U mdU$@sddlmZmZddlZddlZddlmZddlm Z ddl m Z m Z ddl mZmZdd lmZdd lmZdd lmZdd l mZmZed Zde eeeeeeeeeeejdfeeeeeeedeeee dddZdS))OptionalUnionN)version)AnnData)check_random_state check_array)get_init_pos_from_paga_choose_representation)logging)settings)Literal) AnyRandom NeighborsView)pagaspectralrandom??rFumap)rrapids)adatamin_distspread n_componentsmaxiteralphagammanegative_sample_rateinit_pos random_stateabcopymethod neighbors_keyreturncCs| r |n|}|dkrd}||jkr6td|dtd}t||}d|ksb|dddkrxtd |d d ttj d d dddl }W5QRXt |j t dkrdd}n ddlm}ddlm}| dks| dkr|||\} } n| } | } d| | di|jd<t|tr>||jkr>|j|}n*t|trd|dkrdt|| |d}n|}t|drt|tjdd}| dkr| |jddd<t| } |d}t||dd|dddd}| dkrL|d jdd!krd"nd#}|dkr|n|}|||d ||| | ||||| |d$d%|d&itj d'kd(}n| d)kr|d$d%}|d%kr|td*|d+dd,l!m"}|dd-}|dkrd"n|}tj#|tjd.}|||||||||| | tj d'k| d/ }|$|}||jd0<tjd1|d2d3| r |SdS)4a9 Embed the neighborhood graph using UMAP [McInnes18]_. UMAP (Uniform Manifold Approximation and Projection) is a manifold learning technique suitable for visualizing high-dimensional data. Besides tending to be faster than tSNE, it optimizes the embedding such that it best reflects the topology of the data, which we represent throughout Scanpy using a neighborhood graph. tSNE, by contrast, optimizes the distribution of nearest-neighbor distances in the embedding such that these best match the distribution of distances in the high-dimensional space. We use the implementation of `umap-learn `__ [McInnes18]_. For a few comparisons of UMAP with tSNE, see this `preprint `__. Parameters ---------- adata Annotated data matrix. min_dist The effective minimum distance between embedded points. Smaller values will result in a more clustered/clumped embedding where nearby points on the manifold are drawn closer together, while larger values will result on a more even dispersal of points. The value should be set relative to the ``spread`` value, which determines the scale at which embedded points will be spread out. The default of in the `umap-learn` package is 0.1. spread The effective scale of embedded points. In combination with `min_dist` this determines how clustered/clumped the embedded points are. n_components The number of dimensions of the embedding. maxiter The number of iterations (epochs) of the optimization. Called `n_epochs` in the original UMAP. alpha The initial learning rate for the embedding optimization. gamma Weighting applied to negative samples in low dimensional embedding optimization. Values higher than one will result in greater weight being given to negative samples. negative_sample_rate The number of negative edge/1-simplex samples to use per positive edge/1-simplex sample in optimizing the low dimensional embedding. init_pos How to initialize the low dimensional embedding. Called `init` in the original UMAP. Options are: * Any key for `adata.obsm`. * 'paga': positions from :func:`~scanpy.pl.paga`. * 'spectral': use a spectral embedding of the graph. * 'random': assign initial embedding positions at random. * A numpy array of initial embedding positions. random_state If `int`, `random_state` is the seed used by the random number generator; If `RandomState` or `Generator`, `random_state` is the random number generator; If `None`, the random number generator is the `RandomState` instance used by `np.random`. a More specific parameters controlling the embedding. If `None` these values are set automatically as determined by `min_dist` and `spread`. b More specific parameters controlling the embedding. If `None` these values are set automatically as determined by `min_dist` and `spread`. copy Return a copy instead of writing to adata. method Use the original 'umap' implementation, or 'rapids' (experimental, GPU only) neighbors_key If not specified, umap looks .uns['neighbors'] for neighbors settings and .obsp['connectivities'] for connectivities (default storage places for pp.neighbors). If specified, umap looks .uns[neighbors_key] for neighbors settings and .obsp[.uns[neighbors_key]['connectivities_key']] for connectivities. Returns ------- Depending on `copy`, returns or updates `adata` with the following fields. **X_umap** : `adata.obsm` field UMAP coordinates of data. N neighborszDid not find .uns["z "]. Run `sc.pp.neighbors` first.zcomputing UMAPparamsr&rz.obsp["Zconnectivities_keyz$"] have not been computed using umapignorezTensorflow not installed)messagerz0.5.0c_s*ddlm}||didd|\}}|S)Nrsimplicial_set_embeddingF)ZdensmapZ densmap_kwdsZ output_dens) umap.umap_r.)argskwargsr.X_umap_r4K/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/scanpy/tools/_umap.pyr.s  z&umap..simplicial_set_embeddingr-)find_ab_params)r#r$r)r"r'dtypeF)r7Z accept_sparser"Zuse_repZn_pcsT)ZsilentZconnectivitiesi'imetricZ euclideanZ metric_kwds)verboserz+`sc.pp.neighbors` was called with `metric` zB, but umap `method` 'rapids' only supports the 'euclidean' metric.)UMAP n_neighbors)r7) r=rn_epochsZ learning_rateinitrrr r#r$r;r"r2z finishedz1added 'X_umap', UMAP coordinates (adata.obsm))timedeep)%r%Zuns ValueErrorlogginforwarningwarningscatch_warningsfilterwarningsrrparse __version__r/r.r6 isinstancestrZobsmkeysr hasattrrnpZfloat32rr getshapeZtocoor verbosityZcumlr<ZascontiguousarrayZ fit_transform)rrrrrrrr r!r"r#r$r%r&r'startr)rr.r6Z init_coordsZ neigh_paramsXZdefault_epochsr>r2r9r<r=Z X_contiguousr4r4r5rsd                        )rrr NrrrrrNNFrN) typingrrrFnumpyrO packagingrZanndatarZ sklearn.utilsrr_utilsr r r rCZ _settingsr Z_compatrrrZ_InitPosfloatintZndarrayboolrLrr4r4r4r5sV