Using the machine learning MATLAB tutorial:
https://www.mathworks.com/products/demos/machine-learning/cluster_genes/cluster_genes.html
Download your own data set and perform all steps (in the tutorial). Your final document should contain the following:
- Cluster diagram (chart)
- Hierarchical Cluster Tree
- PCA analysis
- K-Means analysis
- com/mathchi/diabetes-data-set“>https://www.kaggle.com/mathchi/diabetes-data-set, I used this data set in my previous assignment.
The code in the tutorial might require some modifications to run on your sample dataset. Your document should provide detailed explanation of the results, your prestatistical analysis, and the charts/diagrams described above. In addition to your document, upload your MATLAB code and dataset.
Grading Rubric
|
Item |
Description |
Points |
|
Comments |
MATLAB code properly and clearly commented |
25 |
|
Data Set |
Data Set properly explained and each variable is discussed |
25 |
|
Pre-statistical analysis |
Proper pre-analysis conducted to determine if any of the variables are strongly correlated |
25 |
|
Cluster diagram, PCA, K-Means and Hierarchical tree |
Student clearly demonstrated all 4 concepts, explained MATLAB code that generated the results, discussed the results and clearly showed results in graphical format (50 points each) |
100 |
|
Results |
Results are properly explained and graphed using MATLAB charts |
50 |
|
Format and professionalism |
Report is clearly written explaining every every step taken to create the NN. Third party references are used to support work |
25 |
|
TOTAL |
250 |
0 comments