RAPIDS
    Preparing search index...

    Class UMAP

    Hierarchy (View Summary)

    Index

    Constructors

    constructor

    Accessors

    a b embeddings init initialAlpha learningRate localConnectivity minDist nComponents negativeSampleRate nEpochs nNeighbors randomState repulsionStrength setOpMixRatio spread targetMetric targetNNeighbors targetWeight transformQueueSize verbosity

    Methods

    fitArray fitDataFrame fitSeries getEmbeddings getUMAPParams setUMAPParams

    Constructors

    • Initialize a UMAP object

      Parameters

      • input: UMAPParams = {}

      Returns UMAP

    Accessors

    • get embeddings(): Embeddings

      Returns Embeddings

      Embeddings in low-dimensional space in float32 format, which can be converted to any of the following types: DataFrame, Series, DeviceBuffer.

      // returns DataFrame<{[K extends number]: Series<Float32>}>
      embeddings.asDataFrame();
      // returns Series<Float32>
      embeddings.asSeries();
      // returns rmm.DeviceBuffer
      embeddings.asDeviceBuffer();
    • get initialAlpha(): number

      Returns number

    • get learningRate(): number

      Returns number

    • get localConnectivity(): number

      Returns number

    • get minDist(): number

      Returns number

    • get nComponents(): number

      Returns number

    • get negativeSampleRate(): number

      Returns number

    • get nEpochs(): number

      Returns number

    • get nNeighbors(): number

      Returns number

    • get randomState(): number

      Returns number

    • get repulsionStrength(): number

      Returns number

    • get setOpMixRatio(): number

      Returns number

    • get spread(): number

      Returns number

    • get targetMetric(): string

      Returns string

    • get targetNNeighbors(): number

      Returns number

    • get targetWeight(): number

      Returns number

    • get transformQueueSize(): number

      Returns number

    • get verbosity(): string

      Returns string

    Methods

    • Fit features into an embedded space.

      Parameters

      • features: MemoryData

        array containing floats or doubles in the format [x1, y1, z1, x2, y2, z2...] for features x, y & z.

        // For a sample dataset of colors, with properties r,g and b:
        features = [
          ...Object.values({ r: xx1, g: xx2, b: xx3 }),
          ...Object.values({ r: xx4, g: xx5, b: xx6 }),
        ] // [xx1, xx2, xx3, xx4, xx5, xx6]
      • Optionaltarget: MemoryData | null

        array containing target values

        // For a sample dataset of colors, with properties r,g and b:
        target = [color1, color2] // len(target) = nFeatures
      • OptionalnFeatures: number

        number of properties in the input features, if features is of the format [x1, y1, x2, y2...]

      Returns FittedUMAP

      FittedUMAP object with updated embeddings

      This method will automatically convert the inputs to float32

    • Fit features into an embedded space.

      Parameters

      • features: DeviceBuffer

        array containing floats or doubles in the format [x1, y1, z1, x2, y2, z2...] for features x, y & z.

        // For a sample dataset of colors, with properties r,g and b:
        features = [
          ...Object.values({ r: xx1, g: xx2, b: xx3 }),
          ...Object.values({ r: xx4, g: xx5, b: xx6 }),
        ] // [xx1, xx2, xx3, xx4, xx5, xx6]
      • Optionaltarget: DeviceBuffer | null

        array containing target values

        // For a sample dataset of colors, with properties r,g and b:
        target = [color1, color2] // len(target) = nFeatures
      • OptionalnFeatures: number

        number of properties in the input features, if features is of the format [x1, y1, x2, y2...]

      Returns FittedUMAP

      FittedUMAP object with updated embeddings

      This method will automatically convert the inputs to float32

    • Fit features into an embedded space.

      Type Parameters

      Parameters

      • features: T

        array containing floats or doubles in the format [x1, y1, z1, x2, y2, z2...] for features x, y & z.

        // For a sample dataset of colors, with properties r,g and b:
        features = [
          ...Object.values({ r: xx1, g: xx2, b: xx3 }),
          ...Object.values({ r: xx4, g: xx5, b: xx6 }),
        ] // [xx1, xx2, xx3, xx4, xx5, xx6]
      • Optionaltarget: R | null

        array containing target values

        // For a sample dataset of colors, with properties r,g and b:
        target = [color1, color2] // len(target) = nFeatures
      • OptionalnFeatures: number

        number of properties in the input features, if features is of the format [x1, y1, x2, y2...]

      Returns FittedUMAP

      FittedUMAP object with updated embeddings

      This method will automatically convert the inputs to float32

    • Fit features into an embedded space.

      Parameters

      • features: (number | bigint | null | undefined)[]

        array containing floats or doubles in the format [x1, y1, z1, x2, y2, z2...] for features x, y & z.

        // For a sample dataset of colors, with properties r,g and b:
        features = [
          ...Object.values({ r: xx1, g: xx2, b: xx3 }),
          ...Object.values({ r: xx4, g: xx5, b: xx6 }),
        ] // [xx1, xx2, xx3, xx4, xx5, xx6]
      • Optionaltarget: (number | bigint | null | undefined)[] | null

        array containing target values

        // For a sample dataset of colors, with properties r,g and b:
        target = [color1, color2] // len(target) = nFeatures
      • OptionalnFeatures: number

        number of properties in the input features, if features is of the format [x1, y1, x2, y2...]

      Returns FittedUMAP

      FittedUMAP object with updated embeddings

      This method will automatically convert the inputs to float32

    • Fit features into an embedded space

      Type Parameters

      Parameters

      • features: DataFrame<{ [P in string]: T }>

        Dense or sparse matrix containing floats or doubles. Acceptable dense formats: cuDF DataFrame

      • Optionaltarget: Series<R>

        cuDF Series containing target values

        // For a sample dataset of colors, with properties r,g and b:
        target = [color1, color2] // len(target) = nFeatures

      Returns FittedUMAP

      FittedUMAP object with updated embeddings

      This method will automatically convert the inputs to float32

    • Fit features into an embedded space

      Type Parameters

      Parameters

      • features: T

        cuDF Series containing floats or doubles in the format [x1, y1, z1, x2, y2, z2...] for features x, y & z.

      • Optionaltarget: R | null

        cuDF Series containing target values

        // For a sample dataset of colors, with properties r,g and b:
        target = [color1, color2] // len(target) = nFeatures
      • nFeatures: number = 1

        number of properties in the input features, if features is of the format [x1,y1,x2,y2...]

      Returns FittedUMAP

      FittedUMAP object with updated embeddings

      This method will automatically convert the inputs to float32

    • Returns Embeddings

      Embeddings in low-dimensional space in dtype format, which can be converted to any of the following types: DataFrame, Series, DeviceBuffer.

      // returns DataFrame<{[K extends number]: Series<Float32>}>
      getEmbeddings(new Float64).asDataFrame();
      // returns Series<Float32>
      getEmbeddings(new Int32).asSeries();
      // returns rmm.DeviceBuffer
      getEmbeddings(new UInt32).asDeviceBuffer();

    • Returns UMAPParams

    • Parameters

      • input: UMAPParams

      Returns void

    Settings

    Member Visibility

    On This Page

    Constructors
    Accessors
    Methods