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..347d3457ef4 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
@@ -20,24 +20,40 @@
 package org.apache.texera.amber.operator.huggingFace
 
 import com.fasterxml.jackson.annotation.{JsonProperty, JsonPropertyDescription}
+import com.kjetland.jackson.jsonSchema.annotations.JsonSchemaInject
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.pybuilder.PyStringTypes.EncodableString
 import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
 import org.apache.texera.amber.core.workflow.{InputPort, OutputPort, PortIdentity}
-import org.apache.texera.amber.operator.PythonOperatorDescriptor
-import org.apache.texera.amber.operator.metadata.annotations.AutofillAttributeName
+import org.apache.texera.amber.operator.{PythonOperatorDescriptor, StandaloneCodeGenerator}
+import org.apache.texera.amber.operator.metadata.annotations.{AutofillAttributeName, SampleColumn}
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.pyStringLiteral
 
-class HuggingFaceIrisLogisticRegressionOpDesc extends PythonOperatorDescriptor {
+// type constraint: both measurements are standardized against the training means
+// and handed to the model as floats, so each column can only be numeric.
+@JsonSchemaInject(json = """
+{
+  "attributeTypeRules": {
+    "petalLengthCmAttribute": { "enum": ["integer", "long", "double"] },
+    "petalWidthCmAttribute": { "enum": ["integer", "long", "double"] }
+  }
+}
+""")
+class HuggingFaceIrisLogisticRegressionOpDesc
+    extends PythonOperatorDescriptor
+    with StandaloneCodeGenerator {
 
   @JsonProperty(value = "petalLengthCmAttribute", required = true)
   @JsonPropertyDescription("attribute in your dataset corresponding to PetalLengthCm")
   @AutofillAttributeName
+  @SampleColumn("petal_length")
   var petalLengthCmAttribute: EncodableString = _
 
   @JsonProperty(value = "petalWidthCmAttribute", required = true)
   @JsonPropertyDescription("attribute in your dataset corresponding to PetalWidthCm")
   @AutofillAttributeName
+  @SampleColumn("petal_width")
   var petalWidthCmAttribute: EncodableString = _
 
   @JsonProperty(
@@ -91,6 +107,15 @@ 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()
@@ -103,6 +128,57 @@ class HuggingFaceIrisLogisticRegressionOpDesc extends PythonOperatorDescriptor {
        |        yield tuple_""".encode
   }
 
+  override def producesDataFrame(): Boolean = true
+
+  // Standalone mirror of generatePythonCode: rebuild+load the pretrained linear
+  // model once, then apply the same per-row standardize→sigmoid→threshold logic,
+  // adding the STRING predicted class and DOUBLE probability columns (in
+  // getOutputSchemas order) to produce out1df.
+  override def generateStandaloneCode(): String = {
+    val lengthLit = pyStringLiteral(petalLengthCmAttribute)
+    val widthLit = pyStringLiteral(petalWidthCmAttribute)
+    s"""import numpy as np
+       |import torch
+       |import torch.nn as nn
+       |from huggingface_hub import PyTorchModelHubMixin
+       |
+       |class LinearModel(nn.Module, PyTorchModelHubMixin):
+       |    def __init__(self):
+       |        super().__init__()
+       |        self.fc = nn.Linear(2, 1)
+       |
+       |    def forward(self, x):
+       |        return self.fc(x)
+       |
+       |model = LinearModel.from_pretrained("sadhaklal/logistic-regression-iris")
+       |model.eval()
+       |
+       |training_features_means = [3.72666667, 1.17619048]
+       |training_features_stds = [1.72528903, 0.73788937]
+       |out1df = in1df.copy()
+       |_classes = []
+       |_probs = []
+       |for _length, _width in zip(out1df[$lengthLit], out1df[$widthLit]):
+       |    # The operator's guard, except that an empty cell reaches a frame read
+       |    # from JSON as a NaN rather than as the None a Tuple hands over, so this
+       |    # side asks pandas, which answers for both.
+       |    if pd.isna(_length) or pd.isna(_width):
+       |        _classes.append(None)
+       |        _probs.append(None)
+       |        continue
+       |    features = np.array([[_length, _width]])
+       |    features = ((features - training_features_means) / training_features_stds)
+       |    features = torch.from_numpy(features).float()
+       |    with torch.no_grad():
+       |        logits = model(features)
+       |    proba = torch.sigmoid(logits.squeeze())
+       |    preds = (proba > 0.5).long()
+       |    _probs.append(float(proba))
+       |    _classes.append("Iris-setosa" if preds == 1 else "Not Iris-setosa")
+       |out1df[${pyStringLiteral(predictionClassName)}] = _classes
+       |out1df[${pyStringLiteral(predictionProbabilityName)}] = _probs""".stripMargin
+  }
+
   override def operatorInfo: OperatorInfo =
     OperatorInfo(
       "Hugging Face Iris Logistic Regression",
diff --git a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSentimentAnalysisOpDesc.scala b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSentimentAnalysisOpDesc.scala
index 0a8fb8a8948..4e237adab44 100644
--- a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSentimentAnalysisOpDesc.scala
+++ b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSentimentAnalysisOpDesc.scala
@@ -20,17 +20,33 @@
 package org.apache.texera.amber.operator.huggingFace
 
