def structure(self):
totalRMSD=0
for filer in self.prodOuts:
# Extract the coordinates from a geometry optimization
p = ccopen(filer)
data = p.parse()
# Use the bridge to create two lists of Biopython atoms
from cclib.bridge import makebiopython
initial = makebiopython(data.atomcoords[0] , data.atomnos)
final = makebiopython(data.atomcoords[-1], data.atomnos)
# Use Biopython to superimpose the two geometries and calculate the RMS
from Bio.PDB.Superimposer import Superimposer
superimposer = Superimposer()
superimposer.set_atoms(initial, final)
totalRMSD+= superimposer.rms
print ('RMSD'+str(superimposer.rms))
for filer in self.reacOuts:
# Extract the coordinates from a geometry optimization
p = ccopen(filer)
data = p.parse()
# Use the bridge to create two lists of Biopython atoms
from cclib.bridge import makebiopython
initial = makebiopython(data.atomcoords[0] , data.atomnos)
final = makebiopython(data.atomcoords[-1], data.atomnos)
# Use Biopython to superimpose the two geometries and calculate the RMS
from Bio.PDB.Superimposer import Superimposer
superimposer = Superimposer()
superimposer.set_atoms(initial, final)
totalRMSD+= superimposer.rms
print ('RMSD'+str(superimposer.rms))
return (totalRMSD)
def main():
"""Goal: Identify first atom in product.out based on connectivity"""
# Parse product output and generate z-matrix
product = ccopen('product.out').parse()
ccproduct = ccData_xyz(product.getattributes())
ccproduct.build_zmatrix()
shift = 2.0
ccproduct.distances[1] += shift
ccproduct.build_xyz()
#ccproduct.print_xyz()
reactant = ccopen('r1.out').parse()
ccreactant = ccData_xyz(reactant.getattributes())
# Shitty design here, but not sure what else to do yet...
P2Ridx = [None]*len(ccreactant.atomnos)
matched = []
for i in range(len(ccproduct.atomnos)):
match = indexmatch(ccproduct, i, ccreactant, ignores=[1], matched=matched)
if match is not None:
P2Ridx[match] = i
matched.append(match)
reactantinproduct(ccreactant, ccproduct, P2Ridx)
def get_geometries(outputfilenames):
snapnums = []
CO2_geometries = []
for outputfilename in outputfilenames:
print("Parsing CO2 geometry from {}".format(outputfilename))
job = ccopen(outputfilename)
try:
data = job.parse()
except:
# Is this the right control flow statement?
continue
# take the first one on the off chance that we've done a
# numerical frequency run, which looks a lot like a geometry
# optimization
geometry_whole = data.atomcoords[0]
start_index = len(data.atomnos) - 3
geometry_CO2 = geometry_whole[start_index:]
CO2_geometries.append(geometry_CO2)
snapnum = int(re.search(r'drop_(\d+)', outputfilename).groups()[0])
snapnums.append(snapnum)
return CO2_geometries, snapnums
def figs(opts):
"""
Determine type of output from opts or file
Call appropriate function
"""
if type(opts.fname) == str:
# Assuming ccinput is a filename
data = parser.ccopen(opts.fname).parse()
else:
data = opts.fname
assert type(data) == parser.data.ccData_optdone_bool \
or type(data) == parser.data.ccData
# TODO: determine what kind of job (opt, sp, freq)
# auto = automatically determine
# or get from opts.job
if opts.job == 'auto':
#print opts.job, "not yet implemented"
_opt(data)
elif opts.job == 'opt':
_opt(data)
elif opts.job == 'sp':
_sp(data)
elif opts.job == 'vib':
print(opts.job, "not yet implemented")
else:
print(opts.job, "not yet implemented")
def extracter(self, trait):
self.ccfile = ccopen(self.outFile) #opens the out file in cclib
self.ccfile.logger.setLevel(
logging.ERROR
) # avoid printing to the screen all the data cclib wants to print
data = self.ccfile.parse(
) # data contain anything cclib knows to extract
return getattr(data, trait)
def get_xyz_block_from_log(logfile_path):
myfile = ccopen(logfile_path,loglevel=logging.WARN)
data = myfile.parse()
lines = get_last_coord_block_str(logfile_path, data = data).split('\n')
scfener = data.scfenergies[-1]
result = '{0: >5d}\n'.format(len(lines))
result += 'scf done:{0: >13.6f}\n'.format(scfener)
for l in lines:
result += ' ' + l + '\n'
return result
def run_calculations(self, fname):
niedoida = "./niedoida"
inp_fname = fname + ".inp"
log_fname = fname + ".log"
subprocess.check_call([niedoida, inp_fname])
log = ccopen(log_fname)
log.logger.setLevel(logging.WARNING)
return log.parse()
def CalcJ(namejob):
molA_parser = ccopen("part1/" + namejob + "part1.log")
molB_parser = ccopen("part2/" + namejob + "part2.log")
molAB_parser = ccopen("dim/" + namejob + "dim.log")
molA = molA_parser.parse()
molB = molB_parser.parse()
molAB = molAB_parser.parse()
print("Parsed...")
nbs = molAB.nbasis
if molA.nbasis != molB.nbasis:
print("Count of basis functions doesn't match. Failing.")
return False
for mole in molA, molB, molAB:
if len(mole.atomcoords) != 1:
print(mole +
" calculation appears to be an optimisation! Failing.")
#Take mocoeffs[0] - the alpha electrons to get matrix in correct order
MolAB_Pro = np.transpose(np.dot(molAB.mocoeffs[0], molAB.aooverlaps))
# print "DimPro via JKP:", DimPro, "DimPro2 via JMF", DimPro2
# print "Psi1DimBS via JKP: ", Psi1DimBS
PsiA_DimBS = np.dot(molA.mocoeffs[0], MolAB_Pro)
PsiB_DimBS = np.dot(molB.mocoeffs[0], MolAB_Pro)
# print "Dim Mocoeffs: ", molAB.moenergies[0]/27.211
#Note: moenergies in eV, so converted to Hartree for checking with JKP code
JAB = np.dot(np.dot(np.diagflat(molAB.moenergies[0] / 27.211), PsiA_DimBS),
np.transpose(PsiB_DimBS))
JAA = np.dot(np.dot(np.diagflat(molAB.moenergies[0] / 27.211), PsiA_DimBS),
np.transpose(PsiA_DimBS))
JBB = np.dot(np.dot(np.diagflat(molAB.moenergies[0] / 27.211), PsiB_DimBS),
np.transpose(PsiB_DimBS))
print "JAB", JAB
print "JAA", JAA
print "JBB", JBB
return [JAB, JAA, JBB]
def get_point_charges_qmout(pc_file_path, pc_type):
"""Use cclib to parse a QM output file for point charges (Mulliken,
Lowdin, CHELPG, ...).
"""
from cclib.parser import ccopen
job = ccopen(pc_file_path)
data = job.parse()
return data.atomcharges[pc_type]
def extractcalcdata(self):
if len(self.gjfs) > 0:
self.log("\tExtracting data from log files")
tostore = []
for j, pname in enumerate(self.gjforder):
mylogfile = os.path.join("gaussian", "%d.out.gz" % j)
if not os.path.isfile(mylogfile):
continue
text = gzip.open(mylogfile, "r").read()
if text.find(
"Excitation energies and oscillator strength") < 0:
continue
lines = iter(text.split("\n"))
for line in lines:
if line.startswith(" #T PM6 OPT"):
line = lines.next()
line = lines.next()
line = lines.next()
break
for line in lines:
if line.startswith(" Initial command"): break
zindofile = list(lines)
if len(zindofile) == 0:
# All the PM6 data is missing
continue
with open("tmp.out", "w") as f:
f.write("\n".join(zindofile))
logfile = ccopen("tmp.out")
logfile.logger.setLevel(logging.ERROR)
try:
data = logfile.parse()
except AssertionError:
continue
try:
lumo = data.moenergies[0][data.homos[0] + 1]
h**o = data.moenergies[0][data.homos[0]]
etens = [x * convert
for x in data.etenergies] # cm-1 to eV
etoscs = data.etoscs
except:
continue
if max(etens) <= 0:
continue
## myjson = json.dumps([h**o, lumo, etens, etoscs])
myjson = json.dumps([
h**o, lumo, etens, etoscs, data.moenergies[0],
data.homos[0]
])
tostore.append((pname, myjson))
for pname, myjson in tostore:
self.admin.storedata(pname, self.gen, myjson)
def generate_data(self,
request,
experiment_output,
experiment,
output_file=None,
**kwargs):
# Parse output_file
output_text = io.TextIOWrapper(output_file)
gaussian = ccopen(output_text)
data = gaussian.parse()
data.listify()
homo_eigenvalues = None
lumo_eigenvalues = None
if hasattr(data, 'homos') and hasattr(data, 'moenergies'):
homos = data.homos[0] + 1
moenergies = data.moenergies[0]
if homos > 9 and len(moenergies) >= homos:
homo_eigenvalues = [
data.moenergies[0][homos - 1 - i] for i in range(1, 10)
]
if homos + 9 <= len(moenergies):
lumo_eigenvalues = [
data.moenergies[0][homos + i] for i in range(1, 10)
]
# Create plot
fig = Figure()
if homo_eigenvalues and lumo_eigenvalues:
fig.suptitle("Eigenvalues")
ax = fig.subplots(2, 1)
ax[0].plot(range(1, 10), homo_eigenvalues, label='H**o')
ax[0].set_ylabel('eV')
ax[0].legend()
ax[1].plot(range(1, 10), lumo_eigenvalues, label='Lumo')
ax[1].set_ylabel('eV')
ax[1].legend()
else:
ax = fig.subplots()
ax.text(0.5,
0.5,
"No applicable data",
horizontalalignment='center',
verticalalignment='center',
transform=ax.transAxes)
# Export plot as image buffer
buffer = io.BytesIO()
fig.savefig(buffer, format='png')
image_bytes = buffer.getvalue()
buffer.close()
# return dictionary with image data
return {'image': image_bytes, 'mime-type': 'image/png'}
def main():
"""Goal: Identify first atom in product.out based on connectivity"""
ccproduct = ccopen('product.out').parse()
product = ccData_xyz(ccproduct.getattributes(), ccdataconvert=True)
product.build_zmatrix()
elements = set(product.elements)
atom0 = NodeAtom(product, index=0)
#atom0.children.pop(0)
atom1 = NodeAtom(product, index=1)
for child in [x for x in atom0.children if x.index == 0]:
atom0.children.remove(child)
#D0 = build_distancematrix(atom0, elements, 3, ignore=[1])
D1 = build_distancematrix(atom1, elements, 3, ignore=[0])
ccr2 = ccopen('r2.out').parse()
r2 = ccData_xyz(ccr2.getattributes(), ccdataconvert=True)
r2.build_zmatrix()
print(r2.connectivity)
print(product.connectivity)
atom1.nodeprint()
for i in range(len(r2.atomnos)):
atomtree = NodeAtom(r2, index=i)
distancematrix = build_distancematrix(atomtree, elements, 3)
if dstmat_equal(distancematrix, D1):
print('Atom 1 found')
break
print('Atom 1 in reactant:')
for dst in distancematrix:
print(dst)
print('Atom 1 in product:')
for dst in D1:
print(dst)
def main():
"""Goal: Identify first atom in product.out based on connectivity"""
ccproduct = ccopen('product.out').parse()
product = ccData_xyz(ccproduct.getattributes(), ccdataconvert=True)
product.build_zmatrix()
elements = set(product.elements)
atom0 = NodeAtom(product, index=0)
#atom0.children.pop(0)
atom1 = NodeAtom(product, index=1)
for child in [x for x in atom0.children if x.index == 0]:
atom0.children.remove(child)
#D0 = build_distancematrix(atom0, elements, 3, ignore=[1])
D1 = build_distancematrix(atom1, elements, 3, ignore=[0])
ccr2 = ccopen('r2.out').parse()
r2 = ccData_xyz(ccr2.getattributes(), ccdataconvert=True)
r2.build_zmatrix()
print(r2.connectivity)
print(product.connectivity)
atom1.nodeprint()
for i in range(len(r2.atomnos)):
atomtree = NodeAtom(r2, index=i)
distancematrix = build_distancematrix(atomtree, elements, 3)
if dstmat_equal(distancematrix, D1):
print('Atom 1 found')
break
print('Atom 1 in reactant:')
for dst in distancematrix:
print(dst)
print('Atom 1 in product:')
for dst in D1:
print(dst)
def main():
stretch('product.out')
rfiles = ['r1.out', 'r2.out']
reactants = []
for rfile in rfiles:
tmp = ccopen(rfile).parse()
reactants.append(ccData_xyz(tmp.getattributes(), ccdataconvert=True))
for reactant in reactants:
reactant.build_zmatrix()
reactant.print_gzmat()
def CalcJ(namejob):
molA_parser=ccopen("part1/"+namejob+"part1.log")
molB_parser=ccopen("part2/"+namejob+"part2.log")
molAB_parser=ccopen("dim/"+namejob+"dim.log")
molA=molA_parser.parse()
molB=molB_parser.parse()
molAB=molAB_parser.parse()
print ("Parsed...")
nbs=molAB.nbasis
if molA.nbasis!=molB.nbasis:
print("Count of basis functions doesn't match. Failing.")
return False
for mole in molA,molB,molAB:
if len(mole.atomcoords)!=1:
print(mole+" calculation appears to be an optimisation! Failing.")
#Take mocoeffs[0] - the alpha electrons to get matrix in correct order
MolAB_Pro = np.transpose(np.dot(molAB.mocoeffs[0],molAB.aooverlaps))
# print "DimPro via JKP:", DimPro, "DimPro2 via JMF", DimPro2
# print "Psi1DimBS via JKP: ", Psi1DimBS
PsiA_DimBS = np.dot(molA.mocoeffs[0], MolAB_Pro)
PsiB_DimBS = np.dot(molB.mocoeffs[0], MolAB_Pro)
# print "Dim Mocoeffs: ", molAB.moenergies[0]/27.211
#Note: moenergies in eV, so converted to Hartree for checking with JKP code
JAB=np.dot(np.dot(np.diagflat(molAB.moenergies[0]/27.211),PsiA_DimBS), np.transpose(PsiB_DimBS) )
JAA=np.dot(np.dot(np.diagflat(molAB.moenergies[0]/27.211),PsiA_DimBS), np.transpose(PsiA_DimBS) )
JBB=np.dot(np.dot(np.diagflat(molAB.moenergies[0]/27.211),PsiB_DimBS), np.transpose(PsiB_DimBS) )
print "JAB", JAB
print "JAA", JAA
print "JBB", JBB
return [JAB, JAA, JBB]
def main():
stretch('product.out')
rfiles = ['r1.out', 'r2.out']
reactants = []
for rfile in rfiles:
tmp = ccopen(rfile).parse()
reactants.append(ccData_xyz(tmp.getattributes(), ccdataconvert=True))
for reactant in reactants:
reactant.build_zmatrix()
reactant.print_gzmat()
def extractcalcdata(self):
if len(self.gjfs) > 0:
self.log("\tExtracting data from log files")
tostore = []
for j, pname in enumerate(self.gjforder):
print 'on pname=%s, j=%s' % (pname, j)
mylogfile = os.path.join("gaussian", "%d.out.gz" % j)
if not os.path.isfile(mylogfile):
continue
#logfile = ccopen("tmp.out")
logfile = ccopen(mylogfile)
logfile.logger.setLevel(logging.ERROR)
try:
data = logfile.parse()
except AssertionError:
continue
try:
lumo = data.moenergies[0][data.homos[0] + 1]
h**o = data.moenergies[0][data.homos[0]]
etens = [x * convert
for x in data.etenergies] # cm-1 to eV
etoscs = data.etoscs
except:
continue
if max(etens) <= 0:
continue
#myjson = json.dumps([h**o, lumo, etens, etoscs.tolist()])
# adds JSON with H**O, LUMO, electronic transition energies, et oscillator strengths
# and then all the MO energies
myjson = json.dumps([
float(h**o),
float(lumo), etens,
list(etoscs),
list(data.moenergies[0]),
int(data.homos[0])
])
tostore.append((pname, myjson))
for pname, myjson in tostore:
# get the sequence
output = get_comb(pname, self.length)
seq = output[0]
# chain the .replace(old, new) function to replace id with A, di with B, uq with D, qu with E
seqSym = seq.replace("(qu)", "A").replace("(uq)", "B").replace(
"(di)", "D").replace("(id)", "E")
self.admin.storedata(pname, self.gen, seqSym, myjson)
def parse(self):
"""Parse the logfile and assign the discrete spectrum values."""
try:
if os.path.exists(self.name):
logfile = ccopen(self.name)
logfile.logger.setLevel(logging.ERROR)
data = logfile.parse()
setattr(self, 'excited_state_energy', data.etenergies)
setattr(self, 'oscillator_strength', data.etoscs)
else:
error('The logfile `%s` could not be found' % self.name)
except TypeError:
error('The `parse()` method requires the `filename` argument '
'in `Logfile`')
def parser(self):
progresser = progress.TextProgress() #text nprogress stores logs
filer = Gauparse.ccopen(self.filename, progresser, logging.ERROR)
attrs = filer.parse()
entries = []
for attr in attrs.__dict__:
if re.match("_(.*)", attr):
pass
else:
entries.append((attr, attrs.__dict__[attr]))
for entry in entries:
print str(entry)
print '\n\n\n'
def parse(self):
"""Parse the logfile and assign the discrete spectrum values."""
try:
if os.path.exists(self.name):
logfile = ccopen(self.name)
logfile.logger.setLevel(logging.ERROR)
data = logfile.parse()
setattr(self, 'excited_state_energy', data.etenergies)
setattr(self, 'oscillator_strength', data.etoscs)
else:
error('The logfile `%s` could not be found' % self.name)
except TypeError:
error('The `parse()` method requires the `filename` argument '
'in `Logfile`')
def add_geomtotxt(egeom,geomfile):
#print(geomfile.get())
#f=open(geomfile.get())
#print(f.read())
from cclib.parser import ccopen
if geomfile.get() == '':
print("No log file!")
filetypes=(("Gaussian Output","*.log"),("all files","*.*"))
logfile = askopenfilename(filetypes = filetypes)
else:
logfile = ccopen(geomfile.get())
data = logfile.parse()
for i in range(len(data.atomnos)):
egeom.insert(END,pertable[data.atomnos[i]]+" "+str(data.atomcoords[-1,i,0])+" "+str(data.atomcoords[-1,i,1])+" "+str(data.atomcoords[-1,i,2])+"\n")
egeom.setvar()
def get_CO2_frequencies_4fs(outputfilenames):
"""The same as above, but for the snapshots separated by 4fs."""
snapnums = []
CO2_frequencies = []
CO2_intensities = []
for outputfilename in outputfilenames:
print("Parsing frequencies from {}".format(outputfilename))
job = ccopen(outputfilename)
try:
data = job.parse()
except:
# Is this the right control flow statement?
continue
# geometry = data.atomcoords[-1]
# atoms = data.atomnos
# start_indices = find_CO2_atom_indices(atoms, geometry)
# assert isinstance(start_indices, list)
try:
vibfreqs = data.vibfreqs
vibdisps = data.vibdisps
vibirs = data.vibirs
except AttributeError:
# Is this the correct control flow statement?
continue
# Assumption!
# start_index = start_indices[0]
# Assumption?
start_index = 0
mode_indices = find_CO2_mode_indices(start_index, vibdisps, thresh=0.50)
# mode_indices = [2]
# freqs = [vibfreqs[modeidx] for modeidx in mode_indices]
# freqs = filter(lambda x: x > 0.0, freqs)
# print(freqs)
# Let's only take the last one...
# print(outputfilename)
CO2_frequencies.append(vibfreqs[mode_indices[-1]])
CO2_intensities.append(vibirs[mode_indices[-1]])
snapnum = int(re.search(r'drop_(\d+)', outputfilename).groups()[0])
snapnums.append(snapnum)
return CO2_frequencies, CO2_intensities, snapnums
def extractcalcdata(self):
if len(self.gjfs) > 0:
self.log("\tExtracting data from log files")
tostore = []
for j, pname in enumerate(self.gjforder):
print 'on pname=%s, j=%s' % (pname, j)
mylogfile = os.path.join("gaussian", "%d.log.gz" % j)
if not os.path.isfile(mylogfile):
continue
# logfile = ccopen("tmp.out")
logfile = ccopen(mylogfile)
logfile.logger.setLevel(logging.ERROR)
try:
data = logfile.parse()
except AssertionError:
continue
try:
# Values rounded to reduce size of output file
lumo = round(data.moenergies[0][data.homos[0] + 1], 3)
h**o = round(data.moenergies[0][data.homos[0]], 3)
etens = [round(x*convert, 3) for x in data.etenergies] # cm-1 to eV
etoscs = [round(x, 3) for x in data.etoscs]
except:
continue
if max(etens) <= 0:
continue
# File stores too much info for large data set, so use other function (below) which saves fewer energies
#myjson = json.dumps([float(h**o), float(lumo), etens, list(etoscs), list(data.moenergies[0]), int(data.homos[0])])
#tostore.append((pname, myjson))
myjson = json.dumps([float(h**o), float(lumo), etens, list(etoscs)])
tostore.append((pname, myjson))
for pname, myjson in tostore:
# get the sequence
output = get_comb(pname, self.length)
seq = output[0]
# chain the .replace(old, new) function to replace id with A, di with B, uq with D, qu with E to make
# sequences easier to read
seqSym = seq.replace("(qu)", "A").replace("(uq)", "B").replace("(di)", "D").replace("(id)", "E")
self.admin.storedata(pname, self.gen, seqSym, myjson)
def get_CO2_frequencies(outputfilenames):
snapnums = []
CO2_frequencies = []
CO2_intensities = []
for outputfilename in outputfilenames:
print("Parsing frequencies from {}".format(outputfilename))
job = ccopen(outputfilename)
try:
data = job.parse()
except:
# Is this the right control flow statement?
continue
# geometry = data.atomcoords[-1]
# atoms = data.atomnos
# start_indices = find_CO2_atom_indices(atoms, geometry)
# assert isinstance(start_indices, list)
try:
vibfreqs = data.vibfreqs
vibirs = data.vibirs
except AttributeError:
# Is this the correct control flow statement?
continue
# Assumption!
# start_index = start_indices[0]
# Assumption?
start_index = len(data.atomnos) - 3
# mode_indices = find_CO2_mode_indices(start_index, vibdisps, thresh=0.50)
mode_indices = [2]
# freqs = [vibfreqs[modeidx] for modeidx in mode_indices]
# freqs = filter(lambda x: x > 0.0, freqs)
# print(freqs)
# Let's only take the last one...
# print(outputfilename)
CO2_frequencies.append(vibfreqs[mode_indices[-1]])
CO2_intensities.append(vibirs[mode_indices[-1]])
snapnum = int(re.search('drop_(\d+)_', outputfilename).groups()[0])
snapnums.append(snapnum)
return CO2_frequencies, CO2_intensities, snapnums
def get_last_coord_block_str(log,step=None, data = None):
"""
Open gaussian log file and prints last coordinates of atoms
as a block for creating new input file.
"""
if data == None:
myfile = ccopen(log,loglevel=logging.WARN)
data = myfile.parse()
if not step:
coords = data.atomcoords[-1]
else:
coords = data.atomcoords[step]
rows = []
t = PeriodicTable()
for i in range(len(coords)):
strrow_l = [t.element[data.atomnos[i]]]
strrow_l.extend(['{0: >12.6f}'.format(x) for x in coords[i]])
rows.append(''.join(strrow_l))
coord_block = '\n'.join(rows + [''])
return coord_block
def fileopen(self):
if self.inputfilename != None:
mydir = os.path.dirname(self.inputfilename)
else:
mydir = "."
inputfilename = tkinter.filedialog.askopenfilename(filetypes=[
("All files", ".*"), ("Output Files", ".out"),
("Log Files", ".log"), ("ADF output", ".adfout")
],
initialdir=mydir)
if inputfilename != "":
self.inputfilename = os.path.basename(inputfilename)
os.chdir(os.path.dirname(inputfilename))
# Create an instance of the parser
if hasattr(self, "logfile") and self.logfile != None:
self.logfile.logger.removeHandler(
self.logfile.logger.handlers[0])
self.logfile = ccopen(self.inputfilename)
self.fileopenednow()
def add_calcul2list(file,molid,t):
t.destroy()
print('Opening file')
log = open(file).read()
# print("Test reading")
# print(log)
basis,funct = scanbasis(file)
#scanfreq(file)
from cclib.parser import ccopen
logfile = ccopen(file)
data = logfile.parse()
freqanharm = np.zeros(len(data.vibfreqs))
intensanharmtmp = np.zeros(len(data.vibfreqs))
intensanharm = np.zeros(len(data.vibfreqs))
freqanharmscan(file,freqanharm,intensanharmtmp,len(data.vibfreqs))
print(freqanharm)
sort = np.argsort(freqanharm)
freqanharm=np.sort(freqanharm)
for k in range(len(intensanharmtmp)):
intensanharm[k]=intensanharmtmp[sort[k]]
db.insertcalc(molid,data,freqanharm,intensanharm,"B3LYP",basis,log)
def main(args):
hessian = read_scratch_hessian(os.path.join(args.scratchdir, 'HESS'))
atomsyms = read_scratch_molecule(os.path.join(args.scratchdir, 'molecule'))
atommasses = atomsyms2atommasses(atomsyms)
hessian_mw = hessian_mass_weight_4(hessian, atommasses)
eigvals, eigvecs = np.linalg.eigh(hessian_mw)
frequencies = np.lib.scimath.sqrt(eigvals)[6:] * vib_constant
print(complex_as_negative(frequencies))
if args.outputfile:
from cclib.parser import ccopen
job = ccopen(args.outputfile)
data = job.parse()
hessian_outputfile = data.hessian
hessian_outputfile_mw = hessian_mass_weight_4(hessian_outputfile, atommasses)
eigvals_outputfile, eigvecs_outputfiles = np.linalg.eigh(hessian_outputfile_mw)
frequencies_outputfile_hess = np.lib.scimath.sqrt(eigvals_outputfile)[6:] * vib_constant
frequencies_outputfile = data.vibfreqs
print(complex_as_negative(frequencies_outputfile_hess))
print(frequencies_outputfile)
if __name__ == '__main__':
import cclib
from cclib.parser import ccopen
from cclib.parser.utils import convertor
args = getargs()
for qmoutputfile in args.qmoutputfile:
qmoutputfile = os.path.abspath(qmoutputfile)
print(qmoutputfile)
job = ccopen(qmoutputfile)
if job:
data = job.parse()
idx_homo = data.homos[-1]
idx_lumo = idx_homo + 1
steps = len(data.scfenergies)
total_e = convertor(data.scfenergies[-1], 'eV', 'hartree')
h**o = convertor(data.moenergies[-1][idx_homo], 'eV', 'hartree')
lumo = convertor(data.moenergies[-1][idx_lumo], 'eV', 'hartree')
job_type = determine_job_type(job)
total_time = extract_total_time(qmoutputfile, job_type)
time_per_step = total_time / steps
def parse(file_name, output_file_name):
result = OrderedDict()
identifiers = OrderedDict()
calculation = OrderedDict()
molecule = OrderedDict()
calculated_properties = OrderedDict()
execution_environment = OrderedDict()
molecule_structural_formats = OrderedDict()
# extracting fields from open-babel
mol = pybel.readfile('mpo', file_name).next()
identifiers['InChI'] = mol.write('inchi').strip()
identifiers['InChIKey'] = mol.write('inchikey').strip()
identifiers['SMILES'] = mol.write('smiles').split('\t')[0]
identifiers['CanonicalSMILES'] = mol.write('can').split('\t')[0]
molecule_structural_formats['PDB'] = mol.write('pdb').split('\t')[0]
molecule_structural_formats['SDF'] = mol.write('sdf').split('\t')[0]
# extracting fields from ccdbt
parser_pyramid = ParserPyramid()
meta_f = metafile(file_name)
if meta_f.parse(parser_pyramid):
if 'CodeVersion' in meta_f.record:
calculation['Package'] = meta_f.record['CodeVersion']
if 'Methods' in meta_f.record:
calculation['Methods'] = meta_f.record['Methods']
if 'Keywords' in meta_f.record:
calculation['Keywords'] = meta_f.record['Keywords']
if 'Basis' in meta_f.record:
calculation['Basis'] = meta_f.record['Basis']
if 'CalcType' in meta_f.record:
calculation['CalcType'] = meta_f.record['CalcType']
if 'JobStatus' in meta_f.record:
calculation['JobStatus'] = meta_f.record['JobStatus']
if 'Formula' in meta_f.record:
molecule['Formula'] = meta_f.record['Formula']
if 'OrbSym' in meta_f.record:
molecule['OrbSym'] = meta_f.record['OrbSym']
if 'Multiplicity' in meta_f.record:
molecule['Multiplicity'] = meta_f.record['Multiplicity']
if 'Charge' in meta_f.record:
molecule['Charge'] = meta_f.record['Charge']
if 'ElecSym' in meta_f.record:
molecule['ElecSym'] = meta_f.record['ElecSym']
if 'Energy' in meta_f.record:
calculated_properties['Energy'] = meta_f.record['Energy']
if 'Dipole' in meta_f.record:
calculated_properties['Dipole'] = meta_f.record['Dipole']
if 'HF' in meta_f.record:
calculated_properties['HF'] = meta_f.record['HF']
if 'CalcMachine' in meta_f.record:
execution_environment['CalcMachine'] = meta_f.record['CalcMachine']
if 'FinTime' in meta_f.record:
execution_environment['FinTime'] = meta_f.record['FinTime']
fin_date = datetime.strptime(execution_environment['FinTime'], '%d %b %y')
execution_environment['FinTimeStamp'] = datetime.utcfromtimestamp(calendar.timegm(fin_date.timetuple()))
if 'CalcBy' in meta_f.record:
execution_environment['CalcBy'] = meta_f.record['CalcBy']
# Rest of the key value pairs are not updated by the seagrid-data
if 'ParsedBy' in meta_f.record:
result['ParsedBy'] = meta_f.record['ParsedBy']
if 'NumBasis' in meta_f.record:
result['NumBasis'] = meta_f.record['NumBasis']
if 'NumFC' in meta_f.record:
result['NumFC'] = meta_f.record['NumFC']
if 'NumVirt' in meta_f.record:
result['NumVirt'] = meta_f.record['NumVirt']
if 'InitGeom' in meta_f.record:
result['InitGeom'] = meta_f.record['InitGeom']
if 'FinalGeom' in meta_f.record:
result['FinalGeom'] = meta_f.record['FinalGeom']
if 'PG' in meta_f.record:
result['PG'] = meta_f.record['PG']
if 'NImag' in meta_f.record:
result['NImag'] = meta_f.record['NImag']
if 'EnergyKcal' in meta_f.record:
result['EnergyKcal'] = meta_f.record['EnergyKcal']
if 'ZPE' in meta_f.record:
result['ZPE'] = meta_f.record['ZPE']
if 'ZPEKcal' in meta_f.record:
result['ZPEKcal'] = meta_f.record['ZPEKcal']
if 'HFKcal' in meta_f.record:
result['HFKcal'] = meta_f.record['HFKcal']
if 'Thermal' in meta_f.record:
result['Thermal'] = meta_f.record['Thermal']
if 'ThermalKcal' in meta_f.record:
result['ThermalKcal'] = meta_f.record['ThermalKcal']
if 'Enthalpy' in meta_f.record:
result['Enthalpy'] = meta_f.record['Enthalpy']
if 'EnthalpyKcal' in meta_f.record:
result['EnthalpyKcal'] = meta_f.record['EnthalpyKcal']
if 'Entropy' in meta_f.record:
result['Entropy'] = meta_f.record['Entropy']
if 'EntropyKcal' in meta_f.record:
result['EntropyKcal'] = meta_f.record['EntropyKcal']
if 'Gibbs' in meta_f.record:
result['Gibbs'] = meta_f.record['Gibbs']
if 'GibbsKcal' in meta_f.record:
result['GibbsKcal'] = meta_f.record['GibbsKcal']
if 'Freq' in meta_f.record:
result['Freq'] = meta_f.record['Freq']
if 'AtomWeigh' in meta_f.record:
result['AtomWeigh'] = meta_f.record['AtomWeigh']
if 'Conditions' in meta_f.record:
result['Conditions'] = meta_f.record['Conditions']
if 'ReacGeom' in meta_f.record:
result['ReacGeom'] = meta_f.record['ReacGeom']
if 'ProdGeom' in meta_f.record:
result['ProdGeom'] = meta_f.record['ProdGeom']
if 'MulCharge' in meta_f.record:
result['MulCharge'] = meta_f.record['MulCharge']
if 'NatCharge' in meta_f.record:
result['NatCharge'] = meta_f.record['NatCharge']
if 'S2' in meta_f.record:
result['S2'] = meta_f.record['S2']
if 'MemCost' in meta_f.record:
result['MemCost'] = meta_f.record['MemCost']
if 'TimeCost' in meta_f.record:
result['TimeCost'] = meta_f.record['TimeCost']
if 'CPUTime' in meta_f.record:
result['CPUTime'] = meta_f.record['CPUTime']
if 'Convergence' in meta_f.record:
result['Convergenece'] = meta_f.record['Convergence']
if 'FullPath' in meta_f.record:
result['FullPath'] = meta_f.record['FullPath']
if 'InputButGeom' in meta_f.record:
result['InputButGeom'] = meta_f.record['InputButGeom']
if 'Otherinfo' in meta_f.record:
result['Otherinfo'] = meta_f.record['Otherinfo']
if 'Comments' in meta_f.record:
result['Comments'] = meta_f.record['Comments']
# End of not updated key-value pairs
# extracting fields from cclib
myfile = ccopen(file_name)
try:
data = myfile.parse()
data.listify()
if hasattr(data, 'natom'):
molecule['NAtom'] = data.natom
if hasattr(data, 'homos'):
calculated_properties['Homos'] = data.homos
if hasattr(data, 'scfenergies'):
result['ScfEnergies'] = data.scfenergies # Not updated by the seagrid-data
if hasattr(data, 'coreelectrons'):
result['CoreElectrons'] = data.coreelectrons # Not updated by the seagrid-data
if hasattr(data, 'moenergies'):
result['MoEnergies'] = data.moenergies # Not updated by the seagrid-data
if hasattr(data, 'atomcoords'):
result['AtomCoords'] = data.atomcoords # Not updated by the seagrid-data
if hasattr(data, 'scftargets'):
result['ScfTargets'] = data.scftargets # Not updated by the seagrid-data
if hasattr(data, 'nmo'):
molecule['Nmo'] = data.nmo
if hasattr(data, 'nbasis'):
calculation['NBasis'] = data.nbasis
if hasattr(data, 'atomnos'):
result['AtomNos'] = data.atomnos # Not updated by the seagrid-data
except:
sys.stderr.write('cclib parsing failed!')
# Drawing the molecule
# mol.draw(show=False, filename=molecule_image_file)
result['Identifiers'] = identifiers
result['Calculation'] = calculation
result['Molecule'] = molecule
result['CalculatedProperties'] = calculated_properties
result['ExecutionEnvironment'] = execution_environment
result['FinalMoleculeStructuralFormats'] = molecule_structural_formats
result = json.dumps(result, separators=(',', ':'), sort_keys=False, indent=4)
json.dump()
output_file = open(output_file_name, 'w')
for row in result:
output_file.write(row)
output_file.close()
def CalcJ():
#
#molA_parser=ccopen("part1/"+namejob+"part1.log")
#molB_parser=ccopen("part2/"+namejob+"part2.log")
#molAB_parser=ccopen("dim/"+namejob+"dim.log")
MOLA_CP=sys.argv[1]
MOLB_CP=sys.argv[2]
MOLAB_CP=sys.argv[3]
# Open the Gaussian 'log' files with CCLIB
molA_parser=ccopen("%s"%(MOLA_CP))
molB_parser=ccopen("%s"%(MOLB_CP))
molAB_parser=ccopen("%s"%(MOLAB_CP))
# Parse the logfiles into mol{A,B,AB} objects
molA=molA_parser.parse()
molB=molB_parser.parse()
molAB=molAB_parser.parse()
print("Gaussian logfiles Loaded and Parsed...")
nbs=molAB.nbasis
if molA.nbasis!=molB.nbasis:
print("Number of basis functions in molA and molB. Failing.")
return False
for mole in molA,molB,molAB:
if len(mole.atomcoords)!=1:
print(mole," calculation appears to be an optimisation (multiple steps)! Warning!")
nhomoA=molA.homos
nhomoB=molB.homos
nhomoAB=molAB.homos
print("Energy splitting in dimer")
print('ESID H**O-H**O coupling: ',(molAB.moenergies[0][nhomoAB]-molAB.moenergies[0][nhomoAB-1])/2.0," eV")
print('ESID LUMO-LUMO coupling: ',(molAB.moenergies[0][nhomoAB+2]-molAB.moenergies[0][nhomoAB+1])/2.0," eV")
#Take mocoeffs[0] - the alpha electrons, to get matrix in correct order
MolAB_Pro = np.transpose(np.dot(molAB.mocoeffs[0],molAB.aooverlaps))
PsiA_DimBS = np.dot(molA.mocoeffs[0], MolAB_Pro)
PsiB_DimBS = np.dot(molB.mocoeffs[0], MolAB_Pro)
# print "Dim Mocoeffs: ", molAB.moenergies[0]/27.211
# JMF 2009-08 CCLIB code to reproduce JKP's original values for Ethene. BELIEVED INCORRECT.
print("Original James KP method; matrix multiplication believed out of order.")
JAB=np.dot(np.dot(np.diagflat(molAB.moenergies[0]),PsiA_DimBS), np.transpose(PsiB_DimBS) )
JAA=np.dot(np.dot(np.diagflat(molAB.moenergies[0]),PsiA_DimBS), np.transpose(PsiA_DimBS) )
JBB=np.dot(np.dot(np.diagflat(molAB.moenergies[0]),PsiB_DimBS), np.transpose(PsiB_DimBS) )
print("JKP H**O-H**O coupling: ", JAB[nhomoA,nhomoB], " eV")
print("JKP LUMO-LUMO coupling: ", JAB[nhomoA+1,nhomoB+1], " eV")
#Note: CCLIB values in eV, so converted to Hartree for checking with JKP original code
print("JKP H**O-H**O coupling: ", JAB[nhomoA,nhomoB]/27.211, " Ha")
print("JKP LUMO-LUMO coupling: ", JAB[nhomoA+1,nhomoB+1]/27.211, " Ha")
# JKP - 2009-09-10 update (script pasted into email)
print("James KP 2009-09-10 re-order matrix multiplication...")
# this is the bit I changed: note the different order of multiplication
# I suspect that most mistakes will tend to be of that kind... x.y != y.x alas...
JAB = np.dot(np.dot( PsiB_DimBS, np.diagflat(molAB.moenergies[0])) , np.transpose(PsiA_DimBS) )
JAA = np.dot(np.dot( PsiA_DimBS, np.diagflat(molAB.moenergies[0])) , np.transpose(PsiA_DimBS) )
JBB = np.dot(np.dot( PsiB_DimBS, np.diagflat(molAB.moenergies[0])) , np.transpose(PsiB_DimBS) )
#print "JAB", JAB
#print "JAA", JAA
#print "JBB", JBB
# I think these are hardwired by James to look at ethene molecular orbital overlaps
# print "PSI1 in dimer", PsiA_DimBS[3][0], PsiA_DimBS[3][1], PsiA_DimBS[3][2], PsiA_DimBS[3][3] , PsiA_DimBS[3][4], PsiA_DimBS[3][5], PsiA_DimBS[3][6], PsiA_DimBS[3][7]
# print "PSI1 in dimer", PsiB_DimBS[3][0], PsiB_DimBS[3][1], PsiB_DimBS[3][2], PsiB_DimBS[3][3] , PsiB_DimBS[3][4], PsiB_DimBS[3][5], PsiB_DimBS[3][6], PsiB_DimBS[3][7]
print("JKP2 H**O-H**O coupling: ", JAB[nhomoA,nhomoB], " eV")
print("JKP2 LUMO-LUMO coupling: ", JAB[nhomoA+1,nhomoB+1], " eV")
#Note: CCLIB values in eV, so converted to Hartree for checking with JKP original code
print("JKP2 H**O-H**O coupling: ", JAB[nhomoA,nhomoB]/27.211, " Ha")
print("JKP2 LUMO-LUMO coupling: ", JAB[nhomoA+1,nhomoB+1]/27.211, " Ha")
# JMF 2016-10-04: These additions are I think due to Bjorn Baumeier 2009-09-17
# Determine overlap analogous to JAB
SAB = np.dot(PsiB_DimBS , np.transpose(PsiA_DimBS) )
# Calculate JAB_eff according to Eq.10 in JACS 128, 9884 (2006)
# !only for the desired orbitals!
print("Bjorn Baumeier JAB_eff (Eq.10 in JACS 128, 9884 (2006)) ")
orbA=nhomoA
orbB=nhomoB
JAB_eff = (JAB[orbA,orbB] - 0.5*(JAA[orbA,orbA]+JBB[orbB,orbB])*SAB[orbA,orbB])/(1.0 - SAB[orbA,orbB]*SAB[orbA,orbB])
print("Jeff H**O-H**O Jeff-coupling", JAB_eff," eV")
orbA=nhomoA+1
orbB=nhomoB+1
JAB_eff = (JAB[orbA,orbB] - 0.5*(JAA[orbA,orbA]+JBB[orbB,orbB])*SAB[orbA,orbB])/(1.0 - SAB[orbA,orbB]*SAB[orbA,orbB])
print("Jeff LUMO-LUMO Jeff-coupling", JAB_eff, " eV")
return [JAB, JAA, JBB]
result['TimeCost'] = meta_f.record['TimeCost']
if 'CPUTime' in meta_f.record:
result['CPUTime'] = meta_f.record['CPUTime']
if 'Convergence' in meta_f.record:
result['Convergenece'] = meta_f.record['Convergence']
if 'FullPath' in meta_f.record:
result['FullPath'] = meta_f.record['FullPath']
if 'InputButGeom' in meta_f.record:
result['InputButGeom'] = meta_f.record['InputButGeom']
if 'Otherinfo' in meta_f.record:
result['Otherinfo'] = meta_f.record['Otherinfo']
if 'Comments' in meta_f.record:
result['Comments'] = meta_f.record['Comments']
#extracting fields from cclib
myfile = ccopen(file_name)
try:
data = myfile.parse()
data.listify()
if hasattr(data, 'natom'):
result['NAtom'] = data.natom
if hasattr(data, 'homos'):
result['Homos'] = data.homos
if hasattr(data, 'scfenergies'):
result['ScfEnergies'] = data.scfenergies
if hasattr(data, 'coreelectrons'):
result['CoreElectrons'] = data.coreelectrons
if hasattr(data, 'moenergies'):
result['MoEnergies'] = data.moenergies
if hasattr(data, 'atomcoords'):
result['AtomCoords'] = data.atomcoords
def CountPJ():
# Read in molecule log files for counterpoise method. Requires IOp(6/7=3) in Gaussian header + ghost atoms to make up basis sets in individual com files
MOLA_CP=sys.argv[1]
MOLB_CP=sys.argv[2]
MOLAB_CP=sys.argv[3]
# Open the log files
molA_parser=ccopen("%s"%(MOLA_CP))
molB_parser=ccopen("%s"%(MOLB_CP))
molAB_parser=ccopen("%s"%(MOLAB_CP))
# Parse the relevant data
molA=molA_parser.parse()
molB=molB_parser.parse()
molAB=molAB_parser.parse()
print ("Parsed...")
# Size of basis sets
Nbasis=molAB.nbasis
# H**O index
nhomoA=molA.homos
nhomoB=molB.homos
nhomoAB=molAB.homos
print "H**O A: ", nhomoA
print "H**O B: ", nhomoB
print "H**O AB: ", nhomoAB
# Every basis set should have the same size (the size of the pair)
if molA.nbasis!=molB.nbasis:
print("Count of basis functions doesn't match. Failing.")
return False
# Get molecular orbitals
MOsA=(molA.mocoeffs[0])
MOsB=(molB.mocoeffs[0])
MOsAB=(molAB.mocoeffs[0])
#print "MOsA: ", MOsA
#print "MOsB: ", MOsB
#print "MOsAB: ", MOsAB
# Get overlaps
SAB=molAB.aooverlaps
#print "Overlaps: ", SAB
# Get eigenvalues of pair
EvalsAB=molAB.moenergies[0]
print "Energies: ", molAB.moenergies
print "Energies: ", EvalsAB
# Find H**O and LUMO from energy splitting in dimer
print "ESID H**O-H**O coupling", 0.5*(EvalsAB[nhomoAB]-EvalsAB[nhomoAB-1])
print "ESID LUMO-LUMO coupling", 0.5*(EvalsAB[nhomoAB+2]-EvalsAB[nhomoAB+1])
# Calculate the molecular orbitals of A and B in the AB basis set
MolAB_Pro = (np.dot(MOsAB,SAB)).T
PsiA_AB_BS = np.dot(MOsA, MolAB_Pro)
PsiB_AB_BS = np.dot(MOsB, MolAB_Pro)
#MolAB_Pro = (np.dot(MOsAB,SAB)).T
#PsiA_AB_BS = np.dot(MOsA, MolAB_Pro)
#PsiB_AB_BS = np.dot(MOsB, MolAB_Pro)
#print "MolA in basis of dimer: ", PsiA_AB_BS
#print "MolB in basis of dimer: ", PsiB_AB_BS
# Calculate the matrix of transfer integrals
JAB=np.dot(np.dot(np.diagflat(EvalsAB),PsiA_AB_BS),PsiB_AB_BS.T)
print "J matrix: ", JAB
# Print the H**O-H**O and LUMO-LUMO coupling
print "H**O-H**O coupling: ", JAB[nhomoA,nhomoB]
print "LUMO-LUMO coupling: ", JAB[nhomoA+1,nhomoB+1]
def extract(filenames, equilibrium_length=None):
frequencies = []
intensities = []
geometry_params = dict()
geometry_params['geometry'] = []
geometry_params['l1'] = []
geometry_params['l2'] = []
geometry_params['l12'] = []
geometry_params['theta'] = []
if equilibrium_length:
geometry_params['l1_diff'] = []
geometry_params['l2_diff'] = []
geometry_params['l12_diff'] = []
geometry_params['o12_diff'] = []
for filename in filenames:
try:
job = ccopen(filename)
data = job.parse()
vibfreqs = data.vibfreqs
vibirs = data.vibirs
geometry = data.atomcoords[0]
assert len(vibfreqs) == len(vibirs) >= 3
frequencies.append(vibfreqs)
intensities.append(vibirs)
C, O1, O2 = 0, 1, 2
d_C_O1 = distance(geometry[C], geometry[O1])
d_C_O2 = distance(geometry[C], geometry[O2])
d_O1_O2 = distance(geometry[O1], geometry[O2])
bond_sum = d_C_O1 + d_C_O2
# bond_difference = abs(d_C_O1 - d_C_O2)
angle = bond_angle(geometry[O1], geometry[C], geometry[O2])
theta = 180.0 - angle
l1 = d_C_O1
l2 = d_C_O2
o12 = d_O1_O2
l12 = bond_sum
# dl = bond_difference
if equilibrium_length:
l1_diff = l1 - equilibrium_length
l2_diff = l2 - equilibrium_length
o12_diff = o12 - (2 * equilibrium_length)
l12_diff = l12 - (2 * equilibrium_length)
geometry_params['l1_diff'].append(l1_diff)
geometry_params['l2_diff'].append(l2_diff)
geometry_params['l12_diff'].append(l12_diff)
geometry_params['o12_diff'].append(o12_diff)
geometry_params['geometry'].append(geometry)
geometry_params['l1'].append(l1)
geometry_params['l2'].append(l2)
geometry_params['l12'].append(l12)
geometry_params['theta'].append(theta)
except:
pass
frequencies = make_numpy_array_from_ragged_list(frequencies)
intensities = make_numpy_array_from_ragged_list(intensities)
for k in geometry_params:
geometry_params[k] = np.array(geometry_params[k])
print("frequencies.shape:", frequencies.shape)
print("intensities.shape:", intensities.shape)
print("geometry_params['geometry'].shape:", geometry_params['geometry'].shape)
return frequencies, intensities, geometry_params
def ProJ():
# Read in molecule log files for projective method. Requires iop(3/33=1,6/7=3) in Gaussian header for calculation on each molecule + the pair
MOLA_proj = sys.argv[1]
MOLB_proj = sys.argv[2]
MOLAB_proj = sys.argv[3]
Degeneracy_HOMO = int(sys.argv[4])
Degeneracy_LUMO = int(
sys.argv[5]) # =0 for non-degenerate, 2,3 etc for doubly, triply etc
# Open the log files
molA_parser = ccopen("%s" % (MOLA_proj))
molB_parser = ccopen("%s" % (MOLB_proj))
molAB_parser = ccopen("%s" % (MOLAB_proj))
# Parse the relevant data
molA = molA_parser.parse()
molB = molB_parser.parse()
molAB = molAB_parser.parse()
#print ("Parsed...")
