Answer-first summary for fast verification
Answer: Add a Select Columns in Dataset module to the inference pipeline after the dataset and use it to select all columns other than the label.
Option A is correct because adding a Select Columns in Dataset module after the dataset in the inference pipeline allows you to explicitly exclude the label column from the input schema. This ensures that client applications only need to provide feature columns, not the predicted label. The community discussion shows 100% consensus on this answer with upvoted comments confirming its correctness. Option B is inefficient as it requires recreating the entire pipeline. Option C would break the pipeline by removing required input. Option D is impractical for real-time inference as it replaces the dataset with manual data entry, which defeats the purpose of a web service.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You create a training pipeline for a classification model in Azure Machine Learning designer. This pipeline uses a dataset containing both features and labels. After creating a real-time inference pipeline from this training pipeline, you observe that the web service input schema includes the label column that the model is designed to predict. Client applications using this web service must not be required to provide a value for this label column.
What should you do to modify the inference pipeline to meet this requirement?
A
Add a Select Columns in Dataset module to the inference pipeline after the dataset and use it to select all columns other than the label.
B
Delete the dataset from the training pipeline and recreate the real-time inference pipeline.
C
Delete the Web Service Input module from the inference pipeline.
D
Replace the dataset in the inference pipeline with an Enter Data Manually module that includes data for the feature columns but not the label column.
No comments yet.