Table 1.

Contingency table for the ensemble method on all ten chromosomes on the complete data set

	Ame.	Con.	Cri.	Cur.	Gui.	Iqu.	Mar.	Nac.	Nan.	Pur.	ci	Recall
Amelonado	68	1	0	0	6	1	4	0	1	13	94	0.72
Contamana	0	63	0	0	0	0	0	3	1	2	69	0.93
Criollo	0	0	39	0	0	0	0	0	0	0	39	1.0
Curaray	0	1	0	114	0	0	0	2	0	0	117	0.97
Guiana	0	0	0	0	58	0	1	0	0	0	59	0.98
Iquitos	0	0	0	0	0	99	2	1	6	9	117	0.85
Marañon	2	1	0	0	0	0	138	0	0	2	143	0.96
Nacional	2	0	1	2	0	1	0	46	0	0	52	0.88
Nanay	0	0	0	0	0	1	0	0	151	0	152	0.99
Purùs	0	1	2	1	0	0	0	7	0	99	110	0.90
pj	72	67	42	117	64	102	145	59	159	125	952
Precision	0.94	0.94	0.93	0.97	0.91	0.97	0.95	0.78	0.95	0.79

The Ensemble method on all ten chromosomes on the complete data set: The 10 × 10 contingency table M for comparing the two partitions is shown above. The reference cluster (c_i) along the rows is from [5]. Our computed partition (p_j) into 10 groups is along the columns. The F-index for this matrix is 0.92 (where a perfect agreement has a value of 1). Also the precision $\left(\frac{\mathsf{\text{TP}}}{\mathsf{\text{TP}}+\mathsf{\text{FP}}}\right)$ and recall $\left(\frac{\mathsf{\text{TP}}}{\mathsf{\text{TP}}+\mathsf{\text{FN}}}\right)$ for each computed partition is shown along the last row and the last column respectively.