# Size of basis sets
nbasisA = molA.nbasis
nbasisB = molB.nbasis
#print "nbasisA: ", nbasisA
#print "nbasisB: ", nbasisB
Nbasis = nbasisA + nbasisB
# Position of H**O
nhomoA = molA.homos
nhomoB = molB.homos
#print "nhomoA: ", nhomoA
#print "nhomoB: ", nhomoB
# Get molecular orbitals. Need the transpose for our purposes.
MOsA = (molA.mocoeffs[0]).T
MOsB = (molB.mocoeffs[0]).T
MOsAB = (molAB.mocoeffs[0]).T
# Get eigenvalues of pair
EvalsAB = molAB.moenergies[0]
# Get overlaps. These are symmetric so transpose not required in this case
SA = molA.aooverlaps
SB = molB.aooverlaps
SAB = molAB.aooverlaps
# Set up matrices for MOs and S
MOs = np.zeros((Nbasis, Nbasis))
S = np.zeros((Nbasis, Nbasis))
MOs[0:nbasisA, 0:nbasisA] = MOsA
MOs[nbasisA:Nbasis, nbasisA:Nbasis] = MOsB
S[0:nbasisA, 0:nbasisA] = SA
S[nbasisA:Nbasis, nbasisA:Nbasis] = SB
# Calculate upper diagonal matrix D, such that S=D.T*D for Lowdin orthogonalisation.
D = sp.linalg.cholesky(S)
Dpair = sp.linalg.cholesky(SAB)
# Orthogonalise MOs matrix and MOsAB matrix
MOsorth = np.dot(D, MOs)
#print np.shape(MOsorth)
MOspairorth = np.dot(Dpair, MOsAB)
#print np.shape(MOspairorth)
# Calculate the Fock matrix
B = np.dot(MOsorth.T, MOspairorth)
Evals = np.diagflat(EvalsAB)
F = np.dot(np.dot(B, Evals), B.T)
# Output the H**O-H**O and LUMO-LUMO coupling elements fromt the Fock matrix
if Degeneracy_HOMO == 0:
print "H**O-H**O coupling: ", F[nhomoB + nbasisA, nhomoA]
if Degeneracy_LUMO == 0:
print "LUMO-LUMO coupling: ", F[nhomoB + nbasisA + 1, nhomoA + 1]
# Degeneracies
if Degeneracy_HOMO != 0:
F_deg_HOMO = F[nhomoB + nbasisA - Degeneracy_HOMO + 1:nhomoB +
nbasisA + 1, nhomoA - Degeneracy_HOMO:nhomoA]
print "H**O-H**O coupling", (np.sum(np.absolute(
F_deg_HOMO**2))) / Degeneracy_HOMO**2
if Degeneracy_LUMO != 0:
F_deg_LUMO = F[nhomoB + nbasisA:nhomoB + nbasisA + Degeneracy_LUMO,
nhomoA:nhomoA + Degeneracy_LUMO]
print "LUMO-LUMO coupling", (np.sum(np.absolute(
F_deg_LUMO**2))) / Degeneracy_LUMO**2
import sys
import os
import numpy as np
import cclib
from cclib.parser import ccopen
if __name__ == "__main__":
# read in filename and parse log file
filename = sys.argv[2]
mylogfile = ccopen(filename)
data = mylogfile.parse()
# if TS calculation
if sys.argv[1] == "TS":
energy = data.scfenergies
print(energy)
# if NF calculation
if sys.argv[1] == "NF":
G = data.freeenergy
freqs = data.vibfreqs
imaginary = freqs[freqs < 0]
print(G, imaginary)
def load_calc_list(job_dir, pname='nwchem.out', context=None):
meta_data = Munch()
calc = Munch(meta_data=meta_data, properties=Munch())
outfile = join(job_dir, pname)
myfile = ccopen(outfile)
#myfile.logger.setLevel(logging.ERROR)
data = myfile.parse()
t = PeriodicTable()
# Vdd calc
# print data.nmo
# print data.moenergies[-1]
# print data.homos
# print data.scfenergies[-1]
if 'optdone' in data.__dict__:
calc.optdone = data.optdone
if context == 'opt':
return calc
else:
calc.optdone = None
if len(data.scfenergies) > 0:
calc.optdone = False
else:
calc.optdone = None
# return calc
if calc.optdone:
meta_data.version = data.metadata['package_version']
meta_data.program = data.metadata['package']
#meta_data.wall_clock_time = data.walltime
#meta_data.wall_clock_time = data.walltime
meta_data.worker_name = pname
calc.theory = data.metadata['methods'][-1]
calc.functional = data.metadata['functional']
calc.basisset = data.metadata['basis_set']
calc.properties.total_energy = convertor(data.scfenergies[-1], "eV",
"hartree")
# calc.properties.total_energy = data.scfenergies[-1]
nmotot = data.nmo
numoc = len(data.nooccnos[-1])
low = len(data.moenergies[-1]) - numoc
newmoe = data.moenergies[-1][low:nmotot]
newmoe = convertor(data.moenergies[-1], "eV", "hartree")[low:nmotot]
occ = []
unocc = []
for index, value in enumerate(data.nooccnos[-1]):
if value != 0.0:
occ_info = dict(method="rhf",
spin="alpha",
type="occ",
number=index + 1,
energy=newmoe[index])
occ.append(occ_info)
else:
unocc_info = dict(method="rhf",
spin="alpha",
type="unocc",
number=index + 1,
energy=newmoe[index])
unocc.append(unocc_info)
for index, value in enumerate(data.nooccnos[-1]):
if value == 0.0:
lumo = newmoe[index]
h**o = newmoe[index - 1]
break
#
calc.properties.h**o = h**o
calc.properties.lumo = lumo
calc.properties.gap = lumo - h**o
#calc.properties.electric_dipole_moment_norm
calc.properties.occupied_orbital_number = len(occ)
calc.orbital_energy_list = occ + unocc
coords = []
for index, value in enumerate(data.atomcoords[-1]):
x, y, z = value
elem = t.element[data.atomnos[index]]
coords.append(dict(element=elem, x=x, y=y, z=z))
calc.coords = coords
return calc
# uses modified cclib 1.00
import sys
sys.path.insert(1, sys.argv[2]) # add $RMG/source to the PYTHONPATH so that import statements below work properly
import logging
from cclib.parser import ccopen
myfile = ccopen(sys.argv[1])
myfile.logger.setLevel(
logging.ERROR
) # cf. http://cclib.sourceforge.net/wiki/index.php/Using_cclib#Additional_information
data = myfile.parse()
print data.natom # print line 1
# print data.atomnos #print line 2; this has a problem with wrapping; Richard West suggested a couple of alternatives as shown below
print [i for i in data.atomnos] # this will put a comma between each element; alternative is:
# for i in data.atomnos:
# print i,
print data.atomcoords[-1] # print the final optimized atom coordinates
print data.scfenergies[
-1
] / 27.2113845 # print the final optimized PM3 energy (cclib gives this in eV, but I have converted here to Hartree); conversion value taken from cclib code; compare CODATA 2006 value 27.21138386(68) eV/Hartree
print data.molmass # print the molecular mass (in amu)
if data.natom > 1: # for species with more than one atom, display vibrational frequencies and rotational constants
# print data.vibfreqs #print the vibrational frequencies; see atomnos discussion above
print [i for i in data.vibfreqs]
print data.rotcons[
-1
] # print the final rotational constants (note that ideally we would use next to last value ([-2]) as this has more significant digits and is for the same geometry, but there is a complication for linear molecules (labeled as "Rotational constant" rather than "...constants"...there might be some ways around this like looking for "Rotational constant" string instead, but it is probably not a big deal to just use rounded values
CMy = sum(positions[:, 1] * masses) / mass_sum
CMz = sum(positions[:, 2] * masses) / mass_sum
return (CMx, CMy, CMz)
def zpe(real_frequencies):
zpe = zpe_prefactor * sum(real_frequencies)
return zpe
if __name__ == '__main__':
filename = sys.argv[1]
print('=' * 78)
print('filename:', filename)
job = ccopen(filename)
data = job.parse()
hessian_scf = data.hessian
# Before obtaining frequencies from the SCF Hessian, we must remove any
# blocks that correspond to ghost atoms, then mass-weight it.
gh_indices = list(i for i in range(len(data.atomnos))
if data.atomnos[i] < 1)
atom_indices = list(i for i in range(len(data.atomnos))
if data.atomnos[i] > 0)
hessian_dim = 3 * len(atom_indices)
hessian_scf_noghost = np.empty(shape = (hessian_dim, hessian_dim))
# Transfer non-ghost blocks to the new Hessian:
def ProJ():
# Read in molecule log files for projective method. Requires iop(3/33=1,6/7=3) in Gaussian header for calculation on each molecule + the pair
#MOLA_proj=sys.argv[1]
#MOLB_proj=sys.argv[2]
#Degeneracy_HOMO=int(sys.argv[4])
#Degeneracy_LUMO=int(sys.argv[5]) # =0 for non-degenerate, 2,3 etc for doubly, triply etc
# Open the log files
molA_parser = ccopen("%s" % (MOLA_CP))
molB_parser = ccopen("%s" % (MOLB_CP))
molAB_parser = ccopen("%s" % (MOLAB_CP))
# Parse the relevant data
molA = molA_parser.parse()
molB = molB_parser.parse()
molAB = molAB_parser.parse()
print ("Parsed...")
# Size of basis sets
nbasisA = molA.nbasis
nbasisB = molB.nbasis
nbasisAB = molAB.nbasis
print ("nbasisA: ", nbasisA)
print ("nbasisB: ", nbasisB)
print ("nbasisAB: ", nbasisAB)
Nbasis = nbasisA + nbasisB
# Position of H**O
nhomoA = molA.homos
nhomoB = molB.homos
nhomoAB = molAB.homos
# Get molecular orbitals. Need the transpose for our purposes.
MOsA=(molA.mocoeffs[0]).T
MOsB=(molB.mocoeffs[0]).T
MOsAB=(molAB.mocoeffs[0]).T
# Get eigenvalues of pair
EvalsAB = molAB.moenergies[0]
# Check degeneracy
deg_homo=1
deg_lumo=1
for i in range(1, 10):
if (np.absolute(EvalsAB[nhomoAB] - EvalsAB[nhomoAB - i]) < 0.005):
deg_homo+=1
if (np.absolute(EvalsAB[nhomoAB + 1 + i] - EvalsAB[nhomoAB + 1]) < 0.005):
deg_lumo+=1
print ("Deg H**O: ", deg_homo)
print ("Deg LUMO: ", deg_lumo)
# Get overlaps. These are symmetric so transpose not required in this case
SA = molA.aooverlaps
SB = molB.aooverlaps
SAB = molAB.aooverlaps
# Set up matrices for MOs and S
MOs = np.zeros((Nbasis, Nbasis))
S = np.zeros((Nbasis, Nbasis))
# First N/2 columns correspond to MO of molA
MOs[:nbasisA, :nbasisA] = MOsA
#MOs[:nbasisA, :MOsA.shape[1]] = MOsA
# Second N/2 columns correspond to MO of molB
MOs[nbasisA:Nbasis, nbasisA:Nbasis] = MOsB
#MOs[nbasisA:Nbasis, MOsA.shape[1]:MOsA.shape[1] + MOsB.shape[1]] = MOsB
# Same for overlaps:
S[0:nbasisA, 0:nbasisA] = SA
S[nbasisA:Nbasis, nbasisA:Nbasis] = SB
# Calculate upper diagonal matrix D, such that S=D.T*D for Lowdin orthogonalisation.
D=sp.linalg.cholesky(S)
Dpair=sp.linalg.cholesky(SAB)
# Orthogonalise MOs matrix and MOsAB matrix
MOsorth = np.dot(D, MOs)
MOspairorth=np.dot(Dpair,MOsAB)
# Calculate the Fock matrix
B = np.dot(MOsorth.T, MOspairorth)
Evals = np.diagflat(EvalsAB)
F = np.dot(np.dot(B, Evals), B.T)
# Output the H**O-H**O and LUMO-LUMO coupling elements fromt the Fock matrix
if deg_homo == 1:
print ("H**O-H**O coupling: ", F[int(nhomoB + nbasisA), int(nhomoA)])
if deg_lumo == 1:
print ("LUMO-LUMO coupling: ", F[int(nhomoB + nbasisA + 1), int(nhomoA + 1)])
# Degeneracies
# If orbitals are degenerate, take root mean square.
# e.g. RMS of H**O-H**O, H**O-H**O-1, H**O-1-H**O and H**O-1-H**O-1
if deg_homo == 2:
j0 = F[int(nhomoB + nbasisA), int(nhomoA)]
print ("H**O-H**O coupling: ", j0)
j1 = F[int(nhomoB + nbasisA - 1), int(nhomoA)]
print ("H**O-H**O-1 coupling: ", j1)
j2 = F[int(nhomoB + nbasisA), int(nhomoA - 1)]
print ("H**O-1-H**O coupling: ", j2)
j3 = F[int(nhomoB + nbasisA - 1), int(nhomoA - 1)]
print ("H**O-1-H**O-1 coupling: ", j3)
print('------------------------------')
print (' H**O-H**O RMS equals', np.sqrt(np.mean(np.square([j0, j3]))))
print('------------------------------')
#Degeneracy_HOMO = deg_homo
#F_deg_HOMO = F[int(nhomoB + nbasisA - Degeneracy_HOMO + 1):int(nhomoB + nbasisA + 1), int(nhomoA - Degeneracy_HOMO):int(nhomoA)]
#F_deg_HOMO = F[int(nhomoB + nbasisA - deg_homo): int(nhomoB + nbasisA), int(nhomoA - deg_homo):int(nhomoA)]
# print(F_deg_HOMO)
# print ("H**O-H**O coupling", (np.sum(np.absolute(F_deg_HOMO**2))) / deg_homo**2) # Strange way to get RMS?
#print ("Degenerate H**O-H**O coupling: ", np.sqrt(np.mean(np.square(F_deg_HOMO))))
if deg_lumo == 2:
j0 = F[int(nhomoB + nbasisA + 1), int(nhomoA + 1)]
print ("LUMO-LUMO coupling: ", j0)
j1 = F[int(nhomoB + nbasisA + 1), int(nhomoA + 1 + 1)]
print ("LUMO-LUMO+1 coupling: ", j1)
j2 = F[int(nhomoB + nbasisA + 1 + 1), int(nhomoA + 1)]
print ("LUMO+1-LUMO coupling: ", j2)
j3 = F[int(nhomoB + nbasisA + 1 + 1), int(nhomoA + 1 + 1)]
print ("LUMO+1-LUMO+1 coupling: ", j3)
print('------------------------------')
print ('LUMO-LUMO-RMS equals', np.sqrt(np.mean(np.square([j0, j3]))))
print('------------------------------')
#print ("LUMO-LUMO coupling: ", F[int(nhomoB + nbasisA + 1), int(nhomoA + 1)])
#F_deg_LUMO = F[int(nhomoB + nbasisA):int(nhomoB + nbasisA + deg_lumo - 1), int(nhomoA + 1):int(nhomoA + 1 + deg_lumo - 1)]
#print(F_deg_LUMO)
## print ("LUMO-LUMO coupling", (np.sum(np.absolute(F_deg_LUMO**2))) / deg_lumo**2)
#print ("Degenerate LUMO-LUMO coupling: ", np.sqrt(np.mean(np.square(F_deg_LUMO))))
pass
def CountPJ():
# Read in molecule log files for counterpoise method. Requires IOp(6/7=3) in Gaussian header + ghost atoms to make up basis sets in individual com files
# MOLA_CP=sys.argv[1]
# MOLB_CP=sys.argv[2]
# MOLAB_CP=sys.argv[3]
# Open the log files
molA_parser = ccopen("%s" % (MOLA_CP))
molB_parser = ccopen("%s" % (MOLB_CP))
molAB_parser = ccopen("%s" % (MOLAB_CP))
# Parse the relevant data
molA = molA_parser.parse()
molB = molB_parser.parse()
molAB = molAB_parser.parse()
print("Parsed...")
