Machine learning backends - Revision history

Devdocsbot: Protected "Machine learning backends": Developer Docs Migration ([Edit=Allow only administrators] (indefinite))

2022-05-31T05:34:08Z

Protected "Machine learning backends": Developer Docs Migration ([Edit=Allow only administrators] (indefinite))

← Older revision	Revision as of 05:34, 31 May 2022
(No difference)

Devdocsbot: Update migration status and path

2022-05-31T05:32:10Z

Update migration status and path

← Older revision		Revision as of 05:32, 31 May 2022
Line 1:		Line 1:
			{{Template:Migrated\|newDocId=/docs/apis/plugintypes/mlbackend/}}
	== Introduction ==		== Introduction ==
	Machine learning backends process the datasets generated from the indicators and targets calculated by the Analytics API. They are used for machine learning training, prediction and models evaluation. May be good that you also read [https://docs.moodle.org/dev/Analytics_API Analytics API] to read some concept definitions, how these concepts are implemented in Moodle and how machine learning backend plugins fit into the analytics API.		Machine learning backends process the datasets generated from the indicators and targets calculated by the Analytics API. They are used for machine learning training, prediction and models evaluation. May be good that you also read [https://docs.moodle.org/dev/Analytics_API Analytics API] to read some concept definitions, how these concepts are implemented in Moodle and how machine learning backend plugins fit into the analytics API.

Ilyatregubov at 07:20, 6 April 2022

2022-04-06T07:20:23Z

← Older revision		Revision as of 07:20, 6 April 2022
Line 9:		Line 9:
	The '''PHP backend''' is the default predictions processor as it is written in PHP and does not have any external dependencies. It is using logistic regression.		The '''PHP backend''' is the default predictions processor as it is written in PHP and does not have any external dependencies. It is using logistic regression.

	The '''Python backend''' requires ''python'' binary (either python 2 or python 3) and [https://pypi.python.org/pypi?name=moodlemlbackend&version=0.0.5&:action=display moodlemlbackend python package] which is maintained by Moodle HQ. Python version and its libraries versions used are very important. We recommend to use 3.7 for mlbackend 3.x version. It is based on [https://www.tensorflow.org/ Google's tensorflow library] and it is using a feed-forward neural network with 1 single hidden layer. ''moodlemlbackend'' package does store model performance information that can be visualised using [https://www.tensorflow.org/get_started/summaries_and_tensorboard tensorboard]. Information generated during models evaluation is available through the models management page, under each model ''Actions > Log'' menu. ''moodlemlbackend'' source code is available in https://github.com/moodlehq/moodle-mlbackend-python.		The '''Python backend''' requires ''python'' binary (either python 2 or python 3) and [https://pypi.python.org/pypi?name=moodlemlbackend&version=0.0.5&:action=display moodlemlbackend python package] which is maintained by Moodle HQ. Python version and its libraries versions used are '''very important'''. We recommend to use 3.7 for mlbackend 3.x version. It is based on [https://www.tensorflow.org/ Google's tensorflow library] and it is using a feed-forward neural network with 1 single hidden layer. ''moodlemlbackend'' package does store model performance information that can be visualised using [https://www.tensorflow.org/get_started/summaries_and_tensorboard tensorboard]. Information generated during models evaluation is available through the models management page, under each model ''Actions > Log'' menu. ''moodlemlbackend'' source code is available in https://github.com/moodlehq/moodle-mlbackend-python.

	'''Python backend is recommended over the PHP''' as it is able to predict more accurately than the PHP backend and it is faster.		'''Python backend is recommended over the PHP''' as it is able to predict more accurately than the PHP backend and it is faster.

Ilyatregubov: Explicitly mention working python version for mlbackend

2022-04-06T07:20:03Z

Explicitly mention working python version for mlbackend

Smoked: /* Backends included in Moodle core */ grammar catch

2020-06-30T22:41:46Z

Backends included in Moodle core: grammar catch

← Older revision		Revision as of 22:41, 30 June 2020
Line 10:		Line 10:
	== Backends included in Moodle core ==		== Backends included in Moodle core ==

	The '''PHP backend''' is the default predictions processor as it is written in PHP and do not have any external dependencies. It is using logistic regression.		The '''PHP backend''' is the default predictions processor as it is written in PHP and does not have any external dependencies. It is using logistic regression.

