aws-sdk-glue 1.41.0 → 1.42.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/aws-sdk-glue.rb +1 -1
- data/lib/aws-sdk-glue/client.rb +1098 -74
- data/lib/aws-sdk-glue/client_api.rb +552 -0
- data/lib/aws-sdk-glue/errors.rb +16 -0
- data/lib/aws-sdk-glue/types.rb +2134 -230
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 9fc97915146dcb08dc83c18f2aa4e32b50ad5efe
|
4
|
+
data.tar.gz: 614626753aa55fb5585512812eb35b0750545024
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e2f5c29b355e20bc6f878327a72f92e5e0e78aca3e70c330bd73998e9147afcf79197bf1676bfce19b43e044c91cc9e45722f5890ef80b5074fc89a659e89dbe
|
7
|
+
data.tar.gz: e863c6bd679f4b5800596ad3ff89501f53629222f65eebed9a7ad832f44c56ee73f33fae5c93f45717528ec3c07ffb53d45fc1b2adc585c002e3b9cbd70f5f84
|
data/lib/aws-sdk-glue.rb
CHANGED
data/lib/aws-sdk-glue/client.rb
CHANGED
@@ -267,7 +267,7 @@ module Aws::Glue
|
|
267
267
|
# Creates one or more partitions in a batch operation.
|
268
268
|
#
|
269
269
|
# @option params [String] :catalog_id
|
270
|
-
# The ID of the catalog in which the
|
270
|
+
# The ID of the catalog in which the partition is to be created.
|
271
271
|
# Currently, this should be the AWS account ID.
|
272
272
|
#
|
273
273
|
# @option params [required, String] :database_name
|
@@ -302,6 +302,9 @@ module Aws::Glue
|
|
302
302
|
# name: "NameString", # required
|
303
303
|
# type: "ColumnTypeString",
|
304
304
|
# comment: "CommentString",
|
305
|
+
# parameters: {
|
306
|
+
# "KeyString" => "ParametersMapValue",
|
307
|
+
# },
|
305
308
|
# },
|
306
309
|
# ],
|
307
310
|
# location: "LocationString",
|
@@ -402,14 +405,14 @@ module Aws::Glue
|
|
402
405
|
#
|
403
406
|
# @option params [String] :catalog_id
|
404
407
|
# The ID of the Data Catalog where the partition to be deleted resides.
|
405
|
-
# If none is
|
408
|
+
# If none is provided, the AWS account ID is used by default.
|
406
409
|
#
|
407
410
|
# @option params [required, String] :database_name
|
408
411
|
# The name of the catalog database in which the table in question
|
409
412
|
# resides.
|
410
413
|
#
|
411
414
|
# @option params [required, String] :table_name
|
412
|
-
# The name of the table
|
415
|
+
# The name of the table that contains the partitions to be deleted.
|
413
416
|
#
|
414
417
|
# @option params [required, Array<Types::PartitionValueList>] :partitions_to_delete
|
415
418
|
# A list of `PartitionInput` structures that define the partitions to be
|
@@ -451,13 +454,13 @@ module Aws::Glue
|
|
451
454
|
|
452
455
|
# Deletes multiple tables at once.
|
453
456
|
#
|
454
|
-
# <note markdown="1"> After completing this operation, you
|
457
|
+
# <note markdown="1"> After completing this operation, you no longer have access to the
|
455
458
|
# table versions and partitions that belong to the deleted table. AWS
|
456
459
|
# Glue deletes these "orphaned" resources asynchronously in a timely
|
457
460
|
# manner, at the discretion of the service.
|
458
461
|
#
|
459
|
-
# To ensure immediate deletion of all related resources, before
|
460
|
-
# `BatchDeleteTable`, use `DeleteTableVersion` or
|
462
|
+
# To ensure the immediate deletion of all related resources, before
|
463
|
+
# calling `BatchDeleteTable`, use `DeleteTableVersion` or
|
461
464
|
# `BatchDeleteTableVersion`, and `DeletePartition` or
|
462
465
|
# `BatchDeletePartition`, to delete any resources that belong to the
|
463
466
|
# table.
|
@@ -466,10 +469,10 @@ module Aws::Glue
|
|
466
469
|
#
|
467
470
|
# @option params [String] :catalog_id
|
468
471
|
# The ID of the Data Catalog where the table resides. If none is
|
469
|
-
#
|
472
|
+
# provided, the AWS account ID is used by default.
|
470
473
|
#
|
471
474
|
# @option params [required, String] :database_name
|
472
|
-
# The name of the catalog database
|
475
|
+
# The name of the catalog database in which the tables to delete reside.
|
473
476
|
# For Hive compatibility, this name is entirely lowercase.
|
474
477
|
#
|
475
478
|
# @option params [required, Array<String>] :tables_to_delete
|
@@ -507,7 +510,7 @@ module Aws::Glue
|
|
507
510
|
#
|
508
511
|
# @option params [String] :catalog_id
|
509
512
|
# The ID of the Data Catalog where the tables reside. If none is
|
510
|
-
#
|
513
|
+
# provided, the AWS account ID is used by default.
|
511
514
|
#
|
512
515
|
# @option params [required, String] :database_name
|
513
516
|
# The database in the catalog in which the table resides. For Hive
|
@@ -794,6 +797,8 @@ module Aws::Glue
|
|
794
797
|
# resp.partitions[0].storage_descriptor.columns[0].name #=> String
|
795
798
|
# resp.partitions[0].storage_descriptor.columns[0].type #=> String
|
796
799
|
# resp.partitions[0].storage_descriptor.columns[0].comment #=> String
|
800
|
+
# resp.partitions[0].storage_descriptor.columns[0].parameters #=> Hash
|
801
|
+
# resp.partitions[0].storage_descriptor.columns[0].parameters["KeyString"] #=> String
|
797
802
|
# resp.partitions[0].storage_descriptor.location #=> String
|
798
803
|
# resp.partitions[0].storage_descriptor.input_format #=> String
|
799
804
|
# resp.partitions[0].storage_descriptor.output_format #=> String
|
@@ -1116,6 +1121,46 @@ module Aws::Glue
|
|
1116
1121
|
req.send_request(options)
|
1117
1122
|
end
|
1118
1123
|
|
1124
|
+
# Cancels (stops) a task run. Machine learning task runs are
|
1125
|
+
# asynchronous tasks that AWS Glue runs on your behalf as part of
|
1126
|
+
# various machine learning workflows. You can cancel a machine learning
|
1127
|
+
# task run at any time by calling `CancelMLTaskRun` with a task run's
|
1128
|
+
# parent transform's `TransformID` and the task run's `TaskRunId`.
|
1129
|
+
#
|
1130
|
+
# @option params [required, String] :transform_id
|
1131
|
+
# The unique identifier of the machine learning transform.
|
1132
|
+
#
|
1133
|
+
# @option params [required, String] :task_run_id
|
1134
|
+
# A unique identifier for the task run.
|
1135
|
+
#
|
1136
|
+
# @return [Types::CancelMLTaskRunResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
1137
|
+
#
|
1138
|
+
# * {Types::CancelMLTaskRunResponse#transform_id #transform_id} => String
|
1139
|
+
# * {Types::CancelMLTaskRunResponse#task_run_id #task_run_id} => String
|
1140
|
+
# * {Types::CancelMLTaskRunResponse#status #status} => String
|
1141
|
+
#
|
1142
|
+
# @example Request syntax with placeholder values
|
1143
|
+
#
|
1144
|
+
# resp = client.cancel_ml_task_run({
|
1145
|
+
# transform_id: "HashString", # required
|
1146
|
+
# task_run_id: "HashString", # required
|
1147
|
+
# })
|
1148
|
+
#
|
1149
|
+
# @example Response structure
|
1150
|
+
#
|
1151
|
+
# resp.transform_id #=> String
|
1152
|
+
# resp.task_run_id #=> String
|
1153
|
+
# resp.status #=> String, one of "STARTING", "RUNNING", "STOPPING", "STOPPED", "SUCCEEDED", "FAILED", "TIMEOUT"
|
1154
|
+
#
|
1155
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/CancelMLTaskRun AWS API Documentation
|
1156
|
+
#
|
1157
|
+
# @overload cancel_ml_task_run(params = {})
|
1158
|
+
# @param [Hash] params ({})
|
1159
|
+
def cancel_ml_task_run(params = {}, options = {})
|
1160
|
+
req = build_request(:cancel_ml_task_run, params)
|
1161
|
+
req.send_request(options)
|
1162
|
+
end
|
1163
|
+
|
1119
1164
|
# Creates a classifier in the user's account. This can be a
|
1120
1165
|
# `GrokClassifier`, an `XMLClassifier`, a `JsonClassifier`, or a
|
1121
1166
|
# `CsvClassifier`, depending on which field of the request is present.
|
@@ -1340,11 +1385,10 @@ module Aws::Glue
|
|
1340
1385
|
#
|
1341
1386
|
# @option params [String] :catalog_id
|
1342
1387
|
# The ID of the Data Catalog in which to create the database. If none is
|
1343
|
-
#
|
1388
|
+
# provided, the AWS account ID is used by default.
|
1344
1389
|
#
|
1345
1390
|
# @option params [required, Types::DatabaseInput] :database_input
|
1346
|
-
#
|
1347
|
-
# the catalog.
|
1391
|
+
# The metadata for the database.
|
1348
1392
|
#
|
1349
1393
|
# @return [Struct] Returns an empty {Seahorse::Client::Response response}.
|
1350
1394
|
#
|
@@ -1359,6 +1403,14 @@ module Aws::Glue
|
|
1359
1403
|
# parameters: {
|
1360
1404
|
# "KeyString" => "ParametersMapValue",
|
1361
1405
|
# },
|
1406
|
+
# create_table_default_permissions: [
|
1407
|
+
# {
|
1408
|
+
# principal: {
|
1409
|
+
# data_lake_principal_identifier: "DataLakePrincipalString",
|
1410
|
+
# },
|
1411
|
+
# permissions: ["ALL"], # accepts ALL, SELECT, ALTER, DROP, DELETE, INSERT, CREATE_DATABASE, CREATE_TABLE, DATA_LOCATION_ACCESS
|
1412
|
+
# },
|
1413
|
+
# ],
|
1362
1414
|
# },
|
1363
1415
|
# })
|
1364
1416
|
#
|
@@ -1424,6 +1476,10 @@ module Aws::Glue
|
|
1424
1476
|
# of memory, 128 GB disk), and provides 1 executor per worker. We
|
1425
1477
|
# recommend this worker type for memory-intensive jobs.
|
1426
1478
|
#
|
1479
|
+
# Known issue: when a development endpoint is created with the `G.2X`
|
1480
|
+
# `WorkerType` configuration, the Spark drivers for the development
|
1481
|
+
# endpoint will run on 4 vCPU, 16 GB of memory, and a 64 GB disk.
|
1482
|
+
#
|
1427
1483
|
# @option params [Integer] :number_of_workers
|
1428
1484
|
# The number of workers of a defined `workerType` that are allocated to
|
1429
1485
|
# the development endpoint.
|
@@ -1741,11 +1797,138 @@ module Aws::Glue
|
|
1741
1797
|
req.send_request(options)
|
1742
1798
|
end
|
1743
1799
|
|
1800
|
+
# Creates an AWS Glue machine learning transform. This operation creates
|
1801
|
+
# the transform and all the necessary parameters to train it.
|
1802
|
+
#
|
1803
|
+
# Call this operation as the first step in the process of using a
|
1804
|
+
# machine learning transform (such as the `FindMatches` transform) for
|
1805
|
+
# deduplicating data. You can provide an optional `Description`, in
|
1806
|
+
# addition to the parameters that you want to use for your algorithm.
|
1807
|
+
#
|
1808
|
+
# You must also specify certain parameters for the tasks that AWS Glue
|
1809
|
+
# runs on your behalf as part of learning from your data and creating a
|
1810
|
+
# high-quality machine learning transform. These parameters include
|
1811
|
+
# `Role`, and optionally, `AllocatedCapacity`, `Timeout`, and
|
1812
|
+
# `MaxRetries`. For more information, see [Jobs][1].
|
1813
|
+
#
|
1814
|
+
#
|
1815
|
+
#
|
1816
|
+
# [1]: https://docs.aws.amazon.com/glue/latest/dg/aws-glue-api-jobs-job.html
|
1817
|
+
#
|
1818
|
+
# @option params [required, String] :name
|
1819
|
+
# The unique name that you give the transform when you create it.
|
1820
|
+
#
|
1821
|
+
# @option params [String] :description
|
1822
|
+
# A description of the machine learning transform that is being defined.
|
1823
|
+
# The default is an empty string.
|
1824
|
+
#
|
1825
|
+
# @option params [required, Array<Types::GlueTable>] :input_record_tables
|
1826
|
+
# A list of AWS Glue table definitions used by the transform.
|
1827
|
+
#
|
1828
|
+
# @option params [required, Types::TransformParameters] :parameters
|
1829
|
+
# The algorithmic parameters that are specific to the transform type
|
1830
|
+
# used. Conditionally dependent on the transform type.
|
1831
|
+
#
|
1832
|
+
# @option params [required, String] :role
|
1833
|
+
# The name or Amazon Resource Name (ARN) of the IAM role with the
|
1834
|
+
# required permissions. Ensure that this role has permission to your
|
1835
|
+
# Amazon Simple Storage Service (Amazon S3) sources, targets, temporary
|
1836
|
+
# directory, scripts, and any libraries that are used by the task run
|
1837
|
+
# for this transform.
|
1838
|
+
#
|
1839
|
+
# @option params [Float] :max_capacity
|
1840
|
+
# The number of AWS Glue data processing units (DPUs) that are allocated
|
1841
|
+
# to task runs for this transform. You can allocate from 2 to 100 DPUs;
|
1842
|
+
# the default is 10. A DPU is a relative measure of processing power
|
1843
|
+
# that consists of 4 vCPUs of compute capacity and 16 GB of memory. For
|
1844
|
+
# more information, see the [AWS Glue pricing page][1].
|
1845
|
+
#
|
1846
|
+
# When the `WorkerType` field is set to a value other than `Standard`,
|
1847
|
+
# the `MaxCapacity` field is set automatically and becomes read-only.
|
1848
|
+
#
|
1849
|
+
#
|
1850
|
+
#
|
1851
|
+
# [1]: https://aws.amazon.com/glue/pricing/
|
1852
|
+
#
|
1853
|
+
# @option params [String] :worker_type
|
1854
|
+
# The type of predefined worker that is allocated when this task runs.
|
1855
|
+
# Accepts a value of Standard, G.1X, or G.2X.
|
1856
|
+
#
|
1857
|
+
# * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
|
1858
|
+
# of memory and a 50GB disk, and 2 executors per worker.
|
1859
|
+
#
|
1860
|
+
# * For the `G.1X` worker type, each worker provides 4 vCPU, 16 GB of
|
1861
|
+
# memory and a 64GB disk, and 1 executor per worker.
|
1862
|
+
#
|
1863
|
+
# * For the `G.2X` worker type, each worker provides 8 vCPU, 32 GB of
|
1864
|
+
# memory and a 128GB disk, and 1 executor per worker.
|
1865
|
+
#
|
1866
|
+
# @option params [Integer] :number_of_workers
|
1867
|
+
# The number of workers of a defined `workerType` that are allocated
|
1868
|
+
# when this task runs.
|
1869
|
+
#
|
1870
|
+
# @option params [Integer] :timeout
|
1871
|
+
# The timeout of the task run for this transform in minutes. This is the
|
1872
|
+
# maximum time that a task run for this transform can consume resources
|
1873
|
+
# before it is terminated and enters `TIMEOUT` status. The default is
|
1874
|
+
# 2,880 minutes (48 hours).
|
1875
|
+
#
|
1876
|
+
# @option params [Integer] :max_retries
|
1877
|
+
# The maximum number of times to retry a task for this transform after a
|
1878
|
+
# task run fails.
|
1879
|
+
#
|
1880
|
+
# @return [Types::CreateMLTransformResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
1881
|
+
#
|
1882
|
+
# * {Types::CreateMLTransformResponse#transform_id #transform_id} => String
|
1883
|
+
#
|
1884
|
+
# @example Request syntax with placeholder values
|
1885
|
+
#
|
1886
|
+
# resp = client.create_ml_transform({
|
1887
|
+
# name: "NameString", # required
|
1888
|
+
# description: "DescriptionString",
|
1889
|
+
# input_record_tables: [ # required
|
1890
|
+
# {
|
1891
|
+
# database_name: "NameString", # required
|
1892
|
+
# table_name: "NameString", # required
|
1893
|
+
# catalog_id: "NameString",
|
1894
|
+
# connection_name: "NameString",
|
1895
|
+
# },
|
1896
|
+
# ],
|
1897
|
+
# parameters: { # required
|
1898
|
+
# transform_type: "FIND_MATCHES", # required, accepts FIND_MATCHES
|
1899
|
+
# find_matches_parameters: {
|
1900
|
+
# primary_key_column_name: "ColumnNameString",
|
1901
|
+
# precision_recall_tradeoff: 1.0,
|
1902
|
+
# accuracy_cost_tradeoff: 1.0,
|
1903
|
+
# enforce_provided_labels: false,
|
1904
|
+
# },
|
1905
|
+
# },
|
1906
|
+
# role: "RoleString", # required
|
1907
|
+
# max_capacity: 1.0,
|
1908
|
+
# worker_type: "Standard", # accepts Standard, G.1X, G.2X
|
1909
|
+
# number_of_workers: 1,
|
1910
|
+
# timeout: 1,
|
1911
|
+
# max_retries: 1,
|
1912
|
+
# })
|
1913
|
+
#
|
1914
|
+
# @example Response structure
|
1915
|
+
#
|
1916
|
+
# resp.transform_id #=> String
|
1917
|
+
#
|
1918
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/CreateMLTransform AWS API Documentation
|
1919
|
+
#
|
1920
|
+
# @overload create_ml_transform(params = {})
|
1921
|
+
# @param [Hash] params ({})
|
1922
|
+
def create_ml_transform(params = {}, options = {})
|
1923
|
+
req = build_request(:create_ml_transform, params)
|
1924
|
+
req.send_request(options)
|
1925
|
+
end
|
1926
|
+
|
1744
1927
|
# Creates a new partition.
|
1745
1928
|
#
|
1746
1929
|
# @option params [String] :catalog_id
|
1747
|
-
# The ID of the catalog in which the
|
1748
|
-
#
|
1930
|
+
# The AWS account ID of the catalog in which the partition is to be
|
1931
|
+
# created.
|
1749
1932
|
#
|
1750
1933
|
# @option params [required, String] :database_name
|
1751
1934
|
# The name of the metadata database in which the partition is to be
|
@@ -1775,6 +1958,9 @@ module Aws::Glue
|
|
1775
1958
|
# name: "NameString", # required
|
1776
1959
|
# type: "ColumnTypeString",
|
1777
1960
|
# comment: "CommentString",
|
1961
|
+
# parameters: {
|
1962
|
+
# "KeyString" => "ParametersMapValue",
|
1963
|
+
# },
|
1778
1964
|
# },
|
1779
1965
|
# ],
|
1780
1966
|
# location: "LocationString",
|
@@ -1972,6 +2158,9 @@ module Aws::Glue
|
|
1972
2158
|
# name: "NameString", # required
|
1973
2159
|
# type: "ColumnTypeString",
|
1974
2160
|
# comment: "CommentString",
|
2161
|
+
# parameters: {
|
2162
|
+
# "KeyString" => "ParametersMapValue",
|
2163
|
+
# },
|
1975
2164
|
# },
|
1976
2165
|
# ],
|
1977
2166
|
# location: "LocationString",
|
@@ -2010,6 +2199,9 @@ module Aws::Glue
|
|
2010
2199
|
# name: "NameString", # required
|
2011
2200
|
# type: "ColumnTypeString",
|
2012
2201
|
# comment: "CommentString",
|
2202
|
+
# parameters: {
|
2203
|
+
# "KeyString" => "ParametersMapValue",
|
2204
|
+
# },
|
2013
2205
|
# },
|
2014
2206
|
# ],
|
2015
2207
|
# view_original_text: "ViewTextString",
|
@@ -2137,7 +2329,7 @@ module Aws::Glue
|
|
2137
2329
|
#
|
2138
2330
|
# @option params [String] :catalog_id
|
2139
2331
|
# The ID of the Data Catalog in which to create the function. If none is
|
2140
|
-
#
|
2332
|
+
# provided, the AWS account ID is used by default.
|
2141
2333
|
#
|
2142
2334
|
# @option params [required, String] :database_name
|
2143
2335
|
# The name of the catalog database in which to create the function.
|
@@ -2294,16 +2486,16 @@ module Aws::Glue
|
|
2294
2486
|
req.send_request(options)
|
2295
2487
|
end
|
2296
2488
|
|
2297
|
-
# Removes a specified
|
2489
|
+
# Removes a specified database from a Data Catalog.
|
2298
2490
|
#
|
2299
|
-
# <note markdown="1"> After completing this operation, you
|
2491
|
+
# <note markdown="1"> After completing this operation, you no longer have access to the
|
2300
2492
|
# tables (and all table versions and partitions that might belong to the
|
2301
2493
|
# tables) and the user-defined functions in the deleted database. AWS
|
2302
2494
|
# Glue deletes these "orphaned" resources asynchronously in a timely
|
2303
2495
|
# manner, at the discretion of the service.
|
2304
2496
|
#
|
2305
|
-
# To ensure immediate deletion of all related resources, before
|
2306
|
-
# `DeleteDatabase`, use `DeleteTableVersion` or
|
2497
|
+
# To ensure the immediate deletion of all related resources, before
|
2498
|
+
# calling `DeleteDatabase`, use `DeleteTableVersion` or
|
2307
2499
|
# `BatchDeleteTableVersion`, `DeletePartition` or
|
2308
2500
|
# `BatchDeletePartition`, `DeleteUserDefinedFunction`, and `DeleteTable`
|
2309
2501
|
# or `BatchDeleteTable`, to delete any resources that belong to the
|
@@ -2313,10 +2505,10 @@ module Aws::Glue
|
|
2313
2505
|
#
|
2314
2506
|
# @option params [String] :catalog_id
|
2315
2507
|
# The ID of the Data Catalog in which the database resides. If none is
|
2316
|
-
#
|
2508
|
+
# provided, the AWS account ID is used by default.
|
2317
2509
|
#
|
2318
2510
|
# @option params [required, String] :name
|
2319
|
-
# The name of the
|
2511
|
+
# The name of the database to delete. For Hive compatibility, this must
|
2320
2512
|
# be all lowercase.
|
2321
2513
|
#
|
2322
2514
|
# @return [Struct] Returns an empty {Seahorse::Client::Response response}.
|
@@ -2388,18 +2580,52 @@ module Aws::Glue
|
|
2388
2580
|
req.send_request(options)
|
2389
2581
|
end
|
2390
2582
|
|
2583
|
+
# Deletes an AWS Glue machine learning transform. Machine learning
|
2584
|
+
# transforms are a special type of transform that use machine learning
|
2585
|
+
# to learn the details of the transformation to be performed by learning
|
2586
|
+
# from examples provided by humans. These transformations are then saved
|
2587
|
+
# by AWS Glue. If you no longer need a transform, you can delete it by
|
2588
|
+
# calling `DeleteMLTransforms`. However, any AWS Glue jobs that still
|
2589
|
+
# reference the deleted transform will no longer succeed.
|
2590
|
+
#
|
2591
|
+
# @option params [required, String] :transform_id
|
2592
|
+
# The unique identifier of the transform to delete.
|
2593
|
+
#
|
2594
|
+
# @return [Types::DeleteMLTransformResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
2595
|
+
#
|
2596
|
+
# * {Types::DeleteMLTransformResponse#transform_id #transform_id} => String
|
2597
|
+
#
|
2598
|
+
# @example Request syntax with placeholder values
|
2599
|
+
#
|
2600
|
+
# resp = client.delete_ml_transform({
|
2601
|
+
# transform_id: "HashString", # required
|
2602
|
+
# })
|
2603
|
+
#
|
2604
|
+
# @example Response structure
|
2605
|
+
#
|
2606
|
+
# resp.transform_id #=> String
|
2607
|
+
#
|
2608
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/DeleteMLTransform AWS API Documentation
|
2609
|
+
#
|
2610
|
+
# @overload delete_ml_transform(params = {})
|
2611
|
+
# @param [Hash] params ({})
|
2612
|
+
def delete_ml_transform(params = {}, options = {})
|
2613
|
+
req = build_request(:delete_ml_transform, params)
|
2614
|
+
req.send_request(options)
|
2615
|
+
end
|
2616
|
+
|
2391
2617
|
# Deletes a specified partition.
|
2392
2618
|
#
|
2393
2619
|
# @option params [String] :catalog_id
|
2394
2620
|
# The ID of the Data Catalog where the partition to be deleted resides.
|
2395
|
-
# If none is
|
2621
|
+
# If none is provided, the AWS account ID is used by default.
|
2396
2622
|
#
|
2397
2623
|
# @option params [required, String] :database_name
|
2398
2624
|
# The name of the catalog database in which the table in question
|
2399
2625
|
# resides.
|
2400
2626
|
#
|
2401
2627
|
# @option params [required, String] :table_name
|
2402
|
-
# The name of the table
|
2628
|
+
# The name of the table that contains the partition to be deleted.
|
2403
2629
|
#
|
2404
2630
|
# @option params [required, Array<String>] :partition_values
|
2405
2631
|
# The values that define the partition.
|
@@ -2470,21 +2696,22 @@ module Aws::Glue
|
|
2470
2696
|
|
2471
2697
|
# Removes a table definition from the Data Catalog.
|
2472
2698
|
#
|
2473
|
-
# <note markdown="1"> After completing this operation, you
|
2699
|
+
# <note markdown="1"> After completing this operation, you no longer have access to the
|
2474
2700
|
# table versions and partitions that belong to the deleted table. AWS
|
2475
2701
|
# Glue deletes these "orphaned" resources asynchronously in a timely
|
2476
2702
|
# manner, at the discretion of the service.
|
2477
2703
|
#
|
2478
|
-
# To ensure immediate deletion of all related resources, before
|
2479
|
-
# `DeleteTable`, use `DeleteTableVersion` or
|
2480
|
-
# and `DeletePartition` or
|
2481
|
-
# resources that belong to the
|
2704
|
+
# To ensure the immediate deletion of all related resources, before
|
2705
|
+
# calling `DeleteTable`, use `DeleteTableVersion` or
|
2706
|
+
# `BatchDeleteTableVersion`, and `DeletePartition` or
|
2707
|
+
# `BatchDeletePartition`, to delete any resources that belong to the
|
2708
|
+
# table.
|
2482
2709
|
#
|
2483
2710
|
# </note>
|
2484
2711
|
#
|
2485
2712
|
# @option params [String] :catalog_id
|
2486
2713
|
# The ID of the Data Catalog where the table resides. If none is
|
2487
|
-
#
|
2714
|
+
# provided, the AWS account ID is used by default.
|
2488
2715
|
#
|
2489
2716
|
# @option params [required, String] :database_name
|
2490
2717
|
# The name of the catalog database in which the table resides. For Hive
|
@@ -2517,7 +2744,7 @@ module Aws::Glue
|
|
2517
2744
|
#
|
2518
2745
|
# @option params [String] :catalog_id
|
2519
2746
|
# The ID of the Data Catalog where the tables reside. If none is
|
2520
|
-
#
|
2747
|
+
# provided, the AWS account ID is used by default.
|
2521
2748
|
#
|
2522
2749
|
# @option params [required, String] :database_name
|
2523
2750
|
# The database in the catalog in which the table resides. For Hive
|
@@ -2803,7 +3030,7 @@ module Aws::Glue
|
|
2803
3030
|
# password. For instance, the AWS Glue console uses this flag to
|
2804
3031
|
# retrieve the connection, and does not display the password. Set this
|
2805
3032
|
# parameter when the caller might not have permission to use the AWS KMS
|
2806
|
-
# key to decrypt the password, but does have permission to access the
|
3033
|
+
# key to decrypt the password, but it does have permission to access the
|
2807
3034
|
# rest of the connection properties.
|
2808
3035
|
#
|
2809
3036
|
# @return [Types::GetConnectionResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
@@ -2851,14 +3078,14 @@ module Aws::Glue
|
|
2851
3078
|
# provided, the AWS account ID is used by default.
|
2852
3079
|
#
|
2853
3080
|
# @option params [Types::GetConnectionsFilter] :filter
|
2854
|
-
# A filter that controls which connections
|
3081
|
+
# A filter that controls which connections are returned.
|
2855
3082
|
#
|
2856
3083
|
# @option params [Boolean] :hide_password
|
2857
3084
|
# Allows you to retrieve the connection metadata without returning the
|
2858
3085
|
# password. For instance, the AWS Glue console uses this flag to
|
2859
3086
|
# retrieve the connection, and does not display the password. Set this
|
2860
3087
|
# parameter when the caller might not have permission to use the AWS KMS
|
2861
|
-
# key to decrypt the password, but does have permission to access the
|
3088
|
+
# key to decrypt the password, but it does have permission to access the
|
2862
3089
|
# rest of the connection properties.
|
2863
3090
|
#
|
2864
3091
|
# @option params [String] :next_token
|
@@ -3101,9 +3328,8 @@ module Aws::Glue
|
|
3101
3328
|
# Retrieves the security configuration for a specified catalog.
|
3102
3329
|
#
|
3103
3330
|
# @option params [String] :catalog_id
|
3104
|
-
# The ID of the Data Catalog
|
3105
|
-
#
|
3106
|
-
# default.
|
3331
|
+
# The ID of the Data Catalog to retrieve the security configuration for.
|
3332
|
+
# If none is provided, the AWS account ID is used by default.
|
3107
3333
|
#
|
3108
3334
|
# @return [Types::GetDataCatalogEncryptionSettingsResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
3109
3335
|
#
|
@@ -3135,7 +3361,7 @@ module Aws::Glue
|
|
3135
3361
|
#
|
3136
3362
|
# @option params [String] :catalog_id
|
3137
3363
|
# The ID of the Data Catalog in which the database resides. If none is
|
3138
|
-
#
|
3364
|
+
# provided, the AWS account ID is used by default.
|
3139
3365
|
#
|
3140
3366
|
# @option params [required, String] :name
|
3141
3367
|
# The name of the database to retrieve. For Hive compatibility, this
|
@@ -3160,6 +3386,10 @@ module Aws::Glue
|
|
3160
3386
|
# resp.database.parameters #=> Hash
|
3161
3387
|
# resp.database.parameters["KeyString"] #=> String
|
3162
3388
|
# resp.database.create_time #=> Time
|
3389
|
+
# resp.database.create_table_default_permissions #=> Array
|
3390
|
+
# resp.database.create_table_default_permissions[0].principal.data_lake_principal_identifier #=> String
|
3391
|
+
# resp.database.create_table_default_permissions[0].permissions #=> Array
|
3392
|
+
# resp.database.create_table_default_permissions[0].permissions[0] #=> String, one of "ALL", "SELECT", "ALTER", "DROP", "DELETE", "INSERT", "CREATE_DATABASE", "CREATE_TABLE", "DATA_LOCATION_ACCESS"
|
3163
3393
|
#
|
3164
3394
|
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetDatabase AWS API Documentation
|
3165
3395
|
#
|
@@ -3170,11 +3400,11 @@ module Aws::Glue
|
|
3170
3400
|
req.send_request(options)
|
3171
3401
|
end
|
3172
3402
|
|
3173
|
-
# Retrieves all
|
3403
|
+
# Retrieves all databases defined in a given Data Catalog.
|
3174
3404
|
#
|
3175
3405
|
# @option params [String] :catalog_id
|
3176
3406
|
# The ID of the Data Catalog from which to retrieve `Databases`. If none
|
3177
|
-
# is
|
3407
|
+
# is provided, the AWS account ID is used by default.
|
3178
3408
|
#
|
3179
3409
|
# @option params [String] :next_token
|
3180
3410
|
# A continuation token, if this is a continuation call.
|
@@ -3204,6 +3434,10 @@ module Aws::Glue
|
|
3204
3434
|
# resp.database_list[0].parameters #=> Hash
|
3205
3435
|
# resp.database_list[0].parameters["KeyString"] #=> String
|
3206
3436
|
# resp.database_list[0].create_time #=> Time
|
3437
|
+
# resp.database_list[0].create_table_default_permissions #=> Array
|
3438
|
+
# resp.database_list[0].create_table_default_permissions[0].principal.data_lake_principal_identifier #=> String
|
3439
|
+
# resp.database_list[0].create_table_default_permissions[0].permissions #=> Array
|
3440
|
+
# resp.database_list[0].create_table_default_permissions[0].permissions[0] #=> String, one of "ALL", "SELECT", "ALTER", "DROP", "DELETE", "INSERT", "CREATE_DATABASE", "CREATE_TABLE", "DATA_LOCATION_ACCESS"
|
3207
3441
|
# resp.next_token #=> String
|
3208
3442
|
#
|
3209
3443
|
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetDatabases AWS API Documentation
|
@@ -3698,6 +3932,330 @@ module Aws::Glue
|
|
3698
3932
|
req.send_request(options)
|
3699
3933
|
end
|
3700
3934
|
|
3935
|
+
# Gets details for a specific task run on a machine learning transform.
|
3936
|
+
# Machine learning task runs are asynchronous tasks that AWS Glue runs
|
3937
|
+
# on your behalf as part of various machine learning workflows. You can
|
3938
|
+
# check the stats of any task run by calling `GetMLTaskRun` with the
|
3939
|
+
# `TaskRunID` and its parent transform's `TransformID`.
|
3940
|
+
#
|
3941
|
+
# @option params [required, String] :transform_id
|
3942
|
+
# The unique identifier of the machine learning transform.
|
3943
|
+
#
|
3944
|
+
# @option params [required, String] :task_run_id
|
3945
|
+
# The unique identifier of the task run.
|
3946
|
+
#
|
3947
|
+
# @return [Types::GetMLTaskRunResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
3948
|
+
#
|
3949
|
+
# * {Types::GetMLTaskRunResponse#transform_id #transform_id} => String
|
3950
|
+
# * {Types::GetMLTaskRunResponse#task_run_id #task_run_id} => String
|
3951
|
+
# * {Types::GetMLTaskRunResponse#status #status} => String
|
3952
|
+
# * {Types::GetMLTaskRunResponse#log_group_name #log_group_name} => String
|
3953
|
+
# * {Types::GetMLTaskRunResponse#properties #properties} => Types::TaskRunProperties
|
3954
|
+
# * {Types::GetMLTaskRunResponse#error_string #error_string} => String
|
3955
|
+
# * {Types::GetMLTaskRunResponse#started_on #started_on} => Time
|
3956
|
+
# * {Types::GetMLTaskRunResponse#last_modified_on #last_modified_on} => Time
|
3957
|
+
# * {Types::GetMLTaskRunResponse#completed_on #completed_on} => Time
|
3958
|
+
# * {Types::GetMLTaskRunResponse#execution_time #execution_time} => Integer
|
3959
|
+
#
|
3960
|
+
# @example Request syntax with placeholder values
|
3961
|
+
#
|
3962
|
+
# resp = client.get_ml_task_run({
|
3963
|
+
# transform_id: "HashString", # required
|
3964
|
+
# task_run_id: "HashString", # required
|
3965
|
+
# })
|
3966
|
+
#
|
3967
|
+
# @example Response structure
|
3968
|
+
#
|
3969
|
+
# resp.transform_id #=> String
|
3970
|
+
# resp.task_run_id #=> String
|
3971
|
+
# resp.status #=> String, one of "STARTING", "RUNNING", "STOPPING", "STOPPED", "SUCCEEDED", "FAILED", "TIMEOUT"
|
3972
|
+
# resp.log_group_name #=> String
|
3973
|
+
# resp.properties.task_type #=> String, one of "EVALUATION", "LABELING_SET_GENERATION", "IMPORT_LABELS", "EXPORT_LABELS", "FIND_MATCHES"
|
3974
|
+
# resp.properties.import_labels_task_run_properties.input_s3_path #=> String
|
3975
|
+
# resp.properties.import_labels_task_run_properties.replace #=> Boolean
|
3976
|
+
# resp.properties.export_labels_task_run_properties.output_s3_path #=> String
|
3977
|
+
# resp.properties.labeling_set_generation_task_run_properties.output_s3_path #=> String
|
3978
|
+
# resp.properties.find_matches_task_run_properties.job_id #=> String
|
3979
|
+
# resp.properties.find_matches_task_run_properties.job_name #=> String
|
3980
|
+
# resp.properties.find_matches_task_run_properties.job_run_id #=> String
|
3981
|
+
# resp.error_string #=> String
|
3982
|
+
# resp.started_on #=> Time
|
3983
|
+
# resp.last_modified_on #=> Time
|
3984
|
+
# resp.completed_on #=> Time
|
3985
|
+
# resp.execution_time #=> Integer
|
3986
|
+
#
|
3987
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetMLTaskRun AWS API Documentation
|
3988
|
+
#
|
3989
|
+
# @overload get_ml_task_run(params = {})
|
3990
|
+
# @param [Hash] params ({})
|
3991
|
+
def get_ml_task_run(params = {}, options = {})
|
3992
|
+
req = build_request(:get_ml_task_run, params)
|
3993
|
+
req.send_request(options)
|
3994
|
+
end
|
3995
|
+
|
3996
|
+
# Gets a list of runs for a machine learning transform. Machine learning
|
3997
|
+
# task runs are asynchronous tasks that AWS Glue runs on your behalf as
|
3998
|
+
# part of various machine learning workflows. You can get a sortable,
|
3999
|
+
# filterable list of machine learning task runs by calling
|
4000
|
+
# `GetMLTaskRuns` with their parent transform's `TransformID` and other
|
4001
|
+
# optional parameters as documented in this section.
|
4002
|
+
#
|
4003
|
+
# This operation returns a list of historic runs and must be paginated.
|
4004
|
+
#
|
4005
|
+
# @option params [required, String] :transform_id
|
4006
|
+
# The unique identifier of the machine learning transform.
|
4007
|
+
#
|
4008
|
+
# @option params [String] :next_token
|
4009
|
+
# A token for pagination of the results. The default is empty.
|
4010
|
+
#
|
4011
|
+
# @option params [Integer] :max_results
|
4012
|
+
# The maximum number of results to return.
|
4013
|
+
#
|
4014
|
+
# @option params [Types::TaskRunFilterCriteria] :filter
|
4015
|
+
# The filter criteria, in the `TaskRunFilterCriteria` structure, for the
|
4016
|
+
# task run.
|
4017
|
+
#
|
4018
|
+
# @option params [Types::TaskRunSortCriteria] :sort
|
4019
|
+
# The sorting criteria, in the `TaskRunSortCriteria` structure, for the
|
4020
|
+
# task run.
|
4021
|
+
#
|
4022
|
+
# @return [Types::GetMLTaskRunsResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
4023
|
+
#
|
4024
|
+
# * {Types::GetMLTaskRunsResponse#task_runs #task_runs} => Array<Types::TaskRun>
|
4025
|
+
# * {Types::GetMLTaskRunsResponse#next_token #next_token} => String
|
4026
|
+
#
|
4027
|
+
# @example Request syntax with placeholder values
|
4028
|
+
#
|
4029
|
+
# resp = client.get_ml_task_runs({
|
4030
|
+
# transform_id: "HashString", # required
|
4031
|
+
# next_token: "PaginationToken",
|
4032
|
+
# max_results: 1,
|
4033
|
+
# filter: {
|
4034
|
+
# task_run_type: "EVALUATION", # accepts EVALUATION, LABELING_SET_GENERATION, IMPORT_LABELS, EXPORT_LABELS, FIND_MATCHES
|
4035
|
+
# status: "STARTING", # accepts STARTING, RUNNING, STOPPING, STOPPED, SUCCEEDED, FAILED, TIMEOUT
|
4036
|
+
# started_before: Time.now,
|
4037
|
+
# started_after: Time.now,
|
4038
|
+
# },
|
4039
|
+
# sort: {
|
4040
|
+
# column: "TASK_RUN_TYPE", # required, accepts TASK_RUN_TYPE, STATUS, STARTED
|
4041
|
+
# sort_direction: "DESCENDING", # required, accepts DESCENDING, ASCENDING
|
4042
|
+
# },
|
4043
|
+
# })
|
4044
|
+
#
|
4045
|
+
# @example Response structure
|
4046
|
+
#
|
4047
|
+
# resp.task_runs #=> Array
|
4048
|
+
# resp.task_runs[0].transform_id #=> String
|
4049
|
+
# resp.task_runs[0].task_run_id #=> String
|
4050
|
+
# resp.task_runs[0].status #=> String, one of "STARTING", "RUNNING", "STOPPING", "STOPPED", "SUCCEEDED", "FAILED", "TIMEOUT"
|
4051
|
+
# resp.task_runs[0].log_group_name #=> String
|
4052
|
+
# resp.task_runs[0].properties.task_type #=> String, one of "EVALUATION", "LABELING_SET_GENERATION", "IMPORT_LABELS", "EXPORT_LABELS", "FIND_MATCHES"
|
4053
|
+
# resp.task_runs[0].properties.import_labels_task_run_properties.input_s3_path #=> String
|
4054
|
+
# resp.task_runs[0].properties.import_labels_task_run_properties.replace #=> Boolean
|
4055
|
+
# resp.task_runs[0].properties.export_labels_task_run_properties.output_s3_path #=> String
|
4056
|
+
# resp.task_runs[0].properties.labeling_set_generation_task_run_properties.output_s3_path #=> String
|
4057
|
+
# resp.task_runs[0].properties.find_matches_task_run_properties.job_id #=> String
|
4058
|
+
# resp.task_runs[0].properties.find_matches_task_run_properties.job_name #=> String
|
4059
|
+
# resp.task_runs[0].properties.find_matches_task_run_properties.job_run_id #=> String
|
4060
|
+
# resp.task_runs[0].error_string #=> String
|
4061
|
+
# resp.task_runs[0].started_on #=> Time
|
4062
|
+
# resp.task_runs[0].last_modified_on #=> Time
|
4063
|
+
# resp.task_runs[0].completed_on #=> Time
|
4064
|
+
# resp.task_runs[0].execution_time #=> Integer
|
4065
|
+
# resp.next_token #=> String
|
4066
|
+
#
|
4067
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetMLTaskRuns AWS API Documentation
|
4068
|
+
#
|
4069
|
+
# @overload get_ml_task_runs(params = {})
|
4070
|
+
# @param [Hash] params ({})
|
4071
|
+
def get_ml_task_runs(params = {}, options = {})
|
4072
|
+
req = build_request(:get_ml_task_runs, params)
|
4073
|
+
req.send_request(options)
|
4074
|
+
end
|
4075
|
+
|
4076
|
+
# Gets an AWS Glue machine learning transform artifact and all its
|
4077
|
+
# corresponding metadata. Machine learning transforms are a special type
|
4078
|
+
# of transform that use machine learning to learn the details of the
|
4079
|
+
# transformation to be performed by learning from examples provided by
|
4080
|
+
# humans. These transformations are then saved by AWS Glue. You can
|
4081
|
+
# retrieve their metadata by calling `GetMLTransform`.
|
4082
|
+
#
|
4083
|
+
# @option params [required, String] :transform_id
|
4084
|
+
# The unique identifier of the transform, generated at the time that the
|
4085
|
+
# transform was created.
|
4086
|
+
#
|
4087
|
+
# @return [Types::GetMLTransformResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
4088
|
+
#
|
4089
|
+
# * {Types::GetMLTransformResponse#transform_id #transform_id} => String
|
4090
|
+
# * {Types::GetMLTransformResponse#name #name} => String
|
4091
|
+
# * {Types::GetMLTransformResponse#description #description} => String
|
4092
|
+
# * {Types::GetMLTransformResponse#status #status} => String
|
4093
|
+
# * {Types::GetMLTransformResponse#created_on #created_on} => Time
|
4094
|
+
# * {Types::GetMLTransformResponse#last_modified_on #last_modified_on} => Time
|
4095
|
+
# * {Types::GetMLTransformResponse#input_record_tables #input_record_tables} => Array<Types::GlueTable>
|
4096
|
+
# * {Types::GetMLTransformResponse#parameters #parameters} => Types::TransformParameters
|
4097
|
+
# * {Types::GetMLTransformResponse#evaluation_metrics #evaluation_metrics} => Types::EvaluationMetrics
|
4098
|
+
# * {Types::GetMLTransformResponse#label_count #label_count} => Integer
|
4099
|
+
# * {Types::GetMLTransformResponse#schema #schema} => Array<Types::SchemaColumn>
|
4100
|
+
# * {Types::GetMLTransformResponse#role #role} => String
|
4101
|
+
# * {Types::GetMLTransformResponse#max_capacity #max_capacity} => Float
|
4102
|
+
# * {Types::GetMLTransformResponse#worker_type #worker_type} => String
|
4103
|
+
# * {Types::GetMLTransformResponse#number_of_workers #number_of_workers} => Integer
|
4104
|
+
# * {Types::GetMLTransformResponse#timeout #timeout} => Integer
|
4105
|
+
# * {Types::GetMLTransformResponse#max_retries #max_retries} => Integer
|
4106
|
+
#
|
4107
|
+
# @example Request syntax with placeholder values
|
4108
|
+
#
|
4109
|
+
# resp = client.get_ml_transform({
|
4110
|
+
# transform_id: "HashString", # required
|
4111
|
+
# })
|
4112
|
+
#
|
4113
|
+
# @example Response structure
|
4114
|
+
#
|
4115
|
+
# resp.transform_id #=> String
|
4116
|
+
# resp.name #=> String
|
4117
|
+
# resp.description #=> String
|
4118
|
+
# resp.status #=> String, one of "NOT_READY", "READY", "DELETING"
|
4119
|
+
# resp.created_on #=> Time
|
4120
|
+
# resp.last_modified_on #=> Time
|
4121
|
+
# resp.input_record_tables #=> Array
|
4122
|
+
# resp.input_record_tables[0].database_name #=> String
|
4123
|
+
# resp.input_record_tables[0].table_name #=> String
|
4124
|
+
# resp.input_record_tables[0].catalog_id #=> String
|
4125
|
+
# resp.input_record_tables[0].connection_name #=> String
|
4126
|
+
# resp.parameters.transform_type #=> String, one of "FIND_MATCHES"
|
4127
|
+
# resp.parameters.find_matches_parameters.primary_key_column_name #=> String
|
4128
|
+
# resp.parameters.find_matches_parameters.precision_recall_tradeoff #=> Float
|
4129
|
+
# resp.parameters.find_matches_parameters.accuracy_cost_tradeoff #=> Float
|
4130
|
+
# resp.parameters.find_matches_parameters.enforce_provided_labels #=> Boolean
|
4131
|
+
# resp.evaluation_metrics.transform_type #=> String, one of "FIND_MATCHES"
|
4132
|
+
# resp.evaluation_metrics.find_matches_metrics.area_under_pr_curve #=> Float
|
4133
|
+
# resp.evaluation_metrics.find_matches_metrics.precision #=> Float
|
4134
|
+
# resp.evaluation_metrics.find_matches_metrics.recall #=> Float
|
4135
|
+
# resp.evaluation_metrics.find_matches_metrics.f1 #=> Float
|
4136
|
+
# resp.evaluation_metrics.find_matches_metrics.confusion_matrix.num_true_positives #=> Integer
|
4137
|
+
# resp.evaluation_metrics.find_matches_metrics.confusion_matrix.num_false_positives #=> Integer
|
4138
|
+
# resp.evaluation_metrics.find_matches_metrics.confusion_matrix.num_true_negatives #=> Integer
|
4139
|
+
# resp.evaluation_metrics.find_matches_metrics.confusion_matrix.num_false_negatives #=> Integer
|
4140
|
+
# resp.label_count #=> Integer
|
4141
|
+
# resp.schema #=> Array
|
4142
|
+
# resp.schema[0].name #=> String
|
4143
|
+
# resp.schema[0].data_type #=> String
|
4144
|
+
# resp.role #=> String
|
4145
|
+
# resp.max_capacity #=> Float
|
4146
|
+
# resp.worker_type #=> String, one of "Standard", "G.1X", "G.2X"
|
4147
|
+
# resp.number_of_workers #=> Integer
|
4148
|
+
# resp.timeout #=> Integer
|
4149
|
+
# resp.max_retries #=> Integer
|
4150
|
+
#
|
4151
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetMLTransform AWS API Documentation
|
4152
|
+
#
|
4153
|
+
# @overload get_ml_transform(params = {})
|
4154
|
+
# @param [Hash] params ({})
|
4155
|
+
def get_ml_transform(params = {}, options = {})
|
4156
|
+
req = build_request(:get_ml_transform, params)
|
4157
|
+
req.send_request(options)
|
4158
|
+
end
|
4159
|
+
|
4160
|
+
# Gets a sortable, filterable list of existing AWS Glue machine learning
|
4161
|
+
# transforms. Machine learning transforms are a special type of
|
4162
|
+
# transform that use machine learning to learn the details of the
|
4163
|
+
# transformation to be performed by learning from examples provided by
|
4164
|
+
# humans. These transformations are then saved by AWS Glue, and you can
|
4165
|
+
# retrieve their metadata by calling `GetMLTransforms`.
|
4166
|
+
#
|
4167
|
+
# @option params [String] :next_token
|
4168
|
+
# A paginated token to offset the results.
|
4169
|
+
#
|
4170
|
+
# @option params [Integer] :max_results
|
4171
|
+
# The maximum number of results to return.
|
4172
|
+
#
|
4173
|
+
# @option params [Types::TransformFilterCriteria] :filter
|
4174
|
+
# The filter transformation criteria.
|
4175
|
+
#
|
4176
|
+
# @option params [Types::TransformSortCriteria] :sort
|
4177
|
+
# The sorting criteria.
|
4178
|
+
#
|
4179
|
+
# @return [Types::GetMLTransformsResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
4180
|
+
#
|
4181
|
+
# * {Types::GetMLTransformsResponse#transforms #transforms} => Array<Types::MLTransform>
|
4182
|
+
# * {Types::GetMLTransformsResponse#next_token #next_token} => String
|
4183
|
+
#
|
4184
|
+
# @example Request syntax with placeholder values
|
4185
|
+
#
|
4186
|
+
# resp = client.get_ml_transforms({
|
4187
|
+
# next_token: "PaginationToken",
|
4188
|
+
# max_results: 1,
|
4189
|
+
# filter: {
|
4190
|
+
# name: "NameString",
|
4191
|
+
# transform_type: "FIND_MATCHES", # accepts FIND_MATCHES
|
4192
|
+
# status: "NOT_READY", # accepts NOT_READY, READY, DELETING
|
4193
|
+
# created_before: Time.now,
|
4194
|
+
# created_after: Time.now,
|
4195
|
+
# last_modified_before: Time.now,
|
4196
|
+
# last_modified_after: Time.now,
|
4197
|
+
# schema: [
|
4198
|
+
# {
|
4199
|
+
# name: "ColumnNameString",
|
4200
|
+
# data_type: "ColumnTypeString",
|
4201
|
+
# },
|
4202
|
+
# ],
|
4203
|
+
# },
|
4204
|
+
# sort: {
|
4205
|
+
# column: "NAME", # required, accepts NAME, TRANSFORM_TYPE, STATUS, CREATED, LAST_MODIFIED
|
4206
|
+
# sort_direction: "DESCENDING", # required, accepts DESCENDING, ASCENDING
|
4207
|
+
# },
|
4208
|
+
# })
|
4209
|
+
#
|
4210
|
+
# @example Response structure
|
4211
|
+
#
|
4212
|
+
# resp.transforms #=> Array
|
4213
|
+
# resp.transforms[0].transform_id #=> String
|
4214
|
+
# resp.transforms[0].name #=> String
|
4215
|
+
# resp.transforms[0].description #=> String
|
4216
|
+
# resp.transforms[0].status #=> String, one of "NOT_READY", "READY", "DELETING"
|
4217
|
+
# resp.transforms[0].created_on #=> Time
|
4218
|
+
# resp.transforms[0].last_modified_on #=> Time
|
4219
|
+
# resp.transforms[0].input_record_tables #=> Array
|
4220
|
+
# resp.transforms[0].input_record_tables[0].database_name #=> String
|
4221
|
+
# resp.transforms[0].input_record_tables[0].table_name #=> String
|
4222
|
+
# resp.transforms[0].input_record_tables[0].catalog_id #=> String
|
4223
|
+
# resp.transforms[0].input_record_tables[0].connection_name #=> String
|
4224
|
+
# resp.transforms[0].parameters.transform_type #=> String, one of "FIND_MATCHES"
|
4225
|
+
# resp.transforms[0].parameters.find_matches_parameters.primary_key_column_name #=> String
|
4226
|
+
# resp.transforms[0].parameters.find_matches_parameters.precision_recall_tradeoff #=> Float
|
4227
|
+
# resp.transforms[0].parameters.find_matches_parameters.accuracy_cost_tradeoff #=> Float
|
4228
|
+
# resp.transforms[0].parameters.find_matches_parameters.enforce_provided_labels #=> Boolean
|
4229
|
+
# resp.transforms[0].evaluation_metrics.transform_type #=> String, one of "FIND_MATCHES"
|
4230
|
+
# resp.transforms[0].evaluation_metrics.find_matches_metrics.area_under_pr_curve #=> Float
|
4231
|
+
# resp.transforms[0].evaluation_metrics.find_matches_metrics.precision #=> Float
|
4232
|
+
# resp.transforms[0].evaluation_metrics.find_matches_metrics.recall #=> Float
|
4233
|
+
# resp.transforms[0].evaluation_metrics.find_matches_metrics.f1 #=> Float
|
4234
|
+
# resp.transforms[0].evaluation_metrics.find_matches_metrics.confusion_matrix.num_true_positives #=> Integer
|
4235
|
+
# resp.transforms[0].evaluation_metrics.find_matches_metrics.confusion_matrix.num_false_positives #=> Integer
|
4236
|
+
# resp.transforms[0].evaluation_metrics.find_matches_metrics.confusion_matrix.num_true_negatives #=> Integer
|
4237
|
+
# resp.transforms[0].evaluation_metrics.find_matches_metrics.confusion_matrix.num_false_negatives #=> Integer
|
4238
|
+
# resp.transforms[0].label_count #=> Integer
|
4239
|
+
# resp.transforms[0].schema #=> Array
|
4240
|
+
# resp.transforms[0].schema[0].name #=> String
|
4241
|
+
# resp.transforms[0].schema[0].data_type #=> String
|
4242
|
+
# resp.transforms[0].role #=> String
|
4243
|
+
# resp.transforms[0].max_capacity #=> Float
|
4244
|
+
# resp.transforms[0].worker_type #=> String, one of "Standard", "G.1X", "G.2X"
|
4245
|
+
# resp.transforms[0].number_of_workers #=> Integer
|
4246
|
+
# resp.transforms[0].timeout #=> Integer
|
4247
|
+
# resp.transforms[0].max_retries #=> Integer
|
4248
|
+
# resp.next_token #=> String
|
4249
|
+
#
|
4250
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetMLTransforms AWS API Documentation
|
4251
|
+
#
|
4252
|
+
# @overload get_ml_transforms(params = {})
|
4253
|
+
# @param [Hash] params ({})
|
4254
|
+
def get_ml_transforms(params = {}, options = {})
|
4255
|
+
req = build_request(:get_ml_transforms, params)
|
4256
|
+
req.send_request(options)
|
4257
|
+
end
|
4258
|
+
|
3701
4259
|
# Creates mappings.
|
3702
4260
|
#
|
3703
4261
|
# @option params [required, Types::CatalogEntry] :source
|
@@ -3774,7 +4332,7 @@ module Aws::Glue
|
|
3774
4332
|
#
|
3775
4333
|
# @option params [String] :catalog_id
|
3776
4334
|
# The ID of the Data Catalog where the partition in question resides. If
|
3777
|
-
# none is
|
4335
|
+
# none is provided, the AWS account ID is used by default.
|
3778
4336
|
#
|
3779
4337
|
# @option params [required, String] :database_name
|
3780
4338
|
# The name of the catalog database where the partition resides.
|
@@ -3810,6 +4368,8 @@ module Aws::Glue
|
|
3810
4368
|
# resp.partition.storage_descriptor.columns[0].name #=> String
|
3811
4369
|
# resp.partition.storage_descriptor.columns[0].type #=> String
|
3812
4370
|
# resp.partition.storage_descriptor.columns[0].comment #=> String
|
4371
|
+
# resp.partition.storage_descriptor.columns[0].parameters #=> Hash
|
4372
|
+
# resp.partition.storage_descriptor.columns[0].parameters["KeyString"] #=> String
|
3813
4373
|
# resp.partition.storage_descriptor.location #=> String
|
3814
4374
|
# resp.partition.storage_descriptor.input_format #=> String
|
3815
4375
|
# resp.partition.storage_descriptor.output_format #=> String
|
@@ -3850,7 +4410,7 @@ module Aws::Glue
|
|
3850
4410
|
#
|
3851
4411
|
# @option params [String] :catalog_id
|
3852
4412
|
# The ID of the Data Catalog where the partitions in question reside. If
|
3853
|
-
# none is
|
4413
|
+
# none is provided, the AWS account ID is used by default.
|
3854
4414
|
#
|
3855
4415
|
# @option params [required, String] :database_name
|
3856
4416
|
# The name of the catalog database where the partitions reside.
|
@@ -3859,7 +4419,7 @@ module Aws::Glue
|
|
3859
4419
|
# The name of the partitions' table.
|
3860
4420
|
#
|
3861
4421
|
# @option params [String] :expression
|
3862
|
-
# An expression
|
4422
|
+
# An expression that filters the partitions to be returned.
|
3863
4423
|
#
|
3864
4424
|
# The expression uses SQL syntax similar to the SQL `WHERE` filter
|
3865
4425
|
# clause. The SQL statement parser [JSQLParser][1] parses the
|
@@ -3870,7 +4430,7 @@ module Aws::Glue
|
|
3870
4430
|
#
|
3871
4431
|
# =
|
3872
4432
|
#
|
3873
|
-
# : Checks
|
4433
|
+
# : Checks whether the values of the two operands are equal; if yes,
|
3874
4434
|
# then the condition becomes true.
|
3875
4435
|
#
|
3876
4436
|
# Example: Assume 'variable a' holds 10 and 'variable b' holds 20.
|
@@ -3879,37 +4439,38 @@ module Aws::Glue
|
|
3879
4439
|
#
|
3880
4440
|
# < >
|
3881
4441
|
#
|
3882
|
-
# : Checks
|
4442
|
+
# : Checks whether the values of two operands are equal; if the values
|
3883
4443
|
# are not equal, then the condition becomes true.
|
3884
4444
|
#
|
3885
4445
|
# Example: (a < > b) is true.
|
3886
4446
|
#
|
3887
4447
|
# >
|
3888
4448
|
#
|
3889
|
-
# : Checks
|
3890
|
-
# the right operand; if yes, then the condition becomes true.
|
4449
|
+
# : Checks whether the value of the left operand is greater than the
|
4450
|
+
# value of the right operand; if yes, then the condition becomes true.
|
3891
4451
|
#
|
3892
4452
|
# Example: (a > b) is not true.
|
3893
4453
|
#
|
3894
4454
|
# <
|
3895
4455
|
#
|
3896
|
-
# : Checks
|
3897
|
-
# the right operand; if yes, then the condition becomes true.
|
4456
|
+
# : Checks whether the value of the left operand is less than the value
|
4457
|
+
# of the right operand; if yes, then the condition becomes true.
|
3898
4458
|
#
|
3899
4459
|
# Example: (a < b) is true.
|
3900
4460
|
#
|
3901
4461
|
# >=
|
3902
4462
|
#
|
3903
|
-
# : Checks
|
3904
|
-
# the value of the right operand; if yes, then the condition
|
3905
|
-
# true.
|
4463
|
+
# : Checks whether the value of the left operand is greater than or
|
4464
|
+
# equal to the value of the right operand; if yes, then the condition
|
4465
|
+
# becomes true.
|
3906
4466
|
#
|
3907
4467
|
# Example: (a >= b) is not true.
|
3908
4468
|
#
|
3909
4469
|
# <=
|
3910
4470
|
#
|
3911
|
-
# : Checks
|
3912
|
-
# value of the right operand; if yes, then the condition
|
4471
|
+
# : Checks whether the value of the left operand is less than or equal
|
4472
|
+
# to the value of the right operand; if yes, then the condition
|
4473
|
+
# becomes true.
|
3913
4474
|
#
|
3914
4475
|
# Example: (a <= b) is true.
|
3915
4476
|
#
|
@@ -3917,7 +4478,7 @@ module Aws::Glue
|
|
3917
4478
|
#
|
3918
4479
|
# : Logical operators.
|
3919
4480
|
#
|
3920
|
-
# *Supported Partition Key Types*\: The following are the
|
4481
|
+
# *Supported Partition Key Types*\: The following are the supported
|
3921
4482
|
# partition keys.
|
3922
4483
|
#
|
3923
4484
|
# * `string`
|
@@ -3993,6 +4554,8 @@ module Aws::Glue
|
|
3993
4554
|
# resp.partitions[0].storage_descriptor.columns[0].name #=> String
|
3994
4555
|
# resp.partitions[0].storage_descriptor.columns[0].type #=> String
|
3995
4556
|
# resp.partitions[0].storage_descriptor.columns[0].comment #=> String
|
4557
|
+
# resp.partitions[0].storage_descriptor.columns[0].parameters #=> Hash
|
4558
|
+
# resp.partitions[0].storage_descriptor.columns[0].parameters["KeyString"] #=> String
|
3996
4559
|
# resp.partitions[0].storage_descriptor.location #=> String
|
3997
4560
|
# resp.partitions[0].storage_descriptor.input_format #=> String
|
3998
4561
|
# resp.partitions[0].storage_descriptor.output_format #=> String
|
@@ -4224,7 +4787,7 @@ module Aws::Glue
|
|
4224
4787
|
#
|
4225
4788
|
# @option params [String] :catalog_id
|
4226
4789
|
# The ID of the Data Catalog where the table resides. If none is
|
4227
|
-
#
|
4790
|
+
# provided, the AWS account ID is used by default.
|
4228
4791
|
#
|
4229
4792
|
# @option params [required, String] :database_name
|
4230
4793
|
# The name of the database in the catalog in which the table resides.
|
@@ -4261,6 +4824,8 @@ module Aws::Glue
|
|
4261
4824
|
# resp.table.storage_descriptor.columns[0].name #=> String
|
4262
4825
|
# resp.table.storage_descriptor.columns[0].type #=> String
|
4263
4826
|
# resp.table.storage_descriptor.columns[0].comment #=> String
|
4827
|
+
# resp.table.storage_descriptor.columns[0].parameters #=> Hash
|
4828
|
+
# resp.table.storage_descriptor.columns[0].parameters["KeyString"] #=> String
|
4264
4829
|
# resp.table.storage_descriptor.location #=> String
|
4265
4830
|
# resp.table.storage_descriptor.input_format #=> String
|
4266
4831
|
# resp.table.storage_descriptor.output_format #=> String
|
@@ -4288,12 +4853,15 @@ module Aws::Glue
|
|
4288
4853
|
# resp.table.partition_keys[0].name #=> String
|
4289
4854
|
# resp.table.partition_keys[0].type #=> String
|
4290
4855
|
# resp.table.partition_keys[0].comment #=> String
|
4856
|
+
# resp.table.partition_keys[0].parameters #=> Hash
|
4857
|
+
# resp.table.partition_keys[0].parameters["KeyString"] #=> String
|
4291
4858
|
# resp.table.view_original_text #=> String
|
4292
4859
|
# resp.table.view_expanded_text #=> String
|
4293
4860
|
# resp.table.table_type #=> String
|
4294
4861
|
# resp.table.parameters #=> Hash
|
4295
4862
|
# resp.table.parameters["KeyString"] #=> String
|
4296
4863
|
# resp.table.created_by #=> String
|
4864
|
+
# resp.table.is_registered_with_lake_formation #=> Boolean
|
4297
4865
|
#
|
4298
4866
|
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetTable AWS API Documentation
|
4299
4867
|
#
|
@@ -4308,7 +4876,7 @@ module Aws::Glue
|
|
4308
4876
|
#
|
4309
4877
|
# @option params [String] :catalog_id
|
4310
4878
|
# The ID of the Data Catalog where the tables reside. If none is
|
4311
|
-
#
|
4879
|
+
# provided, the AWS account ID is used by default.
|
4312
4880
|
#
|
4313
4881
|
# @option params [required, String] :database_name
|
4314
4882
|
# The database in the catalog in which the table resides. For Hive
|
@@ -4350,6 +4918,8 @@ module Aws::Glue
|
|
4350
4918
|
# resp.table_version.table.storage_descriptor.columns[0].name #=> String
|
4351
4919
|
# resp.table_version.table.storage_descriptor.columns[0].type #=> String
|
4352
4920
|
# resp.table_version.table.storage_descriptor.columns[0].comment #=> String
|
4921
|
+
# resp.table_version.table.storage_descriptor.columns[0].parameters #=> Hash
|
4922
|
+
# resp.table_version.table.storage_descriptor.columns[0].parameters["KeyString"] #=> String
|
4353
4923
|
# resp.table_version.table.storage_descriptor.location #=> String
|
4354
4924
|
# resp.table_version.table.storage_descriptor.input_format #=> String
|
4355
4925
|
# resp.table_version.table.storage_descriptor.output_format #=> String
|
@@ -4377,12 +4947,15 @@ module Aws::Glue
|
|
4377
4947
|
# resp.table_version.table.partition_keys[0].name #=> String
|
4378
4948
|
# resp.table_version.table.partition_keys[0].type #=> String
|
4379
4949
|
# resp.table_version.table.partition_keys[0].comment #=> String
|
4950
|
+
# resp.table_version.table.partition_keys[0].parameters #=> Hash
|
4951
|
+
# resp.table_version.table.partition_keys[0].parameters["KeyString"] #=> String
|
4380
4952
|
# resp.table_version.table.view_original_text #=> String
|
4381
4953
|
# resp.table_version.table.view_expanded_text #=> String
|
4382
4954
|
# resp.table_version.table.table_type #=> String
|
4383
4955
|
# resp.table_version.table.parameters #=> Hash
|
4384
4956
|
# resp.table_version.table.parameters["KeyString"] #=> String
|
4385
4957
|
# resp.table_version.table.created_by #=> String
|
4958
|
+
# resp.table_version.table.is_registered_with_lake_formation #=> Boolean
|
4386
4959
|
# resp.table_version.version_id #=> String
|
4387
4960
|
#
|
4388
4961
|
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetTableVersion AWS API Documentation