# H**O and LUMO index
nhomoA = molA.homos
nhomoB = molB.homos
nhomoAB = molAB.homos
nlumoA = nhomoA + 1
nlumoB = nhomoB + 1
#print ("H**O AB: ", nhomoAB)
# Every basis set should have the same size (the size of the pair)
if molA.nbasis != molB.nbasis:
print("Count of basis functions doesn't match. Failing.")
# Get molecular orbitals
MOsA = molA.mocoeffs[0]
MOsB = molB.mocoeffs[0]
MOsAB = molAB.mocoeffs[0]
# Get eigenvalues of pair
EvalsAB = molAB.moenergies[0]
# print ("Energies: ", EvalsAB)
print('----------------------------')
print('molA H**O-3: \t', nhomoA - 3, molA.moenergies[0][nhomoA - 3])
print('molA H**O-2: \t', nhomoA - 2, molA.moenergies[0][nhomoA - 2])
print('molA H**O-1: \t', nhomoA - 1, molA.moenergies[0][nhomoA - 1])
print('molA H**O: \t', nhomoA, molA.moenergies[0][nhomoA])
print('molA LUMO: \t', nhomoA + 1, molA.moenergies[0][nhomoA + 1])
print('----------------------------')
print('molB H**O: \t', nhomoB, molB.moenergies[0][nhomoB])
print('molB LUMO: \t', nhomoB + 1, molB.moenergies[0][nhomoB + 1])
print('molB LUMO+1: \t', nhomoB + 2, molB.moenergies[0][nhomoB + 2])
print('molB LUMO+2: \t', nhomoB + 3, molB.moenergies[0][nhomoB + 3])
print('molB LUMO+3: \t', nhomoB + 4, molB.moenergies[0][nhomoB + 4])
print('----------------------------')
print('molAB H**O-4: \t', nhomoAB - 4, molAB.moenergies[0][nhomoAB - 4])
print('molAB H**O-3: \t', nhomoAB - 3, molAB.moenergies[0][nhomoAB - 3])
print('molAB H**O-2: \t', nhomoAB - 2, molAB.moenergies[0][nhomoAB - 2])
print('molAB H**O-1: \t', nhomoAB - 1, molAB.moenergies[0][nhomoAB - 1])
print('molAB H**O: \t', nhomoAB, molAB.moenergies[0][nhomoAB])
print('molAB LUMO: \t', nhomoAB + 1, molAB.moenergies[0][nhomoAB + 1])
print('molAB LUMO+1: \t', nhomoAB + 2, molAB.moenergies[0][nhomoAB + 2])
print('molAB LUMO+2: \t', nhomoAB + 3, molAB.moenergies[0][nhomoAB + 3])
print('molAB LUMO+3: \t', nhomoAB + 4, molAB.moenergies[0][nhomoAB + 4])
print('molAB LUMO+5: \t', nhomoAB + 5, molAB.moenergies[0][nhomoAB + 5])
print('----------------------------')
print("Gap in isolation: ",
molB.moenergies[0][nhomoB + 1] - molA.moenergies[0][nhomoA])
print("Gap in pair: ", EvalsAB[nhomoAB + 1] - EvalsAB[nhomoAB])
deg_homo = 1
deg_lumo = 1
for i in range(1, 10):
if (np.absolute(EvalsAB[nhomoAB] - EvalsAB[nhomoAB - i]) < 0.005):
deg_homo += 1
if (np.absolute(EvalsAB[nhomoAB + 1 + i] - EvalsAB[nhomoAB + 1]) <
0.005):
deg_lumo += 1
print("Deg H**O: ", deg_homo)
print("Deg LUMO: ", deg_lumo)
# Find H**O and LUMO from energy splitting in dimer
#print ("ESID H**O-H**O coupling", 0.5 * (EvalsAB[nhomoAB] - EvalsAB[nhomoAB - 1]))
#print ("ESID LUMO-LUMO coupling", 0.5 * (EvalsAB[nhomoAB + 2] - EvalsAB[nhomoAB + 1]))
# Calculate the molecular orbitals of A and B in the AB basis set
SAB = molAB.aooverlaps
MolAB_Pro = (np.dot(MOsAB, SAB)).T
PsiA_AB_BS = np.dot(MOsA, MolAB_Pro)
PsiB_AB_BS = np.dot(MOsB, MolAB_Pro)
# print ('PsiA_AB_BS = ',PsiA_AB_BS[nhomoA, nlumoB])
# print ('PsiB_AB_BS = ',PsiB_AB_BS[nhomoA, nlumoB])
# temp = np.dot(PsiA_AB_BS, np.diagflat(EvalsAB))
# print ('PsiA_AB_BS dot E_lk = ', temp[nhomoA,nlumoB])
# temp2 = PsiB_AB_BS.T
# print ('PsiB_AB_BS^T = ',temp2[nhomoA, nlumoB])
# temp3 = np.dot(temp, temp2)
# print ('PsiA_AB_BS dot E_lk dot PsiA_AB_BS^T = ', temp3[nhomoA,nlumoB])
# Calculate the matrix of transfer integrals
JAB = np.dot(np.dot(PsiA_AB_BS, np.diagflat(EvalsAB)), PsiB_AB_BS.T)
JAA = np.dot(np.dot(PsiA_AB_BS, np.diagflat(EvalsAB)), PsiA_AB_BS.T)
JBB = np.dot(np.dot(PsiB_AB_BS, np.diagflat(EvalsAB)), PsiB_AB_BS.T)
S = np.dot(PsiA_AB_BS, PsiB_AB_BS.T)
# Symmetric Lowdin transformation
J_eff = (JAB - 0.5 * (JAA + JBB) * S) / (1.0 - S**2)
# print ('j_AB = ',JAB[nhomoA, nlumoB])
# print ('j_AA = ',JAA[nhomoA, nlumoB])
# print ('j_BB = ',JBB[nhomoA, nlumoB])
# print ('S_AB = ',S[nhomoA, nlumoB])
# Energy eigenvalues
# eA_eff = 0.5*( (JAA + JBB) - 2 * JAB * S + (JAA - JBB) * np.sqrt(1 - S**2 ))/ ( 1 - S**2 )
# eB_eff = 0.5*( (JAA + JBB) - 2 * JAB * S - (JAA - JBB) * np.sqrt(1 - S**2 ))/ ( 1 - S**2 )
# Print the H**O-H**O and LUMO-LUMO coupling
print('\n ---------------------------- \n')
with open(path + jobtitle + '/' + jobtitle + '-CP-calc.txt',
"w") as text_file:
print("Job title: ", jobtitle)
print(f"Job title: {jobtitle}", file=text_file)
if deg_homo == 1:
# print ("nHOMO A: ", nhomoA)
# print ("nHOMO B: ", nlumoB)
# print ("H**O A: ", nhomoA, eA_eff[nhomoA,nhomoA])
# print (f"H**O A: {eA_eff[nhomoA,nhomoA]}", file=text_file)
# print ("LUMO B: ", nlumoB, eB_eff[nlumoB,nlumoB])
# print (f"LUMO B: {eB_eff[nlumoB,nlumoB]}", file=text_file)
# print ("ESID H**O-H**O coupling", 0.5 * (EvalsAB[nhomoAB] - EvalsAB[nhomoAB - 1]))
# print (f"ESID H**O-H**O coupling {0.5 * (EvalsAB[nhomoAB] - EvalsAB[nhomoAB - 1])}", file=text_file)
# print ("H**O-H**O coupling: ", J_eff[nhomoA,nhomoB])
# print (f"H**O-H**O coupling: {J_eff[nhomoA,nhomoB]}", file=text_file)
print("H**O", nhomoA, "-LUMO", nlumoB, " coupling: ",
J_eff[nhomoA, nlumoB])
print(f"H**O-LUMO coupling: {J_eff[nhomoA,nlumoB]}",
file=text_file)
if deg_lumo == 1:
# print ("ESID LUMO-LUMO coupling", 0.5 * (EvalsAB[nhomoAB + 2] - EvalsAB[nhomoAB + 1]))
# print (f"ESID LUMO-LUMO coupling {0.5 * (EvalsAB[nhomoAB + 2] - EvalsAB[nhomoAB + 1])}", file=text_file)
# print ("LUMO-LUMO coupling: ", J_eff[nlumoA,nlumoB])
# print (f"LUMO-LUMO coupling: {J_eff[nlumoA,nlumoB]}", file=text_file)
#print ("LUMO-H**O coupling: ", J_eff[nlumoA,nhomoB])
#print (f"LUMO-H**O coupling: {J_eff[nlumoA,nhomoB]}", file=text_file)
pass
if deg_homo == 2:
# doubly degenerate
# %H00=H_eff(nhomo_mon+nbasis, nhomo_mon );
# %H01=H_eff(nhomo_mon+nbasis, nhomo_mon-1);
# %H10=H_eff(nhomo_mon+nbasis-1, nhomo_mon );
# %H11=H_eff(nhomo_mon+nbasis-1, nhomo_mon-1);
# %L00=H_eff(nhomo_mon+nbasis+1, nhomo_mon+1);
# %L01=H_eff(nhomo_mon+nbasis+1, nhomo_mon);
# %L10=H_eff(nhomo_mon+nbasis, nhomo_mon+1);
# %L11=H_eff(nhomo_mon+nbasis, nhomo_mon );
# %Doubly_degenerate_HOMO_coupling=(abs(H00)+abs(H01)+abs(H10)+abs(H11))/4
# %Doubly_degenerate_LUMO_coupling=(abs(L00)+abs(L01)+abs(L10)+abs(L11))/4
j0 = J_eff[nhomoA, nhomoB]
print("H**O-H**O", nhomoA, nhomoB, "coupling: ", j0)
j1 = J_eff[nhomoA, nhomoB - 1]
print("H**O-H**O-1 coupling: ", j1)
j2 = J_eff[nhomoA - 1, nhomoB]
print("H**O-1-H**O coupling: ", j2)
j3 = J_eff[nhomoA - 1, nhomoB - 1]
print("H**O-1-H**O-1 coupling: ", j3)
print('------------------------------')
print(' H**O-H**O RMS equals', np.sqrt(np.mean(np.square([j0,
j3]))))
print('------------------------------')
# deg_homo_J = J_eff[int(nhomoA - deg_homo + 1):int(nhomoA + 1), int(nhomoB - deg_homo + 1):int(nhomoB + 1)]
# print ("Degenerate H**O-H**O coupling: ", np.sqrt(np.mean(np.square(deg_homo_J))))
# print (f"Degenerate H**O-H**O coupling: {np.sqrt(np.mean(np.square(deg_homo_J)))}", file=text_file)
if deg_lumo == 2:
j0 = J_eff[nlumoA, nlumoB]
print("LUMO-LUMO", nlumoA, nlumoB, " coupling: ", j0)
j1 = J_eff[nlumoA, nlumoB + 1]
print("LUMO-LUMO+1 coupling: ", j1)
j2 = J_eff[nlumoA + 1, nlumoB]
print("LUMO+1-LUMO coupling: ", j2)
j3 = J_eff[nlumoA + 1, nlumoB + 1]
print("LUMO+1-LUMO+1 coupling: ", j3)
print('------------------------------')
print('LUMO-LUMO-RMS equals', np.sqrt(np.mean(np.square([j0,
j3]))))
print('------------------------------')
# deg_lumo_J = J_eff[int(nlumoA):int(nlumoA + deg_lumo), int(nlumoB):int(nlumoB + deg_lumo)]
# print ("Degenerate LUMO-LUMO coupling: ", np.sqrt(np.mean(np.square(deg_lumo_J))))
# print (f"Degenerate LUMO-LUMO coupling: {np.sqrt(np.mean(np.square(deg_lumo_J)))}", file=text_file)
if deg_homo == 4:
# molA H**O
j0 = J_eff[nhomoA, nhomoB]
print("H**O-H**O coupling: ", j0)
# j1 = J_eff[nhomoA, nhomoB - 1]
# j2 = J_eff[nhomoA, nhomoB - 2]
# j3 = J_eff[nhomoA, nhomoB - 3]
# molA H**O-1
# j4 = J_eff[nhomoA-1, nhomoB]
j5 = J_eff[nhomoA - 1, nhomoB - 1]
# j6 = J_eff[nhomoA-1, nhomoB - 2]
# j7 = J_eff[nhomoA-1, nhomoB - 3]
# molA H**O-2
# j8 = J_eff[nhomoA-2, nhomoB]
# j9 = J_eff[nhomoA-2, nhomoB - 1]
j10 = J_eff[nhomoA - 2, nhomoB - 2]
# j11 = J_eff[nhomoA-2, nhomoB - 3]
# molA H**O-3
# j12 = J_eff[nhomoA-3, nhomoB]
# j13 = J_eff[nhomoA-3, nhomoB - 1]
# j14 = J_eff[nhomoA-3, nhomoB - 2]
j15 = J_eff[nhomoA - 3, nhomoB - 3]
print('------------------------------')
# print (' H**O-H**O RMS equals', np.sqrt(np.mean(np.square([j0, j1, j2, j3, j4, j5, j6, j7, j8, j9, j10, j11, j12, j13, j14, j15]))))
print(' H**O-H**O RMS equals',
np.sqrt(np.mean(np.square([j0, j5, j10, j15]))))
print('------------------------------')
deg_homo_J = J_eff[int(nhomoA - deg_homo + 1):int(nhomoA + 1),
int(nhomoB - deg_homo + 1):int(nhomoB + 1)]
print("Degenerate H**O-H**O coupling: ",
np.sqrt(np.mean(np.square(deg_homo_J))))
print(
f"Degenerate H**O-H**O coupling: {np.sqrt(np.mean(np.square(deg_homo_J)))}",
file=text_file)
if deg_lumo == 4:
# molA H**O
j0 = J_eff[nlumoA, nlumoB]
# print ("LUMO-LUMO coupling: ", j0)
j1 = J_eff[nlumoA, nlumoB + 1]
# print ("LUMO-LUMO+1 coupling: ", j1)
j2 = J_eff[nlumoA, nlumoB + 2]
# print ("LUMO-LUMO+2 coupling: ", j2)
j3 = J_eff[nlumoA, nlumoB + 3]
# print ("LUMO-LUMO+3 coupling: ", j3)
# molA H**O-1
j4 = J_eff[nlumoA + 1, nlumoB]
# print ("LUMO+1-LUMO coupling: ", j4)
j5 = J_eff[nlumoA + 1, nlumoB + 1]
# print ("LUMO+1-LUMO+1 coupling: ", j5)
j6 = J_eff[nlumoA + 1, nlumoB + 2]
# print ("LUMO+1-LUMO+2 coupling: ", j6)
j7 = J_eff[nlumoA + 1, nlumoB + 3]
# print ("LUMO+1-LUMO+3 coupling: ", j7)
# molA H**O-2
j8 = J_eff[nlumoA + 2, nlumoB]
# print ("LUMO+2-LUMO coupling: ", j8)
j9 = J_eff[nlumoA + 2, nlumoB + 1]
# print ("LUMO+2-LUMO+1 coupling: ", j9)
j10 = J_eff[nlumoA + 2, nlumoB + 2]
# print ("LUMO+2-LUMO+2 coupling: ", j10)
j11 = J_eff[nlumoA + 2, nlumoB + 3]
# print ("LUMO+2-LUMO+3 coupling: ", j11)
# molA H**O-3
j12 = J_eff[nlumoA + 3, nlumoB]
# print ("LUMO+3-LUMO coupling: ", j12)
j13 = J_eff[nlumoA + 3, nlumoB + 1]
# print ("LUMO+3-LUMO+1 coupling: ", j13)
j14 = J_eff[nlumoA + 3, nlumoB + 2]
# print ("LUMO+3-LUMO+2 coupling: ", j14)
j15 = J_eff[nlumoA + 3, nlumoB + 3]
# print ("LUMO+3-LUMO+3 coupling: ", j15)
# print(j4, j5, j6, j7, j8, j9, j10, j11, j12, j13, j14, j15)
print('------------------------------')
# print (' LUMO-LUMO RMS equals', np.sqrt(np.mean(np.square([j0, j1, j2, j3, j4, j5, j6, j7, j8, j9, j10, j11, j12, j13, j14, j15]))))
print(' LUMO-LUMO RMS equals',
np.sqrt(np.mean(np.square([j0, j5, j10, j15]))))
print('------------------------------')
deg_lumo_J = J_eff[int(nlumoA):int(nlumoA + deg_lumo),
int(nlumoB):int(nlumoB + deg_lumo)]
print("Degenerate LUMO-LUMO coupling: ",
np.sqrt(np.mean(np.square(deg_lumo_J))))
print(
f"Degenerate LUMO-LUMO coupling: {np.sqrt(np.mean(np.square(deg_lumo_J)))}",
file=text_file)
def CountPJ():
# Read in molecule log files for counterpoise method. Requires IOp(6/7=3) in Gaussian header + ghost atoms to make up basis sets in individual com files
MOLA_CP=sys.argv[1]
MOLB_CP=sys.argv[2]
MOLAB_CP=sys.argv[3]
# Open the log files
molA_parser=ccopen("%s"%(MOLA_CP))
molB_parser=ccopen("%s"%(MOLB_CP))
molAB_parser=ccopen("%s"%(MOLAB_CP))
# Parse the relevant data
molA=molA_parser.parse()
molB=molB_parser.parse()
molAB=molAB_parser.parse()
print ("Parsed...")
