У меня есть Пример кода Amazon для запуска comprehend.start_topics_detection_job. Вот код с переменными, заполненными для моей работы:
import re
import csv
import pytz
import boto3
import json
# https://docs.aws.amazon.com/code-samples/latest/catalog/python-comprehend-TopicModeling.py.html
# https://docs.aws.amazon.com/comprehend/latest/dg/API_InputDataConfig.html
# Set these values before running the program
input_s3_url = "s3://comprehend-topic-modelling-bucket/input_800_cleaned_articles/"
input_doc_format = "ONE_DOC_PER_LINE"
output_s3_url = "s3://comprehend-topic-modelling-bucket/output"
data_access_role_arn = "arn:aws:iam::372656143103:role/access-aws-services-from-sagemaker"
number_of_topics = 30
# Set up job configuration
input_data_config = {"S3Uri": input_s3_url, "InputFormat": input_doc_format}
output_data_config = {"S3Uri": output_s3_url}
# Begin a job to detect the topics in the document collection
comprehend = boto3.client('comprehend')
start_result = comprehend.start_topics_detection_job(
NumberOfTopics=number_of_topics,
InputDataConfig=input_data_config,
OutputDataConfig=output_data_config,
DataAccessRoleArn=data_access_role_arn)
# Output the results
print('Start Topic Detection Job: ' + json.dumps(start_result))
job_id = start_result['JobId']
print(f'job_id: {job_id}')
# Retrieve and output information about the job
describe_result = comprehend.describe_topics_detection_job(JobId=job_id)
print('Describe Job: ' + json.dumps(describe_result)) . #<===LINE 36
# List and output information about current jobs
list_result = comprehend.list_topics_detection_jobs()
print('list_topics_detection_jobs_result: ' + json.dumps(list_result))
Ошибка с ошибкой:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-8-840a7ee043d4> in <module>()
34 # Retrieve and output information about the job
35 describe_result = comprehend.describe_topics_detection_job(JobId=job_id)
---> 36 print('Describe Job: ' + json.dumps(describe_result))
37
38 # List and output information about current jobs
~/anaconda3/envs/python3/lib/python3.6/json/__init__.py in dumps(obj, skipkeys, ensure_ascii, check_circular, allow_nan, cls, indent, separators, default, sort_keys, **kw)
229 cls is None and indent is None and separators is None and
230 default is None and not sort_keys and not kw):
--> 231 return _default_encoder.encode(obj)
232 if cls is None:
233 cls = JSONEncoder
~/anaconda3/envs/python3/lib/python3.6/json/encoder.py in encode(self, o)
197 # exceptions aren't as detailed. The list call should be roughly
198 # equivalent to the PySequence_Fast that ''.join() would do.
--> 199 chunks = self.iterencode(o, _one_shot=True)
200 if not isinstance(chunks, (list, tuple)):
201 chunks = list(chunks)
~/anaconda3/envs/python3/lib/python3.6/json/encoder.py in iterencode(self, o, _one_shot)
255 self.key_separator, self.item_separator, self.sort_keys,
256 self.skipkeys, _one_shot)
--> 257 return _iterencode(o, 0)
258
259 def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,
~/anaconda3/envs/python3/lib/python3.6/json/encoder.py in default(self, o)
178 """
179 raise TypeError("Object of type '%s' is not JSON serializable" %
--> 180 o.__class__.__name__)
181
182 def encode(self, o):
TypeError: Object of type 'datetime' is not JSON serializable
Он мгновенно выходит из строя, вторую секунду я "бегу". Мне кажется, что вызов comprehend.start_topics_detection_job может быть неудачным, что приводит к строке ошибки 36, print('Describe Job: ' + json.dumps(describe_result)).
Чего мне не хватает?
UPDATE
Та же роль IAM используется для ноутбука, как и в приведенном выше коде. Вот разрешения, которые в настоящее время назначены этой роли IAM:
