
    sgd                     "   d dl Z d dlmZmZ d dlZddlmZmZm	Z	m
Z
mZmZ ddlmZ ddlmZmZ ddlmZ ddlmZmZmZmZmZ dd	lmZmZmZmZmZ dd
l m!Z! ddl"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z( ddl)m*Z*  ejV                  d      Z,d Z- G d dee
e	e      Z.y)    N)IntegralReal   )BaseEstimatorMetaEstimatorMixinMultiOutputMixinRegressorMixin_fit_contextclone)ConvergenceWarning)check_consistent_lengthcheck_random_state)Bunch)
HasMethodsIntervalOptions
RealNotInt
StrOptions)MetadataRouterMethodMapping_raise_for_params_routing_enabledprocess_routing)sample_without_replacement)_check_method_params_check_sample_weight_deprecate_positional_argscheck_is_fittedhas_fit_parametervalidate_data   )LinearRegressionc           
      <   | t        |      z  }t        t        d|z
        }t        t        d||z  z
        }|dk(  ry|dk(  rt        d      S t        t        t	        j
                  t	        j                  |      t	        j                  |      z                    S )a  Determine 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!   r   inf)floatmax_EPSILONabsnpceillog)	n_inliers	n_samplesmin_samplesprobabilityinlier_rationomdenoms          O/var/www/html/venv/lib/python3.12/site-packages/sklearn/linear_model/_ransac.py_dynamic_max_trialsr4   0   s    0 uY//L
hK
(C!lK778E
axzU|uRWWRVVC[266%=89:;;    c                   @   e Zd ZU dZ eg d      dg eeddd       eeddd      dg eeddd      dge	dge	dg eeddd       e
eej                  h      g eeddd       e
eej                  h      g eeddd       e
eej                  h      g eeddd      g eeddd      g ed	d
h      e	gdgdZeed<   	 ddddddej                  ej                  ej                  dd	dddZ ed       ed      ddd              Zd Zd Zd Zy)RANSACRegressora  RANSAC (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 <ransac_regression>`.

    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 <random_state>`.

    Attributes
    ----------
    estimator_ : object
        Final model fitted on the inliers predicted by the "best" model found
        during RANSAC sampling (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] https://bmva-archive.org.uk/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...])

    For a more detailed example, see
    :ref:`sphx_glr_auto_examples_linear_model_plot_ransac.py`
    )fitscorepredictNr!   left)closedr   bothabsolute_errorsquared_errorrandom_state)	estimatorr.   residual_thresholdis_data_validis_model_valid
max_trials	max_skipsstop_n_inliers
stop_scorestop_probabilitylossr@   _parameter_constraintsd   gGz?)r.   rB   rC   rD   rE   rF   rG   rH   rI   rJ   r@   c                    || _         || _        || _        || _        || _        || _        || _        || _        |	| _        |
| _	        || _
        || _        y N)rA   r.   rB   rC   rD   rE   rF   rG   rH   rI   r@   rJ   )selfrA   r.   rB   rC   rD   rE   rF   rG   rH   rI   rJ   r@   s                r3   __init__zRANSACRegressor.__init__!  s_      #&"4*,$",$ 0(	r5   F)prefer_skip_nested_validationz1.7)version)sample_weightc          	      >   t        || d       t        dd      }t        d      }t        | ||||f      \  }}t        ||       | j                  t        | j                        }n
t               }| j                  .t        |t              st        d      |j                  d	   d	z   }ncd
| j                  cxk  rd	k  r3n n0t        j                  | j                  |j                  d
   z        }n| j                  d	k\  r| j                  }|j                  d
   kD  rt        d|j                  d
   z        | j                  ?t        j                  t        j                  |t        j                  |      z
              }	n| j                  }	| j                   dk(  r|j"                  d	k(  rd }
nKd }
nG| j                   dk(  r|j"                  d	k(  rd }
n%d }
n!t%        | j                         r| j                   }
t'        | j(                        }	 |j+                  |       t-        |d      }t/        |      j0                  }||st        d|z        |||d<   t3               rt5        | dfi |}n>t7               }t7        i i i       |_        |t9        ||      }d|i|j                  _        d	}t        j<                   }d}d}d}d}d
| _        d
| _         d
| _!        |j                  d
   }t        jD                  |      }d
| _#        | jH                  }| jF                  |k  r| xjF                  d	z  c_#        | j>                  | j@                  z   | jB                  z   | jJ                  kD  rntM        |||      }||   }||   }| jN                  (| jO                  ||      s| xj@                  d	z  c_         tQ        ||j                  j:                  |      } |j:                  ||fi | | jR                  *| jS                  |||      s| xjB                  d	z  c_!        |jU                  |      } 
||      }||	k  }t        jV                  |      }||k  r| xj>                  d	z  c_        b||   } ||    }!||    }"tQ        ||j                  jX                  |       }# |jX                  |!|"fi |#}$||k(  r|$|k  r|}|$}|}|!}|"}| }t[        |t]        |||| j^                              }|| j`                  k\  s|| jb                  k\  rn| jF                  |k  r|I| j>                  | j@                  z   | jB                  z   | jJ                  kD  rt        d      t        d      | j>                  | j@                  z   | jB                  z   | jJ                  kD  rte        jf                  dth               tQ        ||j                  j:                  |      }% |j:                  ||fi |% || _5        || _6        | S # t        $ r Y w xY w)a
  Fit 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

