/
types.d.ts
3334 lines (3218 loc) · 128 KB
/
types.d.ts
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
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/**
* BigQuery API
*/
declare namespace bigquery {
/**
* Aggregate metrics for classification/classifier models. For multi-class
* models, the metrics are either macro-averaged or micro-averaged. When
* macro-averaged, the metrics are calculated for each label and then an
* unweighted average is taken of those values. When micro-averaged, the
* metric is calculated globally by counting the total number of correctly
* predicted rows.
*/
type IAggregateClassificationMetrics = {
/**
* Accuracy is the fraction of predictions given the correct label. For
* multiclass this is a micro-averaged metric.
*/
accuracy?: number;
/**
* The F1 score is an average of recall and precision. For multiclass
* this is a macro-averaged metric.
*/
f1Score?: number;
/**
* Logarithmic Loss. For multiclass this is a macro-averaged metric.
*/
logLoss?: number;
/**
* Precision is the fraction of actual positive predictions that had
* positive actual labels. For multiclass this is a macro-averaged
* metric treating each class as a binary classifier.
*/
precision?: number;
/**
* Recall is the fraction of actual positive labels that were given a
* positive prediction. For multiclass this is a macro-averaged metric.
*/
recall?: number;
/**
* Area Under a ROC Curve. For multiclass this is a macro-averaged
* metric.
*/
rocAuc?: number;
/**
* Threshold at which the metrics are computed. For binary
* classification models this is the positive class threshold.
* For multi-class classfication models this is the confidence
* threshold.
*/
threshold?: number;
};
/**
* Input/output argument of a function or a stored procedure.
*/
type IArgument = {
/**
* Optional. Defaults to FIXED_TYPE.
*/
argumentKind?: 'ARGUMENT_KIND_UNSPECIFIED' | 'FIXED_TYPE' | 'ANY_TYPE';
/**
* Required unless argument_kind = ANY_TYPE.
*/
dataType?: IStandardSqlDataType;
/**
* Optional. Specifies whether the argument is input or output.
* Can be set for procedures only.
*/
mode?: 'MODE_UNSPECIFIED' | 'IN' | 'OUT' | 'INOUT';
/**
* Optional. The name of this argument. Can be absent for function return argument.
*/
name?: string;
};
/**
* Arima coefficients.
*/
type IArimaCoefficients = {
/**
* Auto-regressive coefficients, an array of double.
*/
autoRegressiveCoefficients?: Array<number>;
/**
* Intercept coefficient, just a double not an array.
*/
interceptCoefficient?: number;
/**
* Moving-average coefficients, an array of double.
*/
movingAverageCoefficients?: Array<number>;
};
/**
* ARIMA model fitting metrics.
*/
type IArimaFittingMetrics = {
/**
* AIC
*/
aic?: number;
/**
* log-likelihood
*/
logLikelihood?: number;
/**
* variance.
*/
variance?: number;
};
/**
* Arima model information.
*/
type IArimaModelInfo = {
/**
* Arima coefficients.
*/
arimaCoefficients?: IArimaCoefficients;
/**
* Arima fitting metrics.
*/
arimaFittingMetrics?: IArimaFittingMetrics;
/**
* Non-seasonal order.
*/
nonSeasonalOrder?: IArimaOrder;
};
/**
* Arima order, can be used for both non-seasonal and seasonal parts.
*/
type IArimaOrder = {
/**
* Order of the differencing part.
*/
d?: string;
/**
* Order of the autoregressive part.
*/
p?: string;
/**
* Order of the moving-average part.
*/
q?: string;
};
/**
* (Auto-)arima fitting result. Wrap everything in ArimaResult for easier
* refactoring if we want to use model-specific iteration results.
*/
type IArimaResult = {
/**
* This message is repeated because there are multiple arima models
* fitted in auto-arima. For non-auto-arima model, its size is one.
*/
arimaModelInfo?: Array<IArimaModelInfo>;
/**
* Seasonal periods. Repeated because multiple periods are supported for
* one time series.
*/
seasonalPeriods?: Array<
| 'SEASONAL_PERIOD_TYPE_UNSPECIFIED'
| 'NO_SEASONALITY'
| 'DAILY'
| 'WEEKLY'
| 'MONTHLY'
| 'QUARTERLY'
| 'YEARLY'
>;
};
type IBigQueryModelTraining = {
/**
* [Output-only, Beta] Index of current ML training iteration. Updated during create model query job to show job progress.
*/
currentIteration?: number;
/**
* [Output-only, Beta] Expected number of iterations for the create model query job specified as num_iterations in the input query. The actual total number of iterations may be less than this number due to early stop.
*/
expectedTotalIterations?: string;
};
type IBigtableColumn = {
/**
* [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. 'encoding' can also be set at the column family level. However, the setting at this level takes precedence if 'encoding' is set at both levels.
*/
encoding?: string;
/**
* [Optional] If the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as the column field name and is used as field name in queries.
*/
fieldName?: string;
/**
* [Optional] If this is set, only the latest version of value in this column are exposed. 'onlyReadLatest' can also be set at the column family level. However, the setting at this level takes precedence if 'onlyReadLatest' is set at both levels.
*/
onlyReadLatest?: boolean;
/**
* [Required] Qualifier of the column. Columns in the parent column family that has this exact qualifier are exposed as . field. If the qualifier is valid UTF-8 string, it can be specified in the qualifier_string field. Otherwise, a base-64 encoded value must be set to qualifier_encoded. The column field name is the same as the column qualifier. However, if the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as field_name.
*/
qualifierEncoded?: string;
qualifierString?: string;
/**
* [Optional] The type to convert the value in cells of this column. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Default type is BYTES. 'type' can also be set at the column family level. However, the setting at this level takes precedence if 'type' is set at both levels.
*/
type?: string;
};
type IBigtableColumnFamily = {
/**
* [Optional] Lists of columns that should be exposed as individual fields as opposed to a list of (column name, value) pairs. All columns whose qualifier matches a qualifier in this list can be accessed as .. Other columns can be accessed as a list through .Column field.
*/
columns?: Array<IBigtableColumn>;
/**
* [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. This can be overridden for a specific column by listing that column in 'columns' and specifying an encoding for it.
*/
encoding?: string;
/**
* Identifier of the column family.
*/
familyId?: string;
/**
* [Optional] If this is set only the latest version of value are exposed for all columns in this column family. This can be overridden for a specific column by listing that column in 'columns' and specifying a different setting for that column.
*/
onlyReadLatest?: boolean;
/**
* [Optional] The type to convert the value in cells of this column family. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Default type is BYTES. This can be overridden for a specific column by listing that column in 'columns' and specifying a type for it.
*/
type?: string;
};
type IBigtableOptions = {
/**
* [Optional] List of column families to expose in the table schema along with their types. This list restricts the column families that can be referenced in queries and specifies their value types. You can use this list to do type conversions - see the 'type' field for more details. If you leave this list empty, all column families are present in the table schema and their values are read as BYTES. During a query only the column families referenced in that query are read from Bigtable.
*/
columnFamilies?: Array<IBigtableColumnFamily>;
/**
* [Optional] If field is true, then the column families that are not specified in columnFamilies list are not exposed in the table schema. Otherwise, they are read with BYTES type values. The default value is false.
*/
ignoreUnspecifiedColumnFamilies?: boolean;
/**
* [Optional] If field is true, then the rowkey column families will be read and converted to string. Otherwise they are read with BYTES type values and users need to manually cast them with CAST if necessary. The default value is false.
*/
readRowkeyAsString?: boolean;
};
/**
* Evaluation metrics for binary classification/classifier models.
*/
type IBinaryClassificationMetrics = {
/**
* Aggregate classification metrics.
*/
aggregateClassificationMetrics?: IAggregateClassificationMetrics;
/**
* Binary confusion matrix at multiple thresholds.
*/
binaryConfusionMatrixList?: Array<IBinaryConfusionMatrix>;
/**
* Label representing the negative class.
*/
negativeLabel?: string;
/**
* Label representing the positive class.
*/
positiveLabel?: string;
};
/**
* Confusion matrix for binary classification models.
*/
type IBinaryConfusionMatrix = {
/**
* The fraction of predictions given the correct label.
*/
accuracy?: number;
/**
* The equally weighted average of recall and precision.
*/
f1Score?: number;
/**
* Number of false samples predicted as false.
*/
falseNegatives?: string;
/**
* Number of false samples predicted as true.
*/
falsePositives?: string;
/**
* Threshold value used when computing each of the following metric.
*/
positiveClassThreshold?: number;
/**
* The fraction of actual positive predictions that had positive actual
* labels.
*/
precision?: number;
/**
* The fraction of actual positive labels that were given a positive
* prediction.
*/
recall?: number;
/**
* Number of true samples predicted as false.
*/
trueNegatives?: string;
/**
* Number of true samples predicted as true.
*/
truePositives?: string;
};
type IBqmlIterationResult = {
/**
* [Output-only, Beta] Time taken to run the training iteration in milliseconds.
*/
durationMs?: string;
/**
* [Output-only, Beta] Eval loss computed on the eval data at the end of the iteration. The eval loss is used for early stopping to avoid overfitting. No eval loss if eval_split_method option is specified as no_split or auto_split with input data size less than 500 rows.
*/
evalLoss?: number;
/**
* [Output-only, Beta] Index of the ML training iteration, starting from zero for each training run.
*/
index?: number;
/**
* [Output-only, Beta] Learning rate used for this iteration, it varies for different training iterations if learn_rate_strategy option is not constant.
*/
learnRate?: number;
/**
* [Output-only, Beta] Training loss computed on the training data at the end of the iteration. The training loss function is defined by model type.
*/
trainingLoss?: number;
};
type IBqmlTrainingRun = {
/**
* [Output-only, Beta] List of each iteration results.
*/
iterationResults?: Array<IBqmlIterationResult>;
/**
* [Output-only, Beta] Training run start time in milliseconds since the epoch.
*/
startTime?: string;
/**
* [Output-only, Beta] Different state applicable for a training run. IN PROGRESS: Training run is in progress. FAILED: Training run ended due to a non-retryable failure. SUCCEEDED: Training run successfully completed. CANCELLED: Training run cancelled by the user.
*/
state?: string;
/**
* [Output-only, Beta] Training options used by this training run. These options are mutable for subsequent training runs. Default values are explicitly stored for options not specified in the input query of the first training run. For subsequent training runs, any option not explicitly specified in the input query will be copied from the previous training run.
*/
trainingOptions?: {
earlyStop?: boolean;
l1Reg?: number;
l2Reg?: number;
learnRate?: number;
learnRateStrategy?: string;
lineSearchInitLearnRate?: number;
maxIteration?: string;
minRelProgress?: number;
warmStart?: boolean;
};
};
/**
* Representative value of a categorical feature.
*/
type ICategoricalValue = {
/**
* Counts of all categories for the categorical feature. If there are
* more than ten categories, we return top ten (by count) and return
* one more CategoryCount with category "_OTHER_" and count as
* aggregate counts of remaining categories.
*/
categoryCounts?: Array<ICategoryCount>;
};
/**
* Represents the count of a single category within the cluster.
*/
type ICategoryCount = {
/**
* The name of category.
*/
category?: string;
/**
* The count of training samples matching the category within the
* cluster.
*/
count?: string;
};
/**
* Message containing the information about one cluster.
*/
type ICluster = {
/**
* Centroid id.
*/
centroidId?: string;
/**
* Count of training data rows that were assigned to this cluster.
*/
count?: string;
/**
* Values of highly variant features for this cluster.
*/
featureValues?: Array<IFeatureValue>;
};
/**
* Information about a single cluster for clustering model.
*/
type IClusterInfo = {
/**
* Centroid id.
*/
centroidId?: string;
/**
* Cluster radius, the average distance from centroid
* to each point assigned to the cluster.
*/
clusterRadius?: number;
/**
* Cluster size, the total number of points assigned to the cluster.
*/
clusterSize?: string;
};
type IClustering = {
/**
* [Repeated] One or more fields on which data should be clustered. Only top-level, non-repeated, simple-type fields are supported. When you cluster a table using multiple columns, the order of columns you specify is important. The order of the specified columns determines the sort order of the data.
*/
fields?: Array<string>;
};
/**
* Evaluation metrics for clustering models.
*/
type IClusteringMetrics = {
/**
* [Beta] Information for all clusters.
*/
clusters?: Array<ICluster>;
/**
* Davies-Bouldin index.
*/
daviesBouldinIndex?: number;
/**
* Mean of squared distances between each sample to its cluster centroid.
*/
meanSquaredDistance?: number;
};
/**
* Confusion matrix for multi-class classification models.
*/
type IConfusionMatrix = {
/**
* Confidence threshold used when computing the entries of the
* confusion matrix.
*/
confidenceThreshold?: number;
/**
* One row per actual label.
*/
rows?: Array<IRow>;
};
type ICsvOptions = {
/**
* [Optional] Indicates if BigQuery should accept rows that are missing trailing optional columns. If true, BigQuery treats missing trailing columns as null values. If false, records with missing trailing columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false.
*/
allowJaggedRows?: boolean;
/**
* [Optional] Indicates if BigQuery should allow quoted data sections that contain newline characters in a CSV file. The default value is false.
*/
allowQuotedNewlines?: boolean;
/**
* [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
*/
encoding?: string;
/**
* [Optional] The separator for fields in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
*/
fieldDelimiter?: string;
/**
* [Optional] The value that is used to quote data sections in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. The default value is a double-quote ('"'). If your data does not contain quoted sections, set the property value to an empty string. If your data contains quoted newline characters, you must also set the allowQuotedNewlines property to true.
*/
quote?: string;
/**
* [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped. When autodetect is on, the behavior is the following: * skipLeadingRows unspecified - Autodetect tries to detect headers in the first row. If they are not detected, the row is read as data. Otherwise data is read starting from the second row. * skipLeadingRows is 0 - Instructs autodetect that there are no headers and data should be read starting from the first row. * skipLeadingRows = N > 0 - Autodetect skips N-1 rows and tries to detect headers in row N. If headers are not detected, row N is just skipped. Otherwise row N is used to extract column names for the detected schema.
*/
skipLeadingRows?: string;
};
/**
* Data split result. This contains references to the training and evaluation
* data tables that were used to train the model.
*/
type IDataSplitResult = {
/**
* Table reference of the evaluation data after split.
*/
evaluationTable?: ITableReference;
/**
* Table reference of the training data after split.
*/
trainingTable?: ITableReference;
};
type IDataset = {
/**
* [Optional] An array of objects that define dataset access for one or more entities. You can set this property when inserting or updating a dataset in order to control who is allowed to access the data. If unspecified at dataset creation time, BigQuery adds default dataset access for the following entities: access.specialGroup: projectReaders; access.role: READER; access.specialGroup: projectWriters; access.role: WRITER; access.specialGroup: projectOwners; access.role: OWNER; access.userByEmail: [dataset creator email]; access.role: OWNER;
*/
access?: Array<{
/**
* [Pick one] A domain to grant access to. Any users signed in with the domain specified will be granted the specified access. Example: "example.com". Maps to IAM policy member "domain:DOMAIN".
*/
domain?: string;
/**
* [Pick one] An email address of a Google Group to grant access to. Maps to IAM policy member "group:GROUP".
*/
groupByEmail?: string;
/**
* [Pick one] Some other type of member that appears in the IAM Policy but isn't a user, group, domain, or special group.
*/
iamMember?: string;
/**
* [Required] An IAM role ID that should be granted to the user, group, or domain specified in this access entry. The following legacy mappings will be applied: OWNER roles/bigquery.dataOwner WRITER roles/bigquery.dataEditor READER roles/bigquery.dataViewer This field will accept any of the above formats, but will return only the legacy format. For example, if you set this field to "roles/bigquery.dataOwner", it will be returned back as "OWNER".
*/
role?: string;
/**
* [Pick one] A special group to grant access to. Possible values include: projectOwners: Owners of the enclosing project. projectReaders: Readers of the enclosing project. projectWriters: Writers of the enclosing project. allAuthenticatedUsers: All authenticated BigQuery users. Maps to similarly-named IAM members.
*/
specialGroup?: string;
/**
* [Pick one] An email address of a user to grant access to. For example: fred@example.com. Maps to IAM policy member "user:EMAIL" or "serviceAccount:EMAIL".
*/
userByEmail?: string;
/**
* [Pick one] A view from a different dataset to grant access to. Queries executed against that view will have read access to tables in this dataset. The role field is not required when this field is set. If that view is updated by any user, access to the view needs to be granted again via an update operation.
*/
view?: ITableReference;
}>;
/**
* [Output-only] The time when this dataset was created, in milliseconds since the epoch.
*/
creationTime?: string;
/**
* [Required] A reference that identifies the dataset.
*/
datasetReference?: IDatasetReference;
defaultEncryptionConfiguration?: IEncryptionConfiguration;
/**
* [Optional] The default partition expiration for all partitioned tables in the dataset, in milliseconds. Once this property is set, all newly-created partitioned tables in the dataset will have an expirationMs property in the timePartitioning settings set to this value, and changing the value will only affect new tables, not existing ones. The storage in a partition will have an expiration time of its partition time plus this value. Setting this property overrides the use of defaultTableExpirationMs for partitioned tables: only one of defaultTableExpirationMs and defaultPartitionExpirationMs will be used for any new partitioned table. If you provide an explicit timePartitioning.expirationMs when creating or updating a partitioned table, that value takes precedence over the default partition expiration time indicated by this property.
*/
defaultPartitionExpirationMs?: string;
/**
* [Optional] The default lifetime of all tables in the dataset, in milliseconds. The minimum value is 3600000 milliseconds (one hour). Once this property is set, all newly-created tables in the dataset will have an expirationTime property set to the creation time plus the value in this property, and changing the value will only affect new tables, not existing ones. When the expirationTime for a given table is reached, that table will be deleted automatically. If a table's expirationTime is modified or removed before the table expires, or if you provide an explicit expirationTime when creating a table, that value takes precedence over the default expiration time indicated by this property.
*/
defaultTableExpirationMs?: string;
/**
* [Optional] A user-friendly description of the dataset.
*/
description?: string;
/**
* [Output-only] A hash of the resource.
*/
etag?: string;
/**
* [Optional] A descriptive name for the dataset.
*/
friendlyName?: string;
/**
* [Output-only] The fully-qualified unique name of the dataset in the format projectId:datasetId. The dataset name without the project name is given in the datasetId field. When creating a new dataset, leave this field blank, and instead specify the datasetId field.
*/
id?: string;
/**
* [Output-only] The resource type.
*/
kind?: string;
/**
* The labels associated with this dataset. You can use these to organize and group your datasets. You can set this property when inserting or updating a dataset. See Creating and Updating Dataset Labels for more information.
*/
labels?: { [key: string]: string };
/**
* [Output-only] The date when this dataset or any of its tables was last modified, in milliseconds since the epoch.
*/
lastModifiedTime?: string;
/**
* The geographic location where the dataset should reside. The default value is US. See details at https://cloud.google.com/bigquery/docs/locations.
*/
location?: string;
/**
* [Output-only] A URL that can be used to access the resource again. You can use this URL in Get or Update requests to the resource.
*/
selfLink?: string;
};
type IDatasetList = {
/**
* An array of the dataset resources in the project. Each resource contains basic information. For full information about a particular dataset resource, use the Datasets: get method. This property is omitted when there are no datasets in the project.
*/
datasets?: Array<{
/**
* The dataset reference. Use this property to access specific parts of the dataset's ID, such as project ID or dataset ID.
*/
datasetReference?: IDatasetReference;
/**
* A descriptive name for the dataset, if one exists.
*/
friendlyName?: string;
/**
* The fully-qualified, unique, opaque ID of the dataset.
*/
id?: string;
/**
* The resource type. This property always returns the value "bigquery#dataset".
*/
kind?: string;
/**
* The labels associated with this dataset. You can use these to organize and group your datasets.
*/
labels?: { [key: string]: string };
/**
* The geographic location where the data resides.
*/
location?: string;
}>;
/**
* A hash value of the results page. You can use this property to determine if the page has changed since the last request.
*/
etag?: string;
/**
* The list type. This property always returns the value "bigquery#datasetList".
*/
kind?: string;
/**
* A token that can be used to request the next results page. This property is omitted on the final results page.
*/
nextPageToken?: string;
};
type IDatasetReference = {
/**
* [Required] A unique ID for this dataset, without the project name. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
*/
datasetId?: string;
/**
* [Optional] The ID of the project containing this dataset.
*/
projectId?: string;
};
type IDestinationTableProperties = {
/**
* [Optional] The description for the destination table. This will only be used if the destination table is newly created. If the table already exists and a value different than the current description is provided, the job will fail.
*/
description?: string;
/**
* [Optional] The friendly name for the destination table. This will only be used if the destination table is newly created. If the table already exists and a value different than the current friendly name is provided, the job will fail.
*/
friendlyName?: string;
/**
* [Optional] The labels associated with this table. You can use these to organize and group your tables. This will only be used if the destination table is newly created. If the table already exists and labels are different than the current labels are provided, the job will fail.
*/
labels?: { [key: string]: string };
};
type IEncryptionConfiguration = {
/**
* [Optional] Describes the Cloud KMS encryption key that will be used to protect destination BigQuery table. The BigQuery Service Account associated with your project requires access to this encryption key.
*/
kmsKeyName?: string;
};
/**
* A single entry in the confusion matrix.
*/
type IEntry = {
/**
* Number of items being predicted as this label.
*/
itemCount?: string;
/**
* The predicted label. For confidence_threshold > 0, we will
* also add an entry indicating the number of items under the
* confidence threshold.
*/
predictedLabel?: string;
};
type IErrorProto = {
/**
* Debugging information. This property is internal to Google and should not be used.
*/
debugInfo?: string;
/**
* Specifies where the error occurred, if present.
*/
location?: string;
/**
* A human-readable description of the error.
*/
message?: string;
/**
* A short error code that summarizes the error.
*/
reason?: string;
};
/**
* Evaluation metrics of a model. These are either computed on all training
* data or just the eval data based on whether eval data was used during
* training. These are not present for imported models.
*/
type IEvaluationMetrics = {
/**
* Populated for binary classification/classifier models.
*/
binaryClassificationMetrics?: IBinaryClassificationMetrics;
/**
* Populated for clustering models.
*/
clusteringMetrics?: IClusteringMetrics;
/**
* Populated for multi-class classification/classifier models.
*/
multiClassClassificationMetrics?: IMultiClassClassificationMetrics;
/**
* [Alpha] Populated for implicit feedback type matrix factorization
* models.
*/
rankingMetrics?: IRankingMetrics;
/**
* Populated for regression models and explicit feedback type matrix
* factorization models.
*/
regressionMetrics?: IRegressionMetrics;
};
type IExplainQueryStage = {
/**
* Number of parallel input segments completed.
*/
completedParallelInputs?: string;
/**
* Milliseconds the average shard spent on CPU-bound tasks.
*/
computeMsAvg?: string;
/**
* Milliseconds the slowest shard spent on CPU-bound tasks.
*/
computeMsMax?: string;
/**
* Relative amount of time the average shard spent on CPU-bound tasks.
*/
computeRatioAvg?: number;
/**
* Relative amount of time the slowest shard spent on CPU-bound tasks.
*/
computeRatioMax?: number;
/**
* Stage end time represented as milliseconds since epoch.
*/
endMs?: string;
/**
* Unique ID for stage within plan.
*/
id?: string;
/**
* IDs for stages that are inputs to this stage.
*/
inputStages?: Array<string>;
/**
* Human-readable name for stage.
*/
name?: string;
/**
* Number of parallel input segments to be processed.
*/
parallelInputs?: string;
/**
* Milliseconds the average shard spent reading input.
*/
readMsAvg?: string;
/**
* Milliseconds the slowest shard spent reading input.
*/
readMsMax?: string;
/**
* Relative amount of time the average shard spent reading input.
*/
readRatioAvg?: number;
/**
* Relative amount of time the slowest shard spent reading input.
*/
readRatioMax?: number;
/**
* Number of records read into the stage.
*/
recordsRead?: string;
/**
* Number of records written by the stage.
*/
recordsWritten?: string;
/**
* Total number of bytes written to shuffle.
*/
shuffleOutputBytes?: string;
/**
* Total number of bytes written to shuffle and spilled to disk.
*/
shuffleOutputBytesSpilled?: string;
/**
* Slot-milliseconds used by the stage.
*/
slotMs?: string;
/**
* Stage start time represented as milliseconds since epoch.
*/
startMs?: string;
/**
* Current status for the stage.
*/
status?: string;
/**
* List of operations within the stage in dependency order (approximately chronological).
*/
steps?: Array<IExplainQueryStep>;
/**
* Milliseconds the average shard spent waiting to be scheduled.
*/
waitMsAvg?: string;
/**
* Milliseconds the slowest shard spent waiting to be scheduled.
*/
waitMsMax?: string;
/**
* Relative amount of time the average shard spent waiting to be scheduled.
*/
waitRatioAvg?: number;
/**
* Relative amount of time the slowest shard spent waiting to be scheduled.
*/
waitRatioMax?: number;
/**
* Milliseconds the average shard spent on writing output.
*/
writeMsAvg?: string;
/**
* Milliseconds the slowest shard spent on writing output.
*/
writeMsMax?: string;
/**
* Relative amount of time the average shard spent on writing output.
*/
writeRatioAvg?: number;
/**
* Relative amount of time the slowest shard spent on writing output.
