scdesigner 0.0.3__py3-none-any.whl → 0.0.4__py3-none-any.whl

{scdesigner-0.0.3.dist-info → scdesigner-0.0.4.dist-info}/RECORD

@@ -6,14 +6,14 @@ scdesigner/data/sparse.py,sha256=lMp8gI8sq_fUTj3HiAmia0YiCdMRS1QGyyRePmuq3zY,138
 scdesigner/diagnose/__init__.py,sha256=XRBlc0_ns9Tbwq-aMWMIv1c-tcTOgRFQBywBFV46Gt4,3579
 scdesigner/diagnose/aic_bic.py,sha256=9GmtxdEXbbmCvL__pm7jSvQeeCb8KjwawY3UebahVBs,5022
 scdesigner/diagnose/plot.py,sha256=JP1vLbZVnMs171aOBawKbbCUgGiwIfCGKWrQyNh7Y2s,7225
-scdesigner/estimators/__init__.py,sha256=XqtTCAE02FyxMJkbnlg-qi-C_eF-OoOzP2wqa3MJEJ8,907
+scdesigner/estimators/__init__.py,sha256=TDkbc25TvXJp5O4_U2QipM8tmEoJ0HpNG53rlYthsBk,1221
 scdesigner/estimators/bernoulli.py,sha256=vnIETFbHjXErgkKps4ImgeM5W6nta0c-8-ZetYpqK8g,3324
 scdesigner/estimators/gaussian.py,sha256=-CKumYQWw8KbshdCmCdFgpcH5dNbqY-3vNTXCyjJbqc,4311
-scdesigner/estimators/gaussian_copula_factory.py,sha256=tAX4jABUWNmiheDot74k7yuRlviXwZ0iO7meECbotEM,5391
+scdesigner/estimators/gaussian_copula_factory.py,sha256=yeIx_C2fN2jiotTkJstV4pjQYW4aO6RJ-jMuuXR2HVs,14054
 scdesigner/estimators/glm_factory.py,sha256=tjVlEfJwBPK_Vk4G4P_eTYnBqeI8Y0r5_u_iSYB7qfA,2618
-scdesigner/estimators/negbin.py,sha256=JCVDIqFe-IfgYSmFz8gAPXFb4PiIaYiFTqNlU42iFZg,4812
+scdesigner/estimators/negbin.py,sha256=4q_XZOZA8gYHXOOY5Mz17cexs-kzadqB9JlxqWnZ7VQ,5639
 scdesigner/estimators/pnmf.py,sha256=-0WDbwh0uU4V-eyl_0uQ3qLZpT2IuEo9Pa-GEC6vJYI,4781
-scdesigner/estimators/poisson.py,sha256=-B-xXX-XRS22PQUkOTCFiT8HlWtKIXN2WCL_EJtb83w,3365
+scdesigner/estimators/poisson.py,sha256=FMYtkip2NDYmmkyEuO_9hSuM6gtM-AZpPa9GwFrFfD8,4174
 scdesigner/estimators/zero_inflated_negbin.py,sha256=OeMbXf20wzhJUmll2meMXBdLfeHGSya2hikmXNRUKI4,7959
 scdesigner/estimators/zero_inflated_poisson.py,sha256=2lrD2H4QMBxhNbak3gDUHVxPBURLS16IyfN5eCEbq9Q,3364
 scdesigner/format/__init__.py,sha256=PR12wZFvixIqHEd--d1oZkuj6o8tAQx-rgnpUKkr03I,179
@@ -21,20 +21,20 @@ scdesigner/format/format.py,sha256=WLsGnfeM52Mg3fhKHwPx0XbkYJSXfehu2_HmQfUpHdY,5
 scdesigner/format/print.py,sha256=HK3yLQcFw-f5-nSxMy52bD8Mixw_xxAYV2W9K4_ULwg,794
 scdesigner/minimal/__init__.py,sha256=IdMK1a2iiYyJ1gsWoupc2_3wyEu3Udjbm_iC0U724kM,378
 scdesigner/minimal/bernoulli.py,sha256=KvkXiS5aOYIT_L_xymaAWd92ZJyRXZowTcOv_b1RsJo,2304
-scdesigner/minimal/composite.py,sha256=H-OzRUzv52F49zw3eM9Bz6HPC4deXQDNr9zTkR_7Xz4,4548
-scdesigner/minimal/copula.py,sha256=VgjOuKgNhKgSnGEt8GXCdjUfIhucymHFTYmAtCn4c5U,1105
+scdesigner/minimal/composite.py,sha256=lOafmycSpW5U7Yrmm_NgRJx8Y9GvkuS0BVf8IGFse9c,4536
+scdesigner/minimal/copula.py,sha256=nNnK9Pxrp4-jlYWFY4NBt0hiUXGVHjMQMH5P5EhxLVw,8884
 scdesigner/minimal/formula.py,sha256=VFTadNxn-2elBvCkD_yuyh9O-vDZFiitSqjJkZYJy3Y,879
 scdesigner/minimal/gaussian.py,sha256=CKsluKk_XduYMNNUZTtENzH3wf4iTRGRc4L2nzq7qYw,2351
 scdesigner/minimal/kwargs.py,sha256=a32BLKNBj7ont5fR_uUpppYwel55dpP3fqaPeVbmCKM,979
 scdesigner/minimal/loader.py,sha256=gufdcWWKo7MyZQ5e7lzia96ZDKV5Pz8v0WwhZGQEeYM,5947
-scdesigner/minimal/marginal.py,sha256=mxGZH6walwNY8HUqYxp47chPrIysiLEMRacsqAvCxWI,5425
-scdesigner/minimal/negbin.py,sha256=RvReWG50h3LuBBfrHv34AFylcZ8TTjV5WOugR5tBTCg,2572
+scdesigner/minimal/marginal.py,sha256=Z_6eqZ6G6ua2Rckf65N1_S7CGkmv22SGzNQmdwSJiPo,5561
+scdesigner/minimal/negbin.py,sha256=NorV0CQ_wmKwTWuWd-Y1mE3gWYmVPHgmjp3pgI86bEI,2563
 scdesigner/minimal/positive_nonnegative_matrix_factorization.py,sha256=oMIC1aqdH4Cgn2pU446lh2-H3axEe-FSC_ZNcgSBrdk,7445
-scdesigner/minimal/scd3.py,sha256=8D8amY7zqSBgyRkrTvYzaf7r9i6mHNtZCCqeopcFbYY,3047
-scdesigner/minimal/scd3_instances.py,sha256=7Jb45VzEkpYegxbzqVlqpb-zMkIXebdiIMEWdZZnRzc,1993
+scdesigner/minimal/scd3.py,sha256=4EKi6Wonc0LRfWjLdvn8HMhbuR-c5kZbmVNLGbJd7mw,3083
+scdesigner/minimal/scd3_instances.py,sha256=vbCbF_SbCqyCUdi_STwV2ufn9ouoEk14_D9g4Wc9O14,1969
 scdesigner/minimal/simulator.py,sha256=DmeT_uXswR9larJ_OuysXUt32BqIVwxS-2yYMk9PGQw,631
-scdesigner/minimal/standard_covariance.py,sha256=9JlAI9C8bWSGSQRFtBYnKMnoF3UghB0DG08A4piOJ4E,4956
-scdesigner/minimal/transform.py,sha256=FdTOsPoGk3I-M-t8Ugmqx-Znxo0avJs5Os3kCkHotIk,4919
+scdesigner/minimal/standard_copula.py,sha256=-P7JIVxF4XgP2ZMK6Z7FEyzfasKESx-tNDlJ9EdByOU,16478
+scdesigner/minimal/transform.py,sha256=j2sj2vHpFi3YdK9sz4Npl05i8UPGBcDU3kT-n72u28s,5459
 scdesigner/minimal/zero_inflated_negbin.py,sha256=npDoyAGWs9n5rl3HwvAUvDG9UDG3DlwRMUGwkpeqvlc,3179
 scdesigner/predictors/__init__.py,sha256=3ycFB7ifR2y-27Kx2GhESyfcyZsJ-6ds6vxgzwrl6ss,462
 scdesigner/predictors/bernoulli.py,sha256=ln7GpOTh7nxCVX0nvARPXw0E-l3SalDwur0iUEz-SWQ,261
@@ -46,7 +46,7 @@ scdesigner/predictors/zero_inflated_poisson.py,sha256=Krr4r-9vkh7SVy3d45v226NVUY
 scdesigner/samplers/__init__.py,sha256=ns3tA_Q7jYIPgnYPfItvHCUpBV9fDimUg0dEHcNB7wE,775
 scdesigner/samplers/bernoulli.py,sha256=1GLOU69_D2sxcedmxC2dIj1MQbmX5D8i0ccvyxjTcR8,791
 scdesigner/samplers/gaussian.py,sha256=H8DwD4XzzALFguxB1uiwUsUURF_G1B6d2j4r0up-srU,943
-scdesigner/samplers/glm_factory.py,sha256=QUtphZEd-hWE8G0e8o98i3ojQqyvucqanrWiMN2oUew,1287
+scdesigner/samplers/glm_factory.py,sha256=aQvFTgBKAk7kV-SnFJ61aSHQGwemxW9Hl4ZXBmwGJug,3607
 scdesigner/samplers/negbin.py,sha256=d9oWIDxfXl_kNOPCjYUvtVie3uQmBN6yHfxHbrQiX-I,930
 scdesigner/samplers/poisson.py,sha256=_TxotqGuVDFRXJOIiBGqRE_qJK0XkXn96clkCDCRV1A,789
 scdesigner/samplers/zero_inflated_negbin.py,sha256=Z9kUSEQL8Z-lf48wWBLAuz74FcK7mjsKmeIzyBE9ov4,1287
@@ -58,9 +58,9 @@ scdesigner/simulators/pnmf_regression.py,sha256=B_fMK7Q9D4q31HT77384EKZEST7XXVNC
 scdesigner/transform/__init__.py,sha256=cuLIP0_tocIA3dupO7npH2mLFpL1ApLZlLWPudzPt6M,236
 scdesigner/transform/amplify.py,sha256=aNxpuyoDpXI4xK5FyCaGKqLqUh4SxFCZhwZeW8XonEQ,351
 scdesigner/transform/mask.py,sha256=z-NQ6xcnEzCFWvlfCRhQOrE-TWvtAwQ6Cs8KBPahBSk,1032
-scdesigner/transform/nullify.py,sha256=OjeS9UJA1Cm8LImuGFytIKnA-Oy_qXY_C9NBFMjyjNQ,780
+scdesigner/transform/nullify.py,sha256=pEtYNDVT2Z_BmVc5CKl3CoxB37KOvqMReoQGnvFYMKE,792
 scdesigner/transform/split.py,sha256=AK3mU52DHSagdyW-d79tsZ12zMKc5xMF_MockUUvciE,741
 scdesigner/transform/substitute.py,sha256=pozV7IVJLyUzJVKeaSX86v0bl9foSFIAQpZ0oC18xak,326
-scdesigner-0.0.3.dist-info/METADATA,sha256=r2NUcpEnqH9rvuRj3N-qv0yXU7e3yx4fKbojR_RLYvc,766
-scdesigner-0.0.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-scdesigner-0.0.3.dist-info/RECORD,,
+scdesigner-0.0.4.dist-info/METADATA,sha256=PCO4zfyrfvvMsgtZ26iYqEf3cyyFYY6e912X547Qk4g,766
+scdesigner-0.0.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+scdesigner-0.0.4.dist-info/RECORD,,

scdesigner/minimal/standard_covariance.py

@@ -1,124 +0,0 @@
-from .copula import Copula
-from .formula import standardize_formula
-from .kwargs import DEFAULT_ALLOWED_KWARGS, _filter_kwargs
-from anndata import AnnData
-from scipy.stats import norm, multivariate_normal
-from tqdm import tqdm
-from typing import Dict, Union, Callable, Tuple
-import numpy as np
-import pandas as pd
-import torch
-
-
-class StandardCovariance(Copula):
-    def __init__(self, formula: str = "~ 1"):
-        formula = standardize_formula(formula, allowed_keys=['group'])
-        super().__init__(formula)
-        self.groups = None
-
-
-    def setup_data(self, adata: AnnData, marginal_formula: Dict[str, str], **kwargs):
-        data_kwargs = _filter_kwargs(kwargs, DEFAULT_ALLOWED_KWARGS['data'])
-        super().setup_data(adata, marginal_formula, **data_kwargs)
-        _, obs_batch = next(iter(self.loader))
-        obs_batch_group = obs_batch.get("group")
-
-        # fill in group indexing variables
-        self.groups = self.loader.dataset.predictor_names["group"]
-        self.n_groups = len(self.groups)
-        self.group_col = {g: i for i, g in enumerate(self.groups)}
-
-        # check that obs_batch is a binary grouping matrix
-        unique_vals = torch.unique(obs_batch_group)
-        if (not torch.all((unique_vals == 0) | (unique_vals == 1)).item()):
-            raise ValueError("Only categorical groups are currently supported in copula covariance estimation.")
-
-    def fit(self, uniformizer: Callable, **kwargs):
-        sums = {g: np.zeros(self.n_outcomes) for g in self.groups}
-        second_moments = {g: np.eye(self.n_outcomes) for g in self.groups}
-        Ng = {g: 0 for g in self.groups}
-
-        for y, x_dict in tqdm(self.loader, desc="Estimating copula covariance"):
-            memberships = x_dict.get("group").numpy()
-            u = uniformizer(y, x_dict)
-
-            for g in self.groups:
-                ix = np.where(memberships[:, self.group_col[g]] == 1)
-                z = norm().ppf(u[ix])
-                second_moments[g] += z.T @ z
-                sums[g] += z.sum(axis=0)
-                Ng[g] += len(ix[0])
-
-        covariances = {}
-        for g in self.groups:
-            mean = sums[g] / Ng[g]
-            covariances[g] = second_moments[g] / Ng[g] - np.outer(mean, mean)
-
-        if len(self.groups) == 1:
-            covariances = list(covariances.values())[0]
-        self.parameters = self.format_parameters(covariances)
-
-    def format_parameters(self, covariances: Union[Dict, np.array]):
-        var_names = self.adata.var_names
-        def to_df(mat):
-            return pd.DataFrame(mat, index=var_names, columns=var_names)
-
-        if isinstance(covariances, dict):
-            formatted = {}
-            for k, v in covariances.items():
-                formatted[k] = to_df(v)
-            covariances = formatted
-            return covariances
-
-        if isinstance(covariances, (np.ndarray, list, tuple)):
-            covariances = to_df(covariances)
-        return covariances
-
-    def pseudo_obs(self, x_dict: Dict):
-        # convert one-hot encoding memberships to a map
-        #      {"group1": [indices of group 1], "group2": [indices of group 2]}
-        memberships = x_dict.get("group").numpy()
-        group_ix = {g: np.where(memberships[:, self.group_col[g] == 1])[0] for g in self.groups}
-
-        # initialize the result
-        u = np.zeros((len(memberships), self.n_outcomes))
-        parameters = self.parameters
-        if type(parameters) is not dict:
-            parameters = {group: parameters}
-
-        # loop over groups and sample each part in turn
-        for group, sigma in parameters.items():
-            z = np.random.multivariate_normal(
-                mean=np.zeros(self.n_outcomes),
-                cov=sigma,
-                size=len(group_ix[group])
-            )
-            normal_distn = norm(0, np.diag(sigma) ** 0.5)
-            u[group_ix[group]] = normal_distn.cdf(z)
-        return u
-
-    def likelihood(self, uniformizer: Callable, batch: Tuple[torch.Tensor, Dict[str, torch.Tensor]]):
-        # uniformize the observations
-        y, x_dict = batch
-        u = uniformizer(y, x_dict)
-        z = norm().ppf(u)
-
-        # same group manipulation as for pseudobs
-        parameters = self.parameters
-        if type(parameters) is not dict:
-            parameters = {group: parameters}
-
-        memberships = x_dict.get("group").numpy()
-        group_ix = {g: np.where(memberships[:, self.group_col[g] == 1])[0] for g in self.groups}
-        ll = np.zeros(len(z))
-        for group, sigma in parameters.items():
-            ix = group_ix[group]
-            if len(ix) > 0:
-                copula_ll = multivariate_normal.logpdf(z[ix], np.zeros(sigma.shape[0]), sigma)
-                ll[ix] = copula_ll - norm.logpdf(z[ix]).sum(axis=1)
-        return ll
-
-    def num_params(self, **kwargs):
-        S = self.parameters
-        per_group = [(np.sum(S[g].values != 0) - S[g].shape[0]) / 2 for g in self.groups]
-        return sum(per_group)