        **fit_params : dict
            Parameters routed to the `fit` method of the sub-estimator via the
            metadata routing API.

            .. versionadded:: 1.5

                Only available if
                `sklearn.set_config(enable_metadata_routing=True)` is set. See
                :ref:`Metadata Routing User Guide <metadata_routing>` for more
                details.

        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.
        r8   csrF)accept_sparseensure_all_finite)	ensure_2d)validate_separatelyNzR`min_samples` needs to be explicitly set when estimator is not a LinearRegression.r!   r   zG`min_samples` may not be larger than number of samples: n_samples = %d.r>   c                 2    t        j                  | |z
        S rN   )r)   r(   y_truey_preds     r3   <lambda>z%RANSACRegressor.fit.<locals>.<lambda>  s    rvvfvo7N r5   c                 \    t        j                  t        j                  | |z
        d      S )Nr!   axis)r)   sumr(   r[   s     r3   r^   z%RANSACRegressor.fit.<locals>.<lambda>  s!    rvvFF6F?+!8 r5   r?   c                     | |z
  dz  S )Nr    r[   s     r3   r^   z%RANSACRegressor.fit.<locals>.<lambda>  s    A7M r5   c                 <    t        j                  | |z
  dz  d      S )Nr   r!   r`   )r)   rb   r[   s     r3   r^   z%RANSACRegressor.fit.<locals>.<lambda>  s    rvvf_*8 r5   )r@   rS   z[%s does not support sample_weight. Sample weights are only used for the calibration itself.)r8   r:   r9   )paramsindiceszRANSAC 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*).)7r   dictr    r   rA   r   r"   r.   
isinstance
ValueErrorshaper)   r*   rB   medianr(   rJ   ndimcallabler   r@   
set_paramsr   type__name__r   r   r   r   r8   r$   n_skips_no_inliers_n_skips_invalid_data_n_skips_invalid_model_arange	n_trials_rE   rF   r   rC   r   rD   r:   rb   r9   minr4   rI   rG   rH   warningswarnr   
estimator_inlier_mask_)&rO   XyrS   
fit_paramscheck_X_paramscheck_y_paramsrA   r.   rB   loss_functionr@   estimator_fit_has_sample_weightestimator_namerouted_paramsn_inliers_best
score_bestinlier_mask_bestX_inlier_besty_inlier_bestinlier_best_idxs_subsetr-   sample_idxsrE   subset_idxsX_subsety_subsetfit_params_subsetr]   residuals_subsetinlier_mask_subsetn_inliers_subsetinlier_idxs_subsetX_inlier_subsety_inlier_subsetscore_params_inlier_subsetscore_subsetfit_params_best_idxs_subsets&                                         r3   r8   zRANSACRegressor.fit>  s   h 	*dE2EUK.!Q^^,L
1 	 1%>>%dnn-I(*I#i)9: 1  ''!*q.K!!%A%''$"2"2QWWQZ"?@K"**K#.12= 
 ""*!#266!biil2B+C!D!%!8!899((vv{ N! YY/)vv{ M! dii  IIM)$*;*;<	  l ; +<I*W'i11$-L+,  $*7J'+D%F:FM!GM&+Bb&IM#( 4]A F/>.N''+ffW
"&#$ %&"&'# GGAJ	ii	*__
nnz)NNaN ((,,---. 	
  5;\K ~H~H !!-d6H6H(7 **a/* !5-1155{!
 IMM(HB0AB "".t7J7J8X8 ++q0+ &&q)F,Q7 "25G!G!vv&89  .0((A-( "--?!@ 23O 23O *>-1177AS*&
 +9?? -L  >1lZ6O .N%J1+M+M&8##"I{D<Q<QJ !4!44
doo8Uw nnz)| #((,,---. 	
 !/  !L  ((,,---. 	
 3
 ' ';m--11;R'
# 		m]R6QR#,g  		s   X 	XXc                     t        |        t        | |ddd      }t        || d       t               rt	        | dfi |j
                  d   }ni } | j                  j                  |fi |S )a   Predict 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.

        **params : dict
            Parameters routed to the `predict` method of the sub-estimator via
            the metadata routing API.

            .. versionadded:: 1.5

                Only available if
                `sklearn.set_config(enable_metadata_routing=True)` is set. See
                :ref:`Metadata Routing User Guide <metadata_routing>` for more
                details.

        Returns
        -------
        y : array, shape = [n_samples] or [n_samples, n_targets]
            Returns predicted values.
        FTrW   rV   resetr:   )r   r    r   r   r   rA   rz   r:   )rO   r|   rf   predict_paramss       r3   r:   zRANSACRegressor.predicta  s{    4 	#
 	&$	2,T9GGQQN  N&t&&q;N;;r5   c                     t        |        t        | |ddd      }t        || d       t               rt	        | dfi |j
                  d   }ni } | j                  j                  ||fi |S )a6  Return 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.

        **params : dict
            Parameters routed to the `score` method of the sub-estimator via
            the metadata routing API.

            .. versionadded:: 1.5

                Only available if
                `sklearn.set_config(enable_metadata_routing=True)` is set. See
                :ref:`Metadata Routing User Guide <metadata_routing>` for more
                details.

        Returns
        -------
        z : float
            Score of the prediction.
        FTr   r9   )r   r    r   r   r   rA   rz   r9   )rO   r|   r}   rf   score_paramss        r3   r9   zRANSACRegressor.score  sx    : 	#
 	&$0*4CFCMMgVLL$t$$Q:\::r5   c                    t        | j                  j                        j                  | j                  t               j                  dd      j                  dd      j                  dd      j                  dd            }|S )aj  Get metadata routing of this object.

        Please check :ref:`User Guide <metadata_routing>` on how the routing
        mechanism works.

        .. versionadded:: 1.5

        Returns
        -------
        routing : MetadataRouter
            A :class:`~sklearn.utils.metadata_routing.MetadataRouter` encapsulating
            routing information.
        )ownerr8   )callercalleer9   r:   )rA   method_mapping)r   	__class__rq   addrA   r   )rO   routers     r3   get_metadata_routingz$RANSACRegressor.get_metadata_routing  st      dnn&=&=>BBnn(?SeS,SgS.SS0S	)S4 C 
 r5   rN   )rq   
__module____qualname____doc__r   r   r   r   r   rn   r   r)   r$   r   rK   rh   __annotations__rP   r
   r   r8   r:   r9   r   rd   r5   r3   r7   r7   R   s   k\ !!<=tDXq$v6ZAf5

  (afEtL"D)#T*Xq$v6D266(#

 Xq$v6D266(#

 Xq$v6D266(#
  dD@A%dAq@A-?@(K'(3$D <  &&vv66: &+  .)- Y /Yv,<\,;\r5   r7   )/rx   numbersr   r   numpyr)   baser   r   r   r	   r
   r   
exceptionsr   utilsr   r   utils._bunchr   utils._param_validationr   r   r   r   r   utils.metadata_routingr   r   r   r   r   utils.randomr   utils.validationr   r   r   r   r   r    _baser"   spacingr'   r4   r7   rd   r5   r3   <module>r      sz     "   , ?     6  $2::a=<DA
	A
r5   