def FixedFluxScan(self, reaction, lo, hi, n_p):
rv = DataSets.DataSet(ItemNames=[reaction, "ObjVal"])
lo = float(lo)
hi = float(hi)
inc = (hi - lo) / (n_p - 1)
cur = lo
for n in range(n_p):
self.SetFixedFlux({reaction: cur})
self.Solve(False)
sol = self.GetPrimSol()
if len(sol) == 0:
obval = float("NaN") # indicate fail
else:
obval = self.GetObjVal()
sol["ObjVal"] = obval
sol[reaction] = cur
rv.UpdateFromDic(sol)
cur += inc
return rv
if len(train_dirs) > 1:
for i in range(1, len(train_dirs)):
data.load_batch_set(train_dirs[i])
add = data.batch_set
for key in out:
out[key] = np.concatenate((out[key], add[key]))
return out
out_pd = pd.read_excel(
'/Users/jiedeng/GD/ppt/2020/extreme_filter4_with_state.xlsx')
deepmds = out_pd['local_path'].values
i = 8
data = DataSets(deepmds[i], 'set', shuffle_test=False)
train_data = get_train_data(data)
pca = PCA(n_components=2)
projected = pca.fit_transform(train_data['coord'])
print(projected.shape)
plt.scatter(projected[:, 0],
projected[:, 1],
c=digits.target,
edgecolor='none',
alpha=0.5,
cmap=plt.cm.get_cmap('spectral', 10))
plt.xlabel('component 1')
plt.ylabel('component 2')
def __init__(self,
systems,
set_prefix,
batch_size,
test_size,
rcut,
do_norm=False):
self.system_dirs = systems
self.nsystems = len(self.system_dirs)
self.batch_size = batch_size
if isinstance(self.batch_size, int):
self.batch_size = self.batch_size * np.ones(self.nsystems,
dtype=int)
assert (isinstance(self.batch_size, (list, np.ndarray)))
assert (len(self.batch_size) == self.nsystems)
self.data_systems = []
self.ntypes = []
self.natoms = []
self.natoms_vec = []
self.nbatches = []
self.ncopies = []
for ii in self.system_dirs:
self.data_systems.append(DataSets(ii, set_prefix, do_norm))
sys_all_types = np.loadtxt(os.path.join(ii,
"type.raw")).astype(int)
self.ntypes.append(np.max(sys_all_types) + 1)
self.sys_ntypes = max(self.ntypes)
for ii in range(self.nsystems):
self.natoms.append(self.data_systems[ii].get_natoms())
self.natoms_vec.append(self.data_systems[ii].get_natoms_vec(
self.sys_ntypes).astype(int))
self.nbatches.append(self.data_systems[ii].get_sys_numb_batch(
self.batch_size[ii]))
self.ncopies.append(self.data_systems[ii].get_ncopies())
# check the size of data if they satisfy the requirement of batch and test
for ii in range(self.nsystems):
chk_ret = self.data_systems[ii].check_batch_size(
self.batch_size[ii])
if chk_ret is not None:
raise RuntimeError(
" required batch size %d is larger than the size %d of the dataset %s"
% (self.batch_size[ii], chk_ret[1], chk_ret[0]))
chk_ret = self.data_systems[ii].check_test_size(test_size)
if chk_ret is not None:
raise RuntimeError(
" required test size %d is larger than the size %d of the dataset %s"
% (test_size, chk_ret[1], chk_ret[0]))
for ii in range(self.nsystems):
print(
"# find system %s :\t %6d atoms\t %10d batches copied by %s" %
(self.system_dirs[ii], self.natoms[ii], self.nbatches[ii],
self.ncopies[ii]))
self.prob_nbatches = self.nbatches / np.sum(self.nbatches)
self.test_prop_c = []
self.test_energy = []
self.test_force = []
self.test_virial = []
self.test_coord = []
self.test_box = []
self.test_type = []
self.default_mesh = []
for ii in range(self.nsystems):
test_prop_c, test_energy, test_force, test_virial, test_coord, test_box, test_type \
= self.data_systems[ii].get_test ()
self.test_prop_c.append(test_prop_c)
