/
dataset.py
614 lines (542 loc) · 26.9 KB
/
dataset.py
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
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
# -*- coding: utf-8 -*-
# Copyright 2020 Google LLC
#
# 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 Dict, List, Optional, Sequence, Tuple, Union
from google.api_core import operation
from google.auth import credentials as auth_credentials
from google.cloud.aiplatform import base
from google.cloud.aiplatform import initializer
from google.cloud.aiplatform import utils
from google.cloud.aiplatform.compat.services import dataset_service_client
from google.cloud.aiplatform.compat.types import (
dataset as gca_dataset,
encryption_spec as gca_encryption_spec,
io as gca_io,
)
from google.cloud.aiplatform.datasets import _datasources
_LOGGER = base.Logger(__name__)
class _Dataset(base.VertexAiResourceNounWithFutureManager):
"""Managed dataset resource for Vertex AI."""
client_class = utils.DatasetClientWithOverride
_is_client_prediction_client = False
_resource_noun = "datasets"
_getter_method = "get_dataset"
_list_method = "list_datasets"
_delete_method = "delete_dataset"
_supported_metadata_schema_uris: Tuple[str] = ()
def __init__(
self,
dataset_name: str,
project: Optional[str] = None,
location: Optional[str] = None,
credentials: Optional[auth_credentials.Credentials] = None,
):
"""Retrieves an existing managed dataset given a dataset name or ID.
Args:
dataset_name (str):
Required. A fully-qualified dataset resource name or dataset ID.
Example: "projects/123/locations/us-central1/datasets/456" or
"456" when project and location are initialized or passed.
project (str):
Optional project to retrieve dataset from. If not set, project
set in aiplatform.init will be used.
location (str):
Optional location to retrieve dataset from. If not set, location
set in aiplatform.init will be used.
credentials (auth_credentials.Credentials):
Custom credentials to use to retrieve this Dataset. Overrides
credentials set in aiplatform.init.
"""
super().__init__(
project=project,
location=location,
credentials=credentials,
resource_name=dataset_name,
)
self._gca_resource = self._get_gca_resource(resource_name=dataset_name)
self._validate_metadata_schema_uri()
@property
def metadata_schema_uri(self) -> str:
"""The metadata schema uri of this dataset resource."""
self._assert_gca_resource_is_available()
return self._gca_resource.metadata_schema_uri
def _validate_metadata_schema_uri(self) -> None:
"""Validate the metadata_schema_uri of retrieved dataset resource.
Raises:
ValueError if the dataset type of the retrieved dataset resource is
not supported by the class.
"""
if self._supported_metadata_schema_uris and (
self.metadata_schema_uri not in self._supported_metadata_schema_uris
):
raise ValueError(
f"{self.__class__.__name__} class can not be used to retrieve "
f"dataset resource {self.resource_name}, check the dataset type"
)
@classmethod
def create(
cls,
display_name: str,
metadata_schema_uri: str,
gcs_source: Optional[Union[str, Sequence[str]]] = None,
bq_source: Optional[str] = None,
import_schema_uri: Optional[str] = None,
data_item_labels: Optional[Dict] = None,
project: Optional[str] = None,
location: Optional[str] = None,
credentials: Optional[auth_credentials.Credentials] = None,
request_metadata: Optional[Sequence[Tuple[str, str]]] = (),
labels: Optional[Dict[str, str]] = None,
encryption_spec_key_name: Optional[str] = None,
sync: bool = True,
) -> "_Dataset":
"""Creates a new dataset and optionally imports data into dataset when
source and import_schema_uri are passed.
Args:
display_name (str):
Required. The user-defined name of the Dataset.
