MLA-C01 Data Preparation for Machine Learning — Timed 25 Questions

Question 1

A company is using AWS Glue to prepare data for a machine learning pipeline. The source data is in an Amazon S3 bucket in CSV format. The data scientist wants to convert the data to Parquet format and partition it by date. Which AWS Glue feature should be used to optimize the data for query performance and reduce storage costs?

25 minute time limit — choose an answer to begin.

Accepted Answer

Use AWS Glue DynamicFrame to repartition the data and write it as Parquet.. AWS Glue DynamicFrames provide built-in optimizations for writing data in columnar formats like Parquet, which improves query performance through predicate pushdown and compression, and reduces storage costs by using efficient encoding. The DynamicFrame's `repartition()` method allows you to control the number of output files, and writing as Parquet directly from Glue avoids intermediate conversions, making it the most efficient choice for this task.

Answer

Use Amazon Athena to convert the data to JSON format and store it in S3.

Answer

Use AWS Glue to convert the data to Apache Hive format.

Answer

Use Apache Spark DataFrame to write the data as CSV with Snappy compression.

Question 2

A machine learning engineer is preparing a dataset for a binary classification model. The dataset has a severe class imbalance (95% class A, 5% class B). The engineer wants to use Amazon SageMaker to train the model. Which data preparation technique should the engineer apply to the training dataset to address the imbalance and improve model performance?

Accepted Answer

Apply Synthetic Minority Over-sampling Technique (SMOTE) to generate synthetic samples for the minority class.. SMOTE generates synthetic samples for the minority class by interpolating between existing minority instances, which directly addresses the severe class imbalance (95% class A, 5% class B) by creating a more balanced training dataset. This technique is particularly effective for tabular data in Amazon SageMaker, as it increases the representation of the minority class without simply duplicating existing samples, thereby reducing overfitting and improving the model's ability to learn decision boundaries for the minority class.

Answer

Apply data augmentation to the majority class by adding noise.

Answer

Use a weighted loss function during training to penalize misclassifications of the minority class.

Answer

Apply random under-sampling to reduce the majority class to match the minority class size.

Question 3

A company uses AWS Glue to run ETL jobs that prepare data for machine learning. The data is stored in Amazon S3 in Parquet format. A data engineer notices that the Glue job is running slowly and consuming a lot of resources. What is the MOST cost-effective way to improve the performance of the Glue job?

Accepted Answer

Use the G.1X worker type, which provides more memory per worker compared to the Standard worker type.. Increasing the number of DPUs (Data Processing Units) in AWS Glue can improve parallelism and reduce job runtime, but it increases cost. Using G.1X worker type with more memory per worker can improve performance without increasing DPU count, offering better resource utilization. Switching to CSV may degrade performance. Using partition pruning on the source data can reduce data scanned but may not address resource consumption.

Answer

Use partition pruning on the source data to reduce the amount of data processed.

Answer

Switch the output format from Parquet to CSV to reduce processing overhead.

Answer

Use a larger instance type for the Glue job by increasing the number of DPUs.

Question 4

A machine learning team is building a model using a dataset that contains a mix of numerical and categorical features. The categorical features have high cardinality (e.g., zip code with thousands of unique values). The team wants to use Amazon SageMaker for training. Which technique should the team use to encode the high-cardinality categorical features effectively?

Accepted Answer

Apply target encoding (mean encoding) to the high-cardinality features.. Target encoding replaces each high-cardinality category with a statistic (typically the mean of the target) computed from the training data, which compresses thousands of zip codes into a single informative numeric feature without exploding dimensionality. It is the standard SageMaker-recommended approach for high-cardinality categoricals because it preserves predictive signal while keeping the feature space small.

Answer

Apply hash encoding to map categories to a fixed number of buckets.

Answer

Apply one-hot encoding to all categorical features.

Answer

Apply label encoding to assign integer values to each category.

Question 5

A machine learning team is preparing a dataset for a regression model. The dataset contains numerical features that are on different scales (e.g., age 0-100, income 0-1,000,000). The team plans to use Amazon SageMaker to train a linear regression model. Which THREE data preparation steps should the team take to ensure the model performs well? (Select THREE.)