self.test_energy.append(test_energy)
self.test_force.append(test_force)
self.test_virial.append(test_virial)
self.test_coord.append(test_coord)
self.test_box.append(test_box)
self.test_type.append(test_type)
ncell = np.ones(3, dtype=np.int32)
cell_size = np.max(rcut)
avg_box = np.average(test_box, axis=0)
avg_box = np.reshape(avg_box, [3, 3])
for ii in range(3):
ncell[ii] = int(np.linalg.norm(avg_box[ii]) / cell_size)
if (ncell[ii] < 2): ncell[ii] = 2
default_mesh = np.zeros(6, dtype=np.int32)
default_mesh[3] = ncell[0]
default_mesh[4] = ncell[1]
default_mesh[5] = ncell[2]
self.default_mesh.append(default_mesh)
self.pick_idx = 0
def __init__(self,
systems,
set_prefix,
batch_size,
test_size,
rcut,
run_opt=None):
self.system_dirs = systems
self.nsystems = len(self.system_dirs)
self.batch_size = batch_size
if isinstance(self.batch_size, int):
self.batch_size = self.batch_size * np.ones(self.nsystems,
dtype=int)
assert (isinstance(self.batch_size, (list, np.ndarray)))
assert (len(self.batch_size) == self.nsystems)
self.data_systems = []
self.ntypes = []
self.natoms = []
self.natoms_vec = []
self.nbatches = []
for ii in self.system_dirs:
self.data_systems.append(DataSets(ii, set_prefix))
sys_all_types = np.loadtxt(os.path.join(ii,
"type.raw")).astype(int)
self.ntypes.append(np.max(sys_all_types) + 1)
self.sys_ntypes = max(self.ntypes)
type_map = []
for ii in range(self.nsystems):
self.natoms.append(self.data_systems[ii].get_natoms())
self.natoms_vec.append(self.data_systems[ii].get_natoms_vec(
self.sys_ntypes).astype(int))
self.nbatches.append(self.data_systems[ii].get_sys_numb_batch(
self.batch_size[ii]))
type_map.append(self.data_systems[ii].get_type_map())
self.type_map = self.check_type_map_consistency(type_map)
# check frame parameters
has_fparam = [ii.numb_fparam() for ii in self.data_systems]
for ii in has_fparam:
if ii != has_fparam[0]:
raise RuntimeError(
"if any system has frame parameter, then all systems should have the same number of frame parameter"
)
self.has_fparam = has_fparam[0]
# check the size of data if they satisfy the requirement of batch and test
for ii in range(self.nsystems):
chk_ret = self.data_systems[ii].check_batch_size(
self.batch_size[ii])
if chk_ret is not None:
raise RuntimeError ("system %s required batch size %d is larger than the size %d of the dataset %s" % \
(self.system_dirs[ii], self.batch_size[ii], chk_ret[1], chk_ret[0]))
chk_ret = self.data_systems[ii].check_test_size(test_size)
if chk_ret is not None:
print("WARNNING: system %s required test size %d is larger than the size %d of the dataset %s" % \
(self.system_dirs[ii], test_size, chk_ret[1], chk_ret[0]))
if run_opt is not None:
self.print_summary(run_opt)
self.prob_nbatches = [float(i)
for i in self.nbatches] / np.sum(self.nbatches)
self.test_data = collections.defaultdict(list)
self.default_mesh = []
for ii in range(self.nsystems):
test_system_data = self.data_systems[ii].get_test()
for nn in test_system_data:
self.test_data[nn].append(test_system_data[nn])
cell_size = np.max(rcut)
avg_box = np.average(test_system_data["box"], axis=0)
avg_box = np.reshape(avg_box, [3, 3])
ncell = (np.linalg.norm(avg_box, axis=1) / cell_size).astype(
np.int32)
ncell[ncell < 2] = 2
default_mesh = np.zeros(6, dtype=np.int32)
default_mesh[3:6] = ncell
self.default_mesh.append(default_mesh)
self.pick_idx = 0