 import com.fasterxml.jackson.annotation.{JsonProperty, JsonPropertyDescription}
+import com.kjetland.jackson.jsonSchema.annotations.JsonSchemaInject
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.core.workflow.{InputPort, OutputPort, PortIdentity}
-import org.apache.texera.amber.operator.PythonOperatorDescriptor
-import org.apache.texera.amber.operator.metadata.annotations.AutofillAttributeName
+import org.apache.texera.amber.operator.{PythonOperatorDescriptor, StandaloneCodeGenerator}
+import org.apache.texera.amber.operator.metadata.annotations.{AutofillAttributeName, SampleColumn}
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
 import org.apache.texera.amber.pybuilder.PyStringTypes.EncodableString
-import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
-class HuggingFaceSentimentAnalysisOpDesc extends PythonOperatorDescriptor {
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.{
+  PythonTemplateBuilderStringContext,
+  pyStringLiteral
+}
+// type constraint: the tokenizer scores text and refuses anything that is not a
+// string, so the column can only be a string.
+@JsonSchemaInject(json = """
+{
+  "attributeTypeRules": {
+    "attribute": { "enum": ["string"] }
+  }
+}
+""")
+class HuggingFaceSentimentAnalysisOpDesc
+    extends PythonOperatorDescriptor
+    with StandaloneCodeGenerator {
   @JsonProperty(value = "attribute", required = true)
   @JsonPropertyDescription("column to perform sentiment analysis on")
   @AutofillAttributeName
+  @SampleColumn("short_text")
   var attribute: EncodableString = _
 
   @JsonProperty(
@@ -96,6 +112,46 @@ class HuggingFaceSentimentAnalysisOpDesc extends PythonOperatorDescriptor {
        |        yield tuple_""".encode
   }
 
+  override def producesDataFrame(): Boolean = true
+
+  // Standalone mirror of generatePythonCode: load the model once, then apply the
+  // same per-row softmax-over-3-labels logic to in1df, adding the three DOUBLE
+  // result columns (in the same order as getOutputSchemas) to produce out1df.
+  override def generateStandaloneCode(): String = {
+    val positiveLit = pyStringLiteral(resultAttributePositive)
+    val neutralLit = pyStringLiteral(resultAttributeNeutral)
+    val negativeLit = pyStringLiteral(resultAttributeNegative)
+    s"""from transformers import AutoModelForSequenceClassification
+       |from transformers import AutoTokenizer, AutoConfig
+       |import numpy as np
+       |from scipy.special import softmax
+       |
+       |model_name = "cardiffnlp/twitter-roberta-base-sentiment-latest"
+       |tokenizer = AutoTokenizer.from_pretrained(model_name)
+       |config = AutoConfig.from_pretrained(model_name)
+       |model = AutoModelForSequenceClassification.from_pretrained(model_name)
+       |
+       |out1df = in1df.copy()
+       |labels = {"positive": $positiveLit, "neutral": $neutralLit, "negative": $negativeLit}
+       |for _col in ($positiveLit, $neutralLit, $negativeLit):
+       |    out1df[_col] = 0.0
+       |for _idx, _text in out1df[${pyStringLiteral(attribute)}].items():
+       |    # An empty cell arrives as None, which the tokenizer rejects. Keep the row
+       |    # and leave the scores empty rather than ending the run over a value the
+       |    # model has nothing to say about.
+       |    if _text is None or (isinstance(_text, str) and not _text.strip()):
+       |        for _col in ($positiveLit, $neutralLit, $negativeLit):
+       |            out1df.at[_idx, _col] = None
+       |        continue
+       |    encoded_input = tokenizer(_text, return_tensors='pt')
+       |    output = model(**encoded_input)
+       |    scores = softmax(output[0][0].detach().numpy())
+       |    ranking = np.argsort(scores)[::-1]
+       |    for i in range(scores.shape[0]):
+       |        label = labels[config.id2label[ranking[i]]]
+       |        out1df.at[_idx, label] = np.round(float(scores[ranking[i]]), 4)""".stripMargin
+  }
+
   override def operatorInfo: OperatorInfo =
     OperatorInfo(
       "Hugging Face Sentiment Analysis",
diff --git a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSpamSMSDetectionOpDesc.scala b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSpamSMSDetectionOpDesc.scala
index 0daa7cd4aa8..df3e5b1b277 100644
--- a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSpamSMSDetectionOpDesc.scala
+++ b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSpamSMSDetectionOpDesc.scala
@@ -20,17 +20,33 @@
 package org.apache.texera.amber.operator.huggingFace
 
 import com.fasterxml.jackson.annotation.{JsonProperty, JsonPropertyDescription}
+import com.kjetland.jackson.jsonSchema.annotations.JsonSchemaInject
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.core.workflow.{InputPort, OutputPort, PortIdentity}
-import org.apache.texera.amber.operator.PythonOperatorDescriptor
-import org.apache.texera.amber.operator.metadata.annotations.AutofillAttributeName
+import org.apache.texera.amber.operator.{PythonOperatorDescriptor, StandaloneCodeGenerator}
+import org.apache.texera.amber.operator.metadata.annotations.{AutofillAttributeName, SampleColumn}
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
 import org.apache.texera.amber.pybuilder.PyStringTypes.EncodableString
-import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
-class HuggingFaceSpamSMSDetectionOpDesc extends PythonOperatorDescriptor {
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.{
+  PythonTemplateBuilderStringContext,
+  pyStringLiteral
+}
+// type constraint: the classification pipeline reads text and refuses anything
+// that is not a string, so the column can only be a string.
+@JsonSchemaInject(json = """
+{
+  "attributeTypeRules": {
+    "attribute": { "enum": ["string"] }
+  }
+}
+""")
+class HuggingFaceSpamSMSDetectionOpDesc
+    extends PythonOperatorDescriptor
+    with StandaloneCodeGenerator {
   @JsonProperty(value = "attribute", required = true)
   @JsonPropertyDescription("column to perform spam detection on")
   @AutofillAttributeName
+  @SampleColumn("short_text")
   var attribute: EncodableString = _
 
   @JsonProperty(
@@ -75,6 +91,33 @@ class HuggingFaceSpamSMSDetectionOpDesc extends PythonOperatorDescriptor {
        |        yield tuple_""".encode
   }
 
