Google Exam Professional Data Engineer Topic 1 Question 84 Discussion

Actual exam question for Google's Professional Data Engineer exam

Question #: 84
Topic #: 1

[All Professional Data Engineer Questions]

You work for a large real estate firm and are preparing 6 TB of home sales data lo be used for machine learning You will use SOL to transform the data and use BigQuery ML lo create a machine learning model. You plan to use the model for predictions against a raw dataset that has not been transformed. How should you set up your workflow in order to prevent skew at prediction time?

AWhen creating your model, use BigQuerys TRANSFORM clause to define preprocessing stops. At prediction time, use BigQuery's ML. EVALUATE clause without specifying any transformations on the raw input data.

BWhen creating your model, use BigQuery's TRANSFORM clause to define preprocessing steps Before requesting predictions, use a saved query to transform your raw input data, and then use ML. EVALUATE

CUse a BigOuery to define your preprocessing logic. When creating your model, use the view as your model training data. At prediction lime, use BigQuery's ML EVALUATE clause without specifying any transformations on the raw input data.

DPreprocess all data using Dataflow. At prediction time, use BigOuery's ML. EVALUATE clause without specifying any further transformations on the input data.

Show Suggested Answer

Suggested Answer: A

https://cloud.google.com/bigquery-ml/docs/bigqueryml-transform Using the TRANSFORM clause, you can specify all preprocessing during model creation. The preprocessing is automatically applied during the prediction and evaluation phases of machine learning

by Catina at May 20, 2024, 04:40 AM

Limited Time Offer

25%

Off

Get Premium Professional Data Engineer Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Tonette

10 months ago

Whoa, hold up, this question's got me feeling like a real estate mogul! I'm gonna go with Option B and keep my data transformations consistent. Gotta stay on top of that skew, am I right?

upvoted 0 times

...

Teddy

10 months ago

Option A looks like the real estate agent's choice - let BigQuery do all the heavy lifting! But hey, if it works, it works, right?

upvoted 0 times

Ozell

9 months ago

C) Use a BigQuery to define your preprocessing logic. When creating your model, use the view as your model training data. At prediction time, use BigQuery's ML EVALUATE clause without specifying any transformations on the raw input data.

upvoted 0 times

...

Michell

9 months ago

B) When creating your model, use BigQuery's TRANSFORM clause to define preprocessing steps. Before requesting predictions, use a saved query to transform your raw input data, and then use ML. EVALUATE.

upvoted 0 times

...

Omega

9 months ago

A) When creating your model, use BigQuery's TRANSFORM clause to define preprocessing steps. At prediction time, use BigQuery's ML. EVALUATE clause without specifying any transformations on the raw input data.

upvoted 0 times

...

Tonette

10 months ago

Option D, for sure. Preprocessing everything in Dataflow and then letting BigQuery handle the predictions? That's the kind of workflow that keeps things clean and streamlined.

upvoted 0 times

Bette

9 months ago

I agree, using Dataflow for preprocessing and BigQuery for predictions seems like a solid workflow.

upvoted 0 times

...

Alyssa

10 months ago

Option D sounds like the best approach. Dataflow can handle the preprocessing efficiently.

upvoted 0 times

...

Twila

10 months ago

D) Preprocess all data using Dataflow. At prediction time, use BigQuery's ML. EVALUATE clause without specifying any further transformations on the input data.

upvoted 0 times

...

Hannah

10 months ago

I'm all about Option C. Using a view for the model training data and then just evaluating the raw input at prediction time? Now that's what I call efficiency.

upvoted 0 times

Kassandra

10 months ago

Definitely, it simplifies the process and reduces the risk of skew at prediction time.

upvoted 0 times

...

Vanna

10 months ago

I agree, it seems like a more efficient workflow. Just evaluate the raw input at prediction time.

upvoted 0 times

...

Ozell

10 months ago

Option C sounds like the way to go. Using a view for training data is a smart move.

upvoted 0 times

...

Janella

10 months ago

Option B is the way to go, my dude. Gotta make sure that the preprocessing steps are the same for both training and prediction to avoid that pesky skew.

upvoted 0 times

Derrick

9 months ago

B) Option B sounds solid. Consistency in preprocessing is key to avoiding skew in predictions.

upvoted 0 times

...

Paz

10 months ago

A) When creating your model, use BigQuery's TRANSFORM clause to define preprocessing steps Before requesting predictions, use a saved query to transform your raw input data, and then use ML. EVALUATE

upvoted 0 times

...

Annalee

10 months ago

B) Option B is definitely the best choice. Consistency in preprocessing steps is key to avoiding skew in predictions.

upvoted 0 times

...

Annabelle

10 months ago

Yeah, you're right. Consistency in preprocessing is key to accurate predictions.

upvoted 0 times

...

Glynda

10 months ago

A) When creating your model, use BigQuery's TRANSFORM clause to define preprocessing steps Before requesting predictions, use a saved query to transform your raw input data, and then use ML. EVALUATE

upvoted 0 times

...

Denae

10 months ago

Option B is the way to go, my dude. Gotta make sure that the preprocessing steps are the same for both training and prediction to avoid that pesky skew.

upvoted 0 times

...