summaryrefslogtreecommitdiff
path: root/python-smile-datasets.spec
blob: 991ed745bd2fae09827f73e3dfe1d67ecd216c3d (plain)
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
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
%global _empty_manifest_terminate_build 0
Name:		python-smile-datasets
Version:	0.0.6
Release:	1
Summary:	La**S**t **mile** datasets: Use `tf.data` to solve the last mile data loading problem for tensorflow.
License:	Apache Software License
URL:		https://github.com/luozhouyang/smile-datasets
Source0:	https://mirrors.aliyun.com/pypi/web/packages/72/28/bdee1d8fadf99f99daea01b0a09546932871fb995e82838c6c59e5c94ffb/smile-datasets-0.0.6.tar.gz
BuildArch:	noarch

Requires:	python3-tokenizers
Requires:	python3-tensorflow

%description
# smile-datasets

![Python package](https://github.com/luozhouyang/smile-datasets/workflows/Python%20package/badge.svg)
[![PyPI version](https://badge.fury.io/py/smile-datasets.svg)](https://badge.fury.io/py/smile-datasets)
[![Python](https://img.shields.io/pypi/pyversions/smile-datasets.svg?style=plastic)](https://badge.fury.io/py/smile-datasets)


La**S**t **mile** Datasets: Use `tf.data` to solve the last mile data loading problem for tensorflow.

If you want to load public datasets, try:

* [tensorflow/datasets](https://github.com/tensorflow/datasets)
* [huggingface/datasets](https://github.com/huggingface/datasets)

If you want to load local, personal dataset with minimized boilerplate, use **Smile Dataset**!

## Support Matrix

| task                   | supported  | core abstractions |
|:-----------------------|:-----------|:------------------|
| question answering     | [x]        | `ExampleForQuestionAnswering`, `DatasetForQuestionAnswering`, `DatapipeForQuestionAnswering`|
| masked language model  | [x]        | `ExampleForMaskedLanguageModel`, `DatasetForMaskedLanguageModel`, `DatapipeForMaskedLanguageModel`|
| sequence classification| [x]        | `ExampleForSequenceClassification`, `DatasetForSequenceClassification`, `DatapipeForSequenceClassification`|
| token classification   | [x]        | `ExampleForTokenClassification`, `DatasetForTokenClassification`, `DatapipeForTokenClassification`|
| unsupervised simcse    | [x]        | `ExampleForUnsupervisedSimCSE`, `DatasetForUnsupervisedSimCSE`, `DatapipeForUnsupervisedSimCSE`|
| supervised simcse      | [x]        | `ExampleForSupervisedSimCSE`, `DatasetForSupervisedSimCSE`, `DatapipeForSupervisedSimCSE`|
| hard negative simcse   | [x]        | `ExampleForHardNegativeSimCSE`, `DatasetForHardNegativeSimCSE`, `DatapipeForHardNegativeSimCSE`|


## Usage

All datapipes for different tasks has the same interface.

Here is an example for question answering task, but you can use datapipe the same way for other tasks.

### Example for Question Answering

```python

from smile_datasets import DatasetForQuestionAnswering, DatapipeForQuestionAnswering

# each line is a JSON {"sequece": "我喜欢自然语言处理(NLP)"}
train_input_jsonl_files = ["data/train.jsonl"]
train_dataset = DatapipeForQuestionAnswering.from_jsonl_files(
    input_files=train_input_jsonl_files, 
    vocab_file="bert/vocab.txt",
    batch_size=32,
)

# check dataset
print(next(iter(train_dataset)))

# model = build_keras_model(...)
# model.compile(...)
# train model
model.fit(train_dataset, callbacks=[...])