+  override def producesDataFrame(): Boolean = true
+
+  // Standalone mirror of generatePythonCode: build the text-classification
+  // pipeline once, run it per row, and add the BOOLEAN spam flag (LABEL_1) and
+  // the DOUBLE score columns (in getOutputSchemas order) to produce out1df.
+  override def generateStandaloneCode(): String = {
+    val attributeLit = pyStringLiteral(attribute)
+    val spamLit = pyStringLiteral(resultAttributeSpam)
+    val probabilityLit = pyStringLiteral(resultAttributeProbability)
+    s"""from transformers import pipeline
+       |
+       |_pipeline = pipeline("text-classification", model="mrm8488/bert-tiny-finetuned-sms-spam-detection")
+       |out1df = in1df.copy()
+       |
+       |def _classify(_t):
+       |    # An empty cell arrives as None, which the pipeline rejects. Keep the row
+       |    # and leave the results empty rather than ending the run over a value the
+       |    # model has nothing to say about.
+       |    if _t is None or (isinstance(_t, str) and not _t.strip()):
+       |        return None
+       |    return _pipeline(_t)[0]
+       |
+       |_results = [_classify(_t) for _t in out1df[$attributeLit]]
+       |out1df[$spamLit] = [None if _r is None else _r["label"] == "LABEL_1" for _r in _results]
+       |out1df[$probabilityLit] = [None if _r is None else _r["score"] for _r in _results]""".stripMargin
+  }
+
   override def operatorInfo: OperatorInfo =
     OperatorInfo(
       "Hugging Face Spam Detection",
diff --git a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceTextSummarizationOpDesc.scala b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceTextSummarizationOpDesc.scala
index 541bcf46ac9..494cdda5ea0 100644
--- a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceTextSummarizationOpDesc.scala
+++ b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceTextSummarizationOpDesc.scala
@@ -20,17 +20,33 @@
 package org.apache.texera.amber.operator.huggingFace
 
 import com.fasterxml.jackson.annotation.{JsonProperty, JsonPropertyDescription}
+import com.kjetland.jackson.jsonSchema.annotations.JsonSchemaInject
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.core.workflow.{InputPort, OutputPort, PortIdentity}
-import org.apache.texera.amber.operator.PythonOperatorDescriptor
-import org.apache.texera.amber.operator.metadata.annotations.AutofillAttributeName
+import org.apache.texera.amber.operator.{PythonOperatorDescriptor, StandaloneCodeGenerator}
+import org.apache.texera.amber.operator.metadata.annotations.{AutofillAttributeName, SampleColumn}
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
 import org.apache.texera.amber.pybuilder.PyStringTypes.EncodableString
-import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
-class HuggingFaceTextSummarizationOpDesc extends PythonOperatorDescriptor {
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.{
+  PythonTemplateBuilderStringContext,
+  pyStringLiteral
+}
+// type constraint: the tokenizer summarizes text and refuses anything that is not
+// a string, so the column can only be a string.
+@JsonSchemaInject(json = """
+{
+  "attributeTypeRules": {
+    "attribute": { "enum": ["string"] }
+  }
+}
+""")
+class HuggingFaceTextSummarizationOpDesc
+    extends PythonOperatorDescriptor
+    with StandaloneCodeGenerator {
   @JsonProperty(value = "attribute", required = true)
   @JsonPropertyDescription("attribute to perform text summarization on")
   @AutofillAttributeName
+  @SampleColumn("long_text")
   var attribute: EncodableString = _
 
   @JsonProperty(
@@ -76,6 +92,37 @@ class HuggingFaceTextSummarizationOpDesc extends PythonOperatorDescriptor {
        |        yield tuple_""".encode
   }
 
+  override def producesDataFrame(): Boolean = true
+
+  // Standalone mirror of generatePythonCode: load the encoder-decoder model
+  // once, generate a summary per row, and add the STRING result column to
+  // produce out1df.
+  override def generateStandaloneCode(): String = {
+    s"""from transformers import BertTokenizerFast, EncoderDecoderModel
+       |import torch
+       |
+       |model_name = "mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization"
+       |device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+       |tokenizer = BertTokenizerFast.from_pretrained(model_name)
+       |model = EncoderDecoderModel.from_pretrained(model_name).to(device)
+       |
+       |out1df = in1df.copy()
+       |_summaries = []
+       |for _text in out1df[${pyStringLiteral(attribute)}]:
+       |    # An empty cell arrives as None, which the tokenizer rejects. Keep the row
+       |    # and leave the summary empty rather than ending the run over a value the
+       |    # model has nothing to say about.
+       |    if _text is None or (isinstance(_text, str) and not _text.strip()):
+       |        _summaries.append(None)
+       |        continue
+       |    inputs = tokenizer([_text], padding="max_length", truncation=True, max_length=512, return_tensors="pt")
+       |    input_ids = inputs.input_ids.to(device)
+       |    attention_mask = inputs.attention_mask.to(device)
+       |    output = model.generate(input_ids, attention_mask=attention_mask)
+       |    _summaries.append(tokenizer.decode(output[0], skip_special_tokens=True))
+       |out1df[${pyStringLiteral(resultAttribute)}] = _summaries""".stripMargin
+  }
+
   override def operatorInfo: OperatorInfo =
     OperatorInfo(
       "Hugging Face Text Summarization",
diff --git a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnClassifierOpDesc.scala b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnClassifierOpDesc.scala
index a2323e5d19f..b21c6dfaa31 100644
--- a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnClassifierOpDesc.scala
+++ b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnClassifierOpDesc.scala
@@ -19,11 +19,13 @@
 
 package org.apache.texera.amber.operator.sklearn
 
+import org.apache.texera.amber.operator.StandaloneCodeGenerator
 import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.pyStringLiteral
 import org.apache.texera.amber.core.workflow.{InputPort, OutputPort, PortIdentity}
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
 
