MLA-C01 Data Preparation for Machine Learning Practice Test 5 — 15 Questions

Question 1

A machine learning engineer is using SageMaker Processing to run a scikit-learn preprocessing script. The script reads a CSV file from S3, applies a StandardScaler, and writes the output. The job fails with a 'MemoryError'. Which change should the engineer make to the data preparation process?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Increase the instance memory size for the processing job. The MemoryError indicates that the processing job's instance does not have enough RAM to hold the dataset and the intermediate results of the StandardScaler (which computes mean and variance in memory). Increasing the instance memory size (Option B) directly resolves this by providing more RAM for the scikit-learn operations. SageMaker Processing jobs allow you to choose instances with larger memory, such as the r5 or r6i families, to accommodate larger datasets.

Answer

Use a SageMaker Spark container instead of scikit-learn

Answer

Write the output as Parquet instead of CSV

Answer

Standardize the features before loading into the DataFrame

Question 2

A company uses AWS Glue to run ETL jobs that prepare data for machine learning. The source data in S3 has a schema that evolves over time (new columns are added occasionally). The Glue job schema is defined as a fixed schema in the job script. After an update to the source data, the Glue job fails with an error about mismatched schemas. How should the data engineer modify the data preparation process to handle schema evolution?

Accepted Answer

Modify the Glue job to use a dynamic frame and enable schema updates with a 'applyMapping' that includes new columns. AWS Glue DynamicFrames natively handle schema evolution by allowing you to apply a mapping that can include new columns. By using `applyMapping` with `resolveChoice`, you can define how to handle new fields (e.g., cast to a type or keep as a struct), preventing job failures when the source schema changes. This avoids the rigidity of a fixed schema in the job script.

Answer

Run a Glue crawler before each job to update the Data Catalog, but keep the fixed schema in the job

Answer

Store the schema definition in a separate file in S3 and read it at runtime

Answer

Manually update the Glue job script each time the schema changes

Question 3

A data scientist is using SageMaker Data Wrangler to prepare features for a classification model. Which TWO statements about feature engineering in Data Wrangler are correct?

Accepted Answer

Transformations created in Data Wrangler can be exported as a SageMaker Processing script. Option C is correct because Data Wrangler lets you export your data flow as a SageMaker Processing job, generating a Python script (using the SageMaker Processing SDK and the Data Wrangler processing container) that reproduces the transformations at scale. Option E is correct because Data Wrangler can export transformed features directly to an Amazon SageMaker Feature Store online and/or offline store, enabling feature reuse and consistency between training and inference. Option A is wrong because Data Wrangler supports many more sources than CSV and Parquet, including JSON, ORC, database sources via Athena/Redshift, and S3 data in various formats. Option B is wrong because Data Wrangler provides built-in transforms and a visual interface rather than allowing arbitrary custom PySpark transformations to be authored. Option D is wrong because Data Wrangler does not automatically scale features for XGBoost; scaling must be applied explicitly via transforms such as Standard Scaler or Min-Max Scaler.

Answer

Data Wrangler only supports CSV and Parquet input formats

Answer

Data Wrangler enables writing custom PySpark transformations

Answer

Data Wrangler automatically scales features for XGBoost models

Question 4

A team is building a machine learning model for natural language processing using SageMaker BlazingText. The data preparation step must format the training data correctly. What format does BlazingText require for supervised text classification?

Accepted Answer

Tokenized words separated by spaces, with text and labels combined in a single line (e.g., '__label__positive great product'). BlazingText for supervised text classification expects the training data in a specific format where each line contains the text and its labels, with labels prefixed by '__label__'. This format allows BlazingText to efficiently parse and process the data for training the word2vec or classification model without additional preprocessing. Option C correctly describes this format, where the label and text are space-separated on a single line.

Answer

One-hot encoded feature vectors stored in CSV

Answer

JSON lines with a 'text' and 'label' field

Answer

TFRecord files with sequence features

Question 5

A company uses Amazon SageMaker Ground Truth to create labeled datasets for object detection. The output must be in COCO format for downstream model training. How should the data preparation process be configured?

Accepted Answer

Select 'Object Detection' task type and specify 'COCO' as the output format in the labeling job configuration. Amazon SageMaker Ground Truth natively supports outputting object detection labeling jobs in COCO format. When you select 'Object Detection' as the task type, the labeling job configuration includes an option to specify 'COCO' as the output format, which automatically structures the labeled data into the required COCO JSON schema without any post-processing.

Answer

Use a built-in transformation to convert from Ground Truth JSON to COCO after labeling

Answer

Use a pre-built AWS Lambda function to transform annotations to COCO

Answer

Write a custom SageMaker Processing script to convert the output to COCO

Question 6

A machine learning engineer is using SageMaker Data Wrangler to perform data validation. Which step should be added to the pipeline to ensure data quality before training?

