mXrap - Xfit

Xfit

This library provides functions to perform fitting of 2D data to various functions. require.mx('mxjs/base/xdistributionfit.js');

QuickRef

BestFit
BestFit.exp
BestFit.exp_array
BestFit.expSimple
BestFit.expSimple_array
BestFit.linear
BestFit.linear_array
BestFit.log
BestFit.log_array
BestFit.piecewiseLinear
BestFit.piecewiseLinear_array
BestFit.polynomial
BestFit.polynomial_array
BestFit.power
BestFit.power_array
Create
Create.exp
Create.exponentialConstant
Create.expSimple
Create.linear
Create.log
Create.piecewiseLinear
Create.polynomial
Create.power
Measure
Measure.ks
Measure.ks_array
Measure.rmse
Measure.rmse_array
Measure.rsquare
Measure.rsquare_array
Result
Result.generateFunction
Result.getCoefficients
Result.getEquation
Result.loadFromJson
Result.saveAsJson
SetPoints
SetPoints.addPoint
SetPoints.fromArray
SetPoints.fromArray
BestFitter
BestFitter.addPoint
BestFitter.generateFunction
BestFitter.generator
BestFitter.getCoefficients
BestFitter.getEquation

Status	Name
	`BestFitter` BestFit.exp ( `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓optional_read_Filter ) Returns a bestfitter created by using a balanced exponential fit on the input data
	`BestFitter` BestFit.exp_array ( `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Returns a bestfitter created by using a balanced exponential fit on the input data
	`BestFitter` BestFit.expSimple ( `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓optional_read_Filter ) Returns a bestfitter created by using a simple exponential fit on the input data
	`BestFitter` BestFit.expSimple_array ( `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Returns a bestfitter created by using a simple exponential fit on the input data
	`BestFitter` BestFit.linear ( `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓optional_read_Filter ) Returns a bestfitter created by using a linear fit on the input data
	`BestFitter` BestFit.linear_array ( `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Returns a bestfitter created by using a linear fit on the input data
	`BestFitter` BestFit.log ( `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓optional_read_Filter ) Returns a bestfitter created by using a logarithmic fit on the input data
	`BestFitter` BestFit.log_array ( `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Returns a bestfitter created by using a logarithmic fit on the input data
	`BestFitter` BestFit.piecewiseLinear ( `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓optional_read_Filter ) Returns a piecewise linear interpolator on the input data. It returns fitted values as the linear interpolation between the closest data points in the set on either side of the input. If there are only points available on one side, it returns the value of the closest data point.
	`BestFitter` BestFit.piecewiseLinear_array ( `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Returns a piecewise linear interpolator on the input data. It returns fitted values as the linear interpolation between the closest data points in the set on either side of the input. If there are only points available on one side, it returns the value of the closest data point.
	`BestFitter` BestFit.polynomial ( `Number` ↓order, `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓optional_read_Filter ) Returns a bestfitter created by using a polynomial fit of the specified order on the input data
	`BestFitter` BestFit.polynomial_array ( `Number` ↓order, `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Returns a bestfitter created by using a polynomial fit of the specified order on the input data
	`BestFitter` BestFit.power ( `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓optional_read_Filter ) Returns a bestfitter created by using a power fit on the input data
	`BestFitter` BestFit.power_array ( `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Returns a bestfitter created by using a power fit on the input data
	`Bestfitter` Create.exp ( ) Creates a balanced exponential bestfitter.
	`Bestfitter` Create.exponentialConstant ( ) Creates a fitter for exponential with constant
	`Bestfitter` Create.expSimple ( ) Creates a simple exponential bestfitter. This variant is faster but is weighted towards values closer to zero.
	`Bestfitter` Create.linear ( ) Creates a linear bestfitter
	`Bestfitter` Create.log ( ) Creates a logarithmic (ln) bestfitter.
	`Bestfitter` Create.piecewiseLinear ( ) Creates a piecewise linear interpolator
	`Bestfitter` Create.polynomial ( `Number` order ) Creates a polynomial bestfitter for the specified order
	`Bestfitter` Create.power ( ) Creates a power bestfitter
	`Number` Measure.ks ( `BestFitter` ↓bestfitter, `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓optional_read_Filter ) Returns the Kolmogorov�Smirnov test result between the provided data points, and the fit from the provided bestfitter
	`Number` Measure.ks_array ( `BestFitter` ↓bestfitter, `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Returns the Kolmogorov�Smirnov test result between the provided data points, and the fit from the provided bestfitter
	`Number` Measure.rmse ( `BestFitter` ↓bestfitter, `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓optional_read_Filter ) Returns the root-mean-square-error result between the provided data points, and the fit from the provided bestfitter
	`Number` Measure.rmse_array ( `BestFitter` ↓bestfitter, `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Returns the root-mean-square-error result between the provided data points, and the fit from the provided bestfitter
	`Number` Measure.rsquare ( `BestFitter` ↓bestfitter, `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓optional_read_Filter ) Returns the R-square result between the provided data points, and the fit from the provided bestfitter
	`Number` Measure.rsquare_array ( `BestFitter` ↓bestfitter, `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Returns the R-square result between the provided data points, and the fit from the provided bestfitter
	`Function` Result.generateFunction ( `BestFitter` ↓bestfitter ) Returns a function f(x) that can be used to generate values for the best fitted equation.
	`Object` Result.getCoefficients ( `BestFitter` ↓bestfitter ) Gets the coefficients for a particular bestfitter. The coefficients are specific to each bestfitter type.
	`Text` Result.getEquation ( `BestFitter` ↓bestfitter ) Gets the textual representation of the equation for a particular bestfitter
	`BestFitter` Result.loadFromJson ( `Text` ↓text ) Returns a bestfitter as loaded from the JSON text
	`Text` Result.saveAsJson ( `BestFitter` ↓bestfitter ) Returns JSON text which contains the saved state of the bestfitter. This can be persisted to Table values or columns. It allows the Bestfitter to be saved and/or used in another calculation.
	SetPoints.addPoint ( `BestFitter` ↓bestfitter, `Number` x, `Number` y ) Adds input for a bestfitter object from a data point (x, y)
	SetPoints.fromArray ( `BestFitter` ↓bestfitter, `Array` ↓x_array, `Array` ↓y_array, `Number` ↓num_points ) Adds input for a bestfitter object from arrays
	SetPoints.fromArray ( `BestFitter` ↓bestfitter, `Table` ↓Table, `Function` ↓read_FieldX, `Function` ↓read_FieldY, `Function` ↓read_Filter ) Adds input for a bestfitter object from data table columns. The filter is optional, providing it will use only data points that passed the filter.