# Size of basis sets
Nbasis=molAB.nbasis
# H**O index
nhomoA=molA.homos
nhomoB=molB.homos
nhomoAB=molAB.homos
nlumoA=nhomoA+1
nlumoB=nhomoB+1
print "H**O A: ", nhomoA
print "H**O B: ", nhomoB
print "H**O AB: ", nhomoAB
# Every basis set should have the same size (the size of the pair)
if molA.nbasis!=molB.nbasis:
print("Count of basis functions doesn't match. Failing.")
return False
# Get molecular orbitals
MOsA=molA.mocoeffs[0]
MOsB=molB.mocoeffs[0]
MOsAB=molAB.mocoeffs[0]
# Get eigenvalues of pair
EvalsAB=molAB.moenergies[0]
print "Energies: ", EvalsAB
print "Gap: ", EvalsAB[nhomoAB+1]-EvalsAB[nhomoAB]
# Find H**O and LUMO from energy splitting in dimer
print "ESID H**O-H**O coupling", 0.5*(EvalsAB[nhomoAB]-EvalsAB[nhomoAB-1])
print "ESID LUMO-LUMO coupling", 0.5*(EvalsAB[nhomoAB+2]-EvalsAB[nhomoAB+1])
# Calculate the molecular orbitals of A and B in the AB basis set
SAB=molAB.aooverlaps
MolAB_Pro = (np.dot(MOsAB,SAB)).T
PsiA_AB_BS = np.dot(MOsA, MolAB_Pro)
PsiB_AB_BS = np.dot(MOsB, MolAB_Pro)
# Calculate the matrix of transfer integrals
JAB=np.dot(np.dot(PsiB_AB_BS,np.diagflat(EvalsAB)),PsiA_AB_BS.T)
JAA=np.dot(np.dot(PsiA_AB_BS,np.diagflat(EvalsAB)),PsiA_AB_BS.T)
JBB=np.dot(np.dot(PsiB_AB_BS,np.diagflat(EvalsAB)),PsiB_AB_BS.T)
S = np.dot(PsiB_AB_BS,PsiA_AB_BS.T)
# Symmetric Lowdin transformation for required J
J_eff_HOMO = (JAB[nhomoA,nhomoB]- 0.5*(JAA[nhomoA,nhomoA]+JBB[nhomoB,nhomoB])*S[nhomoA,nhomoB])/(1.0-S[nhomoA,nhomoB]*S[nhomoA,nhomoB])
J_eff_LUMO = (JAB[nlumoA,nlumoB]- 0.5*(JAA[nlumoA,nlumoA]+JBB[nlumoB,nlumoB])*S[nlumoA,nlumoB])/(1.0-S[nlumoA,nlumoB]*S[nlumoA,nlumoB])
# Print the H**O-H**O and LUMO-LUMO coupling
print "H**O-H**O coupling: ", J_eff_HOMO
print "LUMO-LUMO coupling: ", J_eff_LUMO
def parse(file_name, local_directory, output_file_name):
result = OrderedDict()
identifiers = OrderedDict()
calculation = OrderedDict()
molecule = OrderedDict()
calculated_properties = OrderedDict()
execution_environment = OrderedDict()
molecule_structural_formats = OrderedDict()
files_dict = OrderedDict()
# extracting fields from open-babel
mol = pybel.readfile('g98', file_name).next()
identifiers['InChI'] = mol.write('inchi').strip()
identifiers['InChIKey'] = mol.write('inchikey').strip()
identifiers['SMILES'] = mol.write('smiles').split('\t')[0]
identifiers['CanonicalSMILES'] = mol.write('can').split('\t')[0]
molecule_structural_formats['PDB'] = mol.write('pdb').split('\t')[0]
molecule_structural_formats['SDF'] = mol.write('sdf').split('\t')[0]
# extracting fields from ccdbt
parser_pyramid = ParserPyramid()
meta_f = metafile(file_name)
if meta_f.parse(parser_pyramid):
if 'CodeVersion' in meta_f.record:
calculation['Package'] = meta_f.record['CodeVersion']
if 'CalcType' in meta_f.record:
calculation['CalcType'] = meta_f.record['CalcType']
if 'Methods' in meta_f.record:
calculation['Methods'] = meta_f.record['Methods']
if 'Basis' in meta_f.record:
calculation['Basis'] = __extract(meta_f.record['Basis'])
if 'Keywords' in meta_f.record:
calculation['Keywords'] = meta_f.record['Keywords']
if 'JobStatus' in meta_f.record:
calculation['JobStatus'] = __extract(meta_f.record['JobStatus'])
if 'Formula' in meta_f.record:
molecule['Formula'] = meta_f.record['Formula']
if 'OrbSym' in meta_f.record:
molecule['OrbSym'] = meta_f.record['OrbSym']
if 'Multiplicity' in meta_f.record:
molecule['Multiplicity'] = meta_f.record['Multiplicity']
if 'Charge' in meta_f.record:
molecule['Charge'] = meta_f.record['Charge']
if 'ElecSym' in meta_f.record:
molecule['ElecSym'] = meta_f.record['ElecSym']
if 'Energy' in meta_f.record:
calculated_properties['Energy'] = meta_f.record['Energy']
if 'Dipole' in meta_f.record:
calculated_properties['Dipole'] = meta_f.record['Dipole']
if 'HF' in meta_f.record:
calculated_properties['HF'] = meta_f.record['HF']
# Calling the jar to get distribution values
process = Popen(
['java', '-jar', './gaussian-helper.jar', '--arg=' + file_name],
stdout=PIPE,
stderr=STDOUT)
for line in process.stdout:
value = line.split(':')
if value[0] == 'Iterations':
calculated_properties['Iterations'] = value[1]
elif value[0] == 'MaximumGradientDistribution':
calculated_properties['MaximumGradientDistribution'] = value[1]
elif value[0] == 'RMSGradientDistribution':
calculated_properties['RMSGradientDistribution'] = value[1]
elif value[0] == 'EnergyDistribution':
calculated_properties['EnergyDistribution'] = value[1]
if 'CalcMachine' in meta_f.record:
tmp = str(meta_f.record['CalcMachine'])
if ';' in tmp:
line = tmp.split(';')[0]
bits = line.split('-')
if len(bits) == 4:
execution_environment['CalcMachine'] = bits[1]
else:
execution_environment['CalcMachine'] = line
else:
bits = tmp.split('-')
if len(bits) == 4:
execution_environment['CalcMachine'] = bits[1]
else:
execution_environment['CalcMachine'] = tmp
if 'FinTime' in meta_f.record:
execution_environment['FinTime'] = __extract(
meta_f.record['FinTime'])
fin_date = datetime.strptime(execution_environment['FinTime'],
'%d %b %y')
execution_environment['FinTimeStamp'] = datetime.utcfromtimestamp(
calendar.timegm(fin_date.timetuple()))
if 'CalcBy' in meta_f.record:
execution_environment['CalcBy'] = __extract(
meta_f.record['CalcBy'])
for f in listdir(WORKING_DIR):
if isfile(join(WORKING_DIR, f)): # Check this in docker container
if f.endswith('.out') or f.endswith('.log'):
files_dict['GaussianOutputFile'] = join(
local_directory,
f) # If exists include the absolute path
elif f.endswith('.com') or f.endswith('.in'):
files_dict['GaussianInputFile'] = join(local_directory, f)
elif f.endswith('.chk'):
files_dict['GaussianCheckpointFile'] = join(
local_directory, f)
elif f.endswith('.fchk'):
files_dict['GaussianFCheckpointFile'] = join(
local_directory, f)
with open(join(WORKING_DIR, 'structure.sdf'), 'w') as output:
output.write(str(molecule_structural_formats['SDF']))
files_dict['SDFStructureFile'] = join(
local_directory,
'structure.sdf') # Local directory path as the key
with open(join(WORKING_DIR, 'structure.pdb'), 'w') as output:
output.write(str(molecule_structural_formats['PDB']))
files_dict['PDBStructureFile'] = join(local_directory, 'structure.pdb')
with open(join(WORKING_DIR, 'inchi.txt'), 'w') as output:
output.write(str(identifiers['InChI']))
files_dict['InChIFile'] = join(local_directory, 'inchi.txt')
with open(join(WORKING_DIR, 'smiles.txt'), 'w') as output:
output.write(str(identifiers['SMILES']))
files_dict['SMILESFile'] = join(local_directory, 'smiles.txt')
# Open Gaussian output file
# Extracting some fields which cannot be extracted from existing parsers
# * Stoichiometry
# * Job cpu time
# * %mem
# * %nprocshare
with open(file_name) as f:
content = f.readlines()
if content is not None and len(content) > 0:
for line in content:
if line.lower().startswith(' stoichiometry'):
formula = line.replace('Stoichiometry', '').strip()
molecule['Formula'] = formula
elif ' job cpu time' in line.lower():
time = line.split(':')[1].strip()
time.replace('days', '')
time.replace('hours', '')
time.replace('minutes', '')
time.replace('seconds', '')
time.replace(' +', '')
time_arr = time.split(' ')
time_in_seconds = 0.0
time_in_seconds += float(time_arr[0]) * 86400
time_in_seconds += float(time_arr[1]) * 3600
time_in_seconds += float(time_arr[2]) * 60
time_in_seconds += float(time_arr[3])
execution_environment['JobCPURunTime'] = time_in_seconds
elif line.lower().startswith(' %mem'):
memory = line.split('=')[1].strip().lower()
# default memory is 256 MB
memory_int = 256
if memory.endswith('gw'):
memory_int = int(memory[:-2]) * 1000 * 8
elif memory.endswith('gb'):
memory_int = int(memory[:-2]) * 1000
elif memory.endswith('mw'):
memory_int = int(memory[:-2]) * 8
elif memory.endswith('mb'):
memory_int = int(memory[:-2])
execution_environment['Memory'] = memory_int
elif line.lower().startswith(' %nproc'):
nproc = line.split('=')[1].strip()
execution_environment['NProcShared'] = nproc
# Rest of the key value pairs are not updated by the seagrid-data
if 'ParsedBy' in meta_f.record:
result['ParsedBy'] = meta_f.record['ParsedBy']
if 'NumBasis' in meta_f.record:
result['NumBasis'] = meta_f.record['NumBasis']
if 'NumFC' in meta_f.record:
result['NumFC'] = meta_f.record['NumFC']
if 'NumVirt' in meta_f.record:
result['NumVirt'] = meta_f.record['NumVirt']
if 'InitGeom' in meta_f.record:
result['InitGeom'] = meta_f.record['InitGeom']
if 'FinalGeom' in meta_f.record:
result['FinalGeom'] = meta_f.record['FinalGeom']
if 'PG' in meta_f.record:
result['PG'] = meta_f.record['PG']
if 'NImag' in meta_f.record:
result['NImag'] = meta_f.record['NImag']
if 'EnergyKcal' in meta_f.record:
result['EnergyKcal'] = meta_f.record['EnergyKcal']
if 'ZPE' in meta_f.record:
result['ZPE'] = meta_f.record['ZPE']
if 'ZPEKcal' in meta_f.record:
result['ZPEKcal'] = meta_f.record['ZPEKcal']
if 'HFKcal' in meta_f.record:
result['HFKcal'] = meta_f.record['HFKcal']
if 'Thermal' in meta_f.record:
result['Thermal'] = meta_f.record['Thermal']
if 'ThermalKcal' in meta_f.record:
result['ThermalKcal'] = meta_f.record['ThermalKcal']
if 'Enthalpy' in meta_f.record:
result['Enthalpy'] = meta_f.record['Enthalpy']
if 'EnthalpyKcal' in meta_f.record:
result['EnthalpyKcal'] = meta_f.record['EnthalpyKcal']
if 'Entropy' in meta_f.record:
result['Entropy'] = meta_f.record['Entropy']
if 'EntropyKcal' in meta_f.record:
result['EntropyKcal'] = meta_f.record['EntropyKcal']
if 'Gibbs' in meta_f.record:
result['Gibbs'] = meta_f.record['Gibbs']
if 'GibbsKcal' in meta_f.record:
result['GibbsKcal'] = meta_f.record['GibbsKcal']
if 'Freq' in meta_f.record:
result['Freq'] = meta_f.record['Freq']
if 'AtomWeigh' in meta_f.record:
result['AtomWeigh'] = meta_f.record['AtomWeigh']
if 'Conditions' in meta_f.record:
result['Conditions'] = meta_f.record['Conditions']
if 'ReacGeom' in meta_f.record:
result['ReacGeom'] = meta_f.record['ReacGeom']
if 'ProdGeom' in meta_f.record:
result['ProdGeom'] = meta_f.record['ProdGeom']
if 'MulCharge' in meta_f.record:
result['MulCharge'] = meta_f.record['MulCharge']
if 'NatCharge' in meta_f.record:
result['NatCharge'] = meta_f.record['NatCharge']
if 'S2' in meta_f.record:
result['S2'] = meta_f.record['S2']
if 'MemCost' in meta_f.record:
result['MemCost'] = meta_f.record['MemCost']
if 'TimeCost' in meta_f.record:
result['TimeCost'] = meta_f.record['TimeCost']
if 'CPUTime' in meta_f.record:
result['CPUTime'] = meta_f.record['CPUTime']
if 'Convergence' in meta_f.record:
result['Convergenece'] = meta_f.record['Convergence']
if 'FullPath' in meta_f.record:
result['FullPath'] = meta_f.record['FullPath']
if 'InputButGeom' in meta_f.record:
result['InputButGeom'] = meta_f.record['InputButGeom']
if 'Otherinfo' in meta_f.record:
result['Otherinfo'] = meta_f.record['Otherinfo']
if 'Comments' in meta_f.record:
result['Comments'] = meta_f.record['Comments']
# extracting fields from cclib
my_file = ccopen(file_name)
try:
data = my_file.parse()
data.listify()
if hasattr(data, 'natom'):
molecule['NAtom'] = data.natom
if hasattr(data, 'homos'):
calculated_properties['Homos'] = data.homos
if hasattr(data, 'scfenergies'): # Not updated by the seagrid-data
result['ScfEnergies'] = data.scfenergies
if hasattr(data, 'coreelectrons'): # Not updated by the seagrid-data
result['CoreElectrons'] = data.coreelectrons
if hasattr(data, 'moenergies'):
calculation['MoEnergies'] = data.moenergies
if hasattr(data, 'atomcoords'): # Not updated by the seagrid-data
result['AtomCoords'] = data.atomcoords
if hasattr(data, 'scftargets'): # Not updated by the seagrid-data
result['ScfTargets'] = data.scftargets
if hasattr(data, 'nmo'):
calculation['Nmo'] = data.nmo
if hasattr(data, 'nbasis'):
calculation['NBasis'] = data.nbasis
if hasattr(data, 'atomnos'): # Not updated by the seagrid-data
result['AtomNos'] = data.atomnos
except:
sys.stderr.write('cclib parsing failed!')
