rtjG0dZddlZddlmZmZddlZddlmZddl m Z m Z ddl m Z ddlmZddlmZdd lmZdd lmZmZdd lmZdd lmZmZmZgd Ze edZGdde ZdS)z5 Kernel Density Estimation ------------------------- N)IntegralReal)gammainc) BaseEstimator _fit_context)BallTree VALID_METRICS)KDTree)check_random_state)Interval StrOptions) row_norms)_check_sample_weightcheck_is_fitted validate_data)gaussiantophat epanechnikov exponentiallinearcosine) ball_treekd_treec eZdZUdZeedddeddhgeee dhzgeee geee j d e Dgeeddd geeddd gd gee d dd gdegd Zeed<dddddddddd dZdZedddZdZddZddZdS) 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]) rNneither)closedscott silvermanautoc(g|]}t|Sr ).0algs T/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/sklearn/neighbors/_kde.py zKernelDensity.s%U%U%USmC&8%U%U%Uleftboolean) bandwidth algorithmkernelmetricatolrtol breadth_first leaf_size metric_params_parameter_constraints?r euclideanT(c ||_||_||_||_||_||_||_||_| |_dSN) r-r,r.r/r0r1r2r3r4) selfr,r-r.r/r0r1r2r3r4s r&__init__zKernelDensity.__init__sK#"    *"*r(c|dkr"|tjvrdS|tjvrdSdS|t|jvr.t dt|||S)Nr!rrzinvalid metric for {0}: '{1}')r valid_metricsr TREE_DICT ValueErrorformat)r;r-r/s r&_choose_algorithmzKernelDensity._choose_algorithms   --- y8111"{21Yy1??? 3::9Y;OQWXX r(F)prefer_skip_nested_validationc\||j|j}t|jt rx|jdkr'|jdd|jddzz z|_nR|jdkr:|jd|jddzzdz d|jddzz z|_n |j|_t||dtj }|t||tj d }|j }|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. rrr+r C)orderdtypeNT)rJensure_non_negative)r/r3 sample_weight)rBr-r/ isinstancer,strshape bandwidth_rnpfloat64rr4r?r3tree_)r;XyrLr-kwargss r&fitzKernelDensity.fitsD6**4>4;GG dnc * * -~(("#'!*qwqzA~1F"G;..#$71:a#@1#D!'!*q.)##nDO $BJ ? ? ?  $0q M# >Fy)  ;n'        r(c lt|t||dtjd}|jj|jjjd}n |jj}|j |z}|j ||j |j ||j |jd}|tj|z}|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. rHF)rIrJresetNrT)hr.r0r1r2 return_log)rrrQrRrSrLdatarO sum_weightr0kernel_densityrPr.r1r2log)r;rTNatol_N log_densitys r& score_sampleszKernelDensity.score_sampless  $BJe L L L : # + %a(AA %AQj// o;,0   rvayy r(cPtj||S)a}Compute the total log-likelihood under the model. Parameters ---------- X : array-like of shape (n_samples, n_features) List of n_features-dimensional data points. Each row corresponds to a single data point. y : None Ignored. This parameter exists only for compatibility with :class:`~sklearn.pipeline.Pipeline`. Returns ------- logprob : float Total log-likelihood of the data in X. This is normalized to be a probability density, so the value will be low for high-dimensional data. )rQsumrc)r;rTrUs r&scorezKernelDensity.score"s"(vd((++,,,r(ct||jdvrttj|jj}t|}|dd|}|jj .||j dz tj }nPtj tj|jj }|d}tj|||z}|jdkr3tj||||jS|jdkr|j d} ||| f} t%| d } t'd | zd | zd | z z|jztj| z } ||| | ddtjfzzSdS) aGenerate random samples from the model. Currently, this is implemented only for gaussian and tophat kernels. Parameters ---------- n_samples : int, default=1 Number of samples to generate. random_state : int, RandomState instance or None, default=None Determines random number generation used to generate random samples. Pass an int for reproducible results across multiple function calls. See :term:`Glossary `. Returns ------- X : array-like of shape (n_samples, n_features) List of samples. )rrrr+)sizeNrErrT)squaredg?r6)rr.NotImplementedErrorrQasarrayrSr\r uniformrLrOastypeint64cumsum searchsorted atleast_2dnormalrPrrsqrtnewaxis) r; n_samples random_stater\rngui cumsum_weightr]dimrTs_sq corrections r&samplezKernelDensity.sample8s*  ;4 4 4%'' 'z$*/** .. KK19K - - : # +TZ]"**2844AAIbj1I&J&JKKM&r*J q:~>>A ;* $ $=DGT_!E!EFF F [H $ $*Q-C C 0 11AQ---DsC$J//C#I>/"'$--   7QAAArzM!::: :% $r()NNr:)r+N)__name__ __module__ __qualname____doc__r rrsetr?keys VALID_KERNELS itertoolschainrdictr5__annotations__r<rBrrWrcrfr~r#r(r&rr*s[[~ HT1d9 5 5 5 J- . . !jY^^%5%5!6!6&!ABBC:cc-00112 JOIO%U%UINNDTDT%U%U%UVWW   $47778$47778#hxD@@@A!$$D,  +++++. \&+444 4l$$$L----,3;3;3;3;3;3;r(r) rrnumbersrrnumpyrQ scipy.specialr sklearn.baserrsklearn.neighbors._ball_treersklearn.neighbors._baser sklearn.neighbors._kd_treer sklearn.utilsr sklearn.utils._param_validationr rsklearn.utils.extmathrsklearn.utils.validationrrrrr?rr#r(r&rsm""""""""""""""44444444111111111111------,,,,,,@@@@@@@@++++++  #v 6 6 A;A;A;A;A;MA;A;A;A;A;r(