I am following this github repo, adopting it to a text classification problem that is built on distil bert. So given a sting of text, the model should return a label and a (probability) score.
Output from the model:
sentiment_input = {"inputs": "I love using the new Inference DLC."}
# sentiment_input= "I love using the new Inference DLC."
response = predictor.predict(data=sentiment_input)
print(response)
Output:
[{'label': 'LABEL_80', 'score': 0.008507220074534416}]
When I run the following
# Create an enpointInput
endpointInput = EndpointInput(
endpoint_name=predictor.endpoint_name,
probability_attribute="score",
inference_attribute="label",
# probability_threshold_attribute=0.5,
destination="/opt/ml/processing/input_data",
)
# Create the monitoring schedule to execute every hour.
from sagemaker.model_monitor import CronExpressionGenerator
response = clinc_intent0911.create_monitoring_schedule(
monitor_schedule_name=clincintent_monitor_schedule_name,
endpoint_input=endpointInput,
output_s3_uri=baseline_results_uri,
problem_type="MulticlassClassification",
ground_truth_input=ground_truth_upload_path,
constraints=baseline_job.suggested_constraints(),
schedule_cron_expression=CronExpressionGenerator.hourly(),
enable_cloudwatch_metrics=True,
)
I get the following error:
---------------------------------------------------------------------------
ClientError Traceback (most recent call last)
<ipython-input-269-72e7049246fb> in <module>
10 constraints=baseline_job.suggested_constraints(),
11 schedule_cron_expression=CronExpressionGenerator.hourly(),
---> 12 enable_cloudwatch_metrics=True,
13 )
/opt/conda/lib/python3.6/site-packages/sagemaker/model_monitor/model_monitoring.py in create_monitoring_schedule(self, endpoint_input, ground_truth_input, problem_type, record_preprocessor_script, post_analytics_processor_script, output_s3_uri, constraints, monitor_schedule_name, schedule_cron_expression, enable_cloudwatch_metrics)
2615 network_config=self.network_config,
2616 )
-> 2617 self.sagemaker_session.sagemaker_client.create_model_quality_job_definition(**request_dict)
2618
2619 # create schedule
/opt/conda/lib/python3.6/site-packages/botocore/client.py in _api_call(self, *args, **kwargs)
355 "%s() only accepts keyword arguments." % py_operation_name)
356 # The "self" in this scope is referring to the BaseClient.
--> 357 return self._make_api_call(operation_name, kwargs)
358
359 _api_call.__name__ = str(py_operation_name)
/opt/conda/lib/python3.6/site-packages/botocore/client.py in _make_api_call(self, operation_name, api_params)
674 error_code = parsed_response.get("Error", {}).get("Code")
675 error_class = self.exceptions.from_code(error_code)
--> 676 raise error_class(parsed_response, operation_name)
677 else:
678 return parsed_response
ClientError: An error occurred (ValidationException) when calling the CreateModelQualityJobDefinition operation: Endpoint 'clinc-intent-analysis-0911' does not exist or is not valid
At this point my sagemaker endpoint is live and unable to debug it is not valid.
SageMaker ModelMonitor only works for tabular datasets at the moment out of the box (see documentation), and hence the "not valid" error message. To use it on NLP problems, you'd have to bring your own model monitor container (BYOC). Here is an example to get started - https://aws.amazon.com/blogs/machine-learning/detect-nlp-data-drift-using-custom-amazon-sagemaker-model-monitor/,
and the associated Github repo is here - https://github.com/aws-samples/detecting-data-drift-in-nlp-using-amazon-sagemaker-custom-model-monitor
I am relatively knew to programming, especially in regards to the problem I am facing in regards to running post requests through amazon web services and use of API requests.
I currently have a program written below.