Accepted Answer

Handle missing values by imputation or removal.. Option C is correct because missing values in a dataset will cause errors or bias in SageMaker linear regression training, so imputing them (e.g., mean/median) or removing affected rows ensures a complete numeric matrix for the algorithm. Option D is correct because linear regression in SageMaker requires all input features to be numeric, so any categorical variables must be converted via one-hot encoding (or similar numeric encoding) before training. Option E is correct because the scenario explicitly states features are on very different scales (age 0-100 vs. income 0-1,000,000); standardization (z-score) or min-max normalization puts them on comparable scales, which improves convergence and coefficient stability for linear regression. Option A is not required: feature selection can help reduce overfitting or dimensionality, but it is not a mandatory preparation step to make linear regression perform well with differently scaled numeric features. Option B is not required: outlier removal can be beneficial in some cases, but it is not a necessary data preparation step for the stated goal and may discard valid data; the question asks for steps the team should take to ensure good performance, and scaling, missing-value handling, and numeric encoding are the essential ones.

Answer

Apply feature selection to reduce the number of features.

Answer

Remove outliers from the dataset.

Question 6

A data scientist is using Amazon SageMaker Data Wrangler to create a data flow for a machine learning project. The source data is in Amazon S3 and contains PII (personally identifiable information) such as email addresses and credit card numbers. The data scientist needs to prepare the data for training while ensuring compliance with data privacy regulations. Which THREE actions should the data scientist take? (Select THREE.)

Accepted Answer

Use Data Wrangler to redact or remove PII columns from the dataset before training.. Option B is correct because SageMaker Data Wrangler provides built-in transforms (such as 'Drop column' or redaction/obfuscation transforms) that let the data scientist remove or mask PII columns like email addresses and credit card numbers before the data reaches training, directly satisfying data minimization requirements under privacy regulations. Option E is correct because Data Wrangler supports anonymization transforms such as hashing (e.g., SHA-256 via the 'Encode categorical' or custom Pandas/PySpark transform) to irreversibly pseudonymize PII while preserving the column for model utility, which is a standard privacy-preserving technique. Option D is correct because writing the prepared output to an S3 bucket with server-side encryption (SSE-S3, SSE-KMS, or SSE-C) protects the data at rest and is a required control for handling sensitive data under regulations such as GDPR, HIPAA, or PCI DSS. Option A is incorrect because relying on the model not to memorize PII is not a compliant control—models can and do memorize training data, and raw PII in training sets violates data minimization and privacy requirements. Option C is incorrect because copying data to another bucket without any transformation neither removes nor protects the PII, so it does nothing to achieve compliance.

Answer

Include the raw PII in the training dataset and rely on the model to not memorize it.

Answer

Use AWS Glue to copy the data to a separate bucket without any transformations.

Question 7

A data scientist is preparing a large dataset for training a binary classification model. The dataset has a severe class imbalance (95% negative, 5% positive). Which data preparation technique should the scientist use to address this imbalance without losing too much data?

Accepted Answer

SMOTE (Synthetic Minority Over-sampling Technique). SMOTE (Synthetic Minority Over-sampling Technique) is the best choice because it generates synthetic examples for the minority class by interpolating between existing minority instances and their k-nearest neighbors, rather than simply duplicating data. This addresses the severe 95:5 class imbalance without losing data (as undersampling would) and without the overfitting risk of naive random oversampling. The synthetic samples help the model learn a more general decision boundary for the positive class.

Answer

Random undersampling of the majority class

Answer

Random oversampling of the minority class

Answer

Apply class weights during model training

Question 8

A machine learning engineer is preparing a dataset that contains both numerical and categorical features. The categorical features have high cardinality (e.g., zip code with thousands of unique values). Which technique is most appropriate for encoding these high-cardinality categorical features?

Accepted Answer

Target encoding. Target encoding is the most appropriate technique for high-cardinality categorical features because it replaces each category with the mean of the target variable for that category, effectively capturing the predictive signal while keeping the feature as a single numeric column. This avoids the dimensionality explosion of one-hot encoding and the arbitrary ordinality of label encoding, making it a common choice in gradient boosting frameworks like XGBoost or LightGBM for datasets with thousands of unique categories.

Answer

Label encoding

Answer

One-hot encoding

Answer

Frequency encoding

Question 9

A team is building a regression model on a dataset with missing values in multiple features. They decide to use a k-Nearest Neighbors (k-NN) imputer. The dataset has 100,000 rows and 50 features. Which step should the team take to ensure the imputation is efficient and accurate?

Accepted Answer

Standardize the features before applying k-NN imputation. Standardizing features before applying k-NN imputation is critical because k-NN relies on distance calculations (e.g., Euclidean distance). If features are on different scales (e.g., one feature ranges 0–1 and another 0–100,000), the distance metric will be dominated by the larger-scale feature, leading to biased neighbor selection and inaccurate imputation. Standardization (e.g., z-score scaling) ensures each feature contributes equally to the distance computation, improving both efficiency and accuracy.

Answer

Set k=1 to minimize bias

Answer

Use all 100,000 rows to find neighbors for each missing value

Answer

Use only the feature with missing values to find neighbors

Question 10

A data engineer is using Amazon SageMaker Data Wrangler to prepare a dataset. The dataset contains a column 'review_date' with timestamps. The engineer wants to extract the day of the week as a new feature. How should this transformation be performed in Data Wrangler?

Accepted Answer

Use the 'day_of_week' transform on the 'review_date' column. Amazon SageMaker Data Wrangler includes a built-in 'day_of_week' transform that directly extracts the day of the week (e.g., Monday, Tuesday) from a timestamp column without requiring custom code or additional formatting. This transform is optimized for Data Wrangler's visual interface and integrates seamlessly with its processing pipeline.

Answer

Write a custom Python script using pandas dt.day_name()

Answer

Use one-hot encoding on the timestamp

Answer

Use the 'extract' transform with format '%A'

Question 11

A data scientist is working on a time series forecasting problem. The dataset contains a column 'sales' with occasional negative values due to returns. The model expects non-negative input. Which data preparation step should be taken?

Accepted Answer

Clip negative sales values to zero. Clipping negative sales values to zero directly addresses the model's requirement for non-negative input while preserving the data's temporal structure. This approach is appropriate for time series forecasting where returns cause occasional negative values, as it treats returns as zero sales rather than removing or distorting the data points.

Answer

Apply log transformation after adding a constant

Answer

Remove all rows with negative sales values

Answer

Impute negative values with the mean

Question 12

A machine learning engineer is preparing a dataset for a multiclass classification task. The dataset has 10 features and 100,000 rows. Which TWO techniques should the engineer use to reduce the risk of overfitting during data preparation?

Accepted Answer

Data augmentation (e.g., adding noise). Option A (Data augmentation, e.g., adding noise) is correct because injecting small perturbations or synthetic variations into the training data enlarges the effective sample diversity, forcing the model to learn robust, generalizable patterns rather than memorizing exact training points, which directly reduces overfitting. Option E (Feature selection using correlation analysis) is correct because with 10 features and 100,000 rows, removing redundant or highly correlated features lowers model complexity and variance, a standard regularization-by-simplification step that mitigates overfitting. Option B (SMOTE) addresses class imbalance, not overfitting, and can even increase overfitting risk by generating synthetic minority samples. Option C (One-hot encoding) is a categorical encoding step that can expand dimensionality and typically increases overfitting risk rather than reducing it. Option D (Log transformation) only stabilizes variance and skewness for certain distributions; it does not by itself reduce overfitting.

Answer

SMOTE to balance classes

Answer

One-hot encoding of all categorical features

Answer

Log transformation of skewed features

Question 13

A retail company is preparing a dataset for a machine learning model to predict customer churn. The dataset includes customer_id, signup_date, last_purchase_date, total_purchases, average_order_value, and churn_label. The data scientist notices that the 'total_purchases' column has missing values for 15% of the records. The company wants to use AWS Glue for data preparation. Which approach should the data scientist take to handle the missing values while minimizing bias and preserving data integrity?

Accepted Answer

Use AWS Glue DynamicFrame to perform model-based imputation, predicting missing total_purchases using other features like average_order_value and signup_date.. Model-based imputation uses relationships between features (e.g., average_order_value and signup_date) to predict missing total_purchases values, minimizing bias compared to simple mean/median imputation. AWS Glue DynamicFrames support custom transformation logic, allowing you to implement a predictive model (e.g., using Spark MLlib) directly within the Glue ETL job. This approach preserves data integrity by leveraging existing data patterns rather than discarding records or introducing arbitrary constants.

Answer

Use AWS Glue DataBrew to fill missing values with the median of total_purchases.

