Explain the confusion matrix, e.g. what are the True Positive (TP) number, the True Negative (TN) number, the False Positive (FP) number, and the False Negative (FN) number?
The confusion matrix
In Week 11, you used Weka to mine some association rules. In this assignment you will use Weka to cluster some data. Your assignment is to cluster data points using K-Means clustering algorithm.
Here is a step by step guide to load this file and run generate the rules.
- Save the “credit-g.arff” file to someplace on your computer that you can quickly find it. This could be a folder in documents or on your desktop.
- Open Weka and go to the Explorer.
- Click “Open File” select the “credit-g.arff” file from wherever you saved it.
- At this point take note of the statistics of the selected attribute. Notice how Weka calculates the minimum, maximum, mean and standard deviation for your quick reference.
- Select the check marks next to all of the attributes to select them all.
- Next click the “Cluster” tab and then select “SimpleKMeans.
- Now under “Cluster mode” select “Classes to clusters evaluation” and press “Start.”
Your report will include a comb
- A screenshot of Weka Explore when the file “credit-g.arff” is successfully loaded;
- A snapshot of Weka Explore when the clustering is completed
- After viewing the clustering results, please explain the confusion matrix, e.g. what are the True Positive (TP) number, the True Negative (TN) number, the False Positive (FP) number, and the False Negative (FN) number?
- Your answer to the following questions: What is the accuracy of the clustering result? (100 words)