scalation.theory
Members list
Type members
Classlikes
The Dataset class supports loading data files (e.g., CSV files) and pre-processing them to create predictor/input matrices and response/output vectors. FIX -- extend to models that allow multiple responses/outputs (vector -> matrix).
The Dataset class supports loading data files (e.g., CSV files) and pre-processing them to create predictor/input matrices and response/output vectors. FIX -- extend to models that allow multiple responses/outputs (vector -> matrix).
Value parameters
- fileName
-
the name of the file storing the dataset
- name
-
the name of the dataset
- xcols
-
the desired column numbers to take for predictors
- ycol
-
the desired column number to take for the response
Attributes
- Supertypes
-
trait Serializabletrait Producttrait Equalsclass Objecttrait Matchableclass AnyShow all
The Theory class provides a high-level unified way to run data science and machine learning models.
The Theory class provides a high-level unified way to run data science and machine learning models.
Attributes
- Supertypes
-
trait Serializabletrait Producttrait Equalsclass Objecttrait Matchableclass AnyShow all
Several modeling techniques such as decision trees need to divide the values into groups, e.g., for branch values: When 'xj' is categorical, these will be all its distinct values. Otherwise, these will be 0 (up to threshold) or 1 (above threshold).
The Variable class provides meta-data for a variable including its kind, distinct values, name and optional ontological concept. The variable may be an input variable (feature) or an output variable (response). Typically, it represents a column 'xj' in a data matrix.
Several modeling techniques such as decision trees need to divide the values into groups, e.g., for branch values: When 'xj' is categorical, these will be all its distinct values. Otherwise, these will be 0 (up to threshold) or 1 (above threshold).
Value parameters
- concept
-
an optional URI for an optological concept
- j
-
the index position within the relevant data matrix
- kind
-
indication of the variable kind
- name
-
the name of column (feature or response)
- xj
-
the column vector (feature/response)
Attributes
- See also
-
classifier.Nodefor 'threshold' - Companion
- object
- Supertypes
-
trait Serializabletrait Producttrait Equalsclass Objecttrait Matchableclass AnyShow all
The Variable companion object provides utilities for variables. Pick either COMMON or ROBUST values to the dummy variables.
The VariableKind enumeration indicates the kind of variable.
The VariableKind enumeration indicates the kind of variable.
Value parameters
- name
-
the name of the variable kind
Attributes
- Supertypes
-
trait Enumtrait Serializabletrait Producttrait Equalsclass Objecttrait Matchableclass AnyShow all
Attributes
- Supertypes
-
class Objecttrait Matchableclass Any
Attributes
- Supertypes
-
class Objecttrait Matchableclass Any
Value members
Concrete methods
The theoryTest main method test the Theory class.
The theoryTest main method test the Theory class.
runMain scalation.theory.theoryTest
Attributes
The variableTest the conversion of a categorical variable into multiple dummy variables.
The variableTest the conversion of a categorical variable into multiple dummy variables.
runMain scalation.modeling.variableTest