from pyxyz import Confpool, KC2H

p = Confpool()
p.include_from_file("initial_set.xyz") # <--- Set the filename
print(f"Initial number of conformers = {p.size}")

n_del = 0
p["Energy"] = lambda m: float(m.descr.strip())
p.sort("Energy")
n_del += p.upper_cutoff("Energy", 10.0 * KC2H) # <--- Energies >10.0 kcal/mol relative to minimal are discarded
p.generate_connectivity(0, mult=1.3, ignore_elements=[], sdf_name='connectivity_check.sdf')
niso = p.generate_isomorphisms()
print(f"Number of isomorphisms = {niso}")

rmsd_status = p.rmsd_filter(0.2, energy_threshold=1.0 * KC2H, energy_key='Energy', mirror_match=True, print_status=False)
n_del += rmsd_status['DelCount']
print(f"{n_del} conformers were filtered in total")
newp = Confpool()
newp.include_subset(p, [rmsd_status["MinRMSD_pairA"], rmsd_status["MinRMSD_pairB"]])
newp.save("rmsd_value_test.xyz")
print(f"The minimal accepted rmsd was {rmsd_status['MinRMSD']}")
print(f"Number of conformers after filtering = {p.size}")
p.save('full_set.xyz') # <--- Set the filename

# What input file do you need?
gjftemplate = """\
%nprocs=24
%chk=conf_{idx}.chk
# opt=(tight,maxcycle=300) freq=noraman def2tzvp empiricaldispersion=gd3bj rpbe1pbe scrf=(cpcm,solvent=water)

Conformation

0 1
{xyz}


"""
atom_symbols = p.atom_symbols
for i, m in enumerate(p):
    xyz = m.xyz
    xyzlines = []
    for j, symbol in enumerate(atom_symbols):
        xyzlines.append("%2s %14.6f %14.6f %14.6f" % (symbol, *xyz[j]))
    with open(f"conf_{i}.gjf", 'w') as f: # <--- Set the template for filename 
        f.write(gjftemplate.format(xyz="\n".join(xyzlines), idx=i))