def get_bridges(self):
res = []
if self.G.is_multigraph():
raise NotImplementedError("Multi Graph not supported.")
else:
for b in nx.bridges(self.G):
if self.G.edges[b].get('amount', 0) == 1:
res.append(b)
return res
if __name__ == '__main__':
from core.power import Power
path = 'D:/PSA_src/psa/localdata/0913/data'
fmt = 'on'
power = Power(fmt)
power.load_power(path, fmt=fmt, lp=False, st=False)
with timer("graph"):
graph1 = PowerGraph(power,
graph_type='single',
node_type='station',
on_only=True)
islands1 = graph1.get_islands(5)
graph2 = PowerGraph(power,
graph_type='multi',
node_type='bus',
on_only=False,
edge_columns=['x'])
islands2 = graph2.get_islands(10)
def set_index(self, types=None, idx='no'):
""" 设置表索引
:param types: list. 需要设置的设备类型。
:param idx: str, no or name. 按编号设置或按名称设置。
"""
if not types:
types = self.format_key['types']
if idx == 'no':
indices = self.index_dict
elif idx == 'name':
indices = name_index_dict()
else:
raise NotImplementedError
types = [t for t in types if t in indices.keys() and t in self.data.keys()]
for t in types:
self.data[t].set_index(indices[t], drop=False, inplace=True)
if __name__ == '__main__':
# set_format_version({'mdc': 2.3})
path = 'D:/PSA_src/psa/localdata/0913/data'
fmt = 'on'
path = 'D:/PSASP_Pro/2020国调年度/冬低731'
fmt = 'off'
power = Power(fmt)
with timer('Load power'):
power.load_power(path, fmt=fmt, lp=False, st=True, station=False)
with timer('Save power'):
power.save_power(path + '/out', lp=False, st=True, fmt=fmt)
dt_train_end=dt_train_end,
dt_test_begin=dt_test_begin,
dt_test_end=dt_test_end,
val_perc=0.1)
assert (0 in ids) and (1 in ids)
data_set.make_dataset_tensors(y_columns=y_columns, only_real=only_real)
train_data, train_labels, _ = data_set.get_dataset(0)
train_sample_size = train_labels.shape[0]
steps_per_epoch = train_sample_size // n_batch
val_data, val_labels, _ = data_set.get_dataset(1)
val_sample_size = val_labels.shape[0]
validation_steps = val_sample_size // n_batch
train_gen = data_set.dataset_generator_multi(train_data, train_labels, n_batch)
val_gen = data_set.dataset_generator_multi(val_data, val_labels, n_batch)
dt_run_start = datetime.datetime.now()
with timer("Timer training"):
history = net.train_model.fit_generator(train_gen,
epochs=n_epochs,
steps_per_epoch=steps_per_epoch,
validation_data=val_gen,
validation_steps=validation_steps)
test_labels, pre = dataset_predict(net.pre_model, data_set, role=2)
save_model(res_path, args.res_type, net.pre_model, suffix='pb')
# save_model(res_path, args.res_type, net.pre_model, suffix='json')
write_input(data_set, res_path + "/input.txt")
write_output(data_set.y.columns[y_columns], res_path + "/output.txt")
sys.exit(0)
net.pre_model.load_weights(res_path + "/" + args.res_type + ".h5")
dt_begin = datetime.datetime.strptime(args.dt_begin, "%Y_%m_%dT%H_%M_%S")
dt_end = datetime.datetime.strptime(args.dt_end, "%Y_%m_%dT%H_%M_%S") \
if max_idx >= len(subs):
abbr = name
else:
abbr = ''.join([subs[i] for i in name_info[k][1]])
fp.write(' '.join((abbr, name)) + '\n')
else:
fp.write('name\n')
fp.write('\n'.join(names) + '\n')
if __name__ == '__main__':
# '''
file_name = os.path.join(os.path.expanduser('~'), 'data', 'gd', 'E', 'gd_20200729_1300_new.QS')
# table_names = ['Grid', 'Station', 'Bus']
with timer('Read E File repeat'):
tables = read_efile(file_name)
# with timer('Read E File buffer'):
# tables = read_efile_buffer(file_name)
# '''
'''
path = 'D:/python/db/2019_09_12/2019_10_01T01_20_00/'
headers = {'CCTOUT': 'no desc name cct gen1 gen2 times tmp1 tmp2'}
update_table_header(path, 'res', headers)
'''
'''
e_file = os.path.join(os.path.expanduser('~'), 'data', 'bj', 'BJ_20200420_000000.QS')
out_file = os.path.join(os.path.expanduser('~'), 'data', 'bj', 'names.txt')
name_info = {'Substation': ('name', [1]),
def get_model_name(model_type, model_no):
model_type = model_type.lower()
if model_type == "avr":
if model_no in range(3, 11):
return 'avr310' if 'avr310' in datalib_columns else None
elif model_no in range(11, 13):
return 'avr1112' if 'avr1112' in datalib_columns else None
