def pro_chargepath(self,file):
"""parse charge_path
Here may have bugs if the input is not generated by the Gaussian.
Formats:
nm atomtype charge
1 C 0.1
2 H 0.2
3 O -0.2
Only three columns are used.
1st : input index
2nd : atom type (ignored)
3rd : value
Otherwise,
Warning will be printed
"""
self.charge_path = file
file_size_check(self.charge_path,fsize=100)
datalist = []
with open(self.charge_path,mode='rt') as f:
while True:
line = f.readline()
if len(line) == 0:
break
sub = line[:line.find('#')] if line.find('#') != -1 else line
lst = sub.split()
if len(lst) == 0: continue
if len(lst) == 3:
try:
n = int(lst[0])
v = float(lst[2])
except ValueError:
print(line)
raise ValueError('wrong defined line')
if n <= self.atomnm:
datalist.append(v)
else:
print('Warning: ignoring ' + line)
if len(datalist) % self.atomnm != 0:
raise ValueError('not corresponded: atomnm & charge_path')
# to avoid using an extra numpy module
# works similar like;
# numpy.array(datalist).reshape(len(datalist)//self.atomnm,self.atomnm)
self.profile = []
i = 0
while i < len(datalist):
ls = []
for j in range(self.atomnm):
ls.append(datalist[i])
i += 1
self.profile.append(ls)
def __init__(self, *args, **kwargs):
if 'toppath' in kwargs and kwargs['toppath'] is not None:
self.toppath = kwargs['toppath']
file_size_check(self.toppath, fsize=10)
else:
raise ValueError('toppath is missing')
if 'file_path' in kwargs and kwargs['file_path'] is not None:
self.file_path = kwargs['file_path']
file_size_check(self.file_path, fsize=500)
else:
raise ValueError('file_path is missing')
self.pro_toppath(self.toppath)
self.pro_file_path(self.file_path)
if 'select_range' in kwargs and kwargs['select_range'] is not None:
try:
self.select_range = float(kwargs['select_range'])
if self.select_range <= 0:
raise ValueError
except ValueError:
raise ValueError('select_range has to be a positive number')
else:
self.select_range = 10
if 'reschoose' in kwargs and kwargs['reschoose'] is not None:
tmp = kwargs['reschoose'].strip()
self.reschoose = 'all' if len(tmp) == 0 else tmp.lower()
else:
self.reschoose = 'all'
if 'gennm' in kwargs and kwargs['gennm'] is not None:
try:
self.gennm = int(kwargs['gennm'])
if self.gennm <= 0: raise ValueError
except ValueError:
raise ValueError('gennm has to be positive integer')
else:
self.gennm = 5
self.pro_selections()
if 'basis_set' in kwargs and kwargs['basis_set'] is not None:
self.basis_set = kwargs['basis_set'].strip()
else:
self.basis_set = '# HF/6-31G(d) Pop=CHelpG'
if 'charge_spin' in kwargs and kwargs['charge_spin'] is not None:
self.charge_spin = kwargs['charge_spin'].strip()
else:
self.charge_spin = '0 1'
if 'fname' in kwargs and kwargs['fname'] is not None:
self.fname = kwargs['fname'].strip()
else:
self.fname = 'GaussInput'
def prochargepath(self, charge_path, in_keyword='ATOM'):
"""
Parameter:
charge_path : str | List[[float,float]]
Returns:
charge_list : List[[float,float], ...]
"""
if isinstance(charge_path, list):
# change the list name
charge_list = charge_path
for i in charge_list:
if isinstance(i,list) and len(i) == 2 and \
isinstance(i[0],(float,int)) and isinstance(i[1],(float,int)):
pass
else:
print('charge_path has to be a 2D nested number list')
print('its each sublist should only contain two indices')
raise ValueError('wrong defined')
elif isinstance(charge_path, str):
charge_list = []
if len(charge_path.strip()) != 0:
file_size_check(charge_path, fsize=100)
with open(charge_path.strip(), mode='rt') as f:
while True:
line = f.readline()
if len(line) == 0:
break
sub = line if line.find(
'#') == -1 else line[:line.find('#')]
ltmp = sub.split()
bo = False
if len(ltmp) == 0:
continue
elif len(ltmp) == 4 and ltmp[0].upper() == in_keyword:
try:
t1 = float(ltmp[2])
t2 = float(ltmp[3])
charge_list.append([t1, t2])
except ValueError:
bo = True
else:
bo = True
if bo:
print(line)
raise ValueError('wrong defined, charge_path')
else:
raise ValueError('wrong defined, charge_path')
return charge_list
def profilepath(self):
"""process file_path based on self.error_tolerance
Attributes:
self.mlinlist
self.totlist
"""
file_size_check(self.file_path, fsize=500)
profile = func_file_input(self.file_path,
dtype=float,
bool_tail=True,
cut_keyword=self.cut_keyword,
bool_force_cut_kw=True)
self.mlinlist = []
for i in profile:
self.totlist.append(i[:-1])
if self.error_tolerance == 'nan':
self.mlinlist.append(i[:-1])
elif isinstance(i[-1], (float, int)):
if self.bool_abscomp and abs(i[-1]) <= self.error_tolerance:
self.mlinlist.append(i[:-1])
elif i[-1] <= self.error_tolerance:
self.mlinlist.append(i[:-1])
if len(self.mlinlist) < 5:
print('the number of entry to be trained has to be no less than 5')
raise ValueError('too less parameters')
print('For error_tolerance: {:}'.format(self.error_tolerance))
print('Number of ML_charge_list is: {:}'.format(len(self.mlinlist)))
if self.bool_abscomp:
print('Note: the absolute comparison is implemented')
else:
print('Note: the average comparison is implemented')
print(' which may cause positive and negative cancellation')
print('\nDo you want to continue? y/yes, else quit?', end=' ')
get = input()
