/**
* Initialize the ModelBuilder, validating all arguments and preparing the training frame. This
* call is expected to be overridden in the subclasses and each subclass will start with
* "super.init();". This call is made by the front-end whenever the GUI is clicked, and needs to
* be fast; heavy-weight prep needs to wait for the trainModel() call.
*/
@Override
public void init(boolean expensive) {
super.init(expensive);
if ((_parms.start_column != null) && !_parms.start_column.isInt())
error("start_column", "start time must be null or of type integer");
if (!_parms.stop_column.isInt()) error("stop_column", "stop time must be of type integer");
if (!_parms.event_column.isInt() && !_parms.event_column.isCategorical())
error("event_column", "event must be of type integer or factor");
if (Double.isNaN(_parms.lre_min) || _parms.lre_min <= 0)
error("lre_min", "lre_min must be a positive number");
if (_parms.iter_max < 1) error("iter_max", "iter_max must be a positive integer");
final int MAX_TIME_BINS = 10000;
final long min_time =
(_parms.start_column == null)
? (long) _parms.stop_column.min()
: (long) _parms.start_column.min() + 1;
final int n_time = (int) (_parms.stop_column.max() - min_time + 1);
if (n_time < 1) error("start_column", "start times must be strictly less than stop times");
if (n_time > MAX_TIME_BINS)
error(
"stop_column",
"number of distinct stop times is "
+ n_time
+ "; maximum number allowed is "
+ MAX_TIME_BINS);
}
/**
* Initialize the ModelBuilder, validating all arguments and preparing the training frame. This
* call is expected to be overridden in the subclasses and each subclass will start with
* "super.init();". This call is made by the front-end whenever the GUI is clicked, and needs to
* be fast; heavy-weight prep needs to wait for the trainModel() call.
*
* <p>Validate the requested ntrees; precompute actual ntrees. Validate the number of classes to
* predict on; validate a checkpoint.
*/
@Override
public void init(boolean expensive) {
super.init(expensive);
if (H2O.ARGS.client && _parms._build_tree_one_node)
error("_build_tree_one_node", "Cannot run on a single node in client mode");
if (_vresponse != null) _vresponse_key = _vresponse._key;
if (_response != null) _response_key = _response._key;
if (_nclass > SharedTreeModel.SharedTreeParameters.MAX_SUPPORTED_LEVELS)
error("_nclass", "Too many levels in response column!");
if (_parms._min_rows < 0) error("_min_rows", "Requested min_rows must be greater than 0");
if (_parms._ntrees < 0 || _parms._ntrees > 100000)
error("_ntrees", "Requested ntrees must be between 1 and 100000");
_ntrees = _parms._ntrees; // Total trees in final model
if (_parms._checkpoint) { // Asking to continue from checkpoint?
Value cv = DKV.get(_parms._model_id);
if (cv != null) { // Look for prior model
M checkpointModel = cv.get();
if (_parms._ntrees < checkpointModel._output._ntrees + 1)
error(
"_ntrees",
"Requested ntrees must be between "
+ checkpointModel._output._ntrees
+ 1
+ " and 100000");
_ntrees = _parms._ntrees - checkpointModel._output._ntrees; // Needed trees
}
}
if (_parms._nbins <= 1) error("_nbins", "_nbins must be > 1.");
if (_parms._nbins >= 1 << 16) error("_nbins", "_nbins must be < " + (1 << 16));
if (_parms._nbins_cats <= 1) error("_nbins_cats", "_nbins_cats must be > 1.");
if (_parms._nbins_cats >= 1 << 16) error("_nbins_cats", "_nbins_cats must be < " + (1 << 16));
if (_parms._max_depth <= 0) error("_max_depth", "_max_depth must be > 0.");
if (_parms._min_rows <= 0) error("_min_rows", "_min_rows must be > 0.");
if (_parms._distribution == Distributions.Family.tweedie) {
_parms._distribution.tweedie.p = _parms._tweedie_power;
}
if (_train != null) {
double sumWeights =
_train.numRows() * (hasWeightCol() ? _train.vec(_parms._weights_column).mean() : 1);
if (sumWeights
< 2 * _parms._min_rows) // Need at least 2*min_rows weighted rows to split even once
error(
"_min_rows",
"The dataset size is too small to split for min_rows="
+ _parms._min_rows
+ ": must have at least "
+ 2 * _parms._min_rows
+ " (weighted) rows, but have only "
+ sumWeights
+ ".");
}
if (_train != null) _ncols = _train.numCols() - 1 - numSpecialCols();
}
/**
* Initialize the ModelBuilder, validating all arguments and preparing the training frame. This
* call is expected to be overridden in the subclasses and each subclass will start with
* "super.init();". This call is made by the front-end whenever the GUI is clicked, and needs to
* be fast; heavy-weight prep needs to wait for the trainModel() call.
*
* <p>Validate the requested ntrees; precompute actual ntrees. Validate the number of classes to
* predict on; validate a checkpoint.
