'how to calculate accuracy from decision trees?

enter image description here

Hi, I am taking a course on Coursera and came into this question. My answer is 1-(4048+3456)/8124=0.076. However, the answer is 0.067. Anybody can help me to solve this? Thank you!!

decision-tree


Solution 1:[1]

Accuracy: The number of correct predictions made divided by the total number of predictions made.

We're going to predict the majority class associated with a particular node as True. i.e. use the larger value attribute from each node.

So the accuracy for:

  • Depth 1: (3796 + 3408) / 8124
  • Depth 2: (3760 + 512 + 3408 + 72) / 8124

Depth_2 - Depth_1 = 0.06745

Solution 2:[2]

First We will draw confusion metrics for both cases and then find accuracy.

Confusion metrics:

enter image description here

Accuracy= (TP + TN) / (Total number of observation)

Accuracy calculation:

Depth 1: (3796 + 3408) / 8124

Depth 2: (3760 + 512 + 3408 + 72) / 8124

Depth_2 - Depth_1 = 0.06745

Solution 3:[3]

Though answer is correct but the confusion matrix looks not correct. This should be the confusion matrix( for depth-2). enter image description here

Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source
Solution 1 patricio
Solution 2 Ashish Anand
Solution 3 Pankaj Singh

Related Questions