transforms#
Classes
|
The .as_set(["x", "y"]) transform indicates that both x and y are treated as sets. |
The .as_time_series transform can be used to indicate that variables shall be treated as time series. |
|
|
Broadcasts arrays or scalars to the shape of a given other array. |
|
Concatenate multiple arrays into a new key. |
|
Constrains neural network predictions of a data variable to specified bounds. |
|
Default transform used to convert all floats from float64 to float32 to be in line with keras framework. |
|
Transform to drop variables from further calculation. |
Base class on which other transforms are based |
|
|
Expand the shape of an array. |
|
Implements a transform that applies a different transform on a subset of the data. |
|
Groups the given variables as a dictionary in the key into. |
|
Name the data parameters that should be kept for futher calculation. |
|
Log transforms a variable. |
|
Implements a transform that applies a set of elementwise transforms to a subset of the data as given by a mapping. |
|
Implements noisy neural posterior estimation (NNPE) as described in [1], which adds noise following a spike-and-slab distribution to the training data as a mild form of data augmentation to robustify against noisy real-world data (see [1, 2] for benchmarks). |
|
Replace NaNs with a default value, and optionally encode a missing-data mask as a separate output key. |
|
A class to apply element-wise transformations using plain NumPy functions. |
|
Changes data to be one-hot encoded. |
|
A transform that takes a random subsample of the data within an axis. |
|
Transform to rename keys in data dictionary. |
|
|
|
Transforms a parameter using a pair of registered serializable forward and inverse functions. |
|
|
|
This is the effective inverse of the |
|
Square-root transform a variable. |
|
Squeeze dimensions of an array. |
|
Transform that when applied standardizes data using typical z-score standardization i.e. for some unstandardized data x the standardized version z would be. |
|
A transform to reduce the dimensionality of arrays output by the summary network Example: adapter.take("x", np.arange(0,3), axis=-1) |
|
Checks provided data for any non-arrays and converts them to numpy arrays. |
|
Convert non-dict batches (e.g., pandas.DataFrame) to dict batches |
Base class on which other transforms are based |
|
|
Ungroups the the variables in key from a dictionary into individual entries. |