*/
writeRatioMax?: number;
};
type IExplainQueryStep = {
/**
* Machine-readable operation type.
*/
kind?: string;
/**
* Human-readable stage descriptions.
*/
substeps?: Array<string>;
};
type IExternalDataConfiguration = {
/**
* Try to detect schema and format options automatically. Any option specified explicitly will be honored.
*/
autodetect?: boolean;
/**
* [Optional] Additional options if sourceFormat is set to BIGTABLE.
*/
bigtableOptions?: IBigtableOptions;
/**
* [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
*/
compression?: string;
/**
* Additional properties to set if sourceFormat is set to CSV.
*/
csvOptions?: ICsvOptions;
/**
* [Optional] Additional options if sourceFormat is set to GOOGLE_SHEETS.
*/
googleSheetsOptions?: IGoogleSheetsOptions;
/**
* [Optional, Trusted Tester] Deprecated, do not use. Please set hivePartitioningOptions instead.
*/
hivePartitioningMode?: string;
/**
* [Optional, Trusted Tester] Options to configure hive partitioning support.
*/
hivePartitioningOptions?: IHivePartitioningOptions;
/**
* [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Bigtable: This setting is ignored. Google Cloud Datastore backups: This setting is ignored. Avro: This setting is ignored.
*/
ignoreUnknownValues?: boolean;
/**
* [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. This is only valid for CSV, JSON, and Google Sheets. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
*/
maxBadRecords?: number;
/**
* [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Bigtable, Cloud Datastore backups, and Avro formats.
*/
schema?: ITableSchema;
/**
* [Required] The data format. For CSV files, specify "CSV". For Google sheets, specify "GOOGLE_SHEETS". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro files, specify "AVRO". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP". [Beta] For Google Cloud Bigtable, specify "BIGTABLE".
*/
sourceFormat?: string;
/**
* [Required] The fully-qualified URIs that point to your data in Google Cloud. For Google Cloud Storage URIs: Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources. For Google Cloud Bigtable URIs: Exactly one URI can be specified and it has be a fully specified and valid HTTPS URL for a Google Cloud Bigtable table. For Google Cloud Datastore backups, exactly one URI can be specified. Also, the '*' wildcard character is not allowed.
*/
sourceUris?: Array<string>;
};
/**
* Representative value of a single feature within the cluster.
*/
type IFeatureValue = {
/**
* The categorical feature value.
*/
categoricalValue?: ICategoricalValue;
/**
* The feature column name.
*/
featureColumn?: string;
/**
* The numerical feature value. This is the centroid value for this
* feature.
*/
numericalValue?: number;
};
type IGetQueryResultsResponse = {
/**
* Whether the query result was fetched from the query cache.
*/
cacheHit?: boolean;
/**
* [Output-only] The first errors or warnings encountered during the running of the job. The final message includes the number of errors that caused the process to stop. Errors here do not necessarily mean that the job has completed or was unsuccessful.
*/
errors?: Array<IErrorProto>;
/**
* A hash of this response.
*/
etag?: string;
/**
* Whether the query has completed or not. If rows or totalRows are present, this will always be true. If this is false, totalRows will not be available.
*/
jobComplete?: boolean;
/**
* Reference to the BigQuery Job that was created to run the query. This field will be present even if the original request timed out, in which case GetQueryResults can be used to read the results once the query has completed. Since this API only returns the first page of results, subsequent pages can be fetched via the same mechanism (GetQueryResults).
*/
jobReference?: IJobReference;
/**
* The resource type of the response.
*/
kind?: string;
/**
* [Output-only] The number of rows affected by a DML statement. Present only for DML statements INSERT, UPDATE or DELETE.
*/
numDmlAffectedRows?: string;
/**
* A token used for paging results.
*/
pageToken?: string;
/**
* An object with as many results as can be contained within the maximum permitted reply size. To get any additional rows, you can call GetQueryResults and specify the jobReference returned above. Present only when the query completes successfully.
*/
rows?: Array<ITableRow>;
/**
* The schema of the results. Present only when the query completes successfully.
*/
schema?: ITableSchema;
/**
* The total number of bytes processed for this query.
*/
totalBytesProcessed?: string;
/**
* The total number of rows in the complete query result set, which can be more than the number of rows in this single page of results. Present only when the query completes successfully.
*/
totalRows?: string;
};
type IGetServiceAccountResponse = {
/**
* The service account email address.
*/