コード例 #1
0
ファイル: SharedTree.java プロジェクト: herberteuler/h2o-3
  @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);
    }
  }
コード例 #2
0
ファイル: KMeans.java プロジェクト: huamichaelchen/h2o-3
 protected void checkMemoryFootPrint() {
   long mem_usage = 8 /*doubles*/ * _parms._k * _train.numCols() * (_parms._standardize ? 2 : 1);
   long max_mem = H2O.SELF._heartbeat.get_free_mem();
   if (mem_usage > max_mem) {
     String msg =
         "Centroids won't fit in the driver node's memory ("
             + PrettyPrint.bytes(mem_usage)
             + " > "
             + PrettyPrint.bytes(max_mem)
             + ") - try reducing the number of columns and/or the number of categorical factors.";
     error("_train", msg);
     cancel(msg);
   }
 }
コード例 #3
0
ファイル: KMeans.java プロジェクト: huamichaelchen/h2o-3
    private TwoDimTable createScoringHistoryTable(KMeansModel.KMeansOutput output) {
      List<String> colHeaders = new ArrayList<>();
      List<String> colTypes = new ArrayList<>();
      List<String> colFormat = new ArrayList<>();
      colHeaders.add("Timestamp");
      colTypes.add("string");
      colFormat.add("%s");
      colHeaders.add("Duration");
      colTypes.add("string");
      colFormat.add("%s");
      colHeaders.add("Iteration");
      colTypes.add("long");
      colFormat.add("%d");
      colHeaders.add("Avg. Change of Std. Centroids");
      colTypes.add("double");
      colFormat.add("%.5f");
      colHeaders.add("Within Cluster Sum Of Squares");
      colTypes.add("double");
      colFormat.add("%.5f");

      final int rows = output._avg_centroids_chg.length;
      TwoDimTable table =
          new TwoDimTable(
              "Scoring History",
              null,
              new String[rows],
              colHeaders.toArray(new String[0]),
              colTypes.toArray(new String[0]),
              colFormat.toArray(new String[0]),
              "");
      int row = 0;
      for (int i = 0; i < rows; i++) {
        int col = 0;
        assert (row < table.getRowDim());
        assert (col < table.getColDim());
        DateTimeFormatter fmt = DateTimeFormat.forPattern("yyyy-MM-dd HH:mm:ss");
        table.set(row, col++, fmt.print(output._training_time_ms[i]));
        table.set(row, col++, PrettyPrint.msecs(output._training_time_ms[i] - _start_time, true));
        table.set(row, col++, i);
        table.set(row, col++, output._avg_centroids_chg[i]);
        table.set(row, col++, output._history_withinss[i]);
        row++;
      }
      return table;
    }
コード例 #4
0
ファイル: Frame.java プロジェクト: NidhiMehta/h2o
 @Override
 public String toString() {
   // Across
   String s = "{" + _names[0];
   long bs = _vecs[0].byteSize();
   for (int i = 1; i < _names.length; i++) {
     s += "," + _names[i];
     bs += _vecs[i].byteSize();
   }
   s += "}, " + PrettyPrint.bytes(bs) + "\n";
   // Down
   Vec v0 = firstReadable();
   if (v0 == null) return s;
   int nc = v0.nChunks();
   s += "Chunk starts: {";
   for (int i = 0; i < nc; i++) s += v0.elem2BV(i)._start + ",";
   s += "}";
   return s;
 }
コード例 #5
0
  /**
   * Create a summary table
   *
   * @return
   */
  TwoDimTable createSummaryTable() {
    Neurons[] neurons = DeepLearningTask.makeNeuronsForTesting(this);
    long byte_size = new AutoBuffer().put(this).buf().length;
    TwoDimTable table =
        new TwoDimTable(
            "Status of Neuron Layers",
            (get_params()._diagnostics ? "" : "diagnostics disabled, ")
                + (!get_params()._autoencoder ? ("predicting " + _train.lastVecName() + ", ") : "")
                + (get_params()._autoencoder
                    ? "auto-encoder"
                    : _classification
                        ? (units[units.length - 1] + "-class classification")
                        : "regression")
                + ", "
                + get_params()._distribution
                + " distribution, "
                + get_params()._loss
                + " loss, "
                + String.format("%,d", size())
                + " weights/biases, "
                + PrettyPrint.bytes(byte_size)
                + ", "
                + String.format("%,d", get_processed_global())
                + " training samples, "
                + "mini-batch size "
                + String.format("%,d", get_params()._mini_batch_size),
            new String[neurons.length],
            new String[] {
              "Layer",
              "Units",
              "Type",
              "Dropout",
              "L1",
              "L2",
              "Mean Rate",
              "Rate RMS",
              "Momentum",
              "Mean Weight",
              "Weight RMS",
              "Mean Bias",
              "Bias RMS"
            },
            new String[] {
              "int", "int", "string", "double", "double", "double", "double", "double", "double",
              "double", "double", "double", "double"
            },
            new String[] {
              "%d",
              "%d",
              "%s",
              "%2.2f %%",
              "%5f",
              "%5f",
              "%5f",
              "%5f",
              "%5f",
              "%5f",
              "%5f",
              "%5f",
              "%5f"
            },
            "");

    for (int i = 0; i < neurons.length; ++i) {
      table.set(i, 0, i + 1);
      table.set(i, 1, neurons[i].units);
      table.set(i, 2, neurons[i].getClass().getSimpleName());

      if (i == 0) {
        table.set(i, 3, neurons[i].params._input_dropout_ratio * 100);
        continue;
      } else if (i < neurons.length - 1) {
        if (neurons[i].params._hidden_dropout_ratios == null) {
          table.set(i, 3, 0);
        } else {
          table.set(i, 3, neurons[i].params._hidden_dropout_ratios[i - 1] * 100);
        }
      }
      table.set(i, 4, neurons[i].params._l1);
      table.set(i, 5, neurons[i].params._l2);
      table.set(
          i,
          6,
          (get_params()._adaptive_rate ? mean_rate[i] : neurons[i].rate(get_processed_total())));
      table.set(i, 7, (get_params()._adaptive_rate ? rms_rate[i] : 0));
      table.set(i, 8, get_params()._adaptive_rate ? 0 : neurons[i].momentum(get_processed_total()));
      table.set(i, 9, mean_weight[i]);
      table.set(i, 10, rms_weight[i]);
      table.set(i, 11, mean_bias[i]);
      table.set(i, 12, rms_bias[i]);
    }
    summaryTable = table;
    return summaryTable;
  }
コード例 #6
0
ファイル: SharedTree.java プロジェクト: herberteuler/h2o-3
  private TwoDimTable createScoringHistoryTable(SharedTreeModel.SharedTreeOutput _output) {
    List<String> colHeaders = new ArrayList<>();
    List<String> colTypes = new ArrayList<>();
    List<String> colFormat = new ArrayList<>();
    colHeaders.add("Timestamp");
    colTypes.add("string");
    colFormat.add("%s");
    colHeaders.add("Duration");
    colTypes.add("string");
    colFormat.add("%s");
    colHeaders.add("Number of Trees");
    colTypes.add("long");
    colFormat.add("%d");
    colHeaders.add("Training MSE");
    colTypes.add("double");
    colFormat.add("%.5f");
    if (_output.isClassifier()) {
      colHeaders.add("Training LogLoss");
      colTypes.add("double");
      colFormat.add("%.5f");
    }
    if (_output.getModelCategory() == ModelCategory.Binomial) {
      colHeaders.add("Training AUC");
      colTypes.add("double");
      colFormat.add("%.5f");
    }
    if (_output.getModelCategory() == ModelCategory.Binomial
        || _output.getModelCategory() == ModelCategory.Multinomial) {
      colHeaders.add("Training Classification Error");
      colTypes.add("double");
      colFormat.add("%.5f");
    }

    if (valid() != null) {
      colHeaders.add("Validation MSE");
      colTypes.add("double");
      colFormat.add("%.5f");
      if (_output.isClassifier()) {
        colHeaders.add("Validation LogLoss");
        colTypes.add("double");
        colFormat.add("%.5f");
      }
      if (_output.getModelCategory() == ModelCategory.Binomial) {
        colHeaders.add("Validation AUC");
        colTypes.add("double");
        colFormat.add("%.5f");
      }
      if (_output.isClassifier()) {
        colHeaders.add("Validation Classification Error");
        colTypes.add("double");
        colFormat.add("%.5f");
      }
    }

    int rows = 0;
    for (int i = 1; i < _output._scored_train.length; i++) {
      if (!Double.isNaN(_output._scored_train[i]._mse)) ++rows;
    }
    TwoDimTable table =
        new TwoDimTable(
            "Scoring History",
            null,
            new String[rows],
            colHeaders.toArray(new String[0]),
            colTypes.toArray(new String[0]),
            colFormat.toArray(new String[0]),
            "");
    int row = 0;
    for (int i = 1; i < _output._scored_train.length; i++) {
      if (Double.isNaN(_output._scored_train[i]._mse)) continue;
      int col = 0;
      assert (row < table.getRowDim());
      assert (col < table.getColDim());
      DateTimeFormatter fmt = DateTimeFormat.forPattern("yyyy-MM-dd HH:mm:ss");
      table.set(row, col++, fmt.print(_output._training_time_ms[i]));
      table.set(row, col++, PrettyPrint.msecs(_output._training_time_ms[i] - _start_time, true));
      table.set(row, col++, i);
      ScoreKeeper st = _output._scored_train[i];
      table.set(row, col++, st._mse);
      if (_output.isClassifier()) table.set(row, col++, st._logloss);
      if (_output.getModelCategory() == ModelCategory.Binomial) table.set(row, col++, st._AUC);
      if (_output.isClassifier()) table.set(row, col++, st._classError);