Category: BestFit

These functions provide a BestFitter object based on input.

↑bestfitter = Lib.BestFit.exp ( ↓Table, ↓read_FieldX, ↓read_FieldY, ↓optional_read_Filter ) Beta

Returns a bestfitter created by using a balanced exponential fit on the input data

Parameters:

Table ↓Table - Table containing the input data
Function ↓read_FieldX - Table read function for the x of the data points.
Function ↓read_FieldY - Table read function for the y of the data points.
Function ↓optional_read_Filter - optional Table read function for the filter

Returns: BestFitter ↑bestfitter

↑bestfitter = Lib.BestFit.exp_array ( ↓x_array, ↓y_array, ↓num_points ) Beta

Returns a bestfitter created by using a balanced exponential fit on the input data

Parameters:

Array ↓x_array - array containing the x of the data points
Array ↓y_array - array containing the y of the data points
Number ↓num_points - the number of data points provided in the arrays above.

Returns: BestFitter ↑bestfitter

↑bestfitter = Lib.BestFit.expSimple ( ↓Table, ↓read_FieldX, ↓read_FieldY, ↓optional_read_Filter ) Beta

Returns a bestfitter created by using a simple exponential fit on the input data

Parameters:

Table ↓Table - Table containing the input data
Function ↓read_FieldX - Table read function for the x of the data points.
Function ↓read_FieldY - Table read function for the y of the data points.
Function ↓optional_read_Filter - optional Table read function for the filter

Returns: BestFitter ↑bestfitter

↑bestfitter = Lib.BestFit.expSimple_array ( ↓x_array, ↓y_array, ↓num_points ) Beta

Returns a bestfitter created by using a simple exponential fit on the input data

Parameters:

Array ↓x_array - array containing the x of the data points
Array ↓y_array - array containing the y of the data points
Number ↓num_points - the number of data points provided in the arrays above.

Returns: BestFitter ↑bestfitter

↑bestfitter = Lib.BestFit.linear ( ↓Table, ↓read_FieldX, ↓read_FieldY, ↓optional_read_Filter ) Beta

Returns a bestfitter created by using a linear fit on the input data

Parameters:

Table ↓Table - Table containing the input data
Function ↓read_FieldX - Table read function for the x of the data points.
Function ↓read_FieldY - Table read function for the y of the data points.
Function ↓optional_read_Filter - optional Table read function for the filter

Returns: BestFitter ↑bestfitter

↑bestfitter = Lib.BestFit.linear_array ( ↓x_array, ↓y_array, ↓num_points ) Beta

Returns a bestfitter created by using a linear fit on the input data

Parameters:

Array ↓x_array - array containing the x of the data points
Array ↓y_array - array containing the y of the data points
Number ↓num_points - the number of data points provided in the arrays above.

Returns: BestFitter ↑bestfitter

↑bestfitter = Lib.BestFit.log ( ↓Table, ↓read_FieldX, ↓read_FieldY, ↓optional_read_Filter ) Beta

Returns a bestfitter created by using a logarithmic fit on the input data

Parameters:

Table ↓Table - Table containing the input data
Function ↓read_FieldX - Table read function for the x of the data points.
Function ↓read_FieldY - Table read function for the y of the data points.
Function ↓optional_read_Filter - optional Table read function for the filter

Returns: BestFitter ↑bestfitter

↑bestfitter = Lib.BestFit.log_array ( ↓x_array, ↓y_array, ↓num_points ) Beta

Returns a bestfitter created by using a logarithmic fit on the input data

Parameters:

Array ↓x_array - array containing the x of the data points
Array ↓y_array - array containing the y of the data points
Number ↓num_points - the number of data points provided in the arrays above.

Returns: BestFitter ↑bestfitter

↑interpolator = Lib.BestFit.piecewiseLinear ( ↓Table, ↓read_FieldX, ↓read_FieldY, ↓optional_read_Filter ) Beta

Returns a piecewise linear interpolator on the input data. It returns fitted values as the linear interpolation between the closest data points in the set on either side of the input. If there are only points available on one side, it returns the value of the closest data point.

Parameters:

Table ↓Table - Table containing the input data
Function ↓read_FieldX - Table read function for the x of the data points.
Function ↓read_FieldY - Table read function for the y of the data points.
Function ↓optional_read_Filter - optional Table read function for the filter

Returns: BestFitter ↑interpolator

↑interpolator = Lib.BestFit.piecewiseLinear_array ( ↓x_array, ↓y_array, ↓num_points ) Beta

Parameters:

Array ↓x_array - array containing the x of the data points
Array ↓y_array - array containing the y of the data points
Number ↓num_points - the number of data points provided in the arrays above.

Returns: BestFitter ↑interpolator

↑bestfitter = Lib.BestFit.polynomial ( ↓order, ↓Table, ↓read_FieldX, ↓read_FieldY, ↓optional_read_Filter ) Beta

Returns a bestfitter created by using a polynomial fit of the specified order on the input data

Parameters:

Number ↓order - order of the polynomial fit
Table ↓Table - Table containing the input data
Function ↓read_FieldX - Table read function for the x of the data points.
Function ↓read_FieldY - Table read function for the y of the data points.
Function ↓optional_read_Filter - optional Table read function for the filter

Returns: BestFitter ↑bestfitter

↑bestfitter = Lib.BestFit.polynomial_array ( ↓order, ↓x_array, ↓y_array, ↓num_points ) Beta

Returns a bestfitter created by using a polynomial fit of the specified order on the input data

Parameters:

Number ↓order - order of the polynomial fit
Array ↓x_array - array containing the x of the data points
Array ↓y_array - array containing the y of the data points
Number ↓num_points - the number of data points provided in the arrays above.

Returns: BestFitter ↑bestfitter

↑bestfitter = Lib.BestFit.power ( ↓Table, ↓read_FieldX, ↓read_FieldY, ↓optional_read_Filter ) Beta

Returns a bestfitter created by using a power fit on the input data

Parameters:

Table ↓Table - Table containing the input data
Function ↓read_FieldX - Table read function for the x of the data points.
Function ↓read_FieldY - Table read function for the y of the data points.
Function ↓optional_read_Filter - optional Table read function for the filter

Returns: BestFitter ↑bestfitter

↑bestfitter = Lib.BestFit.power_array ( ↓x_array, ↓y_array, ↓num_points ) Beta

Returns a bestfitter created by using a power fit on the input data

Parameters:

Array ↓x_array - array containing the x of the data points
Array ↓y_array - array containing the y of the data points
Number ↓num_points - the number of data points provided in the arrays above.

Returns: BestFitter ↑bestfitter

Category: Create

These functions create bestfitter data objects.

↑bestfitter = Lib.Create.exp ( ) Beta

Creates a balanced exponential bestfitter.

Parameters:

Returns: Bestfitter ↑bestfitter

↑bestfitter = Lib.Create.exponentialConstant ( ) Beta

Creates a fitter for exponential with constant

Parameters:

Returns: Bestfitter ↑bestfitter

↑bestfitter = Lib.Create.expSimple ( ) Beta

Creates a simple exponential bestfitter. This variant is faster but is weighted towards values closer to zero.