# Drawing the molecule
# mol.draw(show=False, filename=molecule_image_file)
result['Identifiers'] = identifiers
result['Calculation'] = calculation
result['Molecule'] = molecule
result['CalculatedProperties'] = calculated_properties
result['ExecutionEnvironment'] = execution_environment
result['FinalMoleculeStructuralFormats'] = molecule_structural_formats
result['Files'] = files_dict
result = json.dumps(result,
separators=(',', ':'),
sort_keys=False,
indent=4)
output_file = open(output_file_name, 'w')
for row in result:
output_file.write(row)
output_file.close()
density.data = density.data*2. # doubly-occupied
return density
if __name__=="__main__":
try:
import psyco
psyco.full()
except ImportError:
pass
from cclib.parser import ccopen
import logging
a = ccopen("../../../data/Gaussian/basicGaussian03/dvb_sp_basis.log")
a.logger.setLevel(logging.ERROR)
c = a.parse()
b = ccopen("../../../data/Gaussian/basicGaussian03/dvb_sp.out")
b.logger.setLevel(logging.ERROR)
d = b.parse()
vol = Volume( (-3.0,-6,-2.0), (3.0, 6, 2.0), spacing=(0.25,0.25,0.25) )
wavefn = wavefunction(d.atomcoords[0], d.mocoeffs[0][d.homos[0]],
c.gbasis, vol)
assert abs(wavefn.integrate())<1E-6 # not necessarily true for all wavefns
assert abs(wavefn.integrate_square() - 1.00)<1E-3 # true for all wavefns
print wavefn.integrate(), wavefn.integrate_square()
vol = Volume( (-3.0,-6,-2.0), (3.0, 6, 2.0), spacing=(0.25,0.25,0.25) )
def extractdata(folder):
smiles = [
x.rstrip()
for x in open(os.path.join(folder,
os.path.basename(folder) +
".txt"), "r").readlines()
]
print smiles
archivefile = open(os.path.join(folder, "zindo.txt"), "w")
print >> archivefile, "\t".join([
"File ID", "SMILES", "H**O (eV)", "LUMO (eV)", "Trans (eV)", "Osc",
"..."
])
#getnum = lambda x: int(x.split("/")[1].split(".")[0])
getnum = lambda x: int(x.split("/")[7].split(".")[0])
homos = []
lumos = []
trans = []
convert = 1.0 / utils.convertor(1, "eV", "cm-1")
#for filename in sorted(glob.glob("*.gz"), key=getnum):
for filename in sorted(glob.glob(os.path.join(folder, "*.gz")),
key=getnum):
number = getnum(filename)
smile = smiles[number]
text = gzip.open(filename, "r").read()
if text.find("Excitation energies and oscillator strength") < 0:
continue
lines = iter(text.split("\n"))
for line in lines:
if line.startswith(" Initial command"): break
text = StringIO.StringIO("\n".join(list(lines)))
logfile = ccopen(text)
#logfile.logger.setLevel(logging.ERROR)
data = logfile.parse()
assert (len(data.homos) == 1)
smiles.append(smile)
h**o = data.homos[0]
homos.append(data.moenergies[0][h**o])
lumos.append(data.moenergies[0][h**o + 1])
trans.append(zip(data.etenergies, data.etoscs))
archivefile.write("%d\t%s\t%f\t%f" %
(number, smile, homos[-1], lumos[-1]))
for x in trans[-1]:
archivefile.write("\t%f\t%f" % (x[0] * convert, x[1]))
archivefile.write("\n")
## print >> open("tmp.txt", "w"), text.getvalue()
if smile != "c(s1)c(SN=N2)c2c1c(s1)c(SN=N2)c2c1c(s1)c(SN=N2)c2c1c(s1)c(SN=N2)c2c1c(s1)c(SN=N2)c2c1c(s1)c(SN=N2)c2c1":
mol = pybel.readstring('g09', text.getvalue())
mol.write("xyz",
os.path.join(folder, "%d.xyz" % number),
overwrite=True)
print "%s: Created zindo.txt, plus various xyz files." % folder
def stretch(outputfile, shift=2.0, templatefiles=None):
"""
Generate transition state search for given xyzfile,
assuming that the first 2 atoms are the bond forming atoms
outputfile is assumed to be a geometry optimization Q-Chem output
TODO: option to set fname, and default to the templatefilename + index?
"""
savexyz = True
# If templatefiles doesn't exist, we only save stretched xyz
if templatefiles:
# Always convert templatefiles into list
if not type(templatefiles) is list:
templatefiles = [templatefiles]
# Only keep the templatefiles that exists
templatefiles = [
templatefile for templatefile in templatefiles
if templates.exists(templatefile)
]
# If at least one templatefile exists, we don't save xyz
if templatefiles:
savexyz = False
ccdata = ccopen(outputfile).parse()
fname, _ = os.path.splitext(outputfile)
#xyzfile = fname+'.xyz'
#write.xyzfile(outputccdata, xyzfile)
product = ccData_xyz(ccdata.getattributes())
ccdatas = []
#product = parse.xyzfile(xyzfile, ccxyz=True)
product.build_zmatrix()
reactant = copy.deepcopy(product)
reactant.distances[1] += shift
# TODO:If reactants provided, use their geometry internal coords
# and modify internalcoords of reactant
# FIXME hardcoded paths instead of cli args
#rpaths = ['../../initiators/MeO/0.omegab97x-d_opt.out', '../../ketenes/TMS/0.omegab97x-d_opt.out']
#reactants = []
#for rpath in rpaths:
# reactants.append(parse.xyzfile(rpath, ccdata_xyz=True))
#for r in reactants:
# r.build_zmatrix()
# TODO Determine which reactant is which
# Some ways to do this:
# numatom, atomnos
# TODO How to deal with symmetrical reactants?
# Just guess (1/2 chance) - possibly cli to swap if wrong
product.build_xyz()
reactant.build_xyz()
ccdatas.append(reactant)
ccdatas.append(product)
if not savexyz:
for i in range(len(templatefiles)):
if len(templatefiles) == 1:
idx = ''
else:
idx = '-' + str(i)
if 'opt' in fname:
fname = fname.replace('opt', 'fsm')
else:
fname = fname + '_fsm'
write.inputfile(ccdatas, templatefiles[i], fname + idx + '.qcm')
else:
reactant.print_xyz()
def CountPJ():
# Read in molecule log files for counterpoise method. Requires IOp(6/7=3) in Gaussian header + ghost atoms to make up basis sets in individual com files
MOLA_CP = sys.argv[1]
MOLB_CP = sys.argv[2]
MOLAB_CP = sys.argv[3]
# Open the log files
molA_parser = ccopen("%s" % (MOLA_CP))
molB_parser = ccopen("%s" % (MOLB_CP))
molAB_parser = ccopen("%s" % (MOLAB_CP))
# Parse the relevant data
molA = molA_parser.parse()
molB = molB_parser.parse()
molAB = molAB_parser.parse()
print("Parsed...")
# Size of basis sets
Nbasis = molAB.nbasis
# H**O index
nhomoA = molA.homos
nhomoB = molB.homos
nhomoAB = molAB.homos
nlumoA = nhomoA + 1
nlumoB = nhomoB + 1
print "H**O A: ", nhomoA
print "H**O B: ", nhomoB
print "H**O AB: ", nhomoAB
# Every basis set should have the same size (the size of the pair)
if molA.nbasis != molB.nbasis:
print("Count of basis functions doesn't match. Failing.")
return False
# Get molecular orbitals
MOsA = molA.mocoeffs[0]
MOsB = molB.mocoeffs[0]
MOsAB = molAB.mocoeffs[0]
# Get eigenvalues of pair
EvalsAB = molAB.moenergies[0]
print "Energies: ", EvalsAB
print "Gap: ", EvalsAB[nhomoAB + 1] - EvalsAB[nhomoAB]
# Find H**O and LUMO from energy splitting in dimer
print "ESID H**O-H**O coupling", 0.5 * (EvalsAB[nhomoAB] -
EvalsAB[nhomoAB - 1])
print "ESID LUMO-LUMO coupling", 0.5 * (EvalsAB[nhomoAB + 2] -
EvalsAB[nhomoAB + 1])
# Calculate the molecular orbitals of A and B in the AB basis set
SAB = molAB.aooverlaps
MolAB_Pro = (np.dot(MOsAB, SAB)).T
PsiA_AB_BS = np.dot(MOsA, MolAB_Pro)
PsiB_AB_BS = np.dot(MOsB, MolAB_Pro)
# Calculate the matrix of transfer integrals
JAB = np.dot(np.dot(PsiB_AB_BS, np.diagflat(EvalsAB)), PsiA_AB_BS.T)
JAA = np.dot(np.dot(PsiA_AB_BS, np.diagflat(EvalsAB)), PsiA_AB_BS.T)
JBB = np.dot(np.dot(PsiB_AB_BS, np.diagflat(EvalsAB)), PsiB_AB_BS.T)
S = np.dot(PsiB_AB_BS, PsiA_AB_BS.T)
# Symmetric Lowdin transformation for required J
J_eff_HOMO = (JAB[nhomoA, nhomoB] - 0.5 *
(JAA[nhomoA, nhomoA] + JBB[nhomoB, nhomoB]) *
S[nhomoA, nhomoB]) / (1.0 -
S[nhomoA, nhomoB] * S[nhomoA, nhomoB])
J_eff_LUMO = (JAB[nlumoA, nlumoB] - 0.5 *
(JAA[nlumoA, nlumoA] + JBB[nlumoB, nlumoB]) *
S[nlumoA, nlumoB]) / (1.0 -
S[nlumoA, nlumoB] * S[nlumoA, nlumoB])
# Print the H**O-H**O and LUMO-LUMO coupling
print "H**O-H**O coupling: ", J_eff_HOMO
print "LUMO-LUMO coupling: ", J_eff_LUMO
files = ['A1-Opt_6-31G(d)_B3LYP_Singlet_RHF.log', 'A1-Opt_6-31G(d)_B3LYP_Singlet_UHF.log', 'A1-Opt_6-31G(d)_B3LYP_Triplet.log'] #to hold the data energies = [] symmetries = [] occupied = [] #the number of MOs to be output. is the min no of MOs in the input files nMOs = 1000 #read and extract for f in files: print "Reading file: %s" % f qmRaw = ccopen(os.path.join(path, f)) qmRaw.logger.setLevel(logging.ERROR) #reduce logging info qmParsed = qmRaw.parse() energies.append(qmParsed.moenergies[0]) symmetries.append(qmParsed.mosyms[0]) occupied.append(range(qmParsed.nmo)<=qmParsed.homos[0]) if (qmParsed.nmo<nMOs): nMOs=qmParsed.nmo print "Will export %i MO energies" % nMOs #write out as groups of columns as CSV print "Writing out MO data to %s" % outFile output = open(os.path.join(path,outFile), "w") #group titles for f in files:
def main(which=[], traceback=False, status=False):
dummyfiles = [eval(n)("") for n in testall.parsers]
# It would be nice to fix the structure of this nested list,
# because in its current form it is not amenable to tweaks.
regdir = os.path.join("..", "data", "regression")
programs = [os.path.join(regdir,testall.get_program_dir(p)) for p in testall.parsers]
try:
filenames = [[os.path.join(p,version,fn) for version in os.listdir(p) for fn in os.listdir(os.path.join(p,version))] for p in programs]
except OSError as e:
print(e)
print("\nERROR: At least one program direcory is missing.")
print("Run regression_download.sh in the ../data directory to update.")
sys.exit(1)
# This file should contain the paths to all regresssion test files we have gathered
# over the years. It is not really necessary, since we can discover them on the disk,
# but we keep it as a legacy and a way to track double check the regression tests.
regfile = open(os.path.join("..", "data", "regressionfiles.txt"), "r")
regfilenames = [os.sep.join(x.strip().split("/")) for x in regfile.readlines()]
regfile.close()
# We will want to print a warning if you haven't downloaded all of the regression
# test files, or when, vice versa, not all of the regression test files found on disk
# are included in filenames. However, gather that data here and print the warnings
# at the end so that we test all available files and the messages are displayed
# prominently at the end.
missing_on_disk = []
missing_in_list = []
for fn in regfilenames:
if not os.path.isfile(os.path.join("..", "data", "regression", fn)):
missing_on_disk.append(fn)
for fn in glob.glob(os.path.join('..', 'data', 'regression', '*', '*', '*')):
if os.path.join(*fn.split(os.path.sep)[3:]) not in regfilenames:
missing_in_list.append(fn)
# Create the regression test functions from logfiles that were old unittests.
for path, test_class in old_unittests.items():
funcname = "test" + normalisefilename(path)
func = make_regression_from_old_unittest(test_class)
globals()[funcname] = func
# Gather orphaned tests - functions starting with 'test' and not corresponding
# to any regression file name.
orphaned_tests = []
for ip, parser in enumerate(testall.parsers):
prefix = "test%s" % parser
tests = [fn for fn in globals() if fn[:len(prefix)] == prefix]
normalize = lambda fn: normalisefilename("_".join(fn.split(os.sep)[3:]))
normalized = [normalize(fname) for fname in filenames[ip]]
orphaned = [t for t in tests if t[4:] not in normalized]
orphaned_tests.extend(orphaned)
failures = errors = total = 0
for iname, name in enumerate(testall.parsers):
# Continue to next iteration if we are limiting the regression and the current
# name was not explicitely chosen (that is, passed as an argument).
if len(which) > 0 and not name in which:
continue;
print("Are the %s files ccopened and parsed correctly?" % name)
current_filenames = filenames[iname]
current_filenames.sort()
for fname in current_filenames:
total += 1
print(" %s..." % fname, end=" ")
# Check if there is a test (needs to be an appropriately named function).
# If not, there can also be a test that does not assume the file is
# correctly parsed (for fragments, for example), and these test need
# to be additionaly prepended with 'testnoparse'.
test_this = test_noparse = False
fname_norm = normalisefilename("_".join(fname.split(os.sep)[3:]))
funcname = "test" + fname_norm
test_this = funcname in globals()
funcname_noparse = "testnoparse" + fname_norm
test_noparse = not test_this and funcname_noparse in globals()
if not test_noparse:
try:
logfile = ccopen(fname)
except:
errors += 1
print("ccopen error")
else:
if type(logfile) == type(dummyfiles[iname]):
try:
logfile.logger.setLevel(logging.ERROR)
logfile.data = logfile.parse()
except KeyboardInterrupt:
sys.exit(1)
except:
print("parse error")
errors += 1
else:
if test_this:
try:
res = eval(funcname)(logfile)
if res and len(res.failures) > 0:
failures += len(res.failures)
print("%i test(s) failed" % len(res.failures))
if traceback:
for f in res.failures:
print("Failure for", f[0])
print(f[1])
continue
except AssertionError:
print("test failed")
failures += 1
else:
print("parsed and tested")
else:
print("parsed")
else:
print("ccopen failed")
failures += 1
else:
try:
eval(funcname_noparse)(fname)
except AssertionError:
print("test failed")
failures += 1
except:
print("parse error")
errors += 1
else:
print("test passed")
print()
print("Total: %d Failed: %d Errors: %d" % (total, failures, errors))
if not traceback and failures + errors > 0:
print("\nFor more information on failures/errors, add 'traceback' as an argument.")
