Upload New File

Minimum Working Exemple/run.py

+import os
+import sys
+import ase.io
+import numpy as np
+from ase import Atoms, Atom
+from ase.io import Trajectory
+from sklearn.metrics import mean_squared_error
+from dscribe.descriptors import SOAP
+from scipy.interpolate import UnivariateSpline
+from sklearn.gaussian_process import GaussianProcessRegressor
+from sklearn.gaussian_process.kernels import RBF
+from sklearn.model_selection import train_test_split, learning_curve, validation_curve, GridSearchCV
+from joblib import Parallel, delayed
+from ase import neighborlist 
+from sklearn.preprocessing import StandardScaler
+from create_descriptor import *
+from tool import *
+
+if __name__ == '__main__':
+    #initialisation
+    atomseul='H' #atome adsorbed
+    poscar_file='/mnt/beegfs/gzc01/iht74/THESE/Ag/POSCAR' #slab with no adsorbate
+    data_folder='/mnt/beegfs/gzc01/iht74/THESE/Ag/H/data' #folder where decriptors are saved
+    train_file='train.traj' 
+    atoms_train=Trajectory(train_file)
+    
+    #identification of species and adsorbate
+    species=[]
+    elem=atoms_train[0].get_chemical_symbols() 
+    #identification de l atome seul dans la structure
+    for el in range(len(elem)): 
+        if elem[el] not in species:
+            species.append(elem[el])
+            if elem[el]== atomseul:
+                ats=el
+    
+    #---> we create a 2*2 supercell for adsorbate to be far enough from pbc images, comment line if not necessary
+    atoms=ase.io.read(poscar_file, format='vasp')
+    atoms*=(2,2,1)
+    
+    #create a n*n grid where adsorbtion is predicted
+    xx,yy,zz=pos_to_relax(poscar_file,n=20)
+    
+    #create the descritors
+    params={'species':species,'l_max':3,'n_max':6,'r_cut':6}
+    desc=create_descriptor(method='soap',params=params,ats=ats)
+    X_train=desc.create(atoms_train,load=False)#--> True will save the decriptor in the data folder
+    y_train=[at.get_potential_energy() for at in atoms_train]
+
+    y_mean=np.mean(y_train)
+    y_train=y_train-y_mean
+    scaler=StandardScaler()
+    X_train=scaler.fit_transform(X_train)  
+
+    #fit and prediction
+    kernel=1**2 * RBF(length_scale=200,length_scale_bounds=(1/np.sqrt(2*1e-0),1/np.sqrt(2*1e-8)))
+    GP = GaussianProcessRegressor(kernel=kernel)
+    parameters = {'alpha':[1e-4,]}
+    g_search = GridSearchCV(GP, parameters)
+    g_search.fit(X_train, y_train)
+
+          
+    Parallel(n_jobs=10)(delayed(run_para)([xx[i],yy[i],zz[i]],i,desc,scaler,g_search,poscar=atoms) for i in range(len(xx)))
\ No newline at end of file