Parameters:

Returns: Bestfitter ↑bestfitter

↑bestfitter = Lib.Create.linear ( ) Beta

Creates a linear bestfitter

Parameters:

Returns: Bestfitter ↑bestfitter

↑bestfitter = Lib.Create.log ( ) Beta

Creates a logarithmic (ln) bestfitter.

Parameters:

Returns: Bestfitter ↑bestfitter

↑bestfitter = Lib.Create.piecewiseLinear ( ) Beta

Creates a piecewise linear interpolator

Parameters:

Returns: Bestfitter ↑bestfitter

↑bestfitter = Lib.Create.polynomial ( order ) Beta

Creates a polynomial bestfitter for the specified order

Parameters:

Number order - of polynomial fitting

Returns: Bestfitter ↑bestfitter

↑bestfitter = Lib.Create.power ( ) Beta

Creates a power bestfitter

Parameters:

Returns: Bestfitter ↑bestfitter

Category: Measure

These functions compute a measure of goodness of fit given the original input points (or an alternative sample set) and the BestFitter object.

↑ks = Lib.Measure.ks ( ↓bestfitter, ↓Table, ↓read_FieldX, ↓read_FieldY, ↓optional_read_Filter ) Beta

Returns the Kolmogorov�Smirnov test result between the provided data points, and the fit from the provided bestfitter

Parameters:

BestFitter ↓bestfitter - bestfitter object to compare against
Table ↓Table - Table containing the data points
Function ↓read_FieldX - Table read function for the x of the data points.
Function ↓read_FieldY - Table read function for the y of the data points.
Function ↓optional_read_Filter - optional Table read function for the filter

Returns: Number ↑ks - - the Kolmogorov�Smirnov test result

↑ks = Lib.Measure.ks_array ( ↓bestfitter, ↓x_array, ↓y_array, ↓num_points ) Beta

Returns the Kolmogorov�Smirnov test result between the provided data points, and the fit from the provided bestfitter

Parameters:

BestFitter ↓bestfitter - bestfitter object to compare against
Array ↓x_array - array containing the x of the data points
Array ↓y_array - array containing the y of the data points
Number ↓num_points - the number of data points provided in the arrays above.

Returns: Number ↑ks - - the Kolmogorov�Smirnov test result

↑rmse = Lib.Measure.rmse ( ↓bestfitter, ↓Table, ↓read_FieldX, ↓read_FieldY, ↓optional_read_Filter ) Beta

Returns the root-mean-square-error result between the provided data points, and the fit from the provided bestfitter

Parameters:

BestFitter ↓bestfitter - bestfitter object to compare against
Table ↓Table - Table containing the data points
Function ↓read_FieldX - Table read function for the x of the data points.
Function ↓read_FieldY - Table read function for the y of the data points.
Function ↓optional_read_Filter - optional Table read function for the filter

Returns: Number ↑rmse - - the root-mean-square-error result

↑rmse = Lib.Measure.rmse_array ( ↓bestfitter, ↓x_array, ↓y_array, ↓num_points ) Beta

Returns the root-mean-square-error result between the provided data points, and the fit from the provided bestfitter

Parameters:

BestFitter ↓bestfitter - bestfitter object to compare against
Array ↓x_array - array containing the x of the data points
Array ↓y_array - array containing the y of the data points
Number ↓num_points - the number of data points provided in the arrays above.

Returns: Number ↑rmse - - the root-mean-square-error result

↑rsquare = Lib.Measure.rsquare ( ↓bestfitter, ↓Table, ↓read_FieldX, ↓read_FieldY, ↓optional_read_Filter ) Beta

Returns the R-square result between the provided data points, and the fit from the provided bestfitter

Parameters:

BestFitter ↓bestfitter - bestfitter object to compare against
Table ↓Table - Table containing the data points
Function ↓read_FieldX - Table read function for the x of the data points.
Function ↓read_FieldY - Table read function for the y of the data points.
Function ↓optional_read_Filter - optional Table read function for the filter

Returns: Number ↑rsquare - - the R-square result

↑rsquare = Lib.Measure.rsquare_array ( ↓bestfitter, ↓x_array, ↓y_array, ↓num_points ) Beta

Returns the R-square result between the provided data points, and the fit from the provided bestfitter

Parameters:

BestFitter ↓bestfitter - bestfitter object to compare against
Array ↓x_array - array containing the x of the data points
Array ↓y_array - array containing the y of the data points
Number ↓num_points - the number of data points provided in the arrays above.

Returns: Number ↑rsquare - - the R-square result

Category: Result

These functions extract output from a bestfitter object after input has been specified.