# Show these warnings at the end, so that they're easy to notice. Notice that the lists
# were populated at the beginning of this function.
if len(missing_on_disk) > 0:
print("\nWARNING: You are missing %d regression file(s)." % len(missing_on_disk))
print("Run regression_download.sh in the ../data directory to update.")
print("Missing files:")
print("\n".join(missing_on_disk))
if len(missing_in_list) > 0:
print("\nWARNING: The list in 'regressionfiles.txt' is missing %d file(s)." % len(missing_in_list))
print("Add these files paths to the list and commit the change.")
print("Missing files:")
print("\n".join(missing_in_list))
if len(orphaned_tests) > 0:
print("\nWARNING: There are %d orphaned regression test functions." % len(orphaned_tests))
print("Please make sure these function names correspond to regression files:")
print("\n".join(orphaned_tests))
if status and errors > 0:
os.exit(1)
def ProJ():
# Read in molecule log files for projective method. Requires iop(3/33=1,6/7=3) in Gaussian header for calculation on each molecule + the pair
MOLA_proj=sys.argv[1]
MOLB_proj=sys.argv[2]
MOLAB_proj=sys.argv[3]
Degeneracy_HOMO=int(sys.argv[4])
Degeneracy_LUMO=int(sys.argv[5]) # =0 for non-degenerate, 2,3 etc for doubly, triply etc
# Open the log files
molA_parser=ccopen("%s"%(MOLA_proj))
molB_parser=ccopen("%s"%(MOLB_proj))
molAB_parser=ccopen("%s"%(MOLAB_proj))
# Parse the relevant data
molA=molA_parser.parse()
molB=molB_parser.parse()
molAB=molAB_parser.parse()
#print ("Parsed...")
# Size of basis sets
nbasisA=molA.nbasis
nbasisB=molB.nbasis
#print "nbasisA: ", nbasisA
#print "nbasisB: ", nbasisB
Nbasis=nbasisA+nbasisB
# Position of H**O
nhomoA=molA.homos
nhomoB=molB.homos
#print "nhomoA: ", nhomoA
#print "nhomoB: ", nhomoB
# Get molecular orbitals. Need the transpose for our purposes.
MOsA=(molA.mocoeffs[0]).T
MOsB=(molB.mocoeffs[0]).T
MOsAB=(molAB.mocoeffs[0]).T
# Get eigenvalues of pair
EvalsAB=molAB.moenergies[0]
# Get overlaps. These are symmetric so transpose not required in this case
SA=molA.aooverlaps
SB=molB.aooverlaps
SAB=molAB.aooverlaps
# Set up matrices for MOs and S
MOs=np.zeros((Nbasis,Nbasis))
S=np.zeros((Nbasis,Nbasis))
MOs[0:nbasisA,0:nbasisA]=MOsA
MOs[nbasisA:Nbasis,nbasisA:Nbasis]=MOsB
S[0:nbasisA,0:nbasisA]=SA
S[nbasisA:Nbasis,nbasisA:Nbasis]=SB
# Calculate upper diagonal matrix D, such that S=D.T*D for Lowdin orthogonalisation.
D=sp.linalg.cholesky(S)
Dpair=sp.linalg.cholesky(SAB)
# Orthogonalise MOs matrix and MOsAB matrix
MOsorth=np.dot(D,MOs)
#print np.shape(MOsorth)
MOspairorth=np.dot(Dpair,MOsAB)
#print np.shape(MOspairorth)
# Calculate the Fock matrix
B=np.dot(MOsorth.T,MOspairorth)
Evals=np.diagflat(EvalsAB)
F=np.dot(np.dot(B,Evals),B.T)
# Output the H**O-H**O and LUMO-LUMO coupling elements fromt the Fock matrix
if Degeneracy_HOMO==0:
print "H**O-H**O coupling: ", F[nhomoB+nbasisA,nhomoA]
if Degeneracy_LUMO==0:
print "LUMO-LUMO coupling: ", F[nhomoB+nbasisA+1,nhomoA+1]
# Degeneracies
if Degeneracy_HOMO!=0:
F_deg_HOMO=F[nhomoB+nbasisA-Degeneracy_HOMO+1:nhomoB+nbasisA+1,nhomoA-Degeneracy_HOMO:nhomoA]
print "H**O-H**O coupling", (np.sum(np.absolute(F_deg_HOMO**2)))/Degeneracy_HOMO**2
if Degeneracy_LUMO!=0:
F_deg_LUMO=F[nhomoB+nbasisA:nhomoB+nbasisA+Degeneracy_LUMO,nhomoA:nhomoA+Degeneracy_LUMO]
print "LUMO-LUMO coupling", (np.sum(np.absolute(F_deg_LUMO**2)))/Degeneracy_LUMO**2
density.data = density.data*2. # doubly-occupied
return density
if __name__=="__main__":
try:
import psyco
psyco.full()
except ImportError:
pass
from cclib.parser import ccopen
import logging
a = ccopen("../../../data/Gaussian/basicGaussian03/dvb_sp_basis.log")
a.logger.setLevel(logging.ERROR)
c = a.parse()
b = ccopen("../../../data/Gaussian/basicGaussian03/dvb_sp.out")
b.logger.setLevel(logging.ERROR)
d = b.parse()
vol = Volume( (-3.0,-6,-2.0), (3.0, 6, 2.0), spacing=(0.25,0.25,0.25) )
wavefn = wavefunction(d.atomcoords[0], d.mocoeffs[0][d.homos[0]],
c.gbasis, vol)
assert abs(wavefn.integrate())<1E-6 # not necessarily true for all wavefns
assert abs(wavefn.integrate_square() - 1.00)<1E-3 # true for all wavefns
print wavefn.integrate(), wavefn.integrate_square()
vol = Volume( (-3.0,-6,-2.0), (3.0, 6, 2.0), spacing=(0.25,0.25,0.25) )
def main(which=[], traceback=False):
# Print a warning if you haven't downloaded all of the regression test files,
# or an error if not all of the regression test files are included in filenames.
regfile = open(os.path.join("..", "data", "regressionfiles.txt"), "r")
regfilenames = [os.sep.join(x.strip().split("/")) for x in regfile.readlines()]
regfile.close()
missing = 0
for x in regfilenames:
if not os.path.isfile(os.path.join("..", "data", x)):
missing += 1
elif os.path.join("..", "data", x) not in flatten(filenames):
print("\nERROR: The regression file %s is present, but not included in " \
"the 'filenames' variable.\n\nPlease add a new glob statement." % x)
sys.exit(1)
if missing > 0:
print("\nWARNING: You are missing %d regression file(s).\n" \
" Run wget.sh in the ../data directory to update.\n" % missing)
try:
input("(Press ENTER to continue or CTRL+C to exit)")
except KeyboardInterrupt:
print("\n")
sys.exit(0)
# When a unit test is removed or replaced by a newer version, the old logfile
# typically becomes a regression, and normally we still want to run the unit test
# within the regression suite. To this end, add the logfile location to a list
# called 'old_tests' in the appropriate unit test class, in which case the
# following code will find it and create the becessary regression test function.
for mod in test_modules:
mod_name = "test" + mod
tests = inspect.getmembers(__import__(mod_name), inspect.isclass)
tests = [tc for tc in tests if tc[0][-4:] == "Test"]
for test_name, test_class in tests:
for old in getattr(test_class, "old_tests", []):
funcname = "test" + normalisefilename(old)
func = make_regression_from_old_unittest(old, mod_name, test_name)
globals()[funcname] = func
failures = errors = total = 0
for iname, name in enumerate(parsers):
# Continue to next iteration if we are limiting the regression and the current
# name was not explicitely chosen (that is, passed as an argument).
if len(which) > 0 and not name in which:
continue;
print("Are the %s files ccopened and parsed correctly?" % name)
current_filenames = filenames[iname]
current_filenames.sort()
for fname in current_filenames:
total += 1
print(" %s..." % fname, end=" ")
# Check if there is a test (needs to be an appropriately named function).
# If not, there can also be a test that does not assume the file is
# correctly parsed (for fragments, for example), and these test need
# to be additionaly prepended with 'testnoparse'.
test_this = test_noparse = False
fname_norm = normalisefilename("_".join(fname.split(os.sep)[2:]))
funcname = "test" + fname_norm
test_this = funcname in globals()
funcname_noparse = "testnoparse" + fname_norm
test_noparse = not test_this and funcname_noparse in globals()
if not test_noparse:
try:
logfile = ccopen(fname)
except:
errors += 1
print("ccopen error")
else:
if type(logfile) == type(dummyfiles[iname]):
try:
logfile.logger.setLevel(logging.ERROR)
logfile.data = logfile.parse()
except KeyboardInterrupt:
sys.exit(1)
except:
print("parse error")
errors += 1
else:
if test_this:
try:
res = eval(funcname)(logfile)
if res and len(res.failures) > 0:
failures += len(res.failures)
print("%i test(s) failed" % len(res.failures))
if traceback:
for f in res.failures:
print("Failure for", f[0])
print(f[1])
continue
except AssertionError:
print("test failed")
failures += 1
else:
print("parsed and tested")
else:
print("parsed")
else:
print("ccopen failed")
failures += 1
else:
try:
eval(funcname_noparse)(filename)
except AssertionError:
print("test failed")
failures += 1
except:
print("parse error")
errors += 1
else:
print("test passed")
print
print("Total: %d Failed: %d Errors: %d" % (total, failures, errors))
if not traceback and failures + errors > 0:
print("\nFor more information on failures/errors, add 'traceback' as argument.")
def readGaussian(self):
global vsShifted
self.ZMatModel.dataChanged.disconnect(self.clearUpdateView)
filename = self.fileDialog.getOpenFileName(self, 'Open file', expanduser('~'), '*.log;;*.*')
if filename:
self.gaussianPlot.clear()
self.inp = []
self.populateZMatModel()
file = ccopen(filename)
data = file.parse().getattributes()
self.natom = data['natom']
self.atomnos = data['atomnos'].tolist()
self.atomsymbols = [ str(elements[e]) for e in self.atomnos ]
self.atomcoords = data['atomcoords'].tolist()
self.scfenergies = data['scfenergies'].tolist()
self.geovalues = data['geovalues'].T.tolist()
self.geotargets = data['geotargets'].tolist()
if 'vibfreqs' in data.keys():
self.vibfreqs = data['vibfreqs']
#print(self.vibfreqs)
self.vibirs = data['vibirs']
#print(self.vibirs)
#print(data.keys())
if 'vibramans' in data.keys():
self.vibramans = data['vibramans']
else:
self.vibramans = [''] * len(self.vibirs)
self.vibdisps = data['vibdisps']
#print(self.vibdisps)
self.inp = xyz2zmat(self.atomcoords[0], self.atomsymbols)
self.populateZMatModel()
titles = ['SCF Energies', 'RMS & Max Forces', 'RMS & Max Displacements']
for i in range(3):
self.gaussianPlot.addPlot(row=1, col=i+1)
plot = self.gaussianPlot.getItem(1, i+1)
plot.setTitle(title=titles[i])
if i == 0:
c = ['c']
x = [0]
y = [self.scfenergies]
else:
c = ['r', 'y']
x = [0, 0]
y = [self.geovalues[2*i-2], self.geovalues[2*i-1]]
targety = [self.geotargets[2*i-2], self.geotargets[2*i-1]]
plot.clear()
plot.maxData = plot.plot(y[0], symbol='o', symbolPen=c[0], symbolBrush=c[0], pen=c[0], symbolSize=5, pxMode=True, antialias=True, autoDownsample=False)
plot.highlight=plot.plot(x, [ yy[0] for yy in y ], symbol='o', symbolPen='w', symbolBrush=None, pen=None, symbolSize=15, pxMode=True, antialias=True, autoDownsample=False)
plot.maxData.sigPointsClicked.connect(self.gausclicked)
if i > 0:
for j in range(2):
plot.addLine(y=np.log10(targety[j]), pen=mkPen((255, 255*j, 0, int(255/2)), width=1))
plot.RMSData=plot.plot(y[1], symbol='o', symbolPen=c[1], symbolBrush=c[1], pen=c[1], symbolSize=5, pxMode=True, antialias=True, autoDownsample=False)
plot.RMSData.sigPointsClicked.connect(self.gausclicked)
plot.setLogMode(y=True)
self.showGauss()
self.updateView()
self.statusBar.clearMessage()
self.statusBar.showMessage('Read molecule from '+filename+'.', 5000)
self.ZMatModel.dataChanged.connect(self.clearUpdateView)
if self.natom:
self.showGaussAction.setEnabled(True)
if 'vibfreqs' in data.keys():
self.showFreqAction.setEnabled(True)
# populate the FreqModel
self.populateFreqModel()
self.freqPlot.clear()
irPlot = self.freqPlot.addPlot(row=1, col=1)
irPlot.clear()
minFreq = np.min(self.vibfreqs)
maxFreq = np.max(self.vibfreqs)
maxInt = np.max(self.vibirs)
x = np.sort(np.concatenate([np.linspace(minFreq-100, maxFreq+100, num=1000), self.vibfreqs]))
y = x*0
for f,i in zip(self.vibfreqs, self.vibirs):
y += lorentzv(x, f, 2*np.pi, i)
#xy = np.array([np.concatenate([x, np.array(self.vibfreqs)]), np.concatenate([y, np.array(self.vibirs)])]).T
#xysort = xy[xy[:,0].argsort()]
irPlot.maxData = irPlot.plot(x, y, antialias=True)
markers = ErrorBarItem(x=self.vibfreqs, y=self.vibirs, top=maxInt/30, bottom=None, pen='r')
irPlot.addItem(markers)
self.showFreq()
#self.vibdisps = np.append(self.vibdisps, [np.mean(self.vibdisps, axis=0)], axis=0)
maxt = 100
vsShifted = np.array([ [ vs + self.vibdisps[i]*np.sin(t*2*np.pi/maxt)/3 for t in range(maxt) ] for i in range(len(self.vibfreqs)) ])
else:
self.showFreqAction.setEnabled(False)
self.freqWidget.hide()
def stretch(outputfile, shift=2.0, templatefiles=None):
"""
Generate transition state search for given xyzfile,
assuming that the first 2 atoms are the bond forming atoms
outputfile is assumed to be a geometry optimization Q-Chem output
TODO: option to set fname, and default to the templatefilename + index?
"""
savexyz = True
# If templatefiles doesn't exist, we only save stretched xyz
if templatefiles:
# Always convert templatefiles into list
if not type(templatefiles) is list:
templatefiles = [templatefiles]
# Only keep the templatefiles that exists
templatefiles = [templatefile for templatefile in templatefiles
if templates.exists(templatefile)]
# If at least one templatefile exists, we don't save xyz
if templatefiles:
savexyz = False
ccdata = ccopen(outputfile).parse()
fname, _ = os.path.splitext(outputfile)
#xyzfile = fname+'.xyz'
#write.xyzfile(outputccdata, xyzfile)
product = ccData_xyz(ccdata.getattributes())
ccdatas = []
#product = parse.xyzfile(xyzfile, ccxyz=True)
product.build_zmatrix()
reactant = copy.deepcopy(product)
reactant.distances[1] += shift
# TODO:If reactants provided, use their geometry internal coords
# and modify internalcoords of reactant
# FIXME hardcoded paths instead of cli args
#rpaths = ['../../initiators/MeO/0.omegab97x-d_opt.out', '../../ketenes/TMS/0.omegab97x-d_opt.out']
#reactants = []
#for rpath in rpaths:
# reactants.append(parse.xyzfile(rpath, ccdata_xyz=True))
#for r in reactants:
# r.build_zmatrix()
# TODO Determine which reactant is which
# Some ways to do this:
# numatom, atomnos
# TODO How to deal with symmetrical reactants?
# Just guess (1/2 chance) - possibly cli to swap if wrong
product.build_xyz()
reactant.build_xyz()
ccdatas.append(reactant)
ccdatas.append(product)
if not savexyz:
for i in range(len(templatefiles)):
if len(templatefiles) == 1:
idx = ''
else:
idx = '-'+str(i)
if 'opt' in fname:
fname = fname.replace('opt', 'fsm')
else:
fname = fname + '_fsm'
write.inputfile(ccdatas,
templatefiles[i],
fname+idx+'.qcm')
else:
reactant.print_xyz()