-abstract class SklearnClassifierOpDesc extends SklearnModelOpDesc {
+abstract class SklearnClassifierOpDesc extends SklearnModelOpDesc with StandaloneCodeGenerator {
 
   override def getImportStatements = ""
 
@@ -76,4 +78,46 @@ $reportMissingKept
       ),
       outputPorts = List(OutputPort(blocking = true))
     )
+
+  override def generateStandaloneCode(): String = {
+    val estimator = getImportStatements.split(" ").last
+    val tfidfPart = if (tfidfTransformer) "TfidfTransformer()," else ""
+    val targetLit = pyStringLiteral(target)
+    val modelNameLit = pyStringLiteral(getUserFriendlyModelName)
+    val narrowTrain = dropNonFeatureColumns("X_train", "")
+    val narrowTest = dropNonFeatureColumns("X_test", "")
+
+    s"""${getImportStatements}
+       |from sklearn.metrics import accuracy_score, f1_score, precision_score, recall_score
+       |from sklearn.pipeline import make_pipeline
+       |from sklearn.compose import ColumnTransformer
+       |from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
+       |import numpy as np
+       |import pandas as pd
+       |
+       |# The same rows the operator drops, and on both frames: the model is fitted
+       |# on one and scored on the other, so narrowing only one side would fit and
+       |# score on different data. A local name rather than a reassignment, since
+       |# the input variable belongs to whichever operator produced it.
+       |_train = ${dropMissingRowsStandalone("in1df")}
+       |if len(_train) < len(in1df):
+       |    print("Skipped", len(in1df) - len(_train), "of", len(in1df), "rows with missing values")
+       |Y_train = _train[$targetLit]
+       |X_train = _train.drop($targetLit, axis=1)
+       |$narrowTrain
+       |model = make_pipeline(${vectorizerStage(c => pyStringLiteral(c))}$tfidfPart$estimator()).fit(X_train, Y_train)
+       |
+       |_test = ${dropMissingRowsStandalone("in2df")}
+       |Y_test = _test[$targetLit]
+       |X_test = _test.drop($targetLit, axis=1)
+       |$narrowTest
+       |predictions = model.predict(X_test)
+       |print("Overall Accuracy:", round(accuracy_score(Y_test, predictions), 4))
+       |f1s = f1_score(Y_test, predictions, average=None)
+       |precisions = precision_score(Y_test, predictions, average=None)
+       |recalls = recall_score(Y_test, predictions, average=None)
+       |for i, class_name in enumerate(np.unique(Y_test)):
+       |    print("Class", repr(class_name), " - F1:", round(f1s[i], 4), ", Precision:", round(precisions[i], 4), ", Recall:", round(recalls[i], 4))
+       |out1df = pd.DataFrame([{"model_name": $modelNameLit, "model": model}])""".stripMargin
+  }
 }
diff --git a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearRegressionOpDesc.scala b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearRegressionOpDesc.scala
index 9ea793338e1..3bc6154e437 100644
--- a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearRegressionOpDesc.scala
+++ b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearRegressionOpDesc.scala
@@ -25,16 +25,23 @@ import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
 import org.apache.texera.amber.pybuilder.PyStringTypes.EncodableString
 import org.apache.texera.amber.core.workflow.{InputPort, OutputPort, PortIdentity}
-import org.apache.texera.amber.operator.PythonOperatorDescriptor
-import org.apache.texera.amber.operator.metadata.annotations.AutofillAttributeName
+import org.apache.texera.amber.operator.{PythonOperatorDescriptor, StandaloneCodeGenerator}
+import org.apache.texera.amber.operator.metadata.annotations.{AutofillAttributeName, SampleColumn}
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.pyStringLiteral
 
-class SklearnLinearRegressionOpDesc extends PythonOperatorDescriptor with SklearnFittableColumns {
+class SklearnLinearRegressionOpDesc
+    extends PythonOperatorDescriptor
+    with StandaloneCodeGenerator
+    with SklearnFittableColumns {
 
   @JsonSchemaTitle("Target Attribute")
   @JsonPropertyDescription("Attribute in your dataset corresponding to target.")
   @JsonProperty(required = true)
   @AutofillAttributeName
+  // The label the estimator fits against. Test-only steering: without it the
+  // first column wins, which on a feature/label table is a feature.
+  @SampleColumn("species")
   var target: EncodableString = _
 
   @JsonSchemaTitle("Degree")
@@ -95,4 +102,39 @@ class SklearnLinearRegressionOpDesc extends PythonOperatorDescriptor with Sklear
     )
   }
 
+  override def generateStandaloneCode(): String = {
+    val targetLit = pyStringLiteral(target)
+    s"""from sklearn.metrics import mean_absolute_error, r2_score
+       |from sklearn.pipeline import make_pipeline
+       |from sklearn.linear_model import LinearRegression
+       |from sklearn.preprocessing import PolynomialFeatures
+       |import pandas as pd
+       |
+       |# The same rows the operator drops, and on both frames: the model is fitted
+       |# on one and scored on the other, so narrowing only one side would fit and
+       |# score on different data. Local names rather than reassignments, since the
+       |# input variables belong to whichever operators produced them.
+       |_train = in1df.dropna()
+       |if len(_train) < len(in1df):
+       |    print("Skipped", len(in1df) - len(_train), "of", len(in1df), "rows with missing values")
+       |Y_train = _train[$targetLit]
+       |X_train = _train.drop($targetLit, axis=1)
+       |${narrowToFittableColumns("X_train", "")}
+       |pipeline = make_pipeline(
+       |    PolynomialFeatures(degree=$degree),
+       |    LinearRegression()
+       |)
+       |model = pipeline.fit(X_train, Y_train)
+       |
+       |_test = in2df.dropna()
+       |Y_test = _test[$targetLit]
+       |X_test = _test.drop($targetLit, axis=1)
+       |${narrowToFittableColumns("X_test", "")}
+       |predictions = model.predict(X_test)
+       |mae = round(mean_absolute_error(Y_test, predictions), 4)
+       |r2 = round(r2_score(Y_test, predictions), 4)
+       |print("MAE:", mae, ", R2:", r2)
+       |out1df = pd.DataFrame([{"model_name": "LinearRegression", "model": model}])""".stripMargin
+  }
+
 }
diff --git a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnModelOpDesc.scala b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnModelOpDesc.scala
index c771d31affa..43dd741c0e4 100644
--- a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnModelOpDesc.scala
+++ b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnModelOpDesc.scala
@@ -34,12 +34,14 @@ import com.kjetland.jackson.jsonSchema.annotations.{
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.pybuilder.PyStringTypes.EncodableString
 import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.pyStringLiteral
 import org.apache.texera.amber.core.workflow.PortIdentity
 import org.apache.texera.amber.operator.PythonOperatorDescriptor
 import org.apache.texera.amber.operator.metadata.annotations.{
   AutofillAttributeName,
   CommonOpDescAnnotation,
-  HideAnnotation
+  HideAnnotation,
+  SampleColumn
 }
 
 // `text` names the columns Count Vectorizer tokenizes, so they are string columns
@@ -72,6 +74,9 @@ import org.apache.texera.amber.operator.metadata.annotations.{
 """)
 abstract class SklearnModelOpDesc extends PythonOperatorDescriptor with SklearnFittableColumns {
 
+  // The label the estimator fits against. Test-only steering: without it the
+  // first column wins, which on a feature/label table is a feature.
+  @SampleColumn("species")
   @JsonSchemaTitle("Target Attribute")
   @JsonPropertyDescription("Attribute in your dataset corresponding to target.")
   @JsonProperty(required = true)
@@ -182,6 +187,22 @@ abstract class SklearnModelOpDesc extends PythonOperatorDescriptor with SklearnF
     else if (handlesMissingValues) pyb"table.dropna(subset=[$target])".toString
     else "table.dropna()"
 
+  /** [[dropMissingRows]] for the standalone path, which names its own frame and
+    * has no `self` to decode a column name through. Stated separately rather than
+    * shared through a renderer: `pyb` encodes by the STATIC type of what it
+    * interpolates, so a column handed through a `String => String` loses the
+    * annotation that makes it encode and reaches the script raw.
+    */
+  @JsonIgnore
+  protected def dropMissingRowsStandalone(frame: String): String = {
+    val subset =
+      if (countVectorizer) (text :+ target).map(c => pyStringLiteral(c).toString)
+      else if (handlesMissingValues) Seq(pyStringLiteral(target).toString)
+      else Seq.empty
+    if (subset.isEmpty) s"$frame.dropna()"
+    else subset.mkString(s"$frame.dropna(subset=[", ", ", "])")
+  }
+
   // Rows the estimator keeps are still rows the user did not know were incomplete,
   // so say how many reached the fit. Empty for the estimators that dropped them all.
   @JsonIgnore
@@ -202,6 +223,16 @@ abstract class SklearnModelOpDesc extends PythonOperatorDescriptor with SklearnF
             s" produces. Turn Count Vectorizer off, or use $alternatives."
         )
       }
+      // The generated code drops the target before the text pipeline reads its
+      // columns, so naming it here asks the pipeline for a column that is no
+      // longer there. Refused rather than vectorized: the label is the answer,
+      // and a model given it as a feature reads that answer off its own input.
+      if (text.contains(target)) {
+        throw new RuntimeException(
+          s""""$target" is the Target Attribute, so it cannot also be a Text Attribute.""" +
+            " Remove it from Text Attribute, or fit against a different column."
+        )
+      }
     }
     Map(
       operatorInfo.outputPorts.head.id -> Schema()
diff --git a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnPredictionOpDesc.scala b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnPredictionOpDesc.scala
index 5d8b1b1e7dc..969186c99b2 100644
--- a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnPredictionOpDesc.scala
+++ b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/SklearnPredictionOpDesc.scala
@@ -24,14 +24,15 @@ import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
 import org.apache.texera.amber.pybuilder.PyStringTypes.EncodableString
 import org.apache.texera.amber.core.workflow.{InputPort, OutputPort, PortIdentity}
-import org.apache.texera.amber.operator.PythonOperatorDescriptor
+import org.apache.texera.amber.operator.{PythonOperatorDescriptor, StandaloneCodeGenerator}
 import org.apache.texera.amber.operator.metadata.annotations.{
   AutofillAttributeName,
   AutofillAttributeNameOnPort1
 }
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.pyStringLiteral
 
-class SklearnPredictionOpDesc extends PythonOperatorDescriptor {
+class SklearnPredictionOpDesc extends PythonOperatorDescriptor with StandaloneCodeGenerator {
   @JsonProperty(value = "Model Attribute", required = true, defaultValue = "model")
   @JsonPropertyDescription("attribute corresponding to ML model")
   @AutofillAttributeName
@@ -99,4 +100,39 @@ class SklearnPredictionOpDesc extends PythonOperatorDescriptor {
         .add(resultAttribute, resultType)
     )
   }
+
+  /** Python that narrows `X` to the columns the model was fitted on.
+    *
+    * The fitting side leaves out the columns an estimator cannot fit, so this
+    * side has to leave out the same ones or scikit-learn refuses the frame for
+    * naming features it never saw. Read off the model rather than re-derived:
+    * what it was fitted on is a fact it carries, and asking it cannot drift from
+    * whatever rule the fitting operator applied.
+    */
+  private val narrowToFittedFeatures: String =
+    """_fitted = getattr(model, "feature_names_in_", None)
+      |if _fitted is not None:
+      |    X = X[list(_fitted)]""".stripMargin
+
+  override def generateStandaloneCode(): String = {
+    val modelLit = pyStringLiteral(model)
+    val resultLit = pyStringLiteral(resultAttribute)
+    if (groundTruthAttribute.nonEmpty) {
+      s"""from sklearn.pipeline import Pipeline
+         |
+         |model = in1df[$modelLit].iloc[0]
+         |out1df = in2df.copy()
+         |X = in2df.drop(${pyStringLiteral(groundTruthAttribute)}, axis=1)
+         |$narrowToFittedFeatures
+         |out1df[$resultLit] = model.predict(X)""".stripMargin
+    } else {
+      s"""from sklearn.pipeline import Pipeline
+         |
+         |model = in1df[$modelLit].iloc[0]
+         |out1df = in2df.copy()
+         |X = in2df
+         |$narrowToFittedFeatures
+         |out1df[$resultLit] = [str(p) for p in model.predict(X)]""".stripMargin
+    }
+  }
 }
diff --git a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/testing/SklearnTestingOpDesc.scala b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/testing/SklearnTestingOpDesc.scala
index 94319f09367..ea436d05d6b 100644
--- a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/testing/SklearnTestingOpDesc.scala
+++ b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/testing/SklearnTestingOpDesc.scala
@@ -23,7 +23,7 @@ import com.fasterxml.jackson.annotation.{JsonProperty, JsonPropertyDescription}
 import com.kjetland.jackson.jsonSchema.annotations.JsonSchemaTitle
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.core.workflow.{InputPort, OutputPort, PortIdentity}
-import org.apache.texera.amber.operator.PythonOperatorDescriptor
+import org.apache.texera.amber.operator.{PythonOperatorDescriptor, StandaloneCodeGenerator}
 import org.apache.texera.amber.operator.sklearn.SklearnFittableColumns
 import org.apache.texera.amber.operator.metadata.annotations.{
   AutofillAttributeName,
@@ -31,9 +31,15 @@ import org.apache.texera.amber.operator.metadata.annotations.{
 }
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
 import org.apache.texera.amber.pybuilder.PyStringTypes.EncodableString
-import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.{
+  PythonTemplateBuilderStringContext,
+  pyStringLiteral
+}
 
-class SklearnTestingOpDesc extends PythonOperatorDescriptor with SklearnFittableColumns {
+class SklearnTestingOpDesc
+    extends PythonOperatorDescriptor
+    with StandaloneCodeGenerator
+    with SklearnFittableColumns {
   @JsonProperty(required = true, defaultValue = "false")
   @JsonSchemaTitle("Regression")
   @JsonPropertyDescription(
@@ -118,4 +124,28 @@ class SklearnTestingOpDesc extends PythonOperatorDescriptor with SklearnFittable
             _.add(_, AttributeType.DOUBLE)
           )
     )
+
+  override def generateStandaloneCode(): String = {
+    val isRegressionStr = if (isRegression) "True" else "False"
+    val modelLit = pyStringLiteral(model)
+    val targetLit = pyStringLiteral(target)
+    s"""from sklearn.metrics import accuracy_score, f1_score, precision_score, recall_score, root_mean_squared_error, mean_absolute_error, r2_score
+       |
+       |model = in1df[$modelLit].iloc[0]
+       |out1df = in1df.copy()
+       |Y = in2df[$targetLit]
+       |X = in2df.drop($targetLit, axis=1)
+       |${narrowToFittableColumns("X", "")}
+       |predictions = model.predict(X.squeeze())
+       |if $isRegressionStr:
+       |    out1df["R2"] = r2_score(Y, predictions)
+       |    out1df["RMSE"] = root_mean_squared_error(Y, predictions)
+       |    out1df["MAE"] = mean_absolute_error(Y, predictions)
+       |else:
+       |    out1df["accuracy"] = round(accuracy_score(Y, predictions), 4)
+       |    out1df["f1"] = f1_score(Y, predictions, average="weighted")
+       |    out1df["precision"] = precision_score(Y, predictions, average="weighted")
+       |    out1df["recall"] = recall_score(Y, predictions, average="weighted")""".stripMargin
+  }
+
 }
diff --git a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingOpDesc.scala b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingOpDesc.scala
index c51f322a628..9dab7c27b56 100644
--- a/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingOpDesc.scala
+++ b/common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/sklearn/training/SklearnTrainingOpDesc.scala
@@ -19,12 +19,14 @@
 
 package org.apache.texera.amber.operator.sklearn.training
 
+import org.apache.texera.amber.operator.StandaloneCodeGenerator
 import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.pyStringLiteral
 import org.apache.texera.amber.core.workflow.{InputPort, OutputPort, PortIdentity}
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
 import org.apache.texera.amber.operator.sklearn.SklearnModelOpDesc
 
-class SklearnTrainingOpDesc extends SklearnModelOpDesc {
+class SklearnTrainingOpDesc extends SklearnModelOpDesc with StandaloneCodeGenerator {
 
   override def getImportStatements = ""
 
@@ -64,4 +66,30 @@ $reportMissingKept
       inputPorts = List(InputPort(PortIdentity(), "training")),
       outputPorts = List(OutputPort(blocking = true))
     )
+
+  override def generateStandaloneCode(): String = {
+    val estimator = getImportStatements.split(" ").last
+    val tfidfPart = if (tfidfTransformer) "TfidfTransformer()," else ""
+    val targetLit = pyStringLiteral(target)
+    val modelNameLit = pyStringLiteral(getUserFriendlyModelName)
+    val narrowX = dropNonFeatureColumns("X", "")
+
+    s"""${getImportStatements}
+       |from sklearn.pipeline import make_pipeline
+       |from sklearn.compose import ColumnTransformer
+       |from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
+       |import pandas as pd
+       |
+       |# The same rows the operator drops. A local name rather than a
+       |# reassignment, since the input variable belongs to whichever operator
+       |# produced it.
+       |_train = ${dropMissingRowsStandalone("in1df")}
+       |if len(_train) < len(in1df):
+       |    print("Skipped", len(in1df) - len(_train), "of", len(in1df), "rows with missing values")
+       |Y = _train[$targetLit]
+       |X = _train.drop($targetLit, axis=1)
+       |$narrowX
+       |model = make_pipeline(${vectorizerStage(c => pyStringLiteral(c))}$tfidfPart$estimator()).fit(X, Y)
+       |out1df = pd.DataFrame([{"model_name": $modelNameLit, "model": model}])""".stripMargin
+  }
 }
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..730be48ef50 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
@@ -19,6 +19,7 @@
 