if get.lower() not in ['y', 'yes']:
print('Warning: you have decided to quit the ML charge generation')
raise RuntimeError('user decided quit')
def _f_pro_filepath(self):
log = file_size_check(self.file_path, fsize=500)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return 0
log, profile = function_file_input(self.file_path,
dtype=float,
bool_tail=True,
cut_keyword=self.cut_keyword,
bool_force_cut_kw=True)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return 0
self.mlinlist = []
for i in profile:
self.totlist.append(i[:-1])
if self.bool_abscomp and abs(i[-1]) <= self.error_tolerance:
self.mlinlist.append(i[:-1])
elif i[-1] <= self.error_tolerance:
self.mlinlist.append(i[:-1])
print('For the error_tolerance: {}'.format(self.error_tolerance))
print('The selected number of ML_charge_list is: {:d}'.format(
len(self.mlinlist)))
if self.bool_abscomp:
print('Note: the absolute comparison is implemented')
else:
print(
'Note: the average comparison is implemented, which may cause positive and negative cancellation'
)
print('\nDo you want to continue? y/yes for continue, else quit?',
end=' ')
getinput = input()
if getinput.upper() != 'Y' and getinput.upper() != 'YES':
self.log['nice'] = False
self.log['info'] = ''
print(
'Warning: you have decided to quit the ML charge generateion')
return 0
if len(self.mlinlist) < 5:
self.log['nice'] = False
self.log[
'info'] = 'Error: for machine learning, the number of entry to be trained has to be no less than 5'
return 0
return 1
def _f_pro_charge_path(self,charge_path):
if isinstance(charge_path,list):
# change the list name
charge_list = charge_path
if len(charge_path) == 0:
print('Error: it seems the charge_path is a list, however, its length cannot be zero')
exit()
for i in charge_list:
if isinstance(i,list) and len(i) == 2 and (isinstance(i[0],int) or isinstance(i[0],float)) \
and (isinstance(i[1],int) or isinstance(i[1],float)):
pass
else:
self.log['nice'] = False
self.log['info'] = 'Error: the charge_path has to be a 2D nested number list\n' + \
' and its each sublist only contains two indices'
return 1
elif isinstance(charge_path,str):
log = file_size_check(charge_path,fsize=100)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return 1
charge_list = []
with open(charge_path,mode='rt') as f:
while True:
line = f.readline()
if len(line) == 0:
break
else:
ltmp = line[:line.find('#')].split()
if len(ltmp) != 0 and ltmp[0] == self.in_keyword:
ls = []
ls.append(float(ltmp[2]))
ls.append(float(ltmp[3]))
charge_list.append(ls)
return charge_list
def _f_pro_charge_path(self, charge_path, charge_extend_by):
"""Randomly generate a new charge range based on the charge_extend_by parameters, the return values
are normal charge_range and this new charge_range"""
def bound_mutation(prolist, extend_by, des='string'):
if len(prolist) == 0:
self.log['nice'] = False
self.log['info'] = 'Error: it seems the charge_path is a {:s}, however, nothing was input\n'.format(des) + \
' : Or it is not correctly defined'
return 0
newlist = []
for i in prolist:
vs = i[0] + (random.randrange(3) - 1) * extend_by
vt = i[1] + (random.randrange(3) - 1) * extend_by
ls = []
if vt > vs:
ls.append(vs)
ls.append(vt)
elif vt == vs:
ls.append(vs)
ls.append(vs + 0.1)
else:
ls.append(vt)
ls.append(vs)
newlist.append(ls)
return newlist
if isinstance(charge_path, list):
for i in charge_list:
if isinstance(i,list) and len(i) == 2 and (isinstance(i[0],int) or isinstance(i[0],float)) \
and (isinstance(i[1],int) or isinstance(i[1],float)):
pass
else:
self.log['nice'] = False
self.log['info'] = 'Error: the charge_path has to be a 2D nested number list\n' + \
' and its each sublist only contains two indices'
return 0, 0
# change the list name
charge_nor_list = charge_path
charge_new_list = bound_mutation(charge_path,
charge_extend_by,
des='list')
elif isinstance(charge_path, str):
log = file_size_check(charge_path, fsize=50)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return 0, 0
charge_nor_list = []
with open(charge_path, mode='rt') as f:
while True:
line = f.readline()
if len(line) == 0:
break
else:
ltmp = line[:line.find('#')].split()
if len(ltmp) != 0 and ltmp[0] == 'ATOM':
ls = []
ls.append(float(ltmp[2]))
ls.append(float(ltmp[3]))
charge_nor_list.append(ls)
charge_new_list = bound_mutation(charge_nor_list,
charge_extend_by,
des='file\'s path')
else:
self.log['nice'] = False
self.log[
'info'] = 'Error: the charge file has to be correctly defined'
return 0, 0
return charge_nor_list, charge_new_list
def pro_settingfile(settingfile):
"""Process the input settingfile"""
def f_remove_comment(string):
if string.find('#') == -1:
return string.strip()
return string[:string.find('#')]
log = file_size_check(settingfile, fsize=5)
if not log['nice']:
print(log['info'])
exit()
# this universal string is used to exit prompt
error_info = 'Error: the input setting file is wrong'
infile = []
with open(settingfile, mode='rt') as f:
while True:
line = f.readline()
if len(line) == 0:
break
else:
lt = line.split()
if len(lt) == 0 or lt[0] == '#' or (len(lt[0]) > 1
and lt[0][0] == '#'):
continue
else:
if line.find('=') == -1:
print(error_info)
