ti0ddlmZddlmZmZmZddlmZmZm Z ddl m Z ddl m Z mZddlmZgdZe dd Zd ed efd Ze dGddee Ze dGddeZe dGddee Zy)) defaultdict)CallableIteratorSized)AnyNoReturnTypeVar)functional_datapipe) DataChunk IterDataPipe)_check_unpickable_fn)BatcherIterDataPipeGrouperIterDataPipeUnBatcherIterDataPipe_T_coT) covariantnamereturnc,tdtd|)Nzmodule z has no attribute )AttributeError__name__)rs n/home/ubuntu/crypto_trading_bot/.venv/lib/python3.12/site-packages/torch/utils/data/datapipes/iter/grouping.py __getattr__rs 78*,>tfE FFbatchc eZdZUdZeed<eed<eed<defdededede eddf fd Z de efd Z defd Z xZS) ra2 Creates mini-batches of data (functional name: ``batch``). An outer dimension will be added as ``batch_size`` if ``drop_last`` is set to ``True``, or ``length % batch_size`` for the last batch if ``drop_last`` is set to ``False``. Args: datapipe: Iterable DataPipe being batched batch_size: The size of each batch drop_last: Option to drop the last batch if it's not full wrapper_class: wrapper to apply onto each batch (type ``List``) before yielding, defaults to ``DataChunk`` Example: >>> # xdoctest: +SKIP >>> from torchdata.datapipes.iter import IterableWrapper >>> dp = IterableWrapper(range(10)) >>> dp = dp.batch(batch_size=3, drop_last=True) >>> list(dp) [[0, 1, 2], [3, 4, 5], [6, 7, 8]] datapipe batch_size drop_lastF wrapper_classrNcz|dkr tdt| ||_||_||_||_y)Nrz+Batch size is required to be larger than 0!)AssertionErrorsuper__init__rrrr )selfrrrr __class__s rr$zBatcherIterDataPipe.__init__5s@ ? !NO O   $"*rc#Kg}|jD]A}|j|t||jk(s-|j |g}Ct|dkDr!|j s|j |yyywNr)rappendlenrr r)r%rxs r__iter__zBatcherIterDataPipe.__iter__Ds~ A LLO5zT__,((//   u:>>>((//" s ;BABc8t|jtr`|jr"t |j|j zSt |j|j zdz |j zSt t|jd)Nz# instance doesn't have valid length) isinstancerrrr*r TypeErrortyperr%s r__len__zBatcherIterDataPipe.__len__Oss dmmU +~~4==)T__<<DMM*T__>> # xdoctest: +SKIP >>> from torchdata.datapipes.iter import IterableWrapper >>> source_dp = IterableWrapper([[[0, 1], [2]], [[3, 4], [5]], [[6]]]) >>> dp1 = source_dp.unbatch() >>> list(dp1) [[0, 1], [2], [3, 4], [5], [6]] >>> dp2 = source_dp.unbatch(unbatch_level=2) >>> list(dp2) [0, 1, 2, 3, 4, 5, 6] r unbatch_levelrNc ||_||_yN)rr=)r%rr=s rr$zUnBatcherIterDataPipe.__init__qs  *rc#|K|jD]'}|j||jEd{)y7w)Nr=)r_diver=)r%elements rr,zUnBatcherIterDataPipe.__iter__us:}} MGzz'9K9KzL L L M Ls 0<:<c#vK|dkr td|dk(r>t|ttfr#|D]}|j |dEd{y|y|dk(r|yt|ttfr&|D] }|j ||dz Ed{"yt d|j d7k7"w)Nz unbatch_level must be -1 or >= 0rArr.zunbatch_level z" exceeds the depth of the DataPipe) ValueErrorr/listr rB IndexErrorr=)r%rCr=items rrBzUnBatcherIterDataPipe._diveys 2 ?@ @ B 'D)#45#BD#zz$bzAAAB a M'D)#45#QD#zz$ma>OzPPPQ!$T%7%7$88Z[BQs%AB9 B5 A B9B7!B97B9)r.) rr4r5r6r r8r$r,rBrrrrYs,,++c+$+MrrgroupbyceZdZdZdddddddeedeegefded e d e dzd e dzd ed dfdZ dZ dZ ddZ dZdZddZy)ra Groups data from IterDataPipe by keys from ``group_key_fn``, yielding a ``DataChunk`` with batch size up to ``group_size``. (functional name: ``groupby``). The samples are read sequentially from the source ``datapipe``, and a batch of samples belonging to the same group will be yielded as soon as the size of the batch reaches ``group_size``. When