Answer

Drop all records with missing total_purchases values.

Answer

Replace missing total_purchases with the mean of the non-missing values.

Question 14

A financial services company is building a fraud detection model using transactional data stored in Amazon S3. The data includes transaction_id, timestamp, amount, merchant_category, and fraud_label (0/1). The data is collected from multiple sources and has inconsistencies: timestamps are in different timezones (UTC and EST), merchant categories are sometimes misspelled (e.g., 'RESTAURANT', 'Restaurant', 'restaurant'), and the fraud_label is missing for about 5% of records. The data science team uses AWS Glue for ETL. They need to prepare a clean dataset for training. The final dataset must have consistent timestamps in UTC, standardized merchant categories, and no missing fraud labels. The team also wants to minimize data loss. Which set of actions should the team take?

Accepted Answer

Use AWS Glue to convert timestamps to UTC, use a mapping table to group similar merchant categories (e.g., all restaurant variants to 'Restaurant'), and impute missing fraud_label using mode (most frequent value).. It preserves data by imputing missing fraud labels using the mode (most frequent value), which is appropriate for a binary classification label where the majority class is likely 0. It also standardizes timestamps to UTC and uses a mapping table to group merchant category variants, ensuring consistency without data loss. Dropping records (as in A and C) would reduce the dataset size, and imputing with the mean (as in B) is invalid for a categorical label.

Answer

Use AWS Glue to convert all timestamps to UTC, apply a mapping function to correct merchant category misspellings to a standard list, and drop records with missing fraud_label.

Answer

Use AWS Glue to convert timestamps to UTC, use a fuzzy matching algorithm to standardize merchant categories, and replace missing fraud_label with the mean value (0.05).

Answer

Use AWS Glue to convert timestamps to UTC, correct merchant categories by mapping known misspellings to correct names, and drop records with missing fraud_label.

Question 15

A healthcare startup is building a model to predict patient readmission within 30 days. The data is stored in Amazon Redshift and includes patient demographics, admission history, lab results, and medication records. The data scientist extracts a sample of 10,000 records to Amazon S3 as CSV files for initial prototyping. During exploratory data analysis, they find that the 'age' column has values like '150', '0', and negative numbers. The 'diagnosis_code' column contains codes like 'E11', 'E11.9', and 'e11' (inconsistent formatting). The 'readmitted' target column has 60% 'Yes' and 40% 'No'. The data scientist wants to use AWS Glue DataBrew for data cleaning. Which combination of steps should they use?

Accepted Answer

In AWS Glue DataBrew: 1) Filter age between 0 and 120 to remove invalid values. 2) Standardize diagnosis_code to uppercase using a formula. 3) Apply Random Oversampling to balance the target column.. It uses AWS Glue DataBrew's built-in capabilities to filter invalid age values (0–120), standardize the diagnosis_code to uppercase via a formula, and apply Random Oversampling to address the 60/40 class imbalance. DataBrew supports filtering, formula-based transformations, and built-in ML transforms like Random Oversampling, making this combination valid and efficient for data cleaning.

Answer

In AWS Glue DataBrew: 1) Impute age with the mean. 2) Apply Standard Scaler to all numeric columns. 3) Use Random Oversampling to balance the target column.

Answer

In AWS Glue DataBrew: 1) Replace age with median. 2) Convert diagnosis_code to uppercase. 3) Apply SMOTE to balance the target column.

Answer

In AWS Glue DataBrew: 1) Remove rows where age is outside 0-120. 2) Drop diagnosis_code column. 3) Use Random Undersampling to balance the target column.

Question 16

An e-commerce company is building a recommendation system using user interaction data stored in Amazon DynamoDB. The data includes user_id, product_id, timestamp, event_type (click, add_to_cart, purchase), and session_id. The data science team exports the data to Amazon S3 as JSON files. During preprocessing, they discover that the 'event_type' field contains inconsistent values due to logging errors: 'Click', 'click', 'CLICK', and 'clck' all appear. Also, there are duplicate records where the same user_id, product_id, and timestamp appear multiple times with the same event_type. The team wants to use AWS Glue to clean the data for training a sequence-based recommendation model. Which set of actions should they perform?

