KeyError in analysis.feature_size_map
when use_variance=True
.
The problematic part might be the if use_variance else
part in line 821.
Build a VQPCA classifier for new observations based on the lowest reconstruction error associated with each of the k
local bases.
Kamila Zdybal (474d0b02) at 07 Mar 14:11
Added old installation instructions since they still work
Allow the user to continue training the QoIAwareProjection
class object for a specified number of epochs.
Kamila Zdybal (b4a64ca5) at 10 Feb 20:51
Documentation update
Add missing optional parameters in the example snippet in the documentation of variable selection algorithms: power
, vertical_shift
.
Done in this commit.
Kamila Zdybal (34cf08c4) at 10 Feb 20:43
Adding missing parameters in the example code documenting manifold-...
New functionality: allow for L2 norm over costs in:
analysis.cost_function_normalized_variance_derivative
utilities.manifold_informed_forward_variable_addition
utilities.manifold_informed_backward_variable_elimination
Kamila Zdybal (ae8275a3) at 10 Feb 20:35
.gitignore update
Support for L2 norms in the manifold-informed algorithms done in this commit.
Kamila Zdybal (19c8bbce) at 10 Feb 20:33
Allowing for L2 and normalized-L2 norms in the manifold-informed va...
L2 norm implemented in the analysis.cost_function_normalized_variance_derivative
in this commit.
Kamila Zdybal (16e4f511) at 10 Feb 20:28
Allowing for L2 and normalized-L2 norms over the individual costs
Add missing optional parameters in the example snippet in the documentation of variable selection algorithms: power
, vertical_shift
.
New functionality: allow for L2 norm over costs in:
analysis.cost_function_normalized_variance_derivative
utilities.manifold_informed_forward_variable_addition
utilities.manifold_informed_backward_variable_elimination
Kamila Zdybal (b3adf668) at 16 Dec 19:16
Tutorial update following the latest changes in the code
Kamila Zdybal (b1d03b88) at 14 Dec 18:36
Re-written test following the recent changes in the code
We should allow the user to instantiate QoIAwareProjection
object and set the weights and biases from a pre-trained model.
This should allow for continuing training.
Kamila Zdybal (fbfa3c93) at 14 Dec 17:56
Setting the intial value for best_epoch_counter, otherwise training...