o Rŀg+@sdZddlZddlmZzddlZWney$ddlmZeddwddlm Z e de Gdd d Z d d Z d d Z ddZddZddZddZddZddZddZ     d%d d!Zed"krwdd#lmZedd$dSdS)&z8Maximum Entropy code. Uses Improved Iterative Scaling. N)reduce)MissingPythonDependencyErrorzQPlease install NumPy if you want to use Bio.MaxEntropy. See http://www.numpy.org/)BiopythonDeprecationWarningzThe 'Bio.MaxEntropy' module is deprecated and will be removed in a future release of Biopython. Consider using scikit-learn instead.c@seZdZdZddZdS) MaxEntropyaHold information for a Maximum Entropy classifier. Members: classes List of the possible classes of data. alphas List of the weights for each feature. feature_fns List of the feature functions. Car data from example Naive Bayes Classifier example by Eric Meisner November 22, 2003 http://www.inf.u-szeged.hu/~ormandi/teaching >>> from Bio.MaxEntropy import train, classify >>> xcar = [ ... ['Red', 'Sports', 'Domestic'], ... ['Red', 'Sports', 'Domestic'], ... ['Red', 'Sports', 'Domestic'], ... ['Yellow', 'Sports', 'Domestic'], ... ['Yellow', 'Sports', 'Imported'], ... ['Yellow', 'SUV', 'Imported'], ... ['Yellow', 'SUV', 'Imported'], ... ['Yellow', 'SUV', 'Domestic'], ... ['Red', 'SUV', 'Imported'], ... ['Red', 'Sports', 'Imported']] >>> ycar = ['Yes','No','Yes','No','Yes','No','Yes','No','No','Yes'] Requires some rules or features >>> def udf1(ts, cl): ... return ts[0] != 'Red' ... >>> def udf2(ts, cl): ... return ts[1] != 'Sports' ... >>> def udf3(ts, cl): ... return ts[2] != 'Domestic' ... >>> user_functions = [udf1, udf2, udf3] # must be an iterable type >>> xe = train(xcar, ycar, user_functions) >>> for xv, yv in zip(xcar, ycar): ... xc = classify(xe, xv) ... print('Pred: %s gives %s y is %s' % (xv, xc, yv)) ... Pred: ['Red', 'Sports', 'Domestic'] gives No y is Yes Pred: ['Red', 'Sports', 'Domestic'] gives No y is No Pred: ['Red', 'Sports', 'Domestic'] gives No y is Yes Pred: ['Yellow', 'Sports', 'Domestic'] gives No y is No Pred: ['Yellow', 'Sports', 'Imported'] gives No y is Yes Pred: ['Yellow', 'SUV', 'Imported'] gives No y is No Pred: ['Yellow', 'SUV', 'Imported'] gives No y is Yes Pred: ['Yellow', 'SUV', 'Domestic'] gives No y is No Pred: ['Red', 'SUV', 'Imported'] gives No y is No Pred: ['Red', 'Sports', 'Imported'] gives No y is Yes cCsg|_g|_g|_dS)zInitialize the class.N)classesalphas feature_fns)selfr B/var/www/html/myenv/lib/python3.10/site-packages/Bio/MaxEntropy.py__init__Zs zMaxEntropy.__init__N)__name__ __module__ __qualname____doc__r r r r r r$s 5rcCsdg}t|jt|jksJ|jD]}d}t|j|jD] \}}|||||7}q||q|S)zCalculate the log of the probability for each class. me is a MaxEntropy object that has been trained. observation is a vector representing the observed data. The return value is a list of unnormalized log probabilities for each class. )lenrrrzipappend)me observationscoresklasslprobfnalphar r r calculateas  rcCsVt||}|d|jd}}tdt|D]}|||kr(|||j|}}q|S)z%Classify an observation into a class.r)rrranger)rrr max_scorerir r r classifyrs  r!cCsRi}tt|D]}tt|D]}|||||}|dkr%||||f<qq|S)a>Evaluate a feature function on every instance of the training set and class (PRIVATE). fn is a callback function that takes two parameters: a training instance and a class. Return a dictionary of (training set index, class index) -> non-zero value. Values of 0 are not stored in the dictionary. r)rr)rxsrvaluesr jfr r r _eval_feature_fn|s r&c sit|D]\}}||<qfdd|D}g}t|}|D]} d} t|D]} | | | || fd7} q(|| |q |S)zCalculate the expectation of each function from the data (PRIVATE). This is the constraint for the maximum entropy distribution. Return a list of expectations, parallel to the list of features. csg|]}|qSr r ).0y class2indexr r sz+_calc_empirical_expects..r) enumeraterrgetr) r"ysrfeaturesindexkeyys_iexpectNfeaturesr r r)r _calc_empirical_expectss  r7c Cs`t||||}g}|D]"}d}|D]\\}} } |||| | 7}q||t|q |S)zCalculate the expectation of each feature from the model (PRIVATE). This is not used in maximum entropy training, but provides a good function for debugging. r)_calc_p_class_given_xitemsrr) r"rr/rp_yxexpectsr5sumr r$r%r r r _calc_model_expectssr=c Cstt|t|f}t|t|ksJt||D]\}}|D]\\}}} ||||| 7<q"qt|}tt|D]} t|| } || | || <qA|S)zCalculate conditional probability P(y|x) (PRIVATE). y is the class and x is an instance from the training set. Return a XSxCLASSES matrix of probabilities. )npzerosrrr9exprr<) r"rr/rprob_yxr5rxr(r%r zr r r r8s  r8cCsFt||f}|D]}|D]\\}}}||||7<qq |S)z/Calculate a matrix of f sharp values (PRIVATE).)r>r?r9)r4nclassesr/f_sharpr5r r$r%r r r _calc_f_sharps rFcCsd}d}||kr^d} } |D]'\\} } } || | | t||| | }| |7} | ||| | 7} q|| || |} } | | }||8}t||krV |S|d}||kstd)z,Solve delta using Newton's method (PRIVATE).rrrz Newton's method did not converge)r9r>r@fabs RuntimeError)r4r5rE empiricalrAmax_newton_iterationsnewton_convergedeltaitersf_newton df_newtonr r$r%prodratior r r _iis_solve_deltas"&rRc Csdt||||}t|} |dd} tt|D]} t| || ||| |||} | | | 7<q| S)zBDo one iteration of hill climbing to find better alphas (PRIVATE).N)r8rrrR) r"rr/rEr e_empiricalrJrKr:r4 newalphasr rLr r r _train_iiss  rU'h㈵>d绽|=c sstdtt|krtd|}} tt|fdd|D} ttt| } t|| | } dgt| } d}||krt|| | | | ||}ddt| |D}tt j |d}|} t }| ||_ |_ |_|dury||||kr |S||ksEtd ) aFTrain a maximum entropy classifier, returns MaxEntropy object. Train a maximum entropy classifier on a training set. training_set is a list of observations. results is a list of the class assignments for each observation. feature_fns is a list of the features. These are callback functions that take an observation and class and return a 1 or 0. update_fn is a callback function that is called at each training iteration. It is passed a MaxEntropy object that encapsulates the current state of the training. The maximum number of iterations and the convergence criterion for IIS are given by max_iis_iterations and iis_converge, respectively, while max_newton_iterations and newton_converge are the maximum number of iterations and the convergence criterion for Newton's method. zNo data in the training set.z2training_set and results should be parallel lists.csg|]}t|qSr )r&)r'rr training_setr r r+6sztrain..rrcSsg|] \}}t||qSr )r>rG)r'rBr(r r r r+KsNzIIS did not converge) ValueErrorrsortedsetrFr7rUrrr>addrrrrrH)r[resultsr update_fnmax_iis_iterations iis_convergerJrKr"r.r/rErSrrMnalphasdiffrr rZr trainsD   rf__main__) run_doctest)verbose)NrVrWrXrY)rwarnings functoolsrnumpyr> ImportErrorBiorrwarnrrr!r&r7r=r8rFrRrUrfr Bio._utilsrhr r r r sL     =  $ L