def get_statistics(self, tclass, users=[]):
from aiida.orm.querybuilder import QueryBuilder as QB
from aiida.orm import User
from collections import Counter
def count_statistics(dataset):
def get_statistics_dict(dataset):
results = {}
for count, typestring in sorted(
(v, k) for k, v in dataset.iteritems())[::-1]:
results[typestring] = count
return results
count_dict = {}
types = Counter([r[3] for r in dataset])
count_dict["types"] = get_statistics_dict(types)
ctimelist = [r[1].strftime("%Y-%m") for r in dataset]
ctime = Counter(ctimelist)
count_dict["ctime_by_month"] = get_statistics_dict(ctime)
ctimelist = [r[1].strftime("%Y-%m-%d") for r in dataset]
ctime = Counter(ctimelist)
count_dict["ctime_by_day"] = get_statistics_dict(ctime)
mtimelist = [r[2].strftime("%Y-%m") for r in dataset]
mtime = Counter(ctimelist)
count_dict["mtime_by_month"] = get_statistics_dict(mtime)
mtimelist = [r[1].strftime("%Y-%m-%d") for r in dataset]
mtime = Counter(ctimelist)
count_dict["mtime_by_day"] = get_statistics_dict(mtime)
return count_dict
statistics = {}
q = QB()
q.append(tclass, project=['id', 'ctime', 'mtime', 'type'], tag='node')
q.append(User, creator_of='node', project='email')
qb_res = q.all()
# total count
statistics["total"] = len(qb_res)
node_users = Counter([r[4] for r in qb_res])
statistics["users"] = {}
if isinstance(users, basestring):
users = [users]
if len(users) == 0:
users = node_users
for user in users:
user_data = [r for r in qb_res if r[4] == user]
# statistics for user data
statistics["users"][user] = count_statistics(user_data)
statistics["users"][user]["total"] = node_users[user]
# statistics for node data
statistics.update(count_statistics(qb_res))
return statistics
def get_creation_statistics(self, user_email=None):
"""
Return a dictionary with the statistics of node creation, summarized by day.
:note: Days when no nodes were created are not present in the returned `ctime_by_day` dictionary.
:param user_email: If None (default), return statistics for all users.
If an email is specified, return only the statistics for the given user.
:return: a dictionary as
follows::
{
"total": TOTAL_NUM_OF_NODES,
"types": {TYPESTRING1: count, TYPESTRING2: count, ...},
"ctime_by_day": {'YYYY-MMM-DD': count, ...}
where in `ctime_by_day` the key is a string in the format 'YYYY-MM-DD' and the value is
an integer with the number of nodes created that day.
"""
from aiida.orm.querybuilder import QueryBuilder as QB
from aiida.orm import User, Node
from collections import Counter
import datetime
def count_statistics(dataset):
def get_statistics_dict(dataset):
results = {}
for count, typestring in sorted(
(v, k) for k, v in dataset.iteritems())[::-1]:
results[typestring] = count
return results
count_dict = {}
types = Counter([r[2] for r in dataset])
count_dict["types"] = get_statistics_dict(types)
ctimelist = [r[1].strftime("%Y-%m-%d") for r in dataset]
ctime = Counter(ctimelist)
if len(ctimelist) > 0:
# For the way the string is formatted, we can just sort it alphabetically
firstdate = datetime.datetime.strptime(
sorted(ctimelist)[0], '%Y-%m-%d')
lastdate = datetime.datetime.strptime(
sorted(ctimelist)[-1], '%Y-%m-%d')
curdate = firstdate
outdata = {}
while curdate <= lastdate:
curdatestring = curdate.strftime('%Y-%m-%d')
outdata[curdatestring] = ctime.get(curdatestring, 0)
curdate += datetime.timedelta(days=1)
count_dict["ctime_by_day"] = outdata
else:
count_dict["ctime_by_day"] = {}
return count_dict
statistics = {}
q = QB()
q.append(Node, project=['id', 'ctime', 'type'], tag='node')
if user_email is not None:
q.append(User,
creator_of='node',
project='email',
filters={'email': user_email})
qb_res = q.all()
# total count
statistics["total"] = len(qb_res)
statistics.update(count_statistics(qb_res))
return statistics