|
@@ -4399,7 +4972,7 @@ module Aws::Glue
|
|
4399
4972
|
#
|
4400
4973
|
# @option params [String] :catalog_id
|
4401
4974
|
# The ID of the Data Catalog where the tables reside. If none is
|
4402
|
-
#
|
4975
|
+
# provided, the AWS account ID is used by default.
|
4403
4976
|
#
|
4404
4977
|
# @option params [required, String] :database_name
|
4405
4978
|
# The database in the catalog in which the table resides. For Hive
|
@@ -4446,6 +5019,8 @@ module Aws::Glue
|
|
4446
5019
|
# resp.table_versions[0].table.storage_descriptor.columns[0].name #=> String
|
4447
5020
|
# resp.table_versions[0].table.storage_descriptor.columns[0].type #=> String
|
4448
5021
|
# resp.table_versions[0].table.storage_descriptor.columns[0].comment #=> String
|
5022
|
+
# resp.table_versions[0].table.storage_descriptor.columns[0].parameters #=> Hash
|
5023
|
+
# resp.table_versions[0].table.storage_descriptor.columns[0].parameters["KeyString"] #=> String
|
4449
5024
|
# resp.table_versions[0].table.storage_descriptor.location #=> String
|
4450
5025
|
# resp.table_versions[0].table.storage_descriptor.input_format #=> String
|
4451
5026
|
# resp.table_versions[0].table.storage_descriptor.output_format #=> String
|
@@ -4473,12 +5048,15 @@ module Aws::Glue
|
|
4473
5048
|
# resp.table_versions[0].table.partition_keys[0].name #=> String
|
4474
5049
|
# resp.table_versions[0].table.partition_keys[0].type #=> String
|
4475
5050
|
# resp.table_versions[0].table.partition_keys[0].comment #=> String
|
5051
|
+
# resp.table_versions[0].table.partition_keys[0].parameters #=> Hash
|
5052
|
+
# resp.table_versions[0].table.partition_keys[0].parameters["KeyString"] #=> String
|
4476
5053
|
# resp.table_versions[0].table.view_original_text #=> String
|
4477
5054
|
# resp.table_versions[0].table.view_expanded_text #=> String
|
4478
5055
|
# resp.table_versions[0].table.table_type #=> String
|
4479
5056
|
# resp.table_versions[0].table.parameters #=> Hash
|
4480
5057
|
# resp.table_versions[0].table.parameters["KeyString"] #=> String
|
4481
5058
|
# resp.table_versions[0].table.created_by #=> String
|
5059
|
+
# resp.table_versions[0].table.is_registered_with_lake_formation #=> Boolean
|
4482
5060
|
# resp.table_versions[0].version_id #=> String
|
4483
5061
|
# resp.next_token #=> String
|
4484
5062
|
#
|
@@ -4496,7 +5074,7 @@ module Aws::Glue
|
|
4496
5074
|
#
|
4497
5075
|
# @option params [String] :catalog_id
|
4498
5076
|
# The ID of the Data Catalog where the tables reside. If none is
|
4499
|
-
#
|
5077
|
+
# provided, the AWS account ID is used by default.
|
4500
5078
|
#
|
4501
5079
|
# @option params [required, String] :database_name
|
4502
5080
|
# The database in the catalog whose tables to list. For Hive
|
@@ -4543,6 +5121,8 @@ module Aws::Glue
|
|
4543
5121
|
# resp.table_list[0].storage_descriptor.columns[0].name #=> String
|
4544
5122
|
# resp.table_list[0].storage_descriptor.columns[0].type #=> String
|
4545
5123
|
# resp.table_list[0].storage_descriptor.columns[0].comment #=> String
|
5124
|
+
# resp.table_list[0].storage_descriptor.columns[0].parameters #=> Hash
|
5125
|
+
# resp.table_list[0].storage_descriptor.columns[0].parameters["KeyString"] #=> String
|
4546
5126
|
# resp.table_list[0].storage_descriptor.location #=> String
|
4547
5127
|
# resp.table_list[0].storage_descriptor.input_format #=> String
|
4548
5128
|
# resp.table_list[0].storage_descriptor.output_format #=> String
|
@@ -4570,12 +5150,15 @@ module Aws::Glue
|
|
4570
5150
|
# resp.table_list[0].partition_keys[0].name #=> String
|
4571
5151
|
# resp.table_list[0].partition_keys[0].type #=> String
|
4572
5152
|
# resp.table_list[0].partition_keys[0].comment #=> String
|
5153
|
+
# resp.table_list[0].partition_keys[0].parameters #=> Hash
|
5154
|
+
# resp.table_list[0].partition_keys[0].parameters["KeyString"] #=> String
|
4573
5155
|
# resp.table_list[0].view_original_text #=> String
|
4574
5156
|
# resp.table_list[0].view_expanded_text #=> String
|
4575
5157
|
# resp.table_list[0].table_type #=> String
|
4576
5158
|
# resp.table_list[0].parameters #=> Hash
|
4577
5159
|
# resp.table_list[0].parameters["KeyString"] #=> String
|
4578
5160
|
# resp.table_list[0].created_by #=> String
|
5161
|
+
# resp.table_list[0].is_registered_with_lake_formation #=> Boolean
|
4579
5162
|
# resp.next_token #=> String
|
4580
5163
|
#
|
4581
5164
|
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetTables AWS API Documentation
|
@@ -4732,7 +5315,7 @@ module Aws::Glue
|
|
4732
5315
|
#
|
4733
5316
|
# @option params [String] :catalog_id
|
4734
5317
|
# The ID of the Data Catalog where the function to be retrieved is
|
4735
|
-
# located. If none is
|
5318
|
+
# located. If none is provided, the AWS account ID is used by default.
|
4736
5319
|
#
|
4737
5320
|
# @option params [required, String] :database_name
|
4738
5321
|
# The name of the catalog database where the function is located.
|
@@ -4772,11 +5355,11 @@ module Aws::Glue
|
|
4772
5355
|
req.send_request(options)
|
4773
5356
|
end
|
4774
5357
|
|
4775
|
-
# Retrieves
|
5358
|
+
# Retrieves multiple function definitions from the Data Catalog.
|
4776
5359
|
#
|
4777
5360
|
# @option params [String] :catalog_id
|
4778
5361
|
# The ID of the Data Catalog where the functions to be retrieved are
|
4779
|
-
# located. If none is
|
5362
|
+
# located. If none is provided, the AWS account ID is used by default.
|
4780
5363
|
#
|
4781
5364
|
# @option params [required, String] :database_name
|
4782
5365
|
# The name of the catalog database where the functions are located.
|
@@ -5263,7 +5846,7 @@ module Aws::Glue
|
|
5263
5846
|
req.send_request(options)
|
5264
5847
|
end
|
5265
5848
|
|
5266
|
-
# Imports an existing Athena Data Catalog to AWS Glue
|
5849
|
+
# Imports an existing Amazon Athena Data Catalog to AWS Glue
|
5267
5850
|
#
|
5268
5851
|
# @option params [String] :catalog_id
|
5269
5852
|
# The ID of the catalog to import. Currently, this should be the AWS
|
@@ -5525,9 +6108,8 @@ module Aws::Glue
|
|
5525
6108
|
# every catalog write thereafter.
|
5526
6109
|
#
|
5527
6110
|
# @option params [String] :catalog_id
|
5528
|
-
# The ID of the Data Catalog
|
5529
|
-
#
|
5530
|
-
# default.
|
6111
|
+
# The ID of the Data Catalog to set the security configuration for. If
|
6112
|
+
# none is provided, the AWS account ID is used by default.
|
5531
6113
|
#
|
5532
6114
|
# @option params [required, Types::DataCatalogEncryptionSettings] :data_catalog_encryption_settings
|
5533
6115
|
# The security configuration to set.
|
@@ -5674,6 +6256,134 @@ module Aws::Glue
|
|
5674
6256
|
req.send_request(options)
|
5675
6257
|
end
|
5676
6258
|
|
6259
|
+
# Searches a set of tables based on properties in the table metadata as
|
6260
|
+
# well as on the parent database. You can search against text or filter
|
6261
|
+
# conditions.
|
6262
|
+
#
|
6263
|
+
# You can only get tables that you have access to based on the security
|
6264
|
+
# policies defined in Lake Formation. You need at least a read-only
|
6265
|
+
# access to the table for it to be returned. If you do not have access
|
6266
|
+
# to all the columns in the table, these columns will not be searched
|
6267
|
+
# against when returning the list of tables back to you. If you have
|
6268
|
+
# access to the columns but not the data in the columns, those columns
|
6269
|
+
# and the associated metadata for those columns will be included in the
|
6270
|
+
# search.
|
6271
|
+
#
|
6272
|
+
# @option params [String] :catalog_id
|
6273
|
+
# A unique identifier, consisting of ` account_id/datalake`.
|
6274
|
+
#
|
6275
|
+
# @option params [String] :next_token
|
6276
|
+
# A continuation token, included if this is a continuation call.
|
6277
|
+
#
|
6278
|
+
# @option params [Array<Types::PropertyPredicate>] :filters
|
6279
|
+
# A list of key-value pairs, and a comparator used to filter the search
|
6280
|
+
# results. Returns all entities matching the predicate.
|
6281
|
+
#
|
6282
|
+
# @option params [String] :search_text
|
6283
|
+
# A string used for a text search.
|
6284
|
+
#
|
6285
|
+
# Specifying a value in quotes filters based on an exact match to the
|
6286
|
+
# value.
|
6287
|
+
#
|
6288
|
+
# @option params [Array<Types::SortCriterion>] :sort_criteria
|
6289
|
+
# A list of criteria for sorting the results by a field name, in an
|
6290
|
+
# ascending or descending order.
|
6291
|
+
#
|
6292
|
+
# @option params [Integer] :max_results
|
6293
|
+
# The maximum number of tables to return in a single response.
|
6294
|
+
#
|
6295
|
+
# @return [Types::SearchTablesResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
6296
|
+
#
|
6297
|
+
# * {Types::SearchTablesResponse#next_token #next_token} => String
|
6298
|
+
# * {Types::SearchTablesResponse#table_list #table_list} => Array<Types::Table>
|
6299
|
+
#
|
6300
|
+
# @example Request syntax with placeholder values
|
6301
|
+
#
|
6302
|
+
# resp = client.search_tables({
|
6303
|
+
# catalog_id: "CatalogIdString",
|
6304
|
+
# next_token: "Token",
|
6305
|
+
# filters: [
|
6306
|
+
# {
|
6307
|
+
# key: "ValueString",
|
6308
|
+
# value: "ValueString",
|
6309
|
+
# comparator: "EQUALS", # accepts EQUALS, GREATER_THAN, LESS_THAN, GREATER_THAN_EQUALS, LESS_THAN_EQUALS
|
6310
|
+
# },
|
6311
|
+
# ],
|
6312
|
+
# search_text: "ValueString",
|
6313
|
+
# sort_criteria: [
|
6314
|
+
# {
|
6315
|
+
# field_name: "ValueString",
|
6316
|
+
# sort: "ASC", # accepts ASC, DESC
|
6317
|
+
# },
|
6318
|
+
# ],
|
6319
|
+
# max_results: 1,
|
6320
|
+
# })
|
6321
|
+
#
|
6322
|
+
# @example Response structure
|
6323
|
+
#
|
6324
|
+
# resp.next_token #=> String
|
6325
|
+
# resp.table_list #=> Array
|
6326
|
+
# resp.table_list[0].name #=> String
|
6327
|
+
# resp.table_list[0].database_name #=> String
|
6328
|
+
# resp.table_list[0].description #=> String
|
6329
|
+
# resp.table_list[0].owner #=> String
|
6330
|
+
# resp.table_list[0].create_time #=> Time
|
6331
|
+
# resp.table_list[0].update_time #=> Time
|
6332
|
+
# resp.table_list[0].last_access_time #=> Time
|
6333
|
+
# resp.table_list[0].last_analyzed_time #=> Time
|
6334
|
+
# resp.table_list[0].retention #=> Integer
|
6335
|
+
# resp.table_list[0].storage_descriptor.columns #=> Array
|
6336
|
+
# resp.table_list[0].storage_descriptor.columns[0].name #=> String
|
6337
|
+
# resp.table_list[0].storage_descriptor.columns[0].type #=> String
|
6338
|
+
# resp.table_list[0].storage_descriptor.columns[0].comment #=> String
|
6339
|
+
# resp.table_list[0].storage_descriptor.columns[0].parameters #=> Hash
|
6340
|
+
# resp.table_list[0].storage_descriptor.columns[0].parameters["KeyString"] #=> String
|
6341
|
+
# resp.table_list[0].storage_descriptor.location #=> String
|
6342
|
+
# resp.table_list[0].storage_descriptor.input_format #=> String
|
6343
|
+
# resp.table_list[0].storage_descriptor.output_format #=> String
|
6344
|
+
# resp.table_list[0].storage_descriptor.compressed #=> Boolean
|
6345
|
+
# resp.table_list[0].storage_descriptor.number_of_buckets #=> Integer
|
6346
|
+
# resp.table_list[0].storage_descriptor.serde_info.name #=> String
|
6347
|
+
# resp.table_list[0].storage_descriptor.serde_info.serialization_library #=> String
|
6348
|
+
# resp.table_list[0].storage_descriptor.serde_info.parameters #=> Hash
|
6349
|
+
# resp.table_list[0].storage_descriptor.serde_info.parameters["KeyString"] #=> String
|
6350
|
+
# resp.table_list[0].storage_descriptor.bucket_columns #=> Array
|
6351
|
+
# resp.table_list[0].storage_descriptor.bucket_columns[0] #=> String
|
6352
|
+
# resp.table_list[0].storage_descriptor.sort_columns #=> Array
|
6353
|
+
# resp.table_list[0].storage_descriptor.sort_columns[0].column #=> String
|
6354
|
+
# resp.table_list[0].storage_descriptor.sort_columns[0].sort_order #=> Integer
|
6355
|
+
# resp.table_list[0].storage_descriptor.parameters #=> Hash
|
6356
|
+
# resp.table_list[0].storage_descriptor.parameters["KeyString"] #=> String
|
6357
|
+
# resp.table_list[0].storage_descriptor.skewed_info.skewed_column_names #=> Array
|
6358
|
+
# resp.table_list[0].storage_descriptor.skewed_info.skewed_column_names[0] #=> String
|
6359
|
+
# resp.table_list[0].storage_descriptor.skewed_info.skewed_column_values #=> Array
|
6360
|
+
# resp.table_list[0].storage_descriptor.skewed_info.skewed_column_values[0] #=> String
|
6361
|
+
# resp.table_list[0].storage_descriptor.skewed_info.skewed_column_value_location_maps #=> Hash
|
6362
|
+
# resp.table_list[0].storage_descriptor.skewed_info.skewed_column_value_location_maps["ColumnValuesString"] #=> String
|
6363
|
+
# resp.table_list[0].storage_descriptor.stored_as_sub_directories #=> Boolean
|
6364
|
+
# resp.table_list[0].partition_keys #=> Array
|
6365
|
+
# resp.table_list[0].partition_keys[0].name #=> String
|
6366
|
+
# resp.table_list[0].partition_keys[0].type #=> String
|
6367
|
+
# resp.table_list[0].partition_keys[0].comment #=> String
|
6368
|
+
# resp.table_list[0].partition_keys[0].parameters #=> Hash
|
6369
|
+
# resp.table_list[0].partition_keys[0].parameters["KeyString"] #=> String
|
6370
|
+
# resp.table_list[0].view_original_text #=> String
|
6371
|
+
# resp.table_list[0].view_expanded_text #=> String
|
6372
|
+
# resp.table_list[0].table_type #=> String
|
6373
|
+
# resp.table_list[0].parameters #=> Hash
|
6374
|
+
# resp.table_list[0].parameters["KeyString"] #=> String
|
6375
|
+
# resp.table_list[0].created_by #=> String
|
6376
|
+
# resp.table_list[0].is_registered_with_lake_formation #=> Boolean
|
6377
|
+
#
|
6378
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/SearchTables AWS API Documentation
|
6379
|
+
#
|
6380
|
+
# @overload search_tables(params = {})
|
6381
|
+
# @param [Hash] params ({})
|
6382
|
+
def search_tables(params = {}, options = {})
|
6383
|
+
req = build_request(:search_tables, params)
|
6384
|
+
req.send_request(options)
|
6385
|
+
end
|
6386
|
+
|
5677
6387
|
# Starts a crawl using the specified crawler, regardless of what is
|
5678
6388
|
# scheduled. If the crawler is already running, returns a
|
5679
6389
|
# [CrawlerRunningException][1].
|
@@ -5726,6 +6436,113 @@ module Aws::Glue
|
|
5726
6436
|
req.send_request(options)
|
5727
6437
|
end
|
5728
6438
|
|
6439
|
+
# Begins an asynchronous task to export all labeled data for a
|
6440
|
+
# particular transform. This task is the only label-related API call
|
6441
|
+
# that is not part of the typical active learning workflow. You
|
6442
|
+
# typically use `StartExportLabelsTaskRun` when you want to work with
|
6443
|
+
# all of your existing labels at the same time, such as when you want to
|
6444
|
+
# remove or change labels that were previously submitted as truth. This
|
6445
|
+
# API operation accepts the `TransformId` whose labels you want to
|
6446
|
+
# export and an Amazon Simple Storage Service (Amazon S3) path to export
|
6447
|
+
# the labels to. The operation returns a `TaskRunId`. You can check on
|
6448
|
+
# the status of your task run by calling the `GetMLTaskRun` API.
|
6449
|
+
#
|
6450
|
+
# @option params [required, String] :transform_id
|
6451
|
+
# The unique identifier of the machine learning transform.
|
6452
|
+
#
|
6453
|
+
# @option params [required, String] :output_s3_path
|
6454
|
+
# The Amazon S3 path where you export the labels.
|
6455
|
+
#
|
6456
|
+
# @return [Types::StartExportLabelsTaskRunResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
6457
|
+
#
|
6458
|
+
# * {Types::StartExportLabelsTaskRunResponse#task_run_id #task_run_id} => String
|
6459
|
+
#
|
6460
|
+
# @example Request syntax with placeholder values
|
6461
|
+
#
|
6462
|
+
# resp = client.start_export_labels_task_run({
|
6463
|
+
# transform_id: "HashString", # required
|
6464
|
+
# output_s3_path: "UriString", # required
|
6465
|
+
# })
|
6466
|
+
#
|
6467
|
+
# @example Response structure
|
6468
|
+
#
|
6469
|
+
# resp.task_run_id #=> String
|
6470
|
+
#
|
6471
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/StartExportLabelsTaskRun AWS API Documentation
|
6472
|
+
#
|
6473
|
+
# @overload start_export_labels_task_run(params = {})
|
6474
|
+
# @param [Hash] params ({})
|
6475
|
+
def start_export_labels_task_run(params = {}, options = {})
|
6476
|
+
req = build_request(:start_export_labels_task_run, params)
|
6477
|
+
req.send_request(options)
|
6478
|
+
end
|
6479
|
+
|
6480
|
+
# Enables you to provide additional labels (examples of truth) to be
|
6481
|
+
# used to teach the machine learning transform and improve its quality.
|
6482
|
+
# This API operation is generally used as part of the active learning
|
6483
|
+
# workflow that starts with the `StartMLLabelingSetGenerationTaskRun`
|
6484
|
+
# call and that ultimately results in improving the quality of your
|
6485
|
+
# machine learning transform.
|
6486
|
+
#
|
6487
|
+
# After the `StartMLLabelingSetGenerationTaskRun` finishes, AWS Glue
|
6488
|
+
# machine learning will have generated a series of questions for humans
|
6489
|
+
# to answer. (Answering these questions is often called 'labeling' in
|
6490
|
+
# the machine learning workflows). In the case of the `FindMatches`
|
6491
|
+
# transform, these questions are of the form, “What is the correct way
|
6492
|
+
# to group these rows together into groups composed entirely of matching
|
6493
|
+
# records?” After the labeling process is finished, users upload their
|
6494
|
+
# answers/labels with a call to `StartImportLabelsTaskRun`. After
|
6495
|
+
# `StartImportLabelsTaskRun` finishes, all future runs of the machine
|
6496
|
+
# learning transform use the new and improved labels and perform a
|
6497
|
+
# higher-quality transformation.
|
6498
|
+
#
|
6499
|
+
# By default, `StartMLLabelingSetGenerationTaskRun` continually learns
|
6500
|
+
# from and combines all labels that you upload unless you set `Replace`
|
6501
|
+
# to true. If you set `Replace` to true, `StartImportLabelsTaskRun`
|
6502
|
+
# deletes and forgets all previously uploaded labels and learns only
|
6503
|
+
# from the exact set that you upload. Replacing labels can be helpful if
|
6504
|
+
# you realize that you previously uploaded incorrect labels, and you
|
6505
|
+
# believe that they are having a negative effect on your transform
|
6506
|
+
# quality.
|
6507
|
+
#
|
6508
|
+
# You can check on the status of your task run by calling the
|
6509
|
+
# `GetMLTaskRun` operation.
|
6510
|
+
#
|
6511
|
+
# @option params [required, String] :transform_id
|
6512
|
+
# The unique identifier of the machine learning transform.
|
6513
|
+
#
|
6514
|
+
# @option params [required, String] :input_s3_path
|
6515
|
+
# The Amazon Simple Storage Service (Amazon S3) path from where you
|
6516
|
+
# import the labels.
|
6517
|
+
#
|
6518
|
+
# @option params [Boolean] :replace_all_labels
|
6519
|
+
# Indicates whether to overwrite your existing labels.
|
6520
|
+
#
|
6521
|
+
# @return [Types::StartImportLabelsTaskRunResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
6522
|
+
#
|
6523
|
+
# * {Types::StartImportLabelsTaskRunResponse#task_run_id #task_run_id} => String
|
6524
|
+
#
|
6525
|
+
# @example Request syntax with placeholder values
|
6526
|
+
#
|
6527
|
+
# resp = client.start_import_labels_task_run({
|
6528
|
+
# transform_id: "HashString", # required
|
6529
|
+
# input_s3_path: "UriString", # required
|
6530
|
+
# replace_all_labels: false,
|
6531
|
+
# })
|
6532
|
+
#
|
6533
|
+
# @example Response structure
|
6534
|
+
#
|
6535
|
+
# resp.task_run_id #=> String
|
6536
|
+
#
|
6537
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/StartImportLabelsTaskRun AWS API Documentation
|
6538
|
+
#
|
6539
|
+
# @overload start_import_labels_task_run(params = {})
|
6540
|
+
# @param [Hash] params ({})
|
6541
|
+
def start_import_labels_task_run(params = {}, options = {})
|
6542
|
+
req = build_request(:start_import_labels_task_run, params)
|
6543
|
+
req.send_request(options)
|
6544
|
+
end
|
6545
|
+
|
5729
6546
|
# Starts a job run using a job definition.
|
5730
6547
|
#
|
5731
6548
|
# @option params [required, String] :job_name
|
@@ -5861,6 +6678,90 @@ module Aws::Glue
|
|
5861
6678
|
req.send_request(options)
|
5862
6679
|
end
|
5863
6680
|
|
6681
|
+
# Starts a task to estimate the quality of the transform.
|
6682
|
+
#
|
6683
|
+
# When you provide label sets as examples of truth, AWS Glue machine
|
6684
|
+
# learning uses some of those examples to learn from them. The rest of
|
6685
|
+
# the labels are used as a test to estimate quality.
|
6686
|
+
#
|
6687
|
+
# Returns a unique identifier for the run. You can call `GetMLTaskRun`
|
6688
|
+
# to get more information about the stats of the `EvaluationTaskRun`.
|
6689
|
+
#
|
6690
|
+
# @option params [required, String] :transform_id
|
6691
|
+
# The unique identifier of the machine learning transform.
|
6692
|
+
#
|
6693
|
+
# @return [Types::StartMLEvaluationTaskRunResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
6694
|
+
#
|
6695
|
+
# * {Types::StartMLEvaluationTaskRunResponse#task_run_id #task_run_id} => String
|
6696
|
+
#
|
6697
|
+
# @example Request syntax with placeholder values
|
6698
|
+
#
|
6699
|
+
# resp = client.start_ml_evaluation_task_run({
|
6700
|
+
# transform_id: "HashString", # required
|
6701
|
+
# })
|
6702
|
+
#
|
6703
|
+
# @example Response structure
|
6704
|
+
#
|
6705
|
+
# resp.task_run_id #=> String
|
6706
|
+
#
|
6707
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/StartMLEvaluationTaskRun AWS API Documentation
|
6708
|
+
#
|
6709
|
+
# @overload start_ml_evaluation_task_run(params = {})
|
6710
|
+
# @param [Hash] params ({})
|
6711
|
+
def start_ml_evaluation_task_run(params = {}, options = {})
|
6712
|
+
req = build_request(:start_ml_evaluation_task_run, params)
|
6713
|
+
req.send_request(options)