from chalice import Chalice
import requests, json
import alpaca_trade_api as tradeapi
app = Chalice(app_name='tradingview-webhook-alerts')
API_KEY = 'API'
SECRET_KEY = 'SECRET'
BASE_URL = "https://paper-api.alpaca.markets"
ORDERS_URL = "{}/v2/orders".format(BASE_URL)
HEADERS = {'APCA-API-KEY-ID': API_KEY, 'APCA-API-SECRET-KEY': SECRET_KEY}
#app.route('/GDX',methods=['POST'])
def GDX():
request = app.current_request
webhook_message = request.json_body
p = 1-(webhook_message['close'] / webhook_message['high'])
if p<.0175: #if the high price for the 15m candle is 3% higher than the close, thee excution will not occur
data = {
"symbol": webhook_message['ticker'], #want it to access whatever the payload message is, payload message I believe is what the alert from Trading_View will send
"qty": 8,
"side": "buy",
"type": "limit",
"limit_price": webhook_message['close'],
"time_in_force": "gtc",
"order_class": "bracket",
#need to find out the average max profit per trade
"take_profit": {
"limit_price": webhook_message['close'] * 1.0085 #take 0.6%% profit
},
"stop_loss": {
"stop_price": webhook_message['close'] * 0.95, #stop loss of 6%
"limit_price": webhook_message['close'] * 0.93
}
}
r = requests.post(ORDERS_URL, json=data, headers=HEADERS)
response = json.loads(r.content)
print(response)
print(p)
return {
'message': 'I bought the stock!',
'webhook_message': webhook_message
}
else:
return{
'message': 'stock not purchased',
'webhook_message': webhook_message
}
#app.route('/buy_SLV',methods=['POST'])
def buy_stock():
request = app.current_request
webhook_message = request.json_body
data = {
"symbol": webhook_message['ticker'], #want it to access whatever the payload message is, payload message I believe is what the alert from Trading_View will send
"qty": 4,
"side": "buy",
"type": "limit",
"limit_price": webhook_message['close'],
"time_in_force": "gtc",
"order_class": "bracket",
"take_profit": {
"limit_price": webhook_message['close'] * 1.008 #take 1% profit
},
"stop_loss": {
"stop_price": webhook_message['close'] * 0.95, #stop loss of 2%
"limit_price": webhook_message['close'] * 0.94
}
}
r = requests.post(ORDERS_URL, json=data, headers=HEADERS)
response = json.loads(r.content)
print(response)
print(response.keys())
return {
'message': 'I bought the stock!',
'webhook_message': webhook_message
}
#app.route('/GDX_UpperBB',methods=['POST'])
def GDX_UpperBB():
request = app.current_request
webhook_message = request.json_body
api = tradeapi.REST(API_KEY, SECRET_KEY, base_url=BASE_URL)
ids = []
orders = api.list_orders(
limit=100,
nested=True # show nested multi-leg orders
)
GDX_orders = [o for o in orders if o.symbol == 'GDX']
for i in GDX_orders:
ids.append(i.id)
if len(orders)>0:
print(ids)
for i in ids:
api.cancel_order(i)
else:
print('there are no orders')
return{
'message': 'I bought the stock!',
'webhook_message': webhook_message
}
the first two methods have been running fine (both through AWS and on local server). The third method (GDX_UpperBB) is what causes everything to stop working. When I run the program on a local server and make a call to the GDX_UpperBB method, it executes without issue. but when I deploy the program through the amazon web service API through chalice, I get a 502 BadGateway response with a "message": "Internal server error" throwback.
When I go into AWS and test the method this is the console response that I get (I removed about the first half of the response because it was long and everything said it ran successfully)
Mon Oct 26 00:46:51 UTC 2020 : Received response. Status: 200, Integration latency: 15 ms
Mon Oct 26 00:46:51 UTC 2020 : Endpoint response headers: {Date=Mon, 26 Oct 2020 00:46:51 GMT, Content-Type=application/json, Content-Length=127, Connection=keep-alive, x-amzn-RequestId=621b56f9-6bee-43af-8fe2-7f2cbeb7420e, X-Amz-Function-Error=Unhandled, x-amzn-Remapped-Content-Length=0, X-Amz-Executed-Version=$LATEST, X-Amzn-Trace-Id=root=1-5f961c7b-0a211c4e04be837554d0857f;sampled=0}
Mon Oct 26 00:46:51 UTC 2020 : Endpoint response body before transformations: {"errorMessage": "Unable to import module 'app': No module named 'alpaca_trade_api'", "errorType": "Runtime.ImportModuleError"}
Mon Oct 26 00:46:51 UTC 2020 : Lambda execution failed with status 200 due to customer function error: Unable to import module 'app': No module named 'alpaca_trade_api'. Lambda request id: 621b56f9-6bee-43af-8fe2-7f2cbeb7420e
Mon Oct 26 00:46:51 UTC 2020 : Method completed with status: 502
all help is appreciated.
You need to either add the dependency to your requirements.txt filer or add the code to a vendor directory off your main project directory
Hi I am newbie to AWS Sagemaker, I am trying to deploying the custom time series model on sagemaker, so for that build a docker image using sagemaker terminal,But when i am trying to creating training job it showing some error.I am struggling with past four days, please any one could help me.
Here my code:
lstm = sage.estimator.Estimator(image,
role, 1, 'ml.m4.xlarge',
output_path='s3://' + s3Bucket,
sagemaker_session=sess)
lstm.fit(upload_data)
Here my Error, I attached policy of ecr full access permissions to sagemaker Iam role and also account is in same region.
ClientErrorTraceback (most recent call last)
<ipython-input-48-1d7f3ff70f18> in <module>()
4 sagemaker_session=sess)
5
----> 6 lstm.fit(upload_data)
/home/ec2-user/anaconda3/envs/tensorflow_p27/lib/python2.7/site-packages/sagemaker/estimator.pyc in fit(self, inputs, wait, logs, job_name, experiment_config)
472 self._prepare_for_training(job_name=job_name)
473
--> 474 self.latest_training_job = _TrainingJob.start_new(self, inputs, experiment_config)
475 self.jobs.append(self.latest_training_job)
476 if wait:
/home/ec2-user/anaconda3/envs/tensorflow_p27/lib/python2.7/site-packages/sagemaker/estimator.pyc in start_new(cls, estimator, inputs, experiment_config)
1036 train_args["enable_sagemaker_metrics"] = estimator.enable_sagemaker_metrics
1037
-> 1038 estimator.sagemaker_session.train(**train_args)
1039
1040 return cls(estimator.sagemaker_session, estimator._current_job_name)
/home/ec2-user/anaconda3/envs/tensorflow_p27/lib/python2.7/site-packages/sagemaker/session.pyc in train(self, input_mode, input_config, role, job_name, output_config, resource_config, vpc_config, hyperparameters, stop_condition, tags, metric_definitions, enable_network_isolation, image, algorithm_arn, encrypt_inter_container_traffic, train_use_spot_instances, checkpoint_s3_uri, checkpoint_local_path, experiment_config, debugger_rule_configs, debugger_hook_config, tensorboard_output_config, enable_sagemaker_metrics)
588 LOGGER.info("Creating training-job with name: %s", job_name)
589 LOGGER.debug("train request: %s", json.dumps(train_request, indent=4))
--> 590 self.sagemaker_client.create_training_job(**train_request)
591
592 def process(
/home/ec2-user/anaconda3/envs/tensorflow_p27/lib/python2.7/site-packages/botocore/client.pyc in _api_call(self, *args, **kwargs)
314 "%s() only accepts keyword arguments." % py_operation_name)
315 # The "self" in this scope is referring to the BaseClient.
--> 316 return self._make_api_call(operation_name, kwargs)
317
318 _api_call.__name__ = str(py_operation_name)
/home/ec2-user/anaconda3/envs/tensorflow_p27/lib/python2.7/site-packages/botocore/client.pyc in _make_api_call(self, operation_name, api_params)
624 error_code = parsed_response.get("Error", {}).get("Code")
625 error_class = self.exceptions.from_code(error_code)
--> 626 raise error_class(parsed_response, operation_name)
627 else:
628 return parsed_response
ClientError: An error occurred (ValidationException) when calling the CreateTrainingJob operation: Cannot find repository: sagemaker-model in registry ID: 534860077983 Please check if your ECR repository exists and role arn:aws:iam::534860077983:role/service-role/AmazonSageMaker-ExecutionRole-20190508T215284 has proper pull permissions for SageMaker: ecr:BatchCheckLayerAvailability, ecr:BatchGetImage, ecr:GetDownloadUrlForLayer
TL;DR: Seems like you're not providing the correct repository for the ECR image to the SageMaker estimator. Maybe the repository doesn't exist?
Also make sure that the repository's permissions are configured to allow the principal sagemaker.amazonaws.com to do ecr:BatchCheckLayerAvailability, ecr:BatchGetImage, ecr:GetDownloadUrlForLayer
I am currently working on building "Scrapy spiders control panel" in which I am testing this existing solution available on [Distributed Multi-user Scrapy Spiders Control Panel] https://github.com/aaldaber/Distributed-Multi-User-Scrapy-System-with-a-Web-UI.
I am trying to run this on my local Ubuntu Dev Machine but having issues with scrapd daemon.
One of the Workers, linkgenerator is working but scraper as worker1 is not working.
I can not figure out why scrapyd won't run on another local instance.
Background Information about the configuration.
The application comes bundled with Django, Scrapy, Pipeline for MongoDB (for saving the scraped items) and Scrapy scheduler for RabbitMQ (for distributing the links among workers). I have 2 local Ubuntu instances in which Django, MongoDB, Scrapyd daemon and RabbitMQ server running on Instance1.
On another Scrapyd daemon is running on Instance2.
