Snowflake SnowPro Advanced: Data Scientist Certification 認定 DSA-C03 試験問題:

1. You've trained a machine learning model using Scikit-learn and saved it as 'model.joblib'. You need to deploy this model to Snowflake. Which sequence of commands will correctly stage the model and create a Snowflake external function to use it for inference, assuming you already have a Snowflake stage named 'model_stage'?

A) Option B
B) Option D
C) Option A
D) Option E
E) Option C

2. You are tasked with automating the retraining of a Snowpark ML model based on the performance metrics of the deployed model. You have a table 'MODEL PERFORMANCE that stores daily metrics like accuracy, precision, and recall. You want to automatically trigger retraining when the accuracy drops below a certain threshold (e.g., 0.8). Which of the following approaches using Snowflake features and Snowpark ML is the MOST robust and cost-effective way to implement this automated retraining pipeline?

A) Implement an external service (e.g., AWS Lambda or Azure Function) that periodically queries the "MODEL_PERFORMANCE table using the Snowflake Connector and triggers a Snowpark ML model training script via the Snowflake API.
B) Use a Snowflake stream on the 'MODEL_PERFORMANCE table to detect changes in accuracy, and trigger a Snowpark ML model training function using a PIPE whenever the accuracy drops below the threshold.
C) Create a Dynamic Table that depends on the 'MODEL PERFORMANCE table and materializes when the accuracy is below the threshold. This Dynamic Table refresh triggers a Snowpark ML model training stored procedure. This stored procedure saves the new model with a timestamp and updates a metadata table with the model's details.
D) Implement a Snowpark ML model training script that automatically retrains the model every day, regardless of the performance metrics. This script will overwrite the previous model.
E) Create a Snowflake task that runs every hour, queries the 'MODEL_PERFORMANCE table, and triggers a Snowpark ML model training script if the accuracy threshold is breached. The training script will overwrite the existing model.

3. You're building a fraud detection model and want to determine if the average transaction amount for fraudulent transactions is significantly higher than the average transaction amount for legitimate transactions. You have two tables in Snowflake:
'FRAUDULENT TRANSACTIONS and 'LEGITIMATE TRANSACTIONS, both with a 'TRANSACTION AMOUNT column. You believe that FRAUDULENT TRANSACTIONS contains fewer than 30 transactions. You don't know the population standard deviations. What are the proper steps to conduct the hypothesis test, and what is the correct hypothesis statement?

A) Perform a Z-test. Null Hypothesis: The average transaction amount for fraudulent transactions is less than or equal to the average transaction amount for legitimate transactions. Alternative Hypothesis: The average transaction amount for fraudulent transactions is greater than the average transaction amount for legitimate transactions.
B) Perform a Z-test. Null Hypothesis: The average transaction amount for fraudulent transactions is equal to the average transaction amount for legitimate transactions. Alternative Hypothesis: The average transaction amount for fraudulent transactions is not equal to the average transaction amount for legitimate transactions.
C) Perform a chi-squared test. Null Hypothesis: There is no relationship between transaction amount and whether a transaction is fraudulent. Alternative Hypothesis: There is a relationship between transaction amount and whether a transaction is fraudulent.
D) Perform a t-test. Null Hypothesis: The average transaction amount for fraudulent transactions is less than or equal to the average transaction amount for legitimate transactions. Alternative Hypothesis: The average transaction amount for fraudulent transactions is greater than the average transaction amount for legitimate transactions.
E) Perform a t-test. Null Hypothesis: The average transaction amount for fraudulent transactions is equal to the average transaction amount for legitimate transactions. Alternative Hypothesis: The average transaction amount for fraudulent transactions is not equal to the average transaction amount for legitimate transactions.

4. You are tasked with deploying a pre-trained sentiment analysis model hosted externally using AWS SageMaker. The model endpoint requires an API key for authentication, and you want to score customer reviews stored in a Snowflake table named 'CUSTOMER REVIEWS. Which of the following steps are necessary to securely and efficiently integrate this external model with Snowflake, assuming you have already created a Snowflake stage to store secrets?

A) Create an external function in Snowflake that retrieves the API key from a secure Snowflake secret object. Grant USAGE privilege on the secret to the service account associated with the external function.
B) Use Snowflake's external functions to directly call the SageMaker endpoint from a SQL query, passing the customer review text as input. No separate secure external stage configuration is needed as long as Snowflake has internet access.
C) Create a secret object in Snowflake to store the API key. Grant appropriate privileges on the secret to the role that will execute the external function. Modify external function that references secure external stage.
D) Create an external function in Snowflake that invokes the SageMaker endpoint, hardcoding the API key directly into the function definition for simplicity.
E) Store the API key in an environment variable within the AWS Lambda function (if using API Gateway) that serves as an intermediary between Snowflake and SageMaker. Snowflake calls the API Gateway endpoint which relays the request to the SageMaker endpoint, and no specific configuration is needed on snowflake.

5. You are tasked with building a machine learning model in Python using data stored in Snowflake. You need to efficiently load a large table (100GB+) into a Pandas DataFrame for model training, minimizing memory footprint and network transfer time. You are using the Snowflake Connector for Python. Which of the following approaches would be MOST efficient for loading the data, considering potential memory limitations on your client machine and the need for data transformations during the load process?

A) Use the 'COPY INTO' command to unload the table to an Amazon S3 bucket and then use bot03 in your python script to fetch data from s3 and load into pandas dataframe.
B) Use 'snowsql' to unload the table to a local CSV file, then load the CSV file into a Pandas DataFrame.
C) Load the entire table into a Pandas DataFrame using with a simple 'SELECT FROM my_table' query and then perform data transformations in Pandas.
D) Create a Snowflake view with the necessary transformations, and then load the view into a Pandas DataFrame using 'pd.read_sql()'.
E) Utilize the 'execute_stream' method of the Snowflake cursor to fetch data in chunks, apply transformations in each chunk, and append to a larger DataFrame or process iteratively without creating a large in-memory DataFrame.

質問と回答：