the buffer is full, the DataPipe will yield the largest batch with the same key, provided that its size is larger than ``guaranteed_group_size``. If its size is smaller, it will be dropped if ``drop_remaining=True``. After iterating through the entirety of source ``datapipe``, everything not dropped due to the buffer capacity will be yielded from the buffer, even if the group sizes are smaller than ``guaranteed_group_size``. Args: datapipe: Iterable datapipe to be grouped group_key_fn: Function used to generate group key from the data of the source datapipe keep_key: Option to yield the matching key along with the items in a tuple, resulting in `(key, [items])` otherwise returning [items] buffer_size: The size of buffer for ungrouped data group_size: The max size of each group, a batch is yielded as soon as it reaches this size guaranteed_group_size: The guaranteed minimum group size to be yielded in case the buffer is full drop_remaining: Specifies if the group smaller than ``guaranteed_group_size`` will be dropped from buffer when the buffer is full Example: >>> import os >>> # xdoctest: +SKIP >>> from torchdata.datapipes.iter import IterableWrapper >>> def group_fn(file): ... return os.path.basename(file).split(".")[0] >>> source_dp = IterableWrapper( ... ["a.png", "b.png", "a.json", "b.json", "a.jpg", "c.json"] ... ) >>> dp0 = source_dp.groupby(group_key_fn=group_fn) >>> list(dp0) [['a.png', 'a.json', 'a.jpg'], ['b.png', 'b.json'], ['c.json']] >>> # A group is yielded as soon as its size equals to `group_size` >>> dp1 = source_dp.groupby(group_key_fn=group_fn, group_size=2) >>> list(dp1) [['a.png', 'a.json'], ['b.png', 'b.json'], ['a.jpg'], ['c.json']] >>> # Scenario where `buffer` is full, and group 'a' needs to be yielded since its size > `guaranteed_group_size` >>> dp2 = source_dp.groupby( ... group_key_fn=group_fn, ... buffer_size=3, ... group_size=3, ... guaranteed_group_size=2, ... ) >>> list(dp2) [['a.png', 'a.json'], ['b.png', 'b.json'], ['a.jpg'], ['c.json']] Fi'N)keep_key buffer_size group_sizeguaranteed_group_sizedrop_remainingr group_key_fnrMrNrOrPrQrc|t|||_||_||_||_t t |_d|_||_ d|_ |+|)d|cxkr|kstdtd||_ |+|d|cxkr|kstdtd||_ ||_ t|_y)Nrz)group_size must be > 0 and <= buffer_sizezNguaranteed_group_size must be > 0 and <= group_size and group_size must be set)r rrRrMmax_buffer_sizerrGbuffer_elementscurr_buffer_sizerOrPr"rQr r )r%rrRrMrNrOrPrQs rr$zGrouperIterDataPipe.__init__s \*  (  *7B47H !$%)"  !k&= 1k1$%PQQ2$%PQQ)3D & ,!!.C*Qz*Q$d+R$d*?D &,&rcd}d}d}|jD]8}t|j||kDst|j|}|}:|j=||jkr.|js"t dt |j||j||jk\r|j|}|xj |zc_|j|=|S)NrzFailed to group items)rUr*rPrQ RuntimeErrorstrrV)r% biggest_key biggest_sizeresult_to_yieldfindkeys r_remove_biggest_keyz'GrouperIterDataPipe._remove_biggest_keys  ++ &G4''01L@"4#7#7#@A %  &  & & 2t999'''T-A-A+-N)O   & & .t999"22;?O -   -rc#K|jD]5}|j|}|j|j||xjdz c_|j |j t |j|k(rj|j|j|}|jr||fn||xjt |j|zc_|j|=|j|jk(s|j}||j|}|jr||fn|8t|jjD]^}|j|jj|}|xjt |zc_|jr||fn|`yw)Nr.)rrRrUr)rVrOr*r rMrTr^tuplekeyspop)r%r+keyresultr\s rr,zGrouperIterDataPipe.__iter__s EA##A&C   % , ,Q /  ! !Q & !*t#$$S)C0*.););Drzs#55))EGH  4(GcGhGW<Y,y1<Y<Y~Y1L1 1hYw%,y1w% w%r