Identification of Dry Bean Varieties Based on Multiple Attributes Using CatBoost Machine Learning Algorithm

Table 2

Dataset statistics.

Features	Area	Perimeter	MajorAxisLength	MinorAxisLength	AspectRation	Eccentricity	ConvexArea	EquivDiameter	Extent	Solidity	Roundness	Compactness	ShapeFactor1	ShapeFactor2	ShapeFactor3	ShapeFactor4
Quantile statistics
Minimum	20786.00	534.72	192.80	122.51	1.025	0.2190	21057.00	162.68	0.5724	0.9446	0.490	0.641	0.0028	0.0006	0.410	0.957
5-th percentile	29398.35	636.31	229.51	158.86	1.213	0.5656	29732.30	193.47	0.6554	0.9775	0.764	0.691	0.0034	0.0008	0.478	0.986
Q1	40329.00	743.56	268.51	184.64	1.443	0.7209	40761.25	226.60	0.7226	0.9848	0.823	0.758	0.0053	0.0010	0.574	0.993
Median	52981.50	911.06	350.62	203.69	1.575	0.7724	53858.50	259.73	0.7637	0.9880	0.866	0.795	0.0063	0.0014	0.632	0.996
Q3	75098.75	1070.86	405.75	242.33	1.727	0.8154	76264.75	309.22	0.7888	0.9900	0.908	0.831	0.0069	0.0020	0.690	0.998
95-th percentile	181172.55	1627.96	615.47	381.17	2.078	0.8766	183753.30	480.29	0.8150	0.9921	0.958	0.907	0.0080	0.0027	0.823	0.999
Maximum	254616	1985.37	738.86	460.20	2.430	0.9114	263261	569.37	0.8584	0.9947	0.988	0.987	0.0105	0.0037	0.975	1.000
Range	233830	1450.65	546.06	337.69	1.405	0.6925	242204	406.69	0.2860	0.0501	0.498	0.347	0.0077	0.0031	0.564	0.042
Interquartile range (IQR)	34769.75	327.30	137.24	57.70	0.284	0.0945	35503.50	82.62	0.0662	0.0052	0.085	0.073	0.0016	0.0010	0.116	0.005
Descriptive statistics
Standard deviation	46096.53	296.60	115.00	66.84	0.246	0.0915	46750.50	85.16	0.0495	0.0049	0.0600	0.061	0.001	0.001	0.099	0.005
Coefficient of variation (CV)	0.66	0.31	0.32	0.29	0.154	0.1211	0.66	0.30	0.0658	0.0050	0.0695	0.077	0.229	0.401	0.155	0.005
Kurtosis	2.01	0.56	0.46	1.09	0.000	1.6840	2.02	0.89	0.7746	7.0853	0.4222	−0.223	−0.289	−0.587	−0.104	6.656
Mean	69718.99	969.54	362.43	227.47	1.597	0.7558	70681.22	285.52	0.7525	0.9868	0.8637	0.796	0.006	0.002	0.638	0.994
Median absolute deviation (MAD)	15923.50	164.53	70.33	27.03	0.141	0.0460	16298.00	39.65	0.0301	0.0024	0.0424	0.037	0.001	0	0.058	0.002
Skewness	1.73	1.14	1.02	1.43	0.465	−1.1675	1.73	1.32	−0.9632	−1.996	−0.442	0.156	−0.458	0.653	0.358	−2.035