*/
@Override
public void init(boolean expensive) {
super.init(expensive);
if (H2O.ARGS.client && _parms._build_tree_one_node)
error("_build_tree_one_node", "Cannot run on a single node in client mode");
if (_vresponse != null) _vresponse_key = _vresponse._key;
if (_response != null) _response_key = _response._key;
if (_parms._min_rows < 0) error("_min_rows", "Requested min_rows must be greater than 0");
if (_parms._ntrees < 0 || _parms._ntrees > MAX_NTREES)
error("_ntrees", "Requested ntrees must be between 1 and " + MAX_NTREES);
_ntrees = _parms._ntrees; // Total trees in final model
if (_parms.hasCheckpoint()) { // Asking to continue from checkpoint?
Value cv = DKV.get(_parms._checkpoint);
if (cv != null) { // Look for prior model
M checkpointModel = cv.get();
try {
_parms.validateWithCheckpoint(checkpointModel._parms);
} catch (H2OIllegalArgumentException e) {
error(e.values.get("argument").toString(), e.values.get("value").toString());
}
if (_parms._ntrees < checkpointModel._output._ntrees + 1)
error(
"_ntrees",
"If checkpoint is specified then requested ntrees must be higher than "
+ (checkpointModel._output._ntrees + 1));
// Compute number of trees to build for this checkpoint
_ntrees = _parms._ntrees - checkpointModel._output._ntrees; // Needed trees
}
}
if (_parms._nbins <= 1) error("_nbins", "_nbins must be > 1.");
if (_parms._nbins >= 1 << 16) error("_nbins", "_nbins must be < " + (1 << 16));
if (_parms._nbins_cats <= 1) error("_nbins_cats", "_nbins_cats must be > 1.");
if (_parms._nbins_cats >= 1 << 16) error("_nbins_cats", "_nbins_cats must be < " + (1 << 16));
if (_parms._max_depth <= 0) error("_max_depth", "_max_depth must be > 0.");
if (_parms._min_rows <= 0) error("_min_rows", "_min_rows must be > 0.");
if (_train != null) {
double sumWeights =
_train.numRows() * (hasWeightCol() ? _train.vec(_parms._weights_column).mean() : 1);
if (sumWeights
< 2 * _parms._min_rows) // Need at least 2*min_rows weighted rows to split even once
error(
"_min_rows",
"The dataset size is too small to split for min_rows="
+ _parms._min_rows
+ ": must have at least "
+ 2 * _parms._min_rows
+ " (weighted) rows, but have only "
+ sumWeights
+ ".");
}
if (_train != null) _ncols = _train.numCols() - 1 - numSpecialCols();
}
/**
* Initialize the ModelBuilder, validating all arguments and preparing the training frame. This
* call is expected to be overridden in the subclasses and each subclass will start with
* "super.init();". This call is made by the front-end whenever the GUI is clicked, and needs to
* be fast; heavy-weight prep needs to wait for the trainModel() call.
*
* <p>Validate the probs.
*/
@Override
public void init(boolean expensive) {
super.init(expensive);
for (double p : _parms._probs)
if (p < 0.0 || p > 1.0) error("_probs", "Probabilities must be between 0 and 1");
_ncols =
train().numCols() - numSpecialCols(); // offset/weights/nfold - should only ever be weights
if (numSpecialCols() == 1 && _weights == null)
throw new IllegalArgumentException(
"The only special Vec that is supported for Quantiles is observation weights.");
if (numSpecialCols() > 1)
throw new IllegalArgumentException("Cannot handle more than 1 special vec (weights)");
}
@Override
public void init(boolean expensive) {
super.init(expensive);
// if (_parms._loading_key == null) _parms._loading_key = Key.make("PCALoading_" + Key.rand());
if (_parms._loading_name == null || _parms._loading_name.length() == 0)
_parms._loading_name = "PCALoading_" + Key.rand();
if (_parms._max_iterations < 1 || _parms._max_iterations > 1e6)
error("_max_iterations", "max_iterations must be between 1 and 1e6 inclusive");
if (_train == null) return;
if (_train.numCols() < 2) error("_train", "_train must have more than one column");
_ncolExp = _train.numColsExp(_parms._use_all_factor_levels, false);
// TODO: Initialize _parms._k = min(ncolExp(_train), nrow(_train)) if not set
int k_min = (int) Math.min(_ncolExp, _train.numRows());
if (_parms._k < 1 || _parms._k > k_min) error("_k", "_k must be between 1 and " + k_min);
if (!_parms._use_all_factor_levels && _parms._pca_method == PCAParameters.Method.GLRM)
error("_use_all_factor_levels", "GLRM only implemented for _use_all_factor_levels = true");
if (expensive && error_count() == 0) checkMemoryFootPrint();
}
/**
* Initialize the ModelBuilder, validating all arguments and preparing the training frame. This
* call is expected to be overridden in the subclasses and each subclass will start with
* "super.init();". This call is made by the front-end whenever the GUI is clicked, and needs to
* be fast; heavy-weight prep needs to wait for the trainModel() call.
*
* <p>Validate the very large number of arguments in the DL Parameter directly.
*/
@Override
public void init(boolean expensive) {
super.init(expensive);
_parms.validate(this, expensive);
if (expensive && error_count() == 0) checkMemoryFootPrint();
}