cUdZddlZddlZddlZddlZddlmZmZddl m Z m Z m Z ddl mZmZddlmZmZddlmZejeZdZd Zd Zdd ZGd dZGdde jejZGddZ dS)aModule for `online Hierarchical Dirichlet Processing `_. The core estimation code is directly adapted from the `blei-lab/online-hdp `_ from `Wang, Paisley, Blei: "Online Variational Inference for the Hierarchical Dirichlet Process", JMLR (2011) `_. Examples -------- Train :class:`~gensim.models.hdpmodel.HdpModel` .. sourcecode:: pycon >>> from gensim.test.utils import common_corpus, common_dictionary >>> from gensim.models import HdpModel >>> >>> hdp = HdpModel(common_corpus, common_dictionary) You can then infer topic distributions on new, unseen documents, with .. sourcecode:: pycon >>> unseen_document = [(1, 3.), (2, 4)] >>> doc_hdp = hdp[unseen_document] To print 20 topics with top 10 most probable words. .. sourcecode:: pycon >>> topic_info = hdp.print_topics(num_topics=20, num_words=10) The model can be updated (trained) with new documents via .. sourcecode:: pycon >>> hdp.update([[(1, 2)], [(1, 1), (4, 5)]]) N)gammalnpsi) interfacesutilsmatutils)dirichlet_expectationmean_absolute_difference) basemodelldamodel) deprecatedgh㈵>c^ttj|d}t|d|z }t|d|z }t|ddz}tj|}||d|dz <|ddtj|z|dd<|S)aFor stick-breaking hdp, get the :math:`\mathbb{E}[log(sticks)]`. Parameters ---------- sticks : numpy.ndarray Array of values for stick. Returns ------- numpy.ndarray Computed :math:`\mathbb{E}[log(sticks)]`. rN)rnpsumlenzeroscumsum)sticksdig_sumElogWElog1_Wn Elogstickss 6lib/python3.11/site-packages/gensim/models/hdpmodel.pyexpect_log_sticksrHs"&##$$G q NNW $E&)nnw&G F1IA!J Jq!a%x^bi&8&88JqrrN dctjt|}tjt |}|dd|f}tj||dz}tj|} t|D]} |} ||tj| |z |jzz}t |} tj| }tj||dz}t|| } | tkrntj | tj |z}|tj ||z | zz }|tj t|t|z z }|ttj |ttj |z z }||fS)avPerforms EM-iteration on a single document for calculation of likelihood for a maximum iteration of `max_iter`. Parameters ---------- doc_word_ids : int Id of corresponding words in a document. doc_word_counts : int Count of words in a single document. alpha : numpy.ndarray Lda equivalent value of alpha. beta : numpy.ndarray Lda equivalent value of beta. max_iter : int, optional Maximum number of times the expectation will be maximised. Returns ------- (numpy.ndarray, numpy.ndarray) Computed (:math:`likelihood`, :math:`\gamma`). Ng0.++)ronesrexprdotarrayrangeTr meanchangethreshrlogr) doc_word_idsdoc_word_countsalphabetamax_itergamma expElogthetabetadphinormcounts_ lastgamma Elogtheta meanchange likelihoods r lda_e_stepr7as, GCJJ  E6/6677L L !Ef\5))F2G Xo & &F 8__    rvfw.>'H'HHH)%00 vi(( &u--6-eY?? ( (  E 011J"&%%-94555J"&'%..8999J'"&--((726%==+A+AAAJ u rceZdZdZdZdZdS) SuffStatsa8Stores sufficient statistics for the current chunk of document(s) whenever Hdp model is updated with new corpus. These stats are used when updating lambda and top level sticks. The statistics include number of documents in the chunk, length of words in the documents and top level truncation level. c|||_tj||_tj||f|_dS)z Parameters ---------- T : int Top level truncation level. Wt : int Length of words in the documents. Dt : int Chunk size. N) m_chunksizerrm_var_sticks_ss m_var_beta_ss)selfr%WtDts r__init__zSuffStats.__init__s8!x{{Xq"g..rcn|jd|jddS)z3Fill the sticks and beta array with 0 scalar value.r N)r<fillr=)r>s rset_zerozSuffStats.set_zeros6 !!#&&& $$$$$rN)__name__ __module__ __qualname____doc__rArDrrr9r9s< ///"%%%%%rr9ceZdZdZ d!d Zd Zd"d ZdZdZd#dZ dZ dZ dZ dZ d$dZdZd%dZedd&dZeddZdZdZd ZdS)'HdpModela`Hierarchical Dirichlet Process model `_ Topic models promise to help summarize and organize large archives of texts that cannot be easily analyzed by hand. Hierarchical Dirichlet process (HDP) is a powerful mixed-membership model for the unsupervised analysis of grouped data. Unlike its finite counterpart, latent Dirichlet allocation, the HDP topic model infers the number of topics from the data. Here we have used Online HDP, which provides the speed of online variational Bayes with the modeling flexibility of the HDP. The idea behind Online variational Bayes in general is to optimize the variational objective function with stochastic optimization.The challenge we face is that the existing coordinate ascent variational Bayes algorithms for the HDP require complicated approximation methods or numerical optimization. This model utilises stick breaking construction of Hdp which enables it to allow for coordinate-ascent variational Bayes without numerical approximation. **Stick breaking construction** To understand the HDP model we need to understand how it is modelled using the stick breaking construction. A very good analogy to understand the stick breaking construction is `chinese restaurant franchise `_. For this assume that there is a restaurant franchise (`corpus`) which has a large number of restaurants (`documents`, `j`) under it. They have a global menu of dishes (`topics`, :math:`\Phi_{k}`) which they serve. Also, a single dish (`topic`, :math:`\Phi_{k}`) is only served at a single table `t` for all the customers (`words`, :math:`\theta_{j,i}`) who sit at that table. So, when a customer enters the restaurant he/she has the choice to make where he/she wants to sit. He/she can choose to sit at a table where some customers are already sitting , or he/she can choose to sit at a new table. Here the probability of choosing each option is not same. Now, in this the global menu of dishes correspond to the global atoms :math:`\Phi_{k}`, and each restaurant correspond to a single document `j`. So the number of dishes served in a particular restaurant correspond to the number of topics in a particular document. And the number of people sitting at each table correspond to the number of words belonging to each topic inside the document `j`. Now, coming on to the stick breaking construction, the concept understood from the chinese restaurant franchise is easily carried over to the stick breaking construction for hdp (`"Figure 1" from "Online Variational Inference for the Hierarchical Dirichlet Process" `_). A two level hierarchical dirichlet process is a collection of dirichlet processes :math:`G_{j}` , one for each group, which share a base distribution :math:`G_{0}`, which is also a dirichlet process. Also, all :math:`G_{j}` share the same set of atoms, :math:`\Phi_{k}`, and only the atom weights :math:`\pi _{jt}` differs. There will be multiple document-level atoms :math:`\psi_{jt}` which map to the same corpus-level atom :math:`\Phi_{k}`. Here, the :math:`\beta` signify the weights given to each of the topics globally. Also, each factor :math:`\theta_{j,i}` is distributed according to :math:`G_{j}`, i.e., it takes on the value of :math:`\Phi_{k}` with probability :math:`\pi _{jt}`. :math:`C_{j,t}` is an indicator variable whose value `k` signifies the index of :math:`\Phi`. This helps to map :math:`\psi_{jt}` to :math:`\Phi_{k}`. The top level (`corpus` level) stick proportions correspond the values of :math:`\beta`, bottom level (`document` level) stick proportions correspond to the values of :math:`\pi`. The truncation level for the corpus (`K`) and document (`T`) corresponds to the number of :math:`\beta` and :math:`\pi` which are in existence. Now, whenever coordinate ascent updates are to be performed, they happen at two level. The document level as well as corpus level. At document level, we update the following: #. The parameters to the document level sticks, i.e, a and b parameters of :math:`\beta` distribution of the variable :math:`\pi _{jt}`. #. The parameters to per word topic indicators, :math:`Z_{j,n}`. Here :math:`Z_{j,n}` selects topic parameter :math:`\psi_{jt}`. #. The parameters to per document topic indices :math:`\Phi_{jtk}`. At corpus level, we update the following: #. The parameters to the top level sticks, i.e., the parameters of the :math:`\beta` distribution for the corpus level :math:`\beta`, which signify the topic distribution at corpus level. #. The parameters to the topics :math:`\Phi_{k}`. Now coming on to the steps involved, procedure for online variational inference for the Hdp model is as follows: 1. We initialise the corpus level parameters, topic parameters randomly and set current time to 1. 2. Fetch a random document j from the corpus. 3. Compute all the parameters required for document level updates. 4. Compute natural gradients of corpus level parameters. 5. Initialise the learning rate as a function of kappa, tau and current time. Also, increment current time by 1 each time it reaches this step. 6. Update corpus level parameters. Repeat 2 to 6 until stopping condition is not met. Here the stopping condition corresponds to * time limit expired * chunk limit reached * whole corpus processed Attributes ---------- lda_alpha : numpy.ndarray Same as :math:`\alpha` from :class:`gensim.models.ldamodel.LdaModel`. lda_beta : numpy.ndarray Same as :math:`\beta` from from :class:`gensim.models.ldamodel.LdaModel`. m_D : int Number of documents in the corpus. m_Elogbeta : numpy.ndarray: Stores value of dirichlet expectation, i.e., compute :math:`E[log \theta]` for a vector :math:`\theta \sim Dir(\alpha)`. m_lambda : {numpy.ndarray, float} Drawn samples from the parameterized gamma distribution. m_lambda_sum : {numpy.ndarray, float} An array with the same shape as `m_lambda`, with the specified axis (1) removed. m_num_docs_processed : int Number of documents finished processing.This is incremented in size of chunks. m_r : list Acts as normaliser in lazy updating of `m_lambda` attribute. m_rhot : float Assigns weight to the information obtained from the mini-chunk and its value it between 0 and 1. m_status_up_to_date : bool Flag to indicate whether `lambda `and :math:`E[log \theta]` have been updated if True, otherwise - not. m_timestamp : numpy.ndarray Helps to keep track and perform lazy updates on lambda. m_updatect : int Keeps track of current time and is incremented every time :meth:`~gensim.models.hdpmodel.HdpModel.update_lambda` is called. m_var_sticks : numpy.ndarray Array of values for stick. m_varphi_ss : numpy.ndarray Used to update top level sticks. m_W : int Length of dictionary for the input corpus. N?P@r{Gz?-C6?c8||_||_||_||_||_||_t j||_d|_ d|_ t||_ d|_ |rt||_ | |_||_| |_| |_t%jd| dz f|_d|jd<t+| dz dd|jd<t%j| |_|jdd| |j f|j zdz| |j zz | z |_| |_t5|j|jz|_|dz|_||_| |_d|_d|_ d|_!t%j|j tD |_#dg|_$t%j%|jd |_&||_'|jr|(||)|dSdS) a Parameters ---------- corpus : iterable of list of (int, float) Corpus in BoW format. id2word : :class:`~gensim.corpora.dictionary.Dictionary` Dictionary for the input corpus. max_chunks : int, optional Upper bound on how many chunks to process. It wraps around corpus beginning in another corpus pass, if there are not enough chunks in the corpus. max_time : int, optional Upper bound on time (in seconds) for which model will be trained. chunksize : int, optional Number of documents in one chuck. kappa: float,optional Learning parameter which acts as exponential decay factor to influence extent of learning from each batch. tau: float, optional Learning parameter which down-weights early iterations of documents. K : int, optional Second level truncation level T : int, optional Top level truncation level alpha : int, optional Second level concentration gamma : int, optional First level concentration eta : float, optional The topic Dirichlet scale : float, optional Weights information from the mini-chunk of corpus to calculate rhot. var_converge : float, optional Lower bound on the right side of convergence. Used when updating variational parameters for a single document. outputdir : str, optional Stores topic and options information in the specified directory. random_state : {None, int, array_like, :class:`~np.random.RandomState`, optional} Adds a little random jitter to randomize results around same alpha when trying to fetch a closest corresponding lda model from :meth:`~gensim.models.hdpmodel.HdpModel.suggested_lda_model` NrrrMrT)dtypeaxis)*corpusid2word chunksize max_chunksmax_time outputdirrget_random_state random_state lda_alphalda_betarm_Wm_Dm_Tm_Km_alpham_gammarr m_var_sticksr$ m_varphi_ssr-m_lambdam_etar m_Elogbetam_taum_kappam_scale m_updatectm_status_up_to_datem_num_docs_processedint m_timestampm_rr m_lambda_summ_var_converge save_optionsupdate)r>rYrZr\r]r[kappatauKr%r*r-etascale var_converger^r`s rrAzHdpModel.__init__'sZ  "$  "!2<@@ w<<  #6{{DH  HaQZ00"!$QUAr22!8A;;)//S1dh-HH48SVYY]^aeai]ijmpp  / T]0JKK1W   #' $%!8DHC8883F4=q999* >        KK       rc|j|jtdt|}t |dkr(t dt |tjt ||jj df}t|D]<\}}|st|\}}t|||j|j\}}|||ddf<=|S)a|Infers the gamma value based for `chunk`. Parameters ---------- chunk : iterable of list of (int, float) Corpus in BoW format. Returns ------- numpy.ndarray First level concentration, i.e., Gamma value. Raises ------ RuntimeError If model doesn't trained yet. Nz*model must be trained to perform inferencerz/performing inference on a chunk of %i documentsr) rarb RuntimeErrorlistrloggerdebugrrshape enumeratezipr7) r>chunkr-ddocidsr1r2gammads r inferencezHdpModel.inferences& > MT] MKLL LU  u::> X LLJCPUJJ W W W#e**dm&9!&<=>>&& ! !FAs s)KC"3 NNIAv E!QQQ$KK rctj|\}}|r||S||gd}t |dkr|t |z ng}fdt |DS)a_Accessor method for generating topic distribution of given document. Parameters ---------- bow : {iterable of list of (int, float), list of (int, float) BoW representation of the document/corpus to get topics for. eps : float, optional Ignore topics with probability below `eps`. Returns ------- list of (int, float) **or** :class:`gensim.interfaces.TransformedCorpus` Topic distribution for the given document/corpus `bow`, as a list of `(topic_id, topic_probability)` or transformed corpus rc*g|]\}}|k ||fSrIrI).0topicid topicvalueepss r z(HdpModel.__getitem__..s/lll*=':ZdhkZkl*%lllr)r is_corpus_applyrrr)r>bowrrrYr- topic_dists ` r __getitem__zHdpModel.__getitem__s""OC00 6  ';;v&& &u%%a(+.u::?BUSZZ'' llll:AVAVllllrctdtd|jz }d}tj} t j||jD]}|||xjt|z c_|dz }| |||jrl| | \}}||_ ||_|d|jr|dS||zdkrO| |dt$d|j|j8)aMTrain the model with new documents, by EM-iterating over `corpus` until any of the conditions is satisfied. * time limit expired * chunk limit reached * whole corpus processed Parameters ---------- corpus : iterable of list of (int, float) Corpus in BoW format. ri'rTNz$PROGRESS: finished document %i of %i)maxrtr[time perf_counterrgrouper update_chunkrsrupdate_finishedupdate_expectations hdp_to_ldararb print_topicsr^ save_topicsrinford)r>rY save_freqchunks_processed start_timerr*r+s rrzzHdpModel.updates{3ut~56677 &((  mvt~>> m m!!%((())SZZ7)) A% '' 4DdF_``m,,..."&//"3"3KE4%*DN$(DM%%b)))~+((***FF% 1Q6m,,...%%b)))KK FHacgcklll) mrc|jr ||jkp@|jotj|z |jkp|j o|j o ||jkS)aFlag to determine whether the model has been updated with the new corpus or not. Parameters ---------- start_time : float Indicates the current processor time as a floating point number expressed in seconds. The resolution is typically better on Windows than on Unix by one microsecond due to differing implementation of underlying function calls. chunks_processed : int Indicates progress of the update in terms of the number of chunks processed. docs_processed : int Indicates number of documents finished processing.This is incremented in size of chunks. Returns ------- bool If True - model is updated, False otherwise. )r\r]rrrd)r>rrdocs_processeds rrzHdpModel.update_finishedsk,_ D!1T_!D Z R$"3"5"5 "BT]"R Z O#XDM(9XnPTPX>X [rTc t}g}|D]5}|D]0\}}||vr't|||<||16t|} tjfdj|D} jdd|fxxtjjd| z zcc<tj jdd|fztj j zj ddtj fzz jdd|f<tj| t|} t#j} d} d}|D]W}t|dkrBt'|\}}| | |||j}|t-|z }| |z } X|r| ||| |fS)aPerforms lazy update on necessary columns of lambda and variational inference for documents in the chunk. Parameters ---------- chunk : iterable of list of (int, float) Corpus in BoW format. update : bool, optional If True - call :meth:`~gensim.models.hdpmodel.HdpModel.update_lambda`. opt_o : bool, optional Passed as argument to :meth:`~gensim.models.hdpmodel.HdpModel.update_lambda`. If True then the topics will be ordered, False otherwise. Returns ------- (float, int) A tuple of likelihood and sum of all the word counts from each document in the corpus. c*g|]}j|SrI)rv)rtr>s rrz)HdpModel.update_chunk..&sHHHqtx{HHHrNrUr r)dictrappendrr#rurkr!rvrrlrcrwnewaxisrmr9rerrir doc_e_steprxr update_lambda)r>rrzopt_o unique_words word_listrword_idr2wtrwssElogsticks_1stscorecountr(r) doc_scores` rrzHdpModel.update_chunks(vv   . .C! . . ,..,/ ,=,=L)$$W--- . ^^XHHHHD,.\s<<<L$<<rrrr(r)rchunkids Elogbeta_docvphir6old_likelihoodconvergeiterr,var_phi log_var_philog_normlog_phiElogsticks_2ndphi_allphi_cum log_alphars ` rrzHdpModel.doc_e_stepCs2=<<<|<<<qqq,7 HaA& ' '!|!gs<(($(344s:TXE Xo6 8c>6 X 5L6 ax .&)G(JKK*2*H*Q*Q'h&--&)G(JKKn\*2*H*Q*Q'h&--ax &fWl335&.&DS&I&I#(fWoofWl335F&.&DS&I&I#(fWooBH_55aaamDDG=DHqL=(8 91===AaDiwqqq!""u~q 9 9::G<")BIg,>,>"?"??AaD.q11NJ "&.;">'!IJJ JJt|,,I 48a<94 4J"&A,,''G "&"(C+>"?"?2: "NQR"RWZ[\W]W]`gWg!hii iJ "&1!6!677"&:L:LL LJ "&.7":c!ABB BJ "&9W)X)X!XYY YJ"^3s>7J7JJH'N)# <:;;; AIDmXo6 8c>6 X 5L6 t bfWa000 H%%% 35?;R)S)SS%%%rcd|_|jt|j|jz|j z}|t krt }||_|jdd|fd|z z||j z|j z|j z z|jdd|f<d|z |j z||j ztj|j dz|j z z|_ |xjdz c_|j|j|<|j|jdtjd|z zd|z |jz||jz|j z|j z z|_|r||jd|jdz dz|jd<tj|jdd}tjtj||jz|jd<dS)aUpdate appropriate columns of lambda and top level sticks based on documents. Parameters ---------- sstats : :class:`~gensim.models.hdpmodel.SuffStats` Statistic for all document(s) in the chunk. word_list : list of int Contains word id of all the unique words in the chunk of documents on which update is being performed. opt_o : bool, optional If True - invokes a call to :meth:`~gensim.models.hdpmodel.HdpModel.optimal_ordering` to order the topics. FNrrWrUrMr)rrrppowrnrqro rhot_boundm_rhotrkrdr=r;rwrrrurvrr'rjr<optimal_orderingrerirrrh)r>sstatsrrrhot var_phi_sums rrzHdpModel.update_lambdas$) |c$*t"> NNN *  D  M!!!Y, '1t8 4tdhI]7]`f`r7r r aaal#X):: 48ObfV%9BBB BVEW WX 1&*o#  rva$h'7'778884Z4+ +dV5K.Kdh.VY_Yk.k k   $  ! ! # # # $/ A >D!i 0 455 !y;)?)?@@4<O!rctj|jd}|j||_|j|ddf|_|j||_|j|ddf|_dS)z Performs ordering on the topics.TreverseN)rargsortrwrjrkrm)r>idxs rrzHdpModel.optimal_orderingsjt0$???+C0 c111f-  -c2/#qqq&1rc t|jD]Q}|jdd|fxxtj|jd|j|j|z zcc<Rt|j|jzt|j|jz|j ddtj fzz |_ |j |jdd<d|_ dS)a0Since we're doing lazy updates on lambda, at any given moment the current state of lambda may not be accurate. This function updates all of the elements of lambda and Elogbeta so that if (for example) we want to print out the topics we've learned we'll get the correct behavior. NrUT)r$rcrkrr!rvrurrlrwrrmrqrr)r>ws rrzHdpModel.update_expectationss tx X XA M!!!Q$   26$(2,$BRSTBU9V*V#W#W W      T]* + +c$(TZ2G$J[\]\]\]_a_i\iJj2j.k.k k #o#'   rrFc|tjd|}|js||j|jz}t |j|}|||||S)aPrint the `num_words` most probable words for topic `topic_id`. Parameters ---------- topic_id : int Acts as a representative index for a particular topic. topn : int, optional Number of most probable words to show from given `topic_id`. log : bool, optional If True - logs a message with level INFO on the logger object. formatted : bool, optional If True - get the topics as a list of strings, otherwise - get the topics as lists of (weight, word) pairs. num_words : int, optional DEPRECATED, USE `topn` INSTEAD. Warnings -------- The parameter `num_words` is deprecated, will be removed in 4.0.0, please use `topn` instead. Returns ------- list of (str, numpy.float) **or** list of str Topic terms output displayed whose format depends on `formatted` parameter. N]The parameter `num_words` is deprecated, will be removed in 4.0.0, please use `topn` instead.) warningswarnrrrrkrlHdpTopicFormatterrZ show_topic)r>topic_idtopnr' formatted num_wordsbetas hdp_formatters rrzHdpModel.show_topics4   Mo   D' '  $ $ & & &  *)$,>> ''$YGGGrcf|j|jz}||ddddfz S)zGet the term topic matrix learned during inference. Returns ------- np.ndarray `num_topics` x `vocabulary_size` array of floats rrWN)rkrlr)r>topicss r get_topicszHdpModel.get_topicss8+  **111d7333rc|js||j|jz}t |j|}|||||S)a=Print the `num_words` most probable words for `num_topics` number of topics. Parameters ---------- num_topics : int, optional Number of topics for which most probable `num_words` words will be fetched, if -1 - print all topics. num_words : int, optional Number of most probable words to show from `num_topics` number of topics. log : bool, optional If True - log a message with level INFO on the logger object. formatted : bool, optional If True - get the topics as a list of strings, otherwise - get the topics as lists of (weight, word) pairs. Returns ------- list of (str, numpy.float) **or** list of str Output format for topic terms depends on the value of `formatted` parameter. )rrrrkrlrrZ show_topics)r> num_topicsrr'rrrs rrzHdpModel.show_topicssZ(' '  $ $ & & &  *)$,>> ((YYOOOrz9This method will be removed in 4.0.0, use `save` instead.c|jstd|d}nd|z}|jd|d}td||j|jz}t j||dS)a>Save discovered topics. Warnings -------- This method is deprecated, use :meth:`~gensim.models.hdpmodel.HdpModel.save` instead. Parameters ---------- doc_count : int, optional Indicates number of documents finished processing and are to be saved. z@cannot store topics without having specified an output directoryNfinalzdoc-%i/z.topicszsaving topics to %s)r^rerrorrrkrlrsavetxt)r> doc_countfnamers rrzHdpModel.save_topics9s~ ] LL[ \ \ \  )EEy(E"&...%%%8 )5111  * 5%     rc^|jstddSd|jz}tj|d5}|dt |jdz z|dt |jz|dt |j z|d t |j z|d t |j z|d t |j z|d t |j z|d t |jz|dt |jz|dt |jz|dt |jzddddS#1swxYwYdS)zWrites all the values of the attributes for the current model in "options.dat" file. Warnings -------- This method is deprecated, use :meth:`~gensim.models.hdpmodel.HdpModel.save` instead. zAcannot store options without having specified an output directoryNz%s/options.datwbztau: %s rzchunksize: %s zvar_converge: %s zD: %s zK: %s zT: %s zW: %s z alpha: %s z kappa: %s zeta: %s z gamma: %s )r^rrropenwritestrrnr[rxrdrfrercrgrorlrh)r>rfouts rryzHdpModel.save_optionsSs ~  LL\ ] ] ] F 4>1 Zt $ $ : JJ{Sa%8%88 9 9 9 JJ(3t~+>+>> ? ? ? JJ+c$2E.F.FF G G G JJy3tx==0 1 1 1 JJy3tx==0 1 1 1 JJy3tx==0 1 1 1 JJy3tx==0 1 1 1 JJ}s4<'8'88 9 9 9 JJ}s4<'8'88 9 9 9 JJ{S__4 5 5 5 JJ}s4<'8'88 9 9 9 : : : : : : : : : : : : : : : : : :sGH""H&)H&c|jd|jd|jdzz }tj|j}d}t d|jdz D]}|||z||<|||z }|||jdz <||jz}|j|jz|j|jz|j ddtj fzz }||fS)zGet corresponding alpha and beta values of a LDA almost equivalent to current HDP. Returns ------- (numpy.ndarray, numpy.ndarray) Alpha and Beta arrays. rrrMN) rirrrer$rgrkrlrcrwr)r>rr*leftir+s rrzHdpModel.hdp_to_ldams"1%):1)=@QRS@T)TU""q$(Q,'' # #Aay4'E!H%(?DD"dhl   *tx$*/DtGXYZYZYZ\^\fYfGg/ghd{rc|\}}tj|j||j|jt j}||jdd<|S)aIGet a trained ldamodel object which is closest to the current hdp model. The `num_topics=m_T`, so as to preserve the matrices shapes when we assign alpha and beta. Returns ------- :class:`~gensim.models.ldamodel.LdaModel` Closest corresponding LdaModel to current HdpModel. )rr*rZr`rVN) rr LdaModelrerZr`rfloat64 expElogbeta)r>r*r+ldams rsuggested_lda_modelzHdpModel.suggested_lda_models]oo'' t xudlQUQbjljt   # rctd|j|j!|\|_|_d}d}t |D]\}}t |dkrt|\}}t|||j|j\}} | tj | z } |jdd|f} tj tj | | } t| t |z } td|| ||z }|t|z }td||z |t ||S)aMEvaluates the model on test corpus. Parameters ---------- corpus : iterable of list of (int, float) Test corpus in BoW format. Returns ------- float The value of total likelihood obtained by evaluating the model for all documents in the test corpus. zTEST: evaluating test corpusNr rzTEST: %6d %.5fzrYr total_wordsrrr(r)r6r-theta lda_betad log_predictsrs revaluate_test_corpuszHdpModel.evaluate_test_corpussd  2333 > >T] >,0OO,=,= )DNDM '' 4 4FAs3xx!| 403S - o$.|_dn^b^k$l$l! Eu - M!!!\/: !vbfUI&>&>??  --C8  /I>>>#s?333  J K F     r)NNrLrMrNrOrPrrrQrMrRNN)rQ)TTrFFN)rrFT)N)rErFrGrHrArrrzrrrrrrrrrr rryrr rrIrrrKrKsyytCGHIr topic_data topic_filerr topics_sumsrs rrAzHdpTopicFormatter.__init__s*  /-.. .  /FF  /Zz 122FF-.. .fV!,,, {D9993K $  &%E r c0|||dS)aTGive the most probable `num_words` words from `num_topics` topics. Alias for :meth:`~gensim.models.hdpmodel.HdpTopicFormatter.show_topics`. Parameters ---------- num_topics : int, optional Top `num_topics` to be printed. num_words : int, optional Top `num_words` most probable words to be printed from each topic. Returns ------- list of (str, numpy.float) **or** list of str Output format for `num_words` words from `num_topics` topics depends on the value of `self.style` attribute. T)r)r>rrs rrzHdpTopicFormatter.print_topicss" It<<z/HdpTopicFormatter.show_topics..s adrTkeyr) rminrrr$rrsortedshow_topic_terms format_topicrrr) r>rrr'rshownklambdaktemp topic_termstopics rrzHdpTopicFormatter.show_topicss(Q'' S^^44 z""  Ai111oG -Gwc'll 3 344D$NNDAAAD//i@@K )))![99'KK&&&K( LL     rcb|tjd|}|||dS)aPrint the `topn` most probable words from topic id `topic_id`. Warnings -------- The parameter `num_words` is deprecated, will be removed in 4.0.0, please use `topn` instead. Parameters ---------- topic_id : int Acts as a representative index for a particular topic. topn : int, optional Number of most probable words to show from given `topic_id`. num_words : int, optional DEPRECATED, USE `topn` INSTEAD. Returns ------- list of (str, numpy.float) **or** list of str Output format for terms from a single topic depends on the value of `formatted` parameter. NrT)r)rrr)r>rrrs r print_topiczHdpTopicFormatter.print_topic+sB,   Mo   Dx>>>rrc|tjd|}|j|ddf}||z }t |t t |}t|dd}|||}|r3| ||} |rt | n||f} | dS)aGive the most probable `num_words` words for the id `topic_id`. Warnings -------- The parameter `num_words` is deprecated, will be removed in 4.0.0, please use `topn` instead. Parameters ---------- topic_id : int Acts as a representative index for a particular topic. topn : int, optional Number of most probable words to show from given `topic_id`. log : bool, optional If True logs a message with level INFO on the logger object, False otherwise. formatted : bool, optional If True return the topics as a list of strings, False as lists of (word, weight) pairs. num_words : int, optional DEPRECATED, USE `topn` INSTEAD. Returns ------- list of (str, numpy.float) **or** list of str Output format for terms from a single topic depends on the value of `self.style` attribute. Nrc|dSr$rIr%s rr'z.HdpTopicFormatter.show_topic..ns !A$rTr(r) rrrrrr$rr+r,r-rr) r>rrr'rrr0r1r2r3s rrzHdpTopicFormatter.show_topicIs6   Mo   D)HaaaK(GKKMM)7E#g,,//00d===++D$77  ,%%h <s rrz6HdpTopicFormatter.show_topic_terms..s)[[[=FC%v.[[[rNrI)r>rrs` rr,z"HdpTopicFormatter.show_topic_terms~s* \[[[JzPYzDZ[[[[rc|j|jkr dd|D}ndd|D}||f}|S)aFormat the display for a single topic in two different ways. Parameters ---------- topic_id : int Acts as a representative index for a particular topic. topic_terms : list of (str, numpy.float) Contains the most probable words from a single topic. Returns ------- list of (str, numpy.float) **or** list of str Output format for topic terms depends on the value of `self.style` attribute. z + c3*K|]\}}d||fzVdS)z%.3f*%sNrIrwordr:s r z1HdpTopicFormatter.format_topic..s/ZZNT6Y&$7ZZZZZZr c3*K|]\}}d||fzVdS)z %20s %.8fNrIr>s rr@z1HdpTopicFormatter.format_topic..s0bbNT6.$?bbbbbbr)rrjoin)r>rr2fmts rr-zHdpTopicFormatter.format_topicsh   * c**ZZkZZZZZCC))bbVabbbbbCo r)NNNN)r r )r r FT)NNr) rErFrGrHr STYLE_PRETTYrArrr5rr,r-rIrrrrscc#) \<))))V====&++++Z????<3333j\\\$rr)r)!rHloggingrrnumpyr scipy.specialrrgensimrrrgensim.matutilsrr gensim.modelsr r gensim.utilsr getLoggerrErr&rrr7r9TransformationABCBaseTopicModelrKrrIrrrPs&&P &&&&&&&&..........KKKKKKKK--------######  8 $ $  2++++\%%%%%%%%:M M M M M z+Y-EM M M `jjjjjjjjjjr