The name can be up to 128 characters long and can be consist
of any UTF-8 characters.
metadata_schema_uri (str):
Required. Points to a YAML file stored on Google Cloud Storage
describing additional information about the Dataset. The schema
is defined as an OpenAPI 3.0.2 Schema Object. The schema files
that can be used here are found in gs://google-cloud-
aiplatform/schema/dataset/metadata/.
gcs_source (Union[str, Sequence[str]]):
Google Cloud Storage URI(-s) to the
input file(s). May contain wildcards. For more
information on wildcards, see
https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
examples:
str: "gs://bucket/file.csv"
Sequence[str]: ["gs://bucket/file1.csv", "gs://bucket/file2.csv"]
bq_source (str):
BigQuery URI to the input table.
example:
"bq://project.dataset.table_name"
import_schema_uri (str):
Points to a YAML file stored on Google Cloud
Storage describing the import format. Validation will be
done against the schema. The schema is defined as an
`OpenAPI 3.0.2 Schema
Object <https://tinyurl.com/y538mdwt>`__.
data_item_labels (Dict):
Labels that will be applied to newly imported DataItems. If
an identical DataItem as one being imported already exists
in the Dataset, then these labels will be appended to these
of the already existing one, and if labels with identical
key is imported before, the old label value will be
overwritten. If two DataItems are identical in the same
import data operation, the labels will be combined and if
key collision happens in this case, one of the values will
be picked randomly. Two DataItems are considered identical
if their content bytes are identical (e.g. image bytes or
pdf bytes). These labels will be overridden by Annotation
labels specified inside index file refenced by
``import_schema_uri``,
e.g. jsonl file.
project (str):
Project to upload this model to. Overrides project set in
aiplatform.init.
location (str):
Location to upload this model to. Overrides location set in
aiplatform.init.
credentials (auth_credentials.Credentials):
Custom credentials to use to upload this model. Overrides
credentials set in aiplatform.init.
request_metadata (Sequence[Tuple[str, str]]):
Strings which should be sent along with the request as metadata.
labels (Dict[str, str]):
Optional. Labels with user-defined metadata to organize your Tensorboards.
Label keys and values can be no longer than 64 characters
(Unicode codepoints), can only contain lowercase letters, numeric
characters, underscores and dashes. International characters are allowed.
No more than 64 user labels can be associated with one Tensorboard
(System labels are excluded).
See https://goo.gl/xmQnxf for more information and examples of labels.
System reserved label keys are prefixed with "aiplatform.googleapis.com/"
and are immutable.
encryption_spec_key_name (Optional[str]):
Optional. The Cloud KMS resource identifier of the customer
managed encryption key used to protect the dataset. Has the
form:
``projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key``.
The key needs to be in the same region as where the compute
resource is created.
If set, this Dataset and all sub-resources of this Dataset will be secured by this key.
Overrides encryption_spec_key_name set in aiplatform.init.
sync (bool):
Whether to execute this method synchronously. If False, this method
will be executed in concurrent Future and any downstream object will
be immediately returned and synced when the Future has completed.
Returns:
dataset (Dataset):
Instantiated representation of the managed dataset resource.
"""
utils.validate_display_name(display_name)
if labels:
utils.validate_labels(labels)
api_client = cls._instantiate_client(location=location, credentials=credentials)
datasource = _datasources.create_datasource(
metadata_schema_uri=metadata_schema_uri,
import_schema_uri=import_schema_uri,
gcs_source=gcs_source,
bq_source=bq_source,
data_item_labels=data_item_labels,
)
return cls._create_and_import(
api_client=api_client,
parent=initializer.global_config.common_location_path(
project=project, location=location
),
display_name=display_name,
metadata_schema_uri=metadata_schema_uri,
datasource=datasource,
project=project or initializer.global_config.project,
location=location or initializer.global_config.location,
credentials=credentials or initializer.global_config.credentials,
request_metadata=request_metadata,
labels=labels,
encryption_spec=initializer.global_config.get_encryption_spec(
encryption_spec_key_name=encryption_spec_key_name
),
sync=sync,
)
@classmethod
@base.optional_sync()
def _create_and_import(
cls,
api_client: dataset_service_client.DatasetServiceClient,
parent: str,
display_name: str,
metadata_schema_uri: str,
datasource: _datasources.Datasource,
project: str,
location: str,
credentials: Optional[auth_credentials.Credentials],
request_metadata: Optional[Sequence[Tuple[str, str]]] = (),
labels: Optional[Dict[str, str]] = None,
encryption_spec: Optional[gca_encryption_spec.EncryptionSpec] = None,
sync: bool = True,
) -> "_Dataset":
"""Creates a new dataset and optionally imports data into dataset when
source and import_schema_uri are passed.
