autoemulate 2.1.1__tar.gz → 2.1.2__tar.gz

{autoemulate-2.1.1 → autoemulate-2.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: autoemulate
-Version: 2.1.1
+Version: 2.1.2
 Summary: A python package for semi-automated emulation
 Author: AutoEmulate contributors (see our GitHub page)
 License-Expression: MIT
@@ -20,7 +20,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: matplotlib>=3.7.2
 Requires-Dist: seaborn>=0.12.2
-Requires-Dist: scikit-learn<1.6.0,>=1.3.0
+Requires-Dist: scikit-learn>=1.3.0
 Requires-Dist: pandas>=2.1
 Requires-Dist: torch>=2.1.0
 Requires-Dist: scipy>=1.11.3
@@ -36,7 +36,7 @@ Requires-Dist: anytree>=2.12.1
 Requires-Dist: torchmetrics>=1.7.1
 Requires-Dist: pyro-ppl>=1.9.1
 Requires-Dist: torchrbf>=0.0.1
-Requires-Dist: arviz>=0.21.0
+Requires-Dist: arviz<1.0,>=0.21.0
 Requires-Dist: getdist>=1.7.2
 Requires-Dist: einops>=0.8.1
 Requires-Dist: harmonic>=1.3.0
@@ -87,7 +87,7 @@ You can find the project documentation [here](https://alan-turing-institute.gith
 
 - The AutoEmulate project is run out of the [Alan Turing Institute](https://www.turing.ac.uk/).
 - Visit [autoemulate.com](https://www.autoemulate.com/) to learn more.
-- Feel free to reach out to us at [ai4physics@turing.ac.uk](mailto:ai4physics@turing.ac.uk) for queries about AutoEmulate or ideas for collaboration
+- Feel free to reach out to us at [aiphys@turing.ac.uk](mailto:aiphys@turing.ac.uk) for queries about AutoEmulate or ideas for collaboration.
 - We have also published a paper in [The Journal of Open Source Software](https://joss.theoj.org/papers/10.21105/joss.07626). 
 
   Please cite this paper if you use the package in your work:
@@ -137,14 +137,15 @@ You can find the project documentation [here](https://alan-turing-institute.gith
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/vchhabra-turing"><img src="https://avatars.githubusercontent.com/u/140401853?v=4?s=100" width="100px;" alt="vchhabra-turing"/><br /><sub><b>vchhabra-turing</b></sub></a><br /><a href="#ideas-vchhabra-turing" title="Ideas, Planning, & Feedback">🤔</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/era-23"><img src="https://avatars.githubusercontent.com/u/115151590?v=4?s=100" width="100px;" alt="Ethan Attwood"/><br /><sub><b>Ethan Attwood</b></sub></a><br /><a href="#bug-era-23" title="Bug reports">🐛</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/TheCSGuy25"><img src="https://avatars.githubusercontent.com/u/87066683?v=4?s=100" width="100px;" alt="__aar0n__.py"/><br /><sub><b>__aar0n__.py</b></sub></a><br /><a href="#code-TheCSGuy25" title="Code">💻</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/SyedHaider2084"><img src="https://avatars.githubusercontent.com/u/227389830?v=4?s=100" width="100px;" alt="SyedHaider2084"/><br /><sub><b>SyedHaider2084</b></sub></a><br /><a href="#code-SyedHaider2084" title="Code">💻</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/SyedHaider2084"><img src="https://avatars.githubusercontent.com/u/227389830?v=4?s=100" width="100px;" alt="SyedHaider2084"/><br /><sub><b>SyedHaider2084</b></sub></a><br /><a href="#code-SyedHaider2084" title="Code">💻</a> <a href="#doc-SyedHaider2084" title="Documentation">📖</a></td>
     </tr>
     <tr>
       <td align="center" valign="top" width="14.28%"><a href="https://www.linkedin.com/in/lcm98/"><img src="https://avatars.githubusercontent.com/u/102757707?v=4?s=100" width="100px;" alt="Loh Chun Mun"/><br /><sub><b>Loh Chun Mun</b></sub></a><br /><a href="#doc-cmsamaaa" title="Documentation">📖</a> <a href="#code-cmsamaaa" title="Code">💻</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/z7076"><img src="https://avatars.githubusercontent.com/u/69681924?v=4?s=100" width="100px;" alt="Jichen Zhang"/><br /><sub><b>Jichen Zhang</b></sub></a><br /><a href="#code-z7076" title="Code">💻</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/RemDelaporteMathurin"><img src="https://avatars.githubusercontent.com/u/40028739?v=4?s=100" width="100px;" alt="Rémi Delaporte-Mathurin"/><br /><sub><b>Rémi Delaporte-Mathurin</b></sub></a><br /><a href="#bug-RemDelaporteMathurin" title="Bug reports">🐛</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/z7076"><img src="https://avatars.githubusercontent.com/u/69681924?v=4?s=100" width="100px;" alt="Jichen Zhang"/><br /><sub><b>Jichen Zhang</b></sub></a><br /><a href="#code-z7076" title="Code">💻</a> <a href="#doc-z7076" title="Documentation">📖</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/RemDelaporteMathurin"><img src="https://avatars.githubusercontent.com/u/40028739?v=4?s=100" width="100px;" alt="Rémi Delaporte-Mathurin"/><br /><sub><b>Rémi Delaporte-Mathurin</b></sub></a><br /><a href="#bug-RemDelaporteMathurin" title="Bug reports">🐛</a> <a href="#doc-RemDelaporteMathurin" title="Documentation">📖</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/pmeier"><img src="https://avatars.githubusercontent.com/u/6849766?v=4?s=100" width="100px;" alt="Philip Meier"/><br /><sub><b>Philip Meier</b></sub></a><br /><a href="#bug-pmeier" title="Bug reports">🐛</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/penelopeysm"><img src="https://avatars.githubusercontent.com/u/122629585?v=4?s=100" width="100px;" alt="Penelope Yong"/><br /><sub><b>Penelope Yong</b></sub></a><br /><a href="#ideas-penelopeysm" title="Ideas, Planning, & Feedback">🤔</a> <a href="#review-penelopeysm" title="Reviewed Pull Requests">👀</a> <a href="#code-penelopeysm" title="Code">💻</a> <a href="#doc-penelopeysm" title="Documentation">📖</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/ykd007"><img src="https://avatars.githubusercontent.com/u/79036688?v=4?s=100" width="100px;" alt="Yash Dhawan"/><br /><sub><b>Yash Dhawan</b></sub></a><br /><a href="#doc-ykd007" title="Documentation">📖</a></td>
     </tr>
   </tbody>
 </table>

{autoemulate-2.1.1 → autoemulate-2.1.2}/README.md

@@ -19,7 +19,7 @@ You can find the project documentation [here](https://alan-turing-institute.gith
 
 - The AutoEmulate project is run out of the [Alan Turing Institute](https://www.turing.ac.uk/).
 - Visit [autoemulate.com](https://www.autoemulate.com/) to learn more.
-- Feel free to reach out to us at [ai4physics@turing.ac.uk](mailto:ai4physics@turing.ac.uk) for queries about AutoEmulate or ideas for collaboration
+- Feel free to reach out to us at [aiphys@turing.ac.uk](mailto:aiphys@turing.ac.uk) for queries about AutoEmulate or ideas for collaboration.
 - We have also published a paper in [The Journal of Open Source Software](https://joss.theoj.org/papers/10.21105/joss.07626). 
 
   Please cite this paper if you use the package in your work:
@@ -69,14 +69,15 @@ You can find the project documentation [here](https://alan-turing-institute.gith
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/vchhabra-turing"><img src="https://avatars.githubusercontent.com/u/140401853?v=4?s=100" width="100px;" alt="vchhabra-turing"/><br /><sub><b>vchhabra-turing</b></sub></a><br /><a href="#ideas-vchhabra-turing" title="Ideas, Planning, & Feedback">🤔</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/era-23"><img src="https://avatars.githubusercontent.com/u/115151590?v=4?s=100" width="100px;" alt="Ethan Attwood"/><br /><sub><b>Ethan Attwood</b></sub></a><br /><a href="#bug-era-23" title="Bug reports">🐛</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/TheCSGuy25"><img src="https://avatars.githubusercontent.com/u/87066683?v=4?s=100" width="100px;" alt="__aar0n__.py"/><br /><sub><b>__aar0n__.py</b></sub></a><br /><a href="#code-TheCSGuy25" title="Code">💻</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/SyedHaider2084"><img src="https://avatars.githubusercontent.com/u/227389830?v=4?s=100" width="100px;" alt="SyedHaider2084"/><br /><sub><b>SyedHaider2084</b></sub></a><br /><a href="#code-SyedHaider2084" title="Code">💻</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/SyedHaider2084"><img src="https://avatars.githubusercontent.com/u/227389830?v=4?s=100" width="100px;" alt="SyedHaider2084"/><br /><sub><b>SyedHaider2084</b></sub></a><br /><a href="#code-SyedHaider2084" title="Code">💻</a> <a href="#doc-SyedHaider2084" title="Documentation">📖</a></td>
     </tr>
     <tr>
       <td align="center" valign="top" width="14.28%"><a href="https://www.linkedin.com/in/lcm98/"><img src="https://avatars.githubusercontent.com/u/102757707?v=4?s=100" width="100px;" alt="Loh Chun Mun"/><br /><sub><b>Loh Chun Mun</b></sub></a><br /><a href="#doc-cmsamaaa" title="Documentation">📖</a> <a href="#code-cmsamaaa" title="Code">💻</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/z7076"><img src="https://avatars.githubusercontent.com/u/69681924?v=4?s=100" width="100px;" alt="Jichen Zhang"/><br /><sub><b>Jichen Zhang</b></sub></a><br /><a href="#code-z7076" title="Code">💻</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/RemDelaporteMathurin"><img