Community Articles
Find and share helpful community-sourced technical articles
Announcements
Alert: Welcome to the Unified Cloudera Community. Former HCC members be sure to read and learn how to activate your account here.
Super Guru

Using Deployed Models as a Function as a Service

104409-dataengineering.png 104410-datascience.png 104431-flowmanagement.png

Using Cloudera Data Science Workbench with Apache NiFi we can easily call functions within our deployed models from Apache NiFi as part of flows. I am working against CDSW on HDP (https://www.cloudera.com/documentation/data-science-workbench/latest/topics/cdsw_hdp.html), but it will work for all CDSW regardless of install type.

In my simple example, I built a Python model that uses TextBlob to run sentiment against a passed in sentence. It returns Sentiment Polarity and Subjectivity which we can immediately act upon in our flow.

CDSW is extremely easy to work with and I was up and running in a few minutes. For my model, I created a python 3 script and a shell script for install details. Both of these artifacts are available here: https://github.com/tspannhw/nifi-cdsw

My Apache NiFi 1.8 flow is here (I use no custom processors): cdsw-twitter-sentiment.xml

104433-socialmediacdswarch.jpg

Deploying a Machine Learning Model as a REST Service

104419-installtextblobcorpora.png

Once you login to CDSW and create a project or choose an existing one (https://www.cloudera.com/documentation/data-science-workbench/latest/topics/cdsw_projects.html). From your project, open workbench and you can install some libraries and test some Python. I am using a Python 3 session to download the TextBlob/NLTK Corpora for NLP.

104425-buildamodel.png

Let's Pip Install some libraries for testing

104427-pipinstalltextblob.png

Let's Create a new Model

104426-modeldeploy1.png

You choose your file (mine is sentiment.py see github). The function name is actually sentiment. Notice a typo I had to rebuild this and deploy. You setup an example input (sentence is the input parameter name) and an example output. Input and output will be JSON since this is a REST API.

Let's Deploy It (Python 3)

104428-modeldeploy2.png

The deploy will build it for deployment.

104428-modeldeploy2.png

We can see standard output, standard error, status, # of REST calls received and success.

Once a Model is Deployed We Can Control It

104424-cdswmodels.png

We can stop it, rebuild it or replace the files if need be. I had to update things a few times. The amount of resources used for the model rest hosting if your choice from a drop down. Since I am doing something small I picked the smallest model with only 1 virtual CPU and 2 GB of RAM. All of this is running in Docker on Kubernetes!

Once Deployed, It's Ready To Test and Use From Apache NiFi

104430-sentimentanalysismodeloverview.png

Just click test. See the JSON results and we can now call it from an Apache NiFi flow.

Once Deployed We Can Monitor The Model


104422-cdswmonitoring.png

Let's Run the Test

104420-cdswsentimentmodeltesting.png

See the status and response!

Apache NiFi Example Flow

104404-cdswflow1.png

104405-cdswflow2.png

Step 1: Call Twitter

104407-gettwitterfeed.png

Step 2: Extract Social Attributes of Interest

104411-parsetwitter.png

Step 3: Build our web call with our access key and function parameter

104412-buildcdswcall.png

Step 4: Extract our string as a flow file to send to the HTTP Post

104413-extractaccesskey2.png

104414-extractaccesskey.png

Step 5: Call Our Cloudera Data Science Workbench REST API (see tester).

104415-posttocdsw.png

Step 6: Extract the two result values.

104416-parsingresultfromcdsw.png

Step 7: Let's route on the sentiment

104417-routingsentimentpolarity.png

We can have negative (<0), neutral (0), positive (>0) and very positive (1) polarity of the sentiment. See TextBlob for more information on how this works.

Step 8: Send bad sentiment to a slack channel for human analysis.

104406-putslack.png

We send all the related information to a slack channel including the message.

Example Message Sent to Slack

104434-slackmsg.png

Step 9: Store all the results (or some) in either Phoenix/HBase, Hive LLAP, Impala, Kudu or HDFS.

Results as Attributes

104423-polarityreturned.png


Slack Message Call
${msg:append(" User:"):append(${user_name}):append(${handle}):append(" Geo:"):append(${coordinates}):append(${geo}):append(${location}):append(${place}):append(" Hashtags:"):append(${hashtags}):append(" Polarity:"):append(${polarity}):append(" Subjectivity:"):append(${subjectivity}):append(" Friends Count:"):append(${friends_count}):append(" Followers Count:"):append(${followers_count}):append(" Retweet Count:"):append(${retweet_count}):append(" Source:"):append(${source}):append(" Time:"):append(${time}):append(" Tweet ID:"):append(${tweet_id})}

REST CALL to Model
{"accessKey":"from your workbench","request":{"sentence":"${msg:replaceAll('\"', ''):replaceAll('\n','')}"}}


Resources


parsingresultfromcdsw.pngclouderasession.png
1,320 Views
Don't have an account?
Coming from Hortonworks? Activate your account here
Version history
Revision #:
2 of 2
Last update:
‎08-17-2019 04:49 AM
Updated by:
 
Contributors
Top Kudoed Authors