def log_to_xyz_scan():
weeded_list = sel_files(file_weeder([".log"]))
for item in weeded_list:
log = LogFile(read_item(item))
if log.calc_type.lower() == "red": xyzs = log.scan_geoms(); ext_name = "_scan_traject.xyz"
elif log.calc_type.lower() == "irc": xyzs = log.irc(); ext_name = "_irc_traject.xyz"
elif log.calc_type.lower() in ["opt","ts"]: xyzs = log.opt(); ext_name = "_opt_traject.xyz"
else: print("The file is not a scan, opt or irc log file"); continue
if len(xyzs) < 2:
print("The file contains less than 2 steps")
is_terse_irc = all([len(xyzs) < 2, log.calc_type == "IRC",
log.raw_route.lower().startswith("#t") or log.raw_route.lower().startswith("# t ")])
if is_terse_irc:
print("WARNING! Error above may have been caused by the following:")
print("IRC calculations with the #T keyword may not archive intermediate geometries")
print("#N or #P keywords are recommended instead")
continue
max_e = max(float(i.title()) for i in xyzs)
min_e = min(float(i.title()) for i in xyzs)
c=[0,"percentage","kcal"]
print("{:5}{:^90}{:>8}".format("Entry"," >---> Relative Energy >---> "," kcal"))
for entry in [float(i.title()) for i in xyzs]:
c[0]=c[0]+1
c[1]= "|"*int(90*((float(entry)-min_e)/(max_e-min_e)) if max_e != min_e else 0)
c[2]= (float(entry)-min_e)*627.5
print("{:<5}{:<90}".format(c[0],c[1]),"{:>6.5f}".format(c[2]) if ext_name == "_opt_traject.xyz" else "{:>6.2f}".format(c[2]))
file_name = item.replace(".log",ext_name)
with open(file_name,mode="w",newline="\n") as file: file.write("\n".join([a for i in xyzs for a in i.return_print()]))
def deduplicate():
print("Analyzing energies...")
energies = [[
b.name,
float(b.scf_done[-1][1]), b.normal_termin,
b.last_xyz_obj()
] for i in file_weeder([".log"]) for b in [LogFile(read_item(i))]]
unique = energies
if not unique:
print("No log files to be analyzed")
return
black_list, folder_mov = [], []
print("Starting analysis...")
for file in sorted(unique, key=lambda x: (x[2], -x[1]), reverse=True):
if file[0] in black_list: continue
black_list.append(file[0])
sim_en = [
i for i in unique
if i[0] not in black_list and i[1] + 1 > file[1] > i[1] - 1
]
if sim_en:
duplicates = []
for obj in sim_en:
if obj[3].superimpose(file[3], ret="max_d", conv=6):
print("{} is a duplicate of {}".format(
obj[3].name(), file[3].name()))
duplicates.append(obj[3].name())
black_list.append(obj[3].name())
if duplicates: folder_mov.append([file[3].name(), duplicates])
for folder in folder_mov:
subfolder = os.path.join(
os.getcwd(),
"duplicates_of_{}".format(folder[0].replace(".log", "")))
try:
os.mkdir(subfolder)
except FileExistsError:
pass
print("Moving duplicates of {} to the following directory:\n{}".format(
folder[0], subfolder))
for file in folder[1]:
for alt_file in file_weeder([file.replace(".log", ".")]):
try:
shutil.move(os.path.join(os.getcwd(), alt_file),
os.path.join(subfolder, alt_file))
print("Moved: {}".format(alt_file))
except PermissionError:
print("Error while moving log files:")
print(
"Maybe {} already exists in the following directory:\n{}"
.format(alt_file, subfolder))
except FileNotFoundError:
print("File {} not found in the following directory:\n{}".
format(alt_file, subfolder))
print("Done!")
def save_inp(self,parameters,index):
if not preferences.folder_op: self.weeded_list = sel_files(self.weeded_list)
if not self.weeded_list: return
for i in self.weeded_list:
if os.path.isfile(os.path.join(os.getcwd(), (i.replace(self.original_ext, ".inp")))):
print(i.replace(self.original_ext,".inp") + " already exist on current directory!")
continue
xyz = LogFile(read_item(i)).last_xyz_obj() if self.use_logs else XyzFile(read_item(i))
inp_out = []
for idx_a, line in enumerate(parameters[0:index]):
if self.use_logs and idx_a + 1 == len(parameters[0:index]):
line = "* " + " ".join(LogFile(read_item(i)).charge_mult)
inp_out.append(line.replace("FILENAME", i.replace(self.original_ext, "")) + "\n")
for line in xyz.form_cord_block():
inp_out.append(line + "\n")
for line in parameters[index + 1:]:
inp_out.append(line + "\n")
with open(os.path.join(os.getcwd(), (i.replace(self.original_ext,".inp"))), "w",newline="\n") as file:
for line in inp_out: file.write(line)
print(i.replace(self.original_ext, ".inp"), " created!")
