorts.head.id)
+  }
+
+  it should "reject Count Vectorizer for an estimator that named one" in {
+    val d = new TestSklearnModelOpDesc {
+      override protected def countVectorizerAlternatives: Option[String] = Some("Some Other Model")
+    }
+    d.countVectorizer = true
+    val thrown = intercept[RuntimeException](d.getOutputSchemas(Map.empty))
+    thrown.getMessage should include("Test Model")
+    thrown.getMessage should include("Count Vectorizer")
+    thrown.getMessage should include("Some Other Model")
+  }
+
+  it should "stay silent while Count Vectorizer is off, whatever the estimator" in {
+    // The switch defaults to off, so a freshly dropped operator must not be
+    // reported invalid before anyone has configured it.
+    val d = new TestSklearnModelOpDesc {
+      override protected def countVectorizerAlternatives: Option[String] = Some("Some Other Model")
+    }
+    d.getOutputSchemas(Map.empty).keySet shouldBe Set(d.operatorInfo.outputPorts.head.id)
+  }
 }

common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingGaussianNaiveBayesOpDescSpec.scala

@@ -76,4 +76,15 @@ class SklearnTrainingGaussianNaiveBayesOpDescSpec extends AnyFlatSpec with Match
     r.target shouldBe "label"
     r.countVectorizer shouldBe true
   }
+
+  "SklearnTrainingGaussianNaiveBayesOpDesc.getOutputSchemas" should
+    "reject Count Vectorizer the same way its classifier counterpart does" in {
+    val d = new SklearnTrainingGaussianNaiveBayesOpDesc
+    d.target = "y"
+    d.text = "note"
+    d.countVectorizer = true
+    val thrown = intercept[RuntimeException](d.getOutputSchemas(Map.empty))
+    thrown.getMessage should include("Training: Gaussian Naive Bayes")
+    thrown.getMessage should include("Multinomial, Bernoulli or Complement Naive Bayes")
+  }
 }