# FKSUM v0.1.4

0

Monthly downloads

## Fast Kernel Sums

Implements the method of Hofmeyr, D.P. (2019) <DOI:10.1109/TPAMI.2019.2930501> for fast evaluation of univariate kernel smoothers based on recursive computations.
Applications to the basic problems of density and regression function estimation are provided, as well as some projection pursuit methods
for which the objective is based on non-parametric functionals of the projected density, or conditional density of a response given projected
covariates.

## Functions in FKSUM

Name | Description | |

f_ica | Projection index for independent component analysis. | |

kndksum | Kernel and kernel derivative sums | |

FKSUM-package | Fast Exact Kernel Smoothing | |

fk_mdh | Minimum density hyperplanes | |

ksum | Kernel sums | |

fk_md_dp | C++ code for evaluating partial gradient of mimimum density hyperplane w.r.t. projected data | |

plot.fk_ppr | Plot method for class fk_ppr | |

bin_wts | Compute discrete bin weights | |

fk_md_b | Minimum density hyperplane orthogonal to a vector | |

fk_md | C++ code for evaluating mimimum density hyperplane from projected data | |

plot.fk_mdh | Plot method for class fk_mdh | |

df_ppr | Gradient of the projection index for projection pursuit regression | |

fk_sum | Fast Exact Kernel Sum Evaluation | |

h_Gauss_to_K | Bandwidth conversion from Gaussian | |

print.fk_mdh | Print method for class fk_mdh | |

cbin_alloc | Allocation of points to bins | |

predict.fk_regression | Predict method for class fk_regression | |

fk_density | Fast univariate kernel density estimation | |

df_ica | Gradient of projection index for independent component analysis. | |

dksum | Kernel derivative sums | |

h_K_to_Gauss | Bandwidth conversion to Gaussian | |

fk_NW | Nadaraya-Watson regression estimator | |

fk_fmdh | Projection index for finding minimum density hyperplanes | |

fk_dfmdh | Gradient of projection index for finding minimum density hyperplanes | |

fancy_PPR_initialisation | Initialisation for PPR based on Ridge LM after GAM type smoothing | |

fk_is_minim_md | Check if MDH constraints are active | |

predict.fk_ppr | Predict method for class fk_ppr | |

whiten | Whitening (standardising) a data matrix | |

print.fk_ppr | Print method for class fk_ppr | |

fk_ICA | Independent component analysis with sample entropy estimated via kernel density | |

plot.fk_regression | Plot method for class fk_regression | |

kLLreg | Leave-one-out regression smoother | |

sm_bin_wts | Compute smoothed bin weights | |

fk_ppr | Projection pursuit regression with local linear kernel smoother | |

plot.fk_ICA | Plot method for class fk_ICA | |

fk_loc_lin | Local linear regression estimator | |

norm_K | The L2 norm of a kernel | |

plot.fk_density | Plot method for class fk_density | |

print.fk_ICA | Print method for class fk_ICA | |

fk_regression | Fast univariate kernel regression | |

norm_const_K | Normalising constant for kernels in FKSUM | |

var_K | Variance of a kernel | |

plot_kernel | Plot the shape of a kernel function implemented in FKSUM based on its vector of beta coefficients | |

print.fk_density | Print method for class fk_density | |

print.fk_regression | Print method for class fk_regression | |

roughness_K | Kernel roughness | |

f_ppr | Projection index for projection pursuit regression | |

No Results! |

## Last month downloads

## Details

Type | Package |

License | GPL |

Encoding | UTF-8 |

LinkingTo | Rcpp, RcppArmadillo |

LazyData | true |

NeedsCompilation | yes |

Packaged | 2020-04-29 06:02:14 UTC; david |

Repository | CRAN |

Date/Publication | 2020-04-29 06:30:02 UTC |

imports | MASS , rARPACK |

depends | Rcpp (>= 0.12.16) |

linkingto | RcppArmadillo |

Contributors | David Hofmeyr |

#### Include our badge in your README

```
[![Rdoc](http://www.rdocumentation.org/badges/version/FKSUM)](http://www.rdocumentation.org/packages/FKSUM)
```