Accepted Answer

Apply a 'Data Quality' transformation in Data Wrangler to validate column statistics. SageMaker Data Wrangler includes a built-in 'Data Quality' transformation that allows you to validate column statistics (e.g., missing values, min/max, distinct counts) directly within the visual pipeline. This step ensures data quality without requiring custom code or external services, integrating seamlessly with the Data Wrangler workflow for pre-training validation.

Answer

Write a custom SageMaker Processing job for validation

Answer

Use AWS Glue DataBrew to profile the dataset

Answer

Add a SageMaker Pipeline step to check data quality after Data Wrangler

Question 7

Refer to the exhibit. A data engineer runs an AWS Glue ETL job with the following script portion. The job fails with an error: 'An error occurred while calling o113.pyWriteDynamicFrame. No such file or directory'. What is the most likely cause?

Accepted Answer

The output S3 path is missing a trailing slash. The error 'No such file or directory' when calling `pyWriteDynamicFrame` typically occurs because AWS Glue expects the output S3 path to end with a trailing slash to denote a directory. Without it, Glue may interpret the path as a file name rather than a directory, leading to a failure when attempting to write the Parquet files. Adding a trailing slash (e.g., `s3://bucket/output/`) resolves the issue.

Answer

The output format 'parquet' is not supported by Glue

Answer

The input partition path is incorrect because it includes the partition key

Answer

The schema contains a column with a reserved name

Question 8

Refer to the exhibit. A SageMaker Processing job fails with the following error log. Which change during data preparation would resolve the issue?

Accepted Answer

Modify the preprocessing script to cast 'age' to float using astype(float). The error log indicates a type mismatch when processing the 'age' column, likely due to mixed data types (e.g., strings and numbers) in a column expected to be numeric. By explicitly casting the column to float using astype(float) in the preprocessing script, you ensure consistent numeric type handling, which resolves the failure during SageMaker Processing job execution.

Answer

In SageMaker Data Wrangler, set the 'age' column type to 'number'

Answer

Drop rows with missing values in the 'age' column before training

Answer

Remove the 'age' column from the dataset entirely

Question 9

A data engineer is using SageMaker Pipelines to automate data preparation. Which TWO statements about data validation within a pipeline are correct?

Accepted Answer

The pipeline can be configured to fail if data quality checks do not meet thresholds. Option A is correct because SageMaker Pipelines supports conditional and quality-check steps whose conditions (e.g., a PropertyFile or JsonGet threshold on a quality metric) can be configured so the pipeline fails or stops when data quality checks do not meet the defined thresholds. Option B is correct because SageMaker Pipelines provides a built-in QualityCheck step (often surfaced as CheckDataQuality/DataQualityCheck via the SageMaker Model Monitor/Data Quality framework) that runs data validation against baseline statistics and constraints without requiring custom code. Option C is wrong because data validation can be applied to inference/endpoint data as well as training data, for example with Model Monitor monitoring live inference traffic. Option D is wrong because validation steps emit outputs such as statistics, constraints, and property files that subsequent pipeline steps can consume. Option E is wrong because data quality validation compares data against baselines/constraints and does not require a trained model to evaluate predictions.

Answer

Data validation can only be performed on training data, not inference data

Answer

Data validation steps cannot pass results to subsequent steps

Answer

Data validation requires a trained model to evaluate predictions

Question 10

A data engineer is using Amazon Athena to query a partitioned dataset stored in S3. Which THREE actions are necessary to ensure the queries can access the data and run efficiently?

Accepted Answer

Store the underlying data in a columnar format like Parquet. Option A is correct because storing data in a columnar format like Parquet lets Athena read only the columns referenced in a query, drastically reducing scanned bytes and improving performance and cost. Option D is correct because partition projection computes partition locations from table properties instead of relying on the Glue Data Catalog, so new partitions are queryable automatically without running DDL or repair commands. Option E is correct because MSCK REPAIR TABLE scans the S3 prefix and adds any existing Hive-style partitions to the metastore, making already-present partitions visible to Athena queries. Option B is not required because AWS Glue DataBrew is a visual data-preparation service for building transformation recipes, not a prerequisite for Athena to access or efficiently query partitioned S3 data. Option C is not necessary because manually adding every partition with ALTER TABLE ADD PARTITION is one valid approach, but it is not required when partition projection or MSCK REPAIR TABLE handles partition discovery, and the question asks for the necessary actions.

Answer

Create an AWS Glue DataBrew recipe to transform the data

Answer

Add each partition manually using ALTER TABLE ADD PARTITION

Question 11

A company operates an IoT platform that ingests sensor data from thousands of devices. Data is streamed via Amazon Kinesis Data Streams and stored in an S3 bucket using a Kinesis Firehose delivery stream, which writes data in 5-minute windows. The data is then used to train a machine learning model for anomaly detection. Recently, the data science team noticed that the training dataset is always missing the last 5 minutes of events from the end of each day. The S3 objects show that the last delivery stream buffer window is incomplete. The data engineer checked the Kinesis Firehose metrics and found no delivery errors or data loss, but the 'IncomingBytes' and 'IncomingRecords' metrics show consistent data for all periods. The S3 bucket has Lifecycle policies that do not delete objects. The team suspects the issue is related to the data preparation pipeline. Which course of action would correctly resolve the missing data problem?

Accepted Answer

Increase the buffer size to 10 MB and reduce the buffer interval to 60 seconds in the Firehose delivery stream configuration. The issue is that the last 5-minute buffer window at the end of each day never completes, so Firehose never delivers that final object to S3. By reducing the buffer interval to 60 seconds and increasing the buffer size to 10 MB, Firehose will flush data more frequently, ensuring that even small residual data at the end of the day is delivered before the stream stops. This directly addresses the incomplete last window without requiring reprocessing or changing the pipeline architecture.

Answer

Reprocess the Kinesis stream data from the beginning using a custom application

Answer

Modify the data preparation pipeline to use AWS Lambda to write data to S3 directly from Kinesis

Answer

Increase the buffer interval to 600 seconds to allow more time for data to accumulate

Question 12

A data scientist is preparing a dataset for a binary classification model to predict customer churn. The dataset contains a timestamp column 'signup_date' that is not relevant for the prediction. What is the most appropriate action to handle this column?

Accepted Answer

Drop the 'signup_date' column from the dataset.. The 'signup_date' column is explicitly stated as not relevant for the prediction. In binary classification for customer churn, including an irrelevant timestamp can introduce noise, increase dimensionality, and potentially cause overfitting. Dropping the column is the most appropriate action to maintain model simplicity and focus on predictive features.

Answer

Apply one-hot encoding to the year, month, and day components.

Answer

Convert the timestamp to a numeric feature (e.g., days since signup) and include it.

Answer

Use leave-one-out encoding based on the target variable.

Question 13

A machine learning engineer is building a regression model to predict house prices. The feature 'square_footage' has values ranging from 500 to 10,000, while 'num_bedrooms' ranges from 1 to 10. Which preprocessing step is most critical before training a model that uses gradient descent?

Accepted Answer

Standardize both features to have zero mean and unit variance.. Gradient descent is sensitive to the scale of features because it updates weights proportionally to the feature values. With 'square_footage' (500–10,000) and 'num_bedrooms' (1–10), the large range difference causes the loss function's contours to be elongated, leading to slow or unstable convergence. Standardizing both features to zero mean and unit variance ensures each feature contributes equally to the gradient updates, enabling faster and more reliable optimization.

Answer

Apply a logarithmic transformation to both features.

Answer

Encode the 'num_bedrooms' feature using one-hot encoding.

Answer

Impute missing values using the mean of the feature.

Question 14

A company uses Amazon SageMaker Data Wrangler to create a data flow for a classification model. The dataset contains a high-cardinality categorical feature 'product_id' with 50,000 unique values. The data scientist wants to reduce dimensionality while preserving predictive power. Which approach is most effective?

Accepted Answer

Perform target encoding by replacing each product ID with the average target value for that product.. Target encoding is the most effective approach for high-cardinality categorical features because it replaces each category with the mean of the target variable, preserving predictive signal while drastically reducing dimensionality. In SageMaker Data Wrangler, this can be implemented using the 'Encode categorical' transform with the 'Target encoding' option, which avoids the explosion of features caused by one-hot encoding and retains the relationship between product IDs and the target.

Answer

Apply one-hot encoding to the 'product_id' column.

Answer

Use feature hashing to map product IDs to a fixed number of buckets (e.g., 100).

Answer

Drop the 'product_id' column entirely.

Question 15

A data science team is building a model to predict fraudulent transactions. The dataset has 1 million legitimate transactions and only 1,000 fraudulent ones. They plan to use Amazon SageMaker to train a model. Which data preparation technique should they apply to address the severe class imbalance before training?

Accepted Answer

Use SMOTE (Synthetic Minority Oversampling Technique) to generate synthetic fraudulent samples.. SMOTE (Synthetic Minority Oversampling Technique) is the correct choice because it generates synthetic fraudulent samples by interpolating between existing minority class instances in feature space, rather than simply duplicating records. This creates more diverse and realistic training data, reducing overfitting risk while addressing the severe 1:1000 class imbalance. Amazon SageMaker's built-in algorithms and data processing capabilities can easily integrate SMOTE-applied datasets for training.

Answer

Apply data augmentation using image transformations because fraud detection is like image classification.

Answer

Randomly oversample the fraudulent class to match the legitimate count by duplicating existing fraud records.

Answer

Randomly undersample the legitimate class to 1,000 samples to create a balanced dataset.