U md,@sddlmZmZddlZddlmZmZddlm Z m Z ddl m Z m Z ddlmZddlmZdd lmZd d lmZdd lmZdd lmZdeeejefeeeeeeeeeeeeeeeeejefd ddZdddZdS))OptionalUnionN)issparsespmatrix)LinearOperatorsvds) check_arraycheck_random_state)svd_flip)AnnData)logging) _get_mean_var) AnyRandom)settingsTarpackFfloat32) datan_comps zero_center svd_solver random_state return_infouse_highly_variabledtypecopychunked chunk_sizereturnc Cstd} |dkr | s tdt|t} | r@|r:|n|} nt||jd} |dkrld| jkrltd|dkrd| jkrdnd }|rtd |r| dd| jdfn| }|dkrt |j |j }t j |kr|d }nt j }td |t|}|j}| r|r |s |d kr*tdddlm}t|jd|f|j}||d}|| D],\}}}t|r~|n|}||qb|| D]4\}}}t|r|n|}|||||<qn$t|r|dkr:|r:ddlm}t|r |dkr td|}||||d}||}nt|r|rddlm}|dkrdd }|dkrvtdt||||d}|d}|||d}|d|_|d|_ |d|_!n>|sddlm"}td ||||d!}||}nt#d"|jj$t|j$kr|%|}| r|| j&d<i| j'd#<||d$| j'd#d%<|r~tj| j |fd&| j(d'<|jj)| j(d'| jd<n|jj)| j(d'<|j | j'd#d<|j!| j'd#d<tjd(| d)td*|r| SdStjd(| d)|r||j|j!|j fS|SdS)+u| Principal component analysis [Pedregosa11]_. Computes PCA coordinates, loadings and variance decomposition. Uses the implementation of *scikit-learn* [Pedregosa11]_. .. versionchanged:: 1.5.0 In previous versions, computing a PCA on a sparse matrix would make a dense copy of the array for mean centering. As of scanpy 1.5.0, mean centering is implicit. While results are extremely similar, they are not exactly the same. If you would like to reproduce the old results, pass a dense array. Parameters ---------- data The (annotated) data matrix of shape `n_obs` × `n_vars`. Rows correspond to cells and columns to genes. n_comps Number of principal components to compute. Defaults to 50, or 1 - minimum dimension size of selected representation. zero_center If `True`, compute standard PCA from covariance matrix. If `False`, omit zero-centering variables (uses :class:`~sklearn.decomposition.TruncatedSVD`), which allows to handle sparse input efficiently. Passing `None` decides automatically based on sparseness of the data. svd_solver SVD solver to use: `'arpack'` (the default) for the ARPACK wrapper in SciPy (:func:`~scipy.sparse.linalg.svds`) `'randomized'` for the randomized algorithm due to Halko (2009). `'auto'` chooses automatically depending on the size of the problem. `'lobpcg'` An alternative SciPy solver. .. versionchanged:: 1.4.5 Default value changed from `'auto'` to `'arpack'`. Efficient computation of the principal components of a sparse matrix currently only works with the `'arpack`' or `'lobpcg'` solvers. random_state Change to use different initial states for the optimization. return_info Only relevant when not passing an :class:`~anndata.AnnData`: see “**Returns**”. use_highly_variable Whether to use highly variable genes only, stored in `.var['highly_variable']`. By default uses them if they have been determined beforehand. dtype Numpy data type string to which to convert the result. copy If an :class:`~anndata.AnnData` is passed, determines whether a copy is returned. Is ignored otherwise. chunked If `True`, perform an incremental PCA on segments of `chunk_size`. The incremental PCA automatically zero centers and ignores settings of `random_seed` and `svd_solver`. If `False`, perform a full PCA. chunk_size Number of observations to include in each chunk. Required if `chunked=True` was passed. Returns ------- X_pca : :class:`~scipy.sparse.spmatrix`, :class:`~numpy.ndarray` If `data` is array-like and `return_info=False` was passed, this function only returns `X_pca`… adata : anndata.AnnData …otherwise if `copy=True` it returns or else adds fields to `adata`: `.obsm['X_pca']` PCA representation of data. `.varm['PCs']` The principal components containing the loadings. `.uns['pca']['variance_ratio']` Ratio of explained variance. `.uns['pca']['variance']` Explained variance, equivalent to the eigenvalues of the covariance matrix. z computing PCA> randomizedautozNote that scikit-learn's randomized PCA might not be exactly reproducible across different computational platforms. For exact reproducibility, choose `svd_solver='arpack'.`)rTZhighly_variablezDid not find adata.var['highly_variable']. Either your data already only consists of highly-variable genes or consider running `pp.highly_variable_genes` first.NFz on highly variable genesrz with n_comps=rz.Ignoring zero_center, random_state, svd_solverr)IncrementalPCA) n_componentsr )PCAz{svd_solver 'randomized' does not work with sparse input. Densifying the array. This may take a very large amount of memory.)r#rrr!>lobpcgrzksvd_solver: {svd_solver} can not be used with sparse input. Use "arpack" (the default) or "lobpcg" instead.)solverrX_pca)r#r componentsvariancevariance_ratio) TruncatedSVDa without zero-centering: the explained variance does not correspond to the exact statistical defintion the first component, e.g., might be heavily influenced by different means the following components often resemble the exact PCA very closely)r#r algorithmz0This shouldn't happen. Please open a bug report.pca)rrparams)shapeZPCsz finished)timezand added 'X_pca', the PCA coordinates (adata.obs) 'PC1', 'PC2', ..., the loadings (adata.var) 'pca_variance', the variance / eigenvalues (adata.uns) 'pca_variance_ratio', the variance ratio (adata.uns))*logginfo isinstancer rrvarkeys ValueErrorminZn_varsZn_obsrZN_PCSr XdebugZsklearn.decompositionr"npZzerosr/Z chunked_XrZtoarrayZ partial_fitZ transformr$warningZ fit_transform_pca_with_sparseZ components_Zexplained_variance_Zexplained_variance_ratio_r+ ExceptiondescrZastypeZobsmZunsZvarmT)rrrrrrrrrrrZ logg_startZdata_is_AnnDataZadataZ adata_compZmin_dimr8r"r'Zpca_chunk_startendr$outputr+rER/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/scanpy/preprocessing/_pca.pyr-sc                       r-cst|}tj|tjt|j}t|ddgd}|dkr`| dj dddf}|j |j j |j j |j |j j t|jddddfj fdd}fdd}fd d }fd d } t||j||j|| d } t| |||d\} } } t| | \} } t| }| |ddf} | | dd|f}| |d|jdd}t|d}||}|||| d}|S)NZcsrZcsc)Z accept_sparsercs||SNrEx)XdotmdotrErFmatvecsz _pca_with_sparse..matveccs||SrGrErH)XmatmmatrErFmatmatsz _pca_with_sparse..matmatcs||SrGrErH)XHdotmhdotonesrErFrmatvec sz!_pca_with_sparse..rmatveccs||SrGrErH)XHmatmhmatrRrErFrmatmat#sz!_pca_with_sparse..rmatmat)rLrrOr/rSrV)r&kZv0r r)r'r)r*r()r r:randomZ set_stateZ get_stateZrandr7r/rZmeanAflattendotr?ZconjrRrrrr Zargsortrsum)r8Znpcsr&murZ random_initrLrOrSrVZXLusvidxr'ZevZ total_varZev_ratiorDrE) rPrTrJrMrKrQrUrNrRrFr<sR   r<) NTrrFNrFFN)rNN)typingrrnumpyr:Z scipy.sparserrZscipy.sparse.linalgrrZ sklearn.utilsrr Zsklearn.utils.extmathr Zanndatar r r1_utilsrrrZndarrayintboolstrr-r<rErErErFsH       x