scdesigner 0.0.5__py3-none-any.whl → 0.0.10__py3-none-any.whl

scdesigner/simulators/scd3.py

@@ -0,0 +1,486 @@
+from ..base.copula import Copula
+from ..data.loader import obs_loader, adata_loader
+from ..base.marginal import Marginal
+from ..base.simulator import Simulator
+from anndata import AnnData
+from tqdm import tqdm
+import torch
+import numpy as np
+from ..distributions import (
+    NegBin,
+    NegBinIRLS,
+    ZeroInflatedNegBin,
+    Gaussian,
+    Poisson,
+    ZeroInflatedPoisson,
+    Bernoulli,
+)
+from ..copulas import StandardCopula
+from typing import Optional
+from abc import ABC
+
+
+class SCD3Simulator(Simulator, ABC):
+    """High-level simulation wrapper combining a marginal model and a copula.
+
+    The :class:`SCD3Simulator` class coordinates fitting of a marginal model
+    (e.g. negative binomial, zero-inflated negative binomial) together with a
+    dependence structure specified by a copula (e.g. :class:`StandardCopula`).
+    Subclasses provide concrete combinations of marginal and copula models
+    tailored to common use cases.
+
+    Parameters
+    ----------
+    marginal : Marginal
+        Fitted or unfitted marginal model describing the distribution of each
+        feature (e.g. gene) conditional on covariates.
+    copula : Copula
+        Copula object that captures dependence between features and shares
+        the same covariate structure as the marginal model.
+
+    Attributes
+    ----------
+    marginal : Marginal
+        The marginal model instance used for fitting and simulation.
+    copula : Copula
+        The copula instance used to model dependence between features.
+    template : AnnData or None
+        Reference dataset used to define the observed covariate space and
+        feature set for simulation. Set during :meth:`fit`.
+    parameters : dict or None
+        Dictionary containing fitted parameters for both the marginal and
+        copula components after :meth:`fit` has been called.
+
+    Examples
+    --------
+    The abstract :class:`SCD3Simulator` is not used directly. Instead, use one
+    of its concrete subclasses, e.g. :class:`NegBinCopula`::
+
+        >>> import scanpy as sc
+        >>> from scdesigner.simulators.scd3 import NegBinCopula
+        >>>
+        >>> adata = sc.datasets.pbmc3k()[:, :100].copy()
+        >>>
+        >>> # Mean expression depends on group; copula uses the same group structure
+        >>> sim = NegBinCopula(mean_formula="~ 1", dispersion_formula="~ 1",
+        ...                    copula_formula="~ 1")
+        >>> sim.fit(adata, batch_size=256, max_epochs=10) # doctest: +SKIP
+        >>>
+        >>> # Generate synthetic data with the same obs covariates
+        >>> synthetic = sim.sample(batch_size=512) # doctest: +SKIP
+        >>> synthetic.X.shape == adata.shape # doctest: +SKIP
+        True
+        >>>
+        >>> # Compute model complexity via AIC/BIC of the copula component
+        >>> metrics = sim.complexity() # doctest: +SKIP
+        >>> sorted(metrics.keys()) # doctest: +SKIP
+        ['aic', 'bic'] # doctest: +SKIP
+    """
+
+    def __init__(self, marginal: Marginal, copula: Copula):
+        self.marginal = marginal
+        self.copula = copula
+        self.template = None
+        self.parameters = None
+
+    def fit(self, adata: AnnData, **kwargs):
+        """Fit marginal and copula components to an AnnData object.
+
+        Parameters
+        ----------
+        adata : AnnData
+            Input dataset with cells in rows and features (e.g. genes) in
+            columns. Both the marginal and copula components are fitted to
+            this data.
+        **kwargs
+            Additional keyword arguments forwarded to the marginal and copula
+            fit routines (e.g. ``batch_size``, optimization settings).
+
+        Notes
+        -----
+        This method sets the :attr:`template` attribute to ``adata`` and
+        stores fitted parameters in :attr:`parameters`.
+        """
+        self.template = adata
+        self.marginal.setup_data(adata, **kwargs)
+        self.marginal.setup_optimizer(**kwargs)
+        self.marginal.fit(**kwargs)
+
+        # copula simulator
+        self.copula.setup_data(adata, self.marginal.formula, **kwargs)
+        self.copula.fit(self.marginal.uniformize, **kwargs)
+        self.parameters = {
+            "marginal": self.marginal.parameters,
+            "copula": self.copula.parameters,
+        }
+
+    def predict(self, obs=None, batch_size: int = 1000, **kwargs):
+        """Predict marginal parameters for given covariates.
+
+        Parameters
+        ----------
+        obs : pandas.DataFrame or None, optional
+            Observation-level covariate table. If ``None``, use
+            ``self.template.obs`` from the dataset provided to :meth:`fit`.
+        batch_size : int, optional
+            Number of observations per mini-batch used during prediction.
+        **kwargs
+            Additional keyword arguments passed to :func:`obs_loader`.
+
+        Returns
+        -------
+        dict
+            Dictionary mapping parameter names (e.g. ``"mean"``,
+            ``"dispersion"``) to NumPy arrays of shape ``(n_cells, n_genes)``
+            containing the predicted marginal parameters.
+        """
+        # prepare an internal data loader for this obs
+        if obs is None:
+            obs = self.template.obs
+        loader = obs_loader(obs, self.marginal.formula, batch_size=batch_size, **kwargs)
+
+        # get predictions across batches
+        local_parameters = []
+        for _, x_dict in loader:
+            l = self.marginal.predict(x_dict)
+            local_parameters.append(l)
+
+        # convert to a merged dictionary
+        keys = list(local_parameters[0].keys())
+        return {
+            k: torch.cat([d[k] for d in local_parameters]).detach().cpu().numpy()
+            for k in keys
+        }
+
+    def sample(self, obs=None, batch_size: int = 1000, **kwargs):
+        """Generate synthetic observations from the fitted model.
+
+        Parameters
+        ----------
+        obs : pandas.DataFrame or None, optional
+            Observation-level covariate table defining the covariate space
+            for simulation. If ``None``, use ``self.template.obs``.
+        batch_size : int, optional
+            Number of observations per mini-batch used during sampling.
+        **kwargs
+            Additional keyword arguments passed to :func:`obs_loader`.
+
+        Returns
+        -------
+        AnnData
+            An :class:`AnnData` object with simulated counts in ``.X`` and
+            ``obs`` equal to the provided covariate table.
+        """
+        if obs is None:
+            obs = self.template.obs
+        loader = obs_loader(
+            obs,
+            self.copula.formula | self.marginal.formula,
+            batch_size=batch_size,
+            **kwargs,
+        )
+
+        # get samples across batches
+        samples = []
+        for _, x_dict in loader:
+            u = self.copula.pseudo_obs(x_dict)
+            u = torch.from_numpy(u)
+            samples.append(self.marginal.invert(u, x_dict))
+        samples = torch.cat(samples).detach().cpu().numpy()
+        return AnnData(X=samples, obs=obs)
+
+    def complexity(self, adata: AnnData = None, **kwargs):
+        """Compute model complexity metrics (AIC, BIC) for the copula component.
+
+        Parameters
+        ----------
+        adata : AnnData or None, optional
+            Dataset to evaluate the copula log-likelihood on. If ``None``,
+            use the template dataset stored during :meth:`fit`.
+        **kwargs
+            Additional keyword arguments passed to :func:`adata_loader`.
+
+        Returns
+        -------
+        dict
+            Dictionary with keys ``"aic"`` and ``"bic"`` computed from the
+            copula log-likelihood and :meth:`copula.num_params`.
+        """
+        if adata is None:
+            adata = self.template
+
+        N, ll = 0, 0
+        loader = adata_loader(
+            adata, self.marginal.formula | self.copula.formula, **kwargs
+        )
+        for batch in tqdm(loader, desc="Computing log-likelihood..."):
+            ll += self.copula.likelihood(self.marginal.uniformize, batch).sum()
+            N += len(batch[0])
+
+        return {
+            "aic": -2 * ll + 2 * self.copula.num_params(),
+            "bic": -2 * ll + np.log(N) * self.copula.num_params(),
+        }
+
+
+################################################################################
+## SCD3 instances
+################################################################################
+
+
+class NegBinCopula(SCD3Simulator):
+    """Simulator using negative binomial marginals with a Gaussian copula.
+
+    Parameters
+    ----------
+    mean_formula : str or None, optional
+        Model formula for the mean parameter of the negative binomial
+        marginal (e.g. ``"~ 1"`` or ``"~ group"``). If ``None``, a
+        default constant-mean formula is used.
+    dispersion_formula : str or None, optional
+        Model formula for the dispersion parameter of the negative
+        binomial marginal. If ``None``, a default constant-dispersion
+        formula is used.
+    copula_formula : str or None, optional
+        Copula formula describing how copula depends on experimental
+        or biological conditions (e.g. ``"~ group"``).If ``None``,
+        a default intercept-only formula is used.
+
+    See Also
+    --------
+    :class:`SCD3Simulator`
+    :class:`NegBin`
+    :class:`StandardCopula`
+    """
+
+    def __init__(
+        self,
+        mean_formula: Optional[str] = None,
+        dispersion_formula: Optional[str] = None,
+        copula_formula: Optional[str] = None,
+    ) -> None:
+        marginal = NegBin({"mean": mean_formula, "dispersion": dispersion_formula})
+        covariance = StandardCopula(copula_formula)
+        super().__init__(marginal, covariance)
+
+
+class ZeroInflatedNegBinCopula(SCD3Simulator):
+    """Simulator using zero-inflated negative binomial marginals with
+    a Gaussian copula.
+
+    Parameters
+    ----------
+    mean_formula : str or None, optional
+        Model formula for the mean parameter of the zero-inflated
+        negative binomial marginal (e.g. ``"~ 1"`` or ``"~ group"``).
+        If ``None``, a default constant-mean formula is used.
+    dispersion_formula : str or None, optional
+        Model formula for the dispersion parameter of the zero-inflated
+        negative binomial marginal. If ``None``, a default
+        constant-dispersion formula is used.
+    zero_inflation_formula : str or None, optional
+        Model formula for the zero-inflation parameter of the zero-inflated
+        negative binomial marginal. If ``None``, a default
+        constant-zero-inflation formula is used.
+    copula_formula : str or None, optional
+        Copula formula describing how copula depends on experimental or
+        biological conditions (e.g. ``"~ group"``). If ``None``, a default
+        intercept-only formula is used.
+
+    See Also
+    --------
+    :class:`SCD3Simulator`
+    :class:`ZeroInflatedNegBin`
+    :class:`StandardCopula`
+    """
+
+    def __init__(
+        self,
+        mean_formula: Optional[str] = None,
+        dispersion_formula: Optional[str] = None,
+        zero_inflation_formula: Optional[str] = None,
+        copula_formula: Optional[str] = None,
+    ) -> None:
+        marginal = ZeroInflatedNegBin(
+            {
+                "mean": mean_formula,
+                "dispersion": dispersion_formula,
+                "zero_inflation_formula": zero_inflation_formula,
+            }
+        )
+        covariance = StandardCopula(copula_formula)
+        super().__init__(marginal, covariance)
+
+
+class BernoulliCopula(SCD3Simulator):
+    """Simulator using Bernoulli marginals with a Gaussian copula.
+
+    Parameters
+    ----------
+    mean_formula : str or None, optional
+        Model formula for the mean parameter of the Bernoulli marginal
+        (e.g. ``"~ 1"`` or ``"~ group"``). If ``None``, a default
+        constant-mean formula is used.
+    copula_formula : str or None, optional
+        Copula formula describing how copula depends on experimental or
+        biological conditions (e.g. ``"~ group"``). If ``None``, a default
+        intercept-only formula is used.
+
+    See Also
+    --------
+    :class:`SCD3Simulator`
+    :class:`Bernoulli`
+    :class:`StandardCopula`
+    """
+
+    def __init__(
+        self, mean_formula: Optional[str] = None, copula_formula: Optional[str] = None
+    ) -> None:
+        marginal = Bernoulli({"mean": mean_formula})
+        covariance = StandardCopula(copula_formula)
+        super().__init__(marginal, covariance)
+
+
+class GaussianCopula(SCD3Simulator):
+    """Simulator using Gaussian marginals with a Gaussian copula.
+
+    Parameters
+    ----------
+    mean_formula : str or None, optional
+        Model formula for the mean parameter of the Gaussian marginal
+        (e.g. ``"~ 1"`` or ``"~ group"``). If ``None``, a default
+        constant-mean formula is used.
+    sdev_formula : str or None, optional
+        Model formula for the standard deviation parameter of the Gaussian marginal.
+        If ``None``, a default constant-standard deviation formula is used.
+    copula_formula : str or None, optional
+        Copula formula describing how copula depends on experimental or
+        biological conditions (e.g. ``"~ group"``). If ``None``, a default
+        intercept-only formula is used.
+
+    See Also
+    --------
+    :class:`SCD3Simulator`
+    :class:`Gaussian`
+    :class:`StandardCopula`
+    """
+
+    def __init__(
+        self,
+        mean_formula: Optional[str] = None,
+        sdev_formula: Optional[str] = None,
+        copula_formula: Optional[str] = None,
+    ) -> None:
+        marginal = Gaussian({"mean": mean_formula, "sdev": sdev_formula})
+        covariance = StandardCopula(copula_formula)
+        super().__init__(marginal, covariance)
+
+
+class PoissonCopula(SCD3Simulator):
+    """Simulator using Poisson marginals with a Gaussian copula.
+
+    Parameters
+    ----------
+    mean_formula : str or None, optional
+        Model formula for the mean parameter of the Poisson marginal
+        (e.g. ``"~ 1"`` or ``"~ group"``). If ``None``, a default
+        constant-mean formula is used.
+    copula_formula : str or None, optional
+        Copula formula describing how copula depends on experimental or
+        biological conditions (e.g. ``"~ group"``). If ``None``, a default
+        intercept-only formula is used.
+
+    See Also
+    --------
+    :class:`SCD3Simulator`
+    :class:`Poisson`
+    :class:`StandardCopula`
+    """
+
+    def __init__(
+        self, mean_formula: Optional[str] = None, copula_formula: Optional[str] = None
+    ) -> None:
+        marginal = Poisson({"mean": mean_formula})
+        covariance = StandardCopula(copula_formula)
+        super().__init__(marginal, covariance)
+
+
+class ZeroInflatedPoissonCopula(SCD3Simulator):
+    """Simulator using zero-inflated Poisson marginals with a Gaussian copula.
+
+    Parameters
+    ----------
+    mean_formula : str or None, optional
+        Model formula for the mean parameter of the zero-inflated Poisson marginal
+        (e.g. ``"~ 1"`` or ``"~ group"``). If ``None``, a default
+        constant-mean formula is used.
+    zero_inflation_formula : str or None, optional
+        Model formula for the zero-inflation parameter of the zero-inflated Poisson
+        marginal. If ``None``, a default constant-zero-inflation formula is used.
+    copula_formula : str or None, optional
+        Copula formula describing how copula depends on experimental or
+        biological conditions (e.g. ``"~ group"``). If ``None``, a default
+        intercept-only formula is used.
+
+    See Also
+    --------
+    :class:`SCD3Simulator`
+    :class:`ZeroInflatedPoisson`
+    :class:`StandardCopula`
+    """
+
+    def __init__(
+        self,
+        mean_formula: Optional[str] = None,
+        zero_inflation_formula: Optional[str] = None,
+        copula_formula: Optional[str] = None,
+    ) -> None:
+        marginal = ZeroInflatedPoisson(
+            {"mean": mean_formula, "zero_inflation": zero_inflation_formula}
+        )
+        covariance = StandardCopula(copula_formula)
+        super().__init__(marginal, covariance)
+
+class NegBinIRLSCopula(SCD3Simulator):
+    """Simulator using negative binomial marginals with a Gaussian copula.
+
+    Parameters
+    ----------
+    mean_formula : str or None, optional
+        Model formula for the mean parameter of the negative binomial
+        marginal (e.g. ``"~ 1"`` or ``"~ group"``). If ``None``, a
+        default constant-mean formula is used.
+    dispersion_formula : str or None, optional
+        Model formula for the dispersion parameter of the negative
+        binomial marginal. If ``None``, a default constant-dispersion
+        formula is used.
+    copula_formula : str or None, optional
+        Copula formula describing how copula depends on experimental
+        or biological conditions (e.g. ``"~ group"``).If ``None``,
+        a default intercept-only formula is used.
+
+    See Also
+    --------
+    :class:`SCD3Simulator`
+    :class:`NegBin`
+    :class:`StandardCopula`
+    """
+
+    def __init__(
+        self,
+        mean_formula: Optional[str] = None,
+        dispersion_formula: Optional[str] = None,
+        copula_formula: Optional[str] = None
+    ) -> None:
+        marginal = NegBinIRLS({"mean": mean_formula, "dispersion": dispersion_formula})
+        covariance = StandardCopula(copula_formula)
+        super().__init__(marginal, covariance)
+
+    def fit(self, adata: AnnData, batch_size: int = 8224, device="cpu", **kwargs):
+        super().fit(adata, batch_size=batch_size, device=device, **kwargs)
+
+    def sample(self, obs=None, batch_size: int = 8224, **kwargs):
+        return super().sample(obs, batch_size, device="cpu", **kwargs)
+
+    def predict(self, obs=None, batch_size: int = 8224, **kwargs):
+        return super().predict(obs, batch_size, device="cpu", **kwargs)

scdesigner/transform/__init__.py

@@ -1,7 +1,9 @@
-from .nullify import nullify
-from .amplify import amplify
-from .substitute import substitute
-from .split import split_glm
-from .mask import data_frame_mask
+from .transform import nullify, amplify, decorrelate, correlate, replace_param
 
-__all__ = ["amplify", "nullify", "data_frame_mask", "substitute", "split_glm"]
+__all__ = [
+    "nullify",
+    "amplify",
+    "decorrelate",
+    "correlate",
+    "replace_param",
+]

scdesigner/{minimal → transform}/transform.py

@@ -4,7 +4,7 @@ import pandas as pd
 import re
 import torch
 import copy
-from .copula import CovarianceStructure
+from ..base.copula import CovarianceStructure
 
 
 def nullify(sim, row_pattern: str, col_pattern: str, param: str):

scdesigner/{minimal → utils}/kwargs.py

@@ -11,7 +11,7 @@ DEFAULT_ALLOWED_KWARGS = {
         'log_every_n_steps', 'accumulate_grad_batches'
     },
     'data': {
-        'chunk_size', 'batch_size', 'shuffle', 'num_workers'
+        'chunk_size', 'batch_size', 'shuffle', 'num_workers', 'device'
     },
     'optimizer': {
         'lr', 'learning_rate', 'momentum', 'weight_decay', 'eps', 'betas',
@@ -20,5 +20,8 @@ DEFAULT_ALLOWED_KWARGS = {
         'verbose', 'patience', 'threshold', 'cooldown',
         'optimizer_class', 'optimizer', 'scheduler_class', 'scheduler',
         'monitor', 'interval', 'frequency'
+    },
+    'initialize': {
+        'tol', 'clamp', 'max_iter'
     }
 }

{scdesigner-0.0.5.dist-info → scdesigner-0.0.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scdesigner
-Version: 0.0.5
+Version: 0.0.10
 Summary: Interactive simulation for rigorous and transparent multi-omics analysis.
 Project-URL: Homepage, https://github.com/krisrs1128/scDesigner/
 Project-URL: Issues, https://github.com/krisrs1128/scDesigner/Issues/

scdesigner-0.0.10.dist-info/RECORD

@@ -0,0 +1,28 @@
+scdesigner/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+scdesigner/base/__init__.py,sha256=At6IcDGIUZmFzYaquqbPtrNTEszYUDjH3yMP6Z6gHqE,140
+scdesigner/base/copula.py,sha256=M4PlrMKqztrjlfqhz3zpNV7HKMhOqJvZw6XEBFsixGs,16335
+scdesigner/base/marginal.py,sha256=zMeFihI1G2GXqU8wnKym9BmbxC3Dv0e9xB-rXuyAWHI,17230
+scdesigner/base/simulator.py,sha256=ImJoz-kb5s4Y_4LdpiKENIR7SRbYy4-sKtuxRF9lFAA,1989
+scdesigner/copulas/__init__.py,sha256=wYUnNDtn5Yga16oa709rW34IvFx_A5RiNf76EywernU,137
+scdesigner/copulas/standard_copula.py,sha256=TuXFOczyZLYR38n41TqG1lYmWw3oJKe4UcUQfoFaw1I,23930
+scdesigner/datasets/__init__.py,sha256=ZPMHA8hma-HVhVlIEkRy7AFNO7DTe_W1GmQ4ME4aMnw,90
+scdesigner/datasets/pancreas.py,sha256=Ds5MgXFRqmDQE4bOfGm-Wza2yiSlFMSIp45-7oP7bpQ,1107
+scdesigner/distributions/__init__.py,sha256=WnLKtxD99flKe6zTgtrV0WdFPbPixRrmVDn8lN2ALuM,458
+scdesigner/distributions/bernoulli.py,sha256=CueT4E7aUXRagCVQujBpMyJ9dksZC144wPtDE7jXej4,3273
+scdesigner/distributions/gaussian.py,sha256=zKy9BShPRqgpXr_32fX8Bwd0lLIdJmdMzINO3BbhMbU,4197
+scdesigner/distributions/negbin.py,sha256=qe_Br_kHd4A8ufw65Xpaa9S0YFXW9buyz81fv4cxD6E,4511
+scdesigner/distributions/negbin_irls.py,sha256=-2oI9vB3g1y2eFT9C6sRn3oCnPAhfQm5L-X5Y81EQYo,3078
+scdesigner/distributions/negbin_irls_funs.py,sha256=VfrSUAW7EPpnohtE6QAafpvyNJp03PG40cnc-B9Qzas,15016
+scdesigner/distributions/poisson.py,sha256=cjREg6oXyVPMfYc7vL1thhk4HbmQqf80JjTEe0cs9aU,3145
+scdesigner/distributions/zero_inflated_negbin.py,sha256=eVeRgHQb8OilenGekkA_hX4JJcfOMS34PtY68n2YgeQ,4409
+scdesigner/distributions/zero_inflated_poisson.py,sha256=AH4SCbYP7swqsLlNcNo7A-KponmjdOh-8xybf_g6YgE,3943
+scdesigner/simulators/__init__.py,sha256=OnkPOCXyXH9zfn8Q2vTrUwMXtMwgHwBn12f7j_sMfRM,587
+scdesigner/simulators/composite.py,sha256=1H69xBQNMBZgWYFyd3RDVrzqh6i_5QrnaxXsCR56v-o,9149
+scdesigner/simulators/positive_nonnegative_matrix_factorization.py,sha256=KnPLlN5MgNdHRxehA9G9g7rxT_ZOt6eiiJZRN0lkzyQ,15505
+scdesigner/simulators/scd3.py,sha256=x1gHFnuDxDFBvx-BVzmJwGrNUG22G32d_ng8PnfviQQ,17739
+scdesigner/transform/__init__.py,sha256=F56wBgxPXRv0LYF91FL--R3qfFIsBLe2C9aJyiy7zD8,180
+scdesigner/transform/transform.py,sha256=xhq1fdfCfQGG5bCkSF_bQUCrf9FxNqd6IOMw-PCqOIY,5465
+scdesigner/utils/kwargs.py,sha256=7JAY8Bd47CrMnmlmGoPRViCvvg1DgyjftFPm5PSa36A,1051
+scdesigner-0.0.10.dist-info/METADATA,sha256=5zHm2anjobQkgDQn12MkgNUbQbL306LcQc9iC6j7v_A,742
+scdesigner-0.0.10.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+scdesigner-0.0.10.dist-info/RECORD,,

{scdesigner-0.0.5.dist-info → scdesigner-0.0.10.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.27.0
+Generator: hatchling 1.28.0
 Root-Is-Purelib: true
 Tag: py3-none-any

scdesigner/data/__init__.py

@@ -1,16 +0,0 @@
-from .formula import FormulaViewDataset, formula_loader, multiple_formula_loader, standardize_formula
-from .group import FormulaGroupViewDataset, formula_group_loader, stack_collate, multiple_formula_group_loader
-from .sparse import SparseMatrixDataset, SparseMatrixLoader
-
-__all__ = [
-    "FormulaViewDataset",
-    "SparseMatrixDataset",
-    "SparseMatrixLoader",
-    "FormulaGroupViewDataset",
-    "formula_loader",
-    "formula_group_loader",
-    "stack_collate",
-    "multiple_formula_loader",
-    "multiple_formula_group_loader",
-    "standardize_formula"
-]