Documentation
¶
Index ¶
- type ClassProba
- type ClassesProba
- type DecisionTreeNode
- func (d *DecisionTreeNode) Load(filePath string) error
- func (d *DecisionTreeNode) LoadWithPrefix(reader *base.ClassifierDeserializer, prefix string) error
- func (d *DecisionTreeNode) Predict(what base.FixedDataGrid) (base.FixedDataGrid, error)
- func (d *DecisionTreeNode) Prune(using base.FixedDataGrid)
- func (d *DecisionTreeNode) Save(filePath string) error
- func (d *DecisionTreeNode) SaveWithPrefix(writer *base.ClassifierSerializer, prefix string) error
- func (d *DecisionTreeNode) String() string
- type DecisionTreeRule
- type GiniCoefficientRuleGenerator
- type ID3DecisionTree
- func (t *ID3DecisionTree) Fit(on base.FixedDataGrid) error
- func (t *ID3DecisionTree) GetMetadata() base.ClassifierMetadataV1
- func (t *ID3DecisionTree) Load(filePath string) error
- func (t *ID3DecisionTree) LoadWithPrefix(reader *base.ClassifierDeserializer, prefix string) error
- func (t *ID3DecisionTree) Predict(what base.FixedDataGrid) (base.FixedDataGrid, error)
- func (t *ID3DecisionTree) PredictProba(what base.FixedDataGrid) (ClassesProba, error)
- func (t *ID3DecisionTree) Save(filePath string) error
- func (t *ID3DecisionTree) SaveWithPrefix(writer *base.ClassifierSerializer, prefix string) error
- func (t *ID3DecisionTree) String() string
- type InformationGainRatioRuleGenerator
- type InformationGainRuleGenerator
- type NodeType
- type RandomTree
- func (rt *RandomTree) Fit(from base.FixedDataGrid) error
- func (rt *RandomTree) GetMetadata() base.ClassifierMetadataV1
- func (rt *RandomTree) Load(filePath string) error
- func (rt *RandomTree) LoadWithPrefix(reader *base.ClassifierDeserializer, prefix string) error
- func (rt *RandomTree) Predict(from base.FixedDataGrid) (base.FixedDataGrid, error)
- func (rt *RandomTree) Prune(with base.FixedDataGrid)
- func (rt *RandomTree) Save(filePath string) error
- func (rt *RandomTree) SaveWithPrefix(writer *base.ClassifierSerializer, prefix string) error
- func (rt *RandomTree) String() string
- type RandomTreeRuleGenerator
- type RuleGenerator
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type ClassProba ¶
type ClassesProba ¶
type ClassesProba []ClassProba
func (ClassesProba) Len ¶
func (o ClassesProba) Len() int
func (ClassesProba) Less ¶
func (o ClassesProba) Less(i, j int) bool
func (ClassesProba) Swap ¶
func (o ClassesProba) Swap(i, j int)
type DecisionTreeNode ¶
type DecisionTreeNode struct {
Type NodeType `json:"node_type"`
Children map[string]*DecisionTreeNode `json:"children"`
ClassDist map[string]int `json:"class_dist"`
Class string `json:"class_string"`
ClassAttr base.Attribute `json:"-"`
SplitRule *DecisionTreeRule `json:"decision_tree_rule"`
}
DecisionTreeNode represents a given portion of a decision tree.
func InferID3Tree ¶
func InferID3Tree(from base.FixedDataGrid, with RuleGenerator) *DecisionTreeNode
InferID3Tree builds a decision tree using a RuleGenerator from a set of Instances (implements the ID3 algorithm)
func (*DecisionTreeNode) Load ¶
func (d *DecisionTreeNode) Load(filePath string) error
Load reads from the classifier from an output file
func (*DecisionTreeNode) LoadWithPrefix ¶
func (d *DecisionTreeNode) LoadWithPrefix(reader *base.ClassifierDeserializer, prefix string) error
LoadWithPrefix reads from the classifier from part of another model
func (*DecisionTreeNode) Predict ¶
func (d *DecisionTreeNode) Predict(what base.FixedDataGrid) (base.FixedDataGrid, error)
Predict outputs a base.Instances containing predictions from this tree
func (*DecisionTreeNode) Prune ¶
func (d *DecisionTreeNode) Prune(using base.FixedDataGrid)
Prune eliminates branches which hurt accuracy
func (*DecisionTreeNode) Save ¶
func (d *DecisionTreeNode) Save(filePath string) error
Save sends the classification tree to an output file
func (*DecisionTreeNode) SaveWithPrefix ¶
func (d *DecisionTreeNode) SaveWithPrefix(writer *base.ClassifierSerializer, prefix string) error
func (*DecisionTreeNode) String ¶
func (d *DecisionTreeNode) String() string
String returns a human-readable representation of a given node and it's children
type DecisionTreeRule ¶
type DecisionTreeRule struct {
SplitAttr base.Attribute `json:"split_attribute"`
SplitVal float64 `json:"split_val"`
}
DecisionTreeRule represents the "decision" in "decision tree".