src="https://avatars.githubusercontent.com/u/40028739?v=4?s=100" width="100px;" alt="Rémi Delaporte-Mathurin"/><br /><sub><b>Rémi Delaporte-Mathurin</b></sub></a><br /><a href="#bug-RemDelaporteMathurin" title="Bug reports">🐛</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/z7076"><img src="https://avatars.githubusercontent.com/u/69681924?v=4?s=100" width="100px;" alt="Jichen Zhang"/><br /><sub><b>Jichen Zhang</b></sub></a><br /><a href="#code-z7076" title="Code">💻</a> <a href="#doc-z7076" title="Documentation">📖</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/RemDelaporteMathurin"><img src="https://avatars.githubusercontent.com/u/40028739?v=4?s=100" width="100px;" alt="Rémi Delaporte-Mathurin"/><br /><sub><b>Rémi Delaporte-Mathurin</b></sub></a><br /><a href="#bug-RemDelaporteMathurin" title="Bug reports">🐛</a> <a href="#doc-RemDelaporteMathurin" title="Documentation">📖</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/pmeier"><img src="https://avatars.githubusercontent.com/u/6849766?v=4?s=100" width="100px;" alt="Philip Meier"/><br /><sub><b>Philip Meier</b></sub></a><br /><a href="#bug-pmeier" title="Bug reports">🐛</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/penelopeysm"><img src="https://avatars.githubusercontent.com/u/122629585?v=4?s=100" width="100px;" alt="Penelope Yong"/><br /><sub><b>Penelope Yong</b></sub></a><br /><a href="#ideas-penelopeysm" title="Ideas, Planning, & Feedback">🤔</a> <a href="#review-penelopeysm" title="Reviewed Pull Requests">👀</a> <a href="#code-penelopeysm" title="Code">💻</a> <a href="#doc-penelopeysm" title="Documentation">📖</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/ykd007"><img src="https://avatars.githubusercontent.com/u/79036688?v=4?s=100" width="100px;" alt="Yash Dhawan"/><br /><sub><b>Yash Dhawan</b></sub></a><br /><a href="#doc-ykd007" title="Documentation">📖</a></td>
     </tr>
   </tbody>
 </table>

autoemulate-2.1.2/autoemulate/learners/__init__.py

@@ -0,0 +1,8 @@
+from autoemulate.learners.base import Emulator
+
+from . import stream
+
+# from .base import Emulator, Simulator
+from .base import Simulator
+
+__all__ = ["Emulator", "Simulator", "stream"]

{autoemulate-2.1.1 → autoemulate-2.1.2}/autoemulate/transforms/base.py

@@ -613,16 +613,3 @@ def _is_affine_empirical(transform: Transform, x: TensorLike) -> bool:
     for _ in range(AFFINE_TRIALS):
         errs.append(_measure_affine_err(transform, test_input))  # type: ignore as Tensor input will transform to Tensor output
     return (sum(errs) / len(errs)) < AFFINE_TOL
-
-
-# TODO (#536): complete implementation
-# class AutoEmulateTransformModule(TransformModule):
-#     @abstractmethod
-#     def fit(self, x): ...
-#     def _inverse_gaussian(self, y: GaussianLike) -> GaussianLike:
-#         msg = "This method should be implemented in subclasses."
-#         raise NotImplementedError(msg)
-
-#     def _inverse_sample(self, y: GaussianLike, n_samples: int = 100) -> GaussianLike:
-#         msg = "This method should be implemented in subclasses."
-#         raise NotImplementedError(msg)

