autoemulate 1.2.1__tar.gz → 2.0.0__tar.gz

{autoemulate-1.2.1 → autoemulate-2.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: autoemulate
-Version: 1.2.1
+Version: 2.0.0
 Summary: A python package for semi-automated emulation
 Author: AutoEmulate contributors (see our GitHub page)
 License-Expression: MIT
@@ -73,13 +73,9 @@ Dynamic: license-file
 [![Documentation](https://img.shields.io/badge/documentation-blue)](https://alan-turing-institute.github.io/autoemulate/)
 [![Github Stats](https://img.shields.io/badge/repostats-orange)](https://github.com/alan-turing-institute/autoemulate/blob/github-repo-stats/alan-turing-institute/autoemulate/latest-report/report.pdf)
 
-
 <!-- SPHINX-START -->
 Simulations of physical systems are often slow and need lots of compute, which makes them unpractical for real-world applications like digital twins, or when they have to run thousands of times for sensitivity analyses. The goal of `AutoEmulate` is to make it easy to replace simulations with fast, accurate emulators. To do this, `AutoEmulate` automatically fits and compares various emulators, ranging from simple models like Radial Basis Functions and Second Order Polynomials to more complex models like Support Vector Machines and  Gaussian Processes to find the best emulator for a simulation. 
 
->[!WARNING]
->Although AutoEmulate is currently on version 1.x, we are not following semantic versioning at the moment. The convention for V1 is that breaking and major changes will be made between minor version (1.1 -> 1.2). Bug fixes will be made in patch versions (1.1.1 -> 1.1.2). We plan to implement true semantic versioning in v2 of the package. We recommend pinning the minor version of AutoEmulate if using downstream and carefully reading release notes.
-
 ## Documentation
 
 You can find the project documentation [here](https://alan-turing-institute.github.io/autoemulate/), including [installation](https://alan-turing-institute.github.io/autoemulate/installation.html).
@@ -139,6 +135,10 @@ 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>
+    </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>
     </tr>
   </tbody>
 </table>

{autoemulate-1.2.1 → autoemulate-2.0.0}/README.md

@@ -7,13 +7,9 @@
 [![Documentation](https://img.shields.io/badge/documentation-blue)](https://alan-turing-institute.github.io/autoemulate/)
 [![Github Stats](https://img.shields.io/badge/repostats-orange)](https://github.com/alan-turing-institute/autoemulate/blob/github-repo-stats/alan-turing-institute/autoemulate/latest-report/report.pdf)
 
-
 <!-- SPHINX-START -->
 Simulations of physical systems are often slow and need lots of compute, which makes them unpractical for real-world applications like digital twins, or when they have to run thousands of times for sensitivity analyses. The goal of `AutoEmulate` is to make it easy to replace simulations with fast, accurate emulators. To do this, `AutoEmulate` automatically fits and compares various emulators, ranging from simple models like Radial Basis Functions and Second Order Polynomials to more complex models like Support Vector Machines and  Gaussian Processes to find the best emulator for a simulation. 
 
->[!WARNING]
->Although AutoEmulate is currently on version 1.x, we are not following semantic versioning at the moment. The convention for V1 is that breaking and major changes will be made between minor version (1.1 -> 1.2). Bug fixes will be made in patch versions (1.1.1 -> 1.1.2). We plan to implement true semantic versioning in v2 of the package. We recommend pinning the minor version of AutoEmulate if using downstream and carefully reading release notes.
-
 ## Documentation
 
 You can find the project documentation [here](https://alan-turing-institute.github.io/autoemulate/), including [installation](https://alan-turing-institute.github.io/autoemulate/installation.html).
@@ -73,6 +69,10 @@ 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>
+    </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>
     </tr>
   </tbody>
 </table>

{autoemulate-1.2.1 → autoemulate-2.0.0}/autoemulate/core/plotting.py

@@ -8,7 +8,7 @@ from matplotlib.axes import Axes
 from matplotlib.figure import Figure
 
 from autoemulate.core.types import DistributionLike, GaussianLike, NumpyLike, TensorLike
-from autoemulate.emulators.base import Emulator
+from autoemulate.emulators.base import Emulator, PyTorchBackend
 
 
 def display_figure(fig: Figure):
@@ -601,3 +601,58 @@ def plot_calibration_from_distributions(
         ax.legend()
 
     return fig, ax
+
+
+def plot_loss(
+    model: PyTorchBackend,
+    title: str | None = None,
+    figsize: tuple[int, int] | None = None,
+):
+    """
+    Plot the per-epoch training loss for a model using the PyTorch backend.
+
+    This function visualizes the training loss curve stored in the model's
+    ``loss_history`` attribute. The model must also provide an ``epochs``
+    attribute. If either attribute is missing, an ``AttributeError`` is raised.
+
+    Parameters
+    ----------
+    model : PyTorchBackend
+        A model instance using the PyTorch backend. It must provide both
+        ``loss_history`` and ``epochs`` attributes.
+    title : str, optional
+        Title for the plot. If ``None``, no title is added.
+    figsize : tuple of int, optional
+        Size of the figure as ``(width, height)`` in inches. Defaults to
+        ``(6, 6)`` if not provided.
+
+    Returns
+    -------
+    fig : matplotlib.figure.Figure
+        The created matplotlib Figure object.
+    ax : matplotlib.axes.Axes
+        The Axes on which the loss curve is plotted.
+
+    Raises
+    ------
+    AttributeError
+        If the model does not provide ``loss_history`` or ``epochs``.
+    """
+    if not hasattr(model, "loss_history"):
+        msg = "Emulator does not have a Loss history"
+        raise AttributeError(msg)
+
+    history = model.loss_history
+
+    if figsize is None:
+        figsize = (6, 6)
+
+    fig, ax = plt.subplots(figsize=figsize)
+    ax.plot(range(1, len(history) + 1), history)
+    ax.set_xlabel("Epochs")
+    ax.set_ylabel("Train Loss")
+
+    if title:
+        ax.set_title(title)
+
+    return fig, ax

autoemulate-2.0.0/autoemulate/simulations/__init__.py

@@ -0,0 +1,22 @@
+from .epidemic import Epidemic
+from .flow_problem import FlowProblem
+from .projectile import Projectile, ProjectileMultioutput
+from .seir import SEIRSimulator
+
+ALL_SIMULATORS = [
+    Epidemic,
+    SEIRSimulator,
+    FlowProblem,
+    Projectile,
+    ProjectileMultioutput,
+]
+
+__all__ = [
+    "Epidemic",
+    "FlowProblem",
+    "Projectile",
+    "ProjectileMultioutput",
+    "SEIRSimulator",
+]
+
+SIMULATOR_REGISTRY = dict(zip(__all__, ALL_SIMULATORS, strict=False))

{autoemulate-1.2.1 → autoemulate-2.0.0}/autoemulate/simulations/base.py

@@ -5,8 +5,9 @@ import torch
 from scipy.stats import qmc
 from tqdm import tqdm
 
+from autoemulate.core.device import TorchDeviceMixin
 from autoemulate.core.logging_config import get_configured_logger
-from autoemulate.core.types import TensorLike
+from autoemulate.core.types import DeviceLike, TensorLike
 from autoemulate.data.utils import ValidationMixin, set_random_seed
 
 logger = logging.getLogger("autoemulate")
@@ -362,3 +363,99 @@ class Simulator(ABC, ValidationMixin):
             output_dict[output_name] = self.results_tensor[:, i]
 