Accepted Answer

Use AWS Glue to drop exact duplicate rows (all columns identical). Then apply a mapping function to standardize event_type to a controlled vocabulary (e.g., 'click', 'add_to_cart', 'purchase').. It addresses both data quality issues: first, dropping exact duplicate rows (all columns identical) removes redundant records that would bias the sequence model; second, standardizing event_type to a controlled vocabulary ensures consistent categorical input for ML training. AWS Glue's DynamicFrame with DropDuplicates and Map transformations are the appropriate tools for this ETL task.

Answer

Use AWS Glue to group records by session_id and aggregate event_types into a list per session. Then apply a mapping function to standardize event_type names.

Answer

Use AWS Glue to drop duplicate records based on all columns. Then drop the event_type column and use only numeric features for training.

Answer

Use AWS Glue to impute event_type with the mode for records with inconsistent values. Then drop duplicate records based on user_id, product_id, and timestamp.

Question 17

A data scientist is using Amazon SageMaker Processing to run a feature engineering job. The job requires installing additional Python libraries not included in the default SageMaker containers. Which approach should the data scientist use to include these libraries?

Accepted Answer

Create a custom Docker image with the libraries installed and specify it in the ProcessingInput. SageMaker Processing jobs run in isolated containers that cannot install packages at runtime via pip without internet access or custom images. Creating a custom Docker image with the required libraries pre-installed ensures the environment is consistent, reproducible, and avoids dependency resolution failures during job execution. This approach aligns with SageMaker's best practice for custom dependencies.

Answer

Add the libraries to the `requirements.txt` file in the same S3 bucket as the script

Answer

Use Amazon EFS to store the libraries and mount them to the processing container

Answer

Use the `pip install` command within the processing script at runtime

Question 18

A data engineer needs to join two large datasets from Amazon S3: one containing customer demographics and another containing transaction history. The join key is `customer_id`. To minimize data shuffling and improve performance, the engineer decides to use Amazon SageMaker Processing with Spark. Which configuration should the engineer use?

Accepted Answer

Use a bucketed join with the same number of buckets and co-location. Bucketed joins with the same number of buckets and co-location ensure that data with the same `customer_id` hash is physically stored together on the same nodes. This eliminates the need for expensive shuffles during the join, as Spark can perform the join locally within each executor, dramatically improving performance for large datasets in SageMaker Processing.

Answer

Use a bucketed join with the same number of buckets

Answer

Broadcast join the larger dataset

Answer

Use a repartition on the join key before join

Question 19

A data scientist is preparing a dataset for a regression model that predicts house prices. The dataset includes a `neighborhood` feature with 500 distinct categories. The data scientist wants to encode this feature without increasing dimensionality too much and while capturing the target relationship. Which encoding technique should be used?

Accepted Answer

Target encoding (mean encoding). Target encoding (mean encoding) is the correct choice because it replaces each of the 500 neighborhood categories with the mean of the target variable (house price) for that category. This captures the relationship between the neighborhood and the target while adding only one new feature column, thus avoiding the massive dimensionality explosion that would occur with one-hot encoding (which would create 500 binary columns).

Answer

One-hot encoding

Answer

Frequency encoding

Answer

Label encoding

Question 20

A data scientist is performing feature engineering for a dataset with both numerical and categorical features. The data scientist wants to apply transformations that preserve the interpretability of the features. Which TWO transformations should the data scientist use? (Select TWO)

Accepted Answer

Log transformation of skewed numerical features. Option A (log transformation of skewed numerical features) is correct because applying a log (e.g., natural log or log1p) to right-skewed numeric variables compresses large values and reduces skew while retaining a monotonic, one-to-one mapping, so the transformed values remain directly interpretable in terms of the original feature's scale. Option C (standard scaling of numerical features) is correct because z-score standardization (subtracting the mean and dividing by the standard deviation) is a linear transformation that preserves the relative ordering and shape of the distribution, keeping the feature interpretable as 'number of standard deviations from the mean.' Option B (target encoding) is not appropriate here because it replaces categories with target statistics, which introduces leakage risk and obscures the original categorical meaning. Option D (PCA) is not appropriate because principal components are linear combinations of the original features and are generally not interpretable as the original variables. Option E (one-hot encoding) is not appropriate because it expands a categorical feature into many binary columns, increasing dimensionality and losing the single-feature interpretability the scenario requires.

Answer

Target encoding of high-cardinality categorical features

Answer

PCA dimensionality reduction

Answer

One-hot encoding of categorical features