def insert(db, collection, tmc, debug=True):
repeated, _tmcdoc = check_repeated(db, collection, tmc)
inserted = False
if not repeated:
db[collection].insert_one(tmc.document)
inserted = True
else:
if debug:
print(("existed: ", _tmcdoc["unique_name"]))
print("merging....")
try:
_tmc = tmcMongo(document=_tmcdoc, tag=_tmcdoc["tag"], subtag=_tmcdoc["subtag"],
publication=_tmcdoc["publication"])
converted = True
except ValueError:
converted = False
merge_document_with_new(db, doc1=_tmcdoc, doc_new=tmc.document, update_fields=tmc.update_fields)
if converted:
merge_documents(db, collection,
doc1=_tmcdoc, doc2=tmc.document,
update_fields=tmc.update_fields)
merge_dftruns(dftrun1=_tmc.this_run,
dftrun2=tmc.this_run,
update_fields=tmc.update_fields)
_tmc.write_dftrun(force=True)
return inserted
def push2db(database, collection, tag, subtag, publication=False,
user=False, pwd=False, host="localhost", port=27017, auth=False,
all_runs_pickle=False, update_fields=False, all_runs_list=False,
outpath='/userarchive/db_backup'):
'''
Push data to MongoDB.
:param db: mongo database instance.
:param collection: name of a collection.
:param user: username.
:param pwd: password.
:param host: IP address of the MongoDB.
:param port: port to connect.
:param auth: whether authentication is required to connect to the MongoDB.
:param all_runs_pickle: whether to push from a pickle file of a list of DFTrun objects. If False, will run
check_all_current_convergence() in your mAD folder.
:param tag: tag of your data. Recommend to use the project name (may related to the name of your paper).
:param subtag: Recommend as the name of your mAD folder (considering we may have many mAD folders for each project).
:return: None
'''
from molSimplifyAD.ga_check_jobs import check_all_current_convergence
db = connect2db(user, pwd, host, port, database, auth)
ensure_collection(db, collection)
print(('db push is enabled, attempting commit with tag: %s, subtag: %s to %s' % (tag, subtag, collection)))
if not all_runs_pickle:
if not all_runs_list == False:
all_runs = all_runs_list
else:
_, all_runs, _ = check_all_current_convergence(post_all=True)
else:
all_runs = pickle.load(open(all_runs_pickle, "rb"))
print(("DFTruns loaded from %s." % all_runs_pickle))
print(("number of DFTruns exists: ", len(all_runs)))
count = 0
merged = 0
for this_run in list(all_runs.values()):
print(("adding complex: ", this_run.name))
print(("converged:", this_run.converged, "geo_flag:", this_run.geo_flag,
"ss_flag: ", this_run.ss_flag, "metal_spin_flag: ", this_run.metal_spin_flag))
this_tmc = tmcMongo(this_run=this_run, tag=tag, subtag=subtag,
publication=publication, update_fields=update_fields)
_s = time.time()
insetred = insert(db, collection, this_tmc)
print(("elapse: ", time.time() - _s))
if insetred:
count += 1
else:
merged += 1
print(("add %d entries in the %s['%s']." % (count, database, collection)))
print(("merge %d entries in the %s['%s']." % (merged, database, collection)))
print("creating index...")
db[collection].create_index([("metal", pymongo.ASCENDING),
("ox", pymongo.ASCENDING),
("spin", pymongo.ASCENDING),
("converged", pymongo.ASCENDING),
("alpha", pymongo.ASCENDING),
("lig1", pymongo.ASCENDING),
("lig5", pymongo.ASCENDING),
("lig6", pymongo.ASCENDING),
("status", pymongo.ASCENDING),
("geo_flag", pymongo.ASCENDING),
("ss_flag", pymongo.ASCENDING)
])
dump_databse(database_name=database,
outpath=outpath,
user=user, pwd=pwd)
basepath = os.path.split(basepath)[0]
dbinfo = glob.glob(basepath + '/*dbinfo')
if len(dbinfo) > 0:
with open(dbinfo[0]) as f:
dbval = f.readlines()[0]
reference_struct = query_db(db, 'oct', {'_id': ObjectId(str(dbval))})
print((reference_struct.count()))
print((reference_struct[0]['subtag']))
subtag = reference_struct[0]['subtag'] + '_additional'
else:
subtag = 'no_reference_additional'
print((this_run.geo_flag, this_run.metal_spin_flag, this_run.ss_flag,
this_run.status, subtag))
if write:
this_tmc = tmcMongo(this_run=this_run, tag=tag, subtag=subtag)
_s = time.time()
inserted = insert(db, collection, this_tmc)
print(("elapse: ", time.time() - _s))
if inserted:
count += 1
else:
merged += 1
#### Do this after looping over all outfiles.
print(("add %d entries in the %s['%s']." % (count, database, collection)))
print(("merge %d entries in the %s['%s']." % (merged, database, collection)))
print("creating index...")
