search

rouyang2017 / SISSO

A data-driven method combining symbolic regression and compressed sensing for accurate & interpretable models.
Apache License 2.0
234 stars 77 forks source link

error in first run #27

Closed mahditarighi closed 3 years ago

mahditarighi commented 4 years ago

Dear Dr. Ouyang I'm Innovator in using sisso code and would like to use it in my machine-learning projects. However, I compiled it by mpiiforf without any compilation error, but when I run it at the presence of SISSO.in and train.dat files, the code crashes and shows this error:

forrtl: severe (59): list-directed I/O syntax error, unit -5, file Internal List-Directed Read
Image              PC                Routine            Line        Source             
sisso              00000000004986E6  Unknown               Unknown  Unknown
sisso              00000000004B7BAF  Unknown               Unknown  Unknown
sisso              00000000004B663E  Unknown               Unknown  Unknown
sisso              000000000048D611  Unknown               Unknown  Unknown
sisso              0000000000402AEE  Unknown               Unknown  Unknown
libc.so.6          00002BA0BDD06830  Unknown               Unknown  Unknown
sisso              00000000004029E9  Unknown               Unknown  Unknown

Both SISSO.in and train.dat are attached for clarity. This is my SISSO.in file:

!_________________________________________________________________
! keywords for the target properties                               
!_________________________________________________________________
ptype=1                               
ntask=1                               
nsample=33                            ! number of samples for each task
task_weighting=1
desc_dim=5                            ! dimension of the descriptor  
restart=.false.                       ! set .true. to continue a job that was stopped but not yet finished 
!_________________________________________________________________
!keywords for feature construction and sure independence screening 
!_________________________________________________________________
nsf= 4                            ! number of scalar features (one feature is one number for each material)
rung=2                                ! rung (<=3) of the feature space to be constructed (times of applying the opset recursively)
opset='(+)(-)(*)(/)(exp)(log)(^-1)(^2)(^3)(sqrt)(cbrt)(|-|)'
maxcomplexity=10                      ! max feature complexity (number of operators in a feature)
dimclass=(1:2:3:4)                    ! group features according to their dimension/unit; those not in any () are dimensionless
maxfval_lb=1e-3                       ! features having the max. abs. data value < maxfval_lb will not be selected 
maxfval_ub=1e5                        ! features having the max. abs. data value > maxfval_ub will not be selected
subs_sis=50                          ! size of the SIS-selected (single) subspace for each descriptor dimension
!_________________________________________________________________
!keywords for descriptor identification via a sparsifying operator
!_________________________________________________________________
method='L0'                           ! sparsification operator: 'L1L0' or 'L0'; L0 is recommended!
fit_intercept=.true.                  ! fit to a nonzero intercept (.true.) or force the intercept to zero (.false.)
metric='RMSE'                         ! for regression only, the metric for model selection: RMSE,MaxAE
nm_output=100                         ! number of the best models to output

train.dat :

materials    dft_half_gap    pbe_gap         total_e            colomb_pot_e                  colomb_e
AlAs-216      3.149          1.355         -68080.02590        -104935.5177              -134814.8317
AlAs-186      3.069          1.689         -136160.0320        -209869.5141              -269630.2325
AlN-186       6.121          4.129         -16164.42650        -22887.61690              -30984.17055
AlN-216       5.667          3.194         -8082.159900        -11441.74040              -15491.99290
AlN-225       6.800          4.521         -8081.988900        -11387.52260              -15490.23130
AlP-186       3.330          1.857         -31778.35700        -46347.78760              -61421.24900
AlP-216       3.121          1.458         -15889.16660        -23174.11200              -30710.30160
AlSb-216      2.480          1.170         -182947.1691        -296433.0431              -370563.0144
BAs-186       2.116          1.041         -124315.2232        -192401.9206              -246681.0124
BAs-216       2.121          1.089         -62157.60320        -96202.02930              -123340.4979
Be2C-225      2.932          1.081         -1832.390600        -2288.257900              -3355.758500
BeO-186       10.504         7.532         -4888.655000        -6466.508300              -9150.075400
BeS-216       4.865          2.919         -11247.25590        -16533.60910              -21778.02410
BeSe-194      2.069          0.445         -132971.4590        -206458.1258              -264223.1369
BeSe-216      4.421          2.478         -66486.60637        -103300.2282              -132112.6400
BeSe-225      1.668          0.185         -66485.63960        -103228.3446              -132111.3807
BN-186        7.404          5.046         -4320.406000        -5625.691400              -8039.889500
BN-194        6.287          4.279         -4320.343300        -5791.917900              -8042.123700
BN-216        6.574          4.300         -2160.242300        -2811.809600              -4019.990000
BP-186        1.989          0.913         -19934.36640        -28959.59100              -38473.69420
BP-216        1.998          1.114         -9967.189900        -14479.93150              -19236.86480
BSb-216       1.440          0.671         -177024.8354        -287628.7633              -359087.5343
CaO-225       6.539          3.550         -20536.81340        -30823.76600              -40018.13260
CaS-225       4.226          2.178         -29341.50050        -44176.84650              -57223.23550
CaSe-216      5.301          3.138         -84580.19460        -131056.9032              -167559.0155  
CdS-216       2.720          1.008         -163052.1670        -261587.9915              -328687.1789
CdSe-216      2.130          0.463         -218291.8035        -348406.6972              -439023.3847
GaAs-216      1.598          0.400         -114347.7170        -177044.2114              -226854.0568
GaN-186       3.636          1.879         -108696.6435        -167015.0723              -215058.1597
GaN-216       3.435          1.709         -54348.31670        -83505.50830              -107529.2433
GaN-225       2.626          0.530         -54347.46020        -83419.36840              -107526.7074
GaP-186       2.434          1.288         -124313.2937        -190563.5159              -245498.9299
GaP-216       2.764          1.462         -62156.71210        -95270.00460              -122749.5544

Any guideline would be greatly appreciated.

rouyang2017 commented 4 years ago

Hi. In the SISSO.in file, please change "dimclass=(1:2:3:4) " to "dimclass=(1:4)" and try again.

mahditarighi commented 4 years ago

Great! Thanks a lot! It works.