Table 4 Results of cleaned 16,440 datasets after three rounds of K-means clustering analysis
Samples | Number of constructed models | Clustering number (type) | Model quality | Predictor variable importance |
|---|---|---|---|---|
16,440 | 1st round | 6 | 0.5 | R = 1 m = 1 F = 1 |
11,585 | 2nd round | 6 | 0.7 | R = 1 m = 1 F = 1 |
10,614 | 3rd round | 5 | 0.8 | R = 1 m = 1 F = 0.0563 |