#Definition of filenames
This table describes the four different versions of kmeans output that is being compared in this document.
# |
File Name | Outliers removed before kmeans? | No of buckets | Growth features | Std1&2 combined? | SSE |
|---|---|---|---|---|---|---|
| 1 | results_separate_1.0 | No | 4 | raw_growth | No | 166.72143481403828 |
| 2 | results_separate_1.2 | No | 4 | raw_growth*1.2 | No | 166.67085475235154 |
| 3 | results_separate_1.2_median | No | 4 | raw_growth*1.2,Median taken | No | 208.7057418979538 |
| 4 | results_combined_1.2 | No | 4 | raw_growth*1.2 | Yes | 82.83615257442713 |
#Distribution of buckets
| bucket_new | results_separate_1.0 | results_separate_1.2 | results_separate_1.2_median | results_combined_1.2 |
|---|---|---|---|---|
| bL;gL | 0.32 | 0.31 | 0.31 | 0.32 |
| bL;gH | 0.23 | 0.23 | 0.21 | 0.21 |
| bH;gL | 0.11 | 0.12 | 0.14 | 0.15 |
| bH;gH | 0.33 | 0.33 | 0.34 | 0.32 |
| Total | 0.99 | 0.99 | 1.00 | 1.00 |
#Scatter plot
#Growth Boxplots
#Baseline Boxplots