Google Professional Machine Learning Engineer Question 77
Select 2Google Cloud PlatformYou have a large dataset containing customer demographics, transaction history, and product preferences, and you need to predict the likelihood of a customer purchasing a new product. You decide to use AutoML Tables in Google Cloud to build a predictive model. Which of the following steps are necessary to prepare your data and train the model using AutoML Tables?
- A
Ensure the dataset is in a supported format like CSV or BigQuery table.
- B
Manually encode categorical variables into numerical values before uploading the dataset.
- C
Split the dataset into training, validation, and test sets before uploading it to AutoML Tables.
- D
Specify the target column during the dataset import process.
- E
Review and optimize hyperparameters for the AutoML Tables model before training.
Show answer and explanation
Correct answers: A, D
Explanation
When using AutoML Tables for tabular data, it is important to prepare the dataset in the correct format (e.g., CSV or BigQuery table) and specify the target column when importing the dataset. AutoML Tables automates many steps, such as splitting the data and hyperparameter tuning, so these tasks do not need to be performed manually. Understanding these requirements helps streamline the model development process.
- A. Correct.
AutoML Tables supports datasets in formats like CSV or BigQuery tables. Ensuring the dataset is in a supported format is a necessary step for using AutoML Tables.
- B. Incorrect.
Manually encoding categorical variables is not required. AutoML Tables automatically handles preprocessing, including encoding of categorical features.
- C. Incorrect.
You do not need to manually split the dataset. AutoML Tables automatically splits the data into training, validation, and test subsets during the training process.
- D. Correct.
Specifying the target column is a required step when importing the dataset, as AutoML Tables needs to know what you are trying to predict.
- E. Incorrect.
You do not need to manually optimize hyperparameters. AutoML Tables performs automated hyperparameter tuning during the training process.