|
| TransformationModelLinear (const DataPoints &data, const Param ¶ms) |
| Constructor. More...
|
|
| ~TransformationModelLinear () override=default |
| Destructor. More...
|
|
double | evaluate (double value) const override |
| Evaluates the model at the given value. More...
|
|
void | getParameters (double &slope, double &intercept, String &x_weight, String &y_weight, double &x_datum_min, double &x_datum_max, double &y_datum_min, double &y_datum_max) const |
| Gets the "real" parameters. More...
|
|
void | invert () |
| Computes the inverse. More...
|
|
const Param & | getParameters () const |
| Gets the (actual) parameters. More...
|
|
| TransformationModel () |
| Constructor. More...
|
|
| TransformationModel (const TransformationModel::DataPoints &, const Param &) |
|
virtual | ~TransformationModel () |
| Destructor. More...
|
|
virtual void | weightData (DataPoints &data) |
| Weight the data by the given weight function. More...
|
|
virtual void | unWeightData (DataPoints &data) |
| Unweight the data by the given weight function. More...
|
|
bool | checkValidWeight (const String &weight, const std::vector< String > &valid_weights) const |
| Check for a valid weighting function string. More...
|
|
double | checkDatumRange (const double &datum, const double &datum_min, const double &datum_max) |
| Check that the datum is within the valid min and max bounds. More...
|
|
double | weightDatum (const double &datum, const String &weight) const |
| Weight the data according to the weighting function. More...
|
|
double | unWeightDatum (const double &datum, const String &weight) const |
| Apply the reverse of the weighting function to the data. More...
|
|
const Param & | getParameters () const |
| Gets the (actual) parameters. More...
|
|
std::vector< String > | getValidXWeights () const |
| Returns a list of valid x weight function strings. More...
|
|
std::vector< String > | getValidYWeights () const |
| Returns a list of valid y weight function strings. More...
|
|
Linear model for transformations.
The model can be inferred from data or specified using explicit parameters. If data is given, a least squares fit is used to find the model parameters (slope and intercept). Depending on parameter symmetric_regression
, a normal regression (y on x) or symmetric regression ( on ) is performed.
Without data, the model can be specified by giving the parameters slope
, intercept
, x_weight
, y_weight
explicitly.