Assignment- 3.docx - DSC 441 Assignment 3 1 Problem 1 1...

This preview shows page 1 - 5 out of 13 pages.

10/21/2020 DSC 441 Assignment 3 1. Problem 1
1. Validation: Cross validation Maximum tree depth:8 Minimum cases for parent node: 20 Minimum cases for child node: 10 Growing method: CRT Impurity measure: Gini Index 2. The final tree has 9 nodes with 5 terminal nodes. 3. V10, V11 and V1 are the top three most important features with highest values to make decision in our data on splitting the tree. 4. Increasing number of cases for parent to 30 and child to 15 complexity decreases. Decrease in complexity can be explained by increasing number of cases in child node, which might result in child not having enough cases, so parent cannot be split further. Result shows that remained 3 nodes with 2 terminal nodes 90.6% accuracy.
2. Problem 2 1. There are 6 classes in the red wine dataset. Based on the descriptive statistics, the skewness is reported as 0.218, which indicates a slight right skew. According to the histogram, the data is normally distributed among the classes.

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture