o tBh*@sdZddlZddlmZddlmZddlmZddl m Z m Z ddl m Z d d lmZmZd d lmZgd Zeed ZGdddeZdS)z5 Kernel Density Estimation ------------------------- N)gammainc) BaseEstimator)check_random_state)_check_sample_weightcheck_is_fitted) row_norms)BallTreeDTYPE)KDTree)gaussiantophat epanechnikov exponentiallinearcosine) ball_treekd_treec @sdeZdZdZddddddddd d d d Zd dZdddZddZdddZdddZ ddZ d S) KernelDensitya Kernel Density Estimation. Read more in the :ref:`User Guide `. Parameters ---------- bandwidth : float, default=1.0 The bandwidth of the kernel. algorithm : {'kd_tree', 'ball_tree', 'auto'}, default='auto' The tree algorithm to use. kernel : {'gaussian', 'tophat', 'epanechnikov', 'exponential', 'linear', 'cosine'}, default='gaussian' The kernel to use. metric : str, default='euclidean' 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, default=0 The desired absolute tolerance of the result. A larger tolerance will generally lead to faster execution. rtol : float, default=0 The desired relative tolerance of the result. A larger tolerance will generally lead to faster execution. breadth_first : bool, default=True If true (default), use a breadth-first approach to the problem. Otherwise use a depth-first approach. leaf_size : int, default=40 Specify the leaf size of the underlying tree. See :class:`BallTree` or :class:`KDTree` for details. metric_params : dict, default=None 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`. Attributes ---------- n_features_in_ : int Number of features seen during :term:`fit`. .. versionadded:: 0.24 tree_ : ``BinaryTree`` instance The tree algorithm for fast generalized N-point problems. feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of features seen during :term:`fit`. Defined only when `X` has feature names that are all strings. .. versionadded:: 1.0 See Also -------- sklearn.neighbors.KDTree : K-dimensional tree for fast generalized N-point problems. sklearn.neighbors.BallTree : Ball tree for fast generalized N-point problems. Examples -------- Compute a gaussian kernel density estimate with a fixed bandwidth. >>> from sklearn.neighbors import KernelDensity >>> import numpy as np >>> rng = np.random.RandomState(42) >>> X = rng.random_sample((100, 3)) >>> kde = KernelDensity(kernel='gaussian', bandwidth=0.5).fit(X) >>> log_density = kde.score_samples(X[:3]) >>> log_density array([-1.52955942, -1.51462041, -1.60244657]) ?autor euclideanrT(N) bandwidth algorithmkernelmetricatolrtol breadth_first leaf_size metric_paramsc Cs:||_||_||_||_||_||_||_||_| |_dSN) rrrrrrr r!r") selfrrrrrrr r!r"r%m/var/www/html/riverr-enterprise-integrations-main/venv/lib/python3.10/site-packages/sklearn/neighbors/_kde.py__init__ss  zKernelDensity.__init__cCsn|dkr|tjvr dS|tjvrdStd||tvr0|t|jvr.tdt|||Std|)Nrrrzinvalid metric: '{0}'zinvalid metric for {0}: '{1}'zinvalid algorithm: '{0}')r valid_metricsr ValueErrorformat TREE_DICT)r$rrr%r%r&_choose_algorithms  zKernelDensity._choose_algorithmcCs||j|j}|jdkrtd|jtvrtd|j|j|dt d}|dur2t ||t dd}|j }|dur;i}t ||f|j|j |d ||_|S) aFit the Kernel Density model on the data. Parameters ---------- X : array-like of shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. y : None Ignored. This parameter exists only for compatibility with :class:`~sklearn.pipeline.Pipeline`. sample_weight : array-like of shape (n_samples,), default=None List of sample weights attached to the data X. .. versionadded:: 0.20 Returns ------- self : object Returns the instance itself. rzbandwidth must be positivezinvalid kernel: '{0}'C)orderdtypeNT)only_non_negative)rr! sample_weight)r,rrrr)r VALID_KERNELSr*_validate_datar rr"r+r!tree_)r$Xyr1rkwargsr%r%r&fits.  zKernelDensity.fitc Cs|t||j|dtdd}|jjdur|jjjd}n|jj}|j|}|jj ||j |j ||j |j dd}|t|8}|S)aCompute the log-likelihood of each sample under the model. Parameters ---------- X : array-like of shape (n_samples, n_features) An array of points to query. Last dimension should match dimension of training data (n_features). Returns ------- density : ndarray of shape (n_samples,) Log-likelihood of each sample in `X`. These are normalized to be probability densities, so values will be low for high-dimensional data. r-F)r.r/resetNrT)hrrrr return_log)rr3r r4r1datashape sum_weightrkernel_densityrrrr nplog)r$r5Natol_N log_densityr%r%r& score_sampless"   zKernelDensity.score_samplescCst||S)a}Compute the total log-likelihood under the model. Parameters ---------- X : array-like of shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. y : None Ignored. This parameter exists only for compatibility with :class:`~sklearn.pipeline.Pipeline`. Returns ------- logprob : float Total log-likelihood of the data in X. This is normalized to be a probability density, so the value will be low for high-dimensional data. )r@sumrE)r$r5r6r%r%r&scoreszKernelDensity.scorer c Cs,t||jdvr tt|jj}t|}|jdd|d}|jj dur1||j d tj }nt t|jj }|d}t|||}|jdkrXt||||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, default=1 Number of samples to generate. random_state : int, RandomState instance or None, default=None Determines random number generation used to generate random samples. Pass an int for reproducible results across multiple function calls. See :term:`Glossary `. Returns ------- X : array-like of shape (n_samples, n_features) List of samples. )r rrr )sizeNr rT)squaredg?r)rrNotImplementedErrorr@asarrayr4r<runiformr1r=astypeint64cumsum searchsorted atleast_2dnormalrrrsqrtnewaxis) r$ n_samples random_stater<rngui cumsum_weightr>dimr5s_sq correctionr%r%r&sample s2      zKernelDensity.samplecCs dddiiS)N _xfail_checkscheck_sample_weights_invariancez'sample_weight must have positive valuesr%)r$r%r%r& _more_tagsAs zKernelDensity._more_tags)NNr#)r N) __name__ __module__ __qualname____doc__r'r,r8rErGr_rbr%r%r%r&r s$U  2 &  5r)rfnumpyr@ scipy.specialrbaserutilsrutils.validationrr utils.extmathr _ball_treer r _kd_treer r2r+rr%r%r%r&s