Args:
api_client (dataset_service_client.DatasetServiceClient):
An instance of DatasetServiceClient with the correct api_endpoint
already set based on user's preferences.
parent (str):
Required. Also known as common location path, that usually contains the
project and location that the user provided to the upstream method.
Example: "projects/my-prj/locations/us-central1"
display_name (str):
Required. The user-defined name of the Dataset.
The name can be up to 128 characters long and can be consist
of any UTF-8 characters.
metadata_schema_uri (str):
Required. Points to a YAML file stored on Google Cloud Storage
describing additional information about the Dataset. The schema
is defined as an OpenAPI 3.0.2 Schema Object. The schema files
that can be used here are found in gs://google-cloud-
aiplatform/schema/dataset/metadata/.
datasource (_datasources.Datasource):
Required. Datasource for creating a dataset for Vertex AI.
project (str):
Required. Project to upload this model to. Overrides project set in
aiplatform.init.
location (str):
Required. Location to upload this model to. Overrides location set in
aiplatform.init.
credentials (Optional[auth_credentials.Credentials]):
Custom credentials to use to upload this model. Overrides
credentials set in aiplatform.init.
request_metadata (Sequence[Tuple[str, str]]):
Strings which should be sent along with the request as metadata.
labels (Dict[str, str]):
Optional. Labels with user-defined metadata to organize your Tensorboards.
Label keys and values can be no longer than 64 characters
(Unicode codepoints), can only contain lowercase letters, numeric
characters, underscores and dashes. International characters are allowed.
No more than 64 user labels can be associated with one Tensorboard
(System labels are excluded).
See https://goo.gl/xmQnxf for more information and examples of labels.
System reserved label keys are prefixed with "aiplatform.googleapis.com/"
and are immutable.
encryption_spec (Optional[gca_encryption_spec.EncryptionSpec]):
Optional. The Cloud KMS customer managed encryption key used to protect the dataset.
The key needs to be in the same region as where the compute
resource is created.
If set, this Dataset and all sub-resources of this Dataset will be secured by this key.
sync (bool):
Whether to execute this method synchronously. If False, this method
will be executed in concurrent Future and any downstream object will
be immediately returned and synced when the Future has completed.
Returns:
dataset (Dataset):
Instantiated representation of the managed dataset resource.
"""
create_dataset_lro = cls._create(
api_client=api_client,
parent=parent,
display_name=display_name,
metadata_schema_uri=metadata_schema_uri,
datasource=datasource,
request_metadata=request_metadata,
labels=labels,
encryption_spec=encryption_spec,
)
_LOGGER.log_create_with_lro(cls, create_dataset_lro)
created_dataset = create_dataset_lro.result()
_LOGGER.log_create_complete(cls, created_dataset, "ds")
dataset_obj = cls(
dataset_name=created_dataset.name,
project=project,
location=location,
credentials=credentials,
)
# Import if import datasource is DatasourceImportable
if isinstance(datasource, _datasources.DatasourceImportable):
dataset_obj._import_and_wait(datasource)
return dataset_obj
def _import_and_wait(self, datasource):
_LOGGER.log_action_start_against_resource(
"Importing", "data", self,
)
import_lro = self._import(datasource=datasource)
_LOGGER.log_action_started_against_resource_with_lro(
"Import", "data", self.__class__, import_lro
)
import_lro.result()
_LOGGER.log_action_completed_against_resource("data", "imported", self)
@classmethod
def _create(
cls,
api_client: dataset_service_client.DatasetServiceClient,
parent: str,
display_name: str,
metadata_schema_uri: str,
datasource: _datasources.Datasource,
request_metadata: Sequence[Tuple[str, str]] = (),
labels: Optional[Dict[str, str]] = None,
encryption_spec: Optional[gca_encryption_spec.EncryptionSpec] = None,
) -> operation.Operation:
"""Creates a new managed dataset by directly calling API client.
