Merge pull request #138 from mir-group/feature/steven/hp_merge

WIP: Merge development since merge onto branch

flare/dft_interface/__init__.py

@@ -14,4 +14,4 @@
  from flare.dft_interface import vasp_util
  dft_software["vasp"]=vasp_util
 except ImportError:
- pass
+ pass

flare/dft_interface/qe_util.py

@@ -18,15 +18,15 @@
 
 name = "QE"
 
-def run_dft_par(dft_input, structure, dft_loc, ncpus=1, dft_out='pwscf.out',
+def run_dft_par(dft_input, structure, dft_loc, n_cpus=1, dft_out='pwscf.out',
  npool=None, mpi="mpi", **dft_kwargs):
  """run DFT calculation with given input template
- and atomic configurations. if ncpus == 1, it executes serial run.
+ and atomic configurations. if n_cpus == 1, it executes serial run.
 
  :param dft_input: input template file name
  :param structure: atomic configuration
  :param dft_loc: relative/absolute executable of the DFT code
- :param ncpus: # of CPU for mpi
+ :param n_cpus: # of CPU for mpi
  :param dft_out: output file name
  :param npool: not used
  :param mpi: not used
@@ -43,28 +43,28 @@ def run_dft_par(dft_input, structure, dft_loc, ncpus=1, dft_out='pwscf.out',
  dft_command = \
  f'{dft_loc} -nk {npool} -i {newfilename} > {dft_out}'
 
- if (ncpus > 1):
+ if (n_cpus > 1):
  if (mpi == "mpi"):
- dft_command = f'mpirun -np {ncpus} {dft_command}'
+ dft_command = f'mpirun -np {n_cpus} {dft_command}'
  else:
- dft_command = f'srun -n {ncpus} --mpi=pmi2 {dft_command}'
+ dft_command = f'srun -n {n_cpus} --mpi=pmi2 {dft_command}'
 
  call(dft_command, shell=True)
  os.remove(newfilename)
 
  return parse_dft_forces(dft_out)
 
 
-def run_dft_en_par(dft_input, structure, dft_loc, ncpus):
+def run_dft_en_par(dft_input, structure, dft_loc, n_cpus):
  """run DFT calculation with given input template
  and atomic configurations. This function is not used atm
 
- if ncpus == 1, it executes serial run.
+ if n_cpus == 1, it executes serial run.
 
  :param dft_input: input template file name
  :param structure: atomic configuration
  :param dft_loc: relative/absolute executable of the DFT code
- :param ncpus: # of CPU for mpi
+ :param n_cpus: # of CPU for mpi
  :param dft_out: output file name
  :param npool: not used
  :param mpi: not used
@@ -75,7 +75,7 @@ def run_dft_en_par(dft_input, structure, dft_loc, ncpus):
  run_qe_path = dft_input
  edit_dft_input_positions(run_qe_path, structure)
  qe_command = \
- 'mpirun -np {ncpus} {dft_loc} < {run_qe_path} > pwscf.out'
+ 'mpirun -np {n_cpus} {dft_loc} < {run_qe_path} > pwscf.out'
  call(qe_command, shell=True)
 
  forces, energy = parse_dft_forces_and_energy('pwscf.out')

flare/dft_interface/vasp_util.py

@@ -99,7 +99,7 @@ def run_dft(calc_dir: str, dft_loc: str,
 
 
 def run_dft_par(dft_input: str, structure: Structure,
- dft_command:str= None, ncpus=1,
+ dft_command:str= None, n_cpus=1,
  dft_out="vasprun.xml",
  parallel_prefix="mpi",
  mpi = None, npool = None,
@@ -112,9 +112,9 @@ def run_dft_par(dft_input: str, structure: Structure,
  ("Warning: No VASP Command passed, or stored in "
  "environment as VASP_COMMAND. ")
 
- if ncpus > 1:
+ if n_cpus > 1:
  if parallel_prefix == "mpi":
- dft_command = f'mpirun -np {ncpus} {dft_command}'
+ dft_command = f'mpirun -np {n_cpus} {dft_command}'
  else:
  serial_prefix = dft_kwargs.get('serial_prefix', '')
  dft_command = f'{serial_prefix} {dft_command}'

flare/gp.py

@@ -51,7 +51,7 @@ class GaussianProcess:
  hyperparameter optimization algorithm. Defaults to 10.
  par (bool, optional): If True, the covariance matrix K of the GP is
  computed in parallel. Defaults to False.
- ncpus (int, optional): Number of cpus used for parallel
+ n_cpus (int, optional): Number of cpus used for parallel
  calculations. Defaults to 1.
  output (Output, optional): Output object used to dump hyperparameters
  during optimization. Defaults to None.
@@ -66,7 +66,7 @@ def __init__(self, kernel: Callable,
  opt_algorithm: str = 'L-BFGS-B',
  maxiter: int = 10, par: bool = False, 
  per_atom_par: bool = True,
- ncpus: int = None, nsample: int = 100,
+ n_cpus: int = 1, nsample: int = 100,
  output: Output = None,
  multihyps: bool = False, hyps_mask: dict = None):
  """Initialize GP parameters and training data."""
@@ -89,7 +89,7 @@ def __init__(self, kernel: Callable,
  self.maxiter = maxiter
  self.par = par
  self.per_atom_par = per_atom_par
- self.ncpus = ncpus
+ self.n_cpus = n_cpus
  self.nsample = nsample
  self.output = output
 
