mxlpy 0.18.0__py3-none-any.whl → 0.19.0__py3-none-any.whl

mxlpy/surrogates/_torch.py

@@ -9,16 +9,17 @@ from torch import nn
 from torch.optim.adam import Adam
 from torch.optim.optimizer import ParamsT
 
-from mxlpy.nn._torch import MLP, DefaultDevice, train
-from mxlpy.types import AbstractSurrogate
+from mxlpy.nn._torch import MLP, DefaultDevice
+from mxlpy.nn._torch import train as _train
+from mxlpy.types import AbstractSurrogate, Derived
 
 type LossFn = Callable[[torch.Tensor, torch.Tensor], torch.Tensor]
 
 __all__ = [
     "LossFn",
-    "Torch",
-    "TorchTrainer",
-    "train_torch",
+    "Surrogate",
+    "Trainer",
+    "train",
 ]
 
 
@@ -37,7 +38,7 @@ def _mean_abs(x: torch.Tensor, y: torch.Tensor) -> torch.Tensor:
 
 
 @dataclass(kw_only=True)
-class Torch(AbstractSurrogate):
+class Surrogate(AbstractSurrogate):
     """Surrogate model using PyTorch.
 
     Attributes:
@@ -65,12 +66,25 @@ class Torch(AbstractSurrogate):
                 torch.tensor(y, dtype=torch.float32),
             ).numpy()
 
+    def predict(
+        self,
+        args: dict[str, float | pd.Series | pd.DataFrame],
+    ) -> dict[str, float]:
+        """Predict outputs based on input data."""
+        return dict(
+            zip(
+                self.outputs,
+                self.predict_raw(np.array([args[arg] for arg in self.args])),
+                strict=True,
+            )
+        )
+
 
 @dataclass(init=False)
-class TorchTrainer:
+class Trainer:
     features: pd.DataFrame
     targets: pd.DataFrame
-    approximator: nn.Module
+    model: nn.Module
     optimizer: Adam
     device: torch.device
     losses: list[pd.Series]
@@ -80,22 +94,22 @@ class TorchTrainer:
         self,
         features: pd.DataFrame,
         targets: pd.DataFrame,
-        approximator: nn.Module | None = None,
-        optimimzer_cls: Callable[[ParamsT], Adam] = Adam,
+        model: nn.Module | None = None,
+        optimizer_cls: Callable[[ParamsT], Adam] = Adam,
         device: torch.device = DefaultDevice,
         loss_fn: LossFn = _mean_abs,
     ) -> None:
         self.features = features
         self.targets = targets
 
-        if approximator is None:
-            approximator = MLP(
+        if model is None:
+            model = MLP(
                 n_inputs=len(features.columns),
                 neurons_per_layer=[50, 50, len(targets.columns)],
             )
-        self.approximator = approximator.to(device)
+        self.model = model.to(device)
 
-        self.optimizer = optimimzer_cls(approximator.parameters())
+        self.optimizer = optimizer_cls(model.parameters())
         self.device = device
         self.loss_fn = loss_fn
         self.losses = []
@@ -105,8 +119,8 @@ class TorchTrainer:
         epochs: int,
         batch_size: int | None = None,
     ) -> Self:
-        losses = train(
-            aprox=self.approximator,
+        losses = _train(
+            model=self.model,
             features=self.features.to_numpy(),
             targets=self.targets.to_numpy(),
             epochs=epochs,
@@ -127,10 +141,10 @@ class TorchTrainer:
         self,
         surrogate_args: list[str] | None = None,
         surrogate_outputs: list[str] | None = None,
-        surrogate_stoichiometries: dict[str, dict[str, float]] | None = None,
-    ) -> Torch:
-        return Torch(
-            model=self.approximator,
+        surrogate_stoichiometries: dict[str, dict[str, float | Derived]] | None = None,
+    ) -> Surrogate:
+        return Surrogate(
+            model=self.model,
             args=surrogate_args if surrogate_args is not None else [],
             outputs=surrogate_outputs if surrogate_outputs is not None else [],
             stoichiometries=surrogate_stoichiometries
@@ -139,19 +153,19 @@ class TorchTrainer:
         )
 
 
-def train_torch(
+def train(
     features: pd.DataFrame,
     targets: pd.DataFrame,
     epochs: int,
     surrogate_args: list[str] | None = None,
     surrogate_outputs: list[str] | None = None,
-    surrogate_stoichiometries: dict[str, dict[str, float]] | None = None,
+    surrogate_stoichiometries: dict[str, dict[str, float | Derived]] | None = None,
     batch_size: int | None = None,
-    approximator: nn.Module | None = None,
-    optimimzer_cls: Callable[[ParamsT], Adam] = Adam,
+    model: nn.Module | None = None,
+    optimizer_cls: Callable[[ParamsT], Adam] = Adam,
     device: torch.device = DefaultDevice,
     loss_fn: LossFn = _mean_abs,
-) -> tuple[Torch, pd.Series]:
+) -> tuple[Surrogate, pd.Series]:
     """Train a PyTorch surrogate model.
 
     Examples:
@@ -173,8 +187,8 @@ def train_torch(
         surrogate_outputs: Names of output arguments from the surrogate.
         surrogate_stoichiometries: Mapping of variables to their stoichiometries
         batch_size: Size of mini-batches for training (None for full-batch).
-        approximator: Predefined neural network model (None to use default MLP features-50-50-output).
-        optimimzer_cls: Optimizer class to use for training (default: Adam).
+        model: Predefined neural network model (None to use default MLP features-50-50-output).
+        optimizer_cls: Optimizer class to use for training (default: Adam).
         device: Device to run the training on (default: DefaultDevice).
         loss_fn: Custom loss function or instance of torch loss object
 
@@ -182,11 +196,11 @@ def train_torch(
         tuple[TorchSurrogate, pd.Series]: Trained surrogate model and loss history.
 
     """
-    trainer = TorchTrainer(
+    trainer = Trainer(
         features=features,
         targets=targets,
-        approximator=approximator,
-        optimimzer_cls=optimimzer_cls,
+        model=model,
+        optimizer_cls=optimizer_cls,
         device=device,
         loss_fn=loss_fn,
     ).train(

mxlpy/symbolic/symbolic_model.py

@@ -70,6 +70,6 @@ def to_symbolic_model(model: Model) -> SymbolicModel:
         variables=variables,
         parameters=parameters,
         eqs=[eqs[i] for i in cache.var_names],
-        initial_conditions=model.variables.copy(),
-        parameter_values=model.parameters.copy(),
+        initial_conditions=model.get_initial_conditions(),
+        parameter_values=model.parameters,
     )

mxlpy/types.py

@@ -46,7 +46,7 @@ __all__ = [
     "unwrap2",
 ]
 
-from collections.abc import Callable, Iterator, Mapping
+from collections.abc import Callable, Iterable, Iterator, Mapping
 from typing import TYPE_CHECKING, Any, ParamSpec, Protocol, TypeVar, cast
 
 import numpy as np
@@ -159,7 +159,7 @@ class Derived:
     fn: RateFn
     args: list[str]
 
-    def calculate(self, dependent: dict[str, float]) -> float:
+    def calculate(self, dependent: dict[str, Any]) -> float:
         """Calculate the derived value.
 
         Args:
@@ -171,7 +171,7 @@ class Derived:
         """
         return cast(float, self.fn(*(dependent[arg] for arg in self.args)))
 
-    def calculate_inpl(self, name: str, dependent: dict[str, float]) -> None:
+    def calculate_inpl(self, name: str, dependent: dict[str, Any]) -> None:
         """Calculate the derived value in place.
 