def extract_structure_info(keys, structures=None):
"""
A method that collects a bunch of information (specified in keys) from
structures (default whole db, or provided node list) in the database and
returns that information as a dict, which could be used for further evalation
#keys = ['uuid', 'formula', 'pk', 'symmetry', 'pbc', 'volume', 'total_energy',
'child_nodes', 'natoms', 'group', extras', 'label', 'description', 'cif_file',
'cif_number', 'cif_uuid', 'cif_ref', 'calcfunctions', 'band', 'dos', 'eos',
'init_cls', 'corehole', primitive]
"""
StructureData = DataFactory('structure')
structure_list = []
from aiida_fleur.tools.StructureData_util import get_spacegroup, is_structure
from aiida_fleur.tools.StructureData_util import is_primitive
if not structures:
StructureData = DataFactory('structure')
#t = time.time()
qb = QB()
qb.append(StructureData)
structures = qb.all()
#elapsed = time.time() - t
# print "Total number of structures: {} (retrieved in {} s.)".format(len(structures), elapsed)
#t = time.time()
# for structure in structures:
# structure_dict = {}
# struc = structure[0]
# for key in keys:
# structure_dict[key] = get_methods(key)(struc)
# get information
for structure in structures:
structure_dict = {}
if isinstance(structure, list):
struc = structure[0]
else:
struc = is_structure(structure)
if 'formula' in keys:
structure_dict['formula'] = struc.get_formula()
if 'pk' in keys:
structure_dict['pk'] = struc.pk
if 'uuid' in keys:
structure_dict['uuid'] = str(struc.uuid)
if 'natoms' in keys:
structure_dict['natoms'] = len(struc.sites)
if 'cell' in keys:
structure_dict['cell'] = str(struc.cell)
if 'pbc' in keys:
structure_dict['pbc'] = str(struc.pbc)
if 'label' in keys:
structure_dict['label'] = struc.label
if 'description' in keys:
structure_dict['description'] = struc.description
if 'extras' in keys:
extras = struc.extras
structure_dict['extras'] = str(extras)
if 'symmetry' in keys:
symmetry = get_spacegroup(struc)
structure_dict['symmetry'] = str(symmetry)
if 'volume' in keys:
volume = struc.get_cell_volume()
structure_dict['volume'] = volume
if 'child_nodes' in keys:
child_nodes = len(struc.get_outgoing().all())
structure_dict['child_nodes'] = child_nodes
if 'primitive' in keys:
prim = is_primitive(struc)
structure_dict['primitive'] = prim
if 'cif_file' in keys:
cif_file = get_cif_file(struc)
structure_dict['cif_file'] = cif_file
'''
if 'cif_number' in keys:
cif_number = get_cif_number(struc)
structure_dict['cif_number'] = cif_number
if 'cif_uuid' in keys:
cif_uuid = get_cif_uuid(struc)
structure_dict['cif_uuid'] = cif_uuid
if 'cif_ref' in keys:
cif_ref = get_cif_ref(struc)
structure_dict['cif_ref'] = cif_ref
if 'total_energy' in keys:
total_energy = get_total_energy(struc)
structure_dict['total_energy'] = total_energy
'''
if 'group' in keys:
group = group_member(struc)
structure_dict['group'] = group
if 'scf' in keys:
scf = input_of_workcal('fleur_scf_wc', struc)
structure_dict['scf'] = scf
if 'band' in keys:
band = input_of_workcal('fleur_band_wc', struc)
structure_dict['band'] = band
if 'dos' in keys:
dos = input_of_workcal('fleur_dos_wc', struc)
structure_dict['dos'] = dos
if 'eos' in keys:
eos = input_of_workcal('fleur_eos_wc', struc)
structure_dict['eos'] = eos
if 'init_cls' in keys:
init_cls = input_of_workcal('fleur_initial_cls_wc', struc)
structure_dict['init_cls'] = init_cls
if 'corehole' in keys:
corehole = input_of_workcal('fleur_corehole_wc', struc)
structure_dict['corehole'] = corehole
if 'calcfunctions' in keys:
calcfunctions_uuid, calcfunctions_name = input_of_calcfunctions(
struc)
structure_dict['calcfunctions'] = [
calcfunctions_uuid, calcfunctions_name
]
structure_list.append(structure_dict)
#elapsed = time.time() - t
# print "(needed {} s.!!!)".format(elapsed)
return structure_list