PLearn 0.1
|
#include <KFoldSplitter.h>
Public Member Functions | |
KFoldSplitter (int k=5) | |
Default constructor. | |
virtual void | build () |
Post-constructor. | |
virtual string | classname () const |
virtual OptionList & | getOptionList () const |
virtual OptionMap & | getOptionMap () const |
virtual RemoteMethodMap & | getRemoteMethodMap () const |
virtual KFoldSplitter * | deepCopy (CopiesMap &copies) const |
virtual int | nsplits () const |
Returns the number of available different "splits". | |
virtual int | nSetsPerSplit () const |
Returns the number of sets per split. | |
virtual TVec< VMat > | getSplit (int i=0) |
Returns split number i. | |
Static Public Member Functions | |
static string | _classname_ () |
Declares name and deepCopy methods. | |
static OptionList & | _getOptionList_ () |
static RemoteMethodMap & | _getRemoteMethodMap_ () |
static Object * | _new_instance_for_typemap_ () |
static bool | _isa_ (const Object *o) |
static void | _static_initialize_ () |
static const PPath & | declaringFile () |
Public Attributes | |
bool | append_non_constant_test |
bool | append_train |
pair< real, real > | cross_range |
bool | include_test_in_train |
bool | balance_classes |
int | K |
Static Public Attributes | |
static StaticInitializer | _static_initializer_ |
Static Protected Member Functions | |
static void | declareOptions (OptionList &ol) |
Declares this class' options. | |
Private Types | |
typedef Splitter | inherited |
Private Member Functions | |
void | build_ () |
This does the actual building. |
Definition at line 50 of file KFoldSplitter.h.
typedef Splitter PLearn::KFoldSplitter::inherited [private] |
Reimplemented from PLearn::Splitter.
Definition at line 52 of file KFoldSplitter.h.
PLearn::KFoldSplitter::KFoldSplitter | ( | int | k = 5 | ) |
Default constructor.
Definition at line 56 of file KFoldSplitter.cc.
References cross_range.
: append_non_constant_test(false), append_train(false), include_test_in_train(false), balance_classes(false), K(k) { // Default cross-validation range is the whole dataset. cross_range.first = 0; cross_range.second = 1; }
string PLearn::KFoldSplitter::_classname_ | ( | ) | [static] |
Declares name and deepCopy methods.
Reimplemented from PLearn::Splitter.
Definition at line 77 of file KFoldSplitter.cc.
OptionList & PLearn::KFoldSplitter::_getOptionList_ | ( | ) | [static] |
Reimplemented from PLearn::Splitter.
Definition at line 77 of file KFoldSplitter.cc.
RemoteMethodMap & PLearn::KFoldSplitter::_getRemoteMethodMap_ | ( | ) | [static] |
Reimplemented from PLearn::Splitter.
Definition at line 77 of file KFoldSplitter.cc.
Reimplemented from PLearn::Splitter.
Definition at line 77 of file KFoldSplitter.cc.
Object * PLearn::KFoldSplitter::_new_instance_for_typemap_ | ( | ) | [static] |
Reimplemented from PLearn::Object.
Definition at line 77 of file KFoldSplitter.cc.
StaticInitializer KFoldSplitter::_static_initializer_ & PLearn::KFoldSplitter::_static_initialize_ | ( | ) | [static] |
Reimplemented from PLearn::Splitter.
Definition at line 77 of file KFoldSplitter.cc.
void PLearn::KFoldSplitter::build | ( | ) | [virtual] |
Post-constructor.
The normal implementation should call simply inherited::build(), then this class's build_(). This method should be callable again at later times, after modifying some option fields to change the "architecture" of the object.
Reimplemented from PLearn::Object.
Definition at line 133 of file KFoldSplitter.cc.
References PLearn::Object::build(), and build_().
{ inherited::build(); build_(); }
void PLearn::KFoldSplitter::build_ | ( | ) | [private] |
This does the actual building.
Reimplemented from PLearn::Object.
Definition at line 125 of file KFoldSplitter.cc.
Referenced by build().
string PLearn::KFoldSplitter::classname | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 77 of file KFoldSplitter.cc.
void PLearn::KFoldSplitter::declareOptions | ( | OptionList & | ol | ) | [static, protected] |
Declares this class' options.
