Hands-on Lab: Develop test suites for machine learning models and data with Deepchecks

Опубликовано: 01 Январь 1970
на канале: 650 AI Lab

2,118

Deepchecks Open Source is a python library for data scientists and ML engineers. The package includes extensive test suites for machine learning models and data, built in a way that’s flexible, extendable and editable.

Deepchecks test suites are composed of checks. Each check contains outputs to display in a notebook and/or conditions with a pass/fail output.

Conditions can be added or removed from a check;
Checks can be edited or added/removed to a suite;
Suites can be created from scratch or forked from an existing suite.

The final outcome of the test or test(s) is the report as HTML output. This Report, starts with a list of the Conditions (and which passed or not) and then continues with the Display Data (from the various checks).

Content Timeline:
-----------------
(00:00) Video start
(00:08) Lab Intro
(01:48) When to use Deepchecks
(03:04) Getting started
(03:55) Test Suite Functions
(05:27) Integration in ML Pipeline
(06:15) Data Validation Tests
(10:42) Individual test setup
(12:40) Test result HTML
(15:17) Data Distribution Tests
(25:00) Data Distribution Tests 2
(29:44) Writing custom tests
(39:35) Model analysis and validation tests
(51:21) Random Forest classifier model tests
(54:04) Gradient Boosting Classifier model tests
(56:22) Code push to GitHub
(57:26) Lab Recap
(58:48) Credits

Deepchecks GitHub:
https://github.com/deepchecks/deepchecks

Source Code in this hands-on Lab:
https://github.com/prodramp/publiccod...

Please visit:
------------------
Prodramp LLC | https://prodramp.com | @prodramp
/ prodramp

Content Creator: Avkash Chauhan (@avkashchauhan)
/ avkashchauhan

Tags:
#ai #aicloud #h2oai #driverlessai #machinelearning #cloud #mlops #model #collaboration #deeplearning #modelserving #modeldeployment #keras #tensorflow #pytorch #datarobot #datahub #aiplatform #aicloud #modelperformance #modelfit #modeleffect #modelimpact #bias #modelbias #modeldeployment #modelregistery #modelpipeline #neptuneai #librosa #pythondsp #pythonaudio #spotify #spotipy #streamlit #pythonapps #deepchecks #modeltesting