def ir_spectra(self, threshold=20):
pairs = []
for a, b in zip(self.frequencies(), self.ir_intensities()):
if is_str_float(a) and is_str_float(b):
pairs.append([float(a), float(b)])
for a, b in zip(sorted(pairs, key=lambda x: x[1], reverse=True),
range(threshold)):
print("{:>10.1f}{:>10.1f}".format(float(a[0]), float(a[1])))
print("---------")
def __init__(self, file_content):
self.list = file_content
if len(self.list) < 2: raise Exception(".xyz Object is empty?")
elif not (str(self.list[1]).strip().isdigit()
and len(str(self.list[1]).split()) == 1):
print(
"{} is not a proper .xyz file\nAttempting to read it anyway!".
format(self.list[0]))
try_xyz = []
for line in self.list:
line = line.split()
if len(line) != 4: continue
if not all(is_str_float(line[i]) for i in range(1, 4)):
continue
if line[0] in elements[0:]:
try_xyz.append(" ".join(line))
continue
try:
line[0] = elements[int(line[0])]
try_xyz.append(" ".join(line))
except:
raise Exception("Could not understand file {}".format(
self.list[0]))
try_xyz.insert(0, len(try_xyz))
try_xyz.insert(1, " ")
try_xyz.insert(0, self.list[0])
self.list = try_xyz
self.list_l = [str(a).split() for a in self.list]
def __init__(self, line, idx):
assert type(line) is list
assert len(line) == 4
assert line[0] in elements
assert all(is_str_float(a) for a in line[1:])
self.idx = idx
self.element = line[0]
self.cord = [float(a) for a in line[1:]]
def low_e_xyz_obj(self):
if self.calc_type == "SP": return None
else:
xyzs = {
"TS": self.opt,
"Red": self.scan_geoms,
"IRC": self.irc,
"Opt": self.opt
}[self.calc_type]()
if len(xyzs) == 0: return None
else:
return sorted(xyzs,
key=lambda x: float(x.title())
if is_str_float(x.title()) else 1)[0]
def read_strucure(self):
charge_mult = None
title = None
coordinates = []
for i, a in enumerate(self.list[self.hash_line:]):
if i > 5 and not coordinates: break
a = a.split(",")
if len(a) == 2 and not coordinates:
charge_mult = a
continue
if len(a) == 4:
if a[0] in elements and all(
is_str_float(a[n]) for n in [1, 2, 3]):
coordinates.append(" ".join(a))
elif coordinates:
break
elif coordinates:
break
return charge_mult, XyzFile(
[self.list[0],
str(len(coordinates)), title, *coordinates])
def first_cord_block(self):
if not all([self.start_xyz_idxs, self.end_xyz_idxs]):
if self.input_geom_idx:
coordinates = []
for i, a in enumerate(self.list[self.input_geom_idx:]):
if i > 5 and not coordinates: break
a = a.split()
if len(a) == 4:
if a[0] in elements and all(
is_str_float(a[n]) for n in [1, 2, 3]):
coordinates.append(a)
elif coordinates:
break
elif coordinates:
break
return coordinates
else:
return None
else:
return self.xyz_cord_block(self.start_xyz_idxs[0],
self.end_xyz_idxs[0])
def csv_e_analysis():
options = ["Free energy","+A", "+B", "+C", "+D", "-E", "-F", "Structure", "Rel_E", \
"FOLD", "Filename", "XYZ", "INP", "LOG", "TYP", "iFreq", "Needs refinement?", "Done?",\
"last_SCF", "Hentalphy", "Log Route","Inp Route", "Error msg"]
def idx(name):
return options.index(name)
def evaluate_list(folder, files=set()):
for file in os.listdir(folder):
if os.path.isdir(os.path.join(folder, file)):
evaluate_list(os.path.join(folder, file), files)
elif any([
file.endswith(".log"),
file.endswith(".xyz"),
file.endswith(preferences.gauss_ext)
]):
files.add(os.path.join(folder, os.path.splitext(file)[0]))
return files
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
files = evaluate_list(os.getcwd())
csv_list = [
evaluate_file(file, options, i, len(files))
for i, file in enumerate(files)
]
if not csv_list:
return print("No .log files in {} directory".format(os.getcwd()))
csv_list.sort(key=lambda x: x[idx("FOLD")])
try:
import xlwt
from xlwt import Workbook
except ImportError:
print("xlwt module is needed")
return
wb = Workbook()
sheet1 = wb.add_sheet('Data')
style0 = xlwt.easyxf("", "#.0000000")
for i_b, b in enumerate(options):
sheet1.write(0, i_b, b)
for i_a, a in enumerate(csv_list, start=1):
a[idx("Rel_E")] = a[idx("Rel_E")].replace("#", str(i_a + 1))
for i_b, b in enumerate(a):
if i_b in [
idx(term)
for term in ("Free energy", "last_SCF", "Hentalphy")
]:
sheet1.write(i_a, i_b,
float(b) if is_str_float(b) else b, style0)
elif i_b in [
idx(term)
for term in ("FOLD", "XYZ", "INP", "LOG", "Rel_E")
]:
try:
sheet1.write(i_a, i_b, xlwt.Formula(b))
except Exception:
sheet1.write(i_a, i_b, b)
else:
sheet1.write(i_a, i_b, b)
try:
wb.save("linked_analysis.xls")
except PermissionError:
print(
"Error while saving file!\nIs the file '{}' already open?".format(
"linked_analysis.xls"))
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