Databricks Machine Learning Associate Question 69
Select 3You are using the Databricks AutoML data exploration notebook to understand the key attributes of your dataset before building a machine learning model. Which of the following insights can you derive directly from the data exploration notebook?
- A
The distribution of values for each feature
- B
The correlation between features in the dataset
- C
The precision of the model on the test set
- D
The presence of missing values in the dataset
- E
The recommended hyperparameters for the model
Show answer and explanation
Correct answers: A, B, D
Explanation
The Databricks AutoML data exploration notebook is designed to provide key insights about the dataset, such as feature distributions, correlations, and missing values. However, it does not include insights related to model performance or hyperparameter tuning, which occur in later stages of the AutoML process.
- A. Correct.
Correct: The data exploration notebook provides visualizations like histograms and descriptive statistics to help understand the distribution of values for each feature.
- B. Correct.
Correct: The notebook includes a correlation matrix or heatmap to show relationships between features, making this insight available.
- C. Incorrect.
Incorrect: Model performance metrics like precision are not part of the data exploration step; they are evaluated after training a model.
- D. Correct.
Correct: The data exploration notebook highlights missing values in the dataset, helping users understand data quality issues.
- E. Incorrect.
Incorrect: The notebook does not suggest hyperparameters for models; this is typically done during the model training phase.