RabbitMQ Workers:
linkgenerator
worker1
IP Configurations for Instances:
IP For local Ubuntu Instance1: 192.168.0.101
IP for local Ubuntu Instance2: 192.168.0.106
List of tools used:
MongoDB server
RabbitMQ server
Scrapy Scrapyd API
One RabbitMQ linkgenerator worker (WorkerName: linkgenerator) server with Scrapy installed and running scrapyd daemon on local Ubuntu Instance1: 192.168.0.101
Another one RabbitMQ scraper worker (WorkerName: worker1) server with Scrapy installed and running scrapyd daemon on local Ubuntu Instance2: 192.168.0.106
Instance1: 192.168.0.101
"Instance1" on which Django, RabbitMQ, scrapyd daemon servers running -- IP : 192.168.0.101
Instance2: 192.168.0.106
Scrapy installed on instance2 and running scrapyd daemon
Scrapy Control Panel UI Snapshot:
from snapshot, control panel outlook can be been seen, there are two workers, linkgenerator worked successfully but worker1 did not, the logs given in the end of the post
RabbitMQ status info
linkgenerator worker can successfully push the message to RabbitMQ queue, linkgenerator spider generates start_urls for "scraper spider* are consumed by scraper (worker1), which is not working, please see the logs for worker1 in end of the post
RabbitMQ settings
The below file contains the settings for MongoDB and RabbitMQ:
SCHEDULER = ".rabbitmq.scheduler.Scheduler"
SCHEDULER_PERSIST = True
RABBITMQ_HOST = 'ScrapyDevU79'
RABBITMQ_PORT = 5672
RABBITMQ_USERNAME = 'guest'
RABBITMQ_PASSWORD = 'guest'
MONGODB_PUBLIC_ADDRESS = 'OneScience:27017' # This will be shown on the web interface, but won't be used for connecting to DB
MONGODB_URI = 'localhost:27017' # Actual uri to connect to DB
MONGODB_USER = 'tariq'
MONGODB_PASSWORD = 'toor'
MONGODB_SHARDED = True
MONGODB_BUFFER_DATA = 100
# Set your link generator worker address here
LINK_GENERATOR = 'http://192.168.0.101:6800'
SCRAPERS = ['http://192.168.0.106:6800']
LINUX_USER_CREATION_ENABLED = False # Set this to True if you want a linux user account
linkgenerator scrapy.cfg settings:
[settings]
default = tester2_fda_trial20.settings
[deploy:linkgenerator]
url = http://192.168.0.101:6800
project = tester2_fda_trial20
scraper scrapy.cfg settings:
[settings]
default = tester2_fda_trial20.settings
[deploy:worker1]
url = http://192.168.0.101:6800
project = tester2_fda_trial20
scrapyd.conf file settings for Instance1 (192.168.0.101)
cat /etc/scrapyd/scrapyd.conf
[scrapyd]
eggs_dir = /var/lib/scrapyd/eggs
dbs_dir = /var/lib/scrapyd/dbs
items_dir = /var/lib/scrapyd/items
logs_dir = /var/log/scrapyd
max_proc = 0
max_proc_per_cpu = 4
finished_to_keep = 100
poll_interval = 5.0
bind_address = 0.0.0.0
#bind_address = 127.0.0.1
http_port = 6800
debug = on
runner = scrapyd.runner
application = scrapyd.app.application
launcher = scrapyd.launcher.Launcher
webroot = scrapyd.website.Root
[services]
schedule.json = scrapyd.webservice.Schedule
cancel.json = scrapyd.webservice.Cancel
addversion.json = scrapyd.webservice.AddVersion
listprojects.json = scrapyd.webservice.ListProjects
listversions.json = scrapyd.webservice.ListVersions
listspiders.json = scrapyd.webservice.ListSpiders
delproject.json = scrapyd.webservice.DeleteProject
delversion.json = scrapyd.webservice.DeleteVersion
listjobs.json = scrapyd.webservice.ListJobs
daemonstatus.json = scrapyd.webservice.DaemonStatus
scrapyd.conf file settings for Instance2 (192.168.0.106)
cat /etc/scrapyd/scrapyd.conf
[scrapyd]
eggs_dir = /var/lib/scrapyd/eggs
dbs_dir = /var/lib/scrapyd/dbs
items_dir = /var/lib/scrapyd/items
logs_dir = /var/log/scrapyd
max_proc = 0
max_proc_per_cpu = 4
finished_to_keep = 100
poll_interval = 5.0
bind_address = 0.0.0.0
#bind_address = 127.0.0.1
http_port = 6800
debug = on
runner = scrapyd.runner
application = scrapyd.app.application
launcher = scrapyd.launcher.Launcher
webroot = scrapyd.website.Root
[services]
schedule.json = scrapyd.webservice.Schedule
cancel.json = scrapyd.webservice.Cancel
addversion.json = scrapyd.webservice.AddVersion
listprojects.json = scrapyd.webservice.ListProjects
listversions.json = scrapyd.webservice.ListVersions
listspiders.json = scrapyd.webservice.ListSpiders
delproject.json = scrapyd.webservice.DeleteProject
delversion.json = scrapyd.webservice.DeleteVersion
