ML

Description:

  A record for machine learning algorithms.

ML.Operator

Type: Enumeration.

Description:

  Enumeration for comparison operators

Signature:

enum Operator
	"return"
	"<="
	">"
	"=="
end

BuildDecisionTreeAsync

Type: Function.

Description:

  A function that takes CSV data as input and applies the C4.5 machine learning algorithm to build a decision tree model asynchronously. C4.5 is a decision tree algorithm that uses information gain to select the best attribute to split the data at each node of the tree. The resulting decision tree can be used to make predictions on new data.

Signature:

BuildDecisionTreeAsync: function(
		csvData: string,
		maxDepth: integer,
		handler: function(depth: integer, name: string, op: Operator, value: string)
	): --[[accuracy]] number, --[[error]] string

Parameters:

Parameter	Type	Description
csvData	string	The CSV training data for building the decision tree using delimiter ,.
maxDepth	integer	The maximum depth of the generated decision tree. Set to 0 to prevent limiting the generated tree depth.
handler	function	The callback function to be called for each node of the generated decision tree.

Returns:

Return Type	Description
number｜nil	The accuracy of the decision tree on the training data.
string	An error message if an error occurred during building of the decision tree.

Definition for handler:

• Parameters of handler:

Parameter	Type	Description
depth	integer	The depth of the current node in the decision tree.
name	string	The name of the attribute used for splitting the data at the current node.
op	Operator	The comparison operator used for splitting the data at the current node.
value	string	The value used for splitting the data at the current node.

QLearner

Type: Field.

Description:

  A field for accessing QLearner class.

Signature:

QLearner: QLearnerClass