func (*DecisionTreeRule) MarshalJSON ¶
func (d *DecisionTreeRule) MarshalJSON() ([]byte, error)
func (*DecisionTreeRule) String ¶
func (d *DecisionTreeRule) String() string
String prints a human-readable summary of this thing.
func (*DecisionTreeRule) UnmarshalJSON ¶
func (d *DecisionTreeRule) UnmarshalJSON(data []byte) error
type GiniCoefficientRuleGenerator ¶
type GiniCoefficientRuleGenerator struct {
}
GiniCoefficientRuleGenerator generates DecisionTreeRules which minimize the Geni impurity coefficient at each node.
func (*GiniCoefficientRuleGenerator) GenerateSplitRule ¶
func (g *GiniCoefficientRuleGenerator) GenerateSplitRule(f base.FixedDataGrid) *DecisionTreeRule
GenerateSplitRule returns the non-class Attribute-based DecisionTreeRule which maximises the information gain.
IMPORTANT: passing a base.Instances with no Attributes other than the class variable will panic()
func (*GiniCoefficientRuleGenerator) GetSplitRuleFromSelection ¶
func (g *GiniCoefficientRuleGenerator) GetSplitRuleFromSelection(consideredAttributes []base.Attribute, f base.FixedDataGrid) *DecisionTreeRule
GetSplitRuleFromSelection returns the DecisionTreeRule which maximises the information gain amongst consideredAttributes
IMPORTANT: passing a zero-length consideredAttributes parameter will panic()
type ID3DecisionTree ¶
type ID3DecisionTree struct {
base.BaseClassifier
Root *DecisionTreeNode
PruneSplit float64
Rule RuleGenerator
}
ID3DecisionTree represents an ID3-based decision tree using the Information Gain metric to select which attributes to split on at each node.
func NewID3DecisionTree ¶
func NewID3DecisionTree(prune float64) *ID3DecisionTree
NewID3DecisionTree returns a new ID3DecisionTree with the specified test-prune ratio and InformationGain as the rule generator. If the ratio is less than 0.001, the tree isn't pruned.
func NewID3DecisionTreeFromRule ¶
func NewID3DecisionTreeFromRule(prune float64, rule RuleGenerator) *ID3DecisionTree
NewID3DecisionTreeFromRule returns a new ID3DecisionTree with the specified test-prun ratio and the given rule gnereator.
func (*ID3DecisionTree) Fit ¶
func (t *ID3DecisionTree) Fit(on base.FixedDataGrid) error
Fit builds the ID3 decision tree
func (*ID3DecisionTree) GetMetadata ¶
func (t *ID3DecisionTree) GetMetadata() base.ClassifierMetadataV1
func (*ID3DecisionTree) Load ¶
func (t *ID3DecisionTree) Load(filePath string) error
func (*ID3DecisionTree) LoadWithPrefix ¶
func (t *ID3DecisionTree) LoadWithPrefix(reader *base.ClassifierDeserializer, prefix string) error
func (*ID3DecisionTree) Predict ¶
func (t *ID3DecisionTree) Predict(what base.FixedDataGrid) (base.FixedDataGrid, error)
Predict outputs predictions from the ID3 decision tree
func (*ID3DecisionTree) PredictProba ¶
func (t *ID3DecisionTree) PredictProba(what base.FixedDataGrid) (ClassesProba, error)
Predict class probabilities of the input samples what, returns a sorted array (by probability) of classes, and another array representing it's probabilities
func (*ID3DecisionTree) Save ¶
func (t *ID3DecisionTree) Save(filePath string) error
func (*ID3DecisionTree) SaveWithPrefix ¶
func (t *ID3DecisionTree) SaveWithPrefix(writer *base.ClassifierSerializer, prefix string) error
func (*ID3DecisionTree) String ¶
func (t *ID3DecisionTree) String() string
String returns a human-readable version of this ID3 tree
type InformationGainRatioRuleGenerator ¶
type InformationGainRatioRuleGenerator struct {
}
InformationGainRatioRuleGenerator generates DecisionTreeRules which maximise the InformationGain at each node.
func (*InformationGainRatioRuleGenerator) GenerateSplitRule ¶
func (r *InformationGainRatioRuleGenerator) GenerateSplitRule(f base.FixedDataGrid) *DecisionTreeRule
GenerateSplitRule returns a DecisionTreeRule which maximises information gain ratio considering every available Attribute.
IMPORTANT: passing a base.Instances with no Attributes other than the class variable will panic()
func (*InformationGainRatioRuleGenerator) GetSplitRuleFromSelection ¶
func (r *InformationGainRatioRuleGenerator) GetSplitRuleFromSelection(consideredAttributes []base.Attribute, f base.FixedDataGrid) *DecisionTreeRule
GetSplitRuleFromSelection returns the DecisionRule which maximizes information gain, considering only a subset of Attributes.
IMPORTANT: passing a zero-length consideredAttributes parameter will panic()
type InformationGainRuleGenerator ¶
type InformationGainRuleGenerator struct {
}
InformationGainRuleGenerator generates DecisionTreeRules which maximize information gain at each node.
func (*InformationGainRuleGenerator) GenerateSplitRule ¶
func (r *InformationGainRuleGenerator) GenerateSplitRule(f base.FixedDataGrid) *DecisionTreeRule
GenerateSplitRule returns a DecisionTreeNode based on a non-class Attribute which maximises the information gain.
IMPORTANT: passing a base.Instances with no Attributes other than the class variable will panic()
func (*InformationGainRuleGenerator) GetSplitRuleFromSelection ¶
func (r *InformationGainRuleGenerator) GetSplitRuleFromSelection(consideredAttributes []base.Attribute, f base.FixedDataGrid) *DecisionTreeRule
GetSplitRuleFromSelection returns a DecisionTreeRule which maximises the information gain amongst the considered Attributes.
IMPORTANT: passing a zero-length consideredAttributes parameter will panic()
type RandomTree ¶
type RandomTree struct {
base.BaseClassifier
Root *DecisionTreeNode
Rule *RandomTreeRuleGenerator
}
RandomTree builds a decision tree by considering a fixed number of randomly-chosen attributes at each node
func NewRandomTree ¶
func NewRandomTree(attrs int) *RandomTree
NewRandomTree returns a new RandomTree which considers attrs randomly chosen attributes at each node.
func (*RandomTree) Fit ¶
func (rt *RandomTree) Fit(from base.FixedDataGrid) error
Fit builds a RandomTree suitable for prediction
func (*RandomTree) GetMetadata ¶
func (rt *RandomTree) GetMetadata() base.ClassifierMetadataV1
GetMetadata returns required serialization metadata
func (*RandomTree) Load ¶
func (rt *RandomTree) Load(filePath string) error
Load retrieves this model from a file
func (*RandomTree) LoadWithPrefix ¶
func (rt *RandomTree) LoadWithPrefix(reader *base.ClassifierDeserializer, prefix string) error
LoadWithPrefix retrives this random tree from disk with a given prefix.
func (*RandomTree) Predict ¶
func (rt *RandomTree) Predict(from base.FixedDataGrid) (base.FixedDataGrid, error)
Predict returns a set of Instances containing predictions
func (*RandomTree) Prune ¶
func (rt *RandomTree) Prune(with base.FixedDataGrid)
Prune removes nodes from the tree which are detrimental to determining the accuracy of the test set (with)
func (*RandomTree) Save ¶
func (rt *RandomTree) Save(filePath string) error
Save outputs this model to a file
func (*RandomTree) SaveWithPrefix ¶
func (rt *RandomTree) SaveWithPrefix(writer *base.ClassifierSerializer, prefix string) error
SaveWithPrefix outputs this model to a file with a prefix.
func (*RandomTree) String ¶
func (rt *RandomTree) String() string
String returns a human-readable representation of this structure
type RandomTreeRuleGenerator ¶
type RandomTreeRuleGenerator struct {
Attributes int
// contains filtered or unexported fields
}
RandomTreeRuleGenerator is used to generate decision rules for Random Trees
func (*RandomTreeRuleGenerator) GenerateSplitRule ¶
func (r *RandomTreeRuleGenerator) GenerateSplitRule(f base.FixedDataGrid) *DecisionTreeRule
GenerateSplitRule returns the best attribute out of those randomly chosen which maximises Information Gain
type RuleGenerator ¶
type RuleGenerator interface {
GenerateSplitRule(base.FixedDataGrid) *DecisionTreeRule
}
RuleGenerator implementations analyse instances and determine the best value to split on.
Source Files