listjobs.json = scrapyd.webservice.ListJobs
daemonstatus.json = scrapyd.webservice.DaemonStatus
RabbitMQ Status
sudo service rabbitmq-server status
[sudo] password for mtaziz:
Status of node rabbit#ScrapyDevU79
[{pid,53715},
{running_applications,
[{rabbitmq_shovel_management,
"Management extension for the Shovel plugin","3.6.11"},
{rabbitmq_shovel,"Data Shovel for RabbitMQ","3.6.11"},
{rabbitmq_management,"RabbitMQ Management Console","3.6.11"},
{rabbitmq_web_dispatch,"RabbitMQ Web Dispatcher","3.6.11"},
{rabbitmq_management_agent,"RabbitMQ Management Agent","3.6.11"},
{rabbit,"RabbitMQ","3.6.11"},
{os_mon,"CPO CXC 138 46","2.2.14"},
{cowboy,"Small, fast, modular HTTP server.","1.0.4"},
{ranch,"Socket acceptor pool for TCP protocols.","1.3.0"},
{ssl,"Erlang/OTP SSL application","5.3.2"},
{public_key,"Public key infrastructure","0.21"},
{cowlib,"Support library for manipulating Web protocols.","1.0.2"},
{crypto,"CRYPTO version 2","3.2"},
{amqp_client,"RabbitMQ AMQP Client","3.6.11"},
{rabbit_common,
"Modules shared by rabbitmq-server and rabbitmq-erlang-client",
"3.6.11"},
{inets,"INETS CXC 138 49","5.9.7"},
{mnesia,"MNESIA CXC 138 12","4.11"},
{compiler,"ERTS CXC 138 10","4.9.4"},
{xmerl,"XML parser","1.3.5"},
{syntax_tools,"Syntax tools","1.6.12"},
{asn1,"The Erlang ASN1 compiler version 2.0.4","2.0.4"},
{sasl,"SASL CXC 138 11","2.3.4"},
{stdlib,"ERTS CXC 138 10","1.19.4"},
{kernel,"ERTS CXC 138 10","2.16.4"}]},
{os,{unix,linux}},
{erlang_version,
"Erlang R16B03 (erts-5.10.4) [source] [64-bit] [smp:4:4] [async-threads:64] [kernel-poll:true]\n"},
{memory,
[{connection_readers,0},
{connection_writers,0},
{connection_channels,0},
{connection_other,6856},
{queue_procs,145160},
{queue_slave_procs,0},
{plugins,1959248},
{other_proc,22328920},
{metrics,160112},
{mgmt_db,655320},
{mnesia,83952},
{other_ets,2355800},
{binary,96920},
{msg_index,47352},
{code,27101161},
{atom,992409},
{other_system,31074022},
{total,87007232}]},
{alarms,[]},
{listeners,[{clustering,25672,"::"},{amqp,5672,"::"},{http,15672,"::"}]},
{vm_memory_calculation_strategy,rss},
{vm_memory_high_watermark,0.4},
{vm_memory_limit,3343646720},
{disk_free_limit,50000000},
{disk_free,56257699840},
{file_descriptors,
[{total_limit,924},{total_used,2},{sockets_limit,829},{sockets_used,0}]},
{processes,[{limit,1048576},{used,351}]},
{run_queue,0},
{uptime,34537},
{kernel,{net_ticktime,60}}]
scrapyd daemon on Instance1 ( 192.168.0.101 ) running status:
scrapyd
2017-09-11T06:16:07+0600 [-] Loading /home/mtaziz/.virtualenvs/onescience_dist_env/local/lib/python2.7/site-packages/scrapyd/txapp.py...
2017-09-11T06:16:07+0600 [-] Scrapyd web console available at http://0.0.0.0:6800/
2017-09-11T06:16:07+0600 [-] Loaded.
2017-09-11T06:16:07+0600 [twisted.scripts._twistd_unix.UnixAppLogger#info] twistd 17.5.0 (/home/mtaziz/.virtualenvs/onescience_dist_env/bin/python 2.7.6) starting up.
2017-09-11T06:16:07+0600 [twisted.scripts._twistd_unix.UnixAppLogger#info] reactor class: twisted.internet.epollreactor.EPollReactor.
2017-09-11T06:16:07+0600 [-] Site starting on 6800
2017-09-11T06:16:07+0600 [twisted.web.server.Site#info] Starting factory <twisted.web.server.Site instance at 0x7f5e265c77a0>
2017-09-11T06:16:07+0600 [Launcher] Scrapyd 1.2.0 started: max_proc=16, runner='scrapyd.runner'
2017-09-11T06:16:07+0600 [twisted.python.log#info] "192.168.0.101" - - [11/Sep/2017:00:16:07 +0000] "GET /listprojects.json HTTP/1.1" 200 98 "-" "python-requests/2.18.4"
2017-09-11T06:16:07+0600 [twisted.python.log#info] "192.168.0.101" - - [11/Sep/2017:00:16:07 +0000] "GET /listversions.json?project=tester2_fda_trial20 HTTP/1.1" 200 80 "-" "python-requests/2.18.4"
2017-09-11T06:16:07+0600 [twisted.python.log#info] "192.168.0.101" - - [11/Sep/2017:00:16:07 +0000] "GET /listjobs.json?project=tester2_fda_trial20 HTTP/1.1" 200 92 "-" "python-requests/2.18.4"
scrapyd daemon on instance2 (192.168.0.106) running status:
scrapyd
2017-09-11T06:09:28+0600 [-] Loading /home/mtaziz/.virtualenvs/scrapydevenv/local/lib/python2.7/site-packages/scrapyd/txapp.py...
2017-09-11T06:09:28+0600 [-] Scrapyd web console available at http://0.0.0.0:6800/
2017-09-11T06:09:28+0600 [-] Loaded.
2017-09-11T06:09:28+0600 [twisted.scripts._twistd_unix.UnixAppLogger#info] twistd 17.5.0 (/home/mtaziz/.virtualenvs/scrapydevenv/bin/python 2.7.6) starting up.
2017-09-11T06:09:28+0600 [twisted.scripts._twistd_unix.UnixAppLogger#info] reactor class: twisted.internet.epollreactor.EPollReactor.
2017-09-11T06:09:28+0600 [-] Site starting on 6800
2017-09-11T06:09:28+0600 [twisted.web.server.Site#info] Starting factory <twisted.web.server.Site instance at 0x7fbe6eaeac20>
2017-09-11T06:09:28+0600 [Launcher] Scrapyd 1.2.0 started: max_proc=16, runner='scrapyd.runner'
2017-09-11T06:09:32+0600 [twisted.python.log#info] "192.168.0.101" - - [11/Sep/2017:00:09:32 +0000] "GET /listprojects.json HTTP/1.1" 200 98 "-" "python-requests/2.18.4"
2017-09-11T06:09:32+0600 [twisted.python.log#info] "192.168.0.101" - - [11/Sep/2017:00:09:32 +0000] "GET /listversions.json?project=tester2_fda_trial20 HTTP/1.1" 200 80 "-" "python-requests/2.18.4"
2017-09-11T06:09:32+0600 [twisted.python.log#info] "192.168.0.101" - - [11/Sep/2017:00:09:32 +0000] "GET /listjobs.json?project=tester2_fda_trial20 HTTP/1.1" 200 92 "-" "python-requests/2.18.4"
2017-09-11T06:09:37+0600 [twisted.python.log#info] "192.168.0.101" - - [11/Sep/2017:00:09:37 +0000] "GET /listprojects.json HTTP/1.1" 200 98 "-" "python-requests/2.18.4"
2017-09-11T06:09:37+0600 [twisted.python.log#info] "192.168.0.101" - - [11/Sep/2017:00:09:37 +0000] "GET /listversions.json?project=tester2_fda_trial20 HTTP/1.1" 200 80 "-" "python-requests/2.18.4"
worker1 logs
After updating the code for RabbitMQ server settings followed by the suggestions made by #Tarun Lalwani
The suggestion was to use RabbitMQ Server IP - 192.168.0.101:5672 instead of
127.0.0.1:5672. After I updated as suggested by Tarun Lalwani got the new problems as below............
2017-09-11 15:49:18 [scrapy.utils.log] INFO: Scrapy 1.4.0 started (bot: tester2_fda_trial20)
2017-09-11 15:49:18 [scrapy.utils.log] INFO: Overridden settings: {'NEWSPIDER_MODULE': 'tester2_fda_trial20.spiders', 'ROBOTSTXT_OBEY': True, 'LOG_LEVEL': 'INFO', 'SPIDER_MODULES': ['tester2_fda_trial20.spiders'], 'BOT_NAME': 'tester2_fda_trial20', 'FEED_URI': 'file:///var/lib/scrapyd/items/tester2_fda_trial20/tester2_fda_trial20/79b1123a96d611e79276000c29bad697.jl', 'SCHEDULER': 'tester2_fda_trial20.rabbitmq.scheduler.Scheduler', 'TELNETCONSOLE_ENABLED': False, 'LOG_FILE': '/var/log/scrapyd/tester2_fda_trial20/tester2_fda_trial20/79b1123a96d611e79276000c29bad697.log'}
2017-09-11 15:49:18 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.feedexport.FeedExporter',
'scrapy.extensions.memusage.MemoryUsage',
'scrapy.extensions.logstats.LogStats',
'scrapy.extensions.corestats.CoreStats']
2017-09-11 15:49:18 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware',
'scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
'scrapy.downloadermiddlewares.retry.RetryMiddleware',
'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware',
'scrapy.downloadermiddlewares.stats.DownloaderStats']
2017-09-11 15:49:18 [scrapy.middleware] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
'scrapy.spidermiddlewares.referer.RefererMiddleware',
'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
'scrapy.spidermiddlewares.depth.DepthMiddleware']
2017-09-11 15:49:18 [scrapy.middleware] INFO: Enabled item pipelines:
['tester2_fda_trial20.pipelines.FdaTrial20Pipeline',
'tester2_fda_trial20.mongodb.scrapy_mongodb.MongoDBPipeline']
2017-09-11 15:49:18 [scrapy.core.engine] INFO: Spider opened
2017-09-11 15:49:18 [pika.adapters.base_connection] INFO: Connecting to 192.168.0.101:5672
2017-09-11 15:49:18 [pika.adapters.blocking_connection] INFO: Created channel=1
2017-09-11 15:49:18 [scrapy.core.engine] INFO: Closing spider (shutdown)
2017-09-11 15:49:18 [pika.adapters.blocking_connection] INFO: Channel.close(0, Normal Shutdown)
2017-09-11 15:49:18 [pika.channel] INFO: Channel.close(0, Normal Shutdown)
2017-09-11 15:49:18 [scrapy.utils.signal] ERROR: Error caught on signal handler: <bound method ?.close_spider of <scrapy.extensions.feedexport.FeedExporter object at 0x7f94878b8c50>>
Traceback (most recent call last):
File "/home/mtaziz/.virtualenvs/scrapydevenv/local/lib/python2.7/site-packages/twisted/internet/defer.py", line 150, in maybeDeferred
result = f(*args, **kw)
File "/home/mtaziz/.virtualenvs/scrapydevenv/local/lib/python2.7/site-packages/pydispatch/robustapply.py", line 55, in robustApply
return receiver(*arguments, **named)
File "/home/mtaziz/.virtualenvs/scrapydevenv/local/lib/python2.7/site-packages/scrapy/extensions/feedexport.py", line 201, in close_spider
slot = self.slot
AttributeError: 'FeedExporter' object has no attribute 'slot'
2017-09-11 15:49:18 [scrapy.utils.signal] ERROR: Error caught on signal handler: <bound method ?.spider_closed of <Tester2Fda_Trial20Spider 'tester2_fda_trial20' at 0x7f9484f897d0>>
Traceback (most recent call last):
File "/home/mtaziz/.virtualenvs/scrapydevenv/local/lib/python2.7/site-packages/twisted/internet/defer.py", line 150, in maybeDeferred
result = f(*args, **kw)
File "/home/mtaziz/.virtualenvs/scrapydevenv/local/lib/python2.7/site-packages/pydispatch/robustapply.py", line 55, in robustApply
return receiver(*arguments, **named)
File "/tmp/user/1000/tester2_fda_trial20-10-d4Req9.egg/tester2_fda_trial20/spiders/tester2_fda_trial20.py", line 28, in spider_closed
AttributeError: 'Tester2Fda_Trial20Spider' object has no attribute 'statstask'
2017-09-11 15:49:18 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'finish_reason': 'shutdown',
'finish_time': datetime.datetime(2017, 9, 11, 9, 49, 18, 159896),
'log_count/ERROR': 2,
'log_count/INFO': 10}
2017-09-11 15:49:18 [scrapy.core.engine] INFO: Spider closed (shutdown)
2017-09-11 15:49:18 [twisted] CRITICAL: Unhandled error in Deferred:
2017-09-11 15:49:18 [twisted] CRITICAL:
Traceback (most recent call last):
File "/home/mtaziz/.virtualenvs/scrapydevenv/local/lib/python2.7/site-packages/twisted/internet/defer.py", line 1386, in _inlineCallbacks
result = g.send(result)
File "/home/mtaziz/.virtualenvs/scrapydevenv/local/lib/python2.7/site-packages/scrapy/crawler.py", line 95, in crawl
six.reraise(*exc_info)
File "/home/mtaziz/.virtualenvs/scrapydevenv/local/lib/python2.7/site-packages/scrapy/crawler.py", line 79, in crawl
yield self.engine.open_spider(self.spider, start_requests)
OperationFailure: command SON([('saslStart', 1), ('mechanism', 'SCRAM-SHA-1'), ('payload', Binary('n,,n=tariq,r=MjY5OTQ0OTYwMjA4', 0)), ('autoAuthorize', 1)]) on namespace admin.$cmd failed: Authentication failed.
MongoDBPipeline
# coding:utf-8
import datetime
from pymongo import errors
from pymongo.mongo_client import MongoClient
from pymongo.mongo_replica_set_client import MongoReplicaSetClient
from pymongo.read_preferences import ReadPreference
from scrapy.exporters import BaseItemExporter
try:
from urllib.parse import quote
except:
from urllib import quote
def not_set(string):
""" Check if a string is None or ''
:returns: bool - True if the string is empty
"""
if string is None:
return True
elif string == '':
return True
return False
class MongoDBPipeline(BaseItemExporter):
""" MongoDB pipeline class """
# Default options
config = {
'uri': 'mongodb://localhost:27017',
'fsync': False,
'write_concern': 0,
'database': 'scrapy-mongodb',
'collection': 'items',
'replica_set': None,
'buffer': None,
'append_timestamp': False,
'sharded': False
}
# Needed for sending acknowledgement signals to RabbitMQ for all persisted items
queue = None
acked_signals = []
# Item buffer
item_buffer = dict()
def load_spider(self, spider):
self.crawler = spider.crawler
self.settings = spider.settings
self.queue = self.crawler.engine.slot.scheduler.queue
def open_spider(self, spider):
self.load_spider(spider)
# Configure the connection
self.configure()
self.spidername = spider.name
self.config['uri'] = 'mongodb://' + self.config['username'] + ':' + quote(self.config['password']) + '#' + self.config['uri'] + '/admin'
self.shardedcolls = []
if self.config['replica_set'] is not None:
self.connection = MongoReplicaSetClient(
self.config['uri'],
replicaSet=self.config['replica_set'],
w=self.config['write_concern'],
fsync=self.config['fsync'],
read_preference=ReadPreference.PRIMARY_PREFERRED)
else:
# Connecting to a stand alone MongoDB
self.connection = MongoClient(
self.config['uri'],
fsync=self.config['fsync'],
read_preference=ReadPreference.PRIMARY)
# Set up the collection
self.database = self.connection[spider.name]
# Autoshard the DB
if self.config['sharded']:
db_statuses = self.connection['config']['databases'].find({})
partitioned = []
notpartitioned = []
for status in db_statuses:
if status['partitioned']:
partitioned.append(status['_id'])
else:
notpartitioned.append(status['_id'])
if spider.name in notpartitioned or spider.name not in partitioned:
try:
self.connection.admin.command('enableSharding', spider.name)
except errors.OperationFailure:
pass
else:
collections = self.connection['config']['collections'].find({})
for coll in collections:
if (spider.name + '.') in coll['_id']:
if coll['dropped'] is not True:
if coll['_id'].index(spider.name + '.') == 0:
self.shardedcolls.append(coll['_id'][coll['_id'].index('.') + 1:])
def configure(self):
""" Configure the MongoDB connection """
# Set all regular options
options = [
('uri', 'MONGODB_URI'),
('fsync', 'MONGODB_FSYNC'),
('write_concern', 'MONGODB_REPLICA_SET_W'),
('database', 'MONGODB_DATABASE'),
('collection', 'MONGODB_COLLECTION'),
('replica_set', 'MONGODB_REPLICA_SET'),
('buffer', 'MONGODB_BUFFER_DATA'),
('append_timestamp', 'MONGODB_ADD_TIMESTAMP'),
('sharded', 'MONGODB_SHARDED'),
('username', 'MONGODB_USER'),
('password', 'MONGODB_PASSWORD')
]
for key, setting in options:
if not not_set(self.settings[setting]):
self.config[key] = self.settings[setting]
def process_item(self, item, spider):
""" Process the item and add it to MongoDB
:type item: Item object
:param item: The item to put into MongoDB
:type spider: BaseSpider object
:param spider: The spider running the queries
:returns: Item object
"""
item_name = item.__class__.__name__
# If we are working with a sharded DB, the collection will also be sharded
if self.config['sharded']:
if item_name not in self.shardedcolls:
try:
self.connection.admin.command('shardCollection', '%s.%s' % (self.spidername, item_name), key={'_id': "hashed"})
self.shardedcolls.append(item_name)
except errors.OperationFailure:
self.shardedcolls.append(item_name)
itemtoinsert = dict(self._get_serialized_fields(item))
if self.config['buffer']:
if item_name not in self.item_buffer:
self.item_buffer[item_name] = []
self.item_buffer[item_name].append([])
self.item_buffer[item_name].append(0)
self.item_buffer[item_name][1] += 1
if self.config['append_timestamp']:
itemtoinsert['scrapy-mongodb'] = {'ts': datetime.datetime.utcnow()}
self.item_buffer[item_name][0].append(itemtoinsert)
if self.item_buffer[item_name][1] == self.config['buffer']:
self.item_buffer[item_name][1] = 0
self.insert_item(self.item_buffer[item_name][0], spider, item_name)
return item
self.insert_item(itemtoinsert, spider, item_name)
return item
def close_spider(self, spider):
""" Method called when the spider is closed
:type spider: BaseSpider object
:param spider: The spider running the queries
:returns: None
"""
for key in self.item_buffer:
if self.item_buffer[key][0]:
self.insert_item(self.item_buffer[key][0], spider, key)
def insert_item(self, item, spider, item_name):
""" Process the item and add it to MongoDB
:type item: (Item object) or [(Item object)]
:param item: The item(s) to put into MongoDB
:type spider: BaseSpider object
:param spider: The spider running the queries
:returns: Item object
"""
self.collection = self.database[item_name]
if not isinstance(item, list):
if self.config['append_timestamp']:
item['scrapy-mongodb'] = {'ts': datetime.datetime.utcnow()}
ack_signal = item['ack_signal']
item.pop('ack_signal', None)
self.collection.insert(item, continue_on_error=True)
if ack_signal not in self.acked_signals:
self.queue.acknowledge(ack_signal)
self.acked_signals.append(ack_signal)
else:
signals = []
for eachitem in item:
signals.append(eachitem['ack_signal'])
eachitem.pop('ack_signal', None)
self.collection.insert(item, continue_on_error=True)
del item[:]
for ack_signal in signals:
if ack_signal not in self.acked_signals:
self.queue.acknowledge(ack_signal)
self.acked_signals.append(ack_signal)
To sum up, I believe the problem lies in scrapyd daemons running on both instances but somehow scraper or worker1 can not access it, I could not figure it out, I did not find any use cases on stackoverflow.
Any help is highly appreciated in this regard. Thank you in advance!