Page Reader AI | Exam Professional Machine Learning Engineer topic 1 question 263 discussion

Exam Professional Machine Learning Engineer topic 1 question 263 discussion - ExamTopics

AI Summary Hide AI Generated Summary

Problem Description

The problem involves developing a TensorFlow classification model using tabular data stored in BigQuery. The data contains hundreds of millions of rows with both categorical and numerical features. The goal is to efficiently scale numerical features using MaxMin scaling and apply one-hot encoding to categorical features (like SKU names) while minimizing cost and effort.

Proposed Solutions

Four solutions are presented:

A: Create a separate lookup table for scaling (SQL), use a Hugging Face model in BigQuery for encoding, then feed into Vertex AI Training.
B: Use BigQuery for scaling, feed features to Vertex AI Training, and let TensorFlow handle one-hot encoding.
C: Use TFX components with Dataflow for encoding and scaling, export to Cloud Storage as TFRecords, then feed into Vertex AI Training.
D: Use SQL to create a lookup table for scaling, perform one-hot encoding in BigQuery, and feed into Vertex AI Training.

Suggested Solution

The suggested answer is C. This approach leverages TFX and Dataflow for efficient data preprocessing at scale before training the model on Vertex AI.

You are developing a custom TensorFlow classification model based on tabular data. Your raw data is stored in BigQuery. contains hundreds of millions of rows, and includes both categorical and numerical features. You need to use a MaxMin scaler on some numerical features, and apply a one-hot encoding to some categorical features such as SKU names. Your model will be trained over multiple epochs. You want to minimize the effort and cost of your solution. What should you do?

A. 1. Write a SQL query to create a separate lookup table to scale the numerical features. 2. Deploy a TensorFlow-based model from Hugging Face to BigQuery to encode the text features. 3. Feed the resulting BigQuery view into Vertex AI Training.
B. 1. Use BigQuery to scale the numerical features. 2. Feed the features into Vertex AI Training. 3. Allow TensorFlow to perform the one-hot text encoding.
C. 1. Use TFX components with Dataflow to encode the text features and scale the numerical features. 2. Export results to Cloud Storage as TFRecords. 3. Feed the data into Vertex AI Training.
D. 1. Write a SQL query to create a separate lookup table to scale the numerical features. 2. Perform the one-hot text encoding in BigQuery. 3. Feed the resulting BigQuery view into Vertex AI Training.

Show Suggested Answer Hide Answer

Was this article displayed correctly? Not happy with what you see?

See Archived Versions