def main(timeindices,
variables=None,
snaptype=["gems", "rom", "error"],
trainsize=None,
r=None,
reg=None):
"""Convert a snapshot in .h5 format to a .dat file that matches the format
of grid.dat. The new file is saved in `config.tecplot_path()` with the same
filename and the new file extension .dat.
Parameters
----------
timeindices : ndarray(int) or int
Indices (one-based) in the full time domain of the snapshots to save.
variables : str or list(str)
The variables to scale, a subset of config.ROM_VARIABLES.
Defaults to all variables.
snaptype : {"rom", "gems", "error"} or list(str)
Which kinds of snapshots to save. Options:
* "gems": snapshots from the full-order GEMS data;
* "rom": reconstructed snapshots produced by a ROM;
* "error": absolute error between the full-order data
and the reduced-order reconstruction.
If "rom" or "error" are selected, the ROM is selected by the
remaining arguments.
trainsize : int
Number of snapshots used to train the ROM.
r : int
Number of retained modes in the ROM.
reg : float
Regularization factor used to train the ROM.
"""
utils.reset_logger(trainsize)
# Parse parameters.
timeindices = np.sort(np.atleast_1d(timeindices))
simtime = timeindices.max()
t = utils.load_time_domain(simtime + 1)
# Parse the variables.
if variables is None:
variables = config.ROM_VARIABLES
elif isinstance(variables, str):
variables = [variables]
varnames = '\n'.join(f'"{v}"' for v in variables)
if isinstance(snaptype, str):
snaptype = [snaptype]
for stype in snaptype:
if stype not in ("gems", "rom", "error"):
raise ValueError(f"invalid snaptype '{stype}'")
# Read the grid file.
with utils.timed_block("Reading Tecplot grid data"):
# Parse the header.
grid_path = config.grid_data_path()
with open(grid_path, 'r') as infile:
grid = infile.read()
if int(re.findall(r"Elements=(\d+)", grid)[0]) != config.DOF:
raise RuntimeError(f"{grid_path} DOF and config.DOF do not match")
num_nodes = int(re.findall(r"Nodes=(\d+)", grid)[0])
end_of_header = re.findall(r"DT=.*?\n", grid)[0]
headersize = grid.find(end_of_header) + len(end_of_header)
# Extract geometry information.
grid_data = grid[headersize:].split()
x = grid_data[:num_nodes]
y = grid_data[num_nodes:2 * num_nodes]
cell_volume = grid_data[2 * num_nodes:3 * num_nodes]
connectivity = grid_data[3 * num_nodes:]
# Extract full-order data if needed.
if ("gems" in snaptype) or ("error" in snaptype):
gems_data, _ = utils.load_gems_data(cols=timeindices)
with utils.timed_block("Lifting selected snapshots of GEMS data"):
lifted_data = dproc.lift(gems_data)
true_snaps = np.concatenate(
[dproc.getvar(v, lifted_data) for v in variables])
# Simulate ROM if needed.
if ("rom" in snaptype) or ("error" in snaptype):
# Load the SVD data.
V, _ = utils.load_basis(trainsize, r)
# Load the initial conditions and scales.
X_, _, _, scales = utils.load_projected_data(trainsize, r)
# Load the appropriate ROM.
rom = utils.load_rom(trainsize, r, reg)
# Simulate the ROM over the time domain.
with utils.timed_block(f"Simulating ROM with r={r:d}, reg={reg:.0e}"):
x_rom = rom.predict(X_[:, 0], t, config.U, method="RK45")
if np.any(np.isnan(x_rom)) or x_rom.shape[1] < simtime:
raise ValueError("ROM unstable!")
# Reconstruct the results (only selected variables / snapshots).
with utils.timed_block("Reconstructing simulation results"):
x_rec = dproc.unscale(V[:, :r] @ x_rom[:, timeindices], scales)
x_rec = np.concatenate([dproc.getvar(v, x_rec) for v in variables])
dsets = {}
if "rom" in snaptype:
dsets["rom"] = x_rec
if "gems" in snaptype:
dsets["gems"] = true_snaps
if "error" in snaptype:
with utils.timed_block("Computing absolute error of reconstruction"):
abs_err = np.abs(true_snaps - x_rec)
dsets["error"] = abs_err
# Save each of the selected snapshots in Tecplot format matching grid.dat.
for j, tindex in enumerate(timeindices):
header = HEADER.format(varnames, tindex, t[tindex], num_nodes,
config.DOF,
len(variables) + 2, "SINGLE " * len(variables))
for label, dset in dsets.items():
if label == "gems":
save_path = config.gems_snapshot_path(tindex)
if label in ("rom", "error"):
folder = config.rom_snapshot_path(trainsize, r, reg)
save_path = os.path.join(folder, f"{label}_{tindex:05d}.dat")
with utils.timed_block(f"Writing {label} snapshot {tindex:05d}"):
with open(save_path, 'w') as outfile:
# Write the header.
outfile.write(header)
# Write the geometry data (x,y coordinates).
for i in range(0, len(x), NCOLS):
outfile.write(' '.join(x[i:i + NCOLS]) + '\n')
for i in range(0, len(y), NCOLS):
outfile.write(' '.join(y[i:i + NCOLS]) + '\n')
# Write the data for each variable.
for i in range(0, dset.shape[0], NCOLS):
row = ' '.join(f"{v:.9E}"
for v in dset[i:i + NCOLS, j])
outfile.write(row + '\n')
# Write connectivity information.
for i in range(0, len(connectivity), NCOLS):
outfile.write(' '.join(connectivity[i:i + NCOLS]) +
'\n')
def basis(trainsize, r, variables=None):
"""Export the POD basis vectors to Tecplot format.
Parameters
----------
trainsize : int
Number of snapshots used to compute the basis.
r : int
Number of basis vectors to save.
variables : str or list(str)
Variables to save, a subset of config.ROM_VARIABLES.
Defaults to all variables.
"""
utils.reset_logger(trainsize)
if variables is None:
variables = config.ROM_VARIABLES
elif isinstance(variables, str):
variables = [variables]
varnames = '\n'.join(f'"{v}"' for v in variables)
# Read the grid file.
with utils.timed_block("Reading Tecplot grid data"):
# Parse the header.
grid_path = config.grid_data_path()
with open(grid_path, 'r') as infile:
grid = infile.read()
if int(re.findall(r"Elements=(\d+)", grid)[0]) != config.DOF:
raise RuntimeError(f"{grid_path} DOF and config.DOF do not match")
num_nodes = int(re.findall(r"Nodes=(\d+)", grid)[0])
end_of_header = re.findall(r"DT=.*?\n", grid)[0]
headersize = grid.find(end_of_header) + len(end_of_header)
# Extract geometry information.
grid_data = grid[headersize:].split()
x = grid_data[:num_nodes]
y = grid_data[num_nodes:2 * num_nodes]
# cell_volume = grid_data[2*num_nodes:3*num_nodes]
connectivity = grid_data[3 * num_nodes:]
# Load the basis and extract desired variables.
V, _, _ = utils.load_basis(trainsize, r)
V = np.concatenate([dproc.getvar(var, V) for var in variables])
# Save each of the basis vectors in Tecplot format matching grid.dat.
for j in range(r):
header = HEADER.format(varnames, j, j, num_nodes, config.DOF,
len(variables) + 2, "DOUBLE " * len(variables))
save_folder = config._makefolder(config.tecplot_path(), "basis",
config.TRNFMT(trainsize))
save_path = os.path.join(save_folder, f"vec_{j+1:03d}.dat")
with utils.timed_block(f"Writing basis vector {j+1:d}"):
with open(save_path, 'w') as outfile:
# Write the header.
outfile.write(header)
# Write the geometry data (x,y coordinates).
for i in range(0, len(x), NCOLS):
outfile.write(' '.join(x[i:i + NCOLS]) + '\n')
for i in range(0, len(y), NCOLS):
outfile.write(' '.join(y[i:i + NCOLS]) + '\n')
# Write the data for each variable.
for i in range(0, V.shape[0], NCOLS):
row = ' '.join(f"{v:.9E}" for v in V[i:i + NCOLS, j])
outfile.write(row + '\n')
# Write connectivity information.
for i in range(0, len(connectivity), NCOLS):
outfile.write(' '.join(connectivity[i:i + NCOLS]) + '\n')
print(f"Basis info exported to {save_folder}/*.dat.")
def main(data_folder, overwrite=False, serial=False):
"""Extract snapshot data, in parallel, from the .tar files in the
specified folder of the form Data_<first-snapshot>to<last-snapshot>.tar.
Parameters
----------
data_folder : str
Path to the folder that contains the raw GEMS .tar data files,
preferably as an absolute path (e.g., /path/to/folder).
overwrite : bool
If False and the snapshot matrix file exists, raise an error.
If True, overwrite the existing snapshot matrix file if it exists.
serial : bool
If True, do the unpacking sequentially in 10,000 snapshot chunks.
If False, do the unpacking in parallel with 10,000 snapshot chunks.
"""
utils.reset_logger()
# If it exists, copy the grid file to the Tecplot data directory.
source = os.path.join(data_folder, config.GRID_FILE)
if os.path.isfile(source):
target = config.grid_data_path()
with utils.timed_block(f"Copying {source} to {target}"):
shutil.copy(source, target)
else:
logging.warning(f"Grid file {source} not found!")
# Locate and sort raw .tar files.
target_pattern = os.path.join(data_folder, "Data_*to*.tar")
tarfiles = sorted(glob.glob(target_pattern))
if not tarfiles:
raise FileNotFoundError(target_pattern)
# Get the snapshot indices corresponding to each file from the file names.
starts, stops = [], []
for i,tfile in enumerate(tarfiles):
matches = re.findall(r"Data_(\d+)to(\d+).tar", tfile)
if not matches:
raise ValueError(f"file {tfile} not named with convention "
"Data_<first-snapshot>to<last-snapshot>.tar")
start, stop = [int(d) for d in matches[0]]
if i == 0:
start0 = start # Offset
starts.append(start - start0)
stops.append(stop + 1 - start0)
if i > 0 and stops[i-1] != starts[i]:
raise ValueError(f"file {tfile} not continuous from previous set")
num_snapshots = stops[-1]
# Create an empty HDF5 file of appropriate size for the data.
save_path = config.gems_data_path()
if os.path.isfile(save_path) and not overwrite:
raise FileExistsError(f"{save_path} (use --overwrite to overwrite)")
with utils.timed_block("Initializing HDF5 file for data"):
with h5py.File(save_path, 'w') as hf:
hf.create_dataset("data", shape=(config.DOF*config.NUM_GEMSVARS,
num_snapshots),
dtype=np.float64)
hf.create_dataset("time", shape=(num_snapshots,),
dtype=np.float64)
logging.info(f"Data file initialized as {save_path}.")
# Read the files in chunks.
args = zip(tarfiles, starts, stops)
if serial: # Read the files serially (sequentially).
for tf, start, stop in args:
_read_tar_and_save_data(tf, start, stop, parallel=False)
else: # Read the files in parallel.
with mp.Pool(initializer=_globalize_lock, initargs=(mp.Lock(),),
processes=min([len(tarfiles), mp.cpu_count()])) as pool:
pool.starmap(_read_tar_and_save_data, args)
def temperature_average(trainsize, r, reg, cutoff=60000):
"""Get the average-in-time temperature profile for the GEMS data and a
specific ROM.
Parameters
----------
trainsize : int
Number of snapshots used to train the ROM.
r : int
Dimension of the ROM.
reg : float
Regularization hyperparameters used to train the ROM.
cutoff : int
Number of time steps to average over.
"""
utils.reset_logger(trainsize)
# Read the grid file.
with utils.timed_block("Reading Tecplot grid data"):
# Parse the header.
grid_path = config.grid_data_path()
with open(grid_path, 'r') as infile:
grid = infile.read()
if int(re.findall(r"Elements=(\d+)", grid)[0]) != config.DOF:
raise RuntimeError(f"{grid_path} DOF and config.DOF do not match")
num_nodes = int(re.findall(r"Nodes=(\d+)", grid)[0])
end_of_header = re.findall(r"DT=.*?\n", grid)[0]
headersize = grid.find(end_of_header) + len(end_of_header)
# Extract geometry information.
grid_data = grid[headersize:].split()
x = grid_data[:num_nodes]
y = grid_data[num_nodes:2 * num_nodes]
# cell_volume = grid_data[2*num_nodes:3*num_nodes]
connectivity = grid_data[3 * num_nodes:]
# Compute full-order time-averaged temperature from GEMS data.
_s = config.DOF * config.GEMS_VARIABLES.index("T")
gems_data, _ = utils.load_gems_data(rows=slice(_s, _s + config.DOF),
cols=cutoff)
with utils.timed_block("Computing time-averaged GEMS temperature"):
T_gems = gems_data.mean(axis=1)
assert T_gems.shape == (config.DOF, )
# Simulate ROM and compute the time-averaged temperature.
t, V, scales, q_rom = step4.simulate_rom(trainsize, r, reg, steps=cutoff)
with utils.timed_block("Reconstructing ROM simulation results"):
T_rom = dproc.unscale(dproc.getvar("T", V) @ q_rom, scales, "T")
T_rom = T_rom.mean(axis=1)
assert T_rom.shape == (config.DOF, )
header = HEADER.format('"T"', 0, 0, num_nodes, config.DOF, 3,
"DOUBLE " * 3)
header = header.replace("VARLOCATION=([3-3]", "VARLOCATION=([3]")
for label, dset in zip(["gems", "rom"], [T_gems, T_rom]):
if label == "gems":
save_path = os.path.join(config.tecplot_path(), "gems",
"temperature_average.dat")
elif label == "rom":
folder = config.rom_snapshot_path(trainsize, r, reg)
save_path = os.path.join(folder, "temperature_average.dat")
with utils.timed_block(f"Writing {label} temperature average"):
with open(save_path, 'w') as outfile:
# Write the header.
outfile.write(header)
# Write the geometry data (x,y coordinates).
for i in range(0, len(x), NCOLS):
outfile.write(' '.join(x[i:i + NCOLS]) + '\n')
for i in range(0, len(y), NCOLS):
outfile.write(' '.join(y[i:i + NCOLS]) + '\n')
# Write the data for each variable.
for i in range(0, dset.shape[0], NCOLS):
row = ' '.join(f"{v:.9E}" for v in dset[i:i + NCOLS])
outfile.write(row + '\n')
# Write connectivity information.
for i in range(0, len(connectivity), NCOLS):
outfile.write(' '.join(connectivity[i:i + NCOLS]) + '\n')