rdkit.ML.DecTree.DecTree.DecTreeNode

Class DecTreeNode

Tree.TreeNode --+ | DecTreeNode

This is used to represent decision trees _DecTreeNode_s are simultaneously the roots and branches of decision trees. Everything is nice and recursive. _DecTreeNode_s can save the following pieces of internal state, accessible via standard setter/getter functions: 1) _Examples_: a list of examples which have been classified 2) _BadExamples_: a list of examples which have been misclassified 3) _TrainingExamples_: the list of examples used to train the tree 4) _TestExamples_: the list of examples used to test the tree

Instance Methods

[hide private]

__init__(self, *args, **kwargs)
constructor

source code

ClassifyExample(self, example, appendExamples=0)
Recursively classify an example by running it through the tree

source code

AddChild(self, name, label=None, data=None, isTerminal=0)
Constructs and adds a child with the specified data to our list

source code

GetExamples(self)

source code

SetExamples(self, examples)

source code

GetBadExamples(self)

source code

SetBadExamples(self, examples)

source code

GetTrainingExamples(self)

source code

SetTrainingExamples(self, examples)

source code

GetTestExamples(self)

source code

SetTestExamples(self, examples)

source code

ClearExamples(self)

source code

Inherited from Tree.TreeNode: AddChildNode, Destroy, GetChildren, GetData, GetLabel, GetLevel, GetName, GetParent, GetTerminal, NameModel, NameTree, Pickle, Print, PruneChild, ReplaceChildIndex, SetData, SetLabel, SetLevel, SetName, SetParent, SetTerminal, __cmp__, __eq__, __lt__, __str__

init(self, *args, **kwargs)
(Constructor)

source code

constructor

**Arguments**

  - parent: the parent of this node in the tree

  - name: the name of the node

  - label: the node's label (should be an integer)

  - data: an optional data field

  - level: an integer indicating the level of this node in the hierarchy
    (used for printing)

  - isTerminal: flags a node as being terminal.  This is useful for those
    times when it's useful to know such things.

Overrides: Tree.TreeNode.__init__: (inherited documentation)

ClassifyExample(self, example, appendExamples=0)

source code

Recursively classify an example by running it through the tree

**Arguments**

  - example: the example to be classified

  - appendExamples: if this is nonzero then this node (and all children)
    will store the example

**Returns**

  the classification of _example_

**NOTE:**
  In the interest of speed, I don't use accessor functions
  here.  So if you subclass DecTreeNode for your own trees, you'll
  have to either include ClassifyExample or avoid changing the names
  of the instance variables this needs.

AddChild(self, name, label=None, data=None, isTerminal=0)

source code

Constructs and adds a child with the specified data to our list

**Arguments**

 - name: the name of the new node

 - label: the label of the new node (should be an integer)

 - data: the data to be stored in the new node

 - isTerminal: a toggle to indicate whether or not the new node is
   a terminal (leaf) node.

**Returns*

  the _DecTreeNode_ which is constructed

Overrides: Tree.TreeNode.AddChild

Class DecTreeNode

__init__(self, *args, **kwargs) (Constructor)

ClassifyExample(self, example, appendExamples=0)

AddChild(self, name, label=None, data=None, isTerminal=0)

init(self, *args, **kwargs)
(Constructor)