         return output_dict
+
+
+class TorchSimulator(Simulator, TorchDeviceMixin):
+    """
+    Simulator that runs computations on a specified torch device.
+
+    This subclass extends :class:`Simulator` with the :class:`TorchDeviceMixin`
+    so that simulators implemented in PyTorch (e.g., ``torchcor``) can run on
+    CPU or accelerator hardware. Inputs are moved to ``self.device`` before the
+    forward pass and the resulting tensors are kept on the same device.
+    """
+
+    def __init__(
+        self,
+        parameters_range: dict[str, tuple[float, float]],
+        output_names: list[str],
+        log_level: str = "progress_bar",
+        device: DeviceLike | None = None,
+    ):
+        Simulator.__init__(self, parameters_range, output_names, log_level)
+        TorchDeviceMixin.__init__(self, device=device)
+
+    def sample_inputs(
+        self, n_samples: int, random_seed: int | None = None, method: str = "lhs"
+    ) -> TensorLike:
+        """
+        Sample inputs and move them to the simulator's device.
+
+        Parameters
+        ----------
+        n_samples: int
+            Number of samples to generate.
+        random_seed: int | None
+            Optional random seed to make sampling reproducible.
+        method: str
+            Sampling method, one of ``"lhs"`` or ``"sobol"``.
+
+        Returns
+        -------
+        TensorLike
+            Sampled inputs located on ``self.device``.
+        """
+        samples = super().sample_inputs(
+            n_samples, random_seed=random_seed, method=method
+        )
+        (samples_device,) = self._move_tensors_to_device(samples)
+        return samples_device
+
+    def forward(self, x: TensorLike, allow_failures: bool = True) -> TensorLike | None:
+        """
+        Run a single simulation on the configured device.
+
+        Parameters
+        ----------
+        x: TensorLike
+            Input tensor with shape ``(n_samples, in_dim)``.
+        allow_failures: bool
+            When True, failures return ``None`` instead of raising.
+
+        Returns
+        -------
+        TensorLike | None
+            Simulation result on ``self.device`` or ``None`` on failure.
+        """
+        (x_device,) = self._move_tensors_to_device(x)
+        y = super().forward(x_device, allow_failures=allow_failures)
+        if isinstance(y, torch.Tensor):
+            return y.to(self.device)
+        return y
+
+    def forward_batch(
+        self, x: TensorLike, allow_failures: bool = True
+    ) -> tuple[TensorLike, TensorLike]:
+        """
+        Run a batch of simulations with device management.
+
+        Parameters
+        ----------
+        x: TensorLike
+            Batch of inputs with shape ``(batch_size, in_dim)``.
+        allow_failures: bool
+            Whether to skip failures (True) or raise immediately (False).
+
+        Returns
+        -------
+        tuple[TensorLike, TensorLike]
+            Tuple of ``(results, valid_inputs)`` residing on ``self.device``.
+        """
+        (x_device,) = self._move_tensors_to_device(x)
+        results, valid_inputs = super().forward_batch(
+            x_device, allow_failures=allow_failures
+        )
+        results = results.to(self.device)
+        self.results_tensor = results
+        valid_inputs = valid_inputs.to(self.device)
+        return results, valid_inputs

autoemulate-2.0.0/autoemulate/simulations/seir.py

@@ -0,0 +1,110 @@
+from __future__ import annotations
+
+import numpy as np
+import torch
+from scipy.integrate import solve_ivp
+
+from autoemulate.core.types import NumpyLike, TensorLike
+from autoemulate.simulations.base import Simulator
+
+
+def simulate_seir_epidemic(
+    x: NumpyLike,
+    N: int = 1000,
+    I0: int = 1,
+    E0: int = 0,
+) -> float:
+    """
+    Simulate an epidemic using the SEIR model.
+
+    Parameters
+    ----------
+    x : NumpyLike
+        SEIR parameters [beta, gamma, sigma].
+    N : int
+        Total population.
+    I0 : int
+        Initial infected.
+    E0 : int
+        Initial exposed.
+
+    Returns
+    -------
+    peak_infection_rate : float
+        Peak infection fraction I_max / N.
+    """
+    if len(x) != 3:
+        raise ValueError(f"Expected 3 parameters [beta, gamma, sigma], got {len(x)}")
+
+    beta, gamma, sigma = x
+
+    S0 = N - I0 - E0
+    R0 = 0
+    t_span = (0.0, 160.0)
+    y0 = [S0, E0, I0, R0]
+
+    def seir_model(t, y, N, beta, gamma, sigma):  # noqa: ARG001
+        S, E, I, R = y  # noqa: E741
+        dSdt = -beta * S * I / N
+        dEdt = beta * S * I / N - sigma * E
+        dIdt = sigma * E - gamma * I
+        dRdt = gamma * I
+        return [dSdt, dEdt, dIdt, dRdt]
+
+    t_eval = np.linspace(t_span[0], t_span[1], 160)
+    sol = solve_ivp(
+        seir_model,
+        t_span,
+        y0,
+        args=(N, beta, gamma, sigma),
+        t_eval=t_eval,
+        vectorized=False,
+    )
+
+    _, E, I, R = sol.y  # noqa: E741
+    I_max = np.max(I)
+
+    return float(I_max) / float(N)
+
+
+class SEIRSimulator(Simulator):
+    """Simulator of infectious disease spread using the SEIR model."""
+
+    def __init__(
+        self,
+        parameters_range=None,
+        output_names=None,
+        log_level: str = "progress_bar",
+    ):
+        if parameters_range is None:
+            parameters_range = {
+                "beta": (0.1, 0.5),
+                "gamma": (0.01, 0.2),
+                "sigma": (0.05, 0.3),
+            }
+        if output_names is None:
+            output_names = ["infection_rate"]
+
+        super().__init__(parameters_range, output_names, log_level)
+
+    def _forward(self, x: TensorLike) -> TensorLike:
+        """
+        Simulate the epidemic using the SEIR model.
+
+        Parameters
+        ----------
+        x : TensorLike
+            Input parameter values [beta, gamma, sigma].
+
+        Returns
+        -------
+        TensorLike
+            Peak infection rate (fraction of population).
+        """
+        if x.shape[0] != 1:
+            raise ValueError(
+                f"SEIRSimulator._forward expects a single input, got {x.shape[0]}"
+            )
+
+        y = simulate_seir_epidemic(x.cpu().numpy()[0])
+        return torch.tensor([y], dtype=torch.float32).view(-1, 1)

