oups 2025.9.5__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of oups might be problematic. Click here for more details.
- oups/__init__.py +40 -0
- oups/date_utils.py +62 -0
- oups/defines.py +26 -0
- oups/numpy_utils.py +114 -0
- oups/stateful_loop/__init__.py +14 -0
- oups/stateful_loop/loop_persistence_io.py +55 -0
- oups/stateful_loop/stateful_loop.py +654 -0
- oups/stateful_loop/validate_loop_usage.py +338 -0
- oups/stateful_ops/__init__.py +22 -0
- oups/stateful_ops/aggstream/__init__.py +12 -0
- oups/stateful_ops/aggstream/aggstream.py +1524 -0
- oups/stateful_ops/aggstream/cumsegagg.py +580 -0
- oups/stateful_ops/aggstream/jcumsegagg.py +416 -0
- oups/stateful_ops/aggstream/segmentby.py +1018 -0
- oups/stateful_ops/aggstream/utils.py +71 -0
- oups/stateful_ops/asof_merger/__init__.py +11 -0
- oups/stateful_ops/asof_merger/asof_merger.py +750 -0
- oups/stateful_ops/asof_merger/get_config.py +401 -0
- oups/stateful_ops/asof_merger/validate_params.py +285 -0
- oups/store/__init__.py +15 -0
- oups/store/filepath_utils.py +68 -0
- oups/store/indexer.py +457 -0
- oups/store/ordered_parquet_dataset/__init__.py +19 -0
- oups/store/ordered_parquet_dataset/metadata_filename.py +50 -0
- oups/store/ordered_parquet_dataset/ordered_parquet_dataset/__init__.py +15 -0
- oups/store/ordered_parquet_dataset/ordered_parquet_dataset/base.py +863 -0
- oups/store/ordered_parquet_dataset/ordered_parquet_dataset/read_only.py +252 -0
- oups/store/ordered_parquet_dataset/parquet_adapter.py +157 -0
- oups/store/ordered_parquet_dataset/write/__init__.py +19 -0
- oups/store/ordered_parquet_dataset/write/iter_merge_split_data.py +131 -0
- oups/store/ordered_parquet_dataset/write/merge_split_strategies/__init__.py +22 -0
- oups/store/ordered_parquet_dataset/write/merge_split_strategies/base.py +784 -0
- oups/store/ordered_parquet_dataset/write/merge_split_strategies/n_rows_strategy.py +297 -0
- oups/store/ordered_parquet_dataset/write/merge_split_strategies/time_period_strategy.py +319 -0
- oups/store/ordered_parquet_dataset/write/write.py +270 -0
- oups/store/store/__init__.py +11 -0
- oups/store/store/dataset_cache.py +50 -0
- oups/store/store/iter_intersections.py +397 -0
- oups/store/store/store.py +345 -0
- oups-2025.9.5.dist-info/LICENSE +201 -0
- oups-2025.9.5.dist-info/METADATA +44 -0
- oups-2025.9.5.dist-info/RECORD +43 -0
- oups-2025.9.5.dist-info/WHEEL +4 -0
|
@@ -0,0 +1,345 @@
|
|
|
1
|
+
#!/usr/bin/env python3
|
|
2
|
+
"""
|
|
3
|
+
Created on Wed Dec 4 18:00:00 2021.
|
|
4
|
+
|
|
5
|
+
@author: pierrot
|
|
6
|
+
|
|
7
|
+
"""
|
|
8
|
+
from collections.abc import Iterator
|
|
9
|
+
from pathlib import Path
|
|
10
|
+
|
|
11
|
+
from pandas import Timestamp
|
|
12
|
+
from sortedcontainers import SortedSet
|
|
13
|
+
|
|
14
|
+
from oups.store.filepath_utils import files_at_depth
|
|
15
|
+
from oups.store.indexer import StoreKey
|
|
16
|
+
from oups.store.indexer import TopLevelIndexer
|
|
17
|
+
from oups.store.indexer import is_toplevel
|
|
18
|
+
from oups.store.ordered_parquet_dataset import OrderedParquetDataset
|
|
19
|
+
from oups.store.ordered_parquet_dataset.metadata_filename import get_md_basename
|
|
20
|
+
from oups.store.store.dataset_cache import cached_datasets
|
|
21
|
+
from oups.store.store.iter_intersections import iter_intersections
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
def get_keys[K: StoreKey](basepath: Path, indexer: TopLevelIndexer[K]) -> SortedSet[K]:
|
|
25
|
+
"""
|
|
26
|
+
Identify ordered parquet dataset in directory.
|
|
27
|
+
|
|
28
|
+
Scan 'basepath' directory and create instances of 'indexer' class from
|
|
29
|
+
compatible subpaths. Only file which name ends by '_opdmd' are retained
|
|
30
|
+
to construct a key.
|
|
31
|
+
|
|
32
|
+
Parameters
|
|
33
|
+
----------
|
|
34
|
+
basepath : Path
|
|
35
|
+
Path to directory containing a dataset collection, in folders complying
|
|
36
|
+
with the schema defined by the indexer class.
|
|
37
|
+
indexer : TopLevelIndexer[K]
|
|
38
|
+
Class decorated with '@toplevel' decorator, and defining a path
|
|
39
|
+
schema.
|
|
40
|
+
|
|
41
|
+
Returns
|
|
42
|
+
-------
|
|
43
|
+
SortedSet[StoreKey]
|
|
44
|
+
Sorted set of keys (i.e. instances of indexer) that can be
|
|
45
|
+
found in 'basepath' directory and with a 'valid' opd metadata file
|
|
46
|
+
(ending by '_opdmd').
|
|
47
|
+
|
|
48
|
+
"""
|
|
49
|
+
depth = indexer.depth - 1
|
|
50
|
+
# Filter, keeping only folders having files with correct extension,
|
|
51
|
+
# then materialize paths into keys, filtering out those that can't.
|
|
52
|
+
return SortedSet(
|
|
53
|
+
[
|
|
54
|
+
key
|
|
55
|
+
for path, files in files_at_depth(basepath, depth)
|
|
56
|
+
for file in files
|
|
57
|
+
if (
|
|
58
|
+
(opdmd_basename := get_md_basename(file))
|
|
59
|
+
and (
|
|
60
|
+
key := indexer.from_path(
|
|
61
|
+
Path(*path.parts[-depth:]) / opdmd_basename,
|
|
62
|
+
)
|
|
63
|
+
)
|
|
64
|
+
)
|
|
65
|
+
],
|
|
66
|
+
)
|
|
67
|
+
|
|
68
|
+
|
|
69
|
+
class Store[K: StoreKey]:
|
|
70
|
+
"""
|
|
71
|
+
Sorted list of keys (indexes to parquet datasets).
|
|
72
|
+
|
|
73
|
+
Attributes
|
|
74
|
+
----------
|
|
75
|
+
basepath : Path
|
|
76
|
+
Directory path to the set of parquet datasets.
|
|
77
|
+
indexer : TopLevelIndexer[KT]
|
|
78
|
+
Indexer schema (class) to be used to index parquet datasets.
|
|
79
|
+
keys : SortedSet[K]
|
|
80
|
+
Set of indexes of existing parquet datasets.
|
|
81
|
+
_needs_keys_refresh : bool
|
|
82
|
+
Flag indicating that the 'keys' property needs to be refreshed from
|
|
83
|
+
disk. Set to True when a new 'OrderedParquetDataset' is accessed but
|
|
84
|
+
doesn't yet have a metadata file on disk. When True, the next access to
|
|
85
|
+
the 'keys' property will rescan the filesystem to update the keys
|
|
86
|
+
collection.
|
|
87
|
+
|
|
88
|
+
Methods
|
|
89
|
+
-------
|
|
90
|
+
get
|
|
91
|
+
Return the ``OrderedParquetDataset`` instance corresponding to ``key``.
|
|
92
|
+
iter_intersections
|
|
93
|
+
Iterate over row group intersections across multiple datasets in store.
|
|
94
|
+
__getitem__
|
|
95
|
+
Return the ``OrderedParquetDataset`` instance corresponding to ``key``.
|
|
96
|
+
__delitem__
|
|
97
|
+
Remove dataset from parquet set.
|
|
98
|
+
__iter__
|
|
99
|
+
Iterate over keys.
|
|
100
|
+
__len__
|
|
101
|
+
Return number of datasets.
|
|
102
|
+
__repr__
|
|
103
|
+
List of datasets.
|
|
104
|
+
__contains__
|
|
105
|
+
Assess presence of this dataset.
|
|
106
|
+
|
|
107
|
+
Notes
|
|
108
|
+
-----
|
|
109
|
+
``SortedSet`` is the data structure retained for ``keys`` instead of
|
|
110
|
+
``SortedList`` as its ``__contains__`` appears faster.
|
|
111
|
+
|
|
112
|
+
"""
|
|
113
|
+
|
|
114
|
+
def __init__(self, basepath: str | Path, indexer: TopLevelIndexer[K]):
|
|
115
|
+
"""
|
|
116
|
+
Instantiate parquet set.
|
|
117
|
+
|
|
118
|
+
Parameters
|
|
119
|
+
----------
|
|
120
|
+
basepath : Union[str, Path]
|
|
121
|
+
Path of directory containing parquet datasets.
|
|
122
|
+
indexer : TopLevelIndexer[K]
|
|
123
|
+
Class (not class instance) of the indexer to be used for:
|
|
124
|
+
|
|
125
|
+
- identifying existing parquet datasets in 'basepath' directory,
|
|
126
|
+
- creating the folders where recording new parquet datasets.
|
|
127
|
+
|
|
128
|
+
"""
|
|
129
|
+
if not is_toplevel(indexer):
|
|
130
|
+
raise TypeError(f"{indexer.__name__} has to be '@toplevel' decorated.")
|
|
131
|
+
self._basepath = Path(basepath).resolve()
|
|
132
|
+
self._indexer = indexer
|
|
133
|
+
self._keys = get_keys(basepath, indexer)
|
|
134
|
+
self._needs_keys_refresh = False
|
|
135
|
+
|
|
136
|
+
@property
|
|
137
|
+
def basepath(self) -> Path:
|
|
138
|
+
"""
|
|
139
|
+
Return basepath.
|
|
140
|
+
|
|
141
|
+
Returns
|
|
142
|
+
-------
|
|
143
|
+
Path
|
|
144
|
+
Basepath.
|
|
145
|
+
|
|
146
|
+
"""
|
|
147
|
+
return self._basepath
|
|
148
|
+
|
|
149
|
+
@property
|
|
150
|
+
def indexer(self) -> TopLevelIndexer[K]:
|
|
151
|
+
"""
|
|
152
|
+
Return indexer.
|
|
153
|
+
|
|
154
|
+
Returns
|
|
155
|
+
-------
|
|
156
|
+
TopLevelIndexer[K]
|
|
157
|
+
The toplevel indexer class used by this store.
|
|
158
|
+
|
|
159
|
+
"""
|
|
160
|
+
return self._indexer
|
|
161
|
+
|
|
162
|
+
@property
|
|
163
|
+
def keys(self) -> SortedSet[K]:
|
|
164
|
+
"""
|
|
165
|
+
Return keys.
|
|
166
|
+
|
|
167
|
+
Returns
|
|
168
|
+
-------
|
|
169
|
+
SortedSet[K]
|
|
170
|
+
Sorted set of keys.
|
|
171
|
+
|
|
172
|
+
"""
|
|
173
|
+
if self._needs_keys_refresh:
|
|
174
|
+
# Refresh keys.
|
|
175
|
+
self._keys = get_keys(self.basepath, self.indexer)
|
|
176
|
+
self._needs_keys_refresh = False
|
|
177
|
+
return self._keys
|
|
178
|
+
|
|
179
|
+
def __len__(self) -> int:
|
|
180
|
+
"""
|
|
181
|
+
Return number of datasets.
|
|
182
|
+
|
|
183
|
+
Returns
|
|
184
|
+
-------
|
|
185
|
+
int
|
|
186
|
+
Number of datasets.
|
|
187
|
+
|
|
188
|
+
"""
|
|
189
|
+
return len(self.keys)
|
|
190
|
+
|
|
191
|
+
def __repr__(self) -> str:
|
|
192
|
+
"""
|
|
193
|
+
List of datasets.
|
|
194
|
+
|
|
195
|
+
Returns
|
|
196
|
+
-------
|
|
197
|
+
str
|
|
198
|
+
String representation of the store.
|
|
199
|
+
|
|
200
|
+
"""
|
|
201
|
+
return "\n".join(map(str, self.keys))
|
|
202
|
+
|
|
203
|
+
def __contains__(self, key: K) -> bool:
|
|
204
|
+
"""
|
|
205
|
+
Assess presence of this dataset.
|
|
206
|
+
|
|
207
|
+
Parameters
|
|
208
|
+
----------
|
|
209
|
+
key : K
|
|
210
|
+
Key to assess presence of.
|
|
211
|
+
|
|
212
|
+
Returns
|
|
213
|
+
-------
|
|
214
|
+
bool
|
|
215
|
+
True if the dataset exists, False otherwise.
|
|
216
|
+
|
|
217
|
+
"""
|
|
218
|
+
return key in self.keys
|
|
219
|
+
|
|
220
|
+
def __iter__(self) -> Iterator[K]:
|
|
221
|
+
"""
|
|
222
|
+
Iterate over keys.
|
|
223
|
+
|
|
224
|
+
Yields
|
|
225
|
+
------
|
|
226
|
+
KT
|
|
227
|
+
Key of each dataset.
|
|
228
|
+
|
|
229
|
+
"""
|
|
230
|
+
yield from self.keys
|
|
231
|
+
|
|
232
|
+
def __delitem__(self, key: K):
|
|
233
|
+
"""
|
|
234
|
+
Remove dataset from parquet set.
|
|
235
|
+
|
|
236
|
+
Parameter
|
|
237
|
+
---------
|
|
238
|
+
key : K
|
|
239
|
+
Key specifying the location where to delete the data. It has to be
|
|
240
|
+
an instance produced by the indexer class provided at Store
|
|
241
|
+
instantiation.
|
|
242
|
+
|
|
243
|
+
Raises
|
|
244
|
+
------
|
|
245
|
+
KeyError
|
|
246
|
+
If the key is not found in the store.
|
|
247
|
+
|
|
248
|
+
"""
|
|
249
|
+
if key in self.keys:
|
|
250
|
+
# Get OPD instance and remove its files
|
|
251
|
+
self.get(key).remove_from_disk()
|
|
252
|
+
# Update store's key collection
|
|
253
|
+
self._keys.remove(key)
|
|
254
|
+
# Clean up empty parent directories
|
|
255
|
+
upper_dir = (self.basepath / key.to_path()).parent
|
|
256
|
+
while (upper_dir != self.basepath) and (not list(upper_dir.iterdir())):
|
|
257
|
+
upper_dir.rmdir()
|
|
258
|
+
upper_dir = upper_dir.parent
|
|
259
|
+
else:
|
|
260
|
+
raise KeyError(f"key '{key}' not found in store.")
|
|
261
|
+
|
|
262
|
+
def __getitem__(self, key: K) -> OrderedParquetDataset:
|
|
263
|
+
"""
|
|
264
|
+
Return the ``OrderedParquetDataset`` instance corresponding to ``key``.
|
|
265
|
+
|
|
266
|
+
Wrapper to ``get`` method.
|
|
267
|
+
|
|
268
|
+
Parameters
|
|
269
|
+
----------
|
|
270
|
+
key : K
|
|
271
|
+
Key specifying the location where to read the data from. It has to
|
|
272
|
+
be an instance produced by the indexer class provided at Store
|
|
273
|
+
instantiation.
|
|
274
|
+
|
|
275
|
+
Returns
|
|
276
|
+
-------
|
|
277
|
+
OrderedParquetDataset
|
|
278
|
+
The ``OrderedParquetDataset`` instance corresponding to ``key``.
|
|
279
|
+
|
|
280
|
+
"""
|
|
281
|
+
return self.get(key)
|
|
282
|
+
|
|
283
|
+
def get(self, key: K, **kwargs) -> OrderedParquetDataset:
|
|
284
|
+
"""
|
|
285
|
+
Return the OrderedParquetDataset instance with custom parameters.
|
|
286
|
+
|
|
287
|
+
Parameters
|
|
288
|
+
----------
|
|
289
|
+
key : K
|
|
290
|
+
Key specifying the location where to read the data from.
|
|
291
|
+
**kwargs : dict
|
|
292
|
+
Additional parameters to pass to OrderedParquetDataset constructor
|
|
293
|
+
(e.g., 'ordered_on', 'lock_timeout', 'lock_lifetime').
|
|
294
|
+
|
|
295
|
+
Returns
|
|
296
|
+
-------
|
|
297
|
+
OrderedParquetDataset
|
|
298
|
+
The OrderedParquetDataset instance corresponding to key. Creates a
|
|
299
|
+
new OrderedParquetDataset object if the key doesn't exist.
|
|
300
|
+
|
|
301
|
+
"""
|
|
302
|
+
opd = OrderedParquetDataset(self.basepath / key.to_path(), **kwargs)
|
|
303
|
+
if opd.is_newly_initialized:
|
|
304
|
+
self._needs_keys_refresh = True
|
|
305
|
+
return opd
|
|
306
|
+
|
|
307
|
+
def iter_intersections(
|
|
308
|
+
self,
|
|
309
|
+
keys: list[K],
|
|
310
|
+
start: float | Timestamp | None = None,
|
|
311
|
+
n_prev: int | list[int] | None = 0,
|
|
312
|
+
end_excl: float | Timestamp | None = None,
|
|
313
|
+
):
|
|
314
|
+
"""
|
|
315
|
+
Iterate over row group intersections across multiple datasets in store.
|
|
316
|
+
|
|
317
|
+
This method handles dataset caching and lifecycle management, then
|
|
318
|
+
delegates to the core iter_intersections function.
|
|
319
|
+
|
|
320
|
+
Parameters
|
|
321
|
+
----------
|
|
322
|
+
keys : list[K]
|
|
323
|
+
List of dataset keys.
|
|
324
|
+
start : Optional[Union[int, float, Timestamp]], default None
|
|
325
|
+
Start value (inclusive) for the 'ordered_on' column range.
|
|
326
|
+
n_prev : Union[int, list[int]], default 0
|
|
327
|
+
Number of previous rows (number of values before 'start') to prepend
|
|
328
|
+
to first yielded dataframe for each key.
|
|
329
|
+
If a list, values are used for each key in the same order as 'keys'.
|
|
330
|
+
end_excl : Optional[Union[int, float, Timestamp]], default None
|
|
331
|
+
End value (exclusive) for the 'ordered_on' column range.
|
|
332
|
+
|
|
333
|
+
Yields
|
|
334
|
+
------
|
|
335
|
+
dict[K, DataFrame]
|
|
336
|
+
Dictionary mapping each key to its corresponding DataFrame chunk.
|
|
337
|
+
|
|
338
|
+
"""
|
|
339
|
+
with cached_datasets(self, keys) as datasets:
|
|
340
|
+
yield from iter_intersections(
|
|
341
|
+
datasets=datasets,
|
|
342
|
+
start=start,
|
|
343
|
+
n_prev=n_prev,
|
|
344
|
+
end_excl=end_excl,
|
|
345
|
+
)
|
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright 2025, pierrot
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
|
@@ -0,0 +1,44 @@
|
|
|
1
|
+
Metadata-Version: 2.3
|
|
2
|
+
Name: oups
|
|
3
|
+
Version: 2025.9.5
|
|
4
|
+
Summary: Out-of-core pipelines over ordered data: StatefulLoop, stateful ops, and ordered Parquet Store.
|
|
5
|
+
License: Apache-2.0
|
|
6
|
+
Keywords: out-of-core,streaming,stateful,time-series,pandas,parquet,data-engineering
|
|
7
|
+
Author: pierrot
|
|
8
|
+
Requires-Python: >=3.13,<4.0
|
|
9
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
10
|
+
Classifier: Programming Language :: Python :: 3
|
|
11
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
12
|
+
Requires-Dist: cloudpickle (>=3.1.1)
|
|
13
|
+
Requires-Dist: fastparquet (>=2023.10.1)
|
|
14
|
+
Requires-Dist: flufl-lock (>=8.2.0)
|
|
15
|
+
Requires-Dist: joblib (>=1.3.2)
|
|
16
|
+
Requires-Dist: numba (>=0.61.2)
|
|
17
|
+
Requires-Dist: numpy (>=2.0)
|
|
18
|
+
Requires-Dist: pandas (>=2.2.3)
|
|
19
|
+
Requires-Dist: sortedcontainers (>=2.4.0)
|
|
20
|
+
Project-URL: Changelog, https://codeberg.org/pierrot/oups/src/branch/main/CHANGELOG.md
|
|
21
|
+
Project-URL: Documentation, https://codeberg.org/pierrot/oups/src/branch/main/docs
|
|
22
|
+
Project-URL: Homepage, https://codeberg.org/pierrot/oups
|
|
23
|
+
Project-URL: Issues, https://codeberg.org/pierrot/oups/issues
|
|
24
|
+
Project-URL: Source, https://codeberg.org/pierrot/oups
|
|
25
|
+
Description-Content-Type: text/markdown
|
|
26
|
+
|
|
27
|
+
# Welcome to oups!
|
|
28
|
+
|
|
29
|
+
## What is oups?
|
|
30
|
+
*oups* stands for Ordered Unified Processing Stack — out-of-core processing for ordered data (batch + live).
|
|
31
|
+
|
|
32
|
+
*oups* is a Python toolkit for building end-to-end pipelines over ordered data with the same code in offline training and live streaming/batch contexts.
|
|
33
|
+
|
|
34
|
+
It centers on ``StatefulLoop`` (``loop.bind_function_state``, ``loop.iterate``, ``loop.buffer``), which binds and persists function/object state, orchestrates chunked iteration, and buffers DataFrames under a memory cap with flush-on-limit or last-iteration semantics.
|
|
35
|
+
Complementing the loop, ``stateful_ops`` provides vectorized, chunk-friendly primitives like ``AsofMerger`` for multi-DataFrame as-of joins (with optional windows of previous values) and ``SegmentedAggregator`` (planned) for streamed segmentation and aggregation.
|
|
36
|
+
The ``store`` package manages ordered Parquet datasets via schema-driven keys (``@toplevel``), supports incremental updates (``store[key].write(...)``) and duplicate handling, and offers synchronized iteration across datasets via ``store.iter_intersections(...)`` with optional warm-up (``n_prev``).
|
|
37
|
+
|
|
38
|
+
Together these pieces enable out-of-core processing with resumability, and deterministic buffering. The design favors explicit, minimal APIs and reproducible results, aligning offline feature generation with online serving.
|
|
39
|
+
|
|
40
|
+
## Links
|
|
41
|
+
|
|
42
|
+
- 📖 **[Documentation](https://pierrot.codeberg.page/oups/)** - Guides and API reference
|
|
43
|
+
- 📋 **[Changelog](CHANGELOG.md)** - Release notes and version history
|
|
44
|
+
|
|
@@ -0,0 +1,43 @@
|
|
|
1
|
+
oups/__init__.py,sha256=Tkw_6ZVwI7Ajr9P2YqDJV-AOAt-MJhxAwYSjLV1Xmq0,1060
|
|
2
|
+
oups/date_utils.py,sha256=3E1K1b2oIZVlI0FO4Eq8hW24ZFTEL-2UwnRLPHnPXxA,1501
|
|
3
|
+
oups/defines.py,sha256=d4f0O1m717WlqN8lP9jGdY3q0Z2qyzpSJVMkukqySog,959
|
|
4
|
+
oups/numpy_utils.py,sha256=KmtBillsNwKdB-1Nv8k-fbJHsADvYfPE2uMBNGdpMoY,3404
|
|
5
|
+
oups/stateful_loop/__init__.py,sha256=hSPoYRGm0nZZKE5ieYze5d5zIdU3pVGTrBIRHuwNUPg,210
|
|
6
|
+
oups/stateful_loop/loop_persistence_io.py,sha256=Dx41DgEa2KQ9-BCfGQnajjcbIi3YWbiPfxS400qJXY4,1666
|
|
7
|
+
oups/stateful_loop/stateful_loop.py,sha256=w7NUyY4SwbzCfgCJQvMW_DaFuEN39DRqPbo-s0gKTmM,26144
|
|
8
|
+
oups/stateful_loop/validate_loop_usage.py,sha256=mnJWjcYKZZ_9446ao7IPy5kkrd3QQgxVcT9yxnzr-To,12249
|
|
9
|
+
oups/stateful_ops/__init__.py,sha256=nRxqMdhYHkB8_7aKY6Oa_Ah05Kp-PFnKwSVIDqaGi5w,470
|
|
10
|
+
oups/stateful_ops/aggstream/__init__.py,sha256=iVbdABSRg1l14h9cO0oCuNPppmnYLlHEbz3MAOUWpAw,204
|
|
11
|
+
oups/stateful_ops/aggstream/aggstream.py,sha256=g9bbNAuFTpiOmmP8tZ8KXOz8gh-ln1d-kdaaLjWXSXU,70392
|
|
12
|
+
oups/stateful_ops/aggstream/cumsegagg.py,sha256=G_jz2FNfrVv9Ix-qcgnC3OYC9QGMlRtd_b6wyF9rXPc,27389
|
|
13
|
+
oups/stateful_ops/aggstream/jcumsegagg.py,sha256=Zm_yojGxFEGnBv9zuIexWpWSCEJmFFT89EpAuoGQHhE,14607
|
|
14
|
+
oups/stateful_ops/aggstream/segmentby.py,sha256=nJEI2-_y6k7_8-RCDSOEsheSHTkvotke2kw716YBrBs,46485
|
|
15
|
+
oups/stateful_ops/aggstream/utils.py,sha256=lIWJmLDY3mT71CJ1J_Fv-tECKEKKqIE0yhCkniJxF1k,2054
|
|
16
|
+
oups/stateful_ops/asof_merger/__init__.py,sha256=vHSmkxKrDg4wU9s1oj88IAe0t1z5PZQ-5xLcuf6U-0Y,161
|
|
17
|
+
oups/stateful_ops/asof_merger/asof_merger.py,sha256=djPKMPXYS91bsIGeJrP_uXID6Glkt8k-98A3uVCho7o,36652
|
|
18
|
+
oups/stateful_ops/asof_merger/get_config.py,sha256=cUo6JwzneruhsSYWJzstnulfFn0uTqnFT7p-0n3WiiI,16974
|
|
19
|
+
oups/stateful_ops/asof_merger/validate_params.py,sha256=W7oEpF8XC0Il6swGMAY75KQotSlp8MwUseo3sXbjPOg,10148
|
|
20
|
+
oups/store/__init__.py,sha256=cApoS3iSXwcegv-iqbSOh5bXXN5ezNNdqGGABTSwWlM,422
|
|
21
|
+
oups/store/filepath_utils.py,sha256=bBkFCIExgeJgrk_TAOT7jsK1UjYe-eQTkQsVDmgmOHo,1811
|
|
22
|
+
oups/store/indexer.py,sha256=KQr1TcWnGx4C1-iBJs9N0JhrIA44BuSk04OiClmbP2w,14831
|
|
23
|
+
oups/store/ordered_parquet_dataset/__init__.py,sha256=KT0-7oOY1GZl2hTwjAYDVWFS22OUMCKMfb7hKxp_K9o,372
|
|
24
|
+
oups/store/ordered_parquet_dataset/metadata_filename.py,sha256=YqhmKUQ6T5QyxixU_KTF9j5vD1w6uhSOeUipz1vuN44,1059
|
|
25
|
+
oups/store/ordered_parquet_dataset/ordered_parquet_dataset/__init__.py,sha256=SKQxlX-xzTfxwBef2rzgn2BbUdE5c3UJ0IMXhgz_Zmc,248
|
|
26
|
+
oups/store/ordered_parquet_dataset/ordered_parquet_dataset/base.py,sha256=Rju3mBIDJ8sS4BpPDL4CavmYkvx4LjJe6j-rKJ2USFQ,33358
|
|
27
|
+
oups/store/ordered_parquet_dataset/ordered_parquet_dataset/read_only.py,sha256=3Cv4OH2UM5gj1ekyGmcVkgABtMwDSujfcJEanght1rs,8832
|
|
28
|
+
oups/store/ordered_parquet_dataset/parquet_adapter.py,sha256=xhOhudNLi0bDvxObT0Rvx3_t5HB_ojIF72uWKiNJ0Vs,4988
|
|
29
|
+
oups/store/ordered_parquet_dataset/write/__init__.py,sha256=IwjAp3s0y7dtsR_MQ3HvV-JxrIZUcWmJX3l5rf6eNUk,396
|
|
30
|
+
oups/store/ordered_parquet_dataset/write/iter_merge_split_data.py,sha256=zU-oRz20kQOeYDA3RHVmzXjTQKJhMBQ0tYpAeNm3caw,5270
|
|
31
|
+
oups/store/ordered_parquet_dataset/write/merge_split_strategies/__init__.py,sha256=kjNLNjojUjKedK7ZAVVyKLOK1dXWzWsEV0qZsEEyivo,700
|
|
32
|
+
oups/store/ordered_parquet_dataset/write/merge_split_strategies/base.py,sha256=hl-7Q1iyslbBZE3HY4SEEuKOETgTuLoTJomuglOQdx4,34029
|
|
33
|
+
oups/store/ordered_parquet_dataset/write/merge_split_strategies/n_rows_strategy.py,sha256=uRtDO8vS0CvPXF3b73pI7d1W1F22NeKE43poKn24PbQ,11801
|
|
34
|
+
oups/store/ordered_parquet_dataset/write/merge_split_strategies/time_period_strategy.py,sha256=Ye47ZoBy6P7TEL2Glmq_34qzpSeKvTBQrRqsDh_n3f8,12691
|
|
35
|
+
oups/store/ordered_parquet_dataset/write/write.py,sha256=CAZgPkXgpjM7mq6PgiJg4rlocl61P2CDr8TCqy8mM4c,12052
|
|
36
|
+
oups/store/store/__init__.py,sha256=OVm6fQncS1_726-K5O1cob68DVc9cGizPwfnfrKmozc,121
|
|
37
|
+
oups/store/store/dataset_cache.py,sha256=J0fE4RHyA2TWNQehgI580ndlrtJZfOyez_wtv1IbEg8,1091
|
|
38
|
+
oups/store/store/iter_intersections.py,sha256=xgPWHxDhbJH6pOwuNy3pabcU9_4s3-iN8RJQ1V86JOk,16740
|
|
39
|
+
oups/store/store/store.py,sha256=aJg2p9O_YVPG3-SPbCXTuCyX4BoJwU6UEKK29nj4rb8,10460
|
|
40
|
+
oups-2025.9.5.dist-info/LICENSE,sha256=feEGyubvFPPWktFR_FTDkcjTaosHXBhKdi9IB4klelk,11539
|
|
41
|
+
oups-2025.9.5.dist-info/METADATA,sha256=g6qoIN2Mkhklk94z9lXNGO2oOycEa26QKF_iGKIPVaw,2671
|
|
42
|
+
oups-2025.9.5.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
|
|
43
|
+
oups-2025.9.5.dist-info/RECORD,,
|