o iB@srdZddlZddlmZzddlZWn eydZYnwdadddZdddZdd d Z d d Z d dZ dS)aP 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: https://www.umiacs.umd.edu/~hal/megam/index.html N) find_binarycCstd|dggdddadS)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 megamMEGAM)z megam.optr megam_686zmegam_i686.optz0https://www.umiacs.umd.edu/~hal/megam/index.html)env_vars binary_namesurlN)r _megam_bin)binr N/var/www/edux/Edux_v2/venv/lib/python3.10/site-packages/nltk/classify/megam.py config_megam)s  r Tcs}ddt|D}|D]J\tdr*|dfdd|Dn |d||s@t||n|D]}|dt|||qB|d qd 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. cSsi|]\}}||qSr r ).0ilabelr r r bsz$write_megam_file..cost:c3s"|] }t|VqdSN)strr)rlencoding featuresetrr r is z#write_megam_file..z%dz # N)labels enumeratehasattrwritejoin_write_megam_featuresencode) train_toksrstream bernoulliexplicitrlabelnumrr rr write_megam_fileBs    r(cCshtdurtd|sJd|d}t|d}|D]}|r1|\}}t||t|<q|S)z Given the stdout output generated by ``megam`` when training a model, return a ``numpy`` array containing the corresponding weight vector. This function does not currently handle bias features. Nz.This function requires that numpy be installedznon-explicit not supported yetrd)numpy ValueErrorstripsplitzerosfloatint)sfeatures_countr&linesweightslinefidweightr r r parse_megam_weights~s   r8cCsb|std|D]&\}}|r#|dkr|d|q|dkr"tdq|d|d|qdS)Nz:MEGAM classifier requires the use of an always-on feature.z %srz3If bernoulli=True, then allfeatures must be binary. )r+r)vectorr$r%r6fvalr r r r!s r!cCs~t|tr tdtdurttg|}tj|tjd}|\}}|j dkr3t t |t dt|tr:|S| dS)z= Call the ``megam`` binary with the given arguments. z args should be a list of stringsN)stdoutrzmegam command failed!zutf-8) isinstancer TypeErrorr r subprocessPopenPIPE communicate returncodeprintOSErrordecode)argscmdpr=stderrr r r call_megams      rLr)TT)T) __doc__r@nltk.internalsrr* ImportErrorr r r(r8r!rLr r r r s      <