^j#ddlZddlmZddlmZmZmZddlmZm Z ddl Z ddl m Z ddl mZddlmZddlmZdd lmZmZd d gZe d d ZedGdd eeZdZedGdd eZy)N) namedtuple)CallableIteratorSized)AnyTypeVar)default_collate)functional_datapipe)dataframe_wrapper) IterDataPipe)_check_unpickable_fnvalidate_input_colCollatorIterDataPipeMapperIterDataPipe_T_coT) covariantmapcpeZdZUdZeed<eed< d dededdffd ZdZde e fdZ de fd Z xZS) ra Applies a function over each item from the source DataPipe (functional name: ``map``). The function can be any regular Python function or partial object. Lambda function is not recommended as it is not supported by pickle. Args: datapipe: Source Iterable DataPipe fn: Function being applied over each item input_col: Index or indices of data which ``fn`` is applied, such as: - ``None`` as default to apply ``fn`` to the data directly. - Integer(s) is used for list/tuple. - Key(s) is used for dict. output_col: Index of data where result of ``fn`` is placed. ``output_col`` can be specified only when ``input_col`` is not ``None`` - ``None`` as default to replace the index that ``input_col`` specified; For ``input_col`` with multiple indices, the left-most one is used, and other indices will be removed. - Integer is used for list/tuple. ``-1`` represents to append result at the end. - Key is used for dict. New key is acceptable. Example: >>> # xdoctest: +SKIP >>> from torchdata.datapipes.iter import IterableWrapper, Mapper >>> def add_one(x): ... return x + 1 >>> dp = IterableWrapper(range(10)) >>> # Invocation via functional form is preferred ... map_dp_1 = dp.map(add_one) >>> list(map_dp_1) [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] >>> # We discourage the usage of `lambda` functions as they are not serializable with `pickle` >>> # Use `functools.partial` or explicitly define the function instead >>> map_dp_2 = Mapper(dp, lambda x: x + 1) >>> list(map_dp_2) [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] datapipefnNreturncLtjjdt|||_t |||_||_| | tdt|ttfrt|dkDr td|d}||_t||y)Nzpython.data_pipes.mapz3`output_col` must be None when `input_col` is None.z3`output_col` must be a single-element list or tupler)torch_C_log_api_usage_oncesuper__init__rr r input_col ValueError isinstancelisttuplelen output_colr)selfrrrr% __class__s s/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/torch/utils/data/datapipes/iter/callable.pyrzMapperIterDataPipe.__init__Hs $$%<=   R "  !7RS S j4- 0:" !VWW#AJ$2y)c |j|j|jS|j|j}nlt|jtt fr.t fd|jD}|j|}n|j|j}tt rd}t nd}|jet|jtt fr5||jd<t |jdddD]}|=n@||j<n0|jdk(rj|n||j<|r t SS)Nc3(K|] }| ywN).0coldatas r( z/MapperIterDataPipe._apply_fn..gs=sc=sTFrr)reverse)rr%rr!r"r#sortedappend)r&r0resargst_flagidxs ` r( _apply_fnzMapperIterDataPipe._apply_fn`sF >> !doo&=774= >> !''$-C u 6=dnn==D$''4.C''$t~~./C dE "F:DF ?? "$..4-8*-T^^A&'!$.."4dC"CS "(+T^^$"$ C (+T__%%uT{.$.r)c#TK|jD]}|j|ywr,)rr:)r&r0s r(__iter__zMapperIterDataPipe.__iter__s(MM 'D..& & 's&(ct|jtrt|jSt t |j d)Nz# instance doesn't have valid length)r!rrr$ TypeErrortype__name__)r&s r(__len__zMapperIterDataPipe.__len__s= dmmU +t}}% %4:..//RSTTr))NN)r@ __module__ __qualname____doc__r __annotations__rrr:rrr<intrA __classcell__r's@r(rrsc&PL  ** *  *0!/F'(5/'UUr)ct|jdkDr td|d}tj|}g}g}|D]}||vstd|D]|}||vrt ||s td||}n! ddlm}|jj}|jt||||} |j| ~td|} | |} | S#t$r} td| d} ~ wwxYw)Nrz%Only supports one DataFrame per batchrzConversion keys mismatchz5Collate (DF)DataPipe requires callable as dict valuesz?unable to import default collation function from the TorchArrow CollateResult)r$items RuntimeError df_wrapper get_columnscallabletorcharrow.pytorchpytorchrecDefault Exceptionr5strr) conversionitemdf columns_name tuple_names tuple_valuesname collation_fntapevaluetpl_clsr#s r(_collate_helperrbs0 4::BCC aB))"-LKL; | #9: :;# : Jt,-"K&d+L 0"ww0 3t9%RX&E")#0+6G \ "E L "U s C,, D5 DDcollatec leZdZdZedfdededefee ezeezfzdzdedzddffd Z xZ S) raI Collates samples from DataPipe to Tensor(s) by a custom collate function (functional name: ``collate``). By default, it uses :func:`torch.utils.data.default_collate`. .. note:: While writing a custom collate function, you can import :func:`torch.utils.data.default_collate` for the default behavior and `functools.partial` to specify any additional arguments. Args: datapipe: Iterable DataPipe being collated collate_fn: Customized collate function to collect and combine data or a batch of data. Default function collates to Tensor(s) based on data type. Example: >>> # xdoctest: +SKIP >>> # Convert integer data to float Tensor >>> class MyIterDataPipe(torch.utils.data.IterDataPipe): ... def __init__(self, start, end): ... super(MyIterDataPipe).__init__() ... assert end > start, "this example only works with end >= start" ... self.start = start ... self.end = end ... ... def __iter__(self): ... return iter(range(self.start, self.end)) ... ... def __len__(self): ... return self.end - self.start >>> ds = MyIterDataPipe(start=3, end=7) >>> print(list(ds)) [3, 4, 5, 6] >>> def collate_fn(batch): ... return torch.tensor(batch, dtype=torch.float) >>> collated_ds = CollateIterDataPipe(ds, collate_fn=collate_fn) >>> print(list(collated_ds)) [tensor(3.), tensor(4.), tensor(5.), tensor(6.)] NrrV. collate_fnrc|t|||yt|rt|||ytjt |}t|||y)N)r)rrrO functoolspartialrb)r&rrVrer's r(rzCollatorIterDataPipe.__init__s]  ! G X*  5 # j 9'.. K  j 9r)) r@rBrCrDr r rrdictrUrrGrHs@r(rrsp%X!&* ::S#X& sSy(S.( )* : tO : ::r))rg collectionsrcollections.abcrrrtypingrrrtorch.utils.data._utils.collater %torch.utils.data.datapipes._decoratorr $torch.utils.data.datapipes.dataframer rM#torch.utils.data.datapipes.datapiper 'torch.utils.data.datapipes.utils.commonr r__all__rrrbrr-r)r(rss"55 ;EP<  4(UoUe,oUoUd(VY::-:: ::r)