o NrfX@sddlmZddlZddlZddlZddlmZddlm Z ddl m Z dddZ dd d Z d d Zd dZddZddZddZddZddZddZdS)) annotationsN)partial)islice)BagcCt|||d}|t|S)aChooses k unique random elements from a bag. Returns a new bag containing elements from the population while leaving the original population unchanged. Parameters ---------- population: Bag Elements to sample. k: integer, optional Number of elements to sample. split_every: int (optional) Group partitions into groups of this size while performing reduction. Defaults to 8. Examples -------- >>> import dask.bag as db >>> from dask.bag import random >>> b = db.from_sequence(range(5), npartitions=2) >>> list(random.sample(b, 3).compute()) # doctest: +SKIP [1, 3, 5]  populationk split_every)_samplemap_partitions_finalize_samplerr r resrX/var/www/html/software/conda/envs/catlas/lib/python3.10/site-packages/dask/bag/random.pysample s rcCr)a7 Return a k sized list of elements chosen with replacement. Parameters ---------- population: Bag Elements to sample. k: integer, optional Number of elements to sample. split_every: int (optional) Group partitions into groups of this size while performing reduction. Defaults to 8. Examples -------- >>> import dask.bag as db >>> from dask.bag import random >>> b = db.from_sequence(range(5), npartitions=2) >>> list(random.choices(b, 3).compute()) # doctest: +SKIP [1, 1, 5] r)_sample_with_replacementr r rrrrchoices(s rc Csg}g}d}|D]}|\}}||||7}t|} ||| fq||kr-|s-||fSg} |D]\}} | dkrF|| |} | | g| 7} q1|rLtjnt} | || |d|fS)aq Reduce function used on the sample and choice functions. Parameters ---------- reduce_iter : iterable Each element is a tuple coming generated by the _sample_map_partitions function. replace: bool If True, sample with replacement. If False, sample without replacement. Returns a sequence of uniformly distributed samples; r)rweightsr )extendlenappendrndr&_weighted_sampling_without_replacement) reduce_iterr replaceZns_kssniZs_iZn_iZk_ipZp_iZ sample_funcrrr_sample_reduceBs&     r"cs4fddttD}fddt||DS)zk Source: Weighted random sampling with a reservoir, Pavlos S. Efraimidis, Paul G. Spirakis cs&g|]}tt||fqSr)mathlogrrandom).0r )rrr ms&z:_weighted_sampling_without_replacement..csg|]}|dqS)rr)r&x)rrrr'ns)rangerheapqnlargest)rrr eltr)rrrrhsrcCs4|dkrtd|jtt|dtt|ddt|dS)Nrz(Cannot take a negative number of samplesr Fr rZout_typer ) ValueError reductionr_sample_map_partitionsr"rrrrrr qs  r cCs |d}t||krtd|S)NrzSample larger than population)rr0)rr rrrrr |s r c Csgd}}t|}t||D] }|||d7}qttt|}|dt|}t ||D]'\}}||krV||t |<|ttt|9}|t|7}|d7}q3||fS)z Reservoir sampling strategy based on the L algorithm See https://en.wikipedia.org/wiki/Reservoir_sampling#An_optimal_algorithm rr) iterrrr#expr$rr% _geometric enumerate randrange) rr reservoir stream_lengthstreamewnxtr rrrr2s     r2cCs$|jtt|dtt|ddt|dS)Nr-Tr.r/)r1r'_sample_with_replacement_map_partitionsr"rrrrrrs   rc st|}t|fddt|Dd}}ddt|D}dd|D}t|}t|dD]7\}||krbt|D]"\} } | |kr]|| <|| t9<|| t|| 7<q;t|}|d7}q/||fS)z Reservoir sampling with replacement, the main idea is to use k reservoirs of size 1 See Section Applications in http://utopia.duth.gr/~pefraimi/research/data/2007EncOfAlg.pdf csg|]}qSrrr&_r;rrr'sz;_sample_with_replacement_map_partitions..rcSsg|]}tqSr)rr%r?rrrr'cSsg|]}t|qSr)r5)r&Zwirrrr'rB)r3nextr)minr6rr%r5) rr r:r8r9r<r=Zmin_nxtr jrrrArr>s" r>cCs(tttddtd|dS)Nrr)intr#r$runiform)r!rrrr5s(r5)N)rN) __future__rr*r#r%r functoolsr itertoolsrZ dask.bag.corerrrr"rr r r2rr>r5rrrrs"      &