return
def log_to_xyz():
weeded_list = file_weeder([".log"])
weeded_list = weeded_list if preferences.folder_op else sel_files(weeded_list)
if not weeded_list: return
while True:
print("Which geometry do you want?")
print("0 - Cancel")
print("1 - Last")
print("2 - Lowest energy")
print("3 - First")
geom = input()
if geom == "0": return
if geom in ["1","2","3"]: break
else: print("Invalid option!")
for i in weeded_list:
try:
if geom == "1": LogFile(read_item(i)).last_xyz_obj().save_file()
elif geom == "2": LogFile(read_item(i)).low_e_xyz_obj().save_file()
elif geom == "3": LogFile(read_item(i)).first_xyz_obj().save_file()
except Exception as e:
print("Error on file: {}".format(i))
print(e)
def log_freq_xyz():
weeded_list = sel_files(file_weeder([".log"]))
for i in weeded_list:
log = LogFile(read_item(i))
if not log.last_freq:
print("No frequencies found in file:{}!".format(i))
continue
option = None
while True:
print("Analizing file: {}".format(i))
print("Chose a frequency to split (0-To cancel/m-For more)")
for idx,item in enumerate(log.last_freq.frequencies(),start=1):
print("{:>5}:{:>15}".format(idx,item))
if option == "m": continue
if idx > 2: break
option=input()
if option == "m": continue
elif option in [str(a+1) for a in range(len(log.last_freq.frequencies()))]: break
elif option == "0": break
else: print("Invalid option, try again!")
if option == "0": continue
print("Give a multiplier (recomended multiplier = 1) ")
while True:
try:
mult=float(input().replace(",","."))
break
except ValueError:
print("Not a valid number")
left = log.last_xyz_obj().displace(-mult,log.last_freq.displ_for_freq_idx(int(option)-1))
left.list[0] = i.replace(".log","_l.xyz")
left.save_file()
right = log.last_xyz_obj().displace(mult,log.last_freq.displ_for_freq_idx(int(option)-1))
right.list[0] = i.replace(".log","_r.xyz")
right.save_file()
print("\nJob Done!\n")
print("Finished !")
def rel_scf(list=False):
energies = []
for i in file_weeder([".log"]):
log = LogFile(read_item(i))
energies.append([log.name, log.scf_done[-1][1], log.normal_termin])
if len(energies) == 0:
print("No .log files in current folder")
return
energies = [[i[0], float(i[1]), i[2]] for i in energies]
energies.sort(key=lambda x: x[1])
min_e = energies[0][1]
energies = [[i[0], (i[1] - min_e) * 627.509, i[2]] for i in energies]
if list == False:
print("\n".join(["{:>30}{:>15f}{:>5}".format(*l) for l in energies]))
elif list == True:
return energies
def e_analysis(weeded_list):
"""Analyses Gaussian log files in weeded_list and prints out a txt file with results in current directory"""
file_name = "Extracted_data.txt"
out = []
out.append("{} File(s) were analyzed in total.".format(len(weeded_list)))
out.append("{:^29}|{:^20}|{:^20}|{:^20}".format("Name",
"Sum of Elet an TC",
"Thermal Correct",
"last SCF"))
rel_e = []
for i in weeded_list:
log = LogFile(read_item(i))
t = log.thermal
try:
last_SCF = log.scf_done[-1][-1]
except:
last_SCF = "None"
if t == False:
out.append("{:<30} no_thermo_data_found_Last_SCF: {:>20}".format(
i, last_SCF))
continue
out.append("{:<30}{:>20}{:>20}{:>20}".format(str(i), str(t[7]),
str(t[3]), str(last_SCF)))
rel_e.append([
i,
float(t[7]) * 627.5095,
float(last_SCF) * 627.5095,
float(t[3]) * 627.5095
])
if len(rel_e) > 1:
print(
"Do you want the free energies to be reported relative to which item?"