      if (_valid != null) {
        st = _output._scored_valid[i];
        table.set(row, col++, st._mse);
        if (_output.isClassifier()) table.set(row, col++, st._logloss);
        if (_output.getModelCategory() == ModelCategory.Binomial) table.set(row, col++, st._AUC);
        if (_output.isClassifier()) table.set(row, col++, st._classError);
      }
      row++;
    }
    return table;
  }
コード例 #7
0
ファイル: GridSearch.java プロジェクト: hihihippp/h2o
    @Override
    public boolean toHTML(StringBuilder sb) {
      if (jobs != null) {
        DocGen.HTML.arrayHead(sb);
        sb.append("<tr class='warning'>");
        ArrayList<Argument> args = jobs[0].arguments();
        // Filter some keys to simplify UI
        args = (ArrayList<Argument>) args.clone();
        filter(
            args,
            "destination_key",
            "source",
            "cols",
            "ignored_cols_by_name",
            "response",
            "classification",
            "validation");
        for (int i = 0; i < args.size(); i++)
          sb.append("<td><b>").append(args.get(i)._name).append("</b></td>");
        sb.append("<td><b>").append("run time").append("</b></td>");
        String perf = jobs[0].speedDescription();
        if (perf != null) sb.append("<td><b>").append(perf).append("</b></td>");
        sb.append("<td><b>").append("model key").append("</b></td>");
        sb.append("<td><b>").append("prediction error").append("</b></td>");
        sb.append("<td><b>").append("F1 score").append("</b></td>");
        sb.append("</tr>");

        ArrayList<JobInfo> infos = new ArrayList<JobInfo>();
        for (Job job : jobs) {
          JobInfo info = new JobInfo();
          info._job = job;
          Object value = UKV.get(job.destination_key);
          info._model = value instanceof Model ? (Model) value : null;
          if (info._model != null) info._cm = info._model.cm();
          if (info._cm != null) info._error = info._cm.err();
          infos.add(info);
        }
        Collections.sort(
            infos,
            new Comparator<JobInfo>() {
              @Override
              public int compare(JobInfo a, JobInfo b) {
                return Double.compare(a._error, b._error);
              }
            });

        for (JobInfo info : infos) {
          sb.append("<tr>");
          for (Argument a : args) {
            try {
              Object value = a._field.get(info._job);
              String s;
              if (value instanceof int[]) s = Utils.sampleToString((int[]) value, 20);
              else s = "" + value;
              sb.append("<td>").append(s).append("</td>");
            } catch (Exception e) {
              throw new RuntimeException(e);
            }
          }
          String runTime = "Pending", speed = "";
          if (info._job.start_time != 0) {
            runTime = PrettyPrint.msecs(info._job.runTimeMs(), true);
            speed = perf != null ? PrettyPrint.msecs(info._job.speedValue(), true) : "";
          }
          sb.append("<td>").append(runTime).append("</td>");
          if (perf != null) sb.append("<td>").append(speed).append("</td>");

          String link = info._job.destination_key.toString();
          if (info._job.start_time != 0 && DKV.get(info._job.destination_key) != null) {
            if (info._model instanceof GBMModel)
              link = GBMModelView.link(link, info._job.destination_key);
            else if (info._model instanceof NeuralNetModel)
              link = NeuralNetProgress.link(info._job.self(), info._job.destination_key, link);
            if (info._model instanceof KMeans2Model)
              link = KMeans2ModelView.link(link, info._job.destination_key);
            else link = Inspect.link(link, info._job.destination_key);
          }
          sb.append("<td>").append(link).append("</td>");

          String pct = "", f1 = "";
          if (info._cm != null) {
            pct = String.format("%.2f", 100 * info._error) + "%";
            if (info._cm._arr.length == 2)
              f1 = String.format("%.2f", info._cm.precisionAndRecall());
          }
          sb.append("<td><b>").append(pct).append("</b></td>");
          sb.append("<td><b>").append(f1).append("</b></td>");
          sb.append("</tr>");
        }
        DocGen.HTML.arrayTail(sb);
      }
      return true;
    }