Reimplemented from PLearn::Splitter.
Definition at line 82 of file KFoldSplitter.cc.
References PLearn::OptionBase::advanced_level, append_non_constant_test, append_train, balance_classes, PLearn::OptionBase::buildoption, cross_range, PLearn::declareOption(), PLearn::Splitter::declareOptions(), include_test_in_train, and K.
{ declareOption(ol, "K", &KFoldSplitter::K, OptionBase::buildoption, "Split dataset in K parts (you can use K = -1 to perform leave-one-out CV)."); declareOption(ol, "append_train", &KFoldSplitter::append_train, OptionBase::buildoption, "If set to 1, the trainset will be appended after in the returned sets."); declareOption(ol, "append_non_constant_test", &KFoldSplitter::append_non_constant_test, OptionBase::buildoption, "If true, the non-constant part of the test set will be appended\n" "in the returned sets. This mostly makes sense when 'cross_range'\n" "is not (0:1).", OptionBase::advanced_level); declareOption(ol, "include_test_in_train", &KFoldSplitter::include_test_in_train, OptionBase::buildoption, "If set to 1, the test set will be included in the train set."); declareOption(ol, "cross_range", &KFoldSplitter::cross_range, OptionBase::buildoption, "The range on which cross-validation is applied (similar to the\n" "FractionSplitter ranges).", OptionBase::advanced_level); declareOption(ol, "balance_classes", &KFoldSplitter::balance_classes, OptionBase::buildoption, "Should we balance classes inside the splits to obtain the same\n" "class frequencies. This corresponds to concatenating the results\n" "of a K-Fold performed on the subsets of examples from each class.\n" "Note that it currently does not support leave-one-out, and that\n" "you might obtain strange results if K > number of samples in one\n" "class.\n" "Note also that for this option to work, you have to label your\n" "classes from 0 to (n_classes-1), and all classes must be present\n" "in the source VMat."); inherited::declareOptions(ol); }
static const PPath& PLearn::KFoldSplitter::declaringFile | ( | ) | [inline, static] |
Reimplemented from PLearn::Splitter.
Definition at line 98 of file KFoldSplitter.h.
KFoldSplitter * PLearn::KFoldSplitter::deepCopy | ( | CopiesMap & | copies | ) | const [virtual] |
Reimplemented from PLearn::Splitter.
Definition at line 77 of file KFoldSplitter.cc.
OptionList & PLearn::KFoldSplitter::getOptionList | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 77 of file KFoldSplitter.cc.
OptionMap & PLearn::KFoldSplitter::getOptionMap | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 77 of file KFoldSplitter.cc.
RemoteMethodMap & PLearn::KFoldSplitter::getRemoteMethodMap | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 77 of file KFoldSplitter.cc.
Returns split number i.
Implements PLearn::Splitter.
Definition at line 165 of file KFoldSplitter.cc.
References PLearn::TVec< T >::append(), append_non_constant_test, append_train, balance_classes, PLearn::TVec< T >::copy(), cross_range, PLearn::Splitter::dataset, PLearn::fast_exact_is_equal(), include_test_in_train, K, PLearn::VMat::length(), nsplits(), PLASSERT, PLASSERT_MSG, PLCHECK_MSG, PLERROR, PLWARNING, PLearn::split(), PLearn::tostring(), and PLearn::VMat::width().
{ if (k >= nsplits()) PLERROR("KFoldSplitter::getSplit() - k (%d) cannot be greater than " " the number of splits (%d)", k, nsplits()); real start = cross_range.first; real end = cross_range.second; int n_data = dataset->length(); PLASSERT_MSG(start >= 0 && end >= 0 && end > start && start < n_data && end < n_data, string("start=")+tostring(start)+", end="+tostring(end)+", n_data="+tostring(n_data)); int i_start = 0; if (start > 0) i_start = start >= 1 ? int(round(start)) : int(round(n_data * start)); int i_end = n_data; if (!fast_exact_is_equal(end, 1)) i_end = end >= 1 ? int(round(end)) : int(round(n_data * end)); // The cross validation will be done only on examples i_start, ..., i_end - 1. int n_cross_data = i_end - i_start; bool do_partial_cross = (n_cross_data != n_data); if (K > 0 && K > n_data) PLERROR("In KFoldSplitter::getSplit - The number of splits (%d) cannot" " be greater than the number of samples in the dataset (%d). " "If you want to perform leave-one-out cross-validation, please" "set K = -1", K, n_data); real test_fraction = K > 0 ? (n_cross_data/(real)K) : 0; if ((int)(test_fraction) < 1) test_fraction = 1; // leave-one-out cross-validation TVec<VMat> split_(2); VMat non_constant_test; if (do_partial_cross) { if (balance_classes) PLERROR("balance_classes not implemented with partial_cross"); VMat sub_data = new SubVMatrix(dataset, i_start, 0, n_cross_data, dataset->width()); split(sub_data, test_fraction, split_[0], split_[1], k, true); non_constant_test = split_[1]; if (i_start > 0) { VMat constant_train = new SubVMatrix(dataset, 0, 0, i_start, dataset->width()); split_[0] = new ConcatRowsVMatrix(constant_train, split_[0]); } if (i_end < n_data) { VMat constant_test = new SubVMatrix(dataset, i_end, 0, n_data - i_end, dataset->width()); split_[1] = new ConcatRowsVMatrix(split_[1], constant_test); } } else { if (balance_classes) { PLASSERT( dataset->targetsize() > 0 ); TVec<VMat> tmp_split_(2); int i_class = 0; if (test_fraction > 1.0) test_fraction /= n_cross_data; else PLERROR("In KFoldSplitter::getSplit - Leave-one-out not implemented"); while (true) { // break point below VMat dataset_class = new ClassSubsetVMatrix(dataset, i_class); int length = dataset_class->length(); if (length == 0 ) break; if (length < K) PLWARNING("In KFoldSplitter::getSplit - There are less " "samples from class %d (N = %d) than splits " "(K = %d): you may get weird results", i_class, length, K); split(dataset_class, test_fraction, tmp_split_[0], tmp_split_[1], k, true); if (i_class == 0) { split_ = tmp_split_.copy(); } else { split_[0] = new ConcatRowsVMatrix(split_[0], tmp_split_[0]); split_[1] = new ConcatRowsVMatrix(split_[1], tmp_split_[1]); } i_class++; } } else split(dataset, test_fraction, split_[0], split_[1], k, true); non_constant_test = split_[1]; } if (include_test_in_train) split_[0] = new ConcatRowsVMatrix(split_[0], split_[1]); if (append_train) split_.append(split_[0]); if (append_non_constant_test) { PLCHECK_MSG(!balance_classes, "Not implemented"); split_.append(non_constant_test); } return split_; }
int PLearn::KFoldSplitter::nSetsPerSplit | ( | ) | const [virtual] |
Returns the number of sets per split.
Implements PLearn::Splitter.
Definition at line 152 of file KFoldSplitter.cc.
References append_non_constant_test, and append_train.
{ int nsets = 2; if (append_train) nsets++; if (append_non_constant_test) nsets++; return nsets; }
int PLearn::KFoldSplitter::nsplits | ( | ) | const [virtual] |
Returns the number of available different "splits".
Implements PLearn::Splitter.
Definition at line 142 of file KFoldSplitter.cc.
References PLearn::Splitter::dataset, K, and PLearn::VMat::length().
Referenced by getSplit().
Reimplemented from PLearn::Splitter.
Definition at line 98 of file KFoldSplitter.h.
Definition at line 67 of file KFoldSplitter.h.
Referenced by declareOptions(), getSplit(), and nSetsPerSplit().
Definition at line 68 of file KFoldSplitter.h.
Referenced by declareOptions(), getSplit(), and nSetsPerSplit().
Definition at line 71 of file KFoldSplitter.h.
Referenced by declareOptions(), and getSplit().
Definition at line 69 of file KFoldSplitter.h.
Referenced by declareOptions(), getSplit(), and KFoldSplitter().
Definition at line 70 of file KFoldSplitter.h.
Referenced by declareOptions(), and getSplit().
Definition at line 72 of file KFoldSplitter.h.
Referenced by build_(), declareOptions(), getSplit(), and nsplits().