)
print("Enter 0 if you don't want to analyze them)")
for idx, entry in enumerate(rel_e):
print(" {:<4}{:<20}{:>25}".format(idx + 1, entry[0],
round(entry[1], 2)))
while True:
option = input()
if option in [str(a) for a in range(len(rel_e) + 1)]:
option = int(option)
break
else:
print("Could notunderstand request")
if option == 0: print("Leaving analysis\n")
else:
out.append("\nFree energies relative to {}, (Name,G,H,TC):".format(
rel_e[option - 1][0]))
for i in rel_e:
a = [
i[0], *[
round(i[n] - rel_e[option - 1][n], 2)
for n in [1, 2, 3]
]
]
out.append("{:<26}{:>26}{:>10}{:>10}".format(*a))
out.append("\n")
with open(file_name, mode="w", newline="\n") as file:
file.write("\n".join(out))
print(
"\nDone! \nPlease lookup:\n\n" + os.path.join(os.getcwd(), file_name),
"\n")
def evaluate_file(a, options, i, last):
try:
row = ["None" for _ in options]
#FILE PROPERTIES
row[idx("Filename")] = os.path.basename(a)
#FOLDER PROPERTIES
fold_name = os.path.dirname(a)
row[idx("FOLD")] = 'HYPERLINK("{}";"{}")'.format(
fold_name, os.path.relpath(fold_name, os.getcwd()))
#INPUT PROPERTIES
inp_name = a + preferences.gauss_ext
is_inp = os.path.isfile(os.path.relpath(inp_name, os.getcwd()))
inp = GjfFile(read_item(os.path.relpath(
inp_name, os.getcwd()))) if is_inp else False
row[idx("INP")] = 'HYPERLINK("{}";"Link")'.format(
inp_name) if is_inp else "-"
row[idx("Inp Route")] = inp.route_text() if inp else "No data"
#XYZ PROPERTIES
xyz_name = a + ".xyz"
is_xyz = os.path.isfile(os.path.relpath(xyz_name, os.getcwd()))
row[idx("XYZ")] = 'HYPERLINK("{}";"Link")'.format(
xyz_name) if is_xyz else "-"
#LOG PROPERTIES
log_name = a + ".log"
is_log = os.path.isfile(os.path.relpath(log_name, os.getcwd()))
log = LogFile(read_item(os.path.relpath(
log_name, os.getcwd()))) if is_log else False
freq = log and log.last_freq
row[idx("Free energy")] = str(
log.thermal[7]) if freq else "No data"
row[idx("+A")] = "-"
row[idx("+B")] = "-"
row[idx("+C")] = "-"
row[idx("+D")] = "-"
row[idx("-E")] = "-"
row[idx("-F")] = "-"
row[idx("Structure")] = "-"
row[idx(
"Rel_E"
)] = "(SUM($A#:$E#)-SUM($F#:$G#)-SUM($A#:$E#)+SUM($F#:$G#))*627.509474"
row[idx("iFreq")] = log.last_freq.n_ifreq() if freq else "-"
row[idx("TYP")] = log.calc_type if log else "-"
row[idx("LOG")] = 'HYPERLINK("{}";"Link")'.format(
log_name) if log else "-"
row[idx("Done?")] = "Yes" if log and log.normal_termin else "No"
row[idx("last_SCF")] = str(
log.scf_done[-1][-1]) if log and log.normal_termin else "-"
row[idx("Hentalphy")] = str(log.thermal[6]) if freq else "-"
row[idx("Error msg")] = log.error_msg if log else "-"
row[idx("Needs refinement?")] = log.needs_ref() if log else "-"
row[idx("Log Route")] = log.raw_route if log else "-"
except Exception as e:
print()
print("\nError on file:\n{}\n".format(a))
print(e, "\n")
finally:
if i + 1 < last:
print("\rEvaluating... {}/{}".format(i + 1, last), end=" ")
else:
print(
"\rEvaluation done ({}/{}), saving '.xls' file...".format(
i + 1, last))
return row
def save_gjf(self,parameters,index):
heavy_e, gjf_overwrite, folder_op = [preferences.heavy_atom,preferences.gjf_overwrite,preferences.folder_op]
ecps, basis = None, None
if not folder_op: self.weeded_list = sel_files(self.weeded_list)
if not self.weeded_list: return
if any([b in parameters for b in ["INSERT_GBS_BASIS","INSERT_GBS_ECP"]]):
print("This parameter file requires an aditional gbs file.")
print("Where should it be taken from?")
