// helper for debugging @SuppressWarnings("unused") protected static void printGenerateTrees(DTree[] trees) { for (DTree dtree : trees) if (dtree != null) { try { PrintWriter writer = new PrintWriter("/tmp/h2o-3.tree" + ++counter + ".txt", "UTF-8"); writer.println(dtree.root().toString2(new StringBuilder(), 0)); writer.close(); } catch (FileNotFoundException | UnsupportedEncodingException e) { e.printStackTrace(); } System.out.println(dtree.root().toString2(new StringBuilder(), 0)); } }
@Override public void map(Chunk[] chks) { _gss = new double[_nclass][]; _rss = new double[_nclass][]; // For all tree/klasses for (int k = 0; k < _nclass; k++) { final DTree tree = _trees[k]; final int leaf = _leafs[k]; if (tree == null) continue; // Empty class is ignored // A leaf-biased array of all active Tree leaves. final double gs[] = _gss[k] = new double[tree._len - leaf]; final double rs[] = _rss[k] = new double[tree._len - leaf]; final Chunk nids = chk_nids(chks, k); // Node-ids for this tree/class final Chunk ress = chk_work(chks, k); // Residuals for this tree/class // If we have all constant responses, then we do not split even the // root and the residuals should be zero. if (tree.root() instanceof LeafNode) continue; for (int row = 0; row < nids._len; row++) { // For all rows int nid = (int) nids.at80(row); // Get Node to decide from if (nid < 0) continue; // Missing response if (tree.node(nid) instanceof UndecidedNode) // If we bottomed out the tree nid = tree.node(nid)._pid; // Then take parent's decision DecidedNode dn = tree.decided(nid); // Must have a decision point if (dn._split._col == -1) // Unable to decide? dn = tree.decided(nid = dn._pid); // Then take parent's decision int leafnid = dn.ns(chks, row); // Decide down to a leafnode assert leaf <= leafnid && leafnid < tree._len; assert tree.node(leafnid) instanceof LeafNode; // Note: I can which leaf/region I end up in, but I do not care for // the prediction presented by the tree. For GBM, we compute the // sum-of-residuals (and sum/abs/mult residuals) for all rows in the // leaf, and get our prediction from that. nids.set0(row, leafnid); assert !ress.isNA0(row); double res = ress.at0(row); double ares = Math.abs(res); gs[leafnid - leaf] += _nclass > 1 ? ares * (1 - ares) : 1; rs[leafnid - leaf] += res; } } }
@Override public void map(Chunk[] chks) { final Chunk y = importance ? chk_resp(chks) : null; // Response final double[] rpred = importance ? new double[1 + _nclass] : null; // Row prediction final double[] rowdata = importance ? new double[_ncols] : null; // Pre-allocated row data final Chunk oobt = chk_oobt(chks); // Out-of-bag rows counter over all trees // Iterate over all rows for (int row = 0; row < oobt._len; row++) { final boolean wasOOBRow = ScoreBuildHistogram.isOOBRow((int) chk_nids(chks, 0).at8(row)); // For all tree (i.e., k-classes) for (int k = 0; k < _nclass; k++) { final DTree tree = _trees[k]; if (tree == null) continue; // Empty class is ignored final Chunk nids = chk_nids(chks, k); // Node-ids for this tree/class int nid = (int) nids.at8(row); // Get Node to decide from // Update only out-of-bag rows // This is out-of-bag row - but we would like to track on-the-fly prediction for the row if (wasOOBRow) { final Chunk ct = chk_tree(chks, k); // k-tree working column holding votes for given row nid = ScoreBuildHistogram.oob2Nid(nid); if (tree.node(nid) instanceof UndecidedNode) // If we bottomed out the tree nid = tree.node(nid).pid(); // Then take parent's decision int leafnid; if (tree.root() instanceof LeafNode) { leafnid = 0; } else { DecidedNode dn = tree.decided(nid); // Must have a decision point if (dn._split.col() == -1) // Unable to decide? dn = tree.decided(tree.node(nid).pid()); // Then take parent's decision leafnid = dn.ns(chks, row); // Decide down to a leafnode } // Setup Tree(i) - on the fly prediction of i-tree for row-th row // - for classification: cumulative number of votes for this row // - for regression: cumulative sum of prediction of each tree - has to be // normalized by number of trees double prediction = ((LeafNode) tree.node(leafnid)) .pred(); // Prediction for this k-class and this row if (importance) rpred[1 + k] = (float) prediction; // for both regression and classification ct.set(row, (float) (ct.atd(row) + prediction)); } // reset help column for this row and this k-class nids.set(row, 0); } /* end of k-trees iteration */ // For this tree this row is out-of-bag - i.e., a tree voted for this row if (wasOOBRow) oobt.set(row, oobt.atd(row) + 1); // track number of trees if (importance) { if (wasOOBRow && !y.isNA(row)) { if (isClassifier()) { int treePred = getPrediction( rpred, _model._output._priorClassDist, data_row(chks, row, rowdata), _threshold); int actuPred = (int) y.at8(row); if (treePred == actuPred) rightVotes++; // No miss ! } else { // regression double treePred = rpred[1]; double actuPred = y.atd(row); sse += (actuPred - treePred) * (actuPred - treePred); } allRows++; } } } }