if model_type in datalib_columns:
return model_type
elif model_type + str(model_no) in datalib_columns:
return model_type + str(model_no)
return None
if __name__ == '__main__':
from core.power import Power
path = 'D:/PSASP_Pro/2020¹úµ÷Äê¶È/¶¬µÍ731'
fmt = 'off'
power = Power(fmt)
power.load_power(path, fmt=fmt, lp=False, st=True, station=True)
with timer('Load datalib'):
datalib = load_datalib(path+'/DATALIB.DAT')
iwant = [('gen', 3, 11),
('avr', 12, 18),
('gov', 7, 3),
('pss', 2, 7)]
for t, m, p in iwant:
name = get_model_name(t, m)
if name is not None:
print(datalib[name].loc[p])
RGG = rypb.loc[no_gen, no_gen]
gk = np.zeros((len(indices), len(no_gen)), dtype=np.float32)
for ii, idx in enumerate(indices):
if np.isin(idx, no_load):
gk[ii, :] = RDG.loc[idx]
elif np.isin(idx, no_gen):
gk[ii, :] = RGG.loc[idx]
else:
print(idx, "is slackbus")
gk = pd.DataFrame(gk, index=indices, columns=no_gen)
return gk
if __name__ == '__main__':
from core.power import Power
# path = '../dataset/wepri36'
# fmt = 'off'
path = 'C:/Users/sdy/data/db/SA_2'
fmt = 'on'
power = Power(fmt)
with timer('gsdf'):
power.load_power(path, fmt=fmt, lp=False, st=False)
# ed = calc_ed_from_power(power, island=0, node_type='bus', x_only=False)
# gkr = calc_gsdf(power, 0, {'acline':[29, 44]})
gkr = calc_gsdf(power, 0, {'acline': [ 10547, 10317, 10373, 11136],
'transformer': [51188]}, alpha= 'zwt', node_type='station')
vps = calc_vps(power, 0, {'bus': [878, 914]}, 'bus')
buffer = StringIO()
with open(os.path.join(root, f), 'r') as fp:
for line in fp:
buffer.write(line)
if line[0] == '<' and line[1] != '/':
table = line[1:line.index(':')]
if table in headers:
buffer.write('@ ' + headers[table] + '\n')
fp.readline()
with open(os.path.join(root, f), 'w') as fp:
buffer.seek(0)
for line in buffer:
fp.write(line)
i = i + 1
if i % 100 == 0:
print('\r%dfiles updated.' % i, end='')
if __name__ == '__main__':
file_name = 'D:/PSASP_Pro/2020¹úµ÷Äê¶È/¶¬µÍ731/DataMap.txt'
table_names = ['Grid', 'Station', 'Bus']
with timer('Read E File repeat'):
tables = read_efile(file_name)
with timer('Read E File buffer'):
tables = read_efile_buffer(file_name)
path = 'D:/python/db/2019_09_12/2019_10_01T01_20_00/'
headers = {'CCTOUT': 'no desc name cct gen1 gen2 times tmp1 tmp2'}
update_table_header(path, 'res', headers)
return res
if __name__ == '__main__':
path = 'D:/PSASP_Pro/online/package'
file_name = 'pack.h5'
fmt = 'on'
"""
with timer('Pack power'):
pack_data(path, os.path.join(path, file_name), fmt='on')
with timer('Get infos of package'):
model, data = get_package_info(os.path.join(path, file_name))
print(model, data)
dir = '2019_12_23T13_10_00'
with timer('Unpack power'):
unpack_data(os.path.join(path, 'out'),
os.path.join(path, file_name), fmt='on', dirs=[dir])
"""
path = 'D:/python/db/2019_09_12/data/'
iwant = {'generator': ['p', 'v'], 'station': ['pl', 'ql'], 'dcline': None}
for etype in iwant:
with timer('Collect data [%s] for [%s]' % (path, etype)):
data = collect_learning_data(path, etype, iwant[etype])
"""
path = 'D:/python/db/2019_09_12/data/'
iwant = {'CCTOUT': ['name', 'cct', 'times']}
collect_learning_res(path, iwant)
"""
def group_kmeans(ed, n):
assert isinstance(ed, pd.DataFrame) and ed.shape[0] == ed.shape[1]
kmeans = KMeans(n_clusters=n)
clf = kmeans.fit(ed.values)
groups = {}
for i in range(n):
groups[i] = ed.index[np.where(clf.labels_ == i)[0]].to_list()
return groups
if __name__ == '__main__':
from core.power import Power
path = 'D:/PSA_src/psa/localdata/0913/data'
fmt = 'on'
power = Power(fmt)
power.load_power(path, fmt=fmt, lp=False, st=False)
island = 0
with timer('Generate Y matrix'):
y = generate_y_matrix(power, island, node_type='station', x_only=False)
with timer('Calculate Z from Y'):
z = calc_z_from_y(y)
with timer('Calculate ED matrix'):
indices = power.stations.index[power.stations.island == island][:100].to_numpy()
ed = calc_ed_from_z(z, indices=indices)
# with timer('ED map to 2D by t-SNE'):
# x = ed_map_tsne(ed)
# with timer('Group by kmeans'):
# groups = group_kmeans(ed, 10)