         Args:
@@ -181,20 +181,6 @@ class Derived:
         """
         dependent[name] = cast(float, self.fn(*(dependent[arg] for arg in self.args)))
 
-    def calculate_inpl_time_course(self, name: str, dependent: pd.DataFrame) -> None:
-        """Calculate the derived value in place.
-
-        Args:
-            name: Name of the derived variable.
-            dependent: Dictionary of dependent variables.
-
-        """
-        try:
-            dependent[name] = self.fn(*dependent.loc[:, self.args].to_numpy().T)
-        except ValueError:  # e.g. numpy.where
-            sub = dependent.loc[:, self.args].to_numpy()
-            dependent[name] = [self.fn(*row) for row in sub]
-
 
 @dataclass(kw_only=True, slots=True)
 class Readout:
@@ -203,7 +189,7 @@ class Readout:
     fn: RateFn
     args: list[str]
 
-    def calculate(self, dependent: dict[str, float]) -> float:
+    def calculate(self, dependent: dict[str, Any]) -> float:
         """Calculate the derived value.
 
         Args:
@@ -215,8 +201,8 @@ class Readout:
         """
         return cast(float, self.fn(*(dependent[arg] for arg in self.args)))
 
-    def calculate_inpl(self, name: str, dependent: dict[str, float]) -> None:
-        """Calculate the readout in place.
+    def calculate_inpl(self, name: str, dependent: dict[str, Any]) -> None:
+        """Calculate the reaction in place.
 
         Args:
             name: Name of the derived variable.
@@ -225,20 +211,6 @@ class Readout:
         """
         dependent[name] = cast(float, self.fn(*(dependent[arg] for arg in self.args)))
 
-    def calculate_inpl_time_course(self, name: str, dependent: pd.DataFrame) -> None:
-        """Calculate the derived value in place.
-
-        Args:
-            name: Name of the derived variable.
-            dependent: Dictionary of dependent variables.
-
-        """
-        try:
-            dependent[name] = self.fn(*dependent.loc[:, self.args].to_numpy().T)
-        except ValueError:  # e.g. numpy.where
-            sub = dependent.loc[:, self.args].to_numpy()
-            dependent[name] = [self.fn(*row) for row in sub]
-
 
 @dataclass(kw_only=True, slots=True)
 class Reaction:
@@ -255,7 +227,7 @@ class Reaction:
 
         return [k for k in self.args if k in include and k not in exclude]
 
-    def calculate(self, dependent: dict[str, float]) -> float:
+    def calculate(self, dependent: dict[str, Any]) -> float:
         """Calculate the derived value.
 
         Args:
@@ -267,7 +239,7 @@ class Reaction:
         """
         return cast(float, self.fn(*(dependent[arg] for arg in self.args)))
 
-    def calculate_inpl(self, name: str, dependent: dict[str, float]) -> None:
+    def calculate_inpl(self, name: str, dependent: dict[str, Any]) -> None:
         """Calculate the reaction in place.
 
         Args:
@@ -277,19 +249,57 @@ class Reaction:
         """
         dependent[name] = cast(float, self.fn(*(dependent[arg] for arg in self.args)))
 
-    def calculate_inpl_time_course(self, name: str, dependent: pd.DataFrame) -> None:
-        """Calculate the derived value in place.
 
-        Args:
-            name: Name of the derived variable.
-            dependent: Dictionary of dependent variables.
+@dataclass(kw_only=True)
+class AbstractSurrogate:
+    """Abstract base class for surrogate models.
 
-        """
-        try:
-            dependent[name] = self.fn(*dependent.loc[:, self.args].to_numpy().T)
-        except ValueError:  # e.g. numpy.where
-            sub = dependent.loc[:, self.args].to_numpy()
-            dependent[name] = [self.fn(*row) for row in sub]
+    Attributes:
+        inputs: List of input variable names.
+        stoichiometries: Dictionary mapping reaction names to stoichiometries.
+
+    Methods:
+        predict: Abstract method to predict outputs based on input data.
+
+    """
+
+    args: list[str]
+    outputs: list[str]
+    stoichiometries: dict[str, dict[str, float | Derived]] = field(default_factory=dict)
+
+    @abstractmethod
+    def predict(
+        self, args: dict[str, float | pd.Series | pd.DataFrame]
+    ) -> dict[str, float]:
+        """Predict outputs based on input data."""
+
+    def calculate_inpl(
+        self,
+        name: str,  # noqa: ARG002, for API compatibility
+        args: dict[str, float | pd.Series | pd.DataFrame],
+    ) -> None:
+        """Predict outputs based on input data."""
+        args |= self.predict(args=args)
+
+
+@dataclass(kw_only=True)
+class MockSurrogate(AbstractSurrogate):
+    """Mock surrogate model for testing purposes."""
+
+    fn: Callable[..., Iterable[float]]
+
+    def predict(
+        self,
+        args: dict[str, float | pd.Series | pd.DataFrame],
+    ) -> dict[str, float]:
+        """Predict outputs based on input data."""
+        return dict(
+            zip(
+                self.outputs,
+                self.fn(*(args[i] for i in self.args)),
+                strict=True,
+            )
+        )  # type: ignore
 
 
 @dataclass(kw_only=True, slots=True)
@@ -429,70 +439,6 @@ class ProtocolByPars:
         return cast(pd.DataFrame, mean.unstack().T)
 
 
-@dataclass(kw_only=True)
-class AbstractSurrogate:
-    """Abstract base class for surrogate models.
-
-    Attributes:
-        inputs: List of input variable names.
-        stoichiometries: Dictionary mapping reaction names to stoichiometries.
-
-    Methods:
-        predict: Abstract method to predict outputs based on input data.
-
-    """
-
-    args: list[str]
-    outputs: list[str]
-    stoichiometries: dict[str, dict[str, float]] = field(default_factory=dict)
-
-    @abstractmethod
-    def predict_raw(self, y: np.ndarray) -> np.ndarray:
-        """Predict outputs based on input data."""
-
-    def predict(self, y: np.ndarray) -> dict[str, float]:
-        """Predict outputs based on input data."""
-        return dict(
-            zip(
-                self.outputs,
-                self.predict_raw(y),
-                strict=True,
-            )
-        )
-
-    def calculate_inpl(
-        self,
-        name: str,  # noqa: ARG002, for API compatibility
-        args: dict[str, float],
-    ) -> None:
-        """Predict outputs based on input data."""
-        args |= self.predict(np.array([args[arg] for arg in self.args]))
-
-    def calculate_inpl_time_course(
-        self,
-        name: str,  # noqa: ARG002, for API compatibility
-        args: pd.DataFrame,
-    ) -> None:
-        """Predict outputs based on input data."""
-        args[self.outputs] = pd.DataFrame(
-            [self.predict(y) for y in args.loc[:, self.args].to_numpy()],
-            index=args.index,
-            dtype=float,
-        )
-
-
-@dataclass(kw_only=True)
-class MockSurrogate(AbstractSurrogate):
-    """Mock surrogate model for testing purposes."""
-
-    def predict(
-        self,
-        y: np.ndarray,
-    ) -> dict[str, float]:
-        """Predict outputs based on input data."""
-        return dict(zip(self.outputs, y, strict=True))
-
-
 @dataclass(kw_only=True)
 class AbstractEstimator:
     """Abstract class for parameter estimation using neural networks."""

