Of SrSSKrSSKrSSKJrJr SSKJr SSKJr SSK J r SSK J r SSK Jr "S S \S 9rS rS rSSjr"SS\S 9rg)zLanguage Model Interface.N)ABCMetaabstractmethod)bisect) accumulate) NgramCounter) log_base2) Vocabularyc>\rSrSrSrSr\S5r\S5rSr g) SmoothingzNgram Smoothing Interface Implements Chen & Goodman 1995's idea that all smoothing algorithms have certain features in common. This should ideally allow smoothing algorithms to work both with Backoff and Interpolation. cXlX lg)z :param vocabulary: The Ngram vocabulary object. :type vocabulary: nltk.lm.vocab.Vocabulary :param counter: The counts of the vocabulary items. :type counter: nltk.lm.counter.NgramCounter N)vocabcounts)self vocabularycounters -/usr/lib/python3/dist-packages/nltk/lm/api.py__init__Smoothing.__init__s  c[5eNNotImplementedError)rwords r unigram_scoreSmoothing.unigram_score& !##rc[5errrrcontexts r alpha_gammaSmoothing.alpha_gamma*rr)rrN) __name__ __module__ __qualname____firstlineno____doc__rrrr"__static_attributes__rrr r s4$$$$rr ) metaclassc0[U5[U5- $)z0Return average (aka mean) for sequence of items.)sumlen)itemss r_meanr0/s u:E ""rcp[U[R5(aU$[R"U5$r) isinstancerandomRandom)seed_or_generators r_random_generatorr64s*#V]]33  ==* ++rcU(d [S5e[U5[U5:wa [S5e[[U55nUSnUR 5nU[ X4U-5$)zXLike random.choice, but with weights. Heavily inspired by python 3.6 `random.choices`. z"Can't choose from empty populationz3The number of weights does not match the population) ValueErrorr.listrr3r) populationweightsrandom_generator cum_weightstotal thresholds r_weighted_choicerA:sj =>> :#g,&NOOz'*+K OE '')I f[)*;< ==rcp\rSrSrSrSSjrSSjrSSjr\SSj5r SSjr S r S r S r SS jrS rg) LanguageModelIzCABC for Language Models. Cannot be directly instantiated itself. NcXlU(aC[U[5(d.[R"SUR R <S3SS9 Uc [5OUUlUc[5Ul gUUl g)aCreates new LanguageModel. :param vocabulary: If provided, this vocabulary will be used instead of creating a new one when training. :type vocabulary: `nltk.lm.Vocabulary` or None :param counter: If provided, use this object to count ngrams. :type counter: `nltk.lm.NgramCounter` or None :param ngrams_fn: If given, defines how sentences in training text are turned to ngram sequences. :type ngrams_fn: function or None :param pad_fn: If given, defines how sentences in training text are padded. :type pad_fn: function or None z$The `vocabulary` argument passed to z- must be an instance of `nltk.lm.Vocabulary`.) stacklevelN) orderr2r warningswarn __class__r$rrr)rrHrrs rrLanguageModel.__init__Psi jZ@@ MM6t~~7N7N6QR??  &0%7Z\Z (/ln W rc^TR(d)Uc [S5eTRRU5 TRRU4SjU55 g)zUTrains the model on a text. :param text: Training text as a sequence of sentences. Nz:Cannot fit without a vocabulary or text to create it from.c3Z># UH nTRRU5v M" g7fr)rlookup).0sentrs r $LanguageModel.fit..ts#Dtt4::,,T22ts(+)rr9updater)rtextvocabulary_texts` rfitLanguageModel.fithsN zz& P JJ  o . DtDDrcURURRU5U(aURRU55$S5$)zMasks out of vocab (OOV) words and computes their model score. For model-specific logic of calculating scores, see the `unmasked_score` method. N)unmasked_scorerrOr s rscoreLanguageModel.scorevsI "" JJ  d #7TZZ%6%6w%?  PT  rc[5e)aScore a word given some optional context. Concrete models are expected to provide an implementation. Note that this method does not mask its arguments with the OOV label. Use the `score` method for that. :param str word: Word for which we want the score :param tuple(str) context: Context the word is in. If `None`, compute unigram score. :param context: tuple(str) or None :rtype: float rr s rrZLanguageModel.unmasked_scores "##rc6[URX55$)zwEvaluate the log score of this word in this context. The arguments are the same as for `score` and `unmasked_score`. )rr[r s rlogscoreLanguageModel.logscores D233rcxU(aUR[U5S-U$URR$)zHelper method for retrieving counts for a given context. Assumes context has been checked and oov words in it masked. :type context: tuple(str) or None )rr.unigrams)rr!s rcontext_countsLanguageModel.context_countss77>DKKG q( )' 2 CG;;CWCW rc tS[UVs/sHo RUSUSS5PM sn5-$s snf)aCalculate cross-entropy of model for given evaluation text. This implementation is based on the Shannon-McMillan-Breiman theorem, as used and referenced by Dan Jurafsky and Jordan Boyd-Graber. :param Iterable(tuple(str)) text_ngrams: A sequence of ngram tuples. :rtype: float r8N)r0r`)r text_ngramsngrams rentropyLanguageModel.entropys@E?J K{e]]59eCRj 1{ K   Ks!5 c8[SURU55$)z~Calculates the perplexity of the given text. This is simply 2 ** cross-entropy for the text, so the arguments are the same. g@)powrj)rrhs r perplexityLanguageModel.perplexitys 3 [122rc |^^Uc/O [U5n[U5nUS:Xa[U5TR:aUTR*S-SOUmTR TR R T55nT(aWU(dP[T5S:aTSSO/mTR TR R T55nT(a U(dMP[U5n[U[UU4SjU55U5$/n[U5H%nURTRSX&-US95 M' U$)ahGenerate words from the model. :param int num_words: How many words to generate. By default 1. :param text_seed: Generation can be conditioned on preceding context. :param random_seed: A random seed or an instance of `random.Random`. If provided, makes the random sampling part of generation reproducible. :return: One (str) word or a list of words generated from model. Examples: >>> from nltk.lm import MLE >>> lm = MLE(2) >>> lm.fit([[("a", "b"), ("b", "c")]], vocabulary_text=['a', 'b', 'c']) >>> lm.fit([[("a",), ("b",), ("c",)]]) >>> lm.generate(random_seed=3) 'a' >>> lm.generate(text_seed=['a']) 'b' Nrcc3H># UHnTRUT5v M g7fr)r[)rPwr!rs rrR)LanguageModel.generate..s>gdjjG,,gs") num_words text_seed random_seed) r:r6r.rHrerrOsortedrAtuplerangeappendgenerate) rrtrurvr=samples generated_r!s ` @rr{LanguageModel.generates3*$+Bi ,[9 >y>TZZ/4::+/+,  ))$***;*;G*DEG'),W)9'!"+r--djj.?.?.HI'' WoG#>g>>    y!A    '3 0 "r)rrHr)NNr)rcNN)r$r%r&r'r(rrWr[rrZr`rerjrnr{r)r*rrrCrCIsE E0 E  $ $4    35rrCr)r(r3rIabcrrr itertoolsrnltk.lm.counterr nltk.lm.utilrnltk.lm.vocabularyr r r0r6rArCr*rrrsK ' (")$'$6# , >eger