B >?[@sdZddlmZddlZddlmZddlmZddlm Z y ddl Z Wne k r`dZ YnXda dddZ dd d Zdd d ZddZddZdS)aO A set of functions used to interface with the external megam_ maxent optimization package. Before megam can be used, you should tell NLTK where it can find the megam binary, using the ``config_megam()`` function. Typical usage: >>> from nltk.classify import megam >>> megam.config_megam() # pass path to megam if not found in PATH # doctest: +SKIP [Found megam: ...] Use with MaxentClassifier. Example below, see MaxentClassifier documentation for details. nltk.classify.MaxentClassifier.train(corpus, 'megam') .. _megam: http://www.umiacs.umd.edu/~hal/megam/index.html )print_functionN) string_types)compat) find_binarycCs td|dgddddgddadS) aA Configure NLTK's interface to the ``megam`` maxent optimization package. :param bin: The full path to the ``megam`` binary. If not specified, then nltk will search the system for a ``megam`` binary; and if one is not found, it will raise a ``LookupError`` exception. :type bin: str ZmegamZMEGAMz megam.optZ megam_686zmegam_i686.optz/http://www.umiacs.umd.edu/~hal/megam/index.html)Zenv_varsZ binary_namesZurlN)r _megam_bin)binr2lib/python3.7/site-packages/nltk/classify/megam.py config_megam.s  r Tcs}tddt|D}x|D]\tdrZ|dfdd|Dn|d||st||n,x*|D]"}|dt|||qW|dq$Wd S) a Generate an input file for ``megam`` based on the given corpus of classified tokens. :type train_toks: list(tuple(dict, 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: MaxentFeatureEncodingI :param encoding: A feature encoding, used to convert featuresets into feature vectors. May optionally implement a cost() method in order to assign different costs to different class predictions. :type stream: 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 ``bernoulli=False``, then you must call ``megam`` with the ``-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 ``explicit=True``, then you must call ``megam`` with the ``-explicit`` option. css|]\}}||fVqdS)Nr).0ilabelrrr gsz#write_megam_file..cost:c3s |]}t|VqdS)N)strr)r l)encoding featuresetr rr rnsz%dz # N)labelsdict enumeratehasattrwritejoin_write_megam_featuresencode)Z train_toksrstream bernoulliexplicitrZlabelnumrr)rrr r write_megam_fileGs    r!cCsltdkrtd|std|d}t|d}x0|D](}|r<|\}}t||t|<q)N)TT)T)__doc__Z __future__rr3ZsixrZnltkrZnltk.internalsrr# ImportErrorrr r!r.rr>rrrr s        <