o tBhg[@sddlZddlZddlmZmZmZmZddlmZddl m Z m Z ddl m Z ddlmZmZdd lmZdd lmZdd lmZedZd d ZGdddeeeeZdS)N) BaseEstimatorMetaEstimatorMixinRegressorMixinclone)MultiOutputMixin)check_random_statecheck_consistent_length)sample_without_replacement)check_is_fitted_check_sample_weight)LinearRegression)has_fit_parameter)ConvergenceWarningcCsj|t|}ttd|}ttd||}|dkrdS|dkr$tdStttt|t|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. r rinf)floatmax_EPSILONabsnpceillog) n_inliers n_samples min_samples probability inlier_rationomdenomr s/var/www/html/riverr-enterprise-integrations-main/venv/lib/python3.10/site-packages/sklearn/linear_model/_ransac.py_dynamic_max_trialss "r"c@s`eZdZdZ ddddddejejejddddd dd Zdd d Zd d ZddZ ddZ dS)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 ``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:`linear_model.LinearRegression` is used, the user is encouraged to provide a value. .. deprecated:: 1.0 Not setting `min_samples` explicitly will raise an error in version 1.2 for models other than :class:`~sklearn.linear_model.LinearRegression`. To keep the old default behavior, set `min_samples=X.shape[1] + 1` explicitly. 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 .. deprecated:: 1.0 The loss 'squared_loss' was deprecated in v1.0 and will be removed in version 1.2. Use `loss='squared_error'` which is equivalent. .. deprecated:: 1.0 The loss 'absolute_loss' was deprecated in v1.0 and will be removed in version 1.2. Use `loss='absolute_error'` which is equivalent. 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 `. base_estimator : object, default="deprecated" Use `estimator` instead. .. deprecated:: 1.1 `base_estimator` is deprecated and will be removed in 1.3. Use `estimator` instead. 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/sites/default/files/publications/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...]) NdgGz?absolute_error deprecated) rresidual_threshold is_data_validis_model_valid max_trials max_skipsstop_n_inliers stop_scorestop_probabilityloss random_statebase_estimatorc CsR||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ dSN) estimatorrr'r(r)r*r+r,r-r.r0r/r1)selfr3rr'r(r)r*r+r,r-r.r/r0r1r r r!__init__s zRANSACRegressor.__init__c!Cstddd}tdd}|j||||fd\}}t|||jdkr+tdt|j|_|jdur6t|j}nt }|j durYt |t sQtd |j d d t|j d d }n1d |j krdd krrnn t |j |j d }n|j d kr|j d d krtd |j }ntd ||j d krtd|j d |jd ks|jd krtd|jdurt t |t |}n|j}|jdvr|jdkrtdt|jd krdd} n5dd} n0|jdvr|jdkrtdt|jd krdd} ndd} nt|jr|j} ntd|jt|j} z|j| dWn ty$Ynwt|d} t|j} |dur=| s=td| |durGt||}d } t j }d}d}d}d}d |_d |_ d |_!|j d }t "|}d |_#|j$}|j#|krD|j#d 7_#|j|j |j!|j%krnt&||| d}||}||}|j'dur|'||s|j d 7_ qn|dur|(||n |j(||||d|j)dur|)|||s|j!d 7_!qn|*|}| ||}||k}t +|}|| kr|jd 7_qn||}||}||}|,||} || kr| |krqn|} | }|}|}|}|}t-|t.| |||j}| |j/ks=||j0kr>n|j#|kst|dur^|j|j |j!|j%krZtd td!|j|j |j!|j%krqtd"t1|dur}|(||n |j(||||d||_2||_3|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_separatelyr&zV`base_estimator` was renamed to `estimator` in version 1.1 and will be removed in 1.3.NzFrom version 1.2, `min_samples` needs to be explicitly set otherwise an error will be raised. To keep the current behavior, you need to set `min_samples` to `X.shape[1] + 1 that is r rz4Absolute number of samples must be an integer value.z4Value for `min_samples` must be scalar and positive.zG`min_samples` may not be larger than number of samples: n_samples = %d.z+`stop_probability` must be in range [0, 1].)r% absolute_lossr;zThe loss 'absolute_loss' was deprecated in v1.0 and will be removed in version 1.2. Use `loss='absolute_error'` which is equivalent.cSst||Sr2)rry_truey_predr r r!xsz%RANSACRegressor.fit..cSstjt||ddS)Nr axis)rsumrr<r r r!r?zs) squared_error squared_lossrDzThe loss 'squared_loss' was deprecated in v1.0 and will be removed in version 1.2. Use `loss='squared_error'` which is equivalent.cSs ||dS)Nrr r<r r r!r?s cSstj||dddS)Nrr r@)rrBr<r r r!r?s zHloss should be 'absolute_error', 'squared_error' or a callable. Got %s. )r0 sample_weightz\%s does not support sample_weight. Samples weights are only used for the calibration itself.)rEzRANSAC 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*).)4dict_validate_datar r1warningswarn FutureWarningr3rrr isinstanceshaperr ValueErrorr.r'medianrr/ndimcallablerr0 set_paramsrtype__name__r rn_skips_no_inliers_n_skips_invalid_data_n_skips_invalid_model_arange n_trials_r*r+r r(fitr)predictrBscoreminr"r,r-r estimator_ inlier_mask_)!r4XyrEcheck_X_paramscheck_y_paramsr3rr' loss_functionr0estimator_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_subsetr>residuals_subsetinlier_mask_subsetn_inliers_subsetinlier_idxs_subsetX_inlier_subsety_inlier_subset score_subsetr r r!rYsz !                                       U zRANSACRegressor.fitcCs&t||j|dddd}|j|S)auPredict using the estimated model. This is a wrapper for `estimator_.predict(X)`. Parameters ---------- X : {array-like or sparse matrix} of shape (n_samples, n_features) Input data. Returns ------- y : array, shape = [n_samples] or [n_samples, n_targets] Returns predicted values. FTr8r7reset)r rGr]rZ)r4r_r r r!rZ>s zRANSACRegressor.predictcCs(t||j|dddd}|j||S)aReturn the score of the prediction. This is a wrapper for `estimator_.score(X, y)`. Parameters ---------- X : (array-like or sparse matrix} of shape (n_samples, n_features) Training data. y : array-like of shape (n_samples,) or (n_samples, n_targets) Target values. Returns ------- z : float Score of the prediction. FTrw)r rGr]r[)r4r_r`r r r!r[VszRANSACRegressor.scorecCs dddiiS)N _xfail_checkscheck_sample_weights_invariancez8zero sample_weight is not equivalent to removing samplesr )r4r r r! _more_tagsqs zRANSACRegressor._more_tagsr2) rS __module__ __qualname____doc__rrr5rYrZr[r{r r r r!r#6s0A ) r#)numpyrrHbaserrrrrutilsrr utils.randomr utils.validationr r _baserr exceptionsrspacingrr"r#r r r r!s       "