def load_scaled_data(trainsize):
"""Load scaled snapshot data and the associated scaling factors.
Parameters
----------
trainsize : int
The number of snapshots of scaled data to load. See step1b.py.
Returns
-------
X : (NUM_ROMVARS*DOF,trainsize) ndarray
The lifted, scaled data.
time_domain : (trainsize) ndarray
The time domain corresponding to the lifted, scaled data.
scales : (NUM_ROMVARS,4) ndarray
The min/max factors used to scale the variables.
"""
# Locate the data.
data_path = _checkexists(config.scaled_data_path(trainsize))
# Extract the data.
with timed_block(f"Loading lifted, scaled snapshot data from {data_path}"):
with h5py.File(data_path, 'r') as hf:
# Check data shapes.
if hf["data"].shape != (config.NUM_ROMVARS*config.DOF, trainsize):
raise RuntimeError(f"data set 'data' has incorrect shape")
if hf["time"].shape != (trainsize,):
raise RuntimeError(f"data set 'time' has incorrect shape")
if hf["scales"].shape != (config.NUM_ROMVARS, 4):
raise RuntimeError(f"data set 'scales' has incorrect shape")
# Load and return the data.
return hf["data"][:,:], hf["time"][:], hf["scales"][:,:]
def scale_and_save_data(trainsize, lifted_data, time_domain):
"""Scale lifted snapshots (by variable) and save the scaled snapshots.
Parameters
----------
trainsize : int
Number of snapshots to scale and save.
lifted_data : (NUM_ROMVARS*DOF, k>trainsize) ndarray
Lifted snapshots to scale and then save.
time_domain : (k>trainsize,) ndarray
The time domain corresponding to the lifted snapshots.
"""
# Scale the learning variables to the bounds in config.SCALE_TO.
with utils.timed_block(f"Scaling {trainsize:d} lifted snapshots"):
scaled_data, scales = dproc.scale(lifted_data[:,:trainsize].copy())
# Save the lifted, scaled training data.
save_path = config.scaled_data_path(trainsize)
with utils.timed_block("Saving scaled, lifted training data"):
with h5py.File(save_path, 'w') as hf:
hf.create_dataset("data", data=scaled_data)
hf.create_dataset("time", data=time_domain[:trainsize])
hf.create_dataset("scales", data=scales)
logging.info(f"Scaled data saved as {save_path}.\n")
return scaled_data, scales
def scale_and_save_data(trainsize, lifted_data, time_domain, center=False):
"""Scale lifted snapshots (by variable) and save the scaled snapshots.
Parameters
----------
trainsize : int
Number of snapshots to scale and save.
lifted_data : (NUM_ROMVARS*DOF, k>trainsize) ndarray
Lifted snapshots to scale and then save.
time_domain : (k>trainsize,) ndarray
The time domain corresponding to the lifted snapshots.
center : bool
If True, center the scaled snapshots by the mean scaled snapshot
before computing the POD basis. Default False (no shift).
Returns
-------
training_data : (NUM_ROMVARS*DOF, trainsize) ndarray
Scaled, shifted snapshots to use as training data for the basis.
qbar : (NUM_ROMVARS*DOF,) ndarray
Mean snapshot of the scaled training data. All zeros if center=False.
scales : (NUM_ROMVARS,2) ndarray
Info on how the snapshot data was scaled.
"""
# Scale the learning variables to the bounds in config.SCALE_TO.
with utils.timed_block(f"Scaling {trainsize:d} lifted snapshots"):
training_data, scales = dproc.scale(lifted_data[:, :trainsize].copy())
# Shift the scaled data by the mean snapshot.
if center:
with utils.timed_block("Shifting scaled snapshots by mean"):
qbar = np.mean(training_data, axis=1) # Compute mean snapshot.
training_data -= qbar.reshape((-1, 1)) # Shift columns by mean.
else:
qbar = np.zeros(training_data.shape[0])
# Save the lifted, scaled training data.
save_path = config.scaled_data_path(trainsize)
with utils.timed_block("Saving scaled, lifted training data"):
with h5py.File(save_path, 'w') as hf:
hf.create_dataset("data", data=training_data)
hf.create_dataset("time", data=time_domain[:trainsize])
hf.create_dataset("mean", data=qbar)
hf.create_dataset("scales", data=scales)
logging.info(f"Processed data saved to {save_path}.\n")
return training_data, qbar, scales
def load_scaled_data(trainsize):
"""Load scaled snapshot data and the associated scaling factors.
Parameters
----------
trainsize : int
Number of snapshots of scaled data to load. See step2a_transform.py.
Returns
-------
Q : (NUM_ROMVARS*DOF,trainsize) ndarray
Lifted, scaled, shifted data.
time_domain : (trainsize) ndarray
Time domain corresponding to the lifted, scaled data.
qbar : (NUM_ROMVARS*DOF,) ndarray
Mean snapshot of the scaled training data.
scales : (NUM_ROMVARS,2) ndarray
Factors used to scale the variables.
"""
# Locate the data.
data_path = _checkexists(config.scaled_data_path(trainsize))
# Extract the data.
with timed_block(f"Loading lifted, scaled snapshot data from {data_path}"):
with h5py.File(data_path, 'r') as hf:
# Check data shapes.
if hf["data"].shape != (config.NUM_ROMVARS * config.DOF,
trainsize):
raise RuntimeError("data set 'data' has incorrect shape")
if hf["time"].shape != (trainsize, ):
raise RuntimeError("data set 'time' has incorrect shape")
if "mean" in hf:
if hf["mean"].shape != (hf["data"].shape[0], ):
raise RuntimeError("data set 'mean' has incorrect shape")
mean = hf["mean"][:]
else:
mean = np.zeros(hf["data"].shape[0])
if hf["scales"].shape != (config.NUM_ROMVARS, 2):
raise RuntimeError("data set 'scales' has incorrect shape")
# Load and return the data.
return (hf["data"][:, :], hf["time"][:], mean, hf["scales"][:, :])