print("0 - Current folder")
print("1 - Builtins")
print("2 - User defined")
while True:
option = input()
if option in ["0","1","2"]: break
if option == "0": files_dir = os.getcwd()
elif option == "1": files_dir = self.p_files_dir
elif option == "2": files_dir = self.user_files_dir
gbs_files = file_weeder([".gbs"], cf=files_dir)
print("Chosse one basis/ecp set\n0 - Cancel")
for i, file in enumerate(gbs_files): print("{} - {}".format(i+1, file))
while True:
option = input()
if option in [str(a) for a in range(len(gbs_files)+1)]: break
print("Invalid option")
if option == "0": return
with open(os.path.join(files_dir,gbs_files[int(option)-1])) as file:
gbs_file = file.read().splitlines()
basis, ecps = self.read_gbs(gbs_file)
assert type(basis) == dict, "Basis was not read"
assert type(ecps) == dict, "Ecps were not read"
for i in self.weeded_list:
try:
gjf_out, rm_lines, = [], []
if os.path.isfile(os.path.join(os.getcwd(),(i.replace(self.original_ext,preferences.gauss_ext)))) and not gjf_overwrite:
print(i.replace(self.original_ext,preferences.gauss_ext) + " already exist on current directory!")
continue
xyz = LogFile(read_item(i)).last_xyz_obj() if self.use_logs else XyzFile(read_item(i))
for idx_a,line in enumerate(parameters[0:index]):
if self.use_logs and idx_a+1 == len(parameters[0:index]): line = " ".join(LogFile(read_item(i)).charge_mult)
gjf_out.append(line.replace("FILENAME",i.replace(self.original_ext,""))+"\n")
for line in xyz.form_cord_block():
gjf_out.append(line+"\n")
possible = [str(b + 1) for b in range(xyz.n_atoms())]
for line in parameters[index+1:]:
# SCAN like: "B S APROX" or "B S DIST"
is_mod_red = any("modredundant" in i.lower() for i in parameters[0:index])
s_line = line.split()
while len(s_line) == 3:
if s_line[0] != "B" or s_line[1] != "S": break
if s_line[2] not in ["APROX","DIST"]: break
if not is_mod_red:
print("Missing 'modredundant' keyword?")
break
if xyz.n_atoms() <2:
raise Exception(f"At least two atoms are neded in struture {xyz.name()} to perform a scan")
atom=["a","b"]
if s_line[-1] == "APROX":
print(f"Detected bond scan (APROX) for xyz file {i}.")
while not all(atom[a] in possible if atom[0] != atom[1] else False for a in [0,1]):
atom = [input("Enter atom A: "),input("Enter atom B: ")]
line = f"B {atom[0]} {atom[1]} S APROX"
elif s_line[-1] == "DIST":
print(f"Detected bond scan (DIST) for xyz file {i}.")
while not all(atom[a] in possible if atom[0] != atom[1] else False for a in [0,1]):
atom = [input("Enter atom A: "),input("Enter atom B: ")]
line = f"B {atom[0]} {atom[1]} S DIST"
s_line = line.split()
break
# SCAN like: "B 1 2 S APROX" or "B 1 2 S DIST"
while len(s_line) == 5:
if s_line[0] != "B" or s_line[3] != "S": break
if not s_line[1].isdigit(): break
if not s_line[2].isdigit(): break
if s_line[4] not in ["APROX", "DIST"]: break
if not is_mod_red:
print("Missing 'modredundant' keyword?")
break
if xyz.n_atoms() < 2:
raise Exception(f"At least two atoms are neded in struture {xyz.name()} to perform a scan")
atoms_idx = [int(s_line[1])-1, int(s_line[2])-1]
if any(True for a in atoms_idx if not a in range(xyz.n_atoms())):
raise Exception(f"Scan atom numbers are larger than the number of atoms for: {xyz.name()}")
atoms_cord = [i for idx,i in enumerate(xyz.cord_block()) if idx in atoms_idx]
dist = math.sqrt(sum((float(i)-float(atoms_cord[1][idx]))**2 for idx,i in enumerate(atoms_cord[0]) if idx > 0))
ideal_dist=sum(b[1] for idx,b in enumerate(element_radii) if b[0] in [i[0] for i in atoms_cord])/100
if s_line[-1] == "APROX":
line = line.replace("APROX",f"{1+int((dist-ideal_dist)/0.075)} -0.075")
elif s_line[-1] == "DIST":
line = line.replace("DIST",f"{1+int(ideal_dist/0.075)} 0.075")
s_line = line.split()
break
# SCAN like: "D S"
while len(s_line) == 2:
if not is_mod_red: break
if s_line[0] != "D" or s_line[1] != "S": break
print(f"Detected dihedral scan for xyz file {i}.")
if xyz.n_atoms() < 4:
raise Exception(f"At least two four atoms are neded in struture {xyz.name()} to perform a dihedral scan")
while True:
atom = [input(f"Enter atom {a}: ") for a in ["A","B","C","D"]]
atom = [a.strip() for a in atom]
if not all([len(a.split()) == 1 and a.isdigit() for a in atom]):
print("No non-numeric characters or spaces are allowed for atom numbers")
continue
if not len(set(atom)) == 4:
print("No atom should be repeated!")
continue
if not all([a in possible for a in atom]):
print("Atoms with incorrect number were found!")
continue
break
while True:
n_steps = input("Please give the number of steps to be taken: ").strip()
if n_steps.isdigit(): break
else: print("The number of steps must be an integer")
while True:
print("Please give the step size to be taken in degrees")
size = input("The number must include a dot character as a decimal place (eg. '10.0'): ").strip()
if is_str_float(size) and size.count(".") == 1: break
else: print("Please make sure the number complies with formating rules!")
line = f"D {' '.join(atom)} S {n_steps} {size}"
s_line = line.split()
break
# READOPTIMIZE + NOTATOMS
if line.replace(" ", "").lower() == "notatoms=":
print("Please enter the atoms you want to freeze on structure {} separated by comma".format(xyz.name()))
line = line + input(line)
# READOPTIMIZE + ATOMS
elif line.replace(" ", "").lower() == "noatomsatoms=":
print("Please enter the atoms you want to optimize on structure {} separated by comma".format(xyz.name()))
line = line + input(line)
# BASIS like: "LIGHT_ELEMENT_BASIS 0" or "HEAVY_ELEMENT_BASIS 0" and ECP like "HEAVY_ELEMENT_ECP 0"
elif len(s_line) == 2:
if any(True for a in ["/gen","gen ","genecp"] if a in " ".join(parameters[0:index-3]).lower()):
if s_line == ["LIGHT_ELEMENT_BASIS","0"]:
elm = [a for a in xyz.elements() if elements.index(a) < heavy_e+1]
if elm: line = line.replace("LIGHT_ELEMENT_BASIS"," ".join(elm))
else:
for a in range(3): rm_lines.append(len(gjf_out)+a)
elif s_line == ["HEAVY_ELEMENT_BASIS","0"]:
elm = [a for a in xyz.elements() if elements.index(a) > heavy_e]
if elm: line = line.replace("HEAVY_ELEMENT_BASIS"," ".join(elm))
else:
for a in range(3): rm_lines.append(len(gjf_out)+a)
if "pseudo=read" in " ".join(parameters[0:index - 3]).lower().replace(" ",""):
if s_line == ["HEAVY_ELEMENT_ECP","0"]:
elm = [a for a in xyz.elements() if elements.index(a) > heavy_e]
if elm: line = line.replace("HEAVY_ELEMENT_ECP"," ".join(elm))
else:
pattern = re.compile(r'pseudo.{0,3}=.{0,3}read',re.IGNORECASE)
eval_lines = gjf_out[0:index-3]
for idx_a,a in enumerate(eval_lines):
gjf_out[idx_a] = pattern.sub("",a)
rm_lines.append(len(gjf_out))
rm_lines.append(len(gjf_out)+1)
# BASIS like: "INSERT_GBS_BASIS"
elif "INSERT_GBS_BASIS" in line:
for element in sorted(xyz.elements(),key=lambda x: elements.index(x)):
for line_a in basis[element]:
gjf_out.append(line_a+"\n")
continue
# ECP like: "INSERT_GBS_ECP"
elif "INSERT_GBS_ECP" in line:
if "pseudo=read" in " ".join(parameters[0:index - 3]).lower().replace(" ", ""):
need_ecp = [a for a in xyz.elements() if elements.index(a) > preferences.heavy_atom]
for element in sorted(need_ecp,key=lambda x: elements.index(x)):
for line_a in ecps[element]:
gjf_out.append(line_a+"\n")
if not need_ecp:
pattern = re.compile(r'pseudo.{0,3}=.{0,3}read', re.IGNORECASE)
eval_lines = gjf_out[0:index - 3]
for idx_a, a in enumerate(eval_lines):
gjf_out[idx_a] = pattern.sub("", a)
continue
gjf_out.append(line.replace("FILENAME",i.replace(self.original_ext,""))+"\n")
gjf_out.append("\n")
with open(os.path.join(os.getcwd(),(i.replace(self.original_ext,preferences.gauss_ext))),"w") as gjf_file:
for line in [i for idx,i in enumerate(gjf_out) if idx not in rm_lines]: gjf_file.write(line)
print(i.replace(self.original_ext,preferences.gauss_ext)," created!")
except TypeError as e:
print("Error on file {}".format(i))
print(e)
return