fastmath.kernel.density — generateme/fastmath 3.0.0-alpha2

bandwidth clj

(bandwidth kernel data h)

Returns infered bandwidth (h).

h can be one of:

• :nrd - rule-of-thumb (scale=1.06)
• :nrd0 - rule-of-thumb (scake=0.9)
• :nrd-adjust - kernel specific adjustment of :nrd, doesn't work for silverman and cauchy
• :rlcv - robust likelihood cross-validation
• :lcv - likelihood cross-validation
• :lscv - least squares cross-validation

cauchy clj

(cauchy x)

Cauchy kernel, experimental

cosine clj

(cosine x)

Cosine kernel

epanechnikov clj

(epanechnikov x)

Epanechnikov kernel

gaussian clj

(gaussian x)

Gaussian kernel

kde-data clj

Collection of KDE data.

Keys - kernel keyword, vals - kernel data

• :kernel - kernel fn
• :k2 - integral of K(x)^2
• :x2k - integral of x^2K(x)
• :delta0 - canonical bandwidth
• :efficiency - absolute efficiency
• :radius - radius of the function where function is positive or greater than 1.0e-10

kernel-density clj

(kernel-density kernel data)

(kernel-density kernel data params)

Returns kernel density estimation function, 1d

Arguments:

• kernel - kernel name or kernel function
• data - data
• params - a map containing:
  • :bandwidth - bandwidth h
  • :binned? - if data should be binned, if true the width of the bin is bandwidth divided by 5, if is a number then it will be used as denominator. Default: false.

:bandwidth can be a number or one of:

• :nrd - rule-of-thumb (scale=1.06)
• :nrd0 - rule-of-thumb (scake=0.9)
• :nrd-adjust - kernel specific adjustment of :nrd, doesn't work for silverman and cauchy
• :rlcv - robust likelihood cross-validation
• :lcv - likelihood cross-validation
• :lscv - least squares cross-validation

kernel-density+ clj

(kernel-density+ kernel data)

(kernel-density+ kernel data {:keys [bandwidth binned?]})

Returns kernel density estimation function with additional information, 1d.

Returns a map:

• :kde - density function
• :factor - 1/nh
• :h - provided or infered bandwidth
• :mn and :mx - infered extent of the kde`

For arguments see kernel-density

kernel-density-ci clj

(kernel-density-ci kernel data)

(kernel-density-ci kernel data {:keys [alpha] :or {alpha 0.05} :as params})

Create function which returns confidence intervals for given kde method.

Check 6.1.5 http://sfb649.wiwi.hu-berlin.de/fedc_homepage/xplore/tutorials/xlghtmlnode33.html

Arguments:

• data - sequence of data values
• kernel - kernel name
• bandwidth - as in kde
• alpha - confidence level parameter

Returns three values: density, lower confidence value and upper confidence value

laplace clj

(laplace x)

Laplace kernel, experimental

lcv-target clj

(lcv-target kdata)

Create target function to estimate bandwidth using Likelihood Cross Validation.

logistic clj

(logistic x)

Logistic kernel

lscv-target clj

(lscv-target kdata)

Create target function to estimate bandwidth using Least Squares Cross Validation.

quartic clj

(quartic x)

Quartic kernel

rlcv-target clj

(rlcv-target kdata)

Create target function to estimate bandwidth using Robust Likelihood Cross Validation.

sigmoid clj

(sigmoid x)

Sigmoid kernel

silverman clj

(silverman x)

Silverman kernel

triangular clj

(triangular x)

Triangular kernel

tricube clj

(tricube x)

Tricube kernel

triweight clj

(triweight x)

Triweight kernel

uniform clj

(uniform x)

Uniform kernel

wigner clj

(wigner x)

Wigner kernel, experimental