```


For maximum flexibility, you can always subclass `DatasetForQuestionAnswering` to load your dataset, just like `torch.utils.data.Dataset`:

```python
from smile_datasets import DatasetForQuestionAnswering, DatapipeForQuestionAnswering, ParserForQuestionAnswering

class DuReaderDatasetForQuestionAnswering(DatasetForQuestionAnswering):
    """Dataset reader for DuReader dataset."""

    def __init__(self, input_files, vocab_file, subset="rubost", **kwargs) -> None:
        super().__init__()
        self.parser = ParserForQuestionAnswering(tokenizer=None, vocab_file=vocab_file, **kwargs)
        if subset == "rubost":
            self.instances = list(readers.read_dureader_rubost(input_files, **kwargs))
        else:
            self.instances = list(readers.read_dureader_checklist(input_files, **kwargs))
        self.examples = []
        for instance in self.instances:
            e = self.parser.parse(instance)
            if not e:
                continue
            self.examples.append(e)

    def __len__(self):
        return len(self.examples)

    def __getitem__(self, index) -> ExampleForQuestionAnswering:
        return self.examples[index]


dataset = DuReaderDatasetForQuestionAnswering(input_files=["data/trian.jsonl"], vocab_file="bert/vocab.txt")
train_dataset = DatapipeForQuestionAnswering.from_dataset(dataset, batch_size=32)

# check dataset
print(next(iter(train_dataset)))

# model = build_keras_model(...)
# model.compile(...)
# train model
model.fit(train_dataset, callbacks=[...])
```

For better performance, you can convert `dataset` to `tfrecord` ahead of time, and then build datapipe from tfrecord files directly:

```python
# save dataset in tfrecord format
dataset.save_tfrecord(output_files="data/train.tfrecord")

# build datapipe from tfrecord files
train_dataset = DatapipeForQuestionAnswering.from_tfrecord_files(input_files="data/train.tfrecord", batch_size=32)

# check dataset
print(next(iter(train_dataset)))

# model = build_keras_model(...)
# model.compile(...)
# train model
model.fit(train_dataset, callbacks=[...])
```




%package -n python3-smile-datasets
Summary:	La**S**t **mile** datasets: Use `tf.data` to solve the last mile data loading problem for tensorflow.
Provides:	python-smile-datasets
BuildRequires:	python3-devel
BuildRequires:	python3-setuptools
BuildRequires:	python3-pip
%description -n python3-smile-datasets
# smile-datasets

![Python package](https://github.com/luozhouyang/smile-datasets/workflows/Python%20package/badge.svg)
[![PyPI version](https://badge.fury.io/py/smile-datasets.svg)](https://badge.fury.io/py/smile-datasets)
[![Python](https://img.shields.io/pypi/pyversions/smile-datasets.svg?style=plastic)](https://badge.fury.io/py/smile-datasets)


La**S**t **mile** Datasets: Use `tf.data` to solve the last mile data loading problem for tensorflow.

If you want to load public datasets, try:

* [tensorflow/datasets](https://github.com/tensorflow/datasets)
* [huggingface/datasets](https://github.com/huggingface/datasets)

If you want to load local, personal dataset with minimized boilerplate, use **Smile Dataset**!

## Support Matrix

| task                   | supported  | core abstractions |
|:-----------------------|:-----------|:------------------|
| question answering     | [x]        | `ExampleForQuestionAnswering`, `DatasetForQuestionAnswering`, `DatapipeForQuestionAnswering`|
| masked language model  | [x]        | `ExampleForMaskedLanguageModel`, `DatasetForMaskedLanguageModel`, `DatapipeForMaskedLanguageModel`|
| sequence classification| [x]        | `ExampleForSequenceClassification`, `DatasetForSequenceClassification`, `DatapipeForSequenceClassification`|
| token classification   | [x]        | `ExampleForTokenClassification`, `DatasetForTokenClassification`, `DatapipeForTokenClassification`|
| unsupervised simcse    | [x]        | `ExampleForUnsupervisedSimCSE`, `DatasetForUnsupervisedSimCSE`, `DatapipeForUnsupervisedSimCSE`|
| supervised simcse      | [x]        | `ExampleForSupervisedSimCSE`, `DatasetForSupervisedSimCSE`, `DatapipeForSupervisedSimCSE`|
| hard negative simcse   | [x]        | `ExampleForHardNegativeSimCSE`, `DatasetForHardNegativeSimCSE`, `DatapipeForHardNegativeSimCSE`|


## Usage

All datapipes for different tasks has the same interface.

Here is an example for question answering task, but you can use datapipe the same way for other tasks.

### Example for Question Answering

```python

from smile_datasets import DatasetForQuestionAnswering, DatapipeForQuestionAnswering

# each line is a JSON {"sequece": "我喜欢自然语言处理(NLP)"}
train_input_jsonl_files = ["data/train.jsonl"]
train_dataset = DatapipeForQuestionAnswering.from_jsonl_files(
    input_files=train_input_jsonl_files, 
    vocab_file="bert/vocab.txt",
    batch_size=32,
)

# check dataset
print(next(iter(train_dataset)))

# model = build_keras_model(...)
# model.compile(...)
# train model
model.fit(train_dataset, callbacks=[...])

```


For maximum flexibility, you can always subclass `DatasetForQuestionAnswering` to load your dataset, just like `torch.utils.data.Dataset`:

```python
from smile_datasets import DatasetForQuestionAnswering, DatapipeForQuestionAnswering, ParserForQuestionAnswering

class DuReaderDatasetForQuestionAnswering(DatasetForQuestionAnswering):
    """Dataset reader for DuReader dataset."""

    def __init__(self, input_files, vocab_file, subset="rubost", **kwargs) -> None:
        super().__init__()
        self.parser = ParserForQuestionAnswering(tokenizer=None, vocab_file=vocab_file, **kwargs)
        if subset == "rubost":
            self.instances = list(readers.read_dureader_rubost(input_files, **kwargs))
        else:
            self.instances = list(readers.read_dureader_checklist(input_files, **kwargs))
        self.examples = []
        for instance in self.instances:
            e = self.parser.parse(instance)
            if not e:
                continue
            self.examples.append(e)

    def __len__(self):
        return len(self.examples)

    def __getitem__(self, index) -> ExampleForQuestionAnswering:
        return self.examples[index]


dataset = DuReaderDatasetForQuestionAnswering(input_files=["data/trian.jsonl"], vocab_file="bert/vocab.txt")
train_dataset = DatapipeForQuestionAnswering.from_dataset(dataset, batch_size=32)

# check dataset
print(next(iter(train_dataset)))

# model = build_keras_model(...)
# model.compile(...)
# train model
model.fit(train_dataset, callbacks=[...])
```

For better performance, you can convert `dataset` to `tfrecord` ahead of time, and then build datapipe from tfrecord files directly:

```python
# save dataset in tfrecord format
dataset.save_tfrecord(output_files="data/train.tfrecord")

# build datapipe from tfrecord files
train_dataset = DatapipeForQuestionAnswering.from_tfrecord_files(input_files="data/train.tfrecord", batch_size=32)

# check dataset
print(next(iter(train_dataset)))

# model = build_keras_model(...)
# model.compile(...)
# train model
model.fit(train_dataset, callbacks=[...])
```




%package help
Summary:	Development documents and examples for smile-datasets
Provides:	python3-smile-datasets-doc
%description help
# smile-datasets

![Python package](https://github.com/luozhouyang/smile-datasets/workflows/Python%20package/badge.svg)
[![PyPI version](https://badge.fury.io/py/smile-datasets.svg)](https://badge.fury.io/py/smile-datasets)
[![Python](https://img.shields.io/pypi/pyversions/smile-datasets.svg?style=plastic)](https://badge.fury.io/py/smile-datasets)


La**S**t **mile** Datasets: Use `tf.data` to solve the last mile data loading problem for tensorflow.

If you want to load public datasets, try:

* [tensorflow/datasets](https://github.com/tensorflow/datasets)
* [huggingface/datasets](https://github.com/huggingface/datasets)

If you want to load local, personal dataset with minimized boilerplate, use **Smile Dataset**!

