The FitC companion object records the indices and labels for the base Quality of Fit (QoF) metrics/measures for the classification techniques.
Attributes
Members list
Value members
Concrete methods
Return the labels for the Vector Quality of Fit (QoF) micro-measures.
Return the labels for the Vector Quality of Fit (QoF) micro-measures.
Attributes
Return the help string that describes the Quality of Fit (QoF) measures provided by the FitC trait. The QoF measures are divided into four groups: general, ordinary, micro (per class) vectors and means of the micro vectors. Ordinary are values of the last element in the micro vectors and can be interpreted as, say the precision for the last class value/label, e.g., y = hasCancer in {no, yes}, is the precision of the yes prediction and is most meaningful when the number of class values/labels (k) is 2.
Return the help string that describes the Quality of Fit (QoF) measures provided by the FitC trait. The QoF measures are divided into four groups: general, ordinary, micro (per class) vectors and means of the micro vectors. Ordinary are values of the last element in the micro vectors and can be interpreted as, say the precision for the last class value/label, e.g., y = hasCancer in {no, yes}, is the precision of the yes prediction and is most meaningful when the number of class values/labels (k) is 2.
Attributes
- See also
-
en.wikipedia.org/wiki/Precision_and_recall
en.wikipedia.org/wiki/Cohen%27s_kappa
Create a table to store statistics for QoF measures, where each row corresponds to the statistics on a particular QoF measure, e.g., acc
Create a table to store statistics for QoF measures, where each row corresponds to the statistics on a particular QoF measure, e.g., acc
Attributes
Collect QoF results for a model and return them in a vector.
Collect QoF results for a model and return them in a vector.
Value parameters
- cv_fit
-
the fit array of statistics for cross-validation (upon test sets)
- fit
-
the fit vector with regard to the training set
Attributes
Test and report the confusion matrix and associate QoF measures.
Test and report the confusion matrix and associate QoF measures.
Value parameters
- fc
-
the
FitCobject - k
-
the number of class labels {0, 1, ... , k-1}
- y_
-
the actual class values
- yp
-
the predicted class values
Attributes
Test and report the confusion matrix and associate QoF measures.
Test and report the confusion matrix and associate QoF measures.
Value parameters
- fc
-
the
FitCobject - y_
-
the actual class values
- yp
-
the predicted class values // * @param k the number of class labels {0, 1, ... , k-1}