Package CHEM :: Package ML :: Package features :: Module TreeExtractor :: Class TreeExtractor

Class TreeExtractor

BaseFeatureExtractor.BaseFeatureExtractor --+
                                            |
                                           TreeExtractor

Feature extractor that interprets molecule inputs as a graph of atoms and bonds. Treats each tree of depth d as a feature and records the count of how many times each one appears.

Instance Methods

[hide private]

__init__(self)
Default constructor, modify a few attributes to interpret as molecule feature extractor.

loadOptions(self, options)
Given an options object derived from an optparse.OptionParser, load any options of interest into the state of this object.

__call__(self, obj)
Primary abstract method.

makeSubtree(self, mol, rootAtom, treeDepth)
Return a copy of the molecule object, but only containing atoms starting from the indicated rootAtom up to a depth of treeDepth away.

labelSubtree(self, mol, rootAtom, depth, visitedAtomIndexes)

objectDescription(self, obj)
Input is a molecule object, just return the canonical SMILES representation

getNameID(self, obj)
Input is a molecule object, return the molecule's Title property

Inherited from BaseFeatureExtractor.BaseFeatureExtractor: loadArgs, main, outputFeatures

Class Variables

[hide private]

depth = 0

Inherited from BaseFeatureExtractor.BaseFeatureExtractor: inputFunction, inputIter, outFile, parser

Method Details

[hide private]

init(self)
(Constructor)

Default constructor, modify a few attributes to interpret as molecule feature extractor.

Overrides: BaseFeatureExtractor.BaseFeatureExtractor.__init__

loadOptions(self, options)

Given an options object derived from an optparse.OptionParser, load any options of interest into the state of this object. Sub-classes should have this handle any of the options it added to the command-line parser via the constructor.

Overrides: BaseFeatureExtractor.BaseFeatureExtractor.loadOptions

call(self, obj)
(Call operator)

Primary abstract method. Build a dictionary of an input object's important features.

Should be such that it is easy to compare any two objects' feature dictionaries.

This uses the "callable" interface, which means the object is a functor which should be used like a function call. For example: >>> from SpectrumExtractor import SpectrumExtractor; >>> featureExtractor = SpectrumExtractor(); >>> featureExtractor.k = 1; >>> featureDict = featureExtractor("teststring"); # Note that the extractor object looks like a function call >>> features = featureDict.keys(); >>> features.sort(); >>> for feature in features: ... print feature, featureDict[feature] e 1 g 1 i 1 n 1 r 1 s 2 t 3

Overrides: BaseFeatureExtractor.BaseFeatureExtractor.__call__: (inherited documentation)

objectDescription(self, obj)

Input is a molecule object, just return the canonical SMILES representation

Overrides: BaseFeatureExtractor.BaseFeatureExtractor.objectDescription

getNameID(self, obj)

Input is a molecule object, return the molecule's Title property

Overrides: BaseFeatureExtractor.BaseFeatureExtractor.getNameID

Class TreeExtractor

__init__(self) (Constructor)

loadOptions(self, options)

__call__(self, obj) (Call operator)

objectDescription(self, obj)

getNameID(self, obj)

init(self)
(Constructor)

call(self, obj)
(Call operator)