PKJUOMtext2array/__init__.py# Copyright 2019 Kemal Kurniawan # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. """Convert your NLP text data to arrays!""" __version__ = '0.0.15' __all__ = [ 'Sample', 'Batch', 'Vocab', 'StringStore', 'BatchIterator', 'ShuffleIterator', ] from .batches import Batch from .samples import Sample from .iterators import BatchIterator, ShuffleIterator from .vocab import StringStore, Vocab PK}IUOR%%text2array/batches.py# Copyright 2019 Kemal Kurniawan # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. from collections import UserList from functools import reduce from typing import Dict, List, Mapping, MutableSequence, Optional, Sequence, Union, cast import numpy as np from .samples import FieldName, FieldValue, Sample class Batch(UserList, MutableSequence[Sample]): """A class to represent a single batch. Args: samples (~typing.Sequence[Sample]): Sequence of samples this batch should contain. """ def __init__(self, samples: Optional[Sequence[Sample]] = None) -> None: # constructor required; see https://docs.python.org/3.6/library/collections.html#collections.UserList if samples is None: samples = [] super().__init__(samples) def to_array( self, pad_with: Union[int, Mapping[FieldName, int]] = 0, ) -> Dict[FieldName, np.ndarray]: """Convert the batch into `~numpy.ndarray`. Args: pad_with: Pad sequential field values with this number. Can also be a mapping from field names to padding number for that field. Fields whose name is not in the mapping will be padded with zeros. Returns: A mapping from field names to arrays whose first dimension corresponds to the batch size as returned by `len`. """ if not self: return {} field_names = self[0].keys() if isinstance(pad_with, int): pad_dict = {name: pad_with for name in field_names} else: pad_dict = cast(dict, pad_with) arr = {} for name in field_names: values = self._get_values(name) # Get max length for all depths, 1st elem is batch size try: maxlens = self._get_maxlens(values) except self._InconsistentDepthError: raise ValueError(f"field '{name}' has inconsistent nesting depth") # Get padding for all depths paddings = self._get_paddings(maxlens, pad_dict.get(name, 0)) # Pad the values data = self._pad(values, maxlens, paddings, 0) arr[name] = np.array(data) return arr def _get_values(self, name: str) -> Sequence[FieldValue]: try: return [s[name] for s in self] except KeyError: raise KeyError(f"some samples have no field '{name}'") @classmethod def _get_maxlens(cls, values: Sequence[FieldValue]) -> List[int]: assert values # Base case if isinstance(values[0], str) or not isinstance(values[0], Sequence): return [len(values)] # Recursive case maxlenss = [cls._get_maxlens(x) for x in values] if not all(len(x) == len(maxlenss[0]) for x in maxlenss): raise cls._InconsistentDepthError maxlens = reduce(lambda ml1, ml2: [max(l1, l2) for l1, l2 in zip(ml1, ml2)], maxlenss) maxlens.insert(0, len(values)) return maxlens @classmethod def _get_paddings(cls, maxlens: List[int], with_: int) -> List[Union[int, List[int]]]: res: list = [with_] for maxlen in reversed(maxlens[1:]): res.append([res[-1] for _ in range(maxlen)]) res.reverse() return res @classmethod def _pad( cls, values: Sequence[FieldValue], maxlens: List[int], paddings: List[Union[int, List[int]]], depth: int, ) -> Sequence[FieldValue]: assert values assert len(maxlens) == len(paddings) assert depth < len(maxlens) # Base case if isinstance(values[0], str) or not isinstance(values[0], Sequence): values_ = list(values) # Recursive case else: values_ = [cls._pad(x, maxlens, paddings, depth + 1) for x in values] for _ in range(maxlens[depth] - len(values)): values_.append(paddings[depth]) return values_ class _InconsistentDepthError(Exception): pass PKxEUOmjhhtext2array/iterators.py# Copyright 2019 Kemal Kurniawan # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. from random import Random from typing import Callable, Iterable, Iterator, Optional, Sequence, Sized import statistics as stat from text2array import Batch, Sample class BatchIterator(Iterable[Batch], Sized): """Iterator that produces batches of samples. Example: >>> from text2array import BatchIterator >>> samples = [ ... {'ws': ['a']}, ... {'ws': ['a', 'b']}, ... {'ws': ['b', 'b']}, ... ] >>> iter_ = BatchIterator(samples, batch_size=2) >>> for b in iter_: ... print(list(b)) ... [{'ws': ['a']}, {'ws': ['a', 'b']}] [{'ws': ['b', 'b']}] Args: samples (~typing.Iterable[Sample]): Iterable of samples to batch. batch_size: Maximum number of samples in each batch. Note: When ``samples`` is an instance of `~typing.Sized`, this iterator can be passed to `len` to get the number of batches. Otherwise, a `TypeError` is raised. """ def __init__(self, samples: Iterable[Sample], batch_size: int = 1) -> None: if batch_size <= 0: raise ValueError('batch size must be greater than 0') self._samples = samples self._bsz = batch_size @property def batch_size(self) -> int: return self._bsz def __len__(self) -> int: n = len(self._samples) # type: ignore b = self._bsz return n // b + (1 if n % b != 0 else 0) def __iter__(self) -> Iterator[Batch]: it, exhausted = iter(self._samples), False while not exhausted: batch = Batch() while not exhausted and len(batch) < self._bsz: try: batch.append(next(it)) except StopIteration: exhausted = True if batch: yield batch class ShuffleIterator(Iterable[Sample], Sized): r"""Iterator that shuffles the samples before iterating. When ``key`` is not given, this iterator performs ordinary shuffling using `random.shuffle`. Otherwise, a noisy sorting is performed. The samples are sorted ascending by the value of the given key, plus some random noise :math:`\epsilon \sim` Uniform :math:`(-z, z)`, where :math:`z` equals ``scale`` times the standard deviation of key values. This formulation means that ``scale`` regulates how noisy the sorting is. The larger it is, the more noisy the sorting becomes, i.e. it resembles random shuffling more closely. In an extreme case where ``scale=0``, this method just sorts the samples by ``key``. This method is useful when working with text data, where we want to shuffle the dataset and also minimize padding by ensuring that sentences of similar lengths are not too far apart. Example: >>> from random import Random >>> from text2array import ShuffleIterator >>> samples = [ ... {'ws': ['a', 'b', 'b']}, ... {'ws': ['a']}, ... {'ws': ['a', 'a', 'b', 'b', 'b', 'b']}, ... ] >>> iter_ = ShuffleIterator(samples, key=lambda s: len(s['ws']), rng=Random(1234)) >>> for s in iter_: ... print(s) ... {'ws': ['a']} {'ws': ['a', 'a', 'b', 'b', 'b', 'b']} {'ws': ['a', 'b', 'b']} Args: samples (~typing.Sequence[Sample]): Sequence of samples to shuffle and iterate over. key (typing.Callable[[Sample], int]): Callable to get the key value of a given sample. scale: Value to regulate the noise of the sorting. Must not be negative. rng: Random number generator to use for shuffling. Set this to ensure reproducibility. If not given, an instance of `~random.Random` with the default seed is used. """ def __init__( self, samples: Sequence[Sample], key: Optional[Callable[[Sample], int]] = None, scale: float = 1.0, rng: Optional[Random] = None, ) -> None: if scale < 0: raise ValueError('scale cannot be less than 0') if rng is None: # pragma: no cover rng = Random() self._samples = samples self._key = key self._scale = scale self._rng = rng def __len__(self) -> int: return len(self._samples) def __iter__(self) -> Iterator[Sample]: if self._key is None: self._shuffle() else: self._shuffle_by_key() return iter(self._samples) def _shuffle(self) -> None: self._samples = list(self._samples) self._rng.shuffle(self._samples) def _shuffle_by_key(self) -> None: assert self._key is not None std = stat.stdev(self._key(s) for s in self._samples) z = self._scale * std noises = [self._rng.uniform(-z, z) for _ in range(len(self._samples))] indices = list(range(len(self._samples))) indices.sort(key=lambda i: self._key(self._samples[i]) + noises[i]) # type: ignore shuf_samples = [self._samples[i] for i in indices] self._samples = shuf_samples PKvGOe%{{text2array/samples.py# Copyright 2019 Kemal Kurniawan # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. from typing import Mapping, Sequence, Union # TODO remove these "type ignore" once mypy supports recursive types # see: https://github.com/python/mypy/issues/731 FieldName = str FieldValue = Union[float, int, str, Sequence['FieldValue']] # type: ignore Sample = Mapping[FieldName, FieldValue] # type: ignore PKbHUOӏ$$text2array/vocab.py# Copyright 2019 Kemal Kurniawan # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. from collections import Counter, UserDict, defaultdict from typing import Counter as CounterT, Dict, Iterable, Iterator, Mapping, \ MutableMapping, Optional, Sequence, Set from ordered_set import OrderedSet from tqdm import tqdm from .samples import FieldName, FieldValue, Sample class Vocab(UserDict, MutableMapping[FieldName, 'StringStore']): """A dictionary from field names to `StringStore` objects as the field's vocabulary.""" def __getitem__(self, name: FieldName) -> 'StringStore': try: return super().__getitem__(name) except KeyError: raise KeyError(f"no vocabulary found for field name '{name}'") def stoi(self, samples: Iterable[Sample]) -> Iterable[Sample]: """Convert strings in the given samples to integers according to this vocabulary. This conversion means mapping all the (nested) string field values to integers according to the mapping specified by the `StringStore` object of that field. Field names with no entry in the vocabulary are ignored. Note that the actual conversion is lazy; it is not performed until the resulting iterable is iterated over. Args: samples (~typing.Iterable[Sample]): Samples to convert. Returns: ~typing.Iterable[Sample]: Converted samples. """ return map(self._apply_to_sample, samples) def itos(self, samples: Iterable[Sample]) -> Iterable[Sample]: """Convert integers in the given samples to strings according to this vocabulary. This method is essentially the inverse of `~Vocab.stoi`. Args: samples (~typing.Iterable[Sample]): Samples to convert. Returns: ~typing.Iterable[Sample]: Converted samples. """ return map(lambda s: self._apply_to_sample(s, index=False), samples) @classmethod def from_samples( cls, samples: Iterable[Sample], pbar: Optional[tqdm] = None, options: Optional[Mapping[FieldName, dict]] = None, ) -> 'Vocab': """Make an instance of this class from an iterable of samples. A vocabulary is only made for fields whose value is a string token or a (nested) sequence of string tokens. It is important that ``samples`` be a true iterable, i.e. it can be iterated more than once. No exception is raised when this is violated. Args: samples (~typing.Iterable[Sample]): Iterable of samples. pbar: Instance of `tqdm `_ for displaying a progress bar. options: Mapping from field names to dictionaries to control the creation of the vocabularies. Recognized dictionary keys are: * ``min_count`` (`int`): Exclude tokens occurring fewer than this number of times from the vocabulary (default: 1). * ``pad`` (`str`): String token to represent padding tokens. If ``None``, no padding token is added to the vocabulary. Otherwise, it is the first entry in the vocabulary (index is 0). Note that if the field has no sequential values, no padding is added. String field values are *not* considered sequential (default: ````). * ``unk`` (`str`): String token to represent unknown tokens with. If ``None``, no unknown token is added to the vocabulary. This means when querying the vocabulary with such token, an error is raised. Otherwise, it is the first entry in the vocabulary *after* ``pad``, if any (index is either 0 or 1) (default: ````). * ``max_size`` (`int`): Maximum size of the vocabulary, excluding ``pad`` and ``unk``. If ``None``, no limit on the vocabulary size. Otherwise, at most, only this number of most frequent tokens are included in the vocabulary. Note that ``min_count`` also sets the maximum size implicitly. So, the size is limited by whichever is smaller. (default: ``None``). Returns: Vocab: Vocabulary instance. """ if pbar is None: # pragma: no cover pbar = tqdm(samples, desc='Counting', unit='sample') if options is None: options = {} counter: Dict[FieldName, CounterT[str]] = defaultdict(Counter) seqfield: Set[FieldName] = set() for s in samples: for name, value in s.items(): if cls._needs_vocab(value): counter[name].update(cls._flatten(value)) if isinstance(value, Sequence) and not isinstance(value, str): seqfield.add(name) pbar.update() pbar.close() m = {} for name, c in counter.items(): opts = options.get(name, {}) # Padding and unknown tokens pad = opts.get('pad', '') unk = opts.get('unk', '') inits = [] if name in seqfield and pad is not None: inits.append(pad) if unk is not None: inits.append(unk) store = StringStore(inits, default=unk) min_count = opts.get('min_count', 1) max_size = opts.get('max_size') n = len(store) for tok, freq in c.most_common(): if freq < min_count or (max_size is not None and len(store) - n >= max_size): break store.add(tok) m[name] = store return cls(m) @classmethod def _needs_vocab(cls, val: FieldValue) -> bool: if isinstance(val, str): return True if isinstance(val, Sequence): return False if not val else cls._needs_vocab(val[0]) return False @classmethod def _flatten(cls, xs) -> Iterator[str]: if isinstance(xs, str): yield xs return # must be an iterable, due to how we use this function for x in xs: yield from cls._flatten(x) def _apply_to_sample(self, sample: Sample, index: bool = True) -> Sample: fn = self._index_value if index else self._get_value s = {} for name, value in sample.items(): try: store = self[name] except KeyError: s[name] = value else: s[name] = fn(store, value) return s @classmethod def _index_value(cls, store: 'StringStore', value: FieldValue) -> FieldValue: if isinstance(value, str): return store.index(value) if not isinstance(value, Sequence): return value return [cls._index_value(store, v) for v in value] @classmethod def _get_value(cls, store: 'StringStore', value: FieldValue) -> FieldValue: if not isinstance(value, Sequence): return store[value] if isinstance(value, str): return value return [cls._get_value(store, v) for v in value] class StringStore(OrderedSet): """An ordered set of strings, with an optional default value for unknown strings. This class implements both `~typing.MutableSet` and `~typing.Sequence` with `str` as its contents. Example: >>> from text2array import StringStore >>> store = StringStore('abb', default='a') >>> list(store) ['a', 'b'] >>> store.add('b') 1 >>> store.add('c') 2 >>> list(store) ['a', 'b', 'c'] >>> store.index('a') 0 >>> store.index('b') 1 >>> store.index('d') 0 Args: initial: Initial elements of the store. default: Default string as a representation of unknown strings, i.e. those that do not exist in the store. """ def __init__( self, initial: Optional[Sequence[str]] = None, default: Optional[str] = None, ) -> None: super().__init__(initial) self.default = default def index(self, s: str) -> int: try: return super().index(s) except KeyError: if self.default is not None: return super().index(self.default) raise ValueError(f"cannot find '{s}'") def __eq__(self, o) -> bool: if not isinstance(o, StringStore): return False return self.default == o.default and super().__eq__(o) def __repr__(self) -> str: return f'{self.__class__.__name__}({list(self)!r}, default={self.default!r})' PKvGO]{],],#text2array-0.0.15.dist-info/LICENSE Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document. "Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License. "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License. "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below). "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution." "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work. 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. 3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and (b) You must cause any modified files to carry prominent notices stating that You changed the files; and (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. 5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. 6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. 7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License. 8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages. 9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. END OF TERMS AND CONDITIONS APPENDIX: How to apply the Apache License to your work. To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives. Copyright [yyyy] [name of copyright owner] Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. PK!HPO!text2array-0.0.15.dist-info/WHEEL HM K-*ϳR03rOK-J,/RH,szd&Y)r$[)T&UrPK!H9e $text2array-0.0.15.dist-info/METADATAWmS6_wXcC#(V#[>IN_ۻ넼Nw *UAEږC1T SΩFn+OĨ. \r.@ckÛVX# '~FHiBqc"ڕs7:CqQܺ|BDp\Gt|tt~C6%~:?Ώ#*a }S--Eqiz^34*Ba0#T^SSe ]* g%=*[K1.)/*#; s %~lTQ2Uf5e.j7KnIJ'+C&UѱcM!e36yڇuQ5״x~f]c)ʇ xPsx˨h5hkQQ:gh mo.!G@Le5 a'j߁GB)K$D_n(mRs(.Ϊe.L$R^j3CWv3Bl՗{u!]pZ(]dM⪩4-zߴϲ}h S\RLXړޔgodBҺ,dna ؇ Ejn߇B6JvŊԯ6)5Cj#JY"o EN3lU~OњM2Y捤T|j#i7חWUԓ5$-Ss |czqbOi pnCz~o^w=8== |f_mEÞ)@,ݬ ( udTQ$Q&pWLr)ه<NZX$XŭyɼΚoM£ 8J_Fq2uC)^fNE1d7aցh3~ =5À9i:YiwŸa^#Bh4{'Jh@0G܂[_PKJUOMtext2array/__init__.pyPK}IUOR%%text2array/batches.pyPKxEUOmjhhtext2array/iterators.pyPKvGOe%{{,text2array/samples.pyPKbHUOӏ$$g0text2array/vocab.pyPKvGO]{],],#'Utext2array-0.0.15.dist-info/LICENSEPK!HPO!Łtext2array-0.0.15.dist-info/WHEELPK!H9e $Ttext2array-0.0.15.dist-info/METADATAPK!HC"{text2array-0.0.15.dist-info/RECORDPK o