All Downloads are FREE. Search and download functionalities are using the official Maven repository.

hex.tree.ScoreBuildHistogram Maven / Gradle / Ivy

There is a newer version: 3.46.0.6
Show newest version
package hex.tree;

import hex.Distribution;
import water.H2O.H2OCountedCompleter;
import water.MRTask;
import water.fvec.C0DChunk;
import water.fvec.Chunk;
import water.util.ArrayUtils;
import water.util.AtomicUtils;

/**  Score and Build Histogram
 *
 * 

Fuse 2 conceptual passes into one: * *

* *
Pass 1:
Score a prior partially-built tree model, and make new Node assignments to * every row. This involves pulling out the current assigned DecidedNode, * "scoring" the row against that Node's decision criteria, and assigning the * row to a new child UndecidedNode (and giving it an improved prediction).
* *
Pass 2:
Build new summary DHistograms on the new child UndecidedNodes * every row got assigned into. Collect counts, mean, variance, min, * max per bin, per column.
*
* *

The result is a set of DHistogram arrays; one DHistogram array for each * unique 'leaf' in the tree being histogramed in parallel. These have node * ID's (nids) from 'leaf' to 'tree._len'. Each DHistogram array is for all * the columns in that 'leaf'. * *

The other result is a prediction "score" for the whole dataset, based on * the previous passes' DHistograms. */ public class ScoreBuildHistogram extends MRTask { final int _k; // Which tree final int _ncols;// Active feature columns final int _nbins;// Numerical columns: Number of bins in each histogram final int _nbins_cats;// Categorical columns: Number of bins in each histogram final DTree _tree; // Read-only, shared (except at the histograms in the Nodes) final int _leaf; // Number of active leaves (per tree) // Histograms for every tree, split & active column final DHistogram _hcs[/*tree-relative node-id*/][/*column*/]; final Distribution.Family _family; public ScoreBuildHistogram(H2OCountedCompleter cc, int k, int ncols, int nbins, int nbins_cats, DTree tree, int leaf, DHistogram hcs[][], Distribution.Family family) { super(cc); _k = k; _ncols= ncols; _nbins= nbins; _nbins_cats= nbins_cats; _tree = tree; _leaf = leaf; _hcs = hcs; _family = family; } /** Marker for already decided row. */ static public final int DECIDED_ROW = -1; /** Marker for sampled out rows */ static public final int OUT_OF_BAG = -2; static public boolean isOOBRow(int nid) { return nid <= OUT_OF_BAG; } static public boolean isDecidedRow(int nid) { return nid == DECIDED_ROW; } static public int oob2Nid(int oobNid) { return -oobNid + OUT_OF_BAG; } static public int nid2Oob(int nid) { return -nid + OUT_OF_BAG; } // Once-per-node shared init @Override public void setupLocal( ) { // Init all the internal tree fields after shipping over the wire _tree.init_tree(); // Allocate local shared memory histograms for( int l=_leaf; l<_tree._len; l++ ) { DTree.UndecidedNode udn = _tree.undecided(l); DHistogram hs[] = _hcs[l-_leaf]; int sCols[] = udn._scoreCols; if( sCols != null ) { // Sub-selecting just some columns? for( int col : sCols ) // For tracked cols hs[col].init(); } else { // Else all columns for( int j=0; j<_ncols; j++) // For all columns if( hs[j] != null ) // Tracking this column? hs[j].init(); } } } @Override final public void map( Chunk[] chks ) { final Chunk wrks = chks[_ncols+2]; //fitting target (same as response for DRF, residual for GBM) final Chunk nids = chks[_ncols+3]; final Chunk weight = chks.length >= _ncols+5 ? chks[_ncols+4] : new C0DChunk(1, chks[0].len()); // Pass 1: Score a prior partially-built tree model, and make new Node // assignments to every row. This involves pulling out the current // assigned DecidedNode, "scoring" the row against that Node's decision // criteria, and assigning the row to a new child UndecidedNode (and // giving it an improved prediction). int nnids[] = new int[nids._len]; if( _leaf > 0) // Prior pass exists? score_decide(chks,nids,nnids); else // Just flag all the NA rows for( int row=0; row= 0 ) { // row already predicts perfectly or OOB double w = weight.atd(row); if (w == 0) continue; double resp = wrks.atd(row); assert !Double.isNaN(wrks.atd(row)); // Already marked as sampled-away DHistogram nhs[] = _hcs[nid]; int sCols[] = _tree.undecided(nid+_leaf)._scoreCols; // Columns to score (null, or a list of selected cols) if (sCols == null) { for(int col=0; col= 0 ) nh[i+1]++; // Rollup the histogram of rows-per-NID in this chunk for( int i=0; i<_hcs.length; i++ ) nh[i+1] += nh[i]; // Splat the rows into NID-groups int rows[] = new int[nnids.length]; for( int row=0; row= 0 ) rows[nh[nnids[row]]++] = row; // rows[] has Chunk-local ROW-numbers now, in-order, grouped by NID. // nh[] lists the start of each new NID, and is indexed by NID+1. final DHistogram hcs[][] = _hcs; if( hcs.length==0 ) return; // Unlikely fast cutout // Local temp arrays, no atomic updates. double bins[] = new double[Math.max(_nbins, _nbins_cats)]; double sums[] = new double[Math.max(_nbins, _nbins_cats)]; double ssqs[] = new double[Math.max(_nbins, _nbins_cats)]; int cols = _ncols; int hcslen = hcs.length; double[] ws = new double[chks[0]._len]; double[] cs = new double[chks[0]._len]; double[] ys = new double[chks[0]._len]; //Note: for (n) for (c) is faster than for(c) for(n) for Airlines and MNIST data for DRF and GBM and stochastic GBM weight.getDoubles(ws,0,ws.length); wrks.getDoubles(ys,0,ys.length); for (int c = 0; c < cols; c++) { boolean extracted = false; for (int n = 0; n < hcslen; n++) { int sCols[] = _tree.undecided(n + _leaf)._scoreCols; // Columns to score (null, or a list of selected cols) if (sCols == null || ArrayUtils.find(sCols,c) >= 0) { if (!extracted) { chks[c].getDoubles(cs, 0, cs.length); extracted = true; } overAllRows(cs, ys, ws, rows, hcs[n][c], n == 0 ? 0 : nh[n - 1], nh[n], bins, sums, ssqs); } } } } private static void overAllRows(double [] cs, double [] ys, double [] ws, int[] rows, final DHistogram rh, int lo, int hi, double[] bins, double[] sums, double[] ssqs) { if( rh==null ) return; // Ignore untracked columns in this split int rhbinslen = rh._bins.length; if( rhbinslen > bins.length) { // Grow bins if needed bins = new double[rhbinslen]; sums = new double[rhbinslen]; ssqs = new double[rhbinslen]; } fillLocalHistoForNode(bins, sums, ssqs, ws, cs, ys, rh, rows, hi, lo); bumpSharedHisto(bins,sums,ssqs,rh); } static void bumpSharedHisto(double[]bins,double[]sums,double[]ssqs,DHistogram rh) { final int len = rh._bins.length; for( int b=0; b minmax[1] ) minmax[1] = col_data; int b = rh.bin(col_data); // Compute bin# via linear interpolation double resp = ys[k]; double wy = w*resp; bins[b] += w; // Bump count in bin sums[b] += wy; ssqs[b] += wy*resp; } // Add all the data into the Histogram (atomically add) rh.setMin(minmax[0]); // Track actual lower/upper bound per-bin rh.setMax(minmax[1]); } }





© 2015 - 2025 Weber Informatics LLC | Privacy Policy