ó ‡ˆ\c@s¥dZddlZddlmZmZddlZddlmZddl m Z m Z ddl m Z ddl mZdd l mZdd lmZmZmZdd lmZdd lmZdd lmZddlmZddlmZddddgZdejee e ƒfd„ƒYZ de fd„ƒYZ!dZ"de fd„ƒYZ#de#fd„ƒYZ$de#fd„ƒYZ%de#fd„ƒYZ&dS(sÇ The :mod:`sklearn.naive_bayes` module implements Naive Bayes algorithms. These are supervised learning methods based on applying Bayes' theorem with strong (naive) feature independence assumptions. iÿÿÿÿN(tABCMetatabstractmethod(tissparsei(t BaseEstimatortClassifierMixin(tbinarize(tLabelBinarizer(tlabel_binarize(t check_X_yt check_arraytcheck_consistent_length(tsafe_sparse_dot(t logsumexp(t_check_partial_fit_first_call(tcheck_is_fitted(tsixt BernoulliNBt GaussianNBt MultinomialNBt ComplementNBtBaseNBcBs8eZdZed„ƒZd„Zd„Zd„ZRS(s.Abstract base class for naive Bayes estimatorscCsdS(s(Compute the unnormalized posterior log probability of X I.e. ``log P(c) + log P(x|c)`` for all rows x of X, as an array-like of shape [n_classes, n_samples]. Input is passed to _joint_log_likelihood as-is by predict, predict_proba and predict_log_proba. N((tselftX((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyt_joint_log_likelihood*scCs)|j|ƒ}|jtj|ddƒS(s Perform classification on an array of test vectors X. Parameters ---------- X : array-like, shape = [n_samples, n_features] Returns ------- C : array, shape = [n_samples] Predicted target values for X taxisi(Rtclasses_tnptargmax(RRtjll((s2lib/python2.7/site-packages/sklearn/naive_bayes.pytpredict5s cCs5|j|ƒ}t|ddƒ}|tj|ƒjS(sÏ Return log-probability estimates for the test vector X. Parameters ---------- X : array-like, shape = [n_samples, n_features] Returns ------- C : array-like, shape = [n_samples, n_classes] Returns the log-probability of the samples for each class in the model. The columns correspond to the classes in sorted order, as they appear in the attribute `classes_`. Ri(RR Rt atleast_2dtT(RRRt log_prob_x((s2lib/python2.7/site-packages/sklearn/naive_bayes.pytpredict_log_probaEscCstj|j|ƒƒS(sÇ Return probability estimates for the test vector X. Parameters ---------- X : array-like, shape = [n_samples, n_features] Returns ------- C : array-like, shape = [n_samples, n_classes] Returns the probability of the samples for each class in the model. The columns correspond to the classes in sorted order, as they appear in the attribute `classes_`. (RtexpR!(RR((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyt predict_probaYs(t__name__t __module__t__doc__RRRR!R#(((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR's   cBseeZdZddd„Zdd„Zedd„ƒZddd„Zde dd„Z d„Z RS( s Gaussian Naive Bayes (GaussianNB) Can perform online updates to model parameters via `partial_fit` method. For details on algorithm used to update feature means and variance online, see Stanford CS tech report STAN-CS-79-773 by Chan, Golub, and LeVeque: http://i.stanford.edu/pub/cstr/reports/cs/tr/79/773/CS-TR-79-773.pdf Read more in the :ref:`User Guide `. Parameters ---------- priors : array-like, shape (n_classes,) Prior probabilities of the classes. If specified the priors are not adjusted according to the data. var_smoothing : float, optional (default=1e-9) Portion of the largest variance of all features that is added to variances for calculation stability. Attributes ---------- class_prior_ : array, shape (n_classes,) probability of each class. class_count_ : array, shape (n_classes,) number of training samples observed in each class. theta_ : array, shape (n_classes, n_features) mean of each feature per class sigma_ : array, shape (n_classes, n_features) variance of each feature per class epsilon_ : float absolute additive value to variances Examples -------- >>> import numpy as np >>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]]) >>> Y = np.array([1, 1, 1, 2, 2, 2]) >>> from sklearn.naive_bayes import GaussianNB >>> clf = GaussianNB() >>> clf.fit(X, Y) GaussianNB(priors=None, var_smoothing=1e-09) >>> print(clf.predict([[-0.8, -1]])) [1] >>> clf_pf = GaussianNB() >>> clf_pf.partial_fit(X, Y, np.unique(Y)) GaussianNB(priors=None, var_smoothing=1e-09) >>> print(clf_pf.predict([[-0.8, -1]])) [1] g•Ö&è .