[MDL-67040] Improve the performance of the Analytics ML layer when using small datasets - Moodle Tracker

XML

Word

Printable

Details

Type: New Feature
Status: Closed
Priority: Minor
Resolution: Fixed
Affects Version/s: 3.9
Fix Version/s: 3.9
Component/s: Analytics
Labels:
- ci
- release_notes
- triaged

Affected Branches:
MOODLE_39_STABLE
Fixed Branches:
MOODLE_39_STABLE
Pull from Repository:
git://github.com/dmonllao/moodle.git
Pull Master Branch:
~~MDL-67040~~_master
Pull Master Diff URL:
https://github.com/dmonllao/moodle/compare/MDL-67040_master~...MDL-67040_master
Testing Instructions:
Hide

Prerequisites:

Need python3

Need pip3 (apt-get install python3-pip)

Testing

Install the new version of the python package

git clone git://github.com/dmonllao/moodle-mlbackend-python.git

cd moodle-mlbackend-python

git checkout MDL-67040_master

pip3 install setuptools wheel

pip3 install -e .

Confirm that you did not see any error during the installation process

Check the version:

python3 -m moodlemlbackend.version

Confirm that the version reported was 2.4.0

Set $CFG->pathtopython = '/full/path/to/python3'; in your config.php (to just specify 'python3' is probably enough)

Unit tests including PHPUNIT_LONGTEST should pass and no analytics tests should be skipped. You can do it running the command below:

vendor/bin/phpunit analytics/tests/prediction_test.php
Show
Prerequisites: Need python3 Need pip3 (apt-get install python3-pip) Testing Install the new version of the python package git clone git://github.com/dmonllao/moodle-mlbackend-python.git cd moodle-mlbackend-python git checkout MDL-67040_master pip3 install setuptools wheel pip3 install -e . Confirm that you did not see any error during the installation process Check the version: python3 -m moodlemlbackend.version Confirm that the version reported was 2.4.0 Set $CFG->pathtopython = '/full/path/to/python3'; in your config.php (to just specify 'python3' is probably enough) Unit tests including PHPUNIT_LONGTEST should pass and no analytics tests should be skipped. You can do it running the command below: vendor/bin/phpunit analytics/tests/prediction_test.php

Description

The ML layer has some hardcoded values that may not help models generalise well to all sort of sites. These parameters should change depending on the data available for training.

Attachments

Issue Links

is blocked by

MDL-67622 The evaluation metrics are not ready for multiclass in the python ML backend

Closed

Activity

People

Assignee:: David Monllaó

Reporter:: David Monllaó

Peer reviewer:: Victor Déniz Falcón

Integrator:: Eloy Lafuente (stronk7)

Tester:: Eloy Lafuente (stronk7)

Participants:: CiBoT, David Monllaó, Eloy Lafuente (stronk7), Victor Déniz Falcón

Component watchers:: David Woloszyn, Huong Nguyen, Jake Dallimore, Meirza, Michael Hawkins, Raquel Ortega, Safat Shahin, Stevani Andolo

Votes:: 0 Vote for this issue

Watchers:: 5 Start watching this issue

Dates

Created:: 28/Oct/19 2:59 PM

Updated:: 24/May/21 6:00 PM

Resolved:: 17/Jan/20 1:56 AM

Fix Release Date:: 15/Jun/20

Time Tracking

Estimated:

Not Specified

Remaining:

Logged:

1w 3h