print('Error line: ', line)
exit()
else:
lp = line.split('=', maxsplit=1)
partmp = lp[0].split()
if len(partmp) != 1:
print(error_info)
print('Error line: ', line)
exit()
parname = partmp[0].lower()
ls = []
ls.append(parname)
# take care of 'basis_set' comment exception
if parname != 'basis_set':
# take care of python representation string list to real python list
if parname == 'symmetry_list' or parname == 'counter_list' or \
parname == 'offset_list' or parname == 'atomtype_list':
stmp = f_remove_comment(lp[1])
if len(stmp.split()) == 0:
ls.append(None)
else:
try:
s = eval(stmp)
except:
print(
'Error: the wrong defined python representation parameter'
)
print('Error line: ', line)
exit()
ls.append(s)
# take care of charge_spin exception
elif parname == 'charge_spin':
stmp = f_remove_comment(lp[1])
lr = stmp.split()
if len(lr) == 0:
ls.append('0 1')
elif len(lr) == 2:
ls.append(lr[0] + ' ' + lr[1])
else:
print(
'Error: the wrong definition of charge_spin parameter'
)
print('Error line: ', line)
exit()
# take care of pn_limit exception
elif parname == 'pn_limit':
stmp = f_remove_comment(lp[1])
if len(stmp.split()) == 0:
ls.append(None)
else:
ls.append(stmp)
else:
stmp = f_remove_comment(lp[1])
lr = stmp.split()
if len(lr) == 0:
ls.append(None)
elif len(lr) == 1:
ls.append(sub_eval(lr[0]))
else:
print(error_info)
print('Error line: ', line)
exit()
else:
ndx_first = lp[1].find('#')
if ndx_first == -1:
ltmp = ''
for i in lp[1].split():
ltmp += i + ' '
ls.append(ltmp)
elif ndx_first == len(lp[1]):
ls.append('#')
else:
ndx_second = lp[1][ndx_first + 1:].find('#')
if ndx_second == -1:
ltmp = ''
for i in lp[1].split():
ltmp += i + ' '
ls.append(ltmp)
else:
ltmp = ''
for i in lp[1][:ndx_first + ndx_second +
1].split():
ltmp += i + ' '
ls.append(ltmp)
infile.append(ls)
# process the infile to different blocks
i = 0
profile = []
while i < len(infile):
ls = []
if infile[i][0] == 'command':
ls.append(infile[i])
j = i + 1
while j < len(infile) and infile[j][0] != 'command':
ls.append(infile[j])
j += 1
profile.append(ls)
i = j
else:
i += 1
if len(profile) == 0:
print('Error: no command is found')
exit()
# process the command
prodict = []
for i in profile:
# check the command
cmd = i[0][1].lower()
if not (cmd in par_cmdlist):
print('Error: the command < {:} > is not defined'.format(i[0][1]))
exit()
# ATTENTION! Because of the python 'functionality', here it is very important
# to force python to make a new memory copy of list or dict 'reference'
# to avoid any 'same-memory-reference' allocating
for par in parname_list:
if par['command'].lower() == cmd:
break
fgetdict = {**par}
parlist = [j for j, s in fgetdict.items()]
for name in i:
if not name[0] in parlist:
print('Error: the parameter is not defined')
print(' : In command < {:} >'.format(fgetdict['command']))
print('Error parameter: ', name[0])
exit()
else:
fgetdict[name[0]] = name[1]
prodict.append(fgetdict)
return prodict
def __init__(self, *args, **kwargs):
if 'reschoose' in kwargs and kwargs['reschoose'] is not None:
if isinstance(kwargs['reschoose'], str):
if len(kwargs['reschoose'].strip()) != 0:
self.reschoose = kwargs['reschoose'].strip()
else:
self.reschoose = 'ALL'
else:
print(kwargs['reschose'])
raise ValueError('reschoose is wrong')
else:
self.reschoose = 'ALL'
bo = False
if 'toppath' in kwargs and kwargs['toppath'] is not None:
if isinstance(kwargs['toppath'], str):
if len(kwargs['toppath'].strip()) != 0:
self.toppath = kwargs['toppath'].strip()
else:
bo = True
else:
bo = True
file_size_check(self.toppath, fsize=50)
else:
bo = True
if bo:
raise ValueError('toppath is wrong')
if 'in_keyword' in kwargs and kwargs['in_keyword'] is not None:
if isinstance(kwargs['in_keyword'], str):
if len(kwargs['in_keyword'].strip()) != 0:
self.in_keyword = kwargs['in_keyword'].strip()
else:
self.in_keyword = 'PAIR'
else:
raise ValueError('in_keyword is wrong')
else:
self.in_keyword = 'PAIR'
if 'cut_keyword' in kwargs and kwargs['cut_keyword'] is not None:
if isinstance(kwargs['cut_keyword'], str):
if len(kwargs['cut_keyword'].strip()) != 0:
self.cut_keyword = kwargs['cut_keyword'].strip()
else:
self.cut_keyword = 'MAE'
else:
raise ValueError('cut_keyword is wrong')
else:
self.cut_keyword = 'MAE'
if 'fname' in kwargs and kwargs['fname'] is not None:
if isinstance(kwargs['fname'], str):
if len(kwargs['fname'].strip()) != 0:
self.fname = kwargs['fname'].strip()
else:
self.fname = 'GenGromacsTopfile'
else:
raise ValueError('fname is wrong')
else:
self.fname = 'GenGromacsTopfile'
if 'charge_path' in kwargs and kwargs['charge_path'] is not None:
# func_file_input
charge_path = kwargs['charge_path']
if isinstance(charge_path, str):
file_size_check(charge_path, fsize=50)
self.file_line_chargepath = charge_path
self.prochargefile = func_file_input(
charge_path,
comment_char='#',
dtype=float,
bool_tail=False,
in_keyword=self.in_keyword,
cut_keyword=self.cut_keyword)
elif isinstance(charge_path, list):
self.check_list(charge_path)
self.prochargefile = charge_path
self.file_line_chargepath = 'Note: charge_path input is a list'
else:
print(charge_path)
raise ValueError('charge_path is wrong')
else:
raise ValueError('charge_path is missing')
bo = False
# Note: gennm == 0 means outputs are equal to length of inputs
if 'gennm' in kwargs and kwargs['gennm'] is not None:
if isinstance(kwargs['gennm'], int):
self.gennm = kwargs['gennm']
if self.gennm < 0: bo = True
elif isinstance(kwargs['gennm'], str):
if len(kwargs['gennm'].split()) == 0:
self.gennm = 0
else:
try:
self.gennm = int(kwargs['gennm'])
if self.gennm < 0: raise ValueError
except ValueError:
bo = True
else:
bo = True
else:
self.gennm = 0
if bo:
raise ValueError('gennm is wrong, it has to be a positive integer')
if self.gennm == 0: self.gennm = len(self.prochargefile)
if self.gennm < len(self.prochargefile):
print('Warning: number of charge entries are larger than gennm')
else:
self.gennm = len(self.prochargefile)
# Note: symmetry_list has to deduct 1 for python-list notation
if 'symmetry_list' in kwargs and kwargs['symmetry_list'] is not None:
self.check_symmetry(kwargs['symmetry_list'])
else:
self.symmetry_list = []
self.pro_topfile(self.toppath)
# check the relation topfile with symmetry_list
if self.symmetry_list is None or len(self.symmetry_list) == 0:
self.symmetry_list = list(range(len(self.atomndx)))
elif len(self.atomndx) < self.symmetry_length:
raise ValueError('symmetry_list & topfile are not corresponded')
elif len(self.atomndx) > self.symmetry_length:
print('Note: only first residue is going to be changed')
# check the relation chargefile with symmetry_list
count = 1
lth = len(self.symmetry_list)
ls = []
for i in self.prochargefile[:self.gennm]:
if len(i) < lth:
raise ValueError(
'symmetry_list & topfile are not corresponded')
elif len(i) > lth:
ls.append(count)
count += 1
if len(ls) > 0:
print('Warning: number of charges are larger atoms in the topfile')
print(' : truncation will happen')
print(' : the number of this charge pair is:')
for count in ls:
print(count, end=' ')
print()
def __init__(self, **kwargs):
if 'file_path' in kwargs and kwargs['file_path'] is not None:
self.filepath = kwargs['file_path'].strip()
file_size_check(self.filepath, fsize=200)
else:
raise ValueError('no inputs')
if 'stepsize' in kwargs and kwargs['stepsize'] is not None:
try:
self.stepsize = float(kwargs['stepsize'])
if self.stepsize <= 0:
raise ValueError
except ValueError:
print('stepsize has to be a positive number')
raise ValueError('wrong defined')
else:
self.stepsize = 0.01
if 'percent' in kwargs and kwargs['percent'] is not None:
try:
self.percent = float(kwargs['percent'])
if self.percent <= 0 or self.percent > 1:
raise ValueError
except ValueError:
print('percent has to be a number within the range 0 to 1')
raise ValueError('wrong defined')
else:
self.percent = 0.95
if 'error_tolerance' in kwargs and kwargs[
'error_tolerance'] is not None:
try:
self.error_tolerance = float(kwargs['error_tolerance'])
except ValueError:
print('error_tolerance has to be a number')
raise ValueError('wrong defined')
else:
self.error_tolerance = 0.28
if 'bool_abscomp' in kwargs:
self.bool_abscomp = False if kwargs[
'bool_abscomp'] is False else True
else:
self.bool_abscomp = True
if 'cut_keyword' in kwargs and kwargs['cut_keyword'] is not None:
self.cut_keyword = kwargs['cut_keyword'].strip()
if len(self.cut_keyword) == 0: self.cut_keyword = 'MAE'
else:
self.cut_keyword = 'MAE'
if 'pallette_nm' in kwargs and kwargs['pallette_nm'] is not None:
try:
self.pallette_nm = int(kwargs['pallette_nm'])
if self.pallette_nm <= 0:
raise ValueError
except ValueError:
print('pallette_nm has to be a positive integer')
raise ValueError('wrong defined')
else:
self.pallette_nm = 50
if 'atomtype_list' in kwargs and kwargs['atomtype_list'] is not None:
if isinstance(kwargs['atomtype_list'], list):
if len(kwargs['atomtype_list']) == 0:
self.atomtype_list = None
else:
self.atomtype_list = kwargs['atomtype_list']
else:
print('atomtype_list has to be a list')
raise ValueError('wrong defined')
else:
self.atomtype_list = None
if 'fname' in kwargs and kwargs['fname'] is not None:
self.fname = kwargs['fname'].strip()
if len(self.fname) == 0: self.fname = 'FSS_analysis'
else:
self.fname = 'FSS_analysis'
if 'color_map' in kwargs and kwargs['color_map'] is not None:
self.color_map = kwargs['color_map']
else:
self.color_map = 'rainbow'
def __init__(self, *args, **kwargs):
self.log = {
'nice': True,
}
if 'toppath' in kwargs and kwargs['toppath'] is not None:
self.toppath = kwargs['toppath']
log = file_size_check(self.toppath, fsize=10)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
else:
self.log['nice'] = False
self.log['info'] = 'Error: the parameter toppath is missing'
return
if 'file_path' in kwargs and kwargs['file_path'] is not None:
self.file_path = kwargs['file_path']
log = file_size_check(self.file_path, fsize=500)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
else:
self.log['nice'] = False
self.log['info'] = 'Error: the parameter file_path is missing'
return
self._f_pro_toppath(self.toppath)
if not self.log['nice']: return
self._f_pro_file_path(self.file_path)
if not self.log['nice']: return
self._f_remove_periodic()
if 'select_range' in kwargs and kwargs['select_range'] is not None:
try:
self.select_range = float(kwargs['select_range'])
if self.select_range <= 0:
raise ValueError
except ValueError:
self.log['nice'] = False
self.log[
'info'] = 'Error: the parameter select_range has to be a positve number'
return
else:
self.select_range = 10
self._f_pro_selections()
if 'gennm' in kwargs and kwargs['gennm'] is not None:
try:
self.gennm = int(kwargs['gennm'])
if self.gennm > len(self.prolist) or self.gennm <= 0:
self.gennm = len(self.prolist)
except ValueError:
self.log['nice'] = False
self.log['info'] = 'Error: the parameter gennm has to be a number\n' + \
'Error gennm: ' + kwargs['gennm']
return
elif len(self.prolist) < 5:
self.gennm = len(self.prolist)
else:
self.gennm = 5
self._f_random_selections()
if 'basis_set' in kwargs and kwargs['basis_set'] is not None:
self.basis_set = kwargs['basis_set']
else:
self.basis_set = '# HF/6-31G(d) Pop=CHelpG'
if 'charge_spin' in kwargs and kwargs['charge_spin'] is not None:
self.charge_spin = str(kwargs['charge_spin'])
else:
self.charge_spin = '0 1'
if 'fname' in kwargs and kwargs['fname'] is not None:
self.fname = str(kwargs['fname'])
else:
self.fname = 'GaussInput'
self._prefile()
if not self.log['nice']: return
def __init__(self,*args,**kwargs):
self.log = {'nice':True,}
bo = False
if 'atomnm' in kwargs and kwargs['atomnm'] is not None:
try:
self.atomnm = int(kwargs['atomnm'])
if self.atomnm <= 0:
raise ValueError
except ValueError:
bo = True
self.log['info'] = 'Error: the parameter atomnm has to be a positive number'
else:
bo = True
self.log['info'] = 'Error: the parameter atomnm is missing'
if bo:
self.log['nice'] = False
return
if 'charge_path' in kwargs and kwargs['charge_path'] is not None:
"""ATTENTION! Here may have bugs, if the input charge_file_path is not
generated by the Gaussian. The follow shows the file format:
nm atomtype charge
1 C 0.1
2 H 0.2
3 O -0.2
Only three columns are used. The first column is the input index,
the second column is the atom-type, the last one is the value"""
self.charge_path = kwargs['charge_path']
mcp = file_size_check(self.charge_path,fsize=100)
if not mcp['nice']:
self.log['nice'] = False
self.log['info'] = mcp['info']
return
datalist = []
with open(self.charge_path,mode='rt') as f:
while True:
line = f.readline()
if len(line) == 0:
break
else:
lst = line[:line.find('#')].split()
if len(lst) == 3 and int(lst[0]) <= self.atomnm:
datalist.append(float(lst[2]))
if len(datalist) % self.atomnm != 0:
self.log['nice'] = False
self.log['info'] = 'Error: wrong input_data_file or atom_number\n' + \
'Error: input charge_file_path: ' + self.charge_path + '\n' + \
'Error input atom_number: ' + str(self.atomnm)
return
# to avoid using an extra numpy module
# works similar like;
# numpy.array(datalist).reshape(len(datalist)//self.atomnm,self.atomnm)
self.profile = []
i = 0
while i < len(datalist):
ls = []
j = 0
while j < self.atomnm:
ls.append(datalist[i])
i += 1
j += 1
self.profile.append(ls)
else:
self.log['nice'] = False
self.log['info'] = 'Error: the parameter charge_path is missing'
return
if 'percent' in kwargs and kwargs['percent'] is not None:
try:
self.percent = float(kwargs['percent'])
if self.percent > 1.0 or self.percent <= 0:
raise ValueError
except ValueError:
self.log['nice'] = False
self.log['info'] = 'Error: the parameter percent has to be a positive number\n' + \
' : and its value must fall within in (0,1]'
return
else:
self.percent = 0.8
if 'stepsize' in kwargs and kwargs['stepsize'] is not None:
try:
self.stepsize = float(kwargs['stepsize'])
if self.stepsize <= 0:
raise ValueError
except ValueError:
self.log['nice'] = False
self.log['info'] = 'Error: the parameter stepsize has to be a positive number'
return
else:
self.stepsize = 0.01
if 'nmround' in kwargs and kwargs['nmround'] is not None:
try:
self.nmround = int(kwargs['nmround'])
if self.nmround < 0:
raise ValueError
except ValueError:
self.log['nice'] = False
self.log['info'] = 'Error: the parameter nmround has to be a positive integer'
return
else:
self.nmround = 3
if 'fname' in kwargs and kwargs['fname'] is not None:
self.fname = str(kwargs['fname'])
else:
self.fname = 'ChargeGenRange'
def __init__(self, *args, **kwargs):
self.log = {
'nice': True,
}
if 'reschoose' in kwargs and kwargs['reschoose'] is not None:
self.reschoose = kwargs['reschoose']
else:
self.reschoose = 'All'
if 'toppath' in kwargs and kwargs['toppath'] is not None:
self.toppath = kwargs['toppath']
log = file_size_check(self.toppath, fsize=50)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
fp = self._f_pro_topfile(self.toppath)
if not self.log['nice']: return
else:
self.log['nice'] = False
self.log['info'] = 'Error: the parameter toppath is missing'
return
if 'in_keyword' in kwargs and kwargs['in_keyword'] is not None:
self.in_keyword = kwargs['in_keyword']
else:
self.in_keyword = 'PAIR'
if 'cut_keyword' in kwargs and kwargs['cut_keyword'] is not None:
self.cut_keyword = kwargs['cut_keyword']
else:
self.cut_keyword = 'MAE'
if 'charge_path' in kwargs and kwargs['charge_path'] is not None:
# function_file_input
charge_path = kwargs['charge_path']
if isinstance(charge_path, str):
