Esempio n. 1
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;
  }
Esempio n. 2
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();
    }
Esempio n. 3
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();
    }