 package org.apache.texera.amber.operator.huggingFace
 
+import com.kjetland.jackson.jsonSchema.annotations.JsonSchemaInject
 import org.apache.texera.amber.core.executor.OpExecWithCode
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.core.virtualidentity.{ExecutionIdentity, WorkflowIdentity}
@@ -105,6 +106,16 @@ 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()
@@ -128,4 +139,18 @@ class HuggingFaceIrisLogisticRegressionOpDescSpec extends AnyFlatSpec with Match
     h.predictionClassName shouldBe "species"
     h.predictionProbabilityName shouldBe "probability"
   }
+
+  "HuggingFaceIrisLogisticRegressionOpDesc (class-level)" should
+    "carry @JsonSchemaInject restricting both petal columns to numeric attributes" in {
+    val ann =
+      classOf[HuggingFaceIrisLogisticRegressionOpDesc].getAnnotation(classOf[JsonSchemaInject])
+    ann should not be null
+    val payload = ann.json
+    payload should include("attributeTypeRules")
+    payload should include("petalLengthCmAttribute")
+    payload should include("petalWidthCmAttribute")
+    payload should include("integer")
+    payload should include("long")
+    payload should include("double")
+  }
 }
diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSentimentAnalysisOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSentimentAnalysisOpDescSpec.scala
index 65401d58322..cdcf5de139c 100644
--- a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSentimentAnalysisOpDescSpec.scala
+++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSentimentAnalysisOpDescSpec.scala
@@ -19,6 +19,7 @@
 
 package org.apache.texera.amber.operator.huggingFace
 
+import com.kjetland.jackson.jsonSchema.annotations.JsonSchemaInject
 import org.apache.texera.amber.core.executor.OpExecWithCode
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.core.virtualidentity.{ExecutionIdentity, WorkflowIdentity}
@@ -212,4 +213,14 @@ class HuggingFaceSentimentAnalysisOpDescSpec extends AnyFlatSpec with Matchers {
     h.resultAttributeNeutral shouldBe "neu"
     h.resultAttributeNegative shouldBe "neg"
   }
+
+  "HuggingFaceSentimentAnalysisOpDesc (class-level)" should
+    "carry @JsonSchemaInject restricting `attribute` to STRING columns" in {
+    val ann = classOf[HuggingFaceSentimentAnalysisOpDesc].getAnnotation(classOf[JsonSchemaInject])
+    ann should not be null
+    val payload = ann.json
+    payload should include("attributeTypeRules")
+    payload should include("attribute")
+    payload should include("string")
+  }
 }
diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSpamSMSDetectionOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSpamSMSDetectionOpDescSpec.scala
index f7d39d7beb5..e13d7e2fd41 100644
--- a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSpamSMSDetectionOpDescSpec.scala
+++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSpamSMSDetectionOpDescSpec.scala
@@ -19,6 +19,7 @@
 
 package org.apache.texera.amber.operator.huggingFace
 
+import com.kjetland.jackson.jsonSchema.annotations.JsonSchemaInject
 import org.apache.texera.amber.core.executor.OpExecWithCode
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.core.virtualidentity.{ExecutionIdentity, WorkflowIdentity}
@@ -131,4 +132,14 @@ class HuggingFaceSpamSMSDetectionOpDescSpec extends AnyFlatSpec with Matchers {
     h.resultAttributeSpam shouldBe "is_spam"
     h.resultAttributeProbability shouldBe "score"
   }
+
+  "HuggingFaceSpamSMSDetectionOpDesc (class-level)" should
+    "carry @JsonSchemaInject restricting `attribute` to STRING columns" in {
+    val ann = classOf[HuggingFaceSpamSMSDetectionOpDesc].getAnnotation(classOf[JsonSchemaInject])
+    ann should not be null
+    val payload = ann.json
+    payload should include("attributeTypeRules")
+    payload should include("attribute")
+    payload should include("string")
+  }
 }
diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceTextSummarizationOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceTextSummarizationOpDescSpec.scala
index 1c4f3e0d8ba..03bb5e44f66 100644
--- a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceTextSummarizationOpDescSpec.scala
+++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceTextSummarizationOpDescSpec.scala
@@ -19,6 +19,7 @@
 
 package org.apache.texera.amber.operator.huggingFace
 
+import com.kjetland.jackson.jsonSchema.annotations.JsonSchemaInject
 import org.apache.texera.amber.core.executor.OpExecWithCode
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
 import org.apache.texera.amber.core.virtualidentity.{ExecutionIdentity, WorkflowIdentity}
@@ -135,4 +136,14 @@ class HuggingFaceTextSummarizationOpDescSpec extends AnyFlatSpec with Matchers {
     h.attribute shouldBe "text"
     h.resultAttribute shouldBe "summary"
   }
+
+  "HuggingFaceTextSummarizationOpDesc (class-level)" should
+    "carry @JsonSchemaInject restricting `attribute` to STRING columns" in {
+    val ann = classOf[HuggingFaceTextSummarizationOpDesc].getAnnotation(classOf[JsonSchemaInject])
+    ann should not be null
+    val payload = ann.json
+    payload should include("attributeTypeRules")
+    payload should include("attribute")
+    payload should include("string")
+  }
 }
diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearRegressionOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearRegressionOpDescSpec.scala
index d0364e19985..92a0ebac6e9 100644
--- a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearRegressionOpDescSpec.scala
+++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnLinearRegressionOpDescSpec.scala
@@ -95,6 +95,19 @@ class SklearnLinearRegressionOpDescSpec extends AnyFlatSpec with Matchers {
     code should include("No column left to fit on")
   }
 
