def get_dsoft():
'''
This functions is in charge of reading the file
mesc.txt where the available softwares are listed
'''
# defined here:
if False:
dsoft = {'clhbrpot': 'mpilgrim.itf_asurf', \
'gaussian': 'mpilgrim.itf_gau' ,\
'orca' : 'mpilgrim.itf_orca' \
}
# read from file
if True:
TXTFILE = os.path.dirname(os.path.realpath(__file__)) + "/mesc.txt"
# read file
lines = read_file(TXTFILE)
lines = clean_lines(lines, "#", True)
# get info from lines
dsoft = {}
for line in lines:
if line == "\n": continue
software, module = line.split()
dsoft[software] = module
# return dictionary
return dsoft
def read_tes(filename=PN.IFILE4):
lines = read_file(filename)
dtesLL = {}
dtesHL = {}
bkeep = False
sk1 = "start_meppoint"
sk2 = "start_highlevel"
ek1 = "end_meppoint"
ek2 = "end_highlevel"
for line in lines:
# save LL data
if line.startswith(ek1):
dtesLL[software] = dtesLL.get(software,{})
dtesLL[software].update({ctc:string})
bkeep = False
# save HL data
elif line.startswith(ek2):
dtesHL[software] = dtesHL.get(software,{})
dtesHL[software].update({ctc:string})
bkeep = False
elif bkeep:
string += line
elif line.startswith(sk1) or line.startswith(sk2):
ctc, software = line.split()[1:]
string = ""
bkeep = True
else: continue
if not os.path.exists(filename) : status = -1
elif dtesLL == {} and dtesHL == {}: status = 0
else : status = 1
return (dtesLL,dtesHL), (filename,status)
def file2lines(filename):
if not os.path.exists(filename):
lines = []
status = -1
else:
lines = read_file(filename)
lines = clean_lines(lines,"#",True)
lines = [line for line in lines if line != "\n"]
if lines == []: status = 0
else : status = 1
return lines, status
def read_orcaengrad(orca_engrad):
# Initialize
natoms = None
atonums = [] ; Etot = None
x_cc = [] ; g_cc = []
# Read lines
if not os.path.exists(orca_engrad): return g_cc, (x_cc, atonums, Etot)
lines = read_file(orca_engrad)
# Read natoms, Etot, g_cc, atonums, xcc
natoms = int(lines[3])
Etot = float(lines[7])
g_cc = [float(line) for line in lines[11:11+3*natoms]]
Zxyz = [line.split() for line in lines[-natoms:]]
for Z,x,y,z in Zxyz:
x_cc = x_cc + [float(x),float(y),float(z)]
atonums = atonums + [int(Z)]
# Return data
return g_cc, (x_cc, atonums, Etot)
def read_orcahess(orca_hess):
if not os.path.exists(orca_hess): return []
# Read lines
lines = read_file(orca_hess)
# Read hessian
for idx in range(len(lines)):
line = lines[idx]
if "$hessian" in line:
nrows = int(lines[idx + 1])
idx_hessian = idx
F_cc = [[0.0] * nrows for i in range(nrows)]
fcol = int(lines[idx_hessian + 2].split()[0]) # first column
lcol = int(lines[idx_hessian + 2].split()[-1]) # last column
row = 0
for line in lines[idx_hessian + 3:]:
if row == nrows - 1:
fcol = int(line.split()[0]) # first column
lcol = int(line.split()[-1]) # last column
row = 0
continue
# Split data in line
line_data = line.split()
# Save data
row = int(line_data[0])
F_cc[row][fcol:lcol + 1] = [float(value) for value in line_data[1:]]
