示例#1
0
    // Handle the case where some centers go dry.  Rescue only 1 cluster
    // per iteration ('cause we only tracked the 1 worst row)
    boolean cleanupBadClusters(
        Lloyds task,
        final Vec[] vecs,
        final double[][] centers,
        final double[] means,
        final double[] mults,
        final int[] modes) {
      // Find any bad clusters
      int clu;
      for (clu = 0; clu < _parms._k; clu++) if (task._size[clu] == 0) break;
      if (clu == _parms._k) return false; // No bad clusters

      long row = task._worst_row;
      Log.warn("KMeans: Re-initializing cluster " + clu + " to row " + row);
      data(centers[clu] = task._cMeans[clu], vecs, row, means, mults, modes);
      task._size[clu] =
          1; // FIXME: PUBDEV-871 Some other cluster had their membership count reduced by one!
      // (which one?)

      // Find any MORE bad clusters; we only fixed the first one
      for (clu = 0; clu < _parms._k; clu++) if (task._size[clu] == 0) break;
      if (clu == _parms._k) return false; // No MORE bad clusters

      // If we see 2 or more bad rows, just re-run Lloyds to get the
      // next-worst row.  We don't count this as an iteration, because
      // we're not really adjusting the centers, we're trying to get
      // some centers *at-all*.
      Log.warn("KMeans: Re-running Lloyds to re-init another cluster");
      if (_reinit_attempts++ < _parms._k) {
        return true; // Rerun Lloyds, and assign points to centroids
      } else {
        _reinit_attempts = 0;
        return false;
      }
    }
示例#2
0
  @Override
  protected void checkMemoryFootPrint() {
    if (_model._output._ntrees == 0) return;
    int trees_so_far = _model._output._ntrees; // existing trees
    long model_mem_size =
        new ComputeModelSize(trees_so_far, _model._output._treeKeys).doAllNodes()._model_mem_size;
    _model._output._treeStats._byte_size = model_mem_size;
    double avg_tree_mem_size = (double) model_mem_size / trees_so_far;
    Log.debug(
        "Average tree size (for all classes): " + PrettyPrint.bytes((long) avg_tree_mem_size));

    // all the compressed trees are stored on the driver node
    long max_mem = H2O.SELF.get_max_mem();
    if (_parms._ntrees * avg_tree_mem_size > max_mem) {
      String msg =
          "The tree model will not fit in the driver node's memory ("
              + PrettyPrint.bytes((long) avg_tree_mem_size)
              + " per tree x "
              + _parms._ntrees
              + " > "
              + PrettyPrint.bytes(max_mem)
              + ") - try decreasing ntrees and/or max_depth or increasing min_rows!";
      error("_ntrees", msg);
      cancel(msg);
    }
  }
示例#3
0
    // Main worker thread
    @Override
    protected void compute2() {

      KMeansModel model = null;
      try {
        init(true);
        // Do lock even before checking the errors, since this block is finalized by unlock
        // (not the best solution, but the code is more readable)
        _parms.read_lock_frames(KMeans.this); // Fetch & read-lock input frames
        // Something goes wrong
        if (error_count() > 0)
          throw H2OModelBuilderIllegalArgumentException.makeFromBuilder(KMeans.this);
        // The model to be built
        model = new KMeansModel(dest(), _parms, new KMeansModel.KMeansOutput(KMeans.this));
        model.delete_and_lock(_key);

        //
        final Vec vecs[] = _train.vecs();
        // mults & means for standardization
        final double[] means = _train.means(); // means are used to impute NAs
        final double[] mults = _parms._standardize ? _train.mults() : null;
        final int[] impute_cat = new int[vecs.length];
        for (int i = 0; i < vecs.length; i++)
          impute_cat[i] = vecs[i].isNumeric() ? -1 : DataInfo.imputeCat(vecs[i]);
        model._output._normSub = means;
        model._output._normMul = mults;
        // Initialize cluster centers and standardize if requested
        double[][] centers = initial_centers(model, vecs, means, mults, impute_cat);
        if (centers == null) return; // Stopped/cancelled during center-finding
        double[][] oldCenters = null;

        // ---
        // Run the main KMeans Clustering loop
        // Stop after enough iterations or average_change < TOLERANCE
        model._output._iterations =
            0; // Loop ends only when iterations > max_iterations with strict inequality
        while (!isDone(model, centers, oldCenters)) {
          Lloyds task =
              new Lloyds(centers, means, mults, impute_cat, _isCats, _parms._k, hasWeightCol())
                  .doAll(vecs);
          // Pick the max categorical level for cluster center
          max_cats(task._cMeans, task._cats, _isCats);

          // Handle the case where some centers go dry.  Rescue only 1 cluster
          // per iteration ('cause we only tracked the 1 worst row)
          if (cleanupBadClusters(task, vecs, centers, means, mults, impute_cat)) continue;

          // Compute model stats; update standardized cluster centers
          oldCenters = centers;
          centers = computeStatsFillModel(task, model, vecs, means, mults, impute_cat);

          model.update(_key); // Update model in K/V store
          update(1); // One unit of work
          if (model._parms._score_each_iteration) Log.info(model._output._model_summary);
        }

        Log.info(model._output._model_summary);
        //        Log.info(model._output._scoring_history);
        //
        // Log.info(((ModelMetricsClustering)model._output._training_metrics).createCentroidStatsTable().toString());

        // At the end: validation scoring (no need to gather scoring history)
        if (_valid != null) {
          model.score(_parms.valid()).delete(); // this appends a ModelMetrics on the validation set
          model._output._validation_metrics = ModelMetrics.getFromDKV(model, _parms.valid());
          model.update(_key); // Update model in K/V store
        }
        done(); // Job done!

      } catch (Throwable t) {
        Job thisJob = DKV.getGet(_key);
        if (thisJob._state == JobState.CANCELLED) {
          Log.info("Job cancelled by user.");
        } else {
          t.printStackTrace();
          failed(t);
          throw t;
        }
      } finally {
        updateModelOutput();
        if (model != null) model.unlock(_key);
        _parms.read_unlock_frames(KMeans.this);
      }
      tryComplete();
    }
示例#4
0
  protected double doScoringAndSaveModel(
      boolean finalScoring, boolean oob, boolean build_tree_one_node) {
    double training_r2 = Double.NaN; // Training R^2 value, if computed
    long now = System.currentTimeMillis();
    if (_firstScore == 0) _firstScore = now;
    long sinceLastScore = now - _timeLastScoreStart;
    boolean updated = false;
    new ProgressUpdate(
            "Built " + _model._output._ntrees + " trees so far (out of " + _parms._ntrees + ").")
        .fork(_progressKey);
    // Now model already contains tid-trees in serialized form
    if (_parms._score_each_iteration
        || finalScoring
        || (now - _firstScore < 4000)
        || // Score every time for 4 secs
        // Throttle scoring to keep the cost sane; limit to a 10% duty cycle & every 4 secs
        (sinceLastScore > 4000
            && // Limit scoring updates to every 4sec
            (double) (_timeLastScoreEnd - _timeLastScoreStart) / sinceLastScore
                < 0.1)) { // 10% duty cycle

      checkMemoryFootPrint();

      // If validation is specified we use a model for scoring, so we need to
      // update it!  First we save model with trees (i.e., make them available
      // for scoring) and then update it with resulting error
      _model.update(_key);
      updated = true;

      Log.info("============================================================== ");
      SharedTreeModel.SharedTreeOutput out = _model._output;
      _timeLastScoreStart = now;
      // Score on training data
      new ProgressUpdate("Scoring the model.").fork(_progressKey);
      Score sc =
          new Score(this, true, oob, _model._output.getModelCategory())
              .doAll(train(), build_tree_one_node);
      ModelMetrics mm = sc.makeModelMetrics(_model, _parms.train());
      out._training_metrics = mm;
      if (oob)
        out._training_metrics._description = "Metrics reported on Out-Of-Bag training samples";
      out._scored_train[out._ntrees].fillFrom(mm);
      if (out._ntrees > 0) Log.info("Training " + out._scored_train[out._ntrees].toString());

      // Score again on validation data
      if (_parms._valid != null) {
        Score scv =
            new Score(this, false, false, _model._output.getModelCategory())
                .doAll(valid(), build_tree_one_node);
        ModelMetrics mmv = scv.makeModelMetrics(_model, _parms.valid());
        out._validation_metrics = mmv;
        out._scored_valid[out._ntrees].fillFrom(mmv);
        if (out._ntrees > 0) Log.info("Validation " + out._scored_valid[out._ntrees].toString());
      }

      if (out._ntrees > 0) { // Compute variable importances
        out._model_summary = createModelSummaryTable(out);
        out._scoring_history = createScoringHistoryTable(out);
        out._varimp = new hex.VarImp(_improvPerVar, out._names);
        out._variable_importances = hex.ModelMetrics.calcVarImp(out._varimp);
        Log.info(out._model_summary.toString());
        // For Debugging:
        //        Log.info(out._scoring_history.toString());
        //        Log.info(out._variable_importances.toString());
      }

      ConfusionMatrix cm = mm.cm();
      if (cm != null) {
        if (cm._cm.length <= _parms._max_confusion_matrix_size) {
          Log.info(cm.toASCII());
        } else {
          Log.info(
              "Confusion Matrix is too large (max_confusion_matrix_size="
                  + _parms._max_confusion_matrix_size
                  + "): "
                  + _nclass
                  + " classes.");
        }
      }
      _timeLastScoreEnd = System.currentTimeMillis();
    }

    // Double update - after either scoring or variable importance
    if (updated) _model.update(_key);
    return training_r2;
  }
示例#5
0
    @Override
    protected void compute2() {
      _model = null; // Resulting model!
      try {
        Scope.enter(); // Cleanup temp keys
        init(true); // Do any expensive tests & conversions now
        // Do lock even before checking the errors, since this block is finalized by unlock
        // (not the best solution, but the code is more readable)
        _parms.read_lock_frames(SharedTree.this); // Fetch & read-lock input frames
        if (error_count() > 0)
          throw H2OModelBuilderIllegalArgumentException.makeFromBuilder(SharedTree.this);

        // New Model?  Or continuing from a checkpoint?
        if (_parms._checkpoint && DKV.get(_parms._model_id) != null) {
          _model = DKV.get(_dest).get();
          _model.write_lock(_key); // do not delete previous model; we are extending it
        } else { // New Model
          // Compute the zero-tree error - guessing only the class distribution.
          // MSE is stddev squared when guessing for regression.
          // For classification, guess the largest class.
          _model =
              makeModel(
                  _dest,
                  _parms,
                  initial_MSE(_response, _response),
                  _valid == null
                      ? Double.NaN
                      : initial_MSE(_response, _vresponse)); // Make a fresh model
          _model.delete_and_lock(_key); // and clear & write-lock it (smashing any prior)
          _model._output._init_f = _initialPrediction;
        }

        // Compute the response domain; makes for nicer printouts
        String[] domain = _response.domain();
        assert (_nclass > 1 && domain != null) || (_nclass == 1 && domain == null);
        if (_nclass == 1) domain = new String[] {"r"}; // For regression, give a name to class 0

        // Compute class distribution, used to for initial guesses and to
        // upsample minority classes (if asked for).
        if (_nclass > 1) { // Classification?

          // Handle imbalanced classes by stratified over/under-sampling.
          // initWorkFrame sets the modeled class distribution, and
          // model.score() corrects the probabilities back using the
          // distribution ratios
          if (_model._output.isClassifier() && _parms._balance_classes) {

            float[] trainSamplingFactors =
                new float
                    [_train
                        .lastVec()
                        .domain()
                        .length]; // leave initialized to 0 -> will be filled up below
            if (_parms._class_sampling_factors != null) {
              if (_parms._class_sampling_factors.length != _train.lastVec().domain().length)
                throw new IllegalArgumentException(
                    "class_sampling_factors must have "
                        + _train.lastVec().domain().length
                        + " elements");
              trainSamplingFactors =
                  _parms._class_sampling_factors.clone(); // clone: don't modify the original
            }
            Frame stratified =
                water.util.MRUtils.sampleFrameStratified(
                    _train,
                    _train.lastVec(),
                    _train.vec(_model._output.weightsName()),
                    trainSamplingFactors,
                    (long) (_parms._max_after_balance_size * _train.numRows()),
                    _parms._seed,
                    true,
                    false);
            if (stratified != _train) {
              _train = stratified;
              _response = stratified.vec(_parms._response_column);
              _weights = stratified.vec(_parms._weights_column);
              // Recompute distribution since the input frame was modified
              MRUtils.ClassDist cdmt2 =
                  _weights != null
                      ? new MRUtils.ClassDist(_nclass).doAll(_response, _weights)
                      : new MRUtils.ClassDist(_nclass).doAll(_response);
              _model._output._distribution = cdmt2.dist();
              _model._output._modelClassDist = cdmt2.rel_dist();
            }
          }
          Log.info("Prior class distribution: " + Arrays.toString(_model._output._priorClassDist));
          Log.info("Model class distribution: " + Arrays.toString(_model._output._modelClassDist));
        }

        // Also add to the basic working Frame these sets:
        //   nclass Vecs of current forest results (sum across all trees)
        //   nclass Vecs of working/temp data
        //   nclass Vecs of NIDs, allowing 1 tree per class

        // Current forest values: results of summing the prior M trees
        for (int i = 0; i < _nclass; i++) _train.add("Tree_" + domain[i], _response.makeZero());

        // Initial work columns.  Set-before-use in the algos.
        for (int i = 0; i < _nclass; i++) _train.add("Work_" + domain[i], _response.makeZero());

        // One Tree per class, each tree needs a NIDs.  For empty classes use a -1
        // NID signifying an empty regression tree.
        for (int i = 0; i < _nclass; i++)
          _train.add(
              "NIDs_" + domain[i],
              _response.makeCon(
                  _model._output._distribution == null
                      ? 0
                      : (_model._output._distribution[i] == 0 ? -1 : 0)));

        // Tag out rows missing the response column
        new ExcludeNAResponse().doAll(_train);

        // Variable importance: squared-error-improvement-per-variable-per-split
        _improvPerVar = new float[_ncols];

        // Sub-class tree-model-builder specific build code
        buildModel();
        done(); // Job done!
      } catch (Throwable t) {
        Job thisJob = DKV.getGet(_key);
        if (thisJob._state == JobState.CANCELLED) {
          Log.info("Job cancelled by user.");
        } else {
          t.printStackTrace();
          failed(t);
          throw t;
        }
      } finally {
        if (_model != null) _model.unlock(_key);
        _parms.read_unlock_frames(SharedTree.this);
        if (_model == null) Scope.exit();
        else {
          Scope.exit(
              _model._key,
              ModelMetrics.buildKey(_model, _parms.train()),
              ModelMetrics.buildKey(_model, _parms.valid()));
        }
      }
      tryComplete();
    }
示例#6
0
 /**
  * Simple GLM wrapper to enable launching GLM from command line.
  *
  * <p>Example input: java -jar target/h2o.jar -name=test -runMethod water.util.GLMRunner
  * -file=smalldata/logreg/prostate.csv -y=CAPSULE -family=binomial
  *
  * @param args
  * @throws InterruptedException
  */
 public static void main(String[] args) throws InterruptedException {
   try {
     GLMArgs ARGS = new GLMArgs();
     new Arguments(args).extract(ARGS);
     System.out.println("==================<GLMRunner START>===================");
     ValueArray ary = Utils.loadAndParseKey(ARGS.file);
     int ycol;
     try {
       ycol = Integer.parseInt(ARGS.y);
     } catch (NumberFormatException e) {
       ycol = ary.getColumnIds(new String[] {ARGS.y})[0];
     }
     int ncols = ary.numCols();
     if (ycol < 0 || ycol >= ary.numCols()) {
       System.err.println("invalid y column: " + ycol);
       H2O.exit(-1);
     }
     int[] xcols;
     if (ARGS.xs.equalsIgnoreCase("all")) {
       xcols = new int[ncols - 1];
       for (int i = 0; i < ycol; ++i) xcols[i] = i;
       for (int i = ycol; i < ncols - 1; ++i) xcols[i] = i + 1;
     } else {
       System.out.println("xs = " + ARGS.xs);
       String[] names = ARGS.xs.split(",");
       xcols = new int[names.length];
       try {
         for (int i = 0; i < names.length; ++i) xcols[i] = Integer.valueOf(names[i]);
       } catch (NumberFormatException e) {
         xcols = ary.getColumnIds(ARGS.xs.split(","));
       }
     }
     for (int x : xcols)
       if (x < 0) {
         System.err.println("Invalid predictor specification " + ARGS.xs);
         H2O.exit(-1);
       }
     GLMJob j =
         DGLM.startGLMJob(
             DGLM.getData(ary, xcols, ycol, null, true),
             new ADMMSolver(ARGS.lambda, ARGS._alpha),
             new GLMParams(Family.valueOf(ARGS.family)),
             null,
             ARGS.xval,
             true);
     System.out.print("[GLM] computing model...");
     int progress = 0;
     while (!j.isDone()) {
       int p = (int) (100 * j.progress());
       int dots = p - progress;
       progress = p;
       for (int i = 0; i < dots; ++i) System.out.print('.');
       Thread.sleep(250);
     }
     Log.debug(Sys.GENLM, "DONE.");
     GLMModel m = j.get();
     String[] colnames = ary.colNames();
     System.out.println("Intercept" + " = " + m._beta[ncols - 1]);
     for (int i = 0; i < xcols.length; ++i) {
       System.out.println(colnames[i] + " = " + m._beta[i]);
     }
   } catch (Throwable t) {
     Log.err(t);
   } finally { // we're done. shutdown the cloud
     Log.debug(Sys.GENLM, "==================<GLMRunner DONE>===================");
     UDPRebooted.suicide(UDPRebooted.T.shutdown, H2O.SELF);
   }
 }
    @Override
    protected void compute2() {
      CoxPHModel model = null;
      try {
        Scope.enter();
        _parms.read_lock_frames(CoxPH.this);
        init(true);

        applyScoringFrameSideEffects();

        // The model to be built
        model = new CoxPHModel(dest(), _parms, new CoxPHModel.CoxPHOutput(CoxPH.this));
        model.delete_and_lock(_key);

        applyTrainingFrameSideEffects();

        int nResponses = 1;
        boolean useAllFactorLevels = false;
        final DataInfo dinfo =
            new DataInfo(
                Key.make(),
                _modelBuilderTrain,
                null,
                nResponses,
                useAllFactorLevels,
                DataInfo.TransformType.DEMEAN,
                TransformType.NONE,
                true,
                false,
                false,
                false,
                false,
                false);
        initStats(model, dinfo);

        final int n_offsets =
            (model._parms.offset_columns == null) ? 0 : model._parms.offset_columns.length;
        final int n_coef = dinfo.fullN() - n_offsets;
        final double[] step = MemoryManager.malloc8d(n_coef);
        final double[] oldCoef = MemoryManager.malloc8d(n_coef);
        final double[] newCoef = MemoryManager.malloc8d(n_coef);
        Arrays.fill(step, Double.NaN);
        Arrays.fill(oldCoef, Double.NaN);
        for (int j = 0; j < n_coef; ++j) newCoef[j] = model._parms.init;
        double oldLoglik = -Double.MAX_VALUE;
        final int n_time = (int) (model._output.max_time - model._output.min_time + 1);
        final boolean has_start_column = (model._parms.start_column != null);
        final boolean has_weights_column = (model._parms.weights_column != null);
        for (int i = 0; i <= model._parms.iter_max; ++i) {
          model._output.iter = i;

          final CoxPHTask coxMR =
              new CoxPHTask(
                      self(),
                      dinfo,
                      newCoef,
                      model._output.min_time,
                      n_time,
                      n_offsets,
                      has_start_column,
                      has_weights_column)
                  .doAll(dinfo._adaptedFrame);

          final double newLoglik = calcLoglik(model, coxMR);
          if (newLoglik > oldLoglik) {
            if (i == 0) calcCounts(model, coxMR);

            calcModelStats(model, newCoef, newLoglik);
            calcCumhaz_0(model, coxMR);

            if (newLoglik == 0) model._output.lre = -Math.log10(Math.abs(oldLoglik - newLoglik));
            else model._output.lre = -Math.log10(Math.abs((oldLoglik - newLoglik) / newLoglik));
            if (model._output.lre >= model._parms.lre_min) break;

            Arrays.fill(step, 0);
            for (int j = 0; j < n_coef; ++j)
              for (int k = 0; k < n_coef; ++k)
                step[j] -= model._output.var_coef[j][k] * model._output.gradient[k];
            for (int j = 0; j < n_coef; ++j)
              if (Double.isNaN(step[j]) || Double.isInfinite(step[j])) break;

            oldLoglik = newLoglik;
            System.arraycopy(newCoef, 0, oldCoef, 0, oldCoef.length);
          } else {
            for (int j = 0; j < n_coef; ++j) step[j] /= 2;
          }

          for (int j = 0; j < n_coef; ++j) newCoef[j] = oldCoef[j] - step[j];
        }

        model.update(_key);
      } catch (Throwable t) {
        Job thisJob = DKV.getGet(_key);
        if (thisJob._state == JobState.CANCELLED) {
          Log.info("Job cancelled by user.");
        } else {
          t.printStackTrace();
          failed(t);
          throw t;
        }
      } finally {
        updateModelOutput();
        _parms.read_unlock_frames(CoxPH.this);
        Scope.exit();
        done(); // Job done!
      }
      tryComplete();
    }