r语言机器学习随机森林包

/***************************************************************** Copyright (C) 2001-2012 Leo Breiman, Adele Cutler and Merck & Co., Inc. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. C driver for Breiman & Cutler's random forest code. Re-written from the original main program in Fortran. Andy Liaw Feb. 7, 2002. Modifications to get the forest out Matt Wiener Feb. 26, 2002. *****************************************************************/ #include <R.h> #include <R_ext/Utils.h> #include "rf.h" void oob(int nsample, int nclass, int *jin, int *cl, int *jtr,int *jerr, int *counttr, int *out, double *errtr, int *jest, double *cutoff); void TestSetError(double *countts, int *jts, int *clts, int *jet, int ntest, int nclass, int nvote, double *errts, int labelts, int *nclts, double *cutoff); /* Define the R RNG for use from Fortran. */ void F77_SUB(rrand)(double *r) { *r = unif_rand(); } void classRF(double *x, int *dimx, int *cl, int *ncl, int *cat, int *maxcat, int *sampsize, int *strata, int *Options, int *ntree, int *nvar, int *ipi, double *classwt, double *cut, int *nodesize, int *outcl, int *counttr, double *prox, double *imprt, double *impsd, double *impmat, int *nrnodes, int *ndbigtree, int *nodestatus, int *bestvar, int *treemap, int *nodeclass, double *xbestsplit, double *errtr, int *testdat, double *xts, int *clts, int *nts, double *countts, int *outclts, int *labelts, double *proxts, double *errts, int *inbag) { /****************************************************************** * C wrapper for random forests: get input from R and drive * the Fortran routines. * * Input: * * x: matrix of predictors (transposed!) * dimx: two integers: number of variables and number of cases * cl: class labels of the data * ncl: number of classes in the response * cat: integer vector of number of classes in the predictor; * 1=continuous * maxcat: maximum of cat * Options: 7 integers: (0=no, 1=yes) * add a second class (for unsupervised RF)? * 1: sampling from product of marginals * 2: sampling from product of uniforms * assess variable importance? * calculate proximity? * calculate proximity based on OOB predictions? * calculate outlying measure? * how often to print output? * keep the forest for future prediction? * ntree: number of trees * nvar: number of predictors to use for each split * ipi: 0=use class proportion as prob.; 1=use supplied priors * pi: double vector of class priors * nodesize: minimum node size: no node with fewer than ndsize * cases will be split * * Output: * * outcl: class predicted by RF * counttr: matrix of votes (transposed!) * imprt: matrix of variable importance measures * impmat: matrix of local variable importance measures * prox: matrix of proximity (if iprox=1) ******************************************************************/ int nsample0, mdim, nclass, addClass, mtry, ntest, nsample, ndsize, mimp, nimp, near, nuse, noutall, nrightall, nrightimpall, keepInbag, nstrata; int jb, j, n, m, k, idxByNnode, idxByNsample, imp, localImp, iprox, oobprox, keepf, replace, stratify, trace, *nright, *nrightimp, *nout, *nclts, Ntree; int *out, *bestsplitnext, *bestsplit, *nodepop, *jin, *nodex, *nodexts, *nodestart, *ta, *ncase, *jerr, *varUsed, *jtr, *classFreq, *idmove, *jvr, *at, *a, *b, *mind, *nind, *jts, *oobpair; int **strata_idx, *strata_size, last, ktmp, nEmpty, ntry; double av=0.0, delta=0.0; double *tgini, *tx, *wl, *classpop, *tclasscat, *tclasspop, *win, *tp, *wr; addClass = Options[0]; imp = Options[1]; localImp = Options[2]; iprox = Options[3]; oobprox = Options[4]; trace = Options[5]; keepf = Options[6]; replace = Options[7]; stratify = Options[8]; keepInbag = Options[9]; mdim = dimx[0]; nsample0 = dimx[1]; nclass = (*ncl==1) ? 2 : *ncl; ndsize = *nodesize; Ntree = *ntree; mtry = *nvar; ntest = *nts; nsample = addClass ? (nsample0 + nsample0) : nsample0; mimp = imp ? mdim : 1; nimp = imp ? nsample : 1; near = iprox ? nsample0 : 1; if (trace == 0) trace = Ntree + 1; tgini = (double *) S_alloc(mdim, sizeof(double)); wl = (double *) S_alloc(nclass, sizeof(double)); wr = (double *) S_alloc(nclass, sizeof(double)); classpop = (double *) S_alloc(nclass* *nrnodes, sizeof(double)); tclasscat = (double *) S_alloc(nclass*32, sizeof(double)); tclasspop = (double *) S_alloc(nclass, sizeof(double)); tx = (double *) S_alloc(nsample, sizeof(double)); win = (double *) S_alloc(nsample, sizeof(double)); tp = (double *) S_alloc(nsample, sizeof(double)); out = (int *) S_alloc(nsample, sizeof(int)); bestsplitnext = (int *) S_alloc(*nrnodes, sizeof(int)); bestsplit = (int *) S_alloc(*nrnodes, sizeof(int)); nodepop = (int *) S_alloc(*nrnodes, sizeof(int)); nodestart = (int *) S_alloc(*nrnodes, sizeof(int)); jin = (int *) S_alloc(nsample, sizeof(int)); nodex = (int *) S_alloc(nsample, sizeof(int)); nodexts = (int *) S_alloc(ntest, sizeof(int)); ta = (int *) S_alloc(nsample, sizeof(int)); ncase = (int *) S_alloc(nsample, sizeof(int)); jerr = (int *) S_alloc(nsample, sizeof(int)); varUsed = (int *) S_alloc(mdim, sizeof(int)); jtr = (int *) S_alloc(nsample, sizeof(int)); jvr = (int *) S_alloc(nsample, sizeof(int)); classFreq = (int *) S_alloc(nclass, sizeof(int)); jts = (int *) S_alloc(ntest, sizeof(int)); idmove = (int *) S_alloc(nsample, sizeof(int)); at = (int *) S_alloc(mdim*nsample, sizeof(int)); a = (int *) S_alloc(mdim*nsample, sizeof(int)); b = (int *) S_alloc(mdim*nsample, sizeof(int)); mind = (int *) S_alloc(mdim, sizeof(int)); nright = (int *) S_alloc(nclass, sizeof(int)); nrightimp = (int *) S_alloc(nclass, sizeof(int)); nout = (int *) S_alloc(nclass, sizeof(int)); if (oobprox) { oobpair = (int *) S_alloc(near*near, sizeof(int)); } /* Count number of cases in each class. */ zeroInt(classFreq, nclass); for (n = 0; n < nsample; ++n) classFreq[cl[n] - 1] ++; /* Normalize class weights. */ normClassWt(cl, nsample, nclass, *ipi, classwt, classFreq); if (stratify) { /* Count number of strata and frequency of each stratum. */ nstrata = 0; for (n = 0; n < nsample0; ++n) if (strata[n] > nstrata) nstrata = strata[n]; /* Create the array of pointers, each pointing to a vector of indices of where data of each stratum is. */ strata_size = (int *) S_alloc(nstrata, sizeof(int)); for (n = 0; n < nsample0; ++n) { strata_size[strata[n] - 1] ++; } strata_idx = (int **) S_alloc(nstrata, sizeof(int *)); for (n = 0; n < ns