Args:
api_client (dataset_service_client.DatasetServiceClient):
An instance of DatasetServiceClient with the correct api_endpoint
already set based on user's preferences.
parent (str):
Required. Also known as common location path, that usually contains the
project and location that the user provided to the upstream method.
Example: "projects/my-prj/locations/us-central1"
display_name (str):
Required. The user-defined name of the Dataset.
The name can be up to 128 characters long and can be consist
of any UTF-8 characters.
metadata_schema_uri (str):
Required. Points to a YAML file stored on Google Cloud Storage
describing additional information about the Dataset. The schema
is defined as an OpenAPI 3.0.2 Schema Object. The schema files
that can be used here are found in gs://google-cloud-
aiplatform/schema/dataset/metadata/.
datasource (_datasources.Datasource):
Required. Datasource for creating a dataset for Vertex AI.
request_metadata (Sequence[Tuple[str, str]]):
Strings which should be sent along with the create_dataset
request as metadata. Usually to specify special dataset config.
labels (Dict[str, str]):
Optional. Labels with user-defined metadata to organize your Tensorboards.
Label keys and values can be no longer than 64 characters
(Unicode codepoints), can only contain lowercase letters, numeric
characters, underscores and dashes. International characters are allowed.
No more than 64 user labels can be associated with one Tensorboard
(System labels are excluded).
See https://goo.gl/xmQnxf for more information and examples of labels.
System reserved label keys are prefixed with "aiplatform.googleapis.com/"
and are immutable.
encryption_spec (Optional[gca_encryption_spec.EncryptionSpec]):
Optional. The Cloud KMS customer managed encryption key used to protect the dataset.
The key needs to be in the same region as where the compute
resource is created.
If set, this Dataset and all sub-resources of this Dataset will be secured by this key.
Returns:
operation (Operation):
An object representing a long-running operation.
"""
gapic_dataset = gca_dataset.Dataset(
display_name=display_name,
metadata_schema_uri=metadata_schema_uri,
metadata=datasource.dataset_metadata,
labels=labels,
encryption_spec=encryption_spec,
)
return api_client.create_dataset(
parent=parent, dataset=gapic_dataset, metadata=request_metadata
)
def _import(
self, datasource: _datasources.DatasourceImportable,
) -> operation.Operation:
"""Imports data into managed dataset by directly calling API client.
Args:
datasource (_datasources.DatasourceImportable):
Required. Datasource for importing data to an existing dataset for Vertex AI.
Returns:
operation (Operation):
An object representing a long-running operation.
"""
return self.api_client.import_data(
name=self.resource_name, import_configs=[datasource.import_data_config]
)
@base.optional_sync(return_input_arg="self")
def import_data(
self,
gcs_source: Union[str, Sequence[str]],
import_schema_uri: str,
data_item_labels: Optional[Dict] = None,
sync: bool = True,
) -> "_Dataset":
"""Upload data to existing managed dataset.
Args:
gcs_source (Union[str, Sequence[str]]):
Required. Google Cloud Storage URI(-s) to the
input file(s). May contain wildcards. For more
information on wildcards, see
https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
examples:
str: "gs://bucket/file.csv"
Sequence[str]: ["gs://bucket/file1.csv", "gs://bucket/file2.csv"]
import_schema_uri (str):
Required. Points to a YAML file stored on Google Cloud
Storage describing the import format. Validation will be
done against the schema. The schema is defined as an
`OpenAPI 3.0.2 Schema
Object <https://tinyurl.com/y538mdwt>`__.
data_item_labels (Dict):
Labels that will be applied to newly imported DataItems. If
an identical DataItem as one being imported already exists
in the Dataset, then these labels will be appended to these
of the already existing one, and if labels with identical
key is imported before, the old label value will be
overwritten. If two DataItems are identical in the same
import data operation, the labels will be combined and if
key collision happens in this case, one of the values will
be picked randomly. Two DataItems are considered identical
if their content bytes are identical (e.g. image bytes or
pdf bytes). These labels will be overridden by Annotation
labels specified inside index file refenced by
``import_schema_uri``,
e.g. jsonl file.
sync (bool):
Whether to execute this method synchronously. If False, this method
will be executed in concurrent Future and any downstream object will
be immediately returned and synced when the Future has completed.