{autoemulate-2.1.1 → autoemulate-2.1.2}/autoemulate.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: autoemulate
-Version: 2.1.1
+Version: 2.1.2
 Summary: A python package for semi-automated emulation
 Author: AutoEmulate contributors (see our GitHub page)
 License-Expression: MIT
@@ -20,7 +20,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: matplotlib>=3.7.2
 Requires-Dist: seaborn>=0.12.2
-Requires-Dist: scikit-learn<1.6.0,>=1.3.0
+Requires-Dist: scikit-learn>=1.3.0
 Requires-Dist: pandas>=2.1
 Requires-Dist: torch>=2.1.0
 Requires-Dist: scipy>=1.11.3
@@ -36,7 +36,7 @@ Requires-Dist: anytree>=2.12.1
 Requires-Dist: torchmetrics>=1.7.1
 Requires-Dist: pyro-ppl>=1.9.1
 Requires-Dist: torchrbf>=0.0.1
-Requires-Dist: arviz>=0.21.0
+Requires-Dist: arviz<1.0,>=0.21.0
 Requires-Dist: getdist>=1.7.2
 Requires-Dist: einops>=0.8.1
 Requires-Dist: harmonic>=1.3.0
@@ -87,7 +87,7 @@ You can find the project documentation [here](https://alan-turing-institute.gith
 
 - The AutoEmulate project is run out of the [Alan Turing Institute](https://www.turing.ac.uk/).
 - Visit [autoemulate.com](https://www.autoemulate.com/) to learn more.
-- Feel free to reach out to us at [ai4physics@turing.ac.uk](mailto:ai4physics@turing.ac.uk) for queries about AutoEmulate or ideas for collaboration
+- Feel free to reach out to us at [aiphys@turing.ac.uk](mailto:aiphys@turing.ac.uk) for queries about AutoEmulate or ideas for collaboration.
 - We have also published a paper in [The Journal of Open Source Software](https://joss.theoj.org/papers/10.21105/joss.07626). 
 
   Please cite this paper if you use the package in your work:
@@ -137,14 +137,15 @@ You can find the project documentation [here](https://alan-turing-institute.gith
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/vchhabra-turing"><img src="https://avatars.githubusercontent.com/u/140401853?v=4?s=100" width="100px;" alt="vchhabra-turing"/><br /><sub><b>vchhabra-turing</b></sub></a><br /><a href="#ideas-vchhabra-turing" title="Ideas, Planning, & Feedback">🤔</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/era-23"><img src="https://avatars.githubusercontent.com/u/115151590?v=4?s=100" width="100px;" alt="Ethan Attwood"/><br /><sub><b>Ethan Attwood</b></sub></a><br /><a href="#bug-era-23" title="Bug reports">🐛</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/TheCSGuy25"><img src="https://avatars.githubusercontent.com/u/87066683?v=4?s=100" width="100px;" alt="__aar0n__.py"/><br /><sub><b>__aar0n__.py</b></sub></a><br /><a href="#code-TheCSGuy25" title="Code">💻</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/SyedHaider2084"><img src="https://avatars.githubusercontent.com/u/227389830?v=4?s=100" width="100px;" alt="SyedHaider2084"/><br /><sub><b>SyedHaider2084</b></sub></a><br /><a href="#code-SyedHaider2084" title="Code">💻</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/SyedHaider2084"><img src="https://avatars.githubusercontent.com/u/227389830?v=4?s=100" width="100px;" alt="SyedHaider2084"/><br /><sub><b>SyedHaider2084</b></sub></a><br /><a href="#code-SyedHaider2084" title="Code">💻</a> <a href="#doc-SyedHaider2084" title="Documentation">📖</a></td>
     </tr>
     <tr>
       <td align="center" valign="top" width="14.28%"><a href="https://www.linkedin.com/in/lcm98/"><img src="https://avatars.githubusercontent.com/u/102757707?v=4?s=100" width="100px;" alt="Loh Chun Mun"/><br /><sub><b>Loh Chun Mun</b></sub></a><br /><a href="#doc-cmsamaaa" title="Documentation">📖</a> <a href="#code-cmsamaaa" title="Code">💻</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/z7076"><img src="https://avatars.githubusercontent.com/u/69681924?v=4?s=100" width="100px;" alt="Jichen Zhang"/><br /><sub><b>Jichen Zhang</b></sub></a><br /><a href="#code-z7076" title="Code">💻</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/RemDelaporteMathurin"><img src="https://avatars.githubusercontent.com/u/40028739?v=4?s=100" width="100px;" alt="Rémi Delaporte-Mathurin"/><br /><sub><b>Rémi Delaporte-Mathurin</b></sub></a><br /><a href="#bug-RemDelaporteMathurin" title="Bug reports">🐛</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/z7076"><img src="https://avatars.githubusercontent.com/u/69681924?v=4?s=100" width="100px;" alt="Jichen Zhang"/><br /><sub><b>Jichen Zhang</b></sub></a><br /><a href="#code-z7076" title="Code">💻</a> <a href="#doc-z7076" title="Documentation">📖</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/RemDelaporteMathurin"><img src="https://avatars.githubusercontent.com/u/40028739?v=4?s=100" width="100px;" alt="Rémi Delaporte-Mathurin"/><br /><sub><b>Rémi Delaporte-Mathurin</b></sub></a><br /><a href="#bug-RemDelaporteMathurin" title="Bug reports">🐛</a> <a href="#doc-RemDelaporteMathurin" title="Documentation">📖</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/pmeier"><img src="https://avatars.githubusercontent.com/u/6849766?v=4?s=100" width="100px;" alt="Philip Meier"/><br /><sub><b>Philip Meier</b></sub></a><br /><a href="#bug-pmeier" title="Bug reports">🐛</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/penelopeysm"><img src="https://avatars.githubusercontent.com/u/122629585?v=4?s=100" width="100px;" alt="Penelope Yong"/><br /><sub><b>Penelope Yong</b></sub></a><br /><a href="#ideas-penelopeysm" title="Ideas, Planning, & Feedback">🤔</a> <a href="#review-penelopeysm" title="Reviewed Pull Requests">👀</a> <a href="#code-penelopeysm" title="Code">💻</a> <a href="#doc-penelopeysm" title="Documentation">📖</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/ykd007"><img src="https://avatars.githubusercontent.com/u/79036688?v=4?s=100" width="100px;" alt="Yash Dhawan"/><br /><sub><b>Yash Dhawan</b></sub></a><br /><a href="#doc-ykd007" title="Documentation">📖</a></td>
     </tr>
   </tbody>
 </table>

{autoemulate-2.1.1 → autoemulate-2.1.2}/autoemulate.egg-info/SOURCES.txt

@@ -95,12 +95,8 @@ autoemulate/emulators/transformed/__init__.py
 autoemulate/emulators/transformed/base.py
 autoemulate/emulators/transformed/delta_method.py
 autoemulate/experimental/data/gaussian.py
-autoemulate/experimental/data/spatiotemporal_dataset.py
-autoemulate/experimental/emulators/fno.py
-autoemulate/experimental/emulators/spatiotemporal.py
 autoemulate/experimental/emulators/nn/gaussian_mlp.py
 autoemulate/experimental/emulators/nn/zoib.py
-autoemulate/experimental/neural_processes/conditional_neural_process.py
 autoemulate/feature_generation/polynomial_features.py
 autoemulate/learners/__init__.py
 autoemulate/learners/base.py

{autoemulate-2.1.1 → autoemulate-2.1.2}/autoemulate.egg-info/requires.txt

@@ -1,6 +1,6 @@
 matplotlib>=3.7.2
 seaborn>=0.12.2
-scikit-learn<1.6.0,>=1.3.0
+scikit-learn>=1.3.0
 pandas>=2.1
 torch>=2.1.0
 scipy>=1.11.3
@@ -16,7 +16,7 @@ anytree>=2.12.1
 torchmetrics>=1.7.1
 pyro-ppl>=1.9.1
 torchrbf>=0.0.1
-arviz>=0.21.0
+arviz<1.0,>=0.21.0
 getdist>=1.7.2
 einops>=0.8.1
 harmonic>=1.3.0

{autoemulate-2.1.1 → autoemulate-2.1.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "autoemulate"
-version = "2.1.1"
+version = "2.1.2"
 description = "A python package for semi-automated emulation"
 license = "MIT"
 authors = [{ name = "AutoEmulate contributors (see our GitHub page)" }]
@@ -18,7 +18,7 @@ classifiers = [
 dependencies = [
     "matplotlib>=3.7.2",
     "seaborn>=0.12.2",
-    "scikit-learn>=1.3.0,<1.6.0",
+    "scikit-learn>=1.3.0",
     "pandas>=2.1",
     "torch>=2.1.0",
     "scipy>=1.11.3",
@@ -34,7 +34,7 @@ dependencies = [
     "torchmetrics>=1.7.1",
     "pyro-ppl>=1.9.1",
     "torchrbf>=0.0.1",
-    "arviz>=0.21.0",
+    "arviz>=0.21.0,<1.0",
     "getdist>=1.7.2",
     "einops>=0.8.1",
     "harmonic>=1.3.0",
@@ -125,6 +125,10 @@ filterwarnings = [
     "ignore:jax\\.interpreters\\.xla\\.pytype_aval_mappings is deprecated\\..*:DeprecationWarning:tensorflow_probability\\.python\\.internal\\.backend\\.jax\\.ops",
     # PyTorch MPS backend capability fallbacks are backend noise in tests.
     "ignore:The operator .* is not currently supported on the MPS backend.*:UserWarning",
+    # LightGBM automatically adds feature names to training data, which causes warnings when
+    # making predictions with unnamed data
+    # https://github.com/lightgbm-org/LightGBM/issues/6798
+    "ignore:X does not have valid feature names, but LGBMRegressor was fitted with feature names:UserWarning",
 ]
 
 [tool.pyright]

autoemulate-2.1.1/autoemulate/experimental/data/spatiotemporal_dataset.py

@@ -1,160 +0,0 @@
-import h5py
-import torch
-from autoemulate.core.types import TensorLike
-from torch.utils.data import Dataset
-
-
-class AutoEmulateDataset(Dataset):
-    """A class for spatio-temporal datasets."""
-
-    def __init__(
-        self,
-        data_path: str | None,
-        data: dict | None = None,
-        n_steps_input: int = 1,
-        n_steps_output: int = 1,
-        stride: int = 1,
-        # TODO: support for passing data from dict
-        input_channel_idxs: tuple[int, ...] | None = None,
-        output_channel_idxs: tuple[int, ...] | None = None,
-        dtype: torch.dtype = torch.float32,
-    ):
-        """
-        Initialize the dataset.
-
-        Parameters
-        ----------
-        data_path: str
-            Path to the HDF5 file containing the dataset.
-        n_steps_input: int
-            Number of input time steps.
-        n_steps_output: int
-            Number of output time steps.
-        stride: int
-            Stride for sampling the data.
-        data: dict | None
-            Preloaded data. Defaults to None.
-        input_channel_idxs: tuple[int, ...] | None
-            Indices of input channels to use. Defaults to None.
-        output_channel_idxs: tuple[int, ...] | None
-            Indices of output channels to use. Defaults to None.
-        dtype: torch.dtype
-            Data type for tensors. Defaults to torch.float32.
-        """
-        self.dtype = dtype
-        self.n_steps_input = n_steps_input
-        self.n_steps_output = n_steps_output
-        self.stride = stride
-        self.input_channel_idxs = input_channel_idxs
-        self.output_channel_idxs = output_channel_idxs
-
-        # Read or parse data
-        self.read_data(data_path) if data_path is not None else self.parse_data(data)
-
-        # Destructured here
-        (
-            self.n_trajectories,
-            self.n_timesteps,
-            self.width,
-            self.height,
-            self.n_channels,
-        ) = self.data.shape
-
-        # Pre-compute all subtrajectories for efficient indexing
-        self.all_input_fields = []
-        self.all_output_fields = []
-        self.all_constant_scalars = []
-
-        for traj_idx in range(self.n_trajectories):
-            # Create subtrajectories for this trajectory
-            fields = (
-                self.data[traj_idx]
-                .unfold(0, self.n_steps_input + self.n_steps_output, self.stride)
-                .permute(0, -1, 1, 2, 3)  # [num_subtrajectories, T_in + T_out, W, H, C]
-            )
-
-            # Split into input and output
-            input_fields = fields[
-                :, : self.n_steps_input, ...
-            ]  # [num_subtrajectories, T_in, W, H, C]
-            output_fields = fields[
-                :, self.n_steps_input :, ...
-            ]  # [num_subtrajectories, T_out, W, H, C]
-
-            # Store each subtrajectory separately
-            for sub_idx in range(input_fields.shape[0]):
-                self.all_input_fields.append(
-                    input_fields[sub_idx].to(self.dtype)
-                )  # [T_in, W, H, C]
-                self.all_output_fields.append(
-                    output_fields[sub_idx].to(self.dtype)
-                )  # [T_out, W, H, C]
-
-                # Handle constant scalars
-                if self.constant_scalars is not None:
-                    self.all_constant_scalars.append(
-                        self.constant_scalars[traj_idx].to(self.dtype)
-                    )
-                else:
-                    self.all_constant_scalars.append(torch.tensor([]))
-
-        print(f"Created {len(self.all_input_fields)} subtrajectory samples")
-        print(f"Each input sample shape: {self.all_input_fields[0].shape}")
-        print(f"Each output sample shape: {self.all_output_fields[0].shape}")
-        print(f"Data type: {self.all_input_fields[0].dtype}")
-
-    def read_data(self, data_path: str):
-        """Read data.
-
-        By default assumes HDF5 format in `data_path` with correct shape and fields.
-        """
-        # TODO: support passing as dict
-        # Load data
-        self.data_path = data_path
-        with h5py.File(self.data_path, "r") as f:
-            assert "data" in f, "HDF5 file must contain 'data' dataset"
-            self.data: TensorLike = torch.Tensor(f["data"][:]).to(self.dtype)  # type: ignore # [N, T, W, H, C]  # noqa: PGH003
-        print(f"Loaded data shape: {self.data.shape}")
-        # TODO: add the constant scalars
-        self.constant_scalars = (
-            torch.Tensor(f["constant_scalars"][:]).to(self.dtype)  # type: ignore  # noqa: PGH003
-            if "constant_scalars" in f
-            else None
-        )  # [N, C]
-        # TODO: add the constant fields
-        # self.constant_fields = torch.Tensor(f['data'][:])  # [N, W, H, C]
-
-    def parse_data(self, data: dict | None):
-        """Parse data from a dictionary."""
-        if data is not None:
-            self.data = (
-                data["data"].to(self.dtype)
-                if torch.is_tensor(data["data"])
-                else torch.tensor(data["data"], dtype=self.dtype)
-            )
-            self.constant_scalars = data.get("constant_scalars", None)
-            self.constant_fields = data.get("constant_fields", None)
-            return
-        msg = "No data provided to parse."
-        raise ValueError(msg)
-
-    def __len__(self):  # noqa: D105
-        return len(self.all_input_fields)
-
-    def __getitem__(self, idx):  # noqa: D105
-        return {
-            "input_fields": self.all_input_fields[idx],
-            "output_fields": self.all_output_fields[idx],
-            "constant_scalars": self.all_constant_scalars[idx],
-            # TODO: add this
-            # "constant_fields": self.all_constant_fields[idx],
-        }
-
-
-class MHDDataset(AutoEmulateDataset):
-    """PyTorch Dataset for MHD data."""
-
-    def __init__(self, data_path: str, t_in: int = 5, t_out: int = 10, stride: int = 1):
-        super().__init__(
-            data_path, n_steps_input=t_in, n_steps_output=t_out, stride=stride
-        )

autoemulate-2.1.1/autoemulate/experimental/emulators/fno.py

@@ -1,100 +0,0 @@
-import torch
-from autoemulate.core.types import OutputLike, TensorLike
-from autoemulate.experimental.emulators.spatiotemporal import SpatioTemporalEmulator
-from neuralop.models import FNO
-from torch.utils.data import DataLoader
-
-
-def prepare_batch(sample, channels=(0,), with_constants=True, with_time=False):
-    """Prepare a batch of input and output data."""
-    # Get input fields, constant scalars and output fields
-    x = sample["input_fields"][
-        :, :, :, :, channels
-    ]  # [batch, time, height, width, len(channels)]
-    constant_scalars = sample["constant_scalars"]  # [batch, n_constants]
-    y = sample["output_fields"][
-        :, :, :, :, channels
-    ]  # [batch, time, height, width, len(channels)]
-
-    # Permute both x and y
-    x = x.permute(0, 4, 1, 2, 3)  # [batch, len(channels), time, height, width]
-    y = y.permute(0, 4, 1, 2, 3)  # [batch, len(channels), time, height, width]
-
-    # Only add constants to input, not output
-    if with_constants:
-        # Assign spatio-temporal dims to constants
-        time_window, height, width = x.shape[2], x.shape[3], x.shape[4]
-        n_constants = constant_scalars.shape[-1]
-
-        # Add spatio-temporal dims to constants
-        c_broadcast = constant_scalars.reshape(1, n_constants, 1, 1, 1).expand(
-            1, n_constants, time_window, height, width
-        )
-
-        # Concatenate along channel dimension
-        x = torch.cat([x, c_broadcast], dim=1)
-
-    if not with_time:
-        # Take last time step for both input and output
-        return x[:, :, -1, :, :], y[:, :, -1, :, :]
-    # Otherwise include time
-    return x, y
-
-
-class FNOEmulator(SpatioTemporalEmulator):
-    """An FNO emulator."""
-
-    def __init__(
-        self, x=None, y=None, channels: tuple[int, ...] = (0,), *args, **kwargs
-    ):
-        _, _ = x, y  # Unused
-        # Ensure parent initialisers run before creating nn.Module attributes
-        super().__init__()
-        self.model = FNO(**kwargs)
-        self.channels = channels
-        self.optimizer = torch.optim.Adam(self.model.parameters())
-
-    @staticmethod
-    def is_multioutput() -> bool:  # noqa: D102
-        return True
-
-    def _fit(self, x: TensorLike | DataLoader, y: TensorLike | None = None):
-        assert isinstance(x, DataLoader), "x currently must be a DataLoader"
-        assert y is None, "y currently must be None"
-
-        for idx, batch in enumerate(x):
-            # Prepare input with constants
-            x, y = prepare_batch(
-                batch, channels=self.channels, with_constants=True, with_time=True
-            )  # type: ignore  # noqa: PGH003
-
-            # Predictions
-            y_pred = self.model(x)
-
-            # Get loss
-            # Take the first time idx as the next time step prediction
-            loss = self.loss_fn(y_pred[:, :, :1, ...], y)
-
-            loss.backward()
-            self.optimizer.step()
-            self.optimizer.zero_grad()
-
-            print(f"sample {idx:5d}, loss: {loss.item():.5e}")
-
-    def forward(self, x: TensorLike):
-        """Forward pass."""
-        return self.model(x)
-
-    def _predict(self, x: TensorLike | DataLoader, with_grad: bool) -> OutputLike:
-        assert isinstance(x, DataLoader), "x currently must be a DataLoader"
-        with torch.set_grad_enabled(with_grad):
-            channels = (0,)  # Which channel to use
-            all_preds = []
-            for _, batch in enumerate(x):
-                # Prepare input with constants
-                x, _ = prepare_batch(
-                    batch, channels=channels, with_constants=True, with_time=True
-                )
-                out = self(x)
-                all_preds.append(out)
-            return torch.cat(all_preds)

