Inspire icon

Inspire

The Inspire plugin implements open source, transparent next-generation learning analytics using machine learning backends that go beyond simple descriptive analytics to provide predictions of learner success, and ultimately diagnosis and prescriptions (advisements) to learners and teachers. From Moodle HQ.
Price option: Free

Supports Moodle 3.3 See all versions
Latest release: 9 years ago
Installations: 33
Downloads (last 90 days): 8

Frankenstyle name: tool_inspire
Administration tools

Comments

Comments are no longer open for new posts. Existing comments remain available to read.

Hello.
Up to Moodle version 3.3, this plugin's downloads and implementations stats are easily trackable.
For example, as of today:
Latest release: 5 years
73 sites
26 downloads
28 fans
Starting Moodle version 3.4, this INSPIRE plugin is a built-in feature. How can I find the number of activations or active "implementations" of this feature?
Any help really appreciated.
Thanks a lot.
FN
Hi,
Does the plugin work in the moodle 3.9 environment?
Hi Elyse,
- If you are talking about the students at risk model; from a user point of view this model insights are only available at course level.
- If you are talking about the API for developers; it is up to the model to define the level (course, category, whatever internal organisation) where these insights will be generated; we provide default reports for the generated predictions (the insights report at the level the model defined) but the API allows each model to do basically whatever you want with the predictions generated by the system: From sending notifications to feeding external systems
For either 3.3 as a plugin or 3.4 in core, are these reports only able to be viewed/pulled in specific courses or could you pull them on a site-wide or program-wide basis? For example, could I look at all students in our Grad program vs all students in our Traditional Undergrad?
Each activity module needs to be enhanced to support Inspire. Currently, the Core modules have been enhanced for Moodle 3.4. Third party or locally developed plugins will need to be updated by their maintainers to be included in Inspire calculations.
Hello
Can I set up a custom installed activity module?
Hi María,
PHP 7 is required by the PHP machine learning library we are using. You can either use the python predictions processor or upgrade PHP to 7.x branch.
Regards,
David
Hello,
First of all I´d like to congratulate you on this tool, it´s a great idea.
I'm trying to test it, but I can not evaluate. In the platform where I am testing it I have two courses, one of them is finished to get the training data, and the other is unfinished.
The problem is in "Evaluate", I tried to do it from the platform and from cli, and in both cases appears the following error.
Error evaluate from platform:
[Wed May 24 11:25:29.547753 2017] [:error] [pid 25338:tid 139897838999296] [client 80.30.25.191:53053] FastCGI: server "/usr/lib/cgi-bin/php5-fcgi" stderr: PHP message: PHP Warning: Unsupported declare 'strict_types' in /home/www/dev/dev-inserver/moodle/moodle33/admin/tool/inspire/predict/php/phpml/src/Phpml/Classification/Linear/Perceptron.php on line 3, referer: http://dev.inserver.es/moodle33/admin/tool/inspire/index.php
[Wed May 24 11:25:29.547780 2017] [:error] [pid 25338:tid 139897838999296] [client 80.30.25.191:53053] FastCGI: server "/usr/lib/cgi-bin/php5-fcgi" stderr: PHP message: PHP Fatal error: Default value for parameters with a class type hint can only be NULL in /home/www/dev/dev-inserver/moodle/moodle33/admin/tool/inspire/predict/php/phpml/src/Phpml/Classification/Linear/Perceptron.php on line 73, referer: http://dev.inserver.es/moodle33/admin/tool/inspire/index.php
Error evaluate from cli:
Analysing the site
The site contents are calculated and stored in batches, during evaluation you can stop the process at any moment, the next time you run it it will continue from the point you stopped it.
Processing site contents
PHP Warning: Unsupported declare 'strict_types' in /home/www/dev/dev-inserver/moodle/moodle33/admin/tool/inspire/predict/php/phpml/src/Phpml/Classification/Linear/Perceptron.php on line 3
Warning: Unsupported declare 'strict_types' in /home/www/dev/dev-inserver/moodle/moodle33/admin/tool/inspire/predict/php/phpml/src/Phpml/Classification/Linear/Perceptron.php on line 3
PHP Fatal error: Default value for parameters with a class type hint can only be NULL in /home/www/dev/dev-inserver/moodle/moodle33/admin/tool/inspire/predict/php/phpml/src/Phpml/Classification/Linear/Perceptron.php on line 73
Fatal error: Default value for parameters with a class type hint can only be NULL in /home/www/dev/dev-inserver/moodle/moodle33/admin/tool/inspire/predict/php/phpml/src/Phpml/Classification/Linear/Perceptron.php on line 73
dev01@dev-insrv:/home/www/dev/dev-inserver/moodle/moodle33/admin/tool/inspire/cli$
Please, could you tell me if I'm doing something wrong?
Thank you
Hi Mike,
Thanks for the report. The file that can't be found is the trained machine learning model, the prediction process needs it to base its predictions on it. Do you have any previous error logs? We check that the model is enabled and trained before prediction, the only possible causes I can think of without looking at the code is that the training set was empty but we did still flag the model as trained, any of your test site courses has a past end date with some students activity between the start of the course and its end? We should only flag the model as trained when there is at least 1 valid course, just asking to discard scenarios. Another cause could be a change in the models directory setting (I don't think you did any changes, you use the default one). I am looking at it. In any case feel free to create an issue in https://github.com/moodlehq/moodle-tool_inspire/issues, this is not the expected behaviour and needs to be investigated.
Trying to run this on a test site...
I get the error:
tool_inspire/errorcantloadmodel
More information about this error
Debug info:
Error code: errorcantloadmodel
$a contents: [dataroot]/models/1/1494958559/execution/model.ser
Stack trace:
line 120 of /admin/tool/inspire/predict/php/classes/processor.php: moodle_exception thrown
line 490 of /admin/tool/inspire/classes/model.php: call to predict_php\processor->predict()
line 122 of /admin/tool/inspire/model.php: call to tool_inspire\model->predict()
Approval issue created: CONTRIB-6895