a jE @sNdZddlZddlZddlmZddlZddlmZm Z ddl m Z ddl m Z ddlmZmZdd lmZmZmZmZdd lmZmZdd lmZmZmZdd lmZmZdd l m!Z!m"Z"gdZ#edgdgdddddZ$edgddgeedddddgeedddddgdgddddddddddZ%GdddeeeZ&dS)z8Isotonic regression for obtaining monotonic fit to data.N)Real) interpolateoptimize) spearmanr)metadata_routing)'_inplace_contiguous_isotonic_regression _make_unique) BaseEstimatorRegressorMixinTransformerMixin _fit_context) check_arraycheck_consistent_length)Interval StrOptionsvalidate_params) parse_versionsp_base_version)_check_sample_weightcheck_is_fitted)check_increasingisotonic_regressionIsotonicRegressionz array-like)xyTZprefer_skip_nested_validationc Cst||\}}|dk}|dvrt|dkrdtd|d|}dtt|d}t|d|}t|d|}t|t|krt d|S) a?Determine whether y is monotonically correlated with x. y is found increasing or decreasing with respect to x based on a Spearman correlation test. Parameters ---------- x : array-like of shape (n_samples,) Training data. y : array-like of shape (n_samples,) Training target. Returns ------- increasing_bool : boolean Whether the relationship is increasing or decreasing. Notes ----- The Spearman correlation coefficient is estimated from the data, and the sign of the resulting estimate is used as the result. In the event that the 95% confidence interval based on Fisher transform spans zero, a warning is raised. References ---------- Fisher transformation. Wikipedia. https://en.wikipedia.org/wiki/Fisher_transformation Examples -------- >>> from sklearn.isotonic import check_increasing >>> x, y = [1, 2, 3, 4, 5], [2, 4, 6, 8, 10] >>> check_increasing(x, y) np.True_ >>> y = [10, 8, 6, 4, 2] >>> check_increasing(x, y) np.False_ r)g?g?rrg\(\?zwConfidence interval of the Spearman correlation coefficient spans zero. Determination of ``increasing`` may be suspect.) rlenmathlogsqrttanhnpsignwarningswarn) rrrho_Zincreasing_boolFZF_seZrho_0Zrho_1r+6E:\soccer\ml_env\Lib\site-packages\sklearn/isotonic.pyrs3rbothclosedboolean)r sample_weighty_miny_max increasingr1r2r3r4cCst|ddtjtjgd}ttdkrHtj|||d}tj|j |j d}nh|rZtj ddntj ddd}tj |||j d}t |||j d d }t||}t||||}|dus|dur|durtj }|durtj}t|||||S) a0Solve the isotonic regression model. Read more in the :ref:`User Guide `. Parameters ---------- y : array-like of shape (n_samples,) The data. sample_weight : array-like of shape (n_samples,), default=None Weights on each point of the regression. If None, weight is set to 1 (equal weights). y_min : float, default=None Lower bound on the lowest predicted value (the minimum value may still be higher). If not set, defaults to -inf. y_max : float, default=None Upper bound on the highest predicted value (the maximum may still be lower). If not set, defaults to +inf. increasing : bool, default=True Whether to compute ``y_`` is increasing (if set to True) or decreasing (if set to False). Returns ------- y_ : ndarray of shape (n_samples,) Isotonic fit of y. References ---------- "Active set algorithms for isotonic regression; A unifying framework" by Michael J. Best and Nilotpal Chakravarti, section 3. Examples -------- >>> from sklearn.isotonic import isotonic_regression >>> isotonic_regression([5, 3, 1, 2, 8, 10, 7, 9, 6, 4]) array([2.75 , 2.75 , 2.75 , 2.75 , 7.33..., 7.33..., 7.33..., 7.33..., 7.33..., 7.33...]) Fr) ensure_2d input_namedtypez1.12.0)rweightsr4r8NT)r8copy)rr$float64float32rrrrasarrayrr8Zs_arrayrZascontiguousarrayrinfclip)rr1r2r3r4resorderr+r+r,rfs&7 " rcseZdZUdZdejiZdejiZee dddddgee dddddgde dhge hdgd Z e e d <ddd d d d dZddZddZd&ddZed dd'ddZddZddZddZd(ddZfd d!Zfd"d#Zfd$d%ZZS))ra Isotonic regression model. Read more in the :ref:`User Guide `. .. versionadded:: 0.13 Parameters ---------- y_min : float, default=None Lower bound on the lowest predicted value (the minimum value may still be higher). If not set, defaults to -inf. y_max : float, default=None Upper bound on the highest predicted value (the maximum may still be lower). If not set, defaults to +inf. increasing : bool or 'auto', default=True Determines whether the predictions should be constrained to increase or decrease with `X`. 'auto' will decide based on the Spearman correlation estimate's sign. out_of_bounds : {'nan', 'clip', 'raise'}, default='nan' Handles how `X` values outside of the training domain are handled during prediction. - 'nan', predictions will be NaN. - 'clip', predictions will be set to the value corresponding to the nearest train interval endpoint. - 'raise', a `ValueError` is raised. Attributes ---------- X_min_ : float Minimum value of input array `X_` for left bound. X_max_ : float Maximum value of input array `X_` for right bound. X_thresholds_ : ndarray of shape (n_thresholds,) Unique ascending `X` values used to interpolate the y = f(X) monotonic function. .. versionadded:: 0.24 y_thresholds_ : ndarray of shape (n_thresholds,) De-duplicated `y` values suitable to interpolate the y = f(X) monotonic function. .. versionadded:: 0.24 f_ : function The stepwise interpolating function that covers the input domain ``X``. increasing_ : bool Inferred value for ``increasing``. See Also -------- sklearn.linear_model.LinearRegression : Ordinary least squares Linear Regression. sklearn.ensemble.HistGradientBoostingRegressor : Gradient boosting that is a non-parametric model accepting monotonicity constraints. isotonic_regression : Function to solve the isotonic regression model. Notes ----- Ties are broken using the secondary method from de Leeuw, 1977. References ---------- Isotonic Median Regression: A Linear Programming Approach Nilotpal Chakravarti Mathematics of Operations Research Vol. 14, No. 2 (May, 1989), pp. 303-308 Isotone Optimization in R : Pool-Adjacent-Violators Algorithm (PAVA) and Active Set Methods de Leeuw, Hornik, Mair Journal of Statistical Software 2009 Correctness of Kruskal's algorithms for monotone regression with ties de Leeuw, Psychometrica, 1977 Examples -------- >>> from sklearn.datasets import make_regression >>> from sklearn.isotonic import IsotonicRegression >>> X, y = make_regression(n_samples=10, n_features=1, random_state=41) >>> iso_reg = IsotonicRegression().fit(X, y) >>> iso_reg.predict([.1, .2]) array([1.8628..., 3.7256...]) TNr-r.r0auto>rBnanraiser2r3r4 out_of_bounds_parameter_constraintsTrGcCs||_||_||_||_dSNrI)selfr2r3r4rJr+r+r,__init__ szIsotonicRegression.__init__cCs2|jdks.|jdkr"|jddks.d}t|dS)NrzKIsotonic regression input X should be a 1d array or 2d array with 1 feature)ndimshape ValueError)rMXmsgr+r+r,_check_input_data_shape&s"z*IsotonicRegression._check_input_data_shapecs>|jdk}tdkr&fdd|_ntj|d|d|_dS)zBuild the f_ interp1d function.rHrcs |jSrL)repeatrQ)rrr+r,4z-IsotonicRegression._build_f..Zlinear)kind bounds_errorN)rJrf_rZinterp1d)rMrSrr[r+rWr,_build_f.s   zIsotonicRegression._build_fc sV|||d}|jdkr,t|||_n|j|_t|||jd}|dk}||||||}}}t||ffdd|||fD\}}}t |||\}}}|}t |||j |j |jd}t |t||_|_|rJtjt|ftd} tt|dd|d d t|dd|d d | dd<|| || fS||fSd S) z Build the y_ IsotonicRegression.r;rFr:rcsg|] }|qSr+r+).0r@rDr+r, LrYz/IsotonicRegression._build_y..r5rNrO)rUreshaper4rZ increasing_rr8r$Zlexsortr rr2r3minmaxX_min_X_max_Zonesrbool logical_or not_equal) rMrSrr1Ztrim_duplicatesmaskZunique_XZunique_yZunique_sample_weightZ keep_datar+r_r,_build_y:s6    4 zIsotonicRegression._build_yrcCs~tddd}t|fdtjtjgd|}t|fd|jd|}t|||||||\}}|||_|_ | |||S)aFit the model using X, y as training data. Parameters ---------- X : array-like of shape (n_samples,) or (n_samples, 1) Training data. .. versionchanged:: 0.24 Also accepts 2d array with 1 feature. y : array-like of shape (n_samples,) Training target. sample_weight : array-like of shape (n_samples,), default=None Weights. If set to None, all weights will be set to 1 (equal weights). Returns ------- self : object Returns an instance of self. Notes ----- X is stored for future use, as :meth:`transform` needs X to interpolate new input data. F)Z accept_sparser6rS)r7r8r) dictrr$r=r>r8rrk X_thresholds_ y_thresholds_r])rMrSrr1Z check_paramsr+r+r,fitks    zIsotonicRegression.fitcCsrt|dr|jj}ntj}t||dd}|||d}|jdkrXt ||j |j }| |}| |j}|S)a`_transform` is called by both `transform` and `predict` methods. Since `transform` is wrapped to output arrays of specific types (e.g. NumPy arrays, pandas DataFrame), we cannot make `predict` call `transform` directly. The above behaviour could be changed in the future, if we decide to output other type of arrays when calling `predict`. rmF)r8r6r;rB)hasattrrmr8r$r=rrUrbrJrBrerfr\Zastype)rMrEr8rCr+r+r, _transforms       zIsotonicRegression._transformcCs ||S)aTransform new data by linear interpolation. Parameters ---------- T : array-like of shape (n_samples,) or (n_samples, 1) Data to transform. .. versionchanged:: 0.24 Also accepts 2d array with 1 feature. Returns ------- y_pred : ndarray of shape (n_samples,) The transformed data. rqrMrEr+r+r, transformszIsotonicRegression.transformcCs ||S)a%Predict new data by linear interpolation. Parameters ---------- T : array-like of shape (n_samples,) or (n_samples, 1) Data to transform. Returns ------- y_pred : ndarray of shape (n_samples,) Transformed data. rrrsr+r+r,predicts zIsotonicRegression.predictcCs,t|d|jj}tj|dgtdS)aKGet output feature names for transformation. Parameters ---------- input_features : array-like of str or None, default=None Ignored. Returns ------- feature_names_out : ndarray of str objects An ndarray with one string i.e. ["isotonicregression0"]. r\0r:)r __class____name__lowerr$r?object)rMZinput_features class_namer+r+r,get_feature_names_outs  z(IsotonicRegression.get_feature_names_outcst}|dd|S)z0Pickle-protocol - return state of the estimator.r\N)super __getstate__poprMstaterwr+r,r~s  zIsotonicRegression.__getstate__cs4t|t|dr0t|dr0||j|jdS)znPickle-protocol - set state of the estimator. We need to rebuild the interpolation function. rmrnN)r} __setstate__rpr]rmrnrrr+r,rs zIsotonicRegression.__setstate__cst}d|j_d|j_|S)NTF)r}__sklearn_tags__Z input_tagsZ one_d_arrayZ two_d_array)rMtagsrr+r,rs z#IsotonicRegression.__sklearn_tags__)T)N)N)rx __module__ __qualname____doc__rZUNUSEDZ._IsotonicRegression__metadata_request__predictZ0_IsotonicRegression__metadata_request__transformrrrrKrl__annotations__rNrUr]rkr rorqrtrur|r~rr __classