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
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
|
%global _empty_manifest_terminate_build 0
Name: python-lazy-dataset
Version: 0.0.14
Release: 1
Summary: Process large datasets as if it was an iterable.
License: MIT
URL: https://github.com/fgnt/lazy_dataset
Source0: https://mirrors.aliyun.com/pypi/web/packages/43/e6/5eaa9245879ef9346c2f81af5a47f93322f4f8013e5ed1142496fb15492d/lazy_dataset-0.0.14.tar.gz
BuildArch: noarch
Requires: python3-numpy
Requires: python3-humanfriendly
Requires: python3-mock
Requires: python3-diskcache
Requires: python3-psutil
Requires: python3-humanfriendly
Requires: python3-psutil
Requires: python3-diskcache
Requires: python3-mock
%description
# lazy_dataset
[](https://travis-ci.org/fgnt/lazy_dataset)
[](https://codecov.io/github/fgnt/lazy_dataset?branch=master)
[](https://github.com/fgnt/lazy_dataset/blob/master/LICENSE)
Lazy_dataset is a helper to deal with large datasets that do not fit into memory.
It allows to define transformations that are applied lazily,
(e.g. a mapping function to read data from HDD). When someone iterates over the dataset all
transformations are applied.
Supported transformations:
- `dataset.map(map_fn)`: Apply the function `map_fn` to each example ([builtins.map](https://docs.python.org/3/library/functions.html#map))
- `dataset[2]`: Get example at index `2`.
- `dataset['example_id']` Get that example that has the example id `'example_id'`.
- `dataset[10:20]`: Get a sub dataset that contains only the examples in the slice 10 to 20.
- `dataset.filter(filter_fn, lazy=True)` Drops examples where `filter_fn(example)` is false ([builtins.filter](https://docs.python.org/3/library/functions.html#filter)).
- `dataset.concatenate(*others)`: Concatenates two or more datasets ([numpy.concatenate](https://docs.scipy.org/doc/numpy-1.14.0/reference/generated/numpy.concatenate.html))
- `dataset.intersperse(*others)`: Combine two or more datasets such that examples of each input dataset are evenly spaced (https://stackoverflow.com/a/19293603).
- `dataset.zip(*others)`: Zip two or more datasets
- `dataset.shuffle(reshuffle=False)`: Shuffles the dataset. When `reshuffle` is `True` it shuffles each time when you iterate over the data.
- `dataset.tile(reps, shuffle=False)`: Repeats the dataset `reps` times and concatenates it ([numpy.tile](https://docs.scipy.org/doc/numpy/reference/generated/numpy.tile.html))
- `dataset.groupby(group_fn)`: Groups examples together. In contrast to `itertools.groupby` a sort is not nessesary, like in pandas ([itertools.groupby](https://docs.python.org/3/library/itertools.html#itertools.groupby), [pandas.DataFrame.groupby](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.groupby.html))
- `dataset.sort(key_fn, sort_fn=sorted)`: Sorts the examples depending on the values `key_fn(example)` ([list.sort](https://docs.python.org/3/library/stdtypes.html#list.sort))
- `dataset.batch(batch_size, drop_last=False)`: Batches `batch_size` examples together as a list. Usually followed by a map ([tensorflow.data.Dataset.batch](https://www.tensorflow.org/api_docs/python/tf/data/Dataset#batch))
- `dataset.random_choice()`: Get a random example ([numpy.random.choice](https://docs.scipy.org/doc/numpy/reference/generated/numpy.random.choice.html))
- `dataset.cache()`: Cache in RAM (similar to ESPnet's `keep_all_data_on_mem`)
- `dataset.diskcache()`: Cache to a cache directory on the local filesystem (useful in clusters network slow filesystems)
- ...
```python
>>> from IPython.lib.pretty import pprint
>>> import lazy_dataset
>>> examples = {
... 'example_id_1': {
... 'observation': [1, 2, 3],
... 'label': 1,
... },
... 'example_id_2': {
... 'observation': [4, 5, 6],
... 'label': 2,
... },
... 'example_id_3': {
... 'observation': [7, 8, 9],
... 'label': 3,
... },
... }
>>> for example_id, example in examples.items():
... example['example_id'] = example_id
>>> ds = lazy_dataset.new(examples)
>>> ds
DictDataset(len=3)
MapDataset(_pickle.loads)
>>> ds.keys()
('example_id_1', 'example_id_2', 'example_id_3')
>>> for example in ds:
... print(example)
{'observation': [1, 2, 3], 'label': 1, 'example_id': 'example_id_1'}
{'observation': [4, 5, 6], 'label': 2, 'example_id': 'example_id_2'}
{'observation': [7, 8, 9], 'label': 3, 'example_id': 'example_id_3'}
>>> def transform(example):
... example['label'] *= 10
... return example
>>> ds = ds.map(transform)
>>> for example in ds:
... print(example)
{'observation': [1, 2, 3], 'label': 10, 'example_id': 'example_id_1'}
{'observation': [4, 5, 6], 'label': 20, 'example_id': 'example_id_2'}
{'observation': [7, 8, 9], 'label': 30, 'example_id': 'example_id_3'}
>>> ds = ds.filter(lambda example: example['label'] > 15)
>>> for example in ds:
... print(example)
{'observation': [4, 5, 6], 'label': 20, 'example_id': 'example_id_2'}
{'observation': [7, 8, 9], 'label': 30, 'example_id': 'example_id_3'}
>>> ds['example_id_2']
{'observation': [4, 5, 6], 'label': 20, 'example_id': 'example_id_2'}
>>> ds
DictDataset(len=3)
MapDataset(_pickle.loads)
MapDataset(<function transform at 0x7ff74efb6620>)
FilterDataset(<function <lambda> at 0x7ff74efb67b8>)
```
## Comparison with PyTorch's DataLoader
See [here](comparison/comparison.md) for a feature and throughput comparison of lazy_dataset with PyTorch's DataLoader.
## Installation
Install it directly with Pip, if you just want to use it:
```bash
pip install lazy_dataset
```
If you want to make changes or want the most recent version: Clone the repository and install it as follows:
```bash
git clone https://github.com/fgnt/lazy_dataset.git
cd lazy_dataset
pip install --editable .
```
%package -n python3-lazy-dataset
Summary: Process large datasets as if it was an iterable.
Provides: python-lazy-dataset
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-lazy-dataset
# lazy_dataset
[](https://travis-ci.org/fgnt/lazy_dataset)
[](https://codecov.io/github/fgnt/lazy_dataset?branch=master)
[](https://github.com/fgnt/lazy_dataset/blob/master/LICENSE)
Lazy_dataset is a helper to deal with large datasets that do not fit into memory.
It allows to define transformations that are applied lazily,
(e.g. a mapping function to read data from HDD). When someone iterates over the dataset all
transformations are applied.
Supported transformations:
- `dataset.map(map_fn)`: Apply the function `map_fn` to each example ([builtins.map](https://docs.python.org/3/library/functions.html#map))
- `dataset[2]`: Get example at index `2`.
- `dataset['example_id']` Get that example that has the example id `'example_id'`.
- `dataset[10:20]`: Get a sub dataset that contains only the examples in the slice 10 to 20.
- `dataset.filter(filter_fn, lazy=True)` Drops examples where `filter_fn(example)` is false ([builtins.filter](https://docs.python.org/3/library/functions.html#filter)).
- `dataset.concatenate(*others)`: Concatenates two or more datasets ([numpy.concatenate](https://docs.scipy.org/doc/numpy-1.14.0/reference/generated/numpy.concatenate.html))
- `dataset.intersperse(*others)`: Combine two or more datasets such that examples of each input dataset are evenly spaced (https://stackoverflow.com/a/19293603).
- `dataset.zip(*others)`: Zip two or more datasets
- `dataset.shuffle(reshuffle=False)`: Shuffles the dataset. When `reshuffle` is `True` it shuffles each time when you iterate over the data.
- `dataset.tile(reps, shuffle=False)`: Repeats the dataset `reps` times and concatenates it ([numpy.tile](https://docs.scipy.org/doc/numpy/reference/generated/numpy.tile.html))
- `dataset.groupby(group_fn)`: Groups examples together. In contrast to `itertools.groupby` a sort is not nessesary, like in pandas ([itertools.groupby](https://docs.python.org/3/library/itertools.html#itertools.groupby), [pandas.DataFrame.groupby](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.groupby.html))
- `dataset.sort(key_fn, sort_fn=sorted)`: Sorts the examples depending on the values `key_fn(example)` ([list.sort](https://docs.python.org/3/library/stdtypes.html#list.sort))
- `dataset.batch(batch_size, drop_last=False)`: Batches `batch_size` examples together as a list. Usually followed by a map ([tensorflow.data.Dataset.batch](https://www.tensorflow.org/api_docs/python/tf/data/Dataset#batch))
- `dataset.random_choice()`: Get a random example ([numpy.random.choice](https://docs.scipy.org/doc/numpy/reference/generated/numpy.random.choice.html))
- `dataset.cache()`: Cache in RAM (similar to ESPnet's `keep_all_data_on_mem`)
- `dataset.diskcache()`: Cache to a cache directory on the local filesystem (useful in clusters network slow filesystems)
- ...
```python
>>> from IPython.lib.pretty import pprint
>>> import lazy_dataset
>>> examples = {
... 'example_id_1': {
... 'observation': [1, 2, 3],
... 'label': 1,
... },
... 'example_id_2': {
... 'observation': [4, 5, 6],
... 'label': 2,
... },
... 'example_id_3': {
... 'observation': [7, 8, 9],
... 'label': 3,
... },
... }
>>> for example_id, example in examples.items():
... example['example_id'] = example_id
>>> ds = lazy_dataset.new(examples)
>>> ds
DictDataset(len=3)
MapDataset(_pickle.loads)
>>> ds.keys()
('example_id_1', 'example_id_2', 'example_id_3')
>>> for example in ds:
... print(example)
{'observation': [1, 2, 3], 'label': 1, 'example_id': 'example_id_1'}
{'observation': [4, 5, 6], 'label': 2, 'example_id': 'example_id_2'}
{'observation': [7, 8, 9], 'label': 3, 'example_id': 'example_id_3'}
>>> def transform(example):
... example['label'] *= 10
... return example
>>> ds = ds.map(transform)
>>> for example in ds:
... print(example)
{'observation': [1, 2, 3], 'label': 10, 'example_id': 'example_id_1'}
{'observation': [4, 5, 6], 'label': 20, 'example_id': 'example_id_2'}
{'observation': [7, 8, 9], 'label': 30, 'example_id': 'example_id_3'}
>>> ds = ds.filter(lambda example: example['label'] > 15)
>>> for example in ds:
... print(example)
{'observation': [4, 5, 6], 'label': 20, 'example_id': 'example_id_2'}
{'observation': [7, 8, 9], 'label': 30, 'example_id': 'example_id_3'}
>>> ds['example_id_2']
{'observation': [4, 5, 6], 'label': 20, 'example_id': 'example_id_2'}
>>> ds
DictDataset(len=3)
MapDataset(_pickle.loads)
MapDataset(<function transform at 0x7ff74efb6620>)
FilterDataset(<function <lambda> at 0x7ff74efb67b8>)
```
## Comparison with PyTorch's DataLoader
See [here](comparison/comparison.md) for a feature and throughput comparison of lazy_dataset with PyTorch's DataLoader.
## Installation
Install it directly with Pip, if you just want to use it:
```bash
pip install lazy_dataset
```
If you want to make changes or want the most recent version: Clone the repository and install it as follows:
```bash
git clone https://github.com/fgnt/lazy_dataset.git
cd lazy_dataset
pip install --editable .
```
%package help
Summary: Development documents and examples for lazy-dataset
Provides: python3-lazy-dataset-doc
%description help
# lazy_dataset
[](https://travis-ci.org/fgnt/lazy_dataset)
[](https://codecov.io/github/fgnt/lazy_dataset?branch=master)
[](https://github.com/fgnt/lazy_dataset/blob/master/LICENSE)
Lazy_dataset is a helper to deal with large datasets that do not fit into memory.
It allows to define transformations that are applied lazily,
(e.g. a mapping function to read data from HDD). When someone iterates over the dataset all
transformations are applied.
Supported transformations:
- `dataset.map(map_fn)`: Apply the function `map_fn` to each example ([builtins.map](https://docs.python.org/3/library/functions.html#map))
- `dataset[2]`: Get example at index `2`.
- `dataset['example_id']` Get that example that has the example id `'example_id'`.
- `dataset[10:20]`: Get a sub dataset that contains only the examples in the slice 10 to 20.
- `dataset.filter(filter_fn, lazy=True)` Drops examples where `filter_fn(example)` is false ([builtins.filter](https://docs.python.org/3/library/functions.html#filter)).
- `dataset.concatenate(*others)`: Concatenates two or more datasets ([numpy.concatenate](https://docs.scipy.org/doc/numpy-1.14.0/reference/generated/numpy.concatenate.html))
- `dataset.intersperse(*others)`: Combine two or more datasets such that examples of each input dataset are evenly spaced (https://stackoverflow.com/a/19293603).
- `dataset.zip(*others)`: Zip two or more datasets
- `dataset.shuffle(reshuffle=False)`: Shuffles the dataset. When `reshuffle` is `True` it shuffles each time when you iterate over the data.
- `dataset.tile(reps, shuffle=False)`: Repeats the dataset `reps` times and concatenates it ([numpy.tile](https://docs.scipy.org/doc/numpy/reference/generated/numpy.tile.html))
- `dataset.groupby(group_fn)`: Groups examples together. In contrast to `itertools.groupby` a sort is not nessesary, like in pandas ([itertools.groupby](https://docs.python.org/3/library/itertools.html#itertools.groupby), [pandas.DataFrame.groupby](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.groupby.html))
- `dataset.sort(key_fn, sort_fn=sorted)`: Sorts the examples depending on the values `key_fn(example)` ([list.sort](https://docs.python.org/3/library/stdtypes.html#list.sort))
- `dataset.batch(batch_size, drop_last=False)`: Batches `batch_size` examples together as a list. Usually followed by a map ([tensorflow.data.Dataset.batch](https://www.tensorflow.org/api_docs/python/tf/data/Dataset#batch))
- `dataset.random_choice()`: Get a random example ([numpy.random.choice](https://docs.scipy.org/doc/numpy/reference/generated/numpy.random.choice.html))
- `dataset.cache()`: Cache in RAM (similar to ESPnet's `keep_all_data_on_mem`)
- `dataset.diskcache()`: Cache to a cache directory on the local filesystem (useful in clusters network slow filesystems)
- ...
```python
>>> from IPython.lib.pretty import pprint
>>> import lazy_dataset
>>> examples = {
... 'example_id_1': {
... 'observation': [1, 2, 3],
... 'label': 1,
... },
... 'example_id_2': {
... 'observation': [4, 5, 6],
... 'label': 2,
... },
... 'example_id_3': {
... 'observation': [7, 8, 9],
... 'label': 3,
... },
... }
>>> for example_id, example in examples.items():
... example['example_id'] = example_id
>>> ds = lazy_dataset.new(examples)
>>> ds
DictDataset(len=3)
MapDataset(_pickle.loads)
>>> ds.keys()
('example_id_1', 'example_id_2', 'example_id_3')
>>> for example in ds:
... print(example)
{'observation': [1, 2, 3], 'label': 1, 'example_id': 'example_id_1'}
{'observation': [4, 5, 6], 'label': 2, 'example_id': 'example_id_2'}
{'observation': [7, 8, 9], 'label': 3, 'example_id': 'example_id_3'}
>>> def transform(example):
... example['label'] *= 10
... return example
>>> ds = ds.map(transform)
>>> for example in ds:
... print(example)
{'observation': [1, 2, 3], 'label': 10, 'example_id': 'example_id_1'}
{'observation': [4, 5, 6], 'label': 20, 'example_id': 'example_id_2'}
{'observation': [7, 8, 9], 'label': 30, 'example_id': 'example_id_3'}
>>> ds = ds.filter(lambda example: example['label'] > 15)
>>> for example in ds:
... print(example)
{'observation': [4, 5, 6], 'label': 20, 'example_id': 'example_id_2'}
{'observation': [7, 8, 9], 'label': 30, 'example_id': 'example_id_3'}
>>> ds['example_id_2']
{'observation': [4, 5, 6], 'label': 20, 'example_id': 'example_id_2'}
>>> ds
DictDataset(len=3)
MapDataset(_pickle.loads)
MapDataset(<function transform at 0x7ff74efb6620>)
FilterDataset(<function <lambda> at 0x7ff74efb67b8>)
```
## Comparison with PyTorch's DataLoader
See [here](comparison/comparison.md) for a feature and throughput comparison of lazy_dataset with PyTorch's DataLoader.
## Installation
Install it directly with Pip, if you just want to use it:
```bash
pip install lazy_dataset
```
If you want to make changes or want the most recent version: Clone the repository and install it as follows:
```bash
git clone https://github.com/fgnt/lazy_dataset.git
cd lazy_dataset
pip install --editable .
```
%prep
%autosetup -n lazy_dataset-0.0.14
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "\"/%h/%f.gz\"\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-lazy-dataset -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Tue Jun 20 2023 Python_Bot <Python_Bot@openeuler.org> - 0.0.14-1
- Package Spec generated
|
