Class Pegasos

Primal Estimated sub-GrAdientSOlver for SVM

Index

Constructors

Properties

_b _do_projection _itr _k _r _t _w _x _y

Methods

fit init predict update

Constructors

constructor

new Pegasos(rate: number, k?: number): Pegasos
Parameters
- rate: number
  Learning rate
- Optionalk: number
  Batch size
Returns Pegasos
- Defined in lib/model/pegasos.d.ts:9

Properties

_b

_b: any

_do_projection

_do_projection: boolean

_itr

_itr: number

_k

_k: number

_r

_r: number

_t

_t: number

_w

_w: any

_x

_x: number[][]

_y

_y: (-1 | 1)[]

Methods

fit

fit(): void
Fit model parameters.

Returns void
- Defined in lib/model/pegasos.d.ts:34

init

init(train_x: number[][], train_y: (-1 | 1)[]): void
Initialize this model.
Parameters
- train_x: number[][]
  Training data
- train_y: (-1 | 1)[]
  Target values
Returns void
- Defined in lib/model/pegasos.d.ts:19

predict

predict(data: number[][]): (-1 | 1)[]
Returns predicted values.
Parameters
- data: number[][]
  Sample data
Returns (-1 | 1)[]
Predicted values
- Defined in lib/model/pegasos.d.ts:40

update

update(x: number[][], y: (-1 | 1)[]): void
Update model parameters with some data.
Parameters
- x: number[][]
  Training data
- y: (-1 | 1)[]
  Target value
Returns void
- Defined in lib/model/pegasos.d.ts:30