Go to the documentation of this file.
35 #ifndef QSAR_EXCEPTION
47 class MolecularSimilarity;
87 void readSDFile(
const char* file, std::multiset<int>& act,
bool useExDesc=1,
bool append=0,
bool translate_class_labels=0);
89 void readSDFile(
const char* file, std::set<String>& activity_names,
bool useExDesc=1,
bool append=0,
bool translate_class_labels=0,
bool calc_phychem_properties=1,
bool calc_topological_properties=1);
114 void readCSVFile(
const char* file,
int no_y,
bool xlabels,
bool ylabels,
const char* sep=
",",
bool appendDescriptors=0,
bool translate_class_labels=0);
146 std::vector<QSARData*>
evenSplit(
int no_test_splits,
int current_test_split_id,
int response_id=0)
const;
178 void getSimilarDescriptors(
int descriptor_ID,
double correlation, std::list<std::pair<uint,String> >& similar_descriptor_IDs)
const;
206 void readMatrix(
VMatrix& mat, std::ifstream& in,
char seperator,
unsigned int lines,
unsigned int col);
258 friend class FitModel;
VMatrix descriptor_transformations_
void readSDFile(const char *file, std::multiset< int > &act, bool useExDesc=1, bool append=0, bool translate_class_labels=0)
VMatrix descriptor_matrix_
void checkActivityIDs(std::multiset< int > &act, int no_properties)
void manipulateY(std::vector< String > v)
bool isResponseCentered() const
std::vector< double > * getSubstance(int s) const
vector< string > column_names_
std::multiset< int > invalidDescriptors_
void printMatrix(const VMatrix &mat, std::ostream &out) const
void discretizeY(std::vector< double > thresholds)
std::vector< QSARData * > generateExternalSet(double fraction) const
void centerData(bool center_Y=0)
vector< String > * readPropertyNames(String sd_file)
void readSDFile(const char *file)
void removeHighlyCorrelatedCompounds(double &compound_cor_threshold, double &feature_cor_threshold)
void readSDFile(const char *file, std::set< String > &activity_names, bool useExDesc=1, bool append=0, bool translate_class_labels=0, bool calc_phychem_properties=1, bool calc_topological_properties=1)
void manipulateY(String v)
void saveToFile(string filename) const
void setDataFolder(const char *folder)
std::vector< QSARData * > evenSplit(int no_test_splits, int current_test_split_id, int response_id=0) const
bool checkforDiscreteY(const char *file, std::multiset< int > &activity_IDs) const
void insertSubstance(const QSARData *source, int s, bool backtransformation=0)
void calculateTopologicalDescriptors(Molecule &mol, MolecularSimilarity &molsim, const std::map< String, int > &descriptor_map)
unsigned int getNoResponseVariables() const
vector< string > substance_names_
std::map< String, int > class_names_
void setDescriptorNames(const Molecule &m, std::multiset< int > &activity_IDs, bool useExDesc=1, bool resize=1)
void scaleAllDescriptors()
void readCSVFile(const char *file, int no_y, bool xlabels, bool ylabels, const char *sep=",", bool appendDescriptors=0, bool translate_class_labels=0)
unsigned int getNoSubstances() const
void removeInvalidSubstances(std::multiset< int > &inv)
bool isDataCentered() const
std::multiset< int > invalidSubstances_
void transformX(std::vector< String > v)
std::vector< QSARData * > partitionInputData(int p)
void readFromFile(string filename)
void getSimilarDescriptors(int descriptor_ID, double correlation, std::list< std::pair< uint, String > > &similar_descriptor_IDs) const
void calculateBALLDescriptors(Molecule &m)
void removeInvalidDescriptors(std::multiset< int > &invalidDescriptors)
VMatrix y_transformations_
bool checkforDiscreteY() const
void readMatrix(VMatrix &mat, std::ifstream &in, char seperator, unsigned int lines, unsigned int col)
const std::vector< string > * getSubstanceNames() const
std::vector< double > * getActivity(int s) const
unsigned int getNoDescriptors() const