|
6714
|
+
end
|
6715
|
+
|
6716
|
+
# Starts the active learning workflow for your machine learning
|
6717
|
+
# transform to improve the transform's quality by generating label sets
|
6718
|
+
# and adding labels.
|
6719
|
+
#
|
6720
|
+
# When the `StartMLLabelingSetGenerationTaskRun` finishes, AWS Glue will
|
6721
|
+
# have generated a "labeling set" or a set of questions for humans to
|
6722
|
+
# answer.
|
6723
|
+
#
|
6724
|
+
# In the case of the `FindMatches` transform, these questions are of the
|
6725
|
+
# form, “What is the correct way to group these rows together into
|
6726
|
+
# groups composed entirely of matching records?”
|
6727
|
+
#
|
6728
|
+
# After the labeling process is finished, you can upload your labels
|
6729
|
+
# with a call to `StartImportLabelsTaskRun`. After
|
6730
|
+
# `StartImportLabelsTaskRun` finishes, all future runs of the machine
|
6731
|
+
# learning transform will use the new and improved labels and perform a
|
6732
|
+
# higher-quality transformation.
|
6733
|
+
#
|
6734
|
+
# @option params [required, String] :transform_id
|
6735
|
+
# The unique identifier of the machine learning transform.
|
6736
|
+
#
|
6737
|
+
# @option params [required, String] :output_s3_path
|
6738
|
+
# The Amazon Simple Storage Service (Amazon S3) path where you generate
|
6739
|
+
# the labeling set.
|
6740
|
+
#
|
6741
|
+
# @return [Types::StartMLLabelingSetGenerationTaskRunResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
6742
|
+
#
|
6743
|
+
# * {Types::StartMLLabelingSetGenerationTaskRunResponse#task_run_id #task_run_id} => String
|
6744
|
+
#
|
6745
|
+
# @example Request syntax with placeholder values
|
6746
|
+
#
|
6747
|
+
# resp = client.start_ml_labeling_set_generation_task_run({
|
6748
|
+
# transform_id: "HashString", # required
|
6749
|
+
# output_s3_path: "UriString", # required
|
6750
|
+
# })
|
6751
|
+
#
|
6752
|
+
# @example Response structure
|
6753
|
+
#
|
6754
|
+
# resp.task_run_id #=> String
|
6755
|
+
#
|
6756
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/StartMLLabelingSetGenerationTaskRun AWS API Documentation
|
6757
|
+
#
|
6758
|
+
# @overload start_ml_labeling_set_generation_task_run(params = {})
|
6759
|
+
# @param [Hash] params ({})
|
6760
|
+
def start_ml_labeling_set_generation_task_run(params = {}, options = {})
|
6761
|
+
req = build_request(:start_ml_labeling_set_generation_task_run, params)
|
6762
|
+
req.send_request(options)
|
6763
|
+
end
|
6764
|
+
|
5864
6765
|
# Starts an existing trigger. See [Triggering Jobs][1] for information
|
5865
6766
|
# about how different types of trigger are started.
|
5866
6767
|
#
|
@@ -6310,7 +7211,7 @@ module Aws::Glue
|
|
6310
7211
|
#
|
6311
7212
|
# @option params [String] :catalog_id
|
6312
7213
|
# The ID of the Data Catalog in which the metadata database resides. If
|
6313
|
-
# none is
|
7214
|
+
# none is provided, the AWS account ID is used by default.
|
6314
7215
|
#
|
6315
7216
|
# @option params [required, String] :name
|
6316
7217
|
# The name of the database to update in the catalog. For Hive
|
@@ -6334,6 +7235,14 @@ module Aws::Glue
|
|
6334
7235
|
# parameters: {
|
6335
7236
|
# "KeyString" => "ParametersMapValue",
|
6336
7237
|
# },
|
7238
|
+
# create_table_default_permissions: [
|
7239
|
+
# {
|
7240
|
+
# principal: {
|
7241
|
+
# data_lake_principal_identifier: "DataLakePrincipalString",
|
7242
|
+
# },
|
7243
|
+
# permissions: ["ALL"], # accepts ALL, SELECT, ALTER, DROP, DELETE, INSERT, CREATE_DATABASE, CREATE_TABLE, DATA_LOCATION_ACCESS
|
7244
|
+
# },
|
7245
|
+
# ],
|
6337
7246
|
# },
|
6338
7247
|
# })
|
6339
7248
|
#
|
@@ -6465,24 +7374,130 @@ module Aws::Glue
|
|
6465
7374
|
req.send_request(options)
|
6466
7375
|
end
|
6467
7376
|
|
7377
|
+
# Updates an existing machine learning transform. Call this operation to
|
7378
|
+
# tune the algorithm parameters to achieve better results.
|
7379
|
+
#
|
7380
|
+
# After calling this operation, you can call the
|
7381
|
+
# `StartMLEvaluationTaskRun` operation to assess how well your new
|
7382
|
+
# parameters achieved your goals (such as improving the quality of your
|
7383
|
+
# machine learning transform, or making it more cost-effective).
|
7384
|
+
#
|
7385
|
+
# @option params [required, String] :transform_id
|
7386
|
+
# A unique identifier that was generated when the transform was created.
|
7387
|
+
#
|
7388
|
+
# @option params [String] :name
|
7389
|
+
# The unique name that you gave the transform when you created it.
|
7390
|
+
#
|
7391
|
+
# @option params [String] :description
|
7392
|
+
# A description of the transform. The default is an empty string.
|
7393
|
+
#
|
7394
|
+
# @option params [Types::TransformParameters] :parameters
|
7395
|
+
# The configuration parameters that are specific to the transform type
|
7396
|
+
# (algorithm) used. Conditionally dependent on the transform type.
|
7397
|
+
#
|
7398
|
+
# @option params [String] :role
|
7399
|
+
# The name or Amazon Resource Name (ARN) of the IAM role with the
|
7400
|
+
# required permissions.
|
7401
|
+
#
|
7402
|
+
# @option params [Float] :max_capacity
|
7403
|
+
# The number of AWS Glue data processing units (DPUs) that are allocated
|
7404
|
+
# to task runs for this transform. You can allocate from 2 to 100 DPUs;
|
7405
|
+
# the default is 10. A DPU is a relative measure of processing power
|
7406
|
+
# that consists of 4 vCPUs of compute capacity and 16 GB of memory. For
|
7407
|
+
# more information, see the [AWS Glue pricing page][1].
|
7408
|
+
#
|
7409
|
+
# When the `WorkerType` field is set to a value other than `Standard`,
|
7410
|
+
# the `MaxCapacity` field is set automatically and becomes read-only.
|
7411
|
+
#
|
7412
|
+
#
|
7413
|
+
#
|
7414
|
+
# [1]: https://aws.amazon.com/glue/pricing/
|
7415
|
+
#
|
7416
|
+
# @option params [String] :worker_type
|
7417
|
+
# The type of predefined worker that is allocated when this task runs.
|
7418
|
+
# Accepts a value of Standard, G.1X, or G.2X.
|
7419
|
+
#
|
7420
|
+
# * For the `Standard` worker type, each worker provides 4 vCPU, 16 GB
|
7421
|
+
# of memory and a 50GB disk, and 2 executors per worker.
|
7422
|
+
#
|
7423
|
+
# * For the `G.1X` worker type, each worker provides 4 vCPU, 16 GB of
|
7424
|
+
# memory and a 64GB disk, and 1 executor per worker.
|
7425
|
+
#
|
7426
|
+
# * For the `G.2X` worker type, each worker provides 8 vCPU, 32 GB of
|
7427
|
+
# memory and a 128GB disk, and 1 executor per worker.
|
7428
|
+
#
|
7429
|
+
# @option params [Integer] :number_of_workers
|
7430
|
+
# The number of workers of a defined `workerType` that are allocated
|
7431
|
+
# when this task runs.
|
7432
|
+
#
|
7433
|
+
# @option params [Integer] :timeout
|
7434
|
+
# The timeout for a task run for this transform in minutes. This is the
|
7435
|
+
# maximum time that a task run for this transform can consume resources
|
7436
|
+
# before it is terminated and enters `TIMEOUT` status. The default is
|
7437
|
+
# 2,880 minutes (48 hours).
|
7438
|
+
#
|
7439
|
+
# @option params [Integer] :max_retries
|
7440
|
+
# The maximum number of times to retry a task for this transform after a
|
7441
|
+
# task run fails.
|
7442
|
+
#
|
7443
|
+
# @return [Types::UpdateMLTransformResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
7444
|
+
#
|
7445
|
+
# * {Types::UpdateMLTransformResponse#transform_id #transform_id} => String
|
7446
|
+
#
|
7447
|
+
# @example Request syntax with placeholder values
|
7448
|
+
#
|
7449
|
+
# resp = client.update_ml_transform({
|
7450
|
+
# transform_id: "HashString", # required
|
7451
|
+
# name: "NameString",
|
7452
|
+
# description: "DescriptionString",
|
7453
|
+
# parameters: {
|
7454
|
+
# transform_type: "FIND_MATCHES", # required, accepts FIND_MATCHES
|
7455
|
+
# find_matches_parameters: {
|
7456
|
+
# primary_key_column_name: "ColumnNameString",
|
7457
|
+
# precision_recall_tradeoff: 1.0,
|
7458
|
+
# accuracy_cost_tradeoff: 1.0,
|
7459
|
+
# enforce_provided_labels: false,
|
7460
|
+
# },
|
7461
|
+
# },
|
7462
|
+
# role: "RoleString",
|
7463
|
+
# max_capacity: 1.0,
|
7464
|
+
# worker_type: "Standard", # accepts Standard, G.1X, G.2X
|
7465
|
+
# number_of_workers: 1,
|
7466
|
+
# timeout: 1,
|
7467
|
+
# max_retries: 1,
|
7468
|
+
# })
|
7469
|
+
#
|
7470
|
+
# @example Response structure
|
7471
|
+
#
|
7472
|
+
# resp.transform_id #=> String
|
7473
|
+
#
|
7474
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/UpdateMLTransform AWS API Documentation
|
7475
|
+
#
|
7476
|
+
# @overload update_ml_transform(params = {})
|
7477
|
+
# @param [Hash] params ({})
|
7478
|
+
def update_ml_transform(params = {}, options = {})
|
7479
|
+
req = build_request(:update_ml_transform, params)
|
7480
|
+
req.send_request(options)
|
7481
|
+
end
|
7482
|
+
|
6468
7483
|
# Updates a partition.
|
6469
7484
|
#
|
6470
7485
|
# @option params [String] :catalog_id
|
6471
7486
|
# The ID of the Data Catalog where the partition to be updated resides.
|
6472
|
-
# If none is
|
7487
|
+
# If none is provided, the AWS account ID is used by default.
|
6473
7488
|
#
|
6474
7489
|
# @option params [required, String] :database_name
|
6475
7490
|
# The name of the catalog database in which the table in question
|
6476
7491
|
# resides.
|
6477
7492
|
#
|
6478
7493
|
# @option params [required, String] :table_name
|
6479
|
-
# The name of the table
|
7494
|
+
# The name of the table in which the partition to be updated is located.
|
6480
7495
|
#
|
6481
7496
|
# @option params [required, Array<String>] :partition_value_list
|
6482
7497
|
# A list of the values defining the partition.
|
6483
7498
|
#
|
6484
7499
|
# @option params [required, Types::PartitionInput] :partition_input
|
6485
|
-
# The new partition object to
|
7500
|
+
# The new partition object to update the partition to.
|
6486
7501
|
#
|
6487
7502
|
# @return [Struct] Returns an empty {Seahorse::Client::Response response}.
|
6488
7503
|
#
|
@@ -6502,6 +7517,9 @@ module Aws::Glue
|
|
6502
7517
|
# name: "NameString", # required
|
6503
7518
|
# type: "ColumnTypeString",
|
6504
7519
|
# comment: "CommentString",
|
7520
|
+
# parameters: {
|
7521
|
+
# "KeyString" => "ParametersMapValue",
|
7522
|
+
# },
|
6505
7523
|
# },
|
6506
7524
|
# ],
|
6507
7525
|
# location: "LocationString",
|
@@ -6555,7 +7573,7 @@ module Aws::Glue
|
|
6555
7573
|
#
|
6556
7574
|
# @option params [String] :catalog_id
|
6557
7575
|
# The ID of the Data Catalog where the table resides. If none is
|
6558
|
-
#
|
7576
|
+
# provided, the AWS account ID is used by default.
|
6559
7577
|
#
|
6560
7578
|
# @option params [required, String] :database_name
|
6561
7579
|
# The name of the catalog database in which the table resides. For Hive
|
@@ -6567,7 +7585,7 @@ module Aws::Glue
|
|
6567
7585
|
#
|
6568
7586
|
# @option params [Boolean] :skip_archive
|
6569
7587
|
# By default, `UpdateTable` always creates an archived version of the
|
6570
|
-
# table before updating it.
|
7588
|
+
# table before updating it. However, if `skipArchive` is set to true,
|
6571
7589
|
# `UpdateTable` does not create the archived version.
|
6572
7590
|
#
|
6573
7591
|
# @return [Struct] Returns an empty {Seahorse::Client::Response response}.
|
@@ -6590,6 +7608,9 @@ module Aws::Glue
|
|
6590
7608
|
# name: "NameString", # required
|
6591
7609
|
# type: "ColumnTypeString",
|
6592
7610
|
# comment: "CommentString",
|
7611
|
+
# parameters: {
|
7612
|
+
# "KeyString" => "ParametersMapValue",
|
7613
|
+
# },
|
6593
7614
|
# },
|
6594
7615
|
# ],
|
6595
7616
|
# location: "LocationString",
|
@@ -6628,6 +7649,9 @@ module Aws::Glue
|
|
6628
7649
|
# name: "NameString", # required
|
6629
7650
|
# type: "ColumnTypeString",
|
6630
7651
|
# comment: "CommentString",
|
7652
|
+
# parameters: {
|
7653
|
+
# "KeyString" => "ParametersMapValue",
|
7654
|
+
# },
|
6631
7655
|
# },
|
6632
7656
|
# ],
|
6633
7657
|
# view_original_text: "ViewTextString",
|
@@ -6736,7 +7760,7 @@ module Aws::Glue
|
|
6736
7760
|
#
|
6737
7761
|
# @option params [String] :catalog_id
|
6738
7762
|
# The ID of the Data Catalog where the function to be updated is
|
6739
|
-
# located. If none is
|
7763
|
+
# located. If none is provided, the AWS account ID is used by default.
|
6740
7764
|
#
|
6741
7765
|
# @option params [required, String] :database_name
|
6742
7766
|
# The name of the catalog database where the function to be updated is
|
@@ -6746,7 +7770,7 @@ module Aws::Glue
|
|
6746
7770
|
# The name of the function.
|
6747
7771
|
#
|
6748
7772
|
# @option params [required, Types::UserDefinedFunctionInput] :function_input
|
6749
|
-
# A `FunctionInput` object that
|
7773
|
+
# A `FunctionInput` object that redefines the function in the Data
|
6750
7774
|
# Catalog.
|
6751
7775
|
#
|
6752
7776
|
# @return [Struct] Returns an empty {Seahorse::Client::Response response}.
|
@@ -6832,7 +7856,7 @@ module Aws::Glue
|
|
6832
7856
|
params: params,
|
6833
7857
|
config: config)
|
6834
7858
|
context[:gem_name] = 'aws-sdk-glue'
|
6835
|
-
context[:gem_version] = '1.
|
7859
|
+
context[:gem_version] = '1.42.0'
|
6836
7860
|
Seahorse::Client::Request.new(handlers, context)
|
6837
7861
|
end
|
6838
7862
|
|