{autoemulate-1.2.1 → autoemulate-2.0.0}/autoemulate.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: autoemulate
-Version: 1.2.1
+Version: 2.0.0
 Summary: A python package for semi-automated emulation
 Author: AutoEmulate contributors (see our GitHub page)
 License-Expression: MIT
@@ -73,13 +73,9 @@ Dynamic: license-file
 [![Documentation](https://img.shields.io/badge/documentation-blue)](https://alan-turing-institute.github.io/autoemulate/)
 [![Github Stats](https://img.shields.io/badge/repostats-orange)](https://github.com/alan-turing-institute/autoemulate/blob/github-repo-stats/alan-turing-institute/autoemulate/latest-report/report.pdf)
 
-
 <!-- SPHINX-START -->
 Simulations of physical systems are often slow and need lots of compute, which makes them unpractical for real-world applications like digital twins, or when they have to run thousands of times for sensitivity analyses. The goal of `AutoEmulate` is to make it easy to replace simulations with fast, accurate emulators. To do this, `AutoEmulate` automatically fits and compares various emulators, ranging from simple models like Radial Basis Functions and Second Order Polynomials to more complex models like Support Vector Machines and  Gaussian Processes to find the best emulator for a simulation. 
 
->[!WARNING]
->Although AutoEmulate is currently on version 1.x, we are not following semantic versioning at the moment. The convention for V1 is that breaking and major changes will be made between minor version (1.1 -> 1.2). Bug fixes will be made in patch versions (1.1.1 -> 1.1.2). We plan to implement true semantic versioning in v2 of the package. We recommend pinning the minor version of AutoEmulate if using downstream and carefully reading release notes.
-
 ## Documentation
 
 You can find the project documentation [here](https://alan-turing-institute.github.io/autoemulate/), including [installation](https://alan-turing-institute.github.io/autoemulate/installation.html).
@@ -139,6 +135,10 @@ 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>
+    </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>
     </tr>
   </tbody>
 </table>

{autoemulate-1.2.1 → autoemulate-2.0.0}/autoemulate.egg-info/SOURCES.txt

@@ -114,6 +114,7 @@ autoemulate/simulations/epidemic.py
 autoemulate/simulations/flow_problem.py
 autoemulate/simulations/projectile.py
 autoemulate/simulations/reaction_diffusion.py
+autoemulate/simulations/seir.py
 autoemulate/transforms/__init__.py
 autoemulate/transforms/base.py
 autoemulate/transforms/pca.py

{autoemulate-1.2.1 → autoemulate-2.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "autoemulate"
-version = "1.2.1"
+version = "2.0.0"
 description = "A python package for semi-automated emulation"
 license = "MIT"
 authors = [{ name = "AutoEmulate contributors (see our GitHub page)" }]

autoemulate-1.2.1/autoemulate/simulations/__init__.py

@@ -1,9 +0,0 @@
-from .epidemic import Epidemic
-from .flow_problem import FlowProblem
-from .projectile import Projectile, ProjectileMultioutput
-
-ALL_SIMULATORS = [Epidemic, FlowProblem, Projectile, ProjectileMultioutput]
-
-__all__ = ["Epidemic", "FlowProblem", "Projectile", "ProjectileMultioutput"]
-
-SIMULATOR_REGISTRY = dict(zip(__all__, ALL_SIMULATORS, strict=False))