B 0d-@sddlZddlmZddlmZmZddlmZddl m Z ddl m Z dd l mZdd lmZdd d ZGd ddeeeZdS)N)optimize) BaseEstimatorRegressorMixin) LinearModel)axis0_safe_slice)_check_sample_weight)safe_sparse_dot)_check_optimize_resultc CsX|j\}}|d|jdk}|r(|d} |d} |d|}t|} |t||} |r`| | 8} t| } | || k}| |}t|}|jd|}||}t|}d|t||| ||d}| |}|||}t|j|}|| }|rt|d}nt|d}t ||| }d| t|||d|<t |}| |dk}d||<t |||}|||}|d|d|t||8<|d||d|7<| |d<|d||d8<|d|| 8<|r,d t|| |d<|dd|t|8<| | ||}||t||7}||fS) aReturns the Huber loss and the gradient. Parameters ---------- w : ndarray, shape (n_features + 1,) or (n_features + 2,) Feature vector. w[:n_features] gives the coefficients w[-1] gives the scale factor and if the intercept is fit w[-2] gives the intercept factor. X : ndarray of shape (n_samples, n_features) Input data. y : ndarray of shape (n_samples,) Target vector. epsilon : float Robustness of the Huber estimator. alpha : float Regularization parameter. sample_weight : ndarray of shape (n_samples,), default=None Weight assigned to each sample. Returns ------- loss : float Huber loss. gradient : ndarray, shape (len(w)) Returns the derivative of the Huber loss with respect to each coefficient, intercept and the scale as a vector. rrNg@rgg) shapenpsumr absZ count_nonzerodotTzerosrZ ones_like) wXyepsilonalpha sample_weight_Z n_features fit_interceptZ interceptsigmaZ n_samplesZ linear_lossZabs_linear_lossZ outliers_maskZoutliersZ num_outliersZn_non_outliersZ outliers_swZ n_sw_outliersZ outlier_lossZ non_outliersZweighted_non_outliersZ weighted_lossZ squared_lossZgradZX_non_outliersZsigned_outliersZsigned_outliers_maskZ X_outliersZ sw_outliersZlossrM/var/www/html/venv/lib/python3.7/site-packages/sklearn/linear_model/_huber.py_huber_loss_and_gradientsX#            "r c@s2eZdZdZdddddddd d Zdd d Zd S)HuberRegressoraLinear regression model that is robust to outliers. The Huber Regressor optimizes the squared loss for the samples where ``|(y - X'w) / sigma| < epsilon`` and the absolute loss for the samples where ``|(y - X'w) / sigma| > epsilon``, where w and sigma are parameters to be optimized. The parameter sigma makes sure that if y is scaled up or down by a certain factor, one does not need to rescale epsilon to achieve the same robustness. Note that this does not take into account the fact that the different features of X may be of different scales. This makes sure that the loss function is not heavily influenced by the outliers while not completely ignoring their effect. Read more in the :ref:`User Guide ` .. versionadded:: 0.18 Parameters ---------- epsilon : float, greater than 1.0, default=1.35 The parameter epsilon controls the number of samples that should be classified as outliers. The smaller the epsilon, the more robust it is to outliers. max_iter : int, default=100 Maximum number of iterations that ``scipy.optimize.minimize(method="L-BFGS-B")`` should run for. alpha : float, default=0.0001 Regularization parameter. warm_start : bool, default=False This is useful if the stored attributes of a previously used model has to be reused. If set to False, then the coefficients will be rewritten for every call to fit. See :term:`the Glossary `. fit_intercept : bool, default=True Whether or not to fit the intercept. This can be set to False if the data is already centered around the origin. tol : float, default=1e-05 The iteration will stop when ``max{|proj g_i | i = 1, ..., n}`` <= ``tol`` where pg_i is the i-th component of the projected gradient. Attributes ---------- coef_ : array, shape (n_features,) Features got by optimizing the Huber loss. intercept_ : float Bias. scale_ : float The value by which ``|y - X'w - c|`` is scaled down. n_features_in_ : int Number of features seen during :term:`fit`. .. versionadded:: 0.24 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 n_iter_ : int Number of iterations that ``scipy.optimize.minimize(method="L-BFGS-B")`` has run for. .. versionchanged:: 0.20 In SciPy <= 1.0.0 the number of lbfgs iterations may exceed ``max_iter``. ``n_iter_`` will now report at most ``max_iter``. outliers_ : array, shape (n_samples,) A boolean mask which is set to True where the samples are identified as outliers. See Also -------- RANSACRegressor : RANSAC (RANdom SAmple Consensus) algorithm. TheilSenRegressor : Theil-Sen Estimator robust multivariate regression model. SGDRegressor : Fitted by minimizing a regularized empirical loss with SGD. References ---------- .. [1] Peter J. Huber, Elvezio M. Ronchetti, Robust Statistics Concomitant scale estimates, pg 172 .. [2] Art B. Owen (2006), A robust hybrid of lasso and ridge regression. https://statweb.stanford.edu/~owen/reports/hhu.pdf Examples -------- >>> import numpy as np >>> from sklearn.linear_model import HuberRegressor, LinearRegression >>> from sklearn.datasets import make_regression >>> rng = np.random.RandomState(0) >>> X, y, coef = make_regression( ... n_samples=200, n_features=2, noise=4.0, coef=True, random_state=0) >>> X[:4] = rng.uniform(10, 20, (4, 2)) >>> y[:4] = rng.uniform(10, 20, 4) >>> huber = HuberRegressor().fit(X, y) >>> huber.score(X, y) -7.284... >>> huber.predict(X[:1,]) array([806.7200...]) >>> linear = LinearRegression().fit(X, y) >>> print("True coefficients:", coef) True coefficients: [20.4923... 34.1698...] >>> print("Huber coefficients:", huber.coef_) Huber coefficients: [17.7906... 31.0106...] >>> print("Linear Regression coefficients:", linear.coef_) Linear Regression coefficients: [-1.9221... 7.0226...] g?dg-C6?FTgh㈵>)rmax_iterr warm_startrtolcCs(||_||_||_||_||_||_dS)N)rr#rr$rr%)selfrr#rr$rr%rrr__init__s zHuberRegressor.__init__Nc Cs|j||ddgdtjtjgd\}}t||}|jdkrFtd|j|jrpt|drpt |j |j |j gf}n8|j rt|jdd }nt|jdd}d|d <ttj tjg|jd df}ttjjd |d d <tjt|d d|||j|j|f|j|jd d|d}|j}|jd kr4td|jtd||j|_|d |_ |j rb|d|_ nd|_ |d|jd|_ t|t ||j |j }||j |jk|_!|S)a5Fit the model according to the given training data. Parameters ---------- X : array-like, shape (n_samples, n_features) Training vector, where `n_samples` is the number of samples and `n_features` is the number of features. y : array-like, shape (n_samples,) Target vector relative to X. sample_weight : array-like, shape (n_samples,) Weight given to each sample. Returns ------- self : object Fitted `HuberRegressor` estimator. FZcsrT)copyZ accept_sparseZ y_numericZdtypeg?z6epsilon should be greater than or equal to 1.0, got %fcoef_rrr r zL-BFGS-B)maxiterZgtolZiprint)methodZjacargsoptionsboundszEHuberRegressor convergence failed: l-BFGS-b solver terminated with %sZlbfgsr gN)"Z_validate_datarZfloat64Zfloat32r r ValueErrorr$hasattrZ concatenater)Z intercept_Zscale_rrrZtileinfZfinfoZepsrZminimizer rr#r%xstatusmessager Zn_iter_rr Z outliers_)r&rrr parametersr/Zopt_resZresidualrrrfitsR        zHuberRegressor.fit)N)__name__ __module__ __qualname____doc__r'r7rrrrr!~su r!)N)numpyrZscipyrbaserr_baserutilsrZutils.validationr Z utils.extmathr Zutils.optimizer r r!rrrrs       n