log = file_size_check(charge_path, fsize=50)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
self.file_line_chargepath = charge_path
log, self.prochargefile = function_file_input(
charge_path,
comment_char='#',
dtype=float,
bool_tail=False,
in_keyword=self.in_keyword,
cut_keyword=self.cut_keyword)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
elif isinstance(charge_path, list):
dump_value = self._f_list_dcheck(charge_path)
if not self.log['nice']: return
self.prochargefile = charge_path
self.file_line_chargepath = 'Note: charge_path input is a list'
else:
self.log['nice'] = False
self.log['info'] = 'Error: wrong defined charge_path parameter\n' + \
'Error: it only can either be a list or a real file path'
return
else:
self.log['nice'] = False
self.log['info'] = 'Error: the parameter charge_path is missing'
return
if 'gennm' in kwargs and kwargs['gennm'] is not None:
try:
self.gennm = int(kwargs['gennm'])
if self.gennm == 0 or self.gennm > len(self.prochargefile):
self.gennm = len(self.prochargefile)
elif self.gennm < 0:
raise ValueError
except ValueError:
self.log['nice'] = False
self.log['info'] = 'Error: the gennm has to be a positive integer\n' + \
'Error gennm: '+ str(kwargs['gennm'])
return
else:
self.gennm = len(self.prochargefile)
if 'symmetry_list' in kwargs:
symmetry_list = kwargs['symmetry_list']
else:
symmetry_list = None
ndx = len(self.atomndx)
if symmetry_list is None:
symmetry_list = list(range(ndx))
symmetry_length = ndx
self.file_line_symmetry = None
elif isinstance(symmetry_list, list):
if len(symmetry_list) == 0:
symmetry_list = list(range(ndx))
symmetry_length = ndx
self.file_line_symmetry = None
else:
_par = Pro_list(symmetry_list=symmetry_list)
if not _par.log['nice']:
self.log['nice'] = False
self.log['info'] = _par.log['info']
return
symmetry_list = _par.symmetry_list
symmetry_length = _par.symmetry_length
self.file_line_symmetry = _par.file_line_symmetry
else:
self.log['nice'] = False
self.log[
'info'] = 'Error: the parameter symmetry_list has to be a list'
return
if symmetry_length > ndx:
self.log['nice'] = False
self.log[
'info'] = 'Error: the symmetry_list and topfile are not corresponded'
return
count = 1
lth = len(symmetry_list)
ls = []
for i in self.prochargefile[:self.gennm]:
if len(i) < lth:
print('Error: the chargefile and topfile are not corresponded')
exit()
elif len(i) > lth:
ls.append(count)
count += 1
if len(ls) > 0:
print(
'Warning: the number of charges are bigger than the atom numbers in the topfile'
)
print(
' : truncation will happen, only the number of leading charges will be used'
)
print(' : the number of this charge pair is:')
for count in ls:
print(count, end=' ')
print()
self.refatomtype = []
for i in symmetry_list:
if isinstance(i, int):
line = self.protopfile[self.atomndx[i]]
self.refatomtype.append(line.split()[1])
else:
line_1 = self.protopfile[self.atomndx[i[0]]]
atype = line_1.split()[1]
if len(i) > 1:
for j in i[1:]:
line = self.protopfile[self.atomndx[j]]
if atype != line.split()[1]:
self.log['nice'] = False
self.log['info'] = 'Error: the atom_types under [atoms] directive in top file is not equivalent\n' + \
'Error: symmetry_list:' + line_1[:-1] + '\n' + \
line[:-1]
return
self.refatomtype.append(atype)
dump_value = self._generator()
if not self.log['nice']: return
if 'fname' in kwargs and kwargs['fname'] is not None:
self.fname = kwargs['fname']
else:
self.fname = 'GenGromacsTopfile'
def __init__(self, *args, **kwargs):
self.log = {
'nice': True,
}
if 'file_path' not in kwargs or kwargs['file_path'] is None:
self.log['nice'] = False
self.log['info'] = 'Error: no file inputs'
return
self.file = kwargs['file_path']
log = file_size_check(self.file, fsize=2)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
self.fname = 'PAIR_Charge'
self.parameters = {
'top_gas_path': None,
'top_liq_path': None,
'top_fep_path': None,
'gro_gas_path': None,
'gro_liq_path': None,
'gro_fep_path': None,
'grompp_min_gas_path': None,
'grompp_min_liq_path': None,
'grompp_nvt_liq_path': None,
'grompp_npt_liq_path': None,
'grompp_prod_gas_path': None,
'grompp_prod_liq_path': None,
'grompp_fep_min_steep_path': None,
'grompp_fep_min_lbfgs_path': None,
'grompp_fep_nvt_path': None,
'grompp_fep_npt_path': None,
'grompp_fep_prod_path': None,
'charge_range_path': None,
'gromacs_energy_kw': 'Density',
'literature_value': 1000,
'gmx': 'gmx',
'MAE': 0.05,
'training_total_nm': 5,
'training_cnt': 1,
'gennm': 10,
'error_tolerance': 0.5,
'symmetry_list': None,
'pn_limit': None,
'counter_list': None,
'offset_list': None,
'offset_nm': None,
'ratio': None,
'nmround': None,
'total_charge': 0.0,
'charge_extend_by': None,
'threshold': None,
'bool_neutral': None,
'bool_nozero': None,
'bool_abscomp': None,
'reschoose': None,
'analysis_begintime': None,
'analysis_endtime': None,
}
self._profile()
if not self.log['nice']: return
self._proparameters()
if not self.log['nice']: return
self._try_file_generations()
if not self.log['nice']: return
# check for the bash scripts
if 'bashinterfile' in kwargs and kwargs['bashinterfile'] is not None:
self.bashinterfile = kwargs['bashinterfile']
log = file_size_check(self.bashinterfile, fsize=10)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
with open(self.bashinterfile, mode='rt') as f:
self._shfile = f.read()
else:
self.bashinterfile = 'GAML-BASH-Interface.sh'
self._shfile = resource_string(
__name__,
'shell/' + self.bashinterfile).decode('utf-8').replace(
'\r', '')
def __init__(self, *args, **kwargs):
if 'file_path' not in kwargs or kwargs['file_path'] is None:
raise ValueError('no inputs, file_path is missing')
self.file = kwargs['file_path'].strip()
file_size_check(self.file, fsize=2)
if 'fname' in kwargs and kwargs['fname'] is not None:
self.fname = kwargs['fname'].strip()
if len(self.fname) == 0: self.fname = 'bash_GAML_AutoTraining'
else:
self.fname = 'bash_GAML_AutoTraining'
self.parameters = {
'top_gas_path': None,
'top_liq_path': None,
'top_fep_path': None,
'gro_gas_path': None,
'gro_liq_path': None,
'gro_fep_path': None,
'grompp_min_gas_path': None,
'grompp_min_liq_path': None,
'grompp_nvt_liq_path': None,
'grompp_npt_liq_path': None,
'grompp_prod_gas_path': None,
'grompp_prod_liq_path': None,
'grompp_fep_min_steep_path': None,
'grompp_fep_min_lbfgs_path': None,
'grompp_fep_nvt_path': None,
'grompp_fep_npt_path': None,
'grompp_fep_prod_path': None,
'charge_range_path': None,
'gromacs_energy_kw': 'Density',
'literature_value': 1000,
'gmx': 'gmx',
'MAE': 0.05,
'training_total_nm': 5,
'training_cnt': 1,
'gennm': 10,
'error_tolerance': 0.5,
'symmetry_list': None,
'pn_limit': None,
'counter_list': None,
'offset_list': None,
'offset_nm': None,
'ratio': None,
'nmround': None,
'total_charge': 0.0,
'charge_extend_by': None,
'threshold': None,
'bool_neutral': None,
'bool_nozero': None,
'bool_abscomp': None,
'reschoose': None,
'analysis_begintime': None,
'analysis_endtime': None,
}
# check for the bash scripts
bo = True
if 'bashinterfile' in kwargs and kwargs['bashinterfile'] is not None:
self.bashinterfile = kwargs['bashinterfile'].strip()
if len(self.bashinterfile) == 0:
self.bashinterfile = 'GAML-BASH-Interface.sh'
else:
bo = False
else:
self.bashinterfile = 'GAML-BASH-Interface.sh'
if bo:
self.shfile = resource_string(
__name__,
'scripts/' + self.bashinterfile).decode('utf-8').replace(
'\r', '')
else:
file_size_check(self.bashinterfile, fsize=10)
with open(self.bashinterfile, mode='rt') as f:
self.shfile = f.read()
self.profile()
self.proparameters()
self.trial()
def __init__(self, **kwargs):
self.log = {
'nice': True,
}
if 'file_path' in kwargs and kwargs['file_path'] is not None:
self.filepath = kwargs['file_path']
log = file_size_check(self.filepath, fsize=200)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
else:
self.log['nice'] = False
self.log['info'] = 'Error: no file inputs'
return
if 'stepsize' in kwargs and kwargs['stepsize'] is not None:
try:
self.stepsize = float(kwargs['stepsize'])
if self.stepsize <= 0:
raise ValueError
except ValueError:
self.log['nice'] = False
self.log[
'info'] = 'Error: the parameter stepsize has to be a positive number'
return
else:
self.stepsize = 0.01
if 'percent' in kwargs and kwargs['percent'] is not None:
try:
self.percent = float(kwargs['percent'])
if self.percent <= 0 or self.percent > 1:
raise ValueError
except ValueError:
self.log['nice'] = False
self.log[
'info'] = 'Error: the parameter percent has to be a positive number within the range 0 to 1'
return
else:
self.percent = 0.95
if 'error_tolerance' in kwargs and kwargs[
'error_tolerance'] is not None:
try:
self.error_tolerance = float(kwargs['error_tolerance'])
except ValueError:
self.log['nice'] = False
self.log[
'info'] = 'Error: the parameter error_tolerance has to be a number'
return
else:
self.error_tolerance = 0.28
if 'bool_abscomp' in kwargs:
self.bool_abscomp = False if kwargs[
'bool_abscomp'] is False else True
else:
self.bool_abscomp = True
if 'cut_keyword' in kwargs and kwargs['cut_keyword'] is not None:
self.cut_keyword = kwargs['cut_keyword']
else:
self.cut_keyword = 'MAE'
if 'pallette_nm' in kwargs and kwargs['pallette_nm'] is not None:
try:
self.pallette_nm = int(kwargs['pallette_nm'])
if self.pallette_nm <= 0:
raise ValueError
except ValueError:
self.log['nice'] = False
self.log[
'info'] = 'Error: the parameter pallette_nm has to be a positive integer'
return
else:
self.pallette_nm = 50
if 'atomtype_list' in kwargs and kwargs['atomtype_list'] is not None:
if isinstance(kwargs['atomtype_list'], list):
if len(kwargs['atomtype_list']) == 0:
self.atomtype_list = None
else:
self.atomtype_list = kwargs['atomtype_list']
else:
self.log['nice'] = False
self.log[
'info'] = 'Error: the parameter atomtype_list has to be a list'
return
else:
self.atomtype_list = None
if 'fname' in kwargs and kwargs['fname'] is not None:
self.fname = kwargs['fname']
else:
self.fname = 'FSS_analysis'
if 'color_map' in kwargs and kwargs['color_map'] is not None:
self.color_map = kwargs['color_map']
else:
self.color_map = 'rainbow'
self._function_ready()
if not self.log['nice']: return
def __init__(self, *args, **kwargs):
self.log = {
'nice': True,
}
if 'file_path' in kwargs and kwargs['file_path'] is not None:
self.file = kwargs['file_path']
else:
self.log['nice'] = False
self.log['info'] = 'Error: no file input'
