U md@sddlmZmZmZmZddlmZddlZddl m Z ddl m Z ddl mZzddlmZWn"ek rGdd d ZYnXdd lmZdd lmZdd lmZdd lmZmZdddZde eeeeee ee eedee fee eeeee ej!fd ddZ"dS))OptionalUnionIterableDict)warnN)AnnData)issparse) sparsefuncs)Arrayc@s eZdZdS) DaskArrayN)__name__ __module__ __qualname__rr\/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/scanpy/preprocessing/_normalization.pyr sr )logging)Literal)view_to_actual) _get_obs_rep _set_obs_repFcCs|r |n|}t|jjttjfr0|tj}t |t rL||dk }n ||dk}|dkrntj |ddn|}||dk7}||}t |rt|d|nBt |tjrtj||dddf|dnt||dddf}|S)Nr)Zaxis)out)copy issubclassZdtypetypeintnpintegerZastypeZfloat32 isinstancer Zcompute_chunk_sizesmedianrr Zinplace_row_scalendarraydivide)XcountsafterrZcounts_greater_than_zerorrr_normalize_datas     r%皙?Tall) adata target_sumexclude_highly_expressed max_fraction key_addedlayerlayers layer_norminplacerreturnc Cs`| r|std|}|dks(|dkr0td|dk rDttd|dk rXttd|dkrl|j}nt|trtd |t|t ||d } d} d } |r| d} t | } | | dddf|k d} t | dk} | d |j | 7} | dd| f d} n | d} t| }t | } | dk}t |sVttd |r|dk rp| |j|<t|t| | ||d ntt| | |dd| d}|dkr|}n2|dkrt | |}n|dkrd}ntd|dk r|ndD](}t||||d}|s|d||<qtjd|d|dk rHtd|d| rR|S|s\|SdS)u Normalize counts per cell. Normalize each cell by total counts over all genes, so that every cell has the same total count after normalization. If choosing `target_sum=1e6`, this is CPM normalization. If `exclude_highly_expressed=True`, very highly expressed genes are excluded from the computation of the normalization factor (size factor) for each cell. This is meaningful as these can strongly influence the resulting normalized values for all other genes [Weinreb17]_. Similar functions are used, for example, by Seurat [Satija15]_, Cell Ranger [Zheng17]_ or SPRING [Weinreb17]_. Params ------ adata The annotated data matrix of shape `n_obs` × `n_vars`. Rows correspond to cells and columns to genes. target_sum If `None`, after normalization, each observation (cell) has a total count equal to the median of total counts for observations (cells) before normalization. exclude_highly_expressed Exclude (very) highly expressed genes for the computation of the normalization factor (size factor) for each cell. A gene is considered highly expressed, if it has more than `max_fraction` of the total counts in at least one cell. The not-excluded genes will sum up to `target_sum`. max_fraction If `exclude_highly_expressed=True`, consider cells as highly expressed that have more counts than `max_fraction` of the original total counts in at least one cell. key_added Name of the field in `adata.obs` where the normalization factor is stored. layer Layer to normalize instead of `X`. If `None`, `X` is normalized. inplace Whether to update `adata` or return dictionary with normalized copies of `adata.X` and `adata.layers`. copy Whether to modify copied input object. Not compatible with inplace=False. Returns ------- Returns dictionary with normalized copies of `adata.X` and `adata.layers` or updates `adata` with normalized version of the original `adata.X` and `adata.layers`, depending on `inplace`. Example -------- >>> from anndata import AnnData >>> import scanpy as sc >>> sc.settings.verbosity = 2 >>> np.set_printoptions(precision=2) >>> adata = AnnData(np.array([ ... [3, 3, 3, 6, 6], ... [1, 1, 1, 2, 2], ... [1, 22, 1, 2, 2], ... ])) >>> adata.X array([[ 3., 3., 3., 6., 6.], [ 1., 1., 1., 2., 2.], [ 1., 22., 1., 2., 2.]], dtype=float32) >>> X_norm = sc.pp.normalize_total(adata, target_sum=1, inplace=False)['X'] >>> X_norm array([[0.14, 0.14, 0.14, 0.29, 0.29], [0.14, 0.14, 0.14, 0.29, 0.29], [0.04, 0.79, 0.04, 0.07, 0.07]], dtype=float32) >>> X_norm = sc.pp.normalize_total( ... adata, target_sum=1, exclude_highly_expressed=True, ... max_fraction=0.2, inplace=False ... )['X'] The following highly-expressed genes are not considered during normalization factor computation: ['1', '3', '4'] >>> X_norm array([[ 0.5, 0.5, 0.5, 1. , 1. ], [ 0.5, 0.5, 0.5, 1. , 1. ], [ 0.5, 11. , 0.5, 1. , 1. ]], dtype=float32) z0`copy=True` cannot be used with `inplace=False`.rrz$Choose max_fraction between 0 and 1.NzbThe `layers` argument is deprecated. Instead, specify individual layers to normalize with `layer`.zcThe `layer_norm` argument is deprecated. Specify the target size factor directly with `target_sum`.r'z5`layers` needs to be a list of strings or 'all', not )r-znormalizing counts per cellzb The following highly-expressed genes are not considered during normalization factor computation: zSome cells have zero countsT)r)r"Z norm_factorr$r"z)layer_norm should be "after", "X" or Noner)r-r)r0z finished ({time_passed}))timez and added z2, counts per cell before normalization (adata.obs)) ValueErrorrr FutureWarningr.keysrstrrrsumrZravelZ var_namestolistlogginfor' UserWarningZobsrr%dictrnormalize_totaldebug)r(r)r*r+r,r-r.r/r0rr"Z gene_subsetmsgZcounts_per_cellstartZ cell_subsetZdatr$Z layer_to_normresrrrr=-s^                  r=)NF) NFr&NNNNTF)#typingrrrrwarningsrnumpyrZanndatarZ scipy.sparserZ sklearn.utilsr Z dask.arrayr r ImportErrorZscanpyrr9Zscanpy._compatrZ scanpy._utilsrZ scanpy.getrrr%floatboolr6r r=rrrrsH