diff --git a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceIrisLogisticRegressionOpDesc.scala b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceIrisLogisticRegressionOpDesc.scala
index 9a9ac563250..951971b3fbc 100644
--- a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceIrisLogisticRegressionOpDesc.scala
+++ b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceIrisLogisticRegressionOpDesc.scala
@@ -91,6 +91,15 @@ class HuggingFaceIrisLogisticRegressionOpDesc extends PythonOperatorDescriptor {
        |        training_features_stds = [1.72528903, 0.73788937]
        |        length = tuple_[$petalLengthCmAttribute]
        |        width = tuple_[$petalWidthCmAttribute]
+       |        # An empty cell arrives as None, which numpy carries as an object the
+       |        # standardization cannot subtract from. Keep the row and leave the
+       |        # prediction empty rather than ending the run over a measurement the
+       |        # model was never given.
+       |        if length is None or width is None:
+       |            tuple_[$predictionClassName] = None
+       |            tuple_[$predictionProbabilityName] = None
+       |            yield tuple_
+       |            return
        |        features = np.array([[length, width]])
        |        features = ((features - training_features_means) / training_features_stds)
        |        features = torch.from_numpy(features).float()
diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceIrisLogisticRegressionOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceIrisLogisticRegressionOpDescSpec.scala
index 1c3701b4d66..fb45227194d 100644
--- a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceIrisLogisticRegressionOpDescSpec.scala
+++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceIrisLogisticRegressionOpDescSpec.scala
@@ -105,6 +105,16 @@ class HuggingFaceIrisLogisticRegressionOpDescSpec extends AnyFlatSpec with Match
     carries(code, "species") shouldBe true
   }
 
+  // An empty cell reaches the standardization as a None, which numpy cannot
+  // subtract from, so the row is answered rather than ending the run.
+  it should "leave the prediction empty when a measurement is missing" in {
+    val d = configured()
+    val code = d.generatePythonCode()
+    code should include("if length is None or width is None:")
+    code should include("yield tuple_")
+    code should include("return")
+  }
+
   "HuggingFaceIrisLogisticRegressionOpDesc.getPhysicalOp" should
     "wire an OpExecWithCode python executor carrying the operator's ports" in {
     val d = configured()