Classifier<'a, 'l> (FSharp.Stats)

KNN.Classifier<'a, 'l> Type

Namespace: FSharp.Stats.ML.Unsupervised
Assembly: FSharp.Stats.dll
Parent Module: KNN
Base Type: obj

The [k-nearest neighbors algorithm](https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm) to classify new data points into their target classes, depending on the features of their neighboring data points.

Convencience methods for using `KNN.Array.predict`, similiar to `KNeighborsClassifier` in `sklearn.neighbors`.

Example

 let reds  = [| [ 2.0; 4.0 ]; [ 1.0; 3.0 ]; [ 2.0; 4.0 ]; [ 3.0; 2.0 ]; [ 2.0; 1.0 ] |]
 let blues = [| [ 5.0; 6.0 ]; [ 4.0; 5.0 ]; [ 4.0; 6.0 ]; [ 6.0; 6.0 ]; [ 5.0; 4.0 ] |]
 
 let knnClassifier = KNN.Classifier(FSharp.Stats.DistanceMetrics.euclidean, 3)
 
 // fit the classifier and predict new points
 // version 1.
 let labeledPoints = Map [ "blue", blues; "red", reds ]
 knnClassifier.fit(labeledPoints)
 let color  = knnClassifier.predict [3.0; 3.0] // should be: Some "red"
 let colors = knnClassifier.predict [| [3.0; 3.0]; [6.0; 6.0] |] // should be: [| Some "red"; Some "blue" |]
 
 // version 2.
 let points = Array.append reds blues
 let labels = [| "red"; "red"; "red"; "red"; "red"; "blue"; "blue"; "blue"; "blue"; "blue" |]
 knnClassifier.fit(points, labels)
 let color  = knnClassifier.predict [3.0; 3.0] // should be: Some "red"
 let colors = knnClassifier.predict [| [3.0; 3.0]; [6.0; 6.0] |] // should be: [| Some "red"; Some "blue" |]

val reds: float list array

val blues: float list array

val knnClassifier: obj

namespace Microsoft.FSharp

val labeledPoints: Map<string,float list array>

Multiple items
module Map from Microsoft.FSharp.Collections

--------------------
type Map<'Key,'Value (requires comparison)> = interface IReadOnlyDictionary<'Key,'Value> interface IReadOnlyCollection<KeyValuePair<'Key,'Value>> interface IEnumerable interface IStructuralEquatable interface IComparable interface IEnumerable<KeyValuePair<'Key,'Value>> interface ICollection<KeyValuePair<'Key,'Value>> interface IDictionary<'Key,'Value> new: elements: ('Key * 'Value) seq -> Map<'Key,'Value> member Add: key: 'Key * value: 'Value -> Map<'Key,'Value> ...

--------------------
new: elements: ('Key * 'Value) seq -> Map<'Key,'Value>

val color: obj

val colors: obj

val points: float list array

module Array from Microsoft.FSharp.Collections

val append: array1: 'T array -> array2: 'T array -> 'T array

val labels: string array

Record fields

Record Field	Description
`labeledPoints` Full Usage: `labeledPoints` Field type: `('a * 'l) array` Modifiers: mutable	Field type: `('a * 'l) array`

Constructors

Constructor Description

Constructor	Description
`Classifier(distance, k)` Full Usage: `Classifier(distance, k)` Parameters: distance : `Distance<'a>` k : `int` Returns: `Classifier<'a, 'l>`	distance : `Distance<'a>` k : `int` Returns: `Classifier<'a, 'l>`


                
                  
                    
                      Classifier(distance, k)

Full Usage: Classifier(distance, k)

Parameters:

distance : Distance<'a>

k : int

Returns: Classifier<'a, 'l>

distance : Distance<'a>
k : int

Returns: Classifier<'a, 'l>

Instance members

Instance member	Description
`this.K` Full Usage: `this.K`
`this.OverwriteK` Full Usage: `this.OverwriteK` Parameters: k : `int` - The _positive_ number of nearest neighbors from x to look for. Returns: `int option`	Overwrite the parameter `k` from the constructor. k : `int` The _positive_ number of nearest neighbors from x to look for. Returns: `int option`
`this.fit labeledPoints` Full Usage: `this.fit labeledPoints` Parameters: labeledPoints : `Map<'l, 'a array>` - the array of classified (or labeled) points [in the format "Map"], used for the classification	Fit the constructed `KNN.Classifier`, i.e. provide the points with their labels, used for the prediction. labeledPoints : `Map<'l, 'a array>` the array of classified (or labeled) points [in the format "Map"], used for the classification Example `// .. construct the knnClassifier before .. let reds = [\| [ 2.0; 4.0 ]; [ 1.0; 3.0 ]; [ 2.0; 4.0 ]; [ 3.0; 2.0 ]; [ 2.0; 1.0 ] \|] let blues = [\| [ 5.0; 6.0 ]; [ 4.0; 5.0 ]; [ 4.0; 6.0 ]; [ 6.0; 6.0 ]; [ 5.0; 4.0 ] \|] let labeledPoints = Map [ "blue", blues; "red", reds ] knnClassifier.fit(labeledPoints)` val reds: float list array val blues: float list array val labeledPoints: Map<string,float list array> Multiple items module Map from Microsoft.FSharp.Collections -------------------- type Map<'Key,'Value (requires comparison)> = interface IReadOnlyDictionary<'Key,'Value> interface IReadOnlyCollection<KeyValuePair<'Key,'Value>> interface IEnumerable interface IStructuralEquatable interface IComparable interface IEnumerable<KeyValuePair<'Key,'Value>> interface ICollection<KeyValuePair<'Key,'Value>> interface IDictionary<'Key,'Value> new: elements: ('Key * 'Value) seq -> Map<'Key,'Value> member Add: key: 'Key * value: 'Value -> Map<'Key,'Value> ... -------------------- new: elements: ('Key * 'Value) seq -> Map<'Key,'Value>
`this.fit (points, labels)` Full Usage: `this.fit (points, labels)` Parameters: points : `'a array` - the array of points labels : `'l array` - the array of labels for the `points`	Fit the constructed `KNN.Classifier`, i.e. provide the points with their labels, used for the prediction. Fails if `points` and `labels` do not have the same length. points : `'a array` the array of points labels : `'l array` the array of labels for the `points` Example `// .. construct the knnClassifier before .. let points = seq { [ 2.0; 4.0 ]; [ 1.0; 3.0 ]; [ 2.0; 4.0 ]; [ 3.0; 2.0 ]; [ 2.0; 1.0 ]; [ 5.0; 6.0 ]; [ 4.0; 5.0 ]; [ 4.0; 6.0 ]; [ 6.0; 6.0 ]; [ 5.0; 4.0 ] } let labels = seq { "red"; "red"; "red"; "red"; "red"; "blue"; "blue"; "blue"; "blue"; "blue" } knnClassifier.fit(points, labels)` val points: float list seq Multiple items val seq: sequence: 'T seq -> 'T seq -------------------- type 'T seq = System.Collections.Generic.IEnumerable<'T> val labels: string seq
`this.fit labeledPoints` Full Usage: `this.fit labeledPoints` Parameters: labeledPoints : `('a * 'l) array` - the array of classified (or labeled) points [in the format (point, label)], used for the classification	Fit the constructed `KNN.Classifier`, i.e. provide the points with their labels, used for the prediction. labeledPoints : `('a * 'l) array` the array of classified (or labeled) points [in the format (point, label)], used for the classification Example `// .. construct the knnClassifier before .. let points = seq { [ 2.0; 4.0 ]; [ 1.0; 3.0 ]; [ 2.0; 4.0 ]; [ 3.0; 2.0 ]; [ 2.0; 1.0 ]; [ 5.0; 6.0 ]; [ 4.0; 5.0 ]; [ 4.0; 6.0 ]; [ 6.0; 6.0 ]; [ 5.0; 4.0 ] } let labels = seq { "red"; "red"; "red"; "red"; "red"; "blue"; "blue"; "blue"; "blue"; "blue" } let labeledPoints = Seq.zip points labels knnClassifier.fit(labeledPoints)` val points: float list seq Multiple items val seq: sequence: 'T seq -> 'T seq -------------------- type 'T seq = System.Collections.Generic.IEnumerable<'T> val labels: string seq val labeledPoints: (float list * string) seq module Seq from Microsoft.FSharp.Collections val zip: source1: 'T1 seq -> source2: 'T2 seq -> ('T1 * 'T2) seq
`this.predict (points, ?overwriteK)` Full Usage: `this.predict (points, ?overwriteK)` Parameters: points : `'a array` - the array of points to be classified. ?overwriteK : `int` - Returns: `'l option array`	Predict (or classify) the given collection of points. points : `'a array` the array of points to be classified. ?overwriteK : `int` Returns: `'l option array` Example `// .. construct and fit the knnClassifier before .. knnClassifier.predict [\| [3.0; 3.0]; [6.0; 6.0] \|] // should be: [\| Some "red"; Some "blue" \|]`
`this.predict (x, ?overwriteK)` Full Usage: `this.predict (x, ?overwriteK)` Parameters: x : `'a` - the point to be classified. ?overwriteK : `int` - Returns: `'l option`	Predict (or classify) the given point. x : `'a` the point to be classified. ?overwriteK : `int` Returns: `'l option` Example `// .. construct and fit the knnClassifier before .. knnClassifier.predict [3.0; 3.0] // should be: Some "red"`