return
log = file_size_check(self.file, fsize=100)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
if 'chargefile' in kwargs and kwargs['chargefile'] is not None:
self.chargefile = kwargs['chargefile']
else:
self.log['nice'] = False
self.log['info'] = 'Error: no charge file input'
return
log = file_size_check(self.chargefile, fsize=100)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
log, self.prochargefile = function_file_input(self.chargefile,
bool_tail=False)
if not log['nice']:
self.log['nice'] = False
self.log['info'] = log['info']
return
if 'kwlist' in kwargs and kwargs['kwlist'] is not None:
if len(kwargs['kwlist']) != 0:
self.kwlist = kwargs['kwlist']
else:
self.kwlist = ['Density']
else:
self.kwlist = ['Density']
if 'bool_gas' in kwargs and kwargs['bool_gas'] is not None:
self.bool_gas = True if kwargs['bool_gas'] is True else False
else:
self.bool_gas = False
if self.bool_gas and 'Potential' not in self.kwlist:
self.kwlist.append('Potential')
if 'Potential' in self.kwlist: self.bool_gas = True
if 'temperature' in kwargs and kwargs['temperature'] is not None:
try:
self.temperature = float(kwargs['temperature'])
except ValueError:
self.temperature = 298.0
else:
self.temperature = 298.0
if 'block' in kwargs and kwargs['block'] is not None:
self.block = kwargs['block']
else:
self.block = 'COUNT'
self.literature_value = []
if 'literature_value' in kwargs and kwargs[
'literature_value'] is not None:
for nm in kwargs['literature_value']:
try:
t = float(nm)
self.literature_value.append(t)
except ValueError:
pass
if len(self.literature_value) == 0:
self.log['nice'] = False
self.log['info'] = 'Error: no literature value inputs'
return
if len(self.literature_value) < len(self.kwlist):
print(
'Warning: the number of properties in kwlist are bigger than\n'
)
print(
' : the number of literature value inputs, truncation\n')
print(' : will happen')
self.kwlist = self.kwlist[:len(self.literature_value)]
elif len(self.literature_value) > len(self.kwlist):
print(
'Warning: the number of literature value inputs are bigger\n')
print(' : than the number of properties in kwlist,\n')
print(' : truncation will happen')
self.literature_value = self.literature[:len(self.kwlist)]
if 'atomnm' in kwargs and kwargs['atomnm'] is not None:
try:
self.atomnm = int(float(kwargs['atomnm']))
except ValueError:
self.atomnm = 500
else:
self.atomnm = 500
if 'fname' in kwargs and kwargs['fname'] is not None:
self.fname = kwargs['fname']
else:
self.fname = 'MAE_PAIR'
if 'MAE' in kwargs and kwargs['MAE'] is not None:
try:
self.MAE = float(kwargs['MAE'])
except ValueError:
self.MAE = 0.05
else:
self.MAE = 0.05
self._profile()
self._pro_bool_gas()
def __init__(self, *args, **kwargs):
if 'file_path' in kwargs and kwargs['file_path'] is not None:
self.file = kwargs['file_path'].strip()
file_size_check(self.file, fsize=100)
else:
raise ValueError('no inputs, file_path is missing')
if 'chargefile' in kwargs and kwargs['chargefile'] is not None:
self.chargefile = kwargs['chargefile'].strip()
file_size_check(self.chargefile, fsize=100)
else:
raise ValueError('no inputs, chargefile is missing')
self.prochargefile = func_file_input(self.chargefile, bool_tail=False)
if 'kwlist' in kwargs and kwargs['kwlist'] is not None:
if isinstance(kwargs['kwlist'],
list) and len(kwargs['kwlist']) != 0:
self.kwlist = [i.lower() for i in kwargs['kwlist']]
else:
self.kwlist = ['density']
else:
self.kwlist = ['density']
if 'bool_gas' in kwargs and kwargs['bool_gas'] is not None:
self.bool_gas = True if kwargs['bool_gas'] is True else False
else:
self.bool_gas = False
if self.bool_gas and 'potential' not in self.kwlist:
self.kwlist.append('potential')
if 'potential' in [i.lower() for i in self.kwlist]:
self.bool_gas = True
if 'temperature' in kwargs and kwargs['temperature'] is not None:
try:
self.temperature = float(kwargs['temperature'])
except ValueError:
self.temperature = 298.0
else:
self.temperature = 298.0
if 'block' in kwargs and kwargs['block'] is not None:
if isinstance(kwargs['block'], str):
self.block = kwargs['block'].strip().lower()
else:
self.block = 'count'
else:
self.block = 'count'
self.literature_value = []
if 'literature_value' in kwargs and kwargs[
'literature_value'] is not None:
for nm in kwargs['literature_value']:
try:
t = float(nm)
self.literature_value.append(t)
except ValueError:
print(kwargs['literature_value'])
raise ValueError('wrong defined')
if len(self.literature_value) == 0:
raise ValueError('no inputs, literature_value is missing')
self.literature_value, self.kwlist = self._checknm(
self.literature_value, 'literature_value', self.kwlist, 'kwlist')
if 'atomnm' in kwargs and kwargs['atomnm'] is not None:
try:
self.atomnm = int(float(kwargs['atomnm']))
except ValueError:
self.atomnm = 500
else:
self.atomnm = 500
if 'fname' in kwargs and kwargs['fname'] is not None:
self.fname = kwargs['fname'].strip()
if len(self.fname) == 0: self.fname = 'MAE_PAIR'
else:
self.fname = 'MAE_PAIR'
if 'MAE' in kwargs and kwargs['MAE'] is not None:
try:
self.MAE = float(kwargs['MAE'])
except ValueError:
self.MAE = 0.05
else:
self.MAE = 0.05
