U 3d:0@sdZddlZddlmZmZddlZddlmZddl m Z ddl m Z ddl mZdd lmZmZdd lmZmZdd lmZd d lmZmZd dlmZddddddgZeedZGddde ZdS)z5 Kernel Density Estimation ------------------------- N)IntegralReal)gammainc) BaseEstimator VALID_METRICS)check_random_state)_check_sample_weightcheck_is_fitted)Interval StrOptions) row_norms)BallTreeDTYPE)KDTreegaussiantophatZ epanechnikovZ exponentialZlinearZcosine) ball_treekd_treec @s eZdZUdZeeddddeddhgeee dhBgeee geee j d d e Dgeeddd dgeeddd dgd gee d dd dgdegd Zeed<dddddddddd ddZddZd#ddZddZd$ddZd%dd Zd!d"ZdS)& KernelDensitya Kernel Density Estimation. Read more in the :ref:`User Guide `. Parameters ---------- bandwidth : float or {"scott", "silverman"}, default=1.0 The bandwidth of the kernel. If bandwidth is a float, it defines the bandwidth of the kernel. If bandwidth is a string, one of the estimation methods is implemented. 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' Metric to use for distance computation. See the documentation of `scipy.spatial.distance `_ and the metrics listed in :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric values. Not all metrics are valid with all algorithms: refer to the documentation of :class:`BallTree` and :class:`KDTree`. Note that the normalization of the density output is correct only for the Euclidean distance metric. 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. bandwidth_ : float Value of the bandwidth, given directly by the bandwidth parameter or estimated using the 'scott' or 'silverman' method. .. 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]) rNZneither)closedscott silvermanautocCsg|] }t|qSr).0Zalgrr:/tmp/pip-unpacked-wheel-zrfo1fqw/sklearn/neighbors/_kde.py szKernelDensity.leftbooleanr) bandwidth algorithmkernelmetricatolrtol breadth_first leaf_size metric_params_parameter_constraints?rZ euclideanT(c Cs:||_||_||_||_||_||_||_||_| |_dS)N) r#r"r$r%r&r'r(r)r*) selfr"r#r$r%r&r'r(r)r*rrr__init__s zKernelDensity.__init__cCsP|dkr&|tjkrdS|tjkrLdSn&|t|jkrHtdt|||SdS)Nrrrzinvalid metric for {0}: '{1}')rZ valid_metricsr TREE_DICT ValueErrorformat)r.r#r%rrr_choose_algorithms  zKernelDensity._choose_algorithmcCs|||j|j}t|jtr|jdkrN|jdd|jdd|_q|jdkr|jd|jdddd|jdd|_n|j|_|j |dt d }|d k rt ||t d d }|j }|d kri}t ||f|j|j|d ||_|S)aFit the Kernel Density model on the data. Parameters ---------- X : array-like of shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. y : None Ignored. This parameter exists only for compatibility with :class:`~sklearn.pipeline.Pipeline`. sample_weight : array-like of shape (n_samples,), default=None List of sample weights attached to the data X. .. versionadded:: 0.20 Returns ------- self : object Returns the instance itself. rrrrrC)orderdtypeNT)Zonly_non_negative)r%r) sample_weight)Z_validate_paramsr3r#r% isinstancer"strshape bandwidth__validate_datarr r*r0r)tree_)r.Xyr9r#kwargsrrrfits>    zKernelDensity.fitc Cs|t||j|dtdd}|jjdkr6|jjjd}n|jj}|j|}|jj ||j |j ||j |j dd}|t|8}|S)aCompute the log-likelihood of each sample under the model. Parameters ---------- X : array-like of shape (n_samples, n_features) An array of points to query. Last dimension should match dimension of training data (n_features). Returns ------- density : ndarray of shape (n_samples,) Log-likelihood of each sample in `X`. These are normalized to be probability densities, so values will be low for high-dimensional data. r6F)r7r8resetNrT)hr$r&r'r(Z return_log)r r>rr?r9datar< sum_weightr&Zkernel_densityr=r$r'r(nplog)r.r@NZatol_NZ log_densityrrr score_sampless"   zKernelDensity.score_samplescCst||S)a}Compute the total log-likelihood under the model. Parameters ---------- X : array-like of shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. y : None Ignored. This parameter exists only for compatibility with :class:`~sklearn.pipeline.Pipeline`. Returns ------- logprob : float Total log-likelihood of the data in X. This is normalized to be a probability density, so the value will be low for high-dimensional data. )rHsumrK)r.r@rArrrscoreszKernelDensity.scorec Cs.t||jdkrtt|jj}t|}|jdd|d}|jj dkrb||j d tj }n,t t|jj }|d}t|||}|jdkrt||||jS|jdkr*|j d} |j|| fd} t| d d } td | d | d | |jt| } ||| | ddtjfSdS) aGenerate random samples from the model. Currently, this is implemented only for gaussian and tophat kernels. Parameters ---------- n_samples : int, default=1 Number of samples to generate. random_state : int, RandomState instance or None, default=None Determines random number generation used to generate random samples. Pass an int for reproducible results across multiple function calls. See :term:`Glossary `. Returns ------- X : array-like of shape (n_samples, n_features) List of samples. )rrrr)sizeNr4rrT)Zsquaredg?r,)r r$NotImplementedErrorrHZasarrayr?rFr uniformr9r<ZastypeZint64ZcumsumZ searchsortedZ atleast_2dnormalr=rrsqrtZnewaxis) r.Z n_samplesZ random_staterFrnguiZ cumsum_weightrGZdimr@Zs_sqZ correctionrrrsample0s0      zKernelDensity.samplecCs dddiiS)NZ _xfail_checksZcheck_sample_weights_invariancez'sample_weight must have positive valuesr)r.rrr _more_tagses zKernelDensity._more_tags)NN)N)rN)__name__ __module__ __qualname____doc__r rr setr0keys VALID_KERNELS itertoolschainrdictr+__annotations__r/r3rCrKrMrVrWrrrrr$s@ _    8&  5r)r[r_ZnumbersrrZnumpyrHZ scipy.specialrbaserZneighbors._baserutilsr Zutils.validationr r Zutils._param_validationr r Z utils.extmathrZ _ball_treerrZ_kd_treerr^r0rrrrrs*