Returns:
dataset (Dataset):
Instantiated representation of the managed dataset resource.
"""
datasource = _datasources.create_datasource(
metadata_schema_uri=self.metadata_schema_uri,
import_schema_uri=import_schema_uri,
gcs_source=gcs_source,
data_item_labels=data_item_labels,
)
self._import_and_wait(datasource=datasource)
return self
# TODO(b/174751568) add optional sync support
def export_data(self, output_dir: str) -> Sequence[str]:
"""Exports data to output dir to GCS.
Args:
output_dir (str):
Required. The Google Cloud Storage location where the output is to
be written to. In the given directory a new directory will be
created with name:
``export-data-<dataset-display-name>-<timestamp-of-export-call>``
where timestamp is in YYYYMMDDHHMMSS format. All export
output will be written into that directory. Inside that
directory, annotations with the same schema will be grouped
into sub directories which are named with the corresponding
annotations' schema title. Inside these sub directories, a
schema.yaml will be created to describe the output format.
If the uri doesn't end with '/', a '/' will be automatically
appended. The directory is created if it doesn't exist.
Returns:
exported_files (Sequence[str]):
All of the files that are exported in this export operation.
"""
self.wait()
# TODO(b/171311614): Add support for BiqQuery export path
export_data_config = gca_dataset.ExportDataConfig(
gcs_destination=gca_io.GcsDestination(output_uri_prefix=output_dir)
)
_LOGGER.log_action_start_against_resource("Exporting", "data", self)
export_lro = self.api_client.export_data(
name=self.resource_name, export_config=export_data_config
)
_LOGGER.log_action_started_against_resource_with_lro(
"Export", "data", self.__class__, export_lro
)
export_data_response = export_lro.result()
_LOGGER.log_action_completed_against_resource("data", "export", self)
return export_data_response.exported_files
def update(self):
raise NotImplementedError("Update dataset has not been implemented yet")
@classmethod
def list(
cls,
filter: Optional[str] = None,
order_by: Optional[str] = None,
project: Optional[str] = None,
location: Optional[str] = None,
credentials: Optional[auth_credentials.Credentials] = None,
) -> List[base.VertexAiResourceNoun]:
"""List all instances of this Dataset resource.
Example Usage:
aiplatform.TabularDataset.list(
filter='labels.my_key="my_value"',
order_by='display_name'
)
Args:
filter (str):
Optional. An expression for filtering the results of the request.
For field names both snake_case and camelCase are supported.
order_by (str):
Optional. A comma-separated list of fields to order by, sorted in
ascending order. Use "desc" after a field name for descending.
Supported fields: `display_name`, `create_time`, `update_time`
project (str):
Optional. Project to retrieve list from. If not set, project
set in aiplatform.init will be used.
location (str):
Optional. Location to retrieve list from. If not set, location
set in aiplatform.init will be used.
credentials (auth_credentials.Credentials):
Optional. Custom credentials to use to retrieve list. Overrides
credentials set in aiplatform.init.
Returns:
List[base.VertexAiResourceNoun] - A list of Dataset resource objects
"""
dataset_subclass_filter = (
lambda gapic_obj: gapic_obj.metadata_schema_uri
in cls._supported_metadata_schema_uris
)
return cls._list_with_local_order(
cls_filter=dataset_subclass_filter,
filter=filter,
order_by=order_by,
project=project,
location=location,
credentials=credentials,
)