hUddlZddlmZmZddlZddlmZmZm Z m Z m Z m Z ddl mZddlmZmZddlmZmZmZmZmZddlmZdd lmZmZmZd d lmZej d Z!d Z"Gd dee e eZ#dS)N)IntegralReal) BaseEstimatorMetaEstimatorMixinMultiOutputMixinRegressorMixin _fit_contextclone)ConvergenceWarning)check_consistent_lengthcheck_random_state) HasMethodsIntervalOptions RealNotInt StrOptions)sample_without_replacement)_check_sample_weightcheck_is_fittedhas_fit_parameter)LinearRegressionc p|t|z }ttd|z }ttd||zz }|dkrdS|dkrtdSttt jt j|t j|z S)aDetermine number trials such that at least one outlier-free subset is sampled for the given inlier/outlier ratio. Parameters ---------- n_inliers : int Number of inliers in the data. n_samples : int Total number of samples in the data. min_samples : int Minimum number of samples chosen randomly from original data. probability : float Probability (confidence) that one outlier-free sample is generated. Returns ------- trials : int Number of trials. rrinf)floatmax_EPSILONabsnpceillog) n_inliers n_samples min_samples probability inlier_rationomdenoms d/var/www/html/services/rag-service/venv/lib/python3.11/site-packages/sklearn/linear_model/_ransac.py_dynamic_max_trialsr+"s0uY///L hK ( (C !lK77 8 8E axxq zzU|| uRWRVC[[26%==899:: ; ;;cDeZdZUdZegddgeedddeeddddgeeddddge dge dgeeddde ee j hgeeddde ee j hgeeddde ee j hgeedddgeedddge d d he gd gd Zeed < dddddde j e j e j dd dd dZedddZdZdZdZdS)RANSACRegressoraRANSAC (RANdom SAmple Consensus) algorithm. RANSAC is an iterative algorithm for the robust estimation of parameters from a subset of inliers from the complete data set. Read more in the :ref:`User Guide `. Parameters ---------- estimator : object, default=None Base estimator object which implements the following methods: * `fit(X, y)`: Fit model to given training data and target values. * `score(X, y)`: Returns the mean accuracy on the given test data, which is used for the stop criterion defined by `stop_score`. Additionally, the score is used to decide which of two equally large consensus sets is chosen as the better one. * `predict(X)`: Returns predicted values using the linear model, which is used to compute residual error using loss function. If `estimator` is None, then :class:`~sklearn.linear_model.LinearRegression` is used for target values of dtype float. Note that the current implementation only supports regression estimators. min_samples : int (>= 1) or float ([0, 1]), default=None Minimum number of samples chosen randomly from original data. Treated as an absolute number of samples for `min_samples >= 1`, treated as a relative number `ceil(min_samples * X.shape[0])` for `min_samples < 1`. This is typically chosen as the minimal number of samples necessary to estimate the given `estimator`. By default a :class:`~sklearn.linear_model.LinearRegression` estimator is assumed and `min_samples` is chosen as ``X.shape[1] + 1``. This parameter is highly dependent upon the model, so if a `estimator` other than :class:`~sklearn.linear_model.LinearRegression` is used, the user must provide a value. residual_threshold : float, default=None Maximum residual for a data sample to be classified as an inlier. By default the threshold is chosen as the MAD (median absolute deviation) of the target values `y`. Points whose residuals are strictly equal to the threshold are considered as inliers. is_data_valid : callable, default=None This function is called with the randomly selected data before the model is fitted to it: `is_data_valid(X, y)`. If its return value is False the current randomly chosen sub-sample is skipped. is_model_valid : callable, default=None This function is called with the estimated model and the randomly selected data: `is_model_valid(model, X, y)`. If its return value is False the current randomly chosen sub-sample is skipped. Rejecting samples with this function is computationally costlier than with `is_data_valid`. `is_model_valid` should therefore only be used if the estimated model is needed for making the rejection decision. max_trials : int, default=100 Maximum number of iterations for random sample selection. max_skips : int, default=np.inf Maximum number of iterations that can be skipped due to finding zero inliers or invalid data defined by ``is_data_valid`` or invalid models defined by ``is_model_valid``. .. versionadded:: 0.19 stop_n_inliers : int, default=np.inf Stop iteration if at least this number of inliers are found. stop_score : float, default=np.inf Stop iteration if score is greater equal than this threshold. stop_probability : float in range [0, 1], default=0.99 RANSAC iteration stops if at least one outlier-free set of the training data is sampled in RANSAC. This requires to generate at least N samples (iterations):: N >= log(1 - probability) / log(1 - e**m) where the probability (confidence) is typically set to high value such as 0.99 (the default) and e is the current fraction of inliers w.r.t. the total number of samples. loss : str, callable, default='absolute_error' String inputs, 'absolute_error' and 'squared_error' are supported which find the absolute error and squared error per sample respectively. If ``loss`` is a callable, then it should be a function that takes two arrays as inputs, the true and predicted value and returns a 1-D array with the i-th value of the array