ΑiSSKJr SSKJr SSKJr SSKrSSKJrJ r \(aSSKJ r "SS\ R5r S r S rg) ) annotations)Iterable) TYPE_CHECKINGN) categorical distribution)Tensorc^\rSrSr%SrS\S'S\S'SU4Sjjr\SSj5r\SS j5r SS jr SS jr /4SS jjr SS jr SSjrSrU=r$) Multinomiala Multinomial distribution parameterized by :attr:`total_count` and :attr:`probs`. In probability theory, the multinomial distribution is a generalization of the binomial distribution, it models the probability of counts for each side of a k-sided die rolled n times. When k is 2 and n is 1, the multinomial is the bernoulli distribution, when k is 2 and n is grater than 1, it is the binomial distribution, when k is grater than 2 and n is 1, it is the categorical distribution. The probability mass function (PMF) for multinomial is .. math:: f(x_1, ..., x_k; n, p_1,...,p_k) = \frac{n!}{x_1!...x_k!}p_1^{x_1}...p_k^{x_k} where, :math:`n` is number of trials, k is the number of categories, :math:`p_i` denote probability of a trial falling into each category, :math:`{\textstyle \sum_{i=1}^{k}p_i=1}, p_i \ge 0`, and :math:`x_i` denote count of each category. Args: total_count (int): Number of trials. probs (Tensor): Probability of a trial falling into each category. Last axis of probs indexes over categories, other axes index over batches. Probs value should between [0, 1], and sum to 1 along last axis. If the value over 1, it will be normalized to sum to 1 along the last axis. Examples: .. code-block:: python >>> import paddle >>> paddle.seed(2023) >>> multinomial = paddle.distribution.Multinomial(10, paddle.to_tensor([0.2, 0.3, 0.5])) >>> print(multinomial.sample((2, 3))) Tensor(shape=[2, 3, 3], dtype=float32, place=Place(cpu), stop_gradient=True, [[[1., 5., 4.], [0., 4., 6.], [1., 3., 6.]], [[2., 2., 6.], [0., 6., 4.], [3., 3., 4.]]]) int total_countrprobscn>[U[5(aUS:a [S5eUR5S:a [S5eX"R SSS9- UlXl[R"URU5S9Ul [TU]1URSSURSS5 g)NzBinput parameter total_count must be int type and grater than zero.z9probs parameter should not be none and over one dimensionT)keepdim)logits) isinstancer ValueErrordimsumrr r Categorical_probs_to_logits _categoricalsuper__init__shape)selfr r __class__s _/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/distribution/multinomial.pyrMultinomial.__init__Ms+s++{QT  99;?K YYr4Y88 &'33((/  Sb)5;;rs+;<c4URUR-$)zDmean of multinomial distribution. Returns: Tensor: mean value. )rr rs r meanMultinomial.mean`szzD,,,,r"cTURUR-SUR- -$)zLvariance of multinomial distribution. Returns: Tensor: variance value. r)r rr$s r varianceMultinomial.varianceis&$**,DJJ??r"cL[R"URU55$)probability mass function evaluated at value. Args: value (Tensor): value to be evaluated. Returns: Tensor: probability of value. )paddleexplog_prob)rvalues r probMultinomial.probrszz$--.//r"c[R"U5(a*[R"XRR5n[R "[R "UR5U/5up![R"5(aSX!S:H[R"U5-'O:[RRX!S:H[R"U5-S5n[R"URS5S-5[R"US-5RS5- X-RS5-$)r+rrr) r, is_integercastrdtypebroadcast_tensorslogin_dynamic_modeisinfstaticsetitemlgammar)rr/rs r r.Multinomial.log_prob}s   U # #KKzz'7'78E00 ZZ #U +   ! ! # #<=FQJ6<<#78 9]]**! V(<=qF MM%))B-!+ ,mmEAI&**2. /~""2& ' r"c[U[5(d [S5eURR UR /[ U5Q5n[RRRX RRS5RURR5RS5$)z~draw sample data from multinomial distribution Args: sample_shape (list|tuple, optional): [description]. Defaults to []. z%sample shape must be Iterable object.rr)rr TypeErrorrsampler listr,nn functionalone_hotrrr4r5r)rrsampless r r@Multinomial.samples %**CD D##**D,<,<+KtE{+KL II ( (**2B2B22F G T$**"" # SV r"cR[R"/URURRS9n[R "URS-URRS9R SS[URR5--5SSn[R"URX55nXRR5-[R"US-5- U[R"US-5-RSS/5-$) zHentropy of multinomial distribution Returns: Tensor: entropy value )r fill_valuer5rr5)r)rNrr)r,fullr rr5arangereshapelenrr-_binomial_logpmfrentropyr<r)rnsupport binomial_pmfs r rOMultinomial.entropys KK!1!19I9I --   q  (8(8 '%$TZZ%5%5!666 7<zz$"7"7"CD %%--//&--A2FF FMM'A+6 6 ; ;QG D  r"c URURSS9n[R"US-5n[R"US-5n[R"X- S-5nU[ U5-U[R "[R "[R"U5*55--U- nX#-U- U- U- $)NT) is_binaryr)rrr,r< _clip_by_zerolog1pr-abs)rcountr/rfactor_nfactor_k factor_nmknorms r rNMultinomial._binomial_logpmfs&&tzzT&B==+==+]]5=1#45  M&) )fll6::vzz&/A.A#BCC D  ~(:5<rxs;#$ 9o=,++o=d13r"