Options
All
  • Public
  • Public/Protected
  • All
Menu

External module "node_modules/@modelx/data/src/cross_validation"

Index

Type aliases

Variables

Functions

Object literals

Type aliases

TestTrainOutput

TestTrainOutput: { test: Data; train: Data }

Type declaration

TestTrainTuple

TestTrainTuple: [Data, Data]

TrainTestSplitOptions

TrainTestSplitOptions: { parse_int_train_size?: boolean; random_state?: number; return_array?: boolean; test_size?: number; train_size?: number }

Type declaration

  • Optional parse_int_train_size?: boolean
  • Optional random_state?: number
  • Optional return_array?: boolean
  • Optional test_size?: number
  • Optional train_size?: number

Variables

GridSearch

GridSearch: any

Functions

cross_validate_score

  • cross_validate_score(options?: {}): any[]

  • Used to test variance and bias of a prediction

    memberof

    cross_validation

    Parameters

    • Default value options: {} = {}

    Returns any[]

    Array of accucracy calculations

cross_validation_split

  • cross_validation_split(dataset?: any[], options?: { folds: number; random_state: number }): any[]

  • Provides train/test indices to split data in train/test sets. Split dataset into k consecutive folds. Each fold is then used once as a validation while the k - 1 remaining folds form the training set.

    memberof

    cross_validation

    example

    const testArray = [20, 25, 10, 33, 50, 42, 19, 34, 90, 23, ]; // [ [ 50, 20, 34, 33, 10 ], [ 23, 90, 42, 19, 25 ] ] const crossValidationArrayKFolds = ms.cross_validation.cross_validation_split(testArray, { folds: 2, random_state: 0, });

    Parameters

    • Default value dataset: any[] = []

      array of data to split

    • Default value options: { folds: number; random_state: number } = {folds: 3,random_state: 0,}
      • folds: number
      • random_state: number

    Returns any[]

    returns dataset split into k consecutive folds

grid_search

  • grid_search(options?: any): any

  • Used to test variance and bias of a prediction with parameter tuning

    memberof

    cross_validation

    Parameters

    • Default value options: any = {}

    Returns any

    Array of accucracy calculations

train_test_split

  • Split arrays into random train and test subsets

    memberof

    cross_validation

    example

    const testArray = [20, 25, 10, 33, 50, 42, 19, 34, 90, 23, ]; // { train: [ 50, 20, 34, 33, 10, 23, 90, 42 ], test: [ 25, 19 ] } const trainTestSplit = ms.cross_validation.train_test_split(testArray,{ test_size:0.2, random_state: 0, });

    Parameters

    • Default value dataset: Data = []

      array of data to split

    • Default value options: TrainTestSplitOptions = {test_size: 0.2,train_size: 0.8,random_state: 0,return_array: false,parse_int_train_size: true,}

    Returns {}[][] | { test: {}[]; train: {}[] }

    returns training and test arrays either as an object or arrays

Object literals

Const cross_validation

cross_validation: object
see

https://machinelearningmastery.com/implement-resampling-methods-scratch-python/

GridSearch

GridSearch: any

cross_validate_score

cross_validate_score: cross_validate_score

cross_validation_split

cross_validation_split: cross_validation_split

grid_search

grid_search: grid_search

kfolds

kfolds: cross_validation_split = cross_validation_split

train_test_split

train_test_split: train_test_split