+  // Both frames, since the model is fitted on one and scored on the other: a
+  // narrowing on only one side hands `predict` a different feature set.
+  "SklearnLinearRegressionOpDesc.generateStandaloneCode" should
+    "narrow both the training and the testing features" in {
+    val d = new SklearnLinearRegressionOpDesc
+    d.target = "y"
+    val code = d.generateStandaloneCode()
+    code should include("""_fittable = X_train.select_dtypes(include=["number", "bool"])""")
+    code should include("X_train = _fittable")
+    code should include("""_fittable = X_test.select_dtypes(include=["number", "bool"])""")
+    code should include("X_test = _fittable")
+  }
+
   "SklearnLinearRegressionOpDesc" should
     "round-trip its target through the polymorphic base" in {
     val d = new SklearnLinearRegressionOpDesc
diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnModelOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnModelOpDescSpec.scala
index 127ddabaec6..1ab28a78fb9 100644
--- a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnModelOpDescSpec.scala
+++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnModelOpDescSpec.scala
@@ -142,4 +142,32 @@ class SklearnModelOpDescSpec extends AnyFlatSpec with Matchers {
     }
     d.getOutputSchemas(Map.empty).keySet shouldBe Set(d.operatorInfo.outputPorts.head.id)
   }
+
+  it should "reject the target named as a text column" in {
+    val d = new TestSklearnModelOpDesc
+    d.countVectorizer = true
+    d.target = "species"
+    d.text = List("note", "species")
+    val thrown = intercept[RuntimeException](d.getOutputSchemas(Map.empty))
+    thrown.getMessage should include("species")
+    thrown.getMessage should include("Target Attribute")
+    thrown.getMessage should include("Text Attribute")
+  }
+
+  it should "let the text columns through while none of them is the target" in {
+    val d = new TestSklearnModelOpDesc
+    d.countVectorizer = true
+    d.target = "species"
+    d.text = List("note")
+    d.getOutputSchemas(Map.empty).keySet shouldBe Set(d.operatorInfo.outputPorts.head.id)
+  }
+
+  it should "leave a stale text column alone while Count Vectorizer is off" in {
+    // Nothing reads `text` with the switch off, and the panel hides it, so a value
+    // left behind by an earlier configuration must not report the operator invalid.
+    val d = new TestSklearnModelOpDesc
+    d.target = "species"
+    d.text = List("species")
+    d.getOutputSchemas(Map.empty).keySet shouldBe Set(d.operatorInfo.outputPorts.head.id)
+  }
 }
diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnPredictionOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnPredictionOpDescSpec.scala
index 16aec5da13d..5c7cf9b5167 100644
--- a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnPredictionOpDescSpec.scala
+++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/SklearnPredictionOpDescSpec.scala
@@ -148,10 +148,25 @@ class SklearnPredictionOpDescSpec extends AnyFlatSpec with Matchers {
     d.model = "model"
     d.resultAttribute = "prediction"
     d.groundTruthAttribute = "y"
-    val code = d.generatePythonCode()
+    Seq(d.generatePythonCode(), d.generateStandaloneCode()).foreach { code =>
+      code should include(""""feature_names_in_", None)""")
+      code should include("if _fitted is not None:")
+    }
+    // The two paths narrow with different expressions: this one holds a Tuple,
+    // the standalone one a frame.
+    d.generatePythonCode() should include("input_features.get_partial_tuple(list(_fitted))")
+  }
+
+  // The branch that names no ground truth predicts on the whole frame, so it needs
+  // the same narrowing as the one that drops a column first.
+  it should "narrow the features with no ground-truth column configured too" in {
+    val d = new SklearnPredictionOpDesc
+    d.model = "model"
+    d.resultAttribute = "prediction"
+    d.groundTruthAttribute = ""
+    val code = d.generateStandaloneCode()
     code should include(""""feature_names_in_", None)""")
-    code should include("if _fitted is not None:")
-    code should include("input_features.get_partial_tuple(list(_fitted))")
+    code should include("X = X[list(_fitted)]")
   }
 
   "SklearnPredictionOpDesc" should
diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/testing/SklearnTestingOpDescSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/testing/SklearnTestingOpDescSpec.scala
index 8401c6e20b8..52b2ad72c8c 100644
--- a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/testing/SklearnTestingOpDescSpec.scala
+++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/sklearn/testing/SklearnTestingOpDescSpec.scala
@@ -70,6 +70,20 @@ class SklearnTestingOpDescSpec extends AnyFlatSpec with Matchers {
     schema.getAttribute("MAE").getType shouldBe AttributeType.DOUBLE
   }
 
+  // The scorer reads every column but the target, so it has to leave out what an
+  // estimator cannot fit for the same reason the fitting operators do, and leave
+  // out the same columns: a model fitted without them refuses a frame naming them.
+  "SklearnTestingOpDesc" should "narrow the features to the columns an estimator can fit" in {
+    val d = new SklearnTestingOpDesc
+    d.model = "model"
+    d.target = "y"
+    Seq(d.generatePythonCode(), d.generateStandaloneCode()).foreach { code =>
+      code should include("""_fittable = X.select_dtypes(include=["number", "bool"])""")
+      code should include("""print("Ignoring columns an estimator cannot fit:", _ignored)""")
+      code should include("X = _fittable")
+    }
+  }
+
   "SklearnTestingOpDesc.generatePythonCode" should "emit the scorer tuple operator" in {
     val d = new SklearnTestingOpDesc
     d.model = "model"