# Finished?
if row == nrows - 1 and lcol == nrows - 1: break
# Promediate hessian
for i in range(1, nrows, 1):
for j in range(i):
Fij = F_cc[i][j]
Fji = F_cc[j][i]
average = 0.5 * (Fij + Fji)
F_cc[i][j] = average
F_cc[j][i] = average
# Get lower triangle
F_lt = []
for i in range(nrows):
for j in range(0, i + 1):
F_lt.append(F_cc[i][j])
F_cc = F_lt
# Return data
return F_cc
def read_ispe(filename):
'''
read input file for ispe
'''
# read lines
lines = ff.read_file(filename)
lines = fncs.clean_lines(lines, strip=True)
# initialize data
ispe_xy = []
VR, VP = None, None
tension = 0.0
# find data in lines
for line in lines:
if line == "\n": continue
label, val = line.split()
val = float(val)
if label.lower() == "tension": tension = val
elif label.lower() == "reac": VR = val
elif label.lower() == "prod": VP = val
else: ispe_xy.append((label, val))
return ispe_xy, tension, VR, VP
def set_EXE():
global EXE
txt = os.path.dirname(os.path.realpath(__file__))+"/paths.txt"
# Defined in this file
if 'EXE' in globals():
return
# Try to export it from bashrc
elif "OrcaExe" in os.environ:
# in .bashrc: export OrcaExe="$MYHOME/Software/orca_4_0_1_2/orca"
EXE = os.environ["OrcaExe"]
return
# Export it from file
elif os.path.exists(txt):
lines = read_file(txt)
lines = clean_lines(lines,"#",True)
for line in lines:
if line == "\n": continue
name, path = line.split()
if name == "orca":
EXE = path
return
# Not found
else: raise Exc.ExeNotDef(Exception)
def normal_termination(ofile):
lines = read_file(ofile)
if len(lines) == 0: return False
lastline = lines[-1].lower()
if "normal termination" in lastline: return True
else : return False
def read_gauout_old(gauout):
'''
Read Gaussian output (data in final message)
and return important data
'''
# check extension
end_out = (gauout.lower()).endswith(".out")
end_log = (gauout.lower()).endswith(".log")
if (not end_out) and (not end_log):
raise Exc.FileType(Exception)
# read lines
lines = read_file(gauout)
# CHECK FILE IS GAUSSIAN OUT
correct = False
for line in lines:
if "Entering Gaussian System" in line:
correct = True
break
if not correct: raise Exc.FileType(Exception)
# ONIOM energy?
try:
E_ONIOM = None
for line in lines[::-1]:
if "ONIOM: extrapolated energy" in line:
E_ONIOM = float(line.split()[-1])
break
except: E_ONIOM = None
# Get Forces if exists
key1 = "Forces (Hartrees/Bohr)"
key2 = "Cartesian Forces:"
try:
gcc = []
for line in extract_string(lines,key1,key2).split("\n")[3:-3]:
dummy, dummy, gx, gy, gz = line.split()
gcc += [float(gx),float(gy),float(gz)]
# forces to gradient
gcc = [-g_i for g_i in gcc]
except: gcc = None
if gcc == []: gcc = None
# Read string from gaussian output
DATA_LAST = []
DATA_WFCC = []
key1, key2 = "\GINC-","@"
strings = extract_string(lines,key1,key2,accumulate=True)
for string in strings:
lines = "".join([line.strip() for line in string.split()])
lines = lines.split("\\\\")
if lines == [""]: return None, None, None, None, None, None
# lines[3]: ch, mtp, symbols, xcc
str_geom = lines[3].split("\\")
ch , mtp = str_geom[0].split(",")
xcc = []
symbols = []
ch = int(ch)
mtp = int(mtp)
E = None
masses = []
for line in str_geom[1:]:
coords = line.split(",")
if len(coords) == 4:
symbol, x, y, z = line.split(",")
else:
symbol, tmp, x, y, z = line.split(",")
xcc += [float(x),float(y),float(z)]
symbols.append(symbol)
xcc = [xi/ANGSTROM for xi in xcc] # in bohr
# lines[4]: energy
E = float(lines[4].split("HF=")[1].split("\\")[0])
# Gradient
if gcc is None or len(gcc) == 0: gcc = [0.0 for x in xcc]
# Hessian
Fcc = []
for idx in range(len(lines)):
line = lines[idx]
if "NImag" not in line: continue
Fcc = [float(fij) for fij in lines[idx+1].split(",")]
# other lists
atonums = get_atonums(symbols)
masses = atonums2masses(atonums)
calclevel = ""
