Best-first feature selection

Best-first feature selection | BigML.com

FREE

Details:

Created	Thu, 8 Oct 2026 15:02:53 +0000
Published	Thu, 8 Oct 2026 17:25:58 +0000

Description:

Find the best features for modeling using a greedy algorithm

Tags:

BigMLer BigMLer_ThuOct0826_170252 first feature selection

URL:

https://bigml.com/user/whizzml/gallery/script/6ac7b09d426c2387bb0fdd60

Script FREE

Source code

;; A simple function to get the max value in a list
(define (get-max xs) (reduce (lambda (x y) (if (> x y) x y)) (head xs) xs))

;; Get feature names given ids
(define (feature-names dataset-id ids)
  (let (fields ((fetch dataset-id) "fields"))
    (map (lambda (id) (fields [id "name"])) ids)))

;; Get the default set of input fields for this dataset (all preferred
;; fields minus the objective field).
(define (default-inputs dataset-id obj-id)
  (let (fields ((fetch dataset-id) "fields")
        fids (keys fields))
    (filter (lambda (k) (and (fields [k "preferred"] false) (not (= obj-id k))))
            fids)))

;; Make a list of models using the given dataset, objective field and
;; selected features.  For each model, add one of the potential
;; features in potentials to the input feature list.
(define (make-models dataset-id obj-field selected potentials)
  (let (model-req {"dataset" dataset-id "objective_field" obj-field}
        make-req (lambda (fid)
                   (assoc model-req "input_fields" (cons fid selected)))
        all-reqs (map make-req potentials))
    (create-and-wait* "model" all-reqs)))

;; Given a test dataset, a list of potential features, and a list of
;; model ids corresponding to those features, select the best
;; potential feature by performing an evaluation on each model and
;; returning the feature with the best performance.
(define (select-feature test-dataset-id potentials model-ids)
  (let (eval-req {"dataset" test-dataset-id}
        make-req (lambda (mid) (assoc eval-req "model" mid))
        all-reqs (map make-req model-ids)
        evs (map fetch (create-and-wait* "evaluation" all-reqs))
        vs (map (lambda (ev) (ev ["result" "model" "average_phi"] 0)) evs)
        value-map (make-map potentials vs)
        max-val (get-max vs)
        choose-best (lambda (id) (and (= max-val (value-map id)) id)))
    (some choose-best potentials)))

;; Retrieves and checks whether the objective field of the given
;; dataset is categorical, raising an error otherwise.
(define (get-objective ds-id obj-id)
  (let (obj-id (if (empty? obj-id)
                   (dataset-get-objective-id ds-id)
                   obj-id)
        otype ((fetch ds-id) ["fields" obj-id "optype"] "missing"))
    (when (not (= "categorical" otype))
      (raise (str "The dataset's objective field must be categorical, "
                  "but is " otype)))
    obj-id))

;; Do best-first feature selection.  Given a dataset and a target
;; number of features iteratively construct models for each feature,
;; evaluate them, and add the feature corresponding to the best
;; evaluation to the running set of features.  Stop when you reach the
;; target number, or you run out of features.
(define (select-features dataset-id nfeatures rate objective-id)
  (let (obj-id (get-objective dataset-id objective-id)
        input-ids (default-inputs dataset-id obj-id)
        [train-id test-id] (create-random-dataset-split dataset-id rate))
    (loop (selected []
           potentials input-ids)
      (if (or (>= (count selected) nfeatures) (empty? potentials))
        (feature-names dataset-id selected)
        (let (_ (log-info "Making models...")
              model-ids (make-models train-id obj-id selected potentials)
              _ (log-info "Selecting feature...")
              next-feat (select-feature test-id potentials model-ids)
              _ (log-info "Selected feature is " next-feat))
          (recur (cons next-feat selected)
                 (filter (lambda (id) (not (= id next-feat))) potentials)))))))

(define output-features
  (select-features dataset-id n split-fraction objective-id))

Description

Inputs

Outputs

License: Creative Commons Zero V1.0
Script FREE

Best-first feature selection | BigML.com

Sending Request...

COMPANY

PRODUCT

BUSINESS

TRAINING

GALLERY

License

Embed this Script in your web site

COMPANY

PRODUCT

BUSINESS

TRAINING

GALLERY