³ò
’B_Kc @ s¯ d Z d Z d d k Z d d k Z d d k Z d d k l Z y d d k Z Wn e j
o
d Z n Xd a
d d „ Z e e d „ Z
e d „ Z d „ Z d „ Z d S(
s™
A set of functions used to interface with the external U{megam
} maxent optimization package.
Before C{megam} can be used, you should tell NLTK where it can find
the C{megam} binary, using the L{config_megam()} function. Typical
usage:
>>> import nltk
>>> nltk.config_megam('.../path/to/megam')
>>> classifier = nltk.MaxentClassifier.train(corpus, 'megam')
s
epytext eniÿÿÿÿN( t find_binaryc
C s7 t d | d d d g d d d d d g d d
ƒa d S( sC
Configure NLTK's interface to the C{megam} maxent optimization
package.
@param bin: The full path to the C{megam} binary. If not specified,
then nltk will search the system for a C{megam} binary; and if
one is not found, it will raise a C{LookupError} exception.
@type bin: C{string}
t megamt env_varst MEGAMt MEGAMHOMEt binary_namess megam.optt
megam_686os megam_i686.optot urls" http://www.cs.utah.edu/~hal/megam/N( R t
_megam_bin( t bin( ( s) /p/zhu/06/nlp/nltk/nltk/classify/megam.pyt config_megam' s
c C sã | i ƒ } t g } t | ƒ D] \ } } | | | f q ~ ƒ } x— | D] \ }
} | i d | | ƒ | p t | i |
| ƒ | | ƒ n; x7 | D]/ } | i d ƒ t | i |
| ƒ | | ƒ q› W| i d ƒ qL Wd S( s
Generate an input file for C{megam} based on the given corpus of
classified tokens.
@type train_toks: C{list} of C{tuples} of (C{dict}, C{str})
@param train_toks: 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.
@type encoding: L{MaxentFeatureEncodingI}
@param encoding: A feature encoding, used to convert featuresets
into feature vectors.
@type stream: C{stream}
@param stream: The stream to which the megam input file should be
written.
@param bernoulli: If true, then use the 'bernoulli' format. I.e.,
all joint features have binary values, and are listed iff they
are true. Otherwise, list feature values explicitly. If
C{bernoulli=False}, then you must call C{megam} with the
C{-fvals} option.
@param explicit: If true, then use the 'explicit' format. I.e.,
list the features that would fire for any of the possible
labels, for each token. If C{explicit=True}, then you must
call C{megam} with the C{-explicit} option.
s %ds #s
N( t labelst dictt enumeratet writet _write_megam_featurest encode( t
train_tokst encodingt streamt bernoullit explicitR t _[1]t it labelt labelnumt
featuresett l( ( s) /p/zhu/06/nlp/nltk/nltk/classify/megam.pyt write_megam_file< s 9
c C s© t t j o t d ƒ ‚ n | p
t d ‚ | i ƒ i d ƒ } t i t | ƒ d ƒ } xG | D]? } | i ƒ o, | i ƒ \ } } t | ƒ | t | ƒ s 7