# Does it have hessian?
if Fcc != []: DATA_WFCC = [xcc, atonums, ch, mtp, E, gcc, Fcc, masses, calclevel]
# Save data
DATA_LAST = [xcc, atonums, ch, mtp, E, gcc, Fcc, masses, calclevel]
# Use ONIOM extrapolated energy if found!
if E_ONIOM is not None:
if len(DATA_WFCC) != 0: DATA_WFCC[4] = E_ONIOM
if len(DATA_LAST) != 0: DATA_LAST[4] = E_ONIOM
# return
if DATA_WFCC != []: return DATA_WFCC
else : return DATA_LAST
def read_fchk(fchkfile):
#------------------------#
# The labels to look for #
#------------------------#
labels = {} ; found_dict = {}
labels[0] = "Number of atoms" ; found_dict[0] = False
labels[1] = "Charge" ; found_dict[1] = False
labels[2] = "Multiplicity" ; found_dict[2] = False
labels[3] = "Total Energy" ; found_dict[3] = False
labels[4] = "Atomic numbers" ; found_dict[4] = False
labels[5] = "Current cartesian coordinates" ; found_dict[5] = False
labels[6] = "Real atomic weights" ; found_dict[6] = False
labels[7] = "Cartesian Gradient" ; found_dict[7] = False
labels[8] = "Cartesian Force Constants" ; found_dict[8] = False
# mandatory labels in fchk
idx_basic_labels = [0,1,2,3,4,5,6]
# initialization
natoms = None ; ch = None ; mtp = None ; E = None
atonums = [] ; masses = []
xcc = [] ; gcc = [] ; Fcc = []
# read file
lines = read_file(fchkfile)
# check extension
end_fchk = (fchkfile.lower()).endswith(".fchk")
if (not end_fchk): raise Exc.FileType(Exception)
# CHECK FILE IS FCHK
correct = False
for line in lines:
if line.startswith("Current cartesian coordinates "):
correct = True
break
if not correct: raise Exc.FileType(Exception)
# Get level of calculation
calclevel = " ".join(lines[1].split()[1:])
# get data from lines
for idx in range(len(lines)):
line = lines[idx]
# Number of atoms
if line.startswith(labels[0]):
found_dict[0] = True
natoms = int(line.split()[-1])
# Charge
elif line.startswith(labels[1]):
found_dict[1] = True
ch = int(line.split()[-1])
# Spin multiplicity
elif line.startswith(labels[2]):
found_dict[2] = True
mtp = int(line.split()[-1])
# Total Energy
elif line.startswith(labels[3]):
found_dict[3] = True
E = float(line.split()[-1])
# Atomic Numbers
elif line.startswith(labels[4]):
found_dict[4] = True
length = int(line.split()[-1])
idx2 = idx+1
while len(atonums) != length:
nextline = lines[idx2]
atonums += [int(i) for i in nextline.split()]
idx2 += 1
# Cartesian Coordinates
elif line.startswith(labels[5]):
found_dict[5] = True
length = int(line.split()[-1])
idx2 = idx+1
while len(xcc) != length:
nextline = lines[idx2]
xcc += [float(i) for i in nextline.split()]
idx2 += 1
# List of atomic masses
elif line.startswith(labels[6]):
found_dict[6] = True
length = int(line.split()[-1])
idx2 = idx+1
while len(masses) != length:
nextline = lines[idx2]
masses += [float(i) for i in nextline.split()]
idx2 += 1
# Cartesian Gradient
elif line.startswith(labels[7]) and natoms != 1:
found_dict[7] = True
length = int(line.split()[-1])
idx2 = idx+1
while len(gcc) != length:
nextline = lines[idx2]
gcc += [float(i) for i in nextline.split()]
idx2 += 1
# Cartesian Force Constant Matrix
elif line.startswith(labels[8]) and natoms != 1:
found_dict[8] = True
length = int(line.split()[-1])
idx2 = idx+1