if write:
db[collection].create_index([("metal", pymongo.ASCENDING),
("ox", pymongo.ASCENDING),
this_run.wavefunction = get_wavefunction(scrpath)
else:
this_run.wavefunction = False
if this_run.converged:
this_run.flag_oct = True if int(row["flag_oct"]) else False
else:
this_run.flag_oct = -1
filename = "./oldgen_" + this_run.name + "_optim.xyz"
this_run.init_mol = mol3D()
this_run.init_mol.readfromtxt(get_initgeo(filename))
this_run.mol = mol3D()
this_run.mol.readfromtxt(get_lastgeo(filename))
this_run.progmol = mol3D()
this_run.progmol.readfromtxt(get_lastgeo(filename))
this_tmc = tmcMongo(this_run=this_run,
tag="spectro",
subtag="oldgen",
publication="Duan_JCTC_2019",
update_fields=update_fields)
print((this_tmc.document['status'], this_tmc.document['alphaHOMO']))
_s = time.time()
insetred = insert(db, "oct", this_tmc)
print(("elapse: ", time.time() - _s))
if insetred:
count += 1
else:
merged += 1
print(("add %d entries in the %s['%s']." % (count, "tmc", "oct")))
print(("merge %d entries in the %s['%s']." % (merged, "tmc", "oct")))
def main():
args = arg_parser()
if args.user == None or args.pwd == None:
raise KeyError(
"Please use the format python update_db_documents.py -user <username> -pwd <password>."
)
constraints = {
"lig6": {
"$ne": "x"
},
"status": 0,
"gap": {
"$exists": False
}
}
update_fields = ['gap']
database = "tmc"
collection = "oct"
user = args.user
pwd = args.pwd
db = connect2db(user,
pwd,
host="localhost",
port=27017,
database=database,
auth=True)
print(("Number of complexes in the collection:", db.oct.count()))
cursor = db[collection].find(constraints)
tot = count_find(cursor)
print(("Number of complexes to be updated: ", tot))
cursor = db[collection].find(constraints,
no_cursor_timeout=True).batch_size(10)
print(("Are you sure to update %s with constraints %s in %s[%s]? (y/n)" %
(str(update_fields), str(constraints), database, collection)))
_in = eval(input())
if not _in == "y":
print("Quit. Have a nice day.")
quit()
count = 0
confirmed = False
for _tmcdoc in cursor:
print(("complex: ", _tmcdoc["unique_name"]))
recovered = True
try:
_this_tmc = tmcMongo(document=_tmcdoc,
tag=_tmcdoc["tag"],
subtag=_tmcdoc["subtag"],
publication=_tmcdoc["publication"],
update_fields=update_fields)
print(("complex id_doc:", _this_tmc.id_doc))
except ValueError:
print("The input document cannot recover a DFTrun object.")
recovered = False
if recovered:
####
## Case 1.
## Simple modification. You have already know what to update and you **don't** want to update dftrun.
new_tmc = copy.deepcopy(_this_tmc)
try:
new_tmc.document["gap"] = new_tmc.document[
"alphaLUMO"] - new_tmc.document["alphaHOMO"]
except:
pass
# Change here. e.g. new_tmc.document["publication"] = xxx
####
####
## Case 2.
## Modify both the documents and dftrun.
# _this_run = copy.deepcopy(_this_tmc.this_run)
# current_folder = _this_run.scrpath.strip("optim.xyz")
# multiwfnpath = glob.glob(current_folder + "*.molden")
# if len(multiwfnpath) > 0:
# multiwfnpath = multiwfnpath[0]
# mulliken_spin_list = get_mulliken(multiwfnpath, _this_run.spin, _this_run.liglist[-1])
# print(mulliken_spin_list)
# _this_run.net_metal_spin = mulliken_spin_list[0]
# if len(mulliken_spin_list) > 1:
# _this_run.net_oxygen_spin = mulliken_spin_list[1]
# else:
# print("No molden path found.")
# _this_run.get_check_flags()
# new_tmc = tmcMongo(this_run=_this_run, tag=_tmcdoc["tag"], subtag=_tmcdoc["subtag"],
# publication=_tmcdoc["publication"], update_fields=update_fields)
###
if not confirmed:
for key in update_fields:
print(("=======Key======: ", key))
if key in _tmcdoc:
print(("Current: ", _tmcdoc[key]))
else:
print("Currently does not exist.")
print(("Change to: ", new_tmc.document[key]))
print("Is this expected? (y/n)")
_in = eval(input())
if _in == "y":
confirmed = True
else:
print("Quit. Have a nice day.")
quit()
__ = insert(db, collection, new_tmc)
count += 1
print((" In progress: %d / %d" % (count, tot)))
print(("You have changed %d documents in %s[%s]" %
(tot, database, collection)))