Answer-first summary for fast verification
Answer: Connect the output of the Apply SQL Transformation to the Web Service Output module., Add a Select Columns module before the Score Model module to select all columns other than price., Remove the Apply Math Operation module that replaces price with its natural log from the data flow.
The question requires modifying the inference pipeline to: (1) return the exponential of the scored label as the predicted price, and (2) ensure client applications don't need to include a price value in inputs. In the training pipeline, the model predicts ln(price), so the inference pipeline must transform the scored label (ln(price)) back to the actual price using exponentiation. Option A connects the Apply SQL Transformation (which likely computes the exponential) to the Web Service Output, ensuring the final output is the predicted price. Option C adds a Select Columns module to exclude the price column before scoring, as the model doesn't need the target variable during inference, and clients shouldn't provide it. Option E removes the Apply Math Operation that computes ln(price) from the data flow because the input data from clients won't include the price column, making this transformation unnecessary and potentially causing errors. Other options are less suitable: B and D involve replacing data inputs, which is impractical in a real-time inference pipeline where inputs come from clients; F removes the SQL transformation, which is needed to compute the exponential of the scored label. The community discussion supports ACE, with 62% consensus and reasoning that D is incorrect as inference pipelines don't use training datasets, and C effectively achieves the same goal by filtering columns.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
You create a pipeline in Azure Machine Learning designer to train a model that predicts automobile prices. Due to non-linear relationships in the data, the pipeline computes the natural logarithm (ln) of the prices in the training data, trains a model to predict this ln(price) value, and then calculates the exponential of the scored label to produce the predicted price.
The training pipeline is shown in the exhibit under the "Training pipeline" tab.
You create a real-time inference pipeline from this training pipeline, shown in the exhibit under the "Real-time pipeline" tab.
You need to modify the inference pipeline so that the web service returns the exponential of the scored label as the predicted automobile price, and so that client applications are not required to include a price value in the input data.
Which three modifications must you make to the inference pipeline? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.
A
Connect the output of the Apply SQL Transformation to the Web Service Output module.
B
Replace the Web Service Input module with a data input that does not include the price column.
C
Add a Select Columns module before the Score Model module to select all columns other than price.
D
Replace the training dataset module with a data input that does not include the price column.
E
Remove the Apply Math Operation module that replaces price with its natural log from the data flow.
F
Remove the Apply SQL Transformation module from the data flow.