@@ -245,7 +245,7 @@ def train(self, output=None, custom_bounds=None,
  args = (self.training_data, self.training_labels_np,
  self.kernel_grad, output, 
  self.cutoffs, self.hyps_mask,
- self.ncpus, self.nsample)
+ self.n_cpus, self.nsample)
  objective_func = get_neg_like_grad
  res = None
 
@@ -323,16 +323,16 @@ def predict(self, x_t: AtomicEnvironment, d: int) -> [float, float]:
 
  # Kernel vector allows for evaluation of At. Env.
  if (self.par and not self.per_atom_par):
- ncpus = self.ncpus
+ n_cpus = self.n_cpus
  else:
- ncpus = 1
+ n_cpus = 1
 
  k_v = get_kernel_vector_par(self.training_data, self.kernel,
  x_t, d,
  self.hyps,
  cutoffs=self.cutoffs,
  hyps_mask=self.hyps_mask,
- ncpus=self.ncpus,
+ n_cpus=self.n_cpus,
  nsample=self.nsample)
 
  # Guarantee that alpha is up to date with training set
@@ -479,7 +479,7 @@ def set_L_alpha(self):
  self.kernel,
  cutoffs=self.cutoffs,
  hyps_mask=self.hyps_mask,
- ncpus=self.ncpus,
+ n_cpus=self.n_cpus,
  nsample=self.nsample)
 
  l_mat = np.linalg.cholesky(ky_mat)
@@ -506,16 +506,16 @@ def update_L_alpha(self):
  return
 
  if (self.par and not self.per_atom_par):
- ncpus=self.ncpus
+ n_cpus=self.n_cpus
  else:
- ncpus=1
+ n_cpus=1
 
  ky_mat = get_ky_mat_update_par(self.ky_mat, self.hyps,
  self.training_data,
  self.kernel,
  cutoffs=self.cutoffs,
  hyps_mask=self.hyps_mask,
- ncpus=ncpus,
+ n_cpus=n_cpus,
  nsample=self.nsample)
 
  l_mat = np.linalg.cholesky(ky_mat)
@@ -585,7 +585,7 @@ def from_dict(dictionary):
  """Create GP object from dictionary representation."""
 
  if 'mc' in dictionary['kernel_name']:
- if (dictionary['multihyps'] is False):
+ if (dictionary.get('multihyps',False) is False):
  force_kernel, grad = \
  str_to_mc_kernel(dictionary['kernel_name'], include_grad=True)
  else:
@@ -615,11 +615,13 @@ def from_dict(dictionary):
  hyps=np.array(dictionary['hyps']),
  hyp_labels=dictionary['hyp_labels'],
  par=dictionary['par'],
- ncpus=dictionary['ncpus'],
+ per_atom_par=dictionary.get('per_atom_par',True),
+ n_cpus=dictionary.get('n_cpus') or dictionary.get('no_cpus'),
  maxiter=dictionary['maxiter'],
  opt_algorithm=dictionary['algo'],
- multihyps=dictionary['multihyps'],
- hyps_mask=dictionary['hyps_mask'])
+ multihyps=dictionary.get('multihyps',False),
+ hyps_mask=dictionary.get('hyps_mask',None)
+ )
 
  new_gp.training_data = [AtomicEnvironment.from_dict(env) for env in
  dictionary['training_data']]
@@ -688,3 +690,28 @@ def write_model(self, name: str, format: str = 'json'):
  if (len(self.training_data)>5000):
  self.ky_mat = np.load(f"{name}_ky_mat.npy")
  self.compute_matrices()
+
+
+ @staticmethod
+ def from_file(filename: str, format: str=''):
+ """
+ One-line convenience method to load a GP from a file stored using
+ write_file
+
+ Args:
+ filename (str): path to GP model
+ format (str): json or pickle if format is not in filename
+ :return:
+ """
+
+ if '.json' in filename or 'json' in format:
+ with open(filename, 'r') as f:
+ return GaussianProcess.from_dict(json.loads(f.readline()))
+
+ elif '.pickle' in filename or 'pickle' in format:
+ with open(filename, 'rb') as f:
+ return pickle.load(f)
+
+ else:
+ raise ValueError("Warning: Format unspecified or file is not "
+ ".json or .pickle format.")