Databricks Machine Learning Associate Question 158
Select 3You are using Databricks to train a machine learning model and want to analyze summary statistics for your training dataset. Which of the following actions can be achieved using the summary method in Databricks?
- A
View descriptive statistics such as mean, standard deviation, and min/max for numerical columns.
- B
Identify the most frequent category for categorical columns.
- C
Detect missing values in the dataset.
- D
Compute correlations between numerical columns.
- E
View the number of unique values for categorical columns.
Show answer and explanation
Correct answers: A, B, E
Explanation
The summary method in Databricks is a useful tool for obtaining descriptive statistics for numerical columns (e.g., mean, standard deviation) as well as insights into categorical columns (e.g., most frequent category and distinct values). However, it does not handle tasks like missing value detection or correlation computation, which require different functionalities.
- A. Correct.
The summary method in Databricks provides descriptive statistics like mean, standard deviation, and min/max for numerical columns, making this correct.
- B. Correct.
For categorical columns, the summary method displays the most frequent category along with its count, so this is correct.
- C. Incorrect.
The summary method does not explicitly highlight missing values; it focuses on descriptive statistics, making this incorrect.
- D. Incorrect.
The summary method does not compute correlations. This task requires a separate correlation computation function, making this incorrect.
- E. Correct.
The summary method provides the number of distinct values for categorical columns, making this correct.