## Support Matrix

| task                   | supported  | core abstractions |
|:-----------------------|:-----------|:------------------|
| question answering     | [x]        | `ExampleForQuestionAnswering`, `DatasetForQuestionAnswering`, `DatapipeForQuestionAnswering`|
| masked language model  | [x]        | `ExampleForMaskedLanguageModel`, `DatasetForMaskedLanguageModel`, `DatapipeForMaskedLanguageModel`|
| sequence classification| [x]        | `ExampleForSequenceClassification`, `DatasetForSequenceClassification`, `DatapipeForSequenceClassification`|
| token classification   | [x]        | `ExampleForTokenClassification`, `DatasetForTokenClassification`, `DatapipeForTokenClassification`|
| unsupervised simcse    | [x]        | `ExampleForUnsupervisedSimCSE`, `DatasetForUnsupervisedSimCSE`, `DatapipeForUnsupervisedSimCSE`|
| supervised simcse      | [x]        | `ExampleForSupervisedSimCSE`, `DatasetForSupervisedSimCSE`, `DatapipeForSupervisedSimCSE`|
| hard negative simcse   | [x]        | `ExampleForHardNegativeSimCSE`, `DatasetForHardNegativeSimCSE`, `DatapipeForHardNegativeSimCSE`|


## Usage

All datapipes for different tasks has the same interface.

Here is an example for question answering task, but you can use datapipe the same way for other tasks.

### Example for Question Answering

```python

from smile_datasets import DatasetForQuestionAnswering, DatapipeForQuestionAnswering

# each line is a JSON {"sequece": "我喜欢自然语言处理(NLP)"}
train_input_jsonl_files = ["data/train.jsonl"]
train_dataset = DatapipeForQuestionAnswering.from_jsonl_files(
    input_files=train_input_jsonl_files, 
    vocab_file="bert/vocab.txt",
    batch_size=32,
)

# check dataset
print(next(iter(train_dataset)))

# model = build_keras_model(...)
# model.compile(...)
# train model
model.fit(train_dataset, callbacks=[...])

```


For maximum flexibility, you can always subclass `DatasetForQuestionAnswering` to load your dataset, just like `torch.utils.data.Dataset`:

```python
from smile_datasets import DatasetForQuestionAnswering, DatapipeForQuestionAnswering, ParserForQuestionAnswering

class DuReaderDatasetForQuestionAnswering(DatasetForQuestionAnswering):
    """Dataset reader for DuReader dataset."""

    def __init__(self, input_files, vocab_file, subset="rubost", **kwargs) -> None:
        super().__init__()
        self.parser = ParserForQuestionAnswering(tokenizer=None, vocab_file=vocab_file, **kwargs)
        if subset == "rubost":
            self.instances = list(readers.read_dureader_rubost(input_files, **kwargs))
        else:
            self.instances = list(readers.read_dureader_checklist(input_files, **kwargs))
        self.examples = []
        for instance in self.instances:
            e = self.parser.parse(instance)
            if not e:
                continue
            self.examples.append(e)

    def __len__(self):
        return len(self.examples)

    def __getitem__(self, index) -> ExampleForQuestionAnswering:
        return self.examples[index]


dataset = DuReaderDatasetForQuestionAnswering(input_files=["data/trian.jsonl"], vocab_file="bert/vocab.txt")
train_dataset = DatapipeForQuestionAnswering.from_dataset(dataset, batch_size=32)

# check dataset
print(next(iter(train_dataset)))

# model = build_keras_model(...)
# model.compile(...)
# train model
model.fit(train_dataset, callbacks=[...])
```

For better performance, you can convert `dataset` to `tfrecord` ahead of time, and then build datapipe from tfrecord files directly:

```python
# save dataset in tfrecord format
dataset.save_tfrecord(output_files="data/train.tfrecord")

# build datapipe from tfrecord files
train_dataset = DatapipeForQuestionAnswering.from_tfrecord_files(input_files="data/train.tfrecord", batch_size=32)

# check dataset
print(next(iter(train_dataset)))

# model = build_keras_model(...)
# model.compile(...)
# train model
model.fit(train_dataset, callbacks=[...])
```




%prep
%autosetup -n smile-datasets-0.0.6

%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-smile-datasets -f filelist.lst
%dir %{python3_sitelib}/*

%files help -f doclist.lst
%{_docdir}/*

%changelog
* Tue Jun 20 2023 Python_Bot <Python_Bot@openeuler.org> - 0.0.6-1
- Package Spec generated