nerdexam
Amazon

MLS-C01 · Question #334

A company uses sensors on devices such as motor engines and factory machines to measure parameters, temperature and pressure. The company wants to use the sensor data to predict equipment…

The correct answer is C. Use an Amazon SageMaker Data Wrangler anomaly detection visualization to find outliers in the. To efficiently find outliers in sensor data before training a model with the least operational overhead, the ML specialist should leverage Amazon SageMaker Data Wrangler's anomaly detection visualizations.

Exploratory Data Analysis

Question

A company uses sensors on devices such as motor engines and factory machines to measure parameters, temperature and pressure. The company wants to use the sensor data to predict equipment malfunctions and reduce services outages. Machine learning (ML) specialist needs to gather the sensors data to train a model to predict device malfunctions. The ML specialist must ensure that the data does not contain outliers before training the model. How can the ML specialist meet these requirements with the LEAST operational overhead?

Options

  • ALoad the data into an Amazon SageMaker Studio notebook. Calculate the first and third quartile.
  • BUse an Amazon SageMaker Data Wrangler bias report to find outliers in the dataset. Use a Data
  • CUse an Amazon SageMaker Data Wrangler anomaly detection visualization to find outliers in the
  • DUse Amazon Lookout for Equipment to find and remove outliers from the dataset.

How the community answered

(31 responses)
  • A
    3% (1)
  • B
    6% (2)
  • C
    74% (23)
  • D
    16% (5)

Why each option

To efficiently find outliers in sensor data before training a model with the least operational overhead, the ML specialist should leverage Amazon SageMaker Data Wrangler's anomaly detection visualizations.

ALoad the data into an Amazon SageMaker Studio notebook. Calculate the first and third quartile.

Loading data into a SageMaker Studio notebook and manually calculating quartiles requires writing custom code, which is not the 'least operational overhead' compared to a visual tool.

BUse an Amazon SageMaker Data Wrangler bias report to find outliers in the dataset. Use a Data

Amazon SageMaker Data Wrangler's bias reports are primarily designed to detect and mitigate bias in datasets, not for general-purpose outlier detection in sensor readings.

CUse an Amazon SageMaker Data Wrangler anomaly detection visualization to find outliers in theCorrect

Amazon SageMaker Data Wrangler provides built-in anomaly detection visualizations, offering a visual and low-code approach to quickly identify outliers in sensor data, which minimizes operational overhead compared to manual coding or using higher-level ML services.

DUse Amazon Lookout for Equipment to find and remove outliers from the dataset.

Amazon Lookout for Equipment is an end-to-end ML service for predicting equipment failures and anomalies; it trains its own models and is not primarily a data preparation tool for finding and removing outliers from a dataset for an external model being built by an ML specialist.

Concept tested: SageMaker Data Wrangler for outlier detection

Source: https://docs.aws.amazon.com/sagemaker/latest/dg/data-wrangler-insights.html#data-wrangler-insights-data-quality-summary

Topics

#Data Preprocessing#Outlier Detection#SageMaker Data Wrangler#Operational Overhead

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full MLS-C01 Practice