{mxlpy-0.18.0.dist-info → mxlpy-0.19.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mxlpy
-Version: 0.18.0
+Version: 0.19.0
 Summary: A package to build metabolic models
 Author-email: Marvin van Aalst <marvin.vanaalst@gmail.com>
 Maintainer-email: Marvin van Aalst <marvin.vanaalst@gmail.com>
@@ -24,6 +24,7 @@ Classifier: Topic :: Software Development
 Requires-Python: >=3.12
 Requires-Dist: dill>=0.3.9
 Requires-Dist: latexify-py>=0.4.4
+Requires-Dist: lazy-import>=0.2.2
 Requires-Dist: matplotlib>=3.9.2
 Requires-Dist: mike>=2.1.3
 Requires-Dist: more-itertools>=10.5.0
@@ -41,20 +42,10 @@ Requires-Dist: tabulate>=0.9.0
 Requires-Dist: toml>=0.10.2
 Requires-Dist: tqdm>=4.66.6
 Requires-Dist: typing-extensions>=4.12.2
-Provides-Extra: dev
-Requires-Dist: coverage>=7.6.4; extra == 'dev'
-Requires-Dist: jupyter>=1.1.1; extra == 'dev'
-Requires-Dist: mkdocs-jupyter>=0.25.1; extra == 'dev'
-Requires-Dist: mkdocs-material>=9.5.42; extra == 'dev'
-Requires-Dist: mkdocs>=1.6.1; extra == 'dev'
-Requires-Dist: pre-commit>=4.0.1; extra == 'dev'
-Requires-Dist: pyright>=1.1.387; extra == 'dev'
-Requires-Dist: pytest-cov>=5.0.0; extra == 'dev'
-Requires-Dist: pytest>=8.3.3; extra == 'dev'
-Requires-Dist: requests>=2.32.3; extra == 'dev'
-Requires-Dist: ruff>=0.7.1; extra == 'dev'
-Requires-Dist: ssort>=0.13.0; extra == 'dev'
-Requires-Dist: toml-sort<0.24,>=0.23.1; extra == 'dev'
+Provides-Extra: keras
+Requires-Dist: keras>=3.9.2; extra == 'keras'
+Provides-Extra: tensorflow
+Requires-Dist: tensorflow>=2.19.0; extra == 'tensorflow'
 Provides-Extra: torch
 Requires-Dist: torch>=2.5.1; extra == 'torch'
 Description-Content-Type: text/markdown
@@ -78,14 +69,26 @@ Description-Content-Type: text/markdown
 
 ## Installation
 
-You can install mxlpy using pip: `pip install mxlpy`
+You can install mxlpy using pip: `pip install mxlpy`.
+
+Due to their sizes, the machine learning are optional dependencies. You cann install them using
+
+```shell
+# One of them respectively
+pip install mxlpy[torch]
+pip install mxlpy[tensorflow]
+pip install mxlpy[keras]
+
+# together
+pip install mxlpy[torch, tensorflow, keras]
+```
 
 If you want access to the sundials solver suite via the [assimulo](https://jmodelica.org/assimulo/) package, we recommend setting up a virtual environment via [pixi](https://pixi.sh/) or [mamba / conda](https://mamba.readthedocs.io/en/latest/) using the [conda-forge](https://conda-forge.org/) channel.
 
 ```bash
 pixi init
 pixi add python assimulo
-pixi add --pypi mxlpy[torch]
+pixi add --pypi mxlpy
 ```
 
 ## How to cite
@@ -103,7 +106,7 @@ You have two choices here, using `uv` (pypi-only) or using `pixi` (conda-forge,
 ### uv
 
 - Install `uv` as described in [the docs](https://docs.astral.sh/uv/getting-started/installation/).
-- Run `uv sync --extra dev --extra torch` to install dependencies locally
+- Run `uv sync --all-extras --all-groups` to install dependencies locally
 
 ### pixi
 
@@ -111,7 +114,3 @@ You have two choices here, using `uv` (pypi-only) or using `pixi` (conda-forge,
 - Run `pixi install --frozen`
 
 
-## Notes
-
-- `uv add $package`
-- `uv add --optional dev $package`

{mxlpy-0.18.0.dist-info → mxlpy-0.19.0.dist-info}/RECORD

@@ -1,51 +1,54 @@
-mxlpy/__init__.py,sha256=lGo7XQTVuR1p8rW1J6gZsgdQWRqfYa9AWbvZQwT8oLQ,4236
+mxlpy/__init__.py,sha256=ODndmfAX0zFTSqK1kVQN2s4W3FDqxuu5Mvf1pnv0IdE,4421
 mxlpy/distributions.py,sha256=ce6RTqn19YzMMec-u09fSIUA8A92M6rehCuHuXWcX7A,8734
 mxlpy/fit.py,sha256=WNg98wW47xkd4gNEgj3t8eNNTqfVpHEJTbXMRQBe22o,12457
 mxlpy/fns.py,sha256=VxDDyEdtGD7fEoT5LiiEaRqFk-0fIunRXHr1dCMpCdE,14002
 mxlpy/identify.py,sha256=veYYCjTDAlzibrWtciX2egfEWWgosOpqgLBgbfVj42g,2130
-mxlpy/label_map.py,sha256=urv-QTb0MUEKjwWvKtJSB8H2kvhLn1EKfRIH7awQQ8Y,17769
+mxlpy/label_map.py,sha256=_bStQJtQ4RlmTQyrW34W62pyXFF_XFVbTXv-ybdly0s,17816
 mxlpy/linear_label_map.py,sha256=DqzN_akacPccZwzYAR3ANIdzAU_GU6Xe6gWV9DHAAWU,10282
 mxlpy/mc.py,sha256=oYd8a3ycyZLyh-ZxTYUjDRNfsCcwSQaLWssxv0yC5Cc,17399
 mxlpy/mca.py,sha256=1_qBX9lHI6svXSebtwvMldAMwPlLqMylAPmxMbMQdWw,9359
-mxlpy/model.py,sha256=H1rAKaB5pAQcMuBh5GnXuBReADTx5IDa1x0CdUZ6VlI,58411
+mxlpy/model.py,sha256=ykdFmh7AejqN8qJUXddc9tFVhDWED4CZ8QgRyyCrmK0,60784
 mxlpy/parallel.py,sha256=kX4Td5YoovDwZp6kX_3cfO6QtHSS9ieJ0bMZiKs3Xv8,5002
 mxlpy/parameterise.py,sha256=2jMhhO-bHTFP_0kXercJekeATAZYBg5FrK1MQ_mWGpk,654
 mxlpy/paths.py,sha256=TK2wO4N9lG-UV1JGfeB64q48JVDbwqIUj63rl55MKuQ,1022
-mxlpy/plot.py,sha256=Bu69ZSerqQlY_Hut-Wmn-KpqT1cwW96n8paa6dXOVrw,28853
+mxlpy/plot.py,sha256=MiV2Oi5kvI04VjjWiiVbAzRCGaZWue58_hQIRGzS4ik,28879
 mxlpy/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mxlpy/report.py,sha256=ZwnjquPAvo4A8UqK-BT19SZFSEUOy1FALqoh7uTmbAI,7793
 mxlpy/scan.py,sha256=FBPpjv66v4IWZ5OwG_EWUdrucLWR9gq_XEsLFC-otaw,18969
 mxlpy/simulator.py,sha256=9Ne4P5Jrwgx4oAlljPvCqSCCy98_5Lv1B87y1AkbI4c,21041
-mxlpy/types.py,sha256=EOIOPuxD2vqRjYgX4vYByclxmG7bCCR1WWXYE0Msz7A,14669
+mxlpy/types.py,sha256=swhRTCRNbmI8-2Z3Y0YA9QkxrTxwzYJlMz2qFcfpRsA,12698
 mxlpy/experimental/__init__.py,sha256=kZTE-92OErpHzNRqmgSQYH4CGXrogGJ5EL35XGZQ81M,206
-mxlpy/experimental/diff.py,sha256=4bztagJzFMsQJM7dlun_kv-WrWssM8CIw7gcL63hFf8,8952
