U md8 @sdZddlmZmZddlZddlmZddlm Z ddl m Z ddl m Zdd lmZdd lmZdeeeeeeeeeededeedd ddZd eeeeedddZd!ddZddZddZdS)"zeThis modules provides all non-visualization tools for advanced gene ranking and exploration of genes )Optional CollectionN)AnnData)metrics)issparse)logging) select_groups)LiteralCompletepearson)r GroupRest)r ZkendallZspearman) adata name_listgroupbygroupn_genesdatamethodannotation_keyreturncCs|dkrLt}t|jdD],\}} ||kr0qd||jd||qnt||krd|d|}|dd|f} d} |dks|dkrt| jr| j} n| j} nt|| |\} }|dkrt| jr| j||ddf} n| j||ddf} nX|dkrJt| jr0| j||ddf} n| j||ddf} n t dt j | |d }|j |d }|dkr|dkr||jd <n||jd |t|<n ||j|<dS) ap Calculate correlation matrix. Calculate a correlation matrix for genes strored in sample annotation using :func:`~scanpy.tl.rank_genes_groups`. Parameters ---------- adata Annotated data matrix. name_list Takes a list of genes for which to calculate the correlation matrix groupby If no name list is passed, genes are selected from the results of rank_gene_groups. Then this is the key of the sample grouping to consider. Note that in this case also a group index has to be specified. group Group index for which the correlation matrix for top_ranked genes should be calculated. Currently only int is supported, will change very soon n_genes For how many genes to calculate correlation matrix? If specified, cuts the name list (in whatever order it is passed). data At the moment, this is only relevant for the case that name_list is drawn from rank_gene_groups results. If specified, collects mask for the called group and then takes only those cells specified. If 'Complete', calculate correlation using full data If 'Group', calculate correlation within the selected group. If 'Rest', calculate corrlation for everything except the group method Which kind of correlation coefficient to use pearson standard correlation coefficient kendall Kendall Tau correlation coefficient spearman Spearman rank correlation annotation_key Allows to define the name of the anndata entry where results are stored. Nrank_genes_groups_gene_namesrallr rrz>data argument should be either or or )columns)rZCorrelation_matrix)list enumerateunsappendlenrXtodenser loggerrorpdZ DataFrameZcorrstr)rrrrrrrrjkZadata_relevantgroupsZ Data_array groups_order groups_masksZDF_arrayZ cor_tabler,P/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/scanpy/tools/_top_genes.pycorrelation_matrixs>7            r.d)rrrrcCsh|dkrt}t|jdD],\}}||kr0qJ||jd||qd}t|||\}} | |} i} i} i} i}| }t|D]\}}|dd|gfj}t|r|}n|}tj ||dddd\| ||<| ||<| ||<t | ||| |||||<q| |jd|t |<| |jd|t |<| |jd|t |<||jd |t |<dS) aT Calculate correlation matrix. Calculate a correlation matrix for genes strored in sample annotation Parameters ---------- adata Annotated data matrix. groupby The key of the sample grouping to consider. group Group name or index for which the correlation matrix for top ranked genes should be calculated. If no parameter is passed, ROC/AUC is calculated for all groups n_genes For how many genes to calculate ROC and AUC. If no parameter is passed, calculation is done for all stored top ranked genes. NrrF)Z pos_labelZ sample_weightZdrop_intermediateZROCfprZROCtprZ ROCthresholdsZROC_AUC) rrrrr r!rr"rZ roc_curveZaucr&)rrrrrr'r(r)r*r+maskZfprZtpr thresholdsZroc_aucZy_trueiZvecZy_scorer,r,r-ROC_AUC_analysisysF    &r3{Gz?Gz?cCs|dkr|}dSNr,)r0Z mask_rest precisionZ probabilityr,r,r-subsampled_estimatessr8cCsdSr6r,)rZgroubyr,r,r-dominated_ROC_eliminationsr9cCsdSr6r,)rr0r1r,r,r-_gene_preselectionsr:)NNNr r r N)Nr/)Nr4r5)__doc__typingrrZpandasr%ZanndatarZsklearnrZ scipy.sparserrr#_utilsr Z_compatr r&intr.r3r8r9r:r,r,r,r-sJ        j H