U md#@sddlmZmZddlmZddlZddlZddl m Z ddl m Z ddl mZmZmZmZmZmZmZddlmZeeeeeeedd dd dd d did d d eeeeeeeeeeeeeeeeeeejfd ddZdS))OptionalTuple)AnnDataN) experimental)pca) doc_adatadoc_dist_paramsdoc_genes_batch_chunk doc_pca_chunk doc_layerdoc_check_values doc_inplace) _doc_params)adataZ dist_paramsZgenes_batch_chunkZ pca_chunk check_valuesinplacedi2T) thetaclip n_top_genes batch_key chunksizen_comps random_state kwargs_pcarr) rrrrrrrrrrrreturnc  Cs:td|||||| d} | rNtjj|f| ddi|dd|jdf} n0tjj|f| ddi} |dd| df} tjj| ||| dt| f||d || r.| jd }tf|d | i}| jd |jd <t j |j |fd |j d<| j d|j d|jd<||jd <| jd|jd<dS| | fSdS)a Full pipeline for HVG selection and normalization by analytic Pearson residuals ([Lause21]_). Applies gene selection based on Pearson residuals. On the resulting subset, Pearson residual normalization and PCA are performed. Expects raw count input. Params ------ {adata} {dist_params} {genes_batch_chunk} {pca_chunk} {check_values} {inplace} Returns ------- If `inplace=False`, separately returns the gene selection results (as :class:`~pandas.DataFrame`) and Pearson residual-based PCA results (as :class:`~anndata.AnnData`). If `inplace=True`, updates `adata` with the following fields for gene selection results: `.var['highly_variable']` : bool boolean indicator of highly-variable genes. `.var['means']` : float means per gene. `.var['variances']` : float variances per gene. `.var['residual_variances']` : float Pearson residual variance per gene. Averaged in the case of multiple batches. `.var['highly_variable_rank']` : float Rank of the gene according to residual variance, median rank in the case of multiple batches. `.var['highly_variable_nbatches']` : int If batch_key is given, this denotes in how many batches genes are detected as HVG. `.var['highly_variable_intersection']` : bool If batch_key is given, this denotes the genes that are highly variable in all batches. The following fields contain Pearson residual-based PCA results and normalization settings: `.uns['pearson_residuals_normalization']['pearson_residuals_df']` The subset of highly variable genes, normalized by Pearson residuals. `.uns['pearson_residuals_normalization']['theta']` The used value of the overdisperion parameter theta. `.uns['pearson_residuals_normalization']['clip']` The used value of the clipping parameter. `.obsm['X_pca']` PCA representation of data after gene selection and Pearson residual normalization. `.varm['PCs']` The principal components containing the loadings. When `inplace=True` this will contain empty rows for the genes not selected during HVG selection. `.uns['pca']['variance_ratio']` Ratio of explained variance. `.uns['pca']['variance']` Explained variance, equivalent to the eigenvalues of the covariance matrix. Zpearson_residuals)ZflavorrrrrrrrTNZhighly_variableF)rrr)rrZpearson_residuals_normalizationZpearson_residuals_dfr)shapeZPCsZX_pca)dictrppZhighly_variable_genesvarcopyZnormalize_pearson_residualsrZunsZto_dfnpZzerosZn_varsZvarmZobsm)rrrrrrrrrrrZhvg_argsZ adata_pcaZhvgZnormalization_paramZnormalization_dictr#X/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/scanpy/experimental/pp/_recipes.pyrecipe_pearson_residualssFW   r%)typingrrZanndatarZpandaspdnumpyr"ZscanpyrZscanpy.preprocessingrZscanpy.experimental._docsrrr r r r r Z scanpy._utilsrfloatintstrrboolZ DataFramer%r#r#r#r$sN   $