>cCs||_||_dS(N(tpriorst var_smoothing(RR'R(((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyt__init__¤s cCs=t||ƒ\}}|j||tj|ƒdtd|ƒS(s’Fit Gaussian Naive Bayes according to X, y Parameters ---------- X : array-like, shape (n_samples, n_features) Training vectors, where n_samples is the number of samples and n_features is the number of features. y : array-like, shape (n_samples,) Target values. sample_weight : array-like, shape (n_samples,), optional (default=None) Weights applied to individual samples (1. for unweighted). .. versionadded:: 0.17 Gaussian Naive Bayes supports fitting with *sample_weight*. Returns ------- self : object t_refitt sample_weight(Rt _partial_fitRtuniquetTrue(RRtyR+((s2lib/python2.7/site-packages/sklearn/naive_bayes.pytfit¨s!cCsO|jddkr||fS|dk r„t|jƒƒ}tj|ddd||ƒ}tj||dddd||ƒ}n7|jd}tj|ddƒ}tj|ddƒ}|dkrÑ||fSt||ƒ}|||||} ||} ||} | | |t||ƒ||||d} | |} | | fS(sCompute online update of Gaussian mean and variance. Given starting sample count, mean, and variance, a new set of points X, and optionally sample weights, return the updated mean and variance. (NB - each dimension (column) in X is treated as independent -- you get variance, not covariance). Can take scalar mean and variance, or vector mean and variance to simultaneously update a number of independent Gaussians. See Stanford CS tech report STAN-CS-79-773 by Chan, Golub, and LeVeque: http://i.stanford.edu/pub/cstr/reports/cs/tr/79/773/CS-TR-79-773.pdf Parameters ---------- n_past : int Number of samples represented in old mean and variance. If sample weights were given, this should contain the sum of sample weights represented in old mean and variance. mu : array-like, shape (number of Gaussians,) Means for Gaussians in original set. var : array-like, shape (number of Gaussians,) Variances for Gaussians in original set. sample_weight : array-like, shape (n_samples,), optional (default=None) Weights applied to individual samples (1. for unweighted). Returns ------- total_mu : array-like, shape (number of Gaussians,) Updated mean for each Gaussian over the combined set. total_var : array-like, shape (number of Gaussians,) Updated variance for each Gaussian over the combined set. iRtweightsiN(tshapetNonetfloattsumRtaveragetvartmean(tn_pasttmuR7RR+tn_newtnew_mutnew_vartn_totalttotal_mutold_ssdtnew_ssdt total_ssdt total_var((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyt_update_mean_varianceÂs*(        cCs|j|||dtd|ƒS(s\Incremental fit on a batch of samples. This method is expected to be called several times consecutively on different chunks of a dataset so as to implement out-of-core or online learning. This is especially useful when the whole dataset is too big to fit in memory at once. This method has some performance and numerical stability overhead, hence it is better to call partial_fit on chunks of data that are as large as possible (as long as fitting in the memory budget) to hide the overhead. Parameters ---------- X : array-like, shape (n_samples, n_features) Training vectors, where n_samples is the number of samples and n_features is the number of features. y : array-like, shape (n_samples,) Target values. classes : array-like, shape (n_classes,), optional (default=None) List of all the classes that can possibly appear in the y vector. Must be provided at the first call to partial_fit, can be omitted in subsequent calls. sample_weight : array-like, shape (n_samples,), optional (default=None) Weights applied to individual samples (1. for unweighted). .. versionadded:: 0.17 Returns ------- self : object R*R+(R,tFalse(RRR/tclassesR+((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyt partial_fit s'cCsÝt||ƒ\}}|d k rCt|dtƒ}t||ƒn|jtj|ddƒjƒ|_ |rzd |_ nt ||ƒr­|j d}t |j ƒ}tj||fƒ|_tj||fƒ|_tj|dtjƒ|_|jd k r†tj|jƒ}t |ƒ|kr2tdƒ‚ntj|jƒdƒsYtdƒ‚n|dkjƒrztd ƒ‚n||_q"tjt |j ƒdtjƒ|_nu|j d|jj dkrúd } t| |j d|jj dfƒ‚n|jd d …d d …fc|j 8<|j }tj|ƒ} tj| |ƒ} tj| ƒsytd | | |fƒ‚nx | D]} |j| ƒ} ||| kd d …f}|d k rÜ||| k}|jƒ}nd }|j d}|j|j| |j| d d …f|j| d d …f||ƒ\}}||j| d d …f<||j| d d …f<|j| c|7 0.isAalpha should be a scalar or a numpy array with shape [n_features]sCalpha too small will result in numeric errors, setting alpha = %.1e( RtmintalphaRSt isinstancetndarrayR2tfeature_count_t _ALPHA_MINtwarningstwarntmaximum(R((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyt _check_alphaÖs  cCst|dddtjƒ}|j\}}t||ƒrœt|ƒdkrWt|ƒnd}tj|dtjƒ|_tj||fdtjƒ|_n?||j jdkrÛd}t |||j jdfƒ‚nt |d|j ƒ} | jddkr%tj d| | fd dƒ} n| j\} } |jd | jd kr{d }t ||jd |jd fƒ‚n| jtjƒ} |d k r¾tj|ƒ}| t|ƒj9} n|j} |j|| ƒ|jƒ} |j| ƒ|jd | ƒ|S(sIncremental fit on a batch of samples. This method is expected to be called several times consecutively on different chunks of a dataset so as to implement out-of-core or online learning. This is especially useful when the whole dataset is too big to fit in memory at once. This method has some performance overhead hence it is better to call partial_fit on chunks of data that are as large as possible (as long as fitting in the memory budget) to hide the overhead. Parameters ---------- X : {array-like, sparse matrix}, shape = [n_samples, n_features] Training vectors, where n_samples is the number of samples and n_features is the number of features. y : array-like, shape = [n_samples] Target values. classes : array-like, shape = [n_classes] (default=None) List of all the classes that can possibly appear in the y vector. Must be provided at the first call to partial_fit, can be omitted in subsequent calls. sample_weight : array-like, shape = [n_samples] (default=None) Weights applied to individual samples (1. for unweighted). Returns ------- self : object t accept_sparsetcsrRIiis6Number of features %d does not match previous data %d.iÿÿÿÿRFRis1X.shape[0]=%d and y.shape[0]=%d are incompatible.RtN(R RRPR2R RLRMRQRztcoef_RSRRt concatenatetastypeR3RRRtt_countRt_update_feature_log_probRu(RRR/RFR+t_RZtn_effective_classesR\tYt n_samplesR[RtRw((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyRGäs6$$#"'    c CsRt||dƒ\}}|j\}}tƒ}|j|ƒ}|j|_|jddkr€tjd||fddƒ}n|jtjƒ}|dk rÃtj |ƒ}|t |ƒj 9}n|j }|jd} tj| dtjƒ|_tj| |fdtjƒ|_|j||ƒ|jƒ} |j| ƒ|jd|ƒ|S(s1Fit Naive Bayes classifier according to X, y Parameters ---------- X : {array-like, sparse matrix}, shape = [n_samples, n_features] Training vectors, where n_samples is the number of samples and n_features is the number of features. y : array-like, shape = [n_samples] Target values. sample_weight : array-like, shape = [n_samples], (default=None) Weights applied to individual samples (1. for unweighted). Returns ------- self : object RiRRIRtN(RR2Rt fit_transformRRRƒR„RPR3RR RRtRMRQRzR…RR†Ru( RRR/R+R‡RZtlabelbinR‰RtRˆRw((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR06s*  "     cCs't|jƒdkr |jdS|jS(Nii(RLRtfeature_log_prob_(R((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyt _get_coefjscCs't|jƒdkr |jdS|jS(Nii(RLRRq(R((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyt_get_interceptnsN( R$R%R&R3RuRRGR0RŽRtpropertyR‚t intercept_(((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyRp¿s  R 4   cBs;eZdZdedd„Zd„Zd„Zd„ZRS(s´ Naive Bayes classifier for multinomial models The multinomial Naive Bayes classifier is suitable for classification with discrete features (e.g., word counts for text classification). The multinomial distribution normally requires integer feature counts. However, in practice, fractional counts such as tf-idf may also work. Read more in the :ref:`User Guide `. Parameters ---------- alpha : float, optional (default=1.0) Additive (Laplace/Lidstone) smoothing parameter (0 for no smoothing). fit_prior : boolean, optional (default=True) Whether to learn class prior probabilities or not. If false, a uniform prior will be used. class_prior : array-like, size (n_classes,), optional (default=None) Prior probabilities of the classes. If specified the priors are not adjusted according to the data. Attributes ---------- class_log_prior_ : array, shape (n_classes, ) Smoothed empirical log probability for each class. intercept_ : array, shape (n_classes, ) Mirrors ``class_log_prior_`` for interpreting MultinomialNB as a linear model. feature_log_prob_ : array, shape (n_classes, n_features) Empirical log probability of features given a class, ``P(x_i|y)``. coef_ : array, shape (n_classes, n_features) Mirrors ``feature_log_prob_`` for interpreting MultinomialNB as a linear model. class_count_ : array, shape (n_classes,) Number of samples encountered for each class during fitting. This value is weighted by the sample weight when provided. feature_count_ : array, shape (n_classes, n_features) Number of samples encountered for each (class, feature) during fitting. This value is weighted by the sample weight when provided. Examples -------- >>> import numpy as np >>> X = np.random.randint(5, size=(6, 100)) >>> y = np.array([1, 2, 3, 4, 5, 6]) >>> from sklearn.naive_bayes import MultinomialNB >>> clf = MultinomialNB() >>> clf.fit(X, y) MultinomialNB(alpha=1.0, class_prior=None, fit_prior=True) >>> print(clf.predict(X[2:3])) [3] Notes ----- For the rationale behind the names `coef_` and `intercept_`, i.e. naive Bayes as a linear classifier, see J. Rennie et al. (2003), Tackling the poor assumptions of naive Bayes text classifiers, ICML. References ---------- C.D. Manning, P. Raghavan and H. Schuetze (2008). Introduction to Information Retrieval. Cambridge University Press, pp. 234-265. http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html gð?cCs||_||_||_dS(N(RwRrRt(RRwRrRt((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR)Âs  cCsstjt|ƒr|jn|dkƒr9tdƒ‚n|jt|j|ƒ7_|j|j ddƒ7_dS(s%Count and smooth feature occurrences.isInput X must be non-negativeRN( RRURtdataRSRzR RRQR5(RRR‰((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR…Çs*cCsN|j|}|jddƒ}tj|ƒtj|jddƒƒ|_dS(s=Apply smoothing to raw counts and recompute log probabilitiesRiiÿÿÿÿN(RzR5RRhtreshapeR(RRwt smoothed_fct smoothed_cc((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR†Îs  cCs9t|dƒt|ddƒ}t||jjƒ|jS(s8Calculate the posterior log probability of the samples XRR€R(RR R RRRq(RR((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyRÖs N( R$R%R&R.R3R)R…R†R(((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyRvs J  cBs>eZdZdeded„Zd„Zd„Zd„Z RS(s The Complement Naive Bayes classifier described in Rennie et al. (2003). The Complement Naive Bayes classifier was designed to correct the "severe assumptions" made by the standard Multinomial Naive Bayes classifier. It is particularly suited for imbalanced data sets. Read more in the :ref:`User Guide `. Parameters ---------- alpha : float, optional (default=1.0) Additive (Laplace/Lidstone) smoothing parameter (0 for no smoothing). fit_prior : boolean, optional (default=True) Only used in edge case with a single class in the training set. class_prior : array-like, size (n_classes,), optional (default=None) Prior probabilities of the classes. Not used. norm : boolean, optional (default=False) Whether or not a second normalization of the weights is performed. The default behavior mirrors the implementations found in Mahout and Weka, which do not follow the full algorithm described in Table 9 of the paper. Attributes ---------- class_log_prior_ : array, shape (n_classes, ) Smoothed empirical log probability for each class. Only used in edge case with a single class in the training set. feature_log_prob_ : array, shape (n_classes, n_features) Empirical weights for class complements. class_count_ : array, shape (n_classes,) Number of samples encountered for each class during fitting. This value is weighted by the sample weight when provided. feature_count_ : array, shape (n_classes, n_features) Number of samples encountered for each (class, feature) during fitting. This value is weighted by the sample weight when provided. feature_all_ : array, shape (n_features,) Number of samples encountered for each feature during fitting. This value is weighted by the sample weight when provided. Examples -------- >>> import numpy as np >>> X = np.random.randint(5, size=(6, 100)) >>> y = np.array([1, 2, 3, 4, 5, 6]) >>> from sklearn.naive_bayes import ComplementNB >>> clf = ComplementNB() >>> clf.fit(X, y) ComplementNB(alpha=1.0, class_prior=None, fit_prior=True, norm=False) >>> print(clf.predict(X[2:3])) [3] References ---------- Rennie, J. D., Shih, L., Teevan, J., & Karger, D. R. (2003). Tackling the poor assumptions of naive bayes text classifiers. In ICML (Vol. 3, pp. 616-623). https://people.csail.mit.edu/jrennie/papers/icml03-nb.pdf gð?cCs(||_||_||_||_dS(N(RwRrRttnorm(RRwRrRtR–((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR)"s   cCs‹tjt|ƒr|jn|dkƒr9tdƒ‚n|jt|j|ƒ7_|j|j ddƒ7_|jj ddƒ|_ dS(sCount feature occurrences.isInput X must be non-negativeRN( RRURR’RSRzR RRQR5t feature_all_(RRR‰((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR…)s *cCs||j||j}tj||jdddtƒƒ}| }|jro|jdddtƒ}| |}n||_dS(s6Apply smoothing to raw counts and compute the weights.RitkeepdimsN(R—RzRRhR5R.R–R(RRwt comp_counttloggedtfeature_log_probtsummed((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR†1s% cCs]t|dƒt|ddƒ}t||jjƒ}t|jƒdkrY||j7}n|S(s0Calculate the class scores for the samples in X.RR€Ri(RR R RRRLRRq(RRR((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR<s  N( R$R%R&R.R3RER)R…R†R(((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyRßs A    cBs>eZdZddedd„Zd„Zd„Zd„ZRS(sj Naive Bayes classifier for multivariate Bernoulli models. Like MultinomialNB, this classifier is suitable for discrete data. The difference is that while MultinomialNB works with occurrence counts, BernoulliNB is designed for binary/boolean features. Read more in the :ref:`User Guide `. Parameters ---------- alpha : float, optional (default=1.0) Additive (Laplace/Lidstone) smoothing parameter (0 for no smoothing). binarize : float or None, optional (default=0.0) Threshold for binarizing (mapping to booleans) of sample features. If None, input is presumed to already consist of binary vectors. fit_prior : boolean, optional (default=True) Whether to learn class prior probabilities or not. If false, a uniform prior will be used. class_prior : array-like, size=[n_classes,], optional (default=None) Prior probabilities of the classes. If specified the priors are not adjusted according to the data. Attributes ---------- class_log_prior_ : array, shape = [n_classes] Log probability of each class (smoothed). feature_log_prob_ : array, shape = [n_classes, n_features] Empirical log probability of features given a class, P(x_i|y). class_count_ : array, shape = [n_classes] Number of samples encountered for each class during fitting. This value is weighted by the sample weight when provided. feature_count_ : array, shape = [n_classes, n_features] Number of samples encountered for each (class, feature) during fitting. This value is weighted by the sample weight when provided. Examples -------- >>> import numpy as np >>> X = np.random.randint(2, size=(6, 100)) >>> Y = np.array([1, 2, 3, 4, 4, 5]) >>> from sklearn.naive_bayes import BernoulliNB >>> clf = BernoulliNB() >>> clf.fit(X, Y) BernoulliNB(alpha=1.0, binarize=0.0, class_prior=None, fit_prior=True) >>> print(clf.predict(X[2:3])) [3] References ---------- C.D. Manning, P. Raghavan and H. Schuetze (2008). Introduction to Information Retrieval. Cambridge University Press, pp. 234-265. http://nlp.stanford.edu/IR-book/html/htmledition/the-bernoulli-model-1.html A. McCallum and K. Nigam (1998). A comparison of event models for naive Bayes text classification. Proc. AAAI/ICML-98 Workshop on Learning for Text Categorization, pp. 41-48. V. Metsis, I. Androutsopoulos and G. Paliouras (2006). Spam filtering with naive Bayes -- Which naive Bayes? 3rd Conf. on Email and Anti-Spam (CEAS). gð?gcCs(||_||_||_||_dS(N(RwRRrRt(RRwRRrRt((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR)Žs   cCsa|jdk r't|d|jƒ}n|jt|j|ƒ7_|j|jddƒ7_dS(s%Count and smooth feature occurrences.t thresholdRiN(RR3RzR RRQR5(RRR‰((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR…•scCsM|j|}|j|d}tj|ƒtj|jddƒƒ|_dS(s=Apply smoothing to raw counts and recompute log probabilitiesiiÿÿÿÿiN(RzRQRRhR“R(RRwR”R•((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR†œs  cCsåt|dƒt|ddƒ}|jdk rFt|d|jƒ}n|jj\}}|j\}}||krŒtd||fƒ‚ntjdtj |jƒƒ}t ||j|j ƒ}||j |j ddƒ7}|S( s8Calculate the posterior log probability of the samples XRR€RRs/Expected input with %d features, got %d insteadiRN(RR RR3RR2RSRRhR"R RRqR5(RRR[RZRŠt n_features_Xtneg_probR((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyR¤s  N( R$R%R&R.R3R)R…R†R(((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyRGs E    ('R&R|tabcRRtnumpyRt scipy.sparseRtbaseRRt preprocessingRRRtutilsRR R t utils.extmathR t utils.fixesR tutils.multiclassR tutils.validationRt externalsRt__all__twith_metaclassRRR{RpRRR(((s2lib/python2.7/site-packages/sklearn/naive_bayes.pyts.  %DÿR·ih