+mxlpy/experimental/diff.py,sha256=cxr3GkZOkhUaWDj1eXHbjKSVKciGIp_IUf7Jkh0FdEE,8968
 mxlpy/integrators/__init__.py,sha256=kqmV6a0TRyLGR_XqbyAI652AfptYnXAUpqbSFg0CpP8,450
-mxlpy/integrators/int_assimulo.py,sha256=TCBWQd558ZeRdBba1jCNsFyLBOssKvm8dXK36Aqg4_k,4817
-mxlpy/integrators/int_scipy.py,sha256=dFHlYTeb2zX97f3VuNdMJdI7WEYshF4JAIgprKKk2z4,4581
+mxlpy/integrators/int_assimulo.py,sha256=H092idSPeFkPKAOVbr8M8iGdDpfc-MlPeDvh3-tP4rY,5013
+mxlpy/integrators/int_scipy.py,sha256=87nAVMY0DLQ_RAIDNa7pN6Xw8NFv5ifyZd8EmPT9rgY,4649
 mxlpy/meta/__init__.py,sha256=Jyy4063fZy6iT4LSwjPyEAVr4N_3xxcLc8wDBoDPyKc,278
-mxlpy/meta/codegen_latex.py,sha256=vONj--_wmFM_FJpe15aAYyT06-kolqQwSe2NEbKrQWo,19934
+mxlpy/meta/codegen_latex.py,sha256=OjDgfRRvibs9Bg75J_FSl9fh_MTs8Vqu4Wm9L2JTOCk,19982
 mxlpy/meta/codegen_modebase.py,sha256=_ZAW4NvXhKwJQLGz5hkwwZpL2JMAJlfG-GUWkYIiNvw,3124
 mxlpy/meta/codegen_py.py,sha256=xSdeuEGPGc-QKRMgJO4VSPGMlxCPEV5prkKjNQ2D2hg,3483
-mxlpy/meta/source_tools.py,sha256=IyiCLZ1KScSqADC9p_QSRgedoHGibs9U1RGJuXm827U,13464
-mxlpy/nn/__init__.py,sha256=yUc4o-iqfVVzkq9tZCstWwizrCqNlMft0YUwWGFFO-E,219
-mxlpy/nn/_tensorflow.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mxlpy/nn/_torch.py,sha256=DORLixCSteCUMb7PTrIwd5FrVZ4_k0GIaLc6PI3ViwE,5796
-mxlpy/npe/__init__.py,sha256=IQmqUPJc5A8QXJLzp6Dq6Sjm8Hh2KAYZLrMxXQVeQP8,1181
-mxlpy/npe/_torch.py,sha256=pynnkdspO7NwTT3Pb_BU21jgBjJEvuLBJwaw_A-jAFg,11681
+mxlpy/meta/source_tools.py,sha256=GSSFgH2lZ24e6eQxJ-lx4WSwawoPYdIwj_klt5Kr0h8,13464
+mxlpy/nn/__init__.py,sha256=Qjr-ERsY2lbD75sFBOhCUwEasQDSJKcpBn_kReLZ6oA,633
+mxlpy/nn/_keras.py,sha256=wffBYvQDNGp5me6x2yW4EwpKsnMojCJbXHfKE156a-w,2175
+mxlpy/nn/_torch.py,sha256=Omq7iMx2kbUXht2It-egiIYT2DzLGPbkpTCX-h17teI,5752
+mxlpy/npe/__init__.py,sha256=hBHCUD2JYDBBGS2kTY8mTCfWB3u1R7m5l--wUupZt6o,1270
+mxlpy/npe/_keras.py,sha256=ytvXMPK9KUCGOzTQm08_SgafiMb-MOIUdZQV7JjAO40,9721
+mxlpy/npe/_torch.py,sha256=v3joh6lFJJxvYJj--wzmKXL9UMTaIN3h6hPNq0uX9NU,11250
 mxlpy/sbml/__init__.py,sha256=AS7IwrBzBgN8coUZkyBEtiYa9ICWyY1wzp1ujVm5ItA,226
 mxlpy/sbml/_data.py,sha256=XwT1sSxn6KLTXYMbk4ORbEAEgZhQDBfoyrjMBDAoY_s,1135