↑function = Lib.Result.generateFunction ( ↓bestfitter ) Beta

Returns a function f(x) that can be used to generate values for the best fitted equation.

Parameters:

BestFitter ↓bestfitter

Returns: Function ↑function - this function takes a single numeric input x, and returns the fitted value for x.

↑coefficients = Lib.Result.getCoefficients ( ↓bestfitter ) Beta

Gets the coefficients for a particular bestfitter. The coefficients are specific to each bestfitter type.

Parameters:

BestFitter ↓bestfitter

Returns: Object ↑coefficients

↑equation = Lib.Result.getEquation ( ↓bestfitter ) Beta

Gets the textual representation of the equation for a particular bestfitter

Parameters:

BestFitter ↓bestfitter

Returns: Text ↑equation

↑bestfitter = Lib.Result.loadFromJson ( ↓text ) Beta

Returns a bestfitter as loaded from the JSON text

Parameters:

Text ↓text

Returns: BestFitter ↑bestfitter

↑text = Lib.Result.saveAsJson ( ↓bestfitter ) Beta

Returns JSON text which contains the saved state of the bestfitter. This can be persisted to Table values or columns. It allows the Bestfitter to be saved and/or used in another calculation.

Parameters:

BestFitter ↓bestfitter

Returns: Text ↑text

Category: SetPoints

These functions provide data to a bestfitter object.

Lib.SetPoints.addPoint ( ↓bestfitter, x, y ) Beta

Adds input for a bestfitter object from a data point (x, y)

Parameters:

BestFitter ↓bestfitter - - the BestFitter to add the data point to
Number x
Number y

Lib.SetPoints.fromArray ( ↓bestfitter, ↓x_array, ↓y_array, ↓num_points ) Beta

Adds input for a bestfitter object from arrays

Parameters:

BestFitter ↓bestfitter - - the Bestfitter to add data points to
Array ↓x_array - - input array containing x of data points
Array ↓y_array - - input array containing y of data points
Number ↓num_points - - number of data points (size of the x, y arrays)

Lib.SetPoints.fromArray ( ↓bestfitter, ↓Table, ↓read_FieldX, ↓read_FieldY, ↓read_Filter ) Beta

Adds input for a bestfitter object from data table columns. The filter is optional, providing it will use only data points that passed the filter.

Parameters:

BestFitter ↓bestfitter - - the Bestfitter to add data points to
Table ↓Table - - input Table containing data points
Function ↓read_FieldX - - input Table read Function containing x of data points
Function ↓read_FieldY - - input Table read Function containing y of data points
Function ↓read_Filter - - optional input Table read Function containing filter

Class: BestFitter

A BestFitter object contains the calculated coefficients from a data set and can compute the fitted value for input.

Status	Name
	addPoint ( `Number` x, `Number` y ) Adds the data point (x, y) provided, and recomputes the fit
	`Function` generateFunction ( ) Generates a function f(x) that will compute the fitted value for any input x. The function once generated is standalone from the BestFitter (function will not change if you provide additional data points to this BestFitter that changes the coefficients)
	`Number` generator ( `Number` x ) Computes the fitted value for a specified input x
	`Object` getCoefficients ( ) Returns an object containing the coefficients for this bestfitter. How the coefficients are stored or specified is specific to the BestFitter type.
	`Text` getEquation ( ) Gets a textual representation of the fitted equation.

BestFitter.addPoint ( x, y ) Beta

Adds the data point (x, y) provided, and recomputes the fit

Parameters:

Number x
Number y

BestFitter.generateFunction ( ) Beta

Generates a function f(x) that will compute the fitted value for any input x. The function once generated is standalone from the BestFitter (function will not change if you provide additional data points to this BestFitter that changes the coefficients)

Parameters:

Returns: Function function - - a function f(x) that will compute the fitted value for input x.

BestFitter.generator ( x ) Beta

Computes the fitted value for a specified input x

Parameters:

Number x

Returns: Number y - fitted value for x

BestFitter.getCoefficients ( ) Beta

Returns an object containing the coefficients for this bestfitter. How the coefficients are stored or specified is specific to the BestFitter type.

Parameters:

Returns: Object coefficients - - coefficients object. How the coefficients are stored or specified is specific to the BestFitter type.

BestFitter.getEquation ( ) Beta

Gets a textual representation of the fitted equation.

Parameters:

Returns: Text equation - - textual representation of the fitted equation

Libraries

Categories

Classes

Xfit

Category: BestFit

Category: Create

Category: Measure

Category: Result

Category: SetPoints

Class: BestFitter