Package nltk :: Package classify :: Module maxent :: Class TypedMaxentFeatureEncoding

type TypedMaxentFeatureEncoding

            object --+    
                     |    
MaxentFeatureEncodingI --+
                         |
                        TypedMaxentFeatureEncoding


A feature encoding that generates vectors containing integer, 
float and binary joint-features of the form::

Binary (for string and boolean features):
  joint_feat(fs, l) = { 1 if (fs[fname] == fval) and (l == label)
                      {
                      { 0 otherwise
Value (for integer and float features):
  joint_feat(fs, l) = { fval if     (fs[fname] == type(fval)) 
                      {         and (l == label)
                      {
                      { not encoded otherwise

Where C{fname} is the name of an input-feature, C{fval} is a value
for that input-feature, and C{label} is a label.

Typically, these features are constructed based on a training
corpus, using the L{train()} method.  

For string and boolean features [type(fval) not in (int, float)] 
this method will create one feature for each combination of 
C{fname}, C{fval}, and C{label} that occurs at least once in the
training corpus. 

For integer and float features [type(fval) in (int, float)] this 
method will create one feature for each combination of C{fname} 
and C{label} that occurs at least once in the training corpus.

For binary features the C{unseen_features} parameter can be used 
to add X{unseen-value features}, which are used whenever an input 
feature has a value that was not encountered in the training 
corpus.  These features have the form::

  joint_feat(fs, l) = { 1 if is_unseen(fname, fs[fname])
                      {      and l == label
                      {
                      { 0 otherwise

Where C{is_unseen(fname, fval)} is true if the encoding does not
contain any joint features that are true when C{fs[fname]==fval}.

The C{alwayson_features} parameter can be used to add X{always-on
features}, which have the form::

  joint_feat(fs, l) = { 1 if (l == label)
                      {
                      { 0 otherwise

These always-on features allow the maxent model to directly model
the prior probabilities of each label.

Instance Methods

[hide private]

__init__(self, labels, mapping, unseen_features=False, alwayson_features=False)

source code

list of (int, number)

encode(self, featureset, label)
Given a (featureset, label) pair, return the corresponding vector of joint-feature values.

source code

str

describe(self, f_id)
Returns: A string describing the value of the joint-feature whose index in the generated feature vectors is fid. source code

list

labels(self)
Returns: A list of the "known labels" -- i.e., all labels l such that self.encode(fs,l) can be a nonzero joint-feature vector for some value of fs. source code

int

length(self)
Returns: The size of the fixed-length joint-feature vectors that are generated by this encoding.

source code

Class Methods

[hide private]

train(cls, train_toks, count_cutoff=0, labels=None, **options)
Construct and return new feature encoding, based on a given training corpus train_toks. source code

Instance Variables

[hide private]

_labels
A list of attested labels.

_mapping
dict mapping from (fname,fval,label) -> fid

_length
The length of generated joint feature vectors.

_alwayson
dict mapping from label -> fid

_unseen
dict mapping from fname -> fid

Method Details

[hide private]

init(self, labels, mapping, unseen_features=False, alwayson_features=False)
(Constructor)

source code

Parameters:

labels - A list of the "known labels" for this encoding.
mapping - A dictionary mapping from (fname,fval,label) tuples to corresponding joint-feature indexes. These indexes must be the set of integers from 0...len(mapping). If mapping[fname,fval,label]=id, then self.encode({..., fname:fval, ...}, label)[id] is 1; otherwise, it is 0.
unseen_features - If true, then include unseen value features in the generated joint-feature vectors.
alwayson_features - If true, then include always-on features in the generated joint-feature vectors.

Overrides: object.__init__

encode(self, featureset, label)

source code

Given a (featureset, label) pair, return the corresponding vector of joint-feature values. This vector is represented as a list of (index, value) tuples, specifying the value of each non-zero joint-feature.

Returns: list of (int, number)
Overrides: MaxentFeatureEncodingI.encode: (inherited documentation)

describe(self, f_id)

source code

Returns: str: A string describing the value of the joint-feature whose index in the generated feature vectors is fid.
Overrides: MaxentFeatureEncodingI.describe: (inherited documentation)

labels(self)

source code

Returns: list: A list of the "known labels" -- i.e., all labels l such that self.encode(fs,l) can be a nonzero joint-feature vector for some value of fs.
Overrides: MaxentFeatureEncodingI.labels: (inherited documentation)

length(self)

source code

Returns: int: The size of the fixed-length joint-feature vectors that are generated by this encoding.
Overrides: MaxentFeatureEncodingI.length: (inherited documentation)

train(cls, train_toks, count_cutoff=0, labels=None, **options)
Class Method

source code

Construct and return new feature encoding, based on a given training corpus train_toks. See the class description for a description of the joint-features that will be included in this encoding.

Note: recognized feature values types are (int, float), over types are interpreted as regular binary features.

Parameters:

train_toks (list of tuples of (dict, str)) - Training data, represented as a list of pairs, the first member of which is a feature dictionary, and the second of which is a classification label.
count_cutoff (int) - A cutoff value that is used to discard rare joint-features. If a joint-feature's value is 1 fewer than count_cutoff times in the training corpus, then that joint-feature is not included in the generated encoding.
labels (list) - A list of labels that should be used by the classifier. If not specified, then the set of labels attested in train_toks will be used.
options - Extra parameters for the constructor, such as unseen_features and alwayson_features.

Overrides: MaxentFeatureEncodingI.train

type TypedMaxentFeatureEncoding

__init__(self, labels, mapping, unseen_features=False, alwayson_features=False) (Constructor)

encode(self, featureset, label)

describe(self, f_id)

labels(self)

length(self)

train(cls, train_toks, count_cutoff=0, labels=None, **options) Class Method

init(self, labels, mapping, unseen_features=False, alwayson_features=False)
(Constructor)

train(cls, train_toks, count_cutoff=0, labels=None, **options)
Class Method