Merge remote-tracking branch 'upstream/dev' into feat-adapter-nested

Author: vpratz

README.md

@@ -130,7 +130,7 @@ Many examples from [Bayesian Cognitive Modeling: A Practical Course](https://bay
 1. [Linear regression starter example](examples/Linear_Regression_Starter.ipynb)
 2. [From ABC to BayesFlow](examples/From_ABC_to_BayesFlow.ipynb)
 3. [Two moons starter example](examples/Two_Moons_Starter.ipynb)
-4. [Rapid iteration with point estimators](examples/Lotka_Volterra_Point_Estimation_and_Expert_Stats.ipynb)
+4. [Rapid iteration with point estimators](examples/Lotka_Volterra_Point_Estimation.ipynb)
 5. [SIR model with custom summary network](examples/SIR_Posterior_Estimation.ipynb)
 6. [Bayesian experimental design](examples/Bayesian_Experimental_Design.ipynb)
 7. [Simple model comparison example](examples/One_Sample_TTest.ipynb)

bayesflow/adapters/transforms/random_subsample.py

@@ -8,8 +8,10 @@ class RandomSubsample(ElementwiseTransform):
     """
     A transform that takes a random subsample of the data within an axis.
 
-    Example: adapter.random_subsample("x", sample_size = 3, axis = -1)
+    Examples
+    --------
 
+    >>> adapter = bf.Adapter().random_subsample("x", sample_size=3, axis=-1)
     """
 
     def __init__(
@@ -20,23 +22,22 @@ def __init__(
         super().__init__()
         if isinstance(sample_size, float):
             if sample_size <= 0 or sample_size >= 1:
-                ValueError("Sample size as a percentage must be a float between 0 and 1 exclusive. ")
+                raise ValueError("Sample size as a percentage must be a float between 0 and 1 exclusive. ")
         self.sample_size = sample_size
         self.axis = axis
 
     def forward(self, data: np.ndarray, **kwargs) -> np.ndarray:
-        axis = self.axis
-        max_sample_size = data.shape[axis]
+        max_sample_size = data.shape[self.axis]
 
         if isinstance(self.sample_size, int):
             sample_size = self.sample_size
         else:
             sample_size = np.round(self.sample_size * max_sample_size)
 
         # random sample without replacement
-        sample_indices = np.random.permutation(max_sample_size)[0 : sample_size - 1]
+        sample_indices = np.random.permutation(max_sample_size)[:sample_size]
 
-        return np.take(data, sample_indices, axis)
+        return np.take(data, sample_indices, self.axis)
 
     def inverse(self, data: np.ndarray, **kwargs) -> np.ndarray:
         # non invertible transform

bayesflow/adapters/transforms/standardize.py

@@ -1,4 +1,5 @@
 from collections.abc import Sequence
+import warnings
 
 import numpy as np
 
@@ -69,6 +70,14 @@ def __init__(
     ):
         super().__init__()
 
+        if mean is None or std is None:
+            warnings.warn(
+                "Dynamic standardization is deprecated and will be removed in later versions."
+                "Instead, use the standardize argument of the approximator / workflow instance or provide "
+                "fixed mean and std arguments. You may incur some redundant computations if you keep this transform.",
+                FutureWarning,
+            )
+
         self.mean = mean
         self.std = std
 

bayesflow/adapters/transforms/transform.py

@@ -22,6 +22,7 @@ def __repr__(self):
 
     @classmethod
     def from_config(cls, config: dict, custom_objects=None):
+        # noinspection PyArgumentList
         return cls(**deserialize(config, custom_objects=custom_objects))
 
     def get_config(self) -> dict:

bayesflow/approximators/approximator.py

@@ -11,18 +11,16 @@
 
 
 class Approximator(BackendApproximator):
-    def build(self, data_shapes: any) -> None:
-        mock_data = keras.tree.map_structure(keras.ops.zeros, data_shapes)
-        self.build_from_data(mock_data)
+    def build(self, data_shapes: dict[str, tuple[int] | dict[str, dict]]) -> None:
+        raise NotImplementedError
 
     @classmethod
     def build_adapter(cls, **kwargs) -> Adapter:
         # implemented by each respective architecture
         raise NotImplementedError
 
-    def build_from_data(self, data: dict[str, any]) -> None:
-        self.compute_metrics(**filter_kwargs(data, self.compute_metrics), stage="training")
-        self.built = True
+    def build_from_data(self, adapted_data: dict[str, any]) -> None:
+        raise NotImplementedError
 
     @classmethod
     def build_dataset(
@@ -61,6 +59,9 @@ def build_dataset(
             max_queue_size=max_queue_size,
         )
 
+    def call(self, *args, **kwargs):
+        return self.compute_metrics(*args, **kwargs)
+
     def fit(self, *, dataset: keras.utils.PyDataset = None, simulator: Simulator = None, **kwargs):
         """
         Trains the approximator on the provided dataset or on-demand data generated from the given simulator.
@@ -132,6 +133,7 @@ def fit(self, *, dataset: keras.utils.PyDataset = None, simulator: Simulator = N
             logging.info("Building on a test batch.")
             mock_data = dataset[0]
             mock_data = keras.tree.map_structure(keras.ops.convert_to_tensor, mock_data)
-            self.build_from_data(mock_data)
+            mock_data_shapes = keras.tree.map_structure(keras.ops.shape, mock_data)
+            self.build(mock_data_shapes)
 
         return super().fit(dataset=dataset, **kwargs)