SnowPro Advanced: Data Scientist Certification Exam

Question 1

You are designing a feature engineering pipeline using Snowpark Feature Store for a fraud detection model. You have a transaction table in Snowflake. One crucial feature is the 'average_transaction_amount_last_7_days' for each customer. You want to implement this feature using Snowpark Python and materialize it in the Feature Store. You have the following Snowpark DataFrame 'transactions_df containing 'customer_id' and 'transaction_amount'. Which of the following code snippets correctly defines and registers this feature in the Snowpark Feature Store, ensuring efficient computation and storage?

A.

B.

C.

D.

E.

Correct Answer: D

Explanation: Only visible for Actualtests4sure members. You can sign-up / login (it's free).

Question 2

You have trained a complex machine learning model using Snowpark for Python and are now preparing it for production deployment using Snowpark Container Services. You have containerized the model and pushed it to a Snowflake-managed registry. However, you need to ensure that only authorized users can access and deploy this model. Which of the following actions MUST you take to secure your model in the Snowflake Model Registry, ensuring appropriate access control, and minimizing the risk of unauthorized deployment or modification?

A. Grant the 'READ privilege on the container registry to all users who need to deploy the model. Create a custom role with the 'APPLY MASKING POLICY privilege and grant this role to the deployment team.

B. Grant the 'USAGE privilege on the database and schema containing the model registry, grant the 'READ privilege on the registry itself, and grant the EXECUTE TASK' privilege to the deployment team for the deployment task.

C. Store the model outside of Snowflake managed registry and use external authentication to control access.

D. Grant the 'USAGE privilege on the stage where the model files are stored to all users who need to deploy the model.

E. Create a custom role, grant the USAGE' privilege on the database and schema containing the model registry, grant the 'READ privilege on the registry, and then grant this custom role to only those users authorized to deploy the model. Consider masking sensitive model parameters using masking policies.

Correct Answer: E

Explanation: Only visible for Actualtests4sure members. You can sign-up / login (it's free).

Question 3

You are tasked with training a machine learning model within Snowflake using a Python UDTF. The UDTF is intended to process incoming sales data, calculate features, and update the model incrementally. The model is a simple linear regression using scikit-learn. Your initial attempt fails with a 'ModuleNotFoundError: No module named 'sklearn" error within the UDTF. You have already confirmed that scikit-learn is available in your Anaconda channel and specified it during session creation. Which of the following actions would MOST directly address this issue and allow the UDTF to successfully import and use scikit-learn?

A. When creating the UDTF, use the 'PACKAGES' parameter to explicitly specify the 'skiearn' package. For example: 'CREATE OR REPLACE FUNCTION RETURNS TABLE LANGUAGE PYTHON RUNTIME_VERSION = '3.8' PACKAGES = ('snowflake-snowpark-python','scikit-learn') ...

B. Recreate the Anaconda environment and ensure that the 'sklearn' package is installed specifically within the environment's 'site-packages' directory. Then, recreate the Snowflake session.

C. Ensure that the Anaconda channel containing 'sklearn' is explicitly activated at the account level using the 'ALTER ACCOUNT command. Verify the channel is listed in 'SHOW CHANNELS'.

D. Include ' import snowflake.snowpark; session = snowflake.snowpark.session.get_active_session()' within the UDTF code to explicitly initialize the Snowpark session before importing sklearn. Ensure that scikit-learn is included in the 'imports' argument of the 'create_dataframe' method.

E. Explicitly copy the 'sklearn' directory and its dependencies directly into the same directory as your UDTF definition script on the Snowflake stage, then reference them using relative paths within the UDTF.

Correct Answer: A

Explanation: Only visible for Actualtests4sure members. You can sign-up / login (it's free).

Question 4

You have a Snowpark DataFrame named 'product_reviews' containing customer reviews for different products. The DataFrame includes columns like 'product_id' , 'review_text' , and 'rating'. You want to perform sentiment analysis on the 'review_text' to identify the overall sentiment towards each product. You decide to use Snowpark for Python to create a user-defined function (UDF) that utilizes a pre-trained sentiment analysis model hosted externally. You need to ensure secure access to this model and efficient execution. Which of the following represents the BEST approach, considering security and performance?

A. Create a Java UDF that utilizes a library to call the sentiment analysis API. Pass the API key as a parameter to the UDF each time it is called.

B. Create an inline Python UDF that directly calls the external sentiment analysis API with hardcoded API keys within the UDF code.

C. Create an external function in Snowflake that calls a serverless function (e.g., AWS Lambda, Azure Function) that performs the sentiment analysis. Use Snowflake's network policies to restrict access to the serverless function and secrets management to handle API keys.

D. Create an external function in Snowflake that calls a serverless function. Configure the API gateway in front of the serverless function to enforce authentication via Mutual TLS (mTLS) using Snowflake-managed certificates.

E. Create a Snowpark Pandas UDF that calls the external sentiment analysis API. Use Snowflake secrets management to store the API key and retrieve it within the UDF.

Correct Answer: D

Explanation: Only visible for Actualtests4sure members. You can sign-up / login (it's free).

Question 5

You've built a machine learning model in scikit-learn and want to deploy it to Snowflake for real-time inference. You have the following options for deploying the model. Select all that apply and are considered a best practice for cost and time optimization:

A. Implement a custom microservice that reads data from Snowflake, performs inference using the scikit-learn model, and writes the predictions back to Snowflake.

B. Package the scikit-learn model using 'joblib' or 'pickle' , store it in a Snowflake stage, and create a Snowflake UDF (User-Defined Function) in Python to load the model from the stage and perform inference.

C. Use Snowflake's Snowpark Python API to directly load the model from a stage and execute inference using Snowpark DataFrames, which will implicitly handle the distributed processing of the data.

D. Create a Snowflake external function that calls a cloud-based (AWS SageMaker, Azure Machine Learning, GCP Vertex A1) endpoint for inference, passing the input data to the endpoint and receiving the prediction back.

E. Migrate your entire Snowflake data warehouse to a different platform which better supports real-time ML inference.

Correct Answer: B,C

Explanation: Only visible for Actualtests4sure members. You can sign-up / login (it's free).

Question 6

A telecom company, 'ConnectPlus', observes that the individual call durations of its customers are heavily skewed towards shorter calls, following an exponential distribution. A data science team aims to analyze call patterns and requires to perform hypothesis testing on the average call duration. Which of the following statements regarding the applicability of the Central Limit Theorem (CLT) in this scenario are correct if the sample size is sufficiently large?

A. The CLT is applicable, and the sample mean will converge to the population median.

B. The CLT is not applicable because the population distribution (call durations) is heavily skewed.

C. The CLT is applicable, and the distribution of sample means of call durations will approximate a normal distribution, regardless of the skewness of the individual call durations.

D. The CLT is applicable as long as the sample size is reasonably large (typically n > 30), and the distribution of sample means will be approximately normal. The specific minimum sample size depends on the severity of the skewness.

E. The CLT is applicable only if the sample size is extremely large (e.g., greater than 10,000), due to the exponential distribution's heavy tail.

Correct Answer: C,D

Explanation: Only visible for Actualtests4sure members. You can sign-up / login (it's free).

Question 7

You are deploying a fraud detection model using Snowpark Container Services. The model requires a substantial amount of GPU memory. After deploying your service, you notice that it frequently crashes due to Out-Of-Memory (OOM) errors. You have verified that the container image itself is not the source of the problem. Which of the following strategies are most appropriate to mitigate these OOM errors when using Snowpark Container Services, assuming you want to minimize costs and complexity?

A. Implement a mechanism within your model's inference code to explicitly free up unused memory after each prediction. Use Python's 'gc.collect()' and ensure proper cleanup of large data structures. Configure a smaller 'container.resources.memory' allocation.

B. Increase the 'container.resources.memory' configuration setting in the service definition to a value significantly larger than the model's memory footprint. Monitor memory utilization and adjust as needed.

C. Implement model parallelism across multiple containers, splitting the model's workload and data across them. Configure each container with a smaller 'container.resources.memory' allocation.

D. Ignore OOM errors and rely on the container service to automatically restart the container. The model will eventually process all requests.

E. Utilize CPU-based inference instead of GPU-based inference, as CPU inference is generally less memory-intensive. Convert the model to a format optimized for CPU inference (e.g., using ONNX). Reduce the 'container.resources.cpu' count.

Correct Answer: A,B

Explanation: Only visible for Actualtests4sure members. You can sign-up / login (it's free).

Question 8

You are tasked with automating the retraining of a fraud detection model in Snowflake. The model is deployed as a Snowflake User-Defined Function (UDF). The training data resides in a Snowflake table named 'TRANSACTIONS. You want to trigger retraining if the model's performance, as measured by AUC, drops below 0.80. The model's AUC is tracked in a Snowflake table named 'MODEL PERFORMANCE. Which of the following strategies provides the MOST efficient and robust solution for automating this retraining process within Snowflake, minimizing latency and external dependencies?

A. Create an external function that is invoked periodically by a Snowflake Task. The external function queries 'MODEL PERFORMANCE and uses a cloud provider's machine learning service (e.g., AWS SageMaker) to retrain the model and update the UDF using Snowflake's external functions capabilities for model deployment.

B. Implement a Snowflake Task that executes a stored procedure. The stored procedure queries 'MODEL_PERFORMANCE. If the AUC is below 0.80, it executes a Snowflake ML pipeline using 'snowflake.ml.modeling' to retrain the model directly within Snowflake and updates the UDF in place using 'CREATE OR REPLACE FUNCTION'.

C. Manually monitor on a dashboard and trigger retraining via a Snowflake Worksheet when needed.

D. Use a Snowflake Task that executes a stored procedure. The stored procedure queries 'MODEL PERFORMANCE, and if the AUC is below 0.80, it triggers a Data Engineering pipeline (e.g., using Airflow or Databricks) to retrain the model and update the UDF.

E. Schedule a job on an external system (e.g., a cron job on a Linux server) to periodically query 'MODEL PERFORMANCE and trigger a model retraining process if the AUC is below 0.80. This process would retrain the model externally and update the UDF in Snowflake.

Correct Answer: B

Explanation: Only visible for Actualtests4sure members. You can sign-up / login (it's free).

Snowflake SnowPro Advanced: Data Scientist Certification - DSA-C03 Exam Practice Test

Latest Update

Useful Links

Contact Us