while len(Fcc) != length:
nextline = lines[idx2]
Fcc += [float(fij) for fij in nextline.split()]
idx2 += 1
# Return data
#if gcc == []: gcc = None
#if Fcc == []: Fcc = None
return xcc,atonums,ch,mtp,E,gcc,Fcc,masses, calclevel.strip()
def read_orcaout(orca_out):
# Read lines
lines = read_file(orca_out)
# CHECK FILE IS ORCA OUT
correct = False
for line in lines:
if "This ORCA versions uses" in line:
correct = True
break
if not correct: raise Exc.FileType(Exception)
# Initialize
ch, mtp, E = None, None, None
xcc, symbols, atonums = [], [], []
# basis set
basisset = ""
try:
for line in lines:
if "utilizes the basis" in line:
basisset = line.split(":")[1]
break
except:
pass
# hamiltonian
hamiltonian = ""
try:
for idx, line in enumerate(lines):
if "Hamiltonian:" in line:
hamiltonian = lines[idx + 1].split()[-1]
break
except:
pass
# level of calculation
calclevel = hamiltonian + " " + basisset
# Get ch, mtp, E
pos_cart = None
pos_zmat = None
for idx in range(len(lines)):
line = lines[idx]
if "Total Charge Charge" in line: ch = int(line.split()[-1])
if "Multiplicity Mult" in line: mtp = int(line.split()[-1])
if "FINAL SINGLE POINT ENERGY " in line: E = float(line.split()[-1])
if "CARTESIAN COORDINATES (A.U.)" in line: pos_cart = idx
if "INTERNAL COORDINATES (ANGST" in line: pos_zmat = idx
# Get xcc, symbols, atonums
if pos_cart is None:
sys.exit(
"Unable to find 'CARTESIAN COORDINATES (A.U.)' label in file!")
pos_cart += 3
for line in lines[pos_cart:]:
line = line.strip()
if line == "": break
idx, symbol, atonum, dummy, mass, x, y, z = line.split()
if symbol == "-": symbol = "XX"
xcc += [float(x), float(y), float(z)]
symbols.append(symbol)
atonums.append(int(atonum.split(".")[0]))
# data in internal coordinates
lzmat = None
if pos_zmat is not None:
pos_zmat += 2
lzmat = []
for idx, line in enumerate(lines[pos_zmat:]):
line = line.strip()
if line == "": break
symbol, atk, atj, ati, dist, angle, dihedral = line.split()
if symbol == "-": symbol = "XX"
atk, atj, ati = int(atk) - 1, int(atj) - 1, int(ati) - 1
dist, angle, dihedral = float(dist), float(angle), float(dihedral)
if idx == 0: connections, values = (), ()
elif idx == 1: connections, values = (atk, ), (dist, )
elif idx == 2: connections, values = (atk, atj), (dist, angle)
else:
connections, values = (atk, atj, ati), (dist, angle, dihedral)
data = (symbol, connections, values)
lzmat += [data]
# Return
return xcc, lzmat, atonums, ch, mtp, E, calclevel.strip()
def normal_termination(ofile):
olines = read_file(ofile)
if len(olines) == 0: return False
if "ORCA TERMINATED NORMALLY" not in olines[-2]:
return False
return True
def start_end_blocks(plotfile):
text = "".join(ff.read_file(plotfile))
blocks = text.split("start_")[1:]
blocks = [block.split("end_")[0] for block in blocks]
return blocks
def deal_with_anh(anhfile, ltemp, ZPEMSHO, QMSHO):
RATIO = None
DZPE = None
string = ""
while True:
if anhfile is None: break
anhfile = PN.ANHDIR + anhfile
if not os.path.exists(anhfile):
string += "Anharmonicity file '%s' NOT FOUND!\n" % anhfile
string += "\n"
break
string += "Anharmonicity file '%s' FOUND!\n" % anhfile
string += "\n"
# read lines in file
lines = read_file(anhfile)
# type of file??
itisq2dtor = False
itismstor = False
for line in lines[::-1]:
if "End of Q2DTor output" in line:
itisq2dtor = True
break
if "End of MSTor output" in line:
itismstor = True
break
# get data
if itisq2dtor:
Tlist, ZPE_MSHO, Q_MSHO, ZPE_ANH, Q_ANH = read_q2dtorout(anhfile)
elif itismstor:
Tlist, ZPE_MSHO, Q_MSHO, ZPE_ANH, Q_ANH = read_mstorout(anhfile)
else:
string += " * unable to identify the program where this file come from...\n"
string += "\n"
break
# print info
if None in (ZPE_MSHO, Q_MSHO, ZPE_ANH, Q_ANH):
string += " * unable to read the file properly...\n"
string += "\n"
break
# print zpe
string += " * Data in file:\n"
string += "\n"
string += " ZPE_MSHO: %.8f hartree\n" % ZPE_MSHO
string += " ZPE_ANH : %.8f hartree\n" % ZPE_ANH
string += "\n"
# compare list of temperatures
string += " * checking list of temperatures\n"
common = []
for idxT1, T1 in enumerate(Tlist):
for idxT2, T2 in enumerate(ltemp):
if abs(T1 - T2) < EPS_TEMP: common.append(idxT1)
string += " num_temps(%s) = %i\n" % (PN.IFILE2, len(ltemp))
string += " num_temps(%s) = %i\n" % (anhfile, len(Tlist))
string += " in common --> %i\n" % (len(common))
if len(common) != len(ltemp):
string += " differences in temperatures detected [FAIL]\n"
break
elif len(common) != len(Tlist):
Tlist = [Tlist[idxT] for idxT in common]
Q_MSHO = [Q_MSHO[idxT] for idxT in common]
Q_ANH = [Q_ANH[idxT] for idxT in common]
string += " temperatures match! [OK]\n"
string += "\n"
# print partition functions
thead = " T (K) | Q_MSHO | Q_ANH "
tdivi = "-" * len(thead)
string += " " + tdivi + "\n"
string += " " + thead + "\n"
string += " " + tdivi + "\n"
for idx, T in enumerate(Tlist):
tline = " %8.2f | %10.3E | %10.3E " % (T, Q_MSHO[idx], Q_ANH[idx])
string += " " + tline + "\n"
string += " " + tdivi + "\n"
string += "\n"
# compare ZPE of MSHO
string += " * checking MSHO data...\n"
maxdiff = abs(ZPE_MSHO - ZPEMSHO) * KCALMOL
if maxdiff < 0.1:
string += " abs. diff. in ZPE is %.1E kcal/mol [OK]\n" % maxdiff
else:
string += " abs. diff. in ZPE is %.1E kcal/mol [FAIL]\n" % maxdiff
break
# compare pfn of MSHO
maxdiff = 100 * max(
[abs(pi - pj) / pi for pi, pj in zip(QMSHO, Q_MSHO)])
if maxdiff < 2.0:
string += " max. rel. diff in MSHO partition function is %.1E%% [OK]\n" % maxdiff
else:
string += " max. rel. diff in MSHO partition function is %.1E%% [FAIL]\n" % maxdiff
break
string += "\n"
# calculate ratio
string += " * Calculating anh. ratio = Q_ANH/Q_MSHO * exp(-(ZPE_ANH-ZPE_MSHO)*beta)\n"
string += "\n"
DZPE = ZPE_ANH - ZPE_MSHO
RATIO = [(Q_ANH[idx] / Q_MSHO[idx]) * exp128(-DZPE / KB / T)
for idx, T in enumerate(ltemp)]
# print partition functions
thead = " T (K) | ANH. RATIO "
tdivi = "-" * len(thead)
string += " " + tdivi + "\n"
string += " " + thead + "\n"
string += " " + tdivi + "\n"
for idx, T in enumerate(ltemp):
tline = " %8.2f | %10.3E " % (T, RATIO[idx])
string += " " + tline + "\n"
string += " " + tdivi + "\n"
string += "\n"
break
return RATIO, string
def deal_with_anh(anhfile, ltemp, ZPEMSHO, QMSHO):
RATIO = None
DZPE = None
string = ""
while True:
if anhfile is None: break
anhfile = PN.ANHDIR + anhfile
if not os.path.exists(anhfile):
string += "Anharmonicity file '%s' NOT FOUND!\n" % anhfile
string += "\n"
break
string += "Anharmonicity file '%s' FOUND!\n" % anhfile
string += "\n"
# read lines in file
lines = read_file(anhfile)
# type of file??
itisq2dtor = False
itismstor = False
for line in lines[::-1]:
if "End of Q2DTor output" in line:
itisq2dtor = True
break
if "End of MSTor output" in line:
itismstor = True
break
# get data
if itisq2dtor:
Tlist, ZPE_MSHO, Q_MSHO, ZPE_ANH, Q_ANH = read_q2dtorout(anhfile)
elif itismstor:
Tlist, ZPE_MSHO, Q_MSHO, ZPE_ANH, Q_ANH = read_mstorout(anhfile)
else:
string += " * unable to identify the program where this file come from...\n"
string += "\n"
break
# print info
if None in (ZPE_MSHO, Q_MSHO, ZPE_ANH, Q_ANH):
string += " * unable to read the file properly...\n"
string += "\n"
break
# print zpe
string += " * Data in file:\n"
string += "\n"
string += " ZPE_MSHO: %.8f hartree\n" % ZPE_MSHO
string += " ZPE_ANH : %.8f hartree\n" % ZPE_ANH
string += "\n"
# print partition functions
thead = " T (K) | Q_MSHO | Q_ANH "
tdivi = "-" * len(thead)
string += " " + tdivi + "\n"
string += " " + thead + "\n"
string += " " + tdivi + "\n"
for idx, T in enumerate(Tlist):
tline = " %8.2f | %10.3E | %10.3E " % (T, Q_MSHO[idx], Q_ANH[idx])
string += " " + tline + "\n"
string += " " + tdivi + "\n"
string += "\n"
# compare list of temperatures
string += " * checking list of temperatures\n"
if len(Tlist) != len(ltemp):
string += " different size (%i vs %i) [FAIL]\n" % (len(ltemp),
len(Tlist))
break
else:
string += " same number of temperatures (%i) [OK]\n" % (
len(ltemp))
maxdiff = max([abs(t1 - t2) for t1, t2 in zip(ltemp, Tlist)])
if maxdiff > EPS_TEMP:
string += " temperatures differ more than %.2E Kelvin [FAIL]\n" % (
EPS_TEMP)
break
else:
string += " max. abs. diff in temperatures is %.2E Kelvin [OK]\n" % (
maxdiff)
string += "\n"
# compare ZPE of MSHO
string += " * checking MSHO data...\n"
maxdiff = (ZPE_MSHO - ZPEMSHO) * KCALMOL
if maxdiff < 0.1:
string += " abs. diff. in ZPE is %.1E kcal/mol [OK]\n" % maxdiff
else:
string += " abs. diff. in ZPE is %.1E kcal/mol [FAIL]\n" % maxdiff
break
# compare pfn of MSHO
maxdiff = 100 * max(
[abs(pi - pj) / pi for pi, pj in zip(QMSHO, Q_MSHO)])
if maxdiff < 1.0:
string += " max. rel. diff in MSHO partition function is %.1E%% [OK]\n" % maxdiff
else:
string += " max. rel. diff in MSHO partition function is %.1E%% [FAIL]\n" % maxdiff
break
string += "\n"
# calculate ratio
string += " * Calculating anh. ratio = Q_ANH/Q_MSHO * exp(-(ZPE_ANH-ZPE_MSHO)*beta)\n"
string += "\n"
DZPE = ZPE_ANH - ZPE_MSHO
RATIO = [(Q_ANH[idx] / Q_MSHO[idx]) * np.exp(-DZPE / KB / T)
for idx, T in enumerate(ltemp)]
# print partition functions
thead = " T (K) | ANH. RATIO "
tdivi = "-" * len(thead)
string += " " + tdivi + "\n"
string += " " + thead + "\n"
string += " " + tdivi + "\n"
for idx, T in enumerate(ltemp):
tline = " %8.2f | %10.3E " % (T, RATIO[idx])
string += " " + tline + "\n"
string += " " + tdivi + "\n"
string += "\n"
break
return RATIO, string
