U oeZ@s@dZddlZddlmZedez ddlZWn*ek rZddlmZeddYnXej Z ddZ ej d Z ee ZGd d d Zd d ZddZddZd5ddZdZd6ddZddZddZddZd7ddZdd Zd8d!d"Zd#d$Zd%d&Zd'd(Zd)d*Z d+d,Z!d-d.Z"d/d0Z#d1d2Z$d3d4Z%dS)9aA state-emitting MarkovModel. Note terminology similar to Manning and Schutze is used. Functions: train_bw Train a markov model using the Baum-Welch algorithm. train_visible Train a visible markov model using MLE. find_states Find the a state sequence that explains some observations. load Load a MarkovModel. save Save a MarkovModel. Classes: MarkovModel Holds the description of a markov model N)BiopythonDeprecationWarningzThe 'Bio.MarkovModel' module is deprecated and will be removed in a future release of Biopython. Consider using the hmmlearn package instead.)MissingPythonDependencyErrorzRPlease install NumPy if you want to use Bio.MarkovModel. See http://www.numpy.org/cCs@i}t|ddd}t|d}|D]\}}||||<q&|S)zAReturn a dictionary of values with their sequence offset as keys.N) enumeratelen)valuesdentriesnindexkeyr.lib/python3.8/site-packages/Bio/MarkovModel.py itemindex0s   rgYnc@s"eZdZdZdddZddZdS) MarkovModelz+Create a state-emitting MarkovModel object.NcCs"||_||_||_||_||_dS)zInitialize the class.N)statesalphabet p_initial p_transition p_emission)selfrrrrrrrr__init__Cs zMarkovModel.__init__cCs.ddlm}|}t|||d|S)z9Create a string representation of the MarkovModel object.r)StringIO)iorsaveseekread)rrhandlerrr__str__Ms    zMarkovModel.__str__)NNN)__name__ __module__ __qualname____doc__rrrrrrr@s  rcCs*|}||s&td|d||S)zNRead the first line and evaluate that begisn with the correct start (PRIVATE).z I expected z but got )readline startswith ValueError)rstartlinerrr_readline_and_check_startWs r)cCs~t|d}|dd}t|d}|dd}t||}t|t|}}t||_t|d}tt|D]0}t|d||d}t|d|j|<qrt||f|_ t|d }tt|D]B}t|d||d}d d |ddD|j |ddf<qt||f|_ t|d }tt|D]D}t|d||d}d d |ddD|j |ddf<q4|S)z.Parse a file handle into a MarkovModel object.zSTATES:rNz ALPHABET:zINITIAL: :rz TRANSITION:cSsg|] }t|qSrfloat.0vrrr xszload..z EMISSION:cSsg|] }t|qSrr,r.rrrr1s) r)splitrrnpzerosrranger-rr)rr(rrmmNMirrrload_s,      * ,r:c Cs|j}|dd|jd|dd|jd|dtt|jD](}|d|j|d|j|ddqL|d tt|jD]6}|d|j|ddd d |j|Ddq|d tt|jD]6}|d|j|ddd d |j|DdqdS)z$Save MarkovModel object into handle.zSTATES:   z ALPHABET: z INITIAL: r*z: gz TRANSITION: css|]}t|VqdSNstrr/xrrr szsave..z EMISSION: css|]}t|VqdSr>r?rArrrrCsN) writejoinrrr5rrrr)r6rwr9rrrrs&4rc st|t|}}|std|dk rDt|}|j|fkrDtd|dk rlt|}|j||fkrltd|dk rt|}|j||fkrtdg} t||D]} | fdd| Dqdd| D} t| d krtd t||| ||||d } | \} }}t ||| ||S) a Train a MarkovModel using the Baum-Welch algorithm. Train a MarkovModel using the Baum-Welch algorithm. states is a list of strings that describe the names of each state. alphabet is a list of objects that indicate the allowed outputs. training_data is a list of observations. Each observation is a list of objects from the alphabet. pseudo_initial, pseudo_transition, and pseudo_emission are optional parameters that you can use to assign pseudo-counts to different matrices. They should be matrices of the appropriate size that contain numbers to add to each parameter matrix, before normalization. update_fn is an optional callback that takes parameters (iteration, log_likelihood). It is called once per iteration. zNo training data given.N$pseudo_initial not shape len(states)5pseudo_transition not shape len(states) X len(states)5pseudo_emission not shape len(states) X len(alphabet)csg|] }|qSrrrAindexesrrr1sztrain_bw..cSsg|] }t|qSr)rrArrrr1srz,I got training data with outputs of length 0)pseudo_initialpseudo_transitionpseudo_emission update_fn) rr&r3asarrayshaperappendmin _baum_welchr)rr training_datarLrMrNrOr7r8training_outputsoutputsZlengthsrBrrrrrJrtrain_bwsB      rXic  Csd|dkrt|}n t||f}|dkr4t||f}nt|||f}|dkrXt||f}nt|||f}t|} t|} t|} |dk rt|} nd} |dk rt|}nd}|dk rt|}nd}d}ttD]j}t}|D] }|t|||| | | | || 7}q| dk r| |||dk r>t||dkr>qP|}qt dtdd| | | fDS)zfImplement the Baum-Welch algorithm to evaluate unknown parameters in the MarkovModel object (PRIVATE).Ng?z%HMM did not converge in %d iterationscSsg|]}t|qSr)r3exp)r/_rrrr1%sz_baum_welch..) _random_norm_copy_and_checkr3logr5MAX_ITERATIONSLOG0_baum_welch_onefabs RuntimeError)r7r8rVrrrrLrMrNrO lp_initial lp_transition lp_emissionlpseudo_initiallpseudo_transitionlpseudo_emissionZ prev_llikr9ZllikrWrrrrTsV             rTc  Cst|} t|| ||||} t|| |||} t||| f} t| D]} || }t||f}t|D]R}t|D]D}| || ||||||| || d}||||<qpqd|t|| dddd| f<qBt|| f}t| D]0} t|D]"}t| |dd| f||| <qqt|}t|D]}t||ddf||<q2|dddf}|dk rt||}|t|}t|D]p}t|D],}t| ||ddf|||||<q|dk rt|||||<||t||||<qt|D]}t|t}t| D]:} || }t|D]"}t ||| ||| f||<q2q|t|}|dk rt|||}|t|}|||ddf<qt| dd| fS)zExecute one step for Baum-Welch algorithm (PRIVATE). Do one iteration of Baum-Welch based on a sequence of output. Changes the value for lp_initial, lp_transition and lp_emission in place. rNr) r_forward _backwardr3r4r5_logsum _logvecaddr_ logaddexp)r7r8rWrcrdrerfrgrhTZfmatZbmatZlp_arctkZ lp_traverser9jlpZ lp_arcout_tZ lp_arcoutZksumrrrr`(s`         "       *    $    r`c Cst||df}||dddf<td|dD]n}||d}t|D]T} t} t|D]6} || |d|| | || |} t| | } qX| || |<qHq0|S)zImplement forward algorithm (PRIVATE). Calculate a Nx(T+1) matrix, where the last column is the total probability of the output. rNrr3r4r5r_rm) r7rnrcrdrerWmatrixrorprqlprobr9rrrrrris   ( ric Cst||df}t|dddD]j}||}t|D]T}t} t|D]6} || |d||| |||} t| | } qF| |||<q6q"|S)z'Implement backward algorithm (PRIVATE).rrrs) r7rnrdrerWrtrorpr9rurqrrrrrrjs  ( rjcs&t|t|}}|dk r8t|}|j|fkr8td|dk r`t|}|j||fkr`td|dk rt|}|j||fkrtdgg}} t|t||D]P\} } t| t| krtd|fdd| D| fdd| Dqt||| ||||} | \} }}t||| ||S) a Train a visible MarkovModel using maximum likelihoood estimates for each of the parameters. Train a visible MarkovModel using maximum likelihoood estimates for each of the parameters. states is a list of strings that describe the names of each state. alphabet is a list of objects that indicate the allowed outputs. training_data is a list of (outputs, observed states) where outputs is a list of the emission from the alphabet, and observed states is a list of states from states. pseudo_initial, pseudo_transition, and pseudo_emission are optional parameters that you can use to assign pseudo-counts to different matrices. They should be matrices of the appropriate size that contain numbers to add to each parameter matrix. NrGrHrIzstates and outputs not alignedcsg|] }|qSrrrA)states_indexesrrr1sz!train_visible..csg|] }|qSrrrA)outputs_indexesrrr1s) rr3rPrQr&rrR_mler)rrrUrLrMrNr7r8training_statesrVZtoutputsZtstatesrBrrrr)rwrvr train_visibles@       rzcCst|}|r||}|D]}||dd7<qt|}t||f} |rV| |} |D]D}tt|dD].} || || d} } | | | fd7<qnqZtt| D]4} | | ddft| | ddf| | ddf<qt||f} |r| |} t||f} t||D]4\}}t||D]\}}| ||fd7<q&qtt| D]6} | | ddft| | ddf| | ddf<qV|| | fS)z.csg|]}j|qSr)rrA)r6rrr15s) rrr3r]rVERY_SMALL_NUMBERrrrr_viterbir5rY) Z markov_modeloutputr7rcrdreresultsr9rscorer)rKr6r find_statess   "rcCst|}g}t|D]}|dg|qt||f}||dd|df|dddf<td|D]r} || } t|D]\} |dd| df|dd| f|| | f} t| } | | d|| | f<| || | <qzqfg}g}t|dd|df} | D]&}||d|g|||dfq|r|\} }}| dkrT|||fn6||d| } | D] }|| d|g||fqhq&|S)zSImplement Viterbi algorithm to find most likely states for a given input (PRIVATE).Nrr)rr5rRr3r4rpop)r7rcrdrerrnZ backtracer9ZscoresrorprqZi_scoresrKZ in_processrrrrrrr9s4 $ 0$ "rcCszt|jdkr|t|}nZt|jdkrntt|D]4}||ddft||ddf||ddf<q6ntd|S)z"Normalize matrix object (PRIVATE).rNz&I cannot handle matrixes of that shape)rrQr|r5r&)rtr9rrrr{bs4r{cCst|}t|S)z%Normalize a uniform matrix (PRIVATE).)r3r}r{rQrtrrr _uniform_normos rcCstj|}t|S)z$Normalize a random matrix (PRIVATE).)r3randomr{rrrrr[us r[cCstj|dd}|j|kr tdt|jdkrNtt|ddkrtdnPt|jdkrtt|D]*}tt||ddkrhtd|qhntd |S) zFCopy a matrix and check its dimension. Normalize at the end (PRIVATE).r)copyzIncorrect dimensiong?g{Gz?zmatrix not normalized to 1.0rzmatrix %d not normalized to 1.0z&I don't handle matrices > 2 dimensions)r3ZarrayrQr&rrar|r5)rtZ desired_shaper9rrrr\{s  r\cCsFt|jdkr&t|t|jf}n|}t}|D]}t||}q2|S)z/Implement logsum for a matrix object (PRIVATE).r)rrQr3ZreshapeZprodr_rm)rtZvecr|Znumrrrrks rkcCsRt|t|kstdtt|}tt|D]}t||||||<q2|S)z5Implement a log sum for two vector objects (PRIVATE).zvectors aren't the same length)rAssertionErrorr3r4r5rm)Zlogvec1Zlogvec2Zsumvecr9rrrrls rlcCst|}t|S)z-Return the exponential of a logsum (PRIVATE).)rkr3rY)Znumbersr|rrr _exp_logsumsr)NNNN)NNNNNNN)NNN)N)&r#warningsZBiorwarnZnumpyr3 ImportErrorrrmrrZseedrr]r_rr)r:rrXr^rTr`rirjrzrxrrrr{rr[r\rkrlrrrrrsp     % E J^ ?. )