-mxlpy/sbml/_export.py,sha256=Q6B9rxy-yt73DORzAYu4BpfkZXxCS3MDSDUXwpoXV6Q,19970
+mxlpy/sbml/_export.py,sha256=4tU3SVxfEvl0E1urZWHyphkiAeH5HeRO1cODvvrczAQ,20342
 mxlpy/sbml/_import.py,sha256=5odQBdpD93mQJp2bVIabmPo6NK60nxqrdSVB8fEsF_A,22099
 mxlpy/sbml/_mathml.py,sha256=bNk9RQ_NQFDhY1R354p-gwqqHaIiyAwZ1xLPHHhiguQ,24436
 mxlpy/sbml/_name_conversion.py,sha256=XK9DEyzhrD0GBBwwjK9RA0yORrDX5c-Uvx0VtKMR5rA,1325
 mxlpy/sbml/_unit_conversion.py,sha256=dW_I6_Ou09ccwnp6LIdrPriIQnQUK5lJcjzM2Fawm6U,1927
-mxlpy/surrogates/__init__.py,sha256=ofHPNwe0LAILP2ZUWivAQpOv9LyHHzLZc6iu1cV2LeQ,894
-mxlpy/surrogates/_poly.py,sha256=n1pe4xuD2A4BK8jJagzZ-17WW3kqvFBO-ZYuznmfosw,3303
-mxlpy/surrogates/_torch.py,sha256=dpRZL8qOD8toezniuVPJ7NFTMpA97dF9dyrXfBAcTro,5984
+mxlpy/surrogates/__init__.py,sha256=cz9qr0ToYSutIK45IvKrMe1mPP7Lj0I_V0HYGixfpZU,916
+mxlpy/surrogates/_keras.py,sha256=y4nW626Nr4OQrTdZneDf-Ox2sKmqKmGmEbjpuQMEl10,3816
+mxlpy/surrogates/_poly.py,sha256=qhwiWMQsQGq6qBEzagR-riM7Yp33FilsudMkGZ7mkEU,3598
+mxlpy/surrogates/_qss.py,sha256=q-CoULIntdXclArm7eHGHlZpgBKQmJrZ0ZaG2Q3B_Pg,712
+mxlpy/surrogates/_torch.py,sha256=lGKjLgHmUsD0iAbKzQUeKfN8C88ChQPg1pqidiYucWg,6315
 mxlpy/symbolic/__init__.py,sha256=3hQjCMw8-6iOxeUdfnCg8449fF_BRF2u6lCM1GPpkRY,222
 mxlpy/symbolic/strikepy.py,sha256=UMx2LMRwCkASKjdCYEvh9tKlW9dk3nDoWM9NNJXWL_8,19960
-mxlpy/symbolic/symbolic_model.py,sha256=YL9noEeP3_0DoKXwMPELtfmPuP6mgNcLIJgDRCkyB7A,2434
-mxlpy-0.18.0.dist-info/METADATA,sha256=LgAn8m3f6oRfZl03E3X8UHak-2pJmoUdhealdJXQsJA,4567
-mxlpy-0.18.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-mxlpy-0.18.0.dist-info/licenses/LICENSE,sha256=lHX9Eu70g3Iv1aOxXTWNHa3vq9vaVYSPQx4jOLYmDpw,1096
-mxlpy-0.18.0.dist-info/RECORD,,
+mxlpy/symbolic/symbolic_model.py,sha256=lxkDW7L00Og_8Rwf7j0Gek0nQxRu7kyboioY4ZUqfx0,2435
+mxlpy-0.19.0.dist-info/METADATA,sha256=YValpHti39pA32FnMfkI0zLgmD7yVG8M_WGWNytSrm8,4307
+mxlpy-0.19.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+mxlpy-0.19.0.dist-info/licenses/LICENSE,sha256=lHX9Eu70g3Iv1aOxXTWNHa3vq9vaVYSPQx4jOLYmDpw,1096
+mxlpy-0.19.0.dist-info/RECORD,,