	The '''Python backend''' requires ''python'' binary (either python 2 or python 3) and [https://pypi.python.org/pypi?name=moodlemlbackend&version=0.0.5&:action=display moodlemlbackend python package] which is maintained by Moodle HQ. It is based on [https://www.tensorflow.org/ Google's tensorflow library] and it is using a feed-forward neural network with 1 single hidden layer. ''moodlemlbackend'' package does store model performance information that can be visualised using [https://www.tensorflow.org/get_started/summaries_and_tensorboard tensorboard]. Information generated during models evaluation is available through the models management page, under each model ''Actions > Log'' menu. ''moodlemlbackend'' source code is available in https://github.com/moodlehq/moodle-mlbackend-python.		The '''Python backend''' requires ''python'' binary (either python 2 or python 3) and [https://pypi.python.org/pypi?name=moodlemlbackend&version=0.0.5&:action=display moodlemlbackend python package] which is maintained by Moodle HQ. It is based on [https://www.tensorflow.org/ Google's tensorflow library] and it is using a feed-forward neural network with 1 single hidden layer. ''moodlemlbackend'' package does store model performance information that can be visualised using [https://www.tensorflow.org/get_started/summaries_and_tensorboard tensorboard]. Information generated during models evaluation is available through the models management page, under each model ''Actions > Log'' menu. ''moodlemlbackend'' source code is available in https://github.com/moodlehq/moodle-mlbackend-python.

Dmonllao: /* Predictor */

2019-12-16T08:58:48Z

Predictor

← Older revision		Revision as of 08:58, 16 December 2019
Line 58:		Line 58:
	*		*
	* @param string $modeloutputdir The model directory id (parent of all model versions subdirectories).		* @param string $modeloutputdir The model directory id (parent of all model versions subdirectories).
			* @param string $uniqueid The site model unique id string
	* @return null		* @return null
	*/		*/
	public function delete_output_dir($modeloutputdir);		public function delete_output_dir($modeloutputdir, $uniqueid);

	===== Classifier =====		===== Classifier =====

Emdalton1: /* Regressor / added @param string $trainedmodeldir per MDL-64787

2019-06-28T23:38:55Z

Regressor: added * @param string $trainedmodeldir per MDL-64787

← Older revision		Revision as of 23:38, 28 June 2019
Line 139:		Line 139:
	* @param \stored_file $dataset		* @param \stored_file $dataset
	* @param string $outputdir		* @param string $outputdir
			* @param string $trainedmodeldir
	* @return \stdClass		* @return \stdClass
	*/		*/
	public function evaluate_regression($uniqueid, $maxdeviation, $niterations, \stored_file $dataset, $outputdir);		public function evaluate_regression($uniqueid, $maxdeviation, $niterations, \stored_file $dataset, $outputdir);

Emdalton1: /* Classifier / added @param string $trainedmodeldir per MDL-64787

2019-06-28T23:37:53Z

Classifier: added * @param string $trainedmodeldir per MDL-64787

← Older revision		Revision as of 23:37, 28 June 2019
Line 98:		Line 98:
	* @param \stored_file $dataset		* @param \stored_file $dataset
	* @param string $outputdir		* @param string $outputdir
			* @param string $trainedmodeldir
	* @return \stdClass		* @return \stdClass
	*/		*/

Dmonllao: /* Introduction */

2019-03-27T10:49:05Z

Introduction

← Older revision		Revision as of 10:49, 27 March 2019
Line 5:		Line 5:

	The communication between machine learning backends and Moodle is through files because the code that will process the dataset can be written in PHP, in Python, in other languages or even use cloud services. This needs to be scalable so they are expected to be able to manage big files and train algorithms reading input files in batches if necessary.		The communication between machine learning backends and Moodle is through files because the code that will process the dataset can be written in PHP, in Python, in other languages or even use cloud services. This needs to be scalable so they are expected to be able to manage big files and train algorithms reading input files in batches if necessary.

			Machine learning backend is a new Moodle plugin type. They are stored in lib/mlbackend, where you can add your own plugins.

	== Backends included in Moodle core ==		== Backends included in Moodle core ==

Dmonllao: /* Regressor */

2017-12-27T08:06:32Z

Regressor

← Older revision		Revision as of 08:06, 27 December 2017
Line 103:		Line 103:

	A [https://en.wikipedia.org/wiki/Regression_analysis regressor] predicts the value of an outcome (or dependent) variable based on analysis of the indicators. This value is linear, such as a final grade in a course or the likelihood a student is to pass a course. This machine learning algorithm is "supervised": It requires a training data set of elements whose classification is known (e.g. courses in the past with a clear definition of whether the student has dropped out or not). This is an interface to be implemented by machine learning backends that support regression. It extends ''Predictor'' interface.		A [https://en.wikipedia.org/wiki/Regression_analysis regressor] predicts the value of an outcome (or dependent) variable based on analysis of the indicators. This value is linear, such as a final grade in a course or the likelihood a student is to pass a course. This machine learning algorithm is "supervised": It requires a training data set of elements whose classification is known (e.g. courses in the past with a clear definition of whether the student has dropped out or not). This is an interface to be implemented by machine learning backends that support regression. It extends ''Predictor'' interface.

			Both these methods and ''Predictor'' methods should be implemented.

	/**		/**