B \%@sdZddlZddlmZddlmZddlmZm Z m Z ddl m Z dd l mZmZdd lmZd d d dddgZeedZGdddeZdS)z5 Kernel Density Estimation ------------------------- N)gammainc) BaseEstimator) check_arraycheck_random_statecheck_consistent_length) row_norms)BallTreeDTYPE)KDTreegaussiantophatZ epanechnikovZ exponentialZlinearZcosine) ball_treekd_treec @sHeZdZdZdd d Zd d ZdddZddZdddZdddZ d S) KernelDensityaKernel Density Estimation Read more in the :ref:`User Guide `. Parameters ---------- bandwidth : float The bandwidth of the kernel. algorithm : string The tree algorithm to use. Valid options are ['kd_tree'|'ball_tree'|'auto']. Default is 'auto'. kernel : string The kernel to use. Valid kernels are ['gaussian'|'tophat'|'epanechnikov'|'exponential'|'linear'|'cosine'] Default is 'gaussian'. metric : string The distance metric to use. Note that not all metrics are valid with all algorithms. Refer to the documentation of :class:`BallTree` and :class:`KDTree` for a description of available algorithms. Note that the normalization of the density output is correct only for the Euclidean distance metric. Default is 'euclidean'. atol : float The desired absolute tolerance of the result. A larger tolerance will generally lead to faster execution. Default is 0. rtol : float The desired relative tolerance of the result. A larger tolerance will generally lead to faster execution. Default is 1E-8. breadth_first : boolean If true (default), use a breadth-first approach to the problem. Otherwise use a depth-first approach. leaf_size : int Specify the leaf size of the underlying tree. See :class:`BallTree` or :class:`KDTree` for details. Default is 40. metric_params : dict Additional parameters to be passed to the tree for use with the metric. For more information, see the documentation of :class:`BallTree` or :class:`KDTree`. ?autor euclideanrT(Nc Csp||_||_||_||_||_||_||_||_| |_| |j|j|dkrVt d|t krlt d |dS)Nrzbandwidth must be positivezinvalid kernel: '{0}') algorithm bandwidthkernelmetricatolrtol breadth_first leaf_size metric_params_choose_algorithm ValueError VALID_KERNELSformat) selfrrrrrrrrrr$4lib/python3.7/site-packages/sklearn/neighbors/kde.py__init__IszKernelDensity.__init__cCst|dkr4|tjkrdS|tjkr$dStd|n<|tkrb|t|jkr^tdt|||Std|dS)Nrrrzinvalid metric: '{0}'zinvalid metric for {0}: '{1}'zinvalid algorithm: '{0}')r Z valid_metricsr r r" TREE_DICT)r#rrr$r$r%r`s  zKernelDensity._choose_algorithmcCs||j|j}t|dtd}|dk rvt|dtdd}|jdkrXtd|jd|jt ||| dkrvtd |j }|dkri}t ||f|j|j |d ||_|S) a}Fit the Kernel Density model on the data. Parameters ---------- X : array_like, shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. sample_weight : array_like, shape (n_samples,), optional List of sample weights attached to the data X. C)orderdtypeNF)r)r*Z ensure_2dr z6the shape of sample_weight must be ({0},), but was {1}rz'sample_weight must have positive values)rr sample_weight)rrrrr ndimr r"shaperminrr'rtree_)r#Xyr+rkwargsr$r$r%fitts(      zKernelDensity.fitc Cspt|dtd}|jjdkr*|jjjd}n|jj}|j|}|jj||j |j ||j |j dd}|t |8}|S)aEvaluate the density model on the data. Parameters ---------- X : array_like, shape (n_samples, n_features) An array of points to query. Last dimension should match dimension of training data (n_features). Returns ------- density : ndarray, shape (n_samples,) The array of log(density) evaluations. These are normalized to be probability densities, so values will be low for high-dimensional data. r()r)r*NrT)hrrrrZ return_log)rr r/r+datar- sum_weightrZkernel_densityrrrrnplog)r#r0NZatol_NZ log_densityr$r$r% score_sampless   zKernelDensity.score_samplescCst||S)aCompute the total log probability density under the model. Parameters ---------- X : array_like, shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. Returns ------- logprob : float Total log-likelihood of the data in X. This is normalized to be a probability density, so the value will be low for high-dimensional data. )r7sumr:)r#r0r1r$r$r%scoreszKernelDensity.scorer c Cs&|jdkrtt|jj}t|}|jdd|d}|jjdkrZ||j d tj }n,t t|jj}|d}t |||}|jdkrt||||jS|jdkr"|j d} |j|| fd} t| d d } td | d | d | |jt| } ||| | ddtjfSdS) aGenerate random samples from the model. Currently, this is implemented only for gaussian and tophat kernels. Parameters ---------- n_samples : int, optional Number of samples to generate. Defaults to 1. random_state : int, RandomState instance or None. default to None If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. Returns ------- X : array_like, shape (n_samples, n_features) List of samples. )r rrr )sizeNr rT)Zsquaredg?g?)rNotImplementedErrorr7Zasarrayr/r5rZuniformr+r-ZastypeZint64ZcumsumZ searchsortedZ atleast_2dZnormalrrrZsqrtZnewaxis) r#Z n_samplesZ random_stater5rnguiZ cumsum_weightr6Zdimr0Zs_sqZ correctionr$r$r%samples$      *zKernelDensity.sample) rrr rrrTrN)NN)N)r N) __name__ __module__ __qualname____doc__r&rr3r:r<rCr$r$r$r%rs/  " r)rGZnumpyr7Z scipy.specialrbaserZutilsrrrZ utils.extmathrrr r rr r!r'rr$r$r$r%s