Question: During the classification tree construction process, you are determining how to split the 8 datapoints provided below using one of the two predictor variables, X1
During the classification tree construction process, you are determining how to split the 8 datapoints provided below using one of the two predictor variables, X1 and X2. Express all answers rounded to four decimal places, but use unrounded values in all calculations.
| x1 | x2 | y |
|---|---|---|
| 8.7 | 3.6 | 0 |
| 1.2 | 3.3 | 1 |
| 4.9 | 8.9 | 1 |
| 3.2 | 4.5 | 0 |
| 2.9 | 3.2 | 1 |
| 9.2 | 4.3 | 1 |
| 9.7 | 6.2 | 1 |
| 2.3 | 8 | 0 |
Analyze the possible split points for X11 by filling in the table below.
- Identify the possible split points.
- Count the number of 0s and 1s in each branch of the possible splits.
- Calculate the Gini index for each branch of the possible splits.
- Calculate the combined Gini index for each possible splits.
Information about the possible split points for X22 is provided for you in the table below.Determine the optimal split.
- What is the minimum Gini index overall?
- Which variable would be split?
- What split point would be used for the logical test of this new decison node?
- X11
- X22
| Split Point | # of 0s Left Branch | # of 1s Left Branch | # of 0s Right Branch | # of 1s Right Branch | Gini Index Left Branch | Gini Index Right Branch | Combined Gini Index |
|---|---|---|---|---|---|---|---|
| 3.25 | 0 | 1 | 3 | 4 | 0 | 0.4898 | 0.4286 |
| 3.45 | 0 | 2 | 3 | 3 | 0 | 0.5 | 0.375 |
| 3.95 | 1 | 2 | 2 | 3 | 0.4444 | 0.48 | 0.4667 |
| 4.4 | 1 | 3 | 2 | 2 | 0.375 | 0.5 | 0.4375 |
| 5.35 | 2 | 3 | 1 | 2 | 0.48 | 0.4444 | 0.4667 |
| 7.1 | 2 | 4 | 1 | 1 | 0.4444 | 0.5 | 0.4583 |
| 8.45 | 3 | 4 | 0 | 1 | 0.4898 | 0 | 0.4286 |
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
