You have trained a complex Random Forest model in Snowflake to predict loan default risk. You wish to understand the individual and combined effects of 'credit_score' and 'debt_to_income_ratio' on the predicted probability of default. Which approach is MOST suitable for visualizing and interpreting these relationships?

• A. Generate individual Partial Dependence Plots (PDPs) for 'credit_score' and 'debt_to_income_ratio'.
• B. Create a two-way Partial Dependence Plot (PDP) showing the interaction between 'credit_score' and 'debt_to_income_ratio'.
• C. Examine the model's overall accuracy (e.g., AUC) and assume the relationships are well-represented.
• D. Fit a simpler linear model (e.g., Logistic Regression) to the data and interpret its coefficients.
• E. Calculate feature importance using SNOWFLAKE.ML.FEATURE IMPORTANCE and focus on the features with the highest scores.

You are building a data science pipeline in Snowflake to perform time series forecasting. You've decided to use a Python UDTF to encapsulate the forecasting logic using a library like 'Prophet'. The UDTF needs to access historical data to train the model and generate forecasts. The data is stored in a Snowflake table named 'SALES DATA with columns 'DATE' and 'SALES'. Which of the following approaches is/are most efficient and secure for accessing the 'SALES DATA table from within the UDTF during model training?

• A. Use the Snowpark API within the UDTF to query the 'SALES DATA' table directly, leveraging the existing Snowflake session context. This requires no additional credentials management.
• B. Pass the entire 'SALES DATA' table as a Pandas DataFrame to the UDTF as an argument. This approach is suitable for smaller datasets. Do not partition the data frame.
• C. Use the 'snowflake.connector' to connect to Snowflake using a dedicated service account with read-only access to the 'SALES DATA' table. Store the service account credentials securely in Snowflake secrets and retrieve them within the UDTF.
• D. Create a view on top of 'SALES DATA' and grant access to the UDTF's owner role to the view. Then, query the view using Snowpark within the UDTF.
• E. Bypass Snowflake entirely and load data from S3 stage into a Pandas dataframe.

You are tasked with preparing customer data for a churn prediction model in Snowflake. You have two tables: 'customers' (customer_id, name, signup_date, plan_id) and 'usage' (customer_id, usage_date, data_used_gb). You need to create a Snowpark DataFrame that calculates the total data usage for each customer in the last 30 days and joins it with customer information. However, the 'usage' table contains potentially erroneous entries with negative values, which should be treated as zero. Also, some customers might not have any usage data in the last 30 days, and these customers should be included in the final result with a total data usage of 0. Which of the following Snowpark Python code snippets will correctly achieve this?

• A.
  
• B.
  
• C. None of the above
• D.
  
• E.
  

You are building a fraud detection model using Snowflake data'. The dataset 'TRANSACTIONS' contains billions of records and is partitioned by 'TRANSACTION DATE'. You want to use cross-validation to evaluate your model's performance on different subsets of the data and ensure temporal separation of training and validation sets. Given the following Snowflake table structure:

Which approach would be MOST appropriate for implementing time-based cross-validation within Snowflake to avoid data leakage and ensure robust model evaluation? (Assume using Snowpark Python to develop)

• A. Use 'SNOWFLAKE.ML.MODEL REGISTRY.CREATE MODEL' with default settings, which automatically handles temporal partitioning based on the insertion timestamp of the data.
• B. Utilize the 'SNOWFLAKE.ML.MODEL REGISTRY.CREATE MODEL' with the 'input_colS argument containing 'TRANSACTION DATE'. Snowflake will automatically infer the temporal nature of the data and perform time-based cross-validation.
• C. Implement a custom splitting function within Snowpark, creating sequential folds based on the 'TRANSACTION DATE column and use that with Snowpark ML's cross_validation. Ensure each fold represents a distinct time window without overlap.
• D. Explicitly define training and validation sets based on date ranges within the Snowpark Python environment, performing iterative training and evaluation within the client environment before deploying a model to Snowflake. No built-in cross-validation used
• E. Create a UDF that assigns each row to a fold based on the 'TRANSACTION DATE column using a modulo operation. This is then passed to the 'cross_validation' function in Snowpark ML.

You are evaluating a binary classification model's performance using the Area Under the ROC Curve (AUC). You have the following predictions and actual values. What steps can you take to reliably calculate this in Snowflake, and which snippet represents a crucial part of that calculation? (Assume tables 'predictions' with columns 'predicted_probability' (FLOAT) and 'actual_value' (BOOLEAN); TRUE indicates positive class, FALSE indicates negative class). Which of the below code snippet should be used to calculate the 'True positive Rate' and 'False positive Rate' for different thresholds

• A. Using only SQL, Create a temporary table with calculated True Positive Rate (TPR) and False Positive Rate (FPR) at different probability thresholds. Then, approximate the AUC using the trapezoidal rule.
  
• B. The best way to calculate AUC is to randomly guess the probabilities and see how it performs.
• C. The AUC cannot be reliably calculated within Snowflake due to limitations in SQL functionality for statistical analysis.
• D. Calculate AUC directly within a Snowpark Python UDF using scikit-learn's function. This avoids data transfer overhead, making it highly efficient for large datasets. No further SQL is needed beyond querying the predictions data.
  
• E. Export the 'predicted_probability' and 'actual_value' columns to a local Python environment and calculate the AUC using scikit-learn.