corresponding to the loss on ``X[i]``. If the loss on a sample is greater than the ``residual_threshold``, then this sample is classified as an outlier. .. versionadded:: 0.18 random_state : int, RandomState instance, default=None The generator used to initialize the centers. Pass an int for reproducible output across multiple function calls. See :term:`Glossary `. Attributes ---------- estimator_ : object Best fitted model (copy of the `estimator` object). n_trials_ : int Number of random selection trials until one of the stop criteria is met. It is always ``<= max_trials``. inlier_mask_ : bool array of shape [n_samples] Boolean mask of inliers classified as ``True``. n_skips_no_inliers_ : int Number of iterations skipped due to finding zero inliers. .. versionadded:: 0.19 n_skips_invalid_data_ : int Number of iterations skipped due to invalid data defined by ``is_data_valid``. .. versionadded:: 0.19 n_skips_invalid_model_ : int Number of iterations skipped due to an invalid model defined by ``is_model_valid``. .. versionadded:: 0.19 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 See Also -------- HuberRegressor : Linear regression model that is robust to outliers. TheilSenRegressor : Theil-Sen Estimator robust multivariate regression model. SGDRegressor : Fitted by minimizing a regularized empirical loss with SGD. References ---------- .. [1] https://en.wikipedia.org/wiki/RANSAC .. [2] https://www.sri.com/wp-content/uploads/2021/12/ransac-publication.pdf .. [3] http://www.bmva.org/bmvc/2009/Papers/Paper355/Paper355.pdf Examples -------- >>> from sklearn.linear_model import RANSACRegressor >>> from sklearn.datasets import make_regression >>> X, y = make_regression( ... n_samples=200, n_features=2, noise=4.0, random_state=0) >>> reg = RANSACRegressor(random_state=0).fit(X, y) >>> reg.score(X, y) 0.9885... >>> reg.predict(X[:1,]) array([-31.9417...]) )fitscorepredictNrleft)closedrbothabsolute_error squared_error random_state) estimatorr%residual_threshold is_data_validis_model_valid max_trials max_skipsstop_n_inliers stop_scorestop_probabilitylossr7_parameter_constraintsdgGz?) r%r9r:r;r<r=r>r?r@rAr7c ||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ dSN) r8r%r9r:r;r<r=r>r?r@r7rA) selfr8r%r9r:r;r<r=r>r?r@rAr7s r*__init__zRANSACRegressor.__init__ sc #&"4*,$",$ 0( r,F)prefer_skip_nested_validationc  tdd}td}|||||f\}}t|||jt |j}nt }|j5t|t std|j ddz}nOd |jcxkrdkr+nn(tj |j|j d z}n|jdkr|j}||j d krtd |j d z|j |j|jz|jz|j krtdtd|j|jz|jz|j krt[j.dt^||#||n|#||||||_0||_1|S)aFit estimator using RANSAC algorithm. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Training data. y : array-like of shape (n_samples,) or (n_samples, n_targets) Target values. sample_weight : array-like of shape (n_samples,), default=None Individual weights for each sample raises error if sample_weight is passed and estimator fit method does not support it. .. versionadded:: 0.18 Returns ------- self : object Fitted `RANSACRegressor` estimator. Raises ------ ValueError If no valid consensus set could be found. This occurs if `is_data_valid` and `is_model_valid` return False for all `max_trials` randomly chosen sub-samples. csrF) accept_sparseforce_all_finite) ensure_2d)validate_separatelyNzR`min_samples` needs to be explicitly set when estimator is not a LinearRegression.rrzG`min_samples` may not be larger than number of samples: n_samples = %d.r5c0tj||z SrE)r ry_truey_preds r*z%RANSACRegressor.fit..ssrvfvo7N7Nr,cXtjtj||z dS)Nraxis)r sumrrPs r*rSz%RANSACRegressor.fit..us*rvF6F?++!888r,r6c||z dzS)NrrPs r*rSz%RANSACRegressor.fit..zsA7Mr,c:tj||z dzdS)NrrrU)r rWrPs r*rSz%RANSACRegressor.fit..|s%rvf_*888r,)r7 sample_weightz\%s does not support sample_weight. Samples weights are only used for the calibration itself.)r[zRANSAC skipped more iterations than `max_skips` without finding a valid consensus set. Iterations were skipped because each randomly chosen sub-sample failed the passing criteria. See estimator attributes for diagnostics (n_skips*).zRANSAC could not find a valid consensus set. All `max_trials` iterations were skipped because each randomly chosen sub-sample failed the passing criteria. See estimator attributes for diagnostics (n_skips*).zRANSAC found a valid consensus set but exited early due to skipping more iterations than `max_skips`. See estimator attributes for diagnostics (n_skips*).)2dict_validate_datar r8r rr% isinstance ValueErrorshaper r!r9medianrrAndimcallablerr7 set_paramsrtype__name__rrn_skips_no_inliers_n_skips_invalid_data_n_skips_invalid_model_arange n_trials_r<r=rr:r/r;r1rWr0minr+r@r>r?warningswarnr estimator_ inlier_mask_)!rFXyr[check_X_paramscheck_y_paramsr8r%r9 loss_functionr7estimator_fit_has_sample_weightestimator_namen_inliers_best score_bestinlier_mask_best X_inlier_best y_inlier_bestinlier_best_idxs_subsetr$ sample_idxsr< subset_idxsX_subsety_subsetrRresiduals_subsetinlier_mask_subsetn_inliers_subsetinlier_idxs_subsetX_inlier_subsety_inlier_subset score_subsets! r*r/zRANSACRegressor.fit)sJEEJJJ..."" q~~&F#  1 1%%% > %dn--II(**I   #i)9::  1'!*q.KK ! % % % %A % % % % %'$"2QWQZ"?@@KK   " "*K  # #.12=   " *!#26!bill2B+C+C!D!D  !%!8  9( ( (v{{ N N !! Y/ ) )v{{ M M !! di  & IM)$*;<<    l ; ; ; ;    D +11lZ6O6O.N%J1 +M+M&8 ##"I{Drs """""""",+++++????????655555WWWWWWWWWW###### 2:a==<<