Add files via upload

input_templates/SISSO.in

@@ -0,0 +1,38 @@
+!>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
+! Texts after a exclamation mark (!) are comments
+! The (R), (C) and (R&C) denotes the keyword used by regression, classification, and both, respectively.
+! A complete list and more explanations on these keywords can be found in the SISSO_Guide.pdf
+! The setting below is just an example, and user may need to change them for their jobs.
+!>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
+ptype=1                !Property type 1: regression, 2:classification.
+ntask=1                !(R&C) Multi-task learning (MTL) is invoked if >1.
+scmt=.false.           !(R) Sign-Constrained MTL is invoked if .true.
+desc_dim=2             !(R&C) Dimension of the descriptor/model.
+nsample=5              !(R) Number of samples in train.dat. Set nsample=N1,N2,... for MTL.
+!nsample=(n1,n2,...)   !(C) Number of samples. Set nsample=(n1,n2,...),(m1,m2,...),... for MTL.
+restart=0              !(R&C) 0: starts from scratch, 1: continues the job(progress in the file CONTINUE)
+
+!>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
+! Feature construction (FC) and sure independence screening (SIS)
+! Implemented operators:(+)(-)(*)(/)(exp)(exp-)(^-1)(^2)(^3)(sqrt)(cbrt)(log)(|-|)(scd)(^6)(sin)(cos)
+! scd: standard Cauchy distribution
+!>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
+fstore=1               !(R&C) Features storage in memory. 1: by data (fast); 2: by S-expression (low-memory)
+nsf= 3                 !(R&C) Number of scalar features provided in the file train.dat
+ops='(+)(-)(*)(/)'     !(R&C) Operators to be customized by user from the list shown above.
+fcomplexity=3          !(R&C) Maximal feature complexity (# of operators in a feature), starting from 0.
+funit=(1:2)(3:3)       !(R&C) Feature unit: (n1:n2), features from n1 to n2 in train.dat have the same unit 
+fmax_min=1e-3          !(R&C) The feature will be discarded if the max. abs. value in it is < fmax_min.
+fmax_max=1e5           !(R&C) The feature will be discarded if the max. abs. value in it is > fmax_max.
+nf_sis=50000           !(R&C) Number of features in each of the SIS-selected subspace. 
+
+!>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
+! Descriptor identification (DI) via sparse regression (SO)
+!>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
+method_so= 'L0'        !(R&C) 'L0' or 'L1L0'(LASSO+L0). 'L0' is always recommended.
+fit_intercept=.true.   !(R) Fit to a nonzero (.true.) or zero (.false.) intercept for the linear model.
+metric= 'RMSE'         !(R) The metric for model selection in regression: RMSE or MaxAE (max absolute error)
+nmodel=100             !(R&C) Number of the top-ranked models to output (see the folder 'Models')
+isconvex=(1,1,...)     !(C) Each data group constrained to be convex domain, 1: YES; 0: NO
+bwidth=0.001           !(C) Boundary tolerance for classification 
+

input_templates/train.dat_classification

@@ -0,0 +1,6 @@
+materials           feature1  feature2  feature3
+sample1_group1       0.8626    0.7043    0.6312
+sample2_group1       0.7260    0.7818    0.6119
+sample1_group2       0.4943    0.0044    0.4420
+sample2_group2       0.0106    0.0399    0.9877
+sample3_group2       0.0970    0.3199    0.5504

input_templates/train.dat_classification_multitask

@@ -0,0 +1,17 @@
+materials                  feature1  feature2  feature3
+sample1_group1_task1         xxx       xxx        xxx        
+sample2_group1_task1         xxx       xxx        xxx
+sample1_group2_task1         xxx       xxx        xxx
+sample2_group2_task1         xxx       xxx        xxx
+sample3_group2_task1         xxx       xxx        xxx
+sample1_group1_task2         xxx       xxx        xxx
+sample2_group1_task2         xxx       xxx        xxx
+sample3_group1_task2         xxx       xxx        xxx
+sample4_group1_task2         xxx       xxx        xxx
+sample1_group2_task2         xxx       xxx        xxx
+sample2_group2_task2         xxx       xxx        xxx
+sample3_group2_task2         xxx       xxx        xxx
+sample4_group2_task2         xxx       xxx        xxx
+sample1_group3_task2         xxx       xxx        xxx
+sample2_group3_task2         xxx       xxx        xxx
+sample3_group3_task2         xxx       xxx        xxx

input_templates/train.dat_regression

@@ -0,0 +1,6 @@
+materials    property  feature1  feature2  feature3
+sample1       3.0862    0.8626    0.7043    0.6312
+sample2       2.8854    0.7260    0.7818    0.6119
+sample3       0.6907    0.4943    0.0044    0.4420
+sample4       0.9902    0.0106    0.0399    0.9877
+sample5       0.7242    0.0970    0.3199    0.5504

input_templates/train.dat_regression_multitask

@@ -0,0 +1,13 @@
+materials          property  feature1  feature2  feature3
+sample1_task1        xxx       xxx        xxx      xxx         
+sample2_task1        xxx       xxx        xxx      xxx      
+sample3_task1        xxx       xxx        xxx      xxx      
+sample4_task1        xxx       xxx        xxx      xxx      
+sample5_task1        xxx       xxx        xxx      xxx      
+sample1_task2        xxx       xxx        xxx      xxx      
+sample2_task2        xxx       xxx        xxx      xxx      
+sample3_task2        xxx       xxx        xxx      xxx      
+sample4_task2        xxx       xxx        xxx      xxx      
+sample5_task2        xxx       xxx        xxx      xxx      
+sample6_task2        xxx       xxx        xxx      xxx
+sample7_task2        xxx       xxx        xxx      xxx