autoemulate-2.1.1/autoemulate/experimental/emulators/spatiotemporal.py

@@ -1,98 +0,0 @@
-from abc import abstractmethod
-
-import torch
-from autoemulate.core.types import OutputLike, TensorLike
-from autoemulate.emulators.base import PyTorchBackend
-from torch.utils.data import DataLoader
-
-
-class SpatioTemporalEmulator(PyTorchBackend):
-    """A spatio-temporal backend for emulators."""
-
-    channels: tuple[int, ...]
-
-    def fit(self, x: TensorLike | DataLoader, y: TensorLike | None = None):
-        """Train a spatio-temporal emulator.
-
-        Parameters
-        ----------
-        x: TensorLike | DataLoader
-            Input features as `TensorLike` or `DataLoader`.
-        y: OutputLike | None
-            Target values (not needed if x is a DataLoader).
-
-        """
-        if isinstance(x, TensorLike) and isinstance(y, TensorLike):
-            return super().fit(x, y)
-        if isinstance(x, DataLoader) and y is None:
-            return self._fit(x, y)
-        msg = "Invalid input types. Expected pair of TensorLike or DataLoader only."
-        raise RuntimeError(msg)
-
-    @abstractmethod
-    def _fit(self, x: TensorLike | DataLoader, y: TensorLike | None = None): ...
-
-    def predict(
-        self,
-        x: TensorLike | DataLoader,
-        with_grad: bool = False,
-    ) -> OutputLike:
-        """Predict the output for the given input.
-
-        Parameters
-        ----------
-        x: TensorLike | DataLoader
-            Input `TensorLike` or `DataLoader` to make predictions for.
-        with_grad: bool
-            Whether to enable gradient calculation. Defaults to False.
-
-        Returns
-        -------
-        OutputLike
-            The emulator predicted spatiotemporal output.
-        """
-        if isinstance(x, TensorLike):
-            return super().predict(x, with_grad)
-        return self._predict(x, with_grad)
-
-    @abstractmethod
-    def _predict(self, x: TensorLike | DataLoader, with_grad: bool) -> OutputLike: ...
-
-    # TODO: update to handle DataLoader input as part of #814 and #815
-    def predict_autoregressive(self, initial_sample: dict, n_steps: int) -> TensorLike:
-        """Perform autoregressive prediction."""
-        from autoemulate.experimental.emulators.fno import (  # noqa: PLC0415 to avoid circular import
-            prepare_batch,
-        )
-
-        self.eval()
-        predictions = []
-        # Get initial input
-        current_input = initial_sample[
-            "input_fields"
-        ]  # [batch, time, height, width, channels]
-        constant_scalars = initial_sample["constant_scalars"]
-        with torch.no_grad():
-            for _ in range(n_steps):
-                # Prepare current input in the format expected by prepare_batch
-                current_sample = {
-                    "input_fields": current_input,
-                    "output_fields": current_input,  # dummy, not used
-                    "constant_scalars": constant_scalars,
-                }
-                # Use prepare_batch to get properly formatted input
-                x, _ = prepare_batch(
-                    current_sample,
-                    channels=self.channels,
-                    with_constants=True,
-                    with_time=True,
-                )
-                # Forward pass
-                pred = self(x)  # [batch, channels, time, height, width]
-                assert isinstance(pred, TensorLike)
-                predictions.append(pred)
-                # Update input for next iteration
-                # Convert prediction back to input format
-                current_input = pred.permute(0, 2, 3, 4, 1)
-        # Stack all predictions along time dimension
-        return torch.cat(predictions, dim=2)