File size: 9,023 Bytes
803d9a3 100c2eb b462f85 100c2eb a254196 699f8e1 a254196 62fd389 100c2eb a254196 62fd389 b462f85 100c2eb b462f85 100c2eb b462f85 100c2eb b462f85 100c2eb b462f85 100c2eb b462f85 100c2eb b462f85 a254196 803d9a3 a254196 b462f85 62fd389 a254196 fa27fcf a254196 62fd389 dbcdf0f a254196 fa27fcf a254196 803d9a3 a254196 100c2eb 59ca01e a254196 100c2eb a254196 62fd389 100c2eb a254196 803d9a3 a254196 dbcdf0f a254196 dbcdf0f a254196 0e6c666 a254196 100c2eb 62fd389 a254196 62fd389 a254196 dbcdf0f a254196 0e6c666 a254196 100c2eb 62fd389 a254196 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 |
import tempfile
import traceback
import warnings
from abc import abstractmethod
from copy import deepcopy
from typing import Any, Callable, Dict, Generator, Iterable, List
from datasets import Dataset, DatasetDict, IterableDataset, IterableDatasetDict
from .dataclass import Dataclass, OptionalField
from .generator_utils import CopyingReusableGenerator, ReusableGenerator
from .logging_utils import get_logger
from .settings_utils import get_settings
settings = get_settings()
logger = get_logger()
class Stream(Dataclass):
@abstractmethod
def __iter__(self):
pass
@abstractmethod
def peek(self):
pass
@abstractmethod
def take(self, n):
pass
@abstractmethod
def set_copying(self, copying: bool):
pass
class ListStream(Stream):
instances_list: List[Dict[str, Any]]
copying: bool = False
def __iter__(self):
if self.copying:
return iter(deepcopy(self.instances_list))
return iter(self.instances_list)
def peek(self):
return next(iter(self))
def take(self, n) -> Generator:
for i, instance in enumerate(self.instances_list):
if i >= n:
break
yield instance
def set_copying(self, copying: bool):
self.copying = copying
class GeneratorStream(Stream):
"""A class for handling streaming data in a customizable way.
This class provides methods for generating, caching, and manipulating streaming data.
Attributes:
generator (function): A generator function for streaming data. :no-index:
gen_kwargs (dict, optional): A dictionary of keyword arguments for the generator function. :no-index:
caching (bool): Whether the data is cached or not. :no-index:
"""
generator: Callable
gen_kwargs: Dict[str, Any] = OptionalField(default_factory=dict)
caching: bool = False
copying: bool = False
def _get_initiator(self):
"""Private method to get the correct initiator based on the streaming and caching attributes.
Returns:
function: The correct initiator function.
"""
if self.caching:
return Dataset.from_generator
if self.copying:
return CopyingReusableGenerator
return ReusableGenerator
def _get_stream(self):
"""Private method to get the stream based on the initiator function.
Returns:
object: The stream object.
"""
return self._get_initiator()(self.generator, gen_kwargs=self.gen_kwargs)
def __iter__(self):
return iter(self._get_stream())
def peek(self):
return next(iter(self))
def take(self, n):
for i, instance in enumerate(self):
if i >= n:
break
yield instance
def set_copying(self, copying: bool):
self.copying = copying
class FaultyStreamError(Exception):
"""Base class for all stream-related exceptions."""
pass
class MissingStreamError(FaultyStreamError):
"""Raised when a required stream is missing."""
pass
class EmptyStreamError(FaultyStreamError):
"""Raised when a stream is unexpectedly empty."""
pass
def eager_failed():
traceback.print_exc()
warnings.warn(
"The eager execution has failed due to the error above.", stacklevel=2
)
class DynamicStream(Stream):
generator: Callable
gen_kwargs: Dict[str, Any] = OptionalField(default_factory=dict)
caching: bool = False
copying: bool = False
def __post_init__(self):
self.stream = None
if settings.use_eager_execution:
try:
instances_list = []
for instance in self.generator(**self.gen_kwargs):
instances_list.append(instance)
self.stream = ListStream(
instances_list=instances_list, copying=self.copying
)
except FaultyStreamError:
eager_failed()
except RuntimeError as e:
if isinstance(e.__cause__, FaultyStreamError):
eager_failed()
else:
raise e
if self.stream is None:
self.stream = GeneratorStream(
generator=self.generator,
gen_kwargs=self.gen_kwargs,
caching=self.caching,
copying=self.copying,
)
def __iter__(self):
return self.stream.__iter__()
def peek(self):
return self.stream.peek()
def take(self, n):
return self.stream.take(n)
def set_copying(self, copying: bool):
self.stream.set_copying(copying)
class MultiStream(dict):
"""A class for handling multiple streams of data in a dictionary-like format.
This class extends dict and its values should be instances of the Stream class.
Attributes:
data (dict): A dictionary of Stream objects.
"""
def __init__(self, data=None):
"""Initializes the MultiStream with the provided data.
Args:
data (dict, optional): A dictionary of Stream objects. Defaults to None.
Raises:
AssertionError: If the values are not instances of Stream or keys are not strings.
"""
for key, value in data.items():
isinstance(value, Stream), "MultiStream values must be Stream"
isinstance(key, str), "MultiStream keys must be strings"
super().__init__(data)
def get_generator(self, key) -> Generator:
"""Gets a generator for a specified key.
Args:
key (str): The key for the generator.
Yields:
object: The next value in the stream.
"""
yield from self[key]
def set_caching(self, caching: bool):
for stream in self.values():
stream.caching = caching
def set_copying(self, copying: bool):
for stream in self.values():
stream.set_copying(copying)
def to_dataset(self, disable_cache=True, cache_dir=None) -> DatasetDict:
with tempfile.TemporaryDirectory() as dir_to_be_deleted:
cache_dir = dir_to_be_deleted if disable_cache else cache_dir
return DatasetDict(
{
key: Dataset.from_generator(
self.get_generator,
keep_in_memory=disable_cache,
cache_dir=cache_dir,
gen_kwargs={"key": key},
)
for key in self.keys()
}
)
def to_iterable_dataset(self) -> IterableDatasetDict:
return IterableDatasetDict(
{
key: IterableDataset.from_generator(
self.get_generator, gen_kwargs={"key": key}
)
for key in self.keys()
}
)
def __setitem__(self, key, value):
assert isinstance(value, Stream), "StreamDict values must be Stream"
assert isinstance(key, str), "StreamDict keys must be strings"
super().__setitem__(key, value)
@classmethod
def from_generators(
cls, generators: Dict[str, ReusableGenerator], caching=False, copying=False
):
"""Creates a MultiStream from a dictionary of ReusableGenerators.
Args:
generators (Dict[str, ReusableGenerator]): A dictionary of ReusableGenerators.
caching (bool, optional): Whether the data should be cached or not. Defaults to False.
copying (bool, optional): Whether the data should be copied or not. Defaults to False.
Returns:
MultiStream: A MultiStream object.
"""
assert all(isinstance(v, ReusableGenerator) for v in generators.values())
return cls(
{
key: DynamicStream(
generator.generator,
gen_kwargs=generator.gen_kwargs,
caching=caching,
copying=copying,
)
for key, generator in generators.items()
}
)
@classmethod
def from_iterables(
cls, iterables: Dict[str, Iterable], caching=False, copying=False
):
"""Creates a MultiStream from a dictionary of iterables.
Args:
iterables (Dict[str, Iterable]): A dictionary of iterables.
caching (bool, optional): Whether the data should be cached or not. Defaults to False.
copying (bool, optional): Whether the data should be copied or not. Defaults to False.
Returns:
MultiStream: A MultiStream object.
"""
return cls(
{
key: DynamicStream(
iterable.__iter__,
caching=caching,
copying=copying,
)
for key, iterable in iterables.items()
}
)
|