Exploring the UCI SECOM data

To round out this chapter and solidify your understanding of bagging, it's time to work with a new dataset! This data is from a semi-conductor manufacturing process, obtained from the UCI Machine Learning Repository.

Each row represents a production entity. The features are measurements from sensors or points in the process. The labels represent whether the entity passes (1) or fails (-1) the test.

The dataset is loaded and available to you as uci_secom. The target is the 'Pass/Fail' column. Use the .value_counts() and .describe() methods to check this variable. What do you notice?

Possible Answers

There are fewer negative than positive tests.
The target has many missing values.
There is evidence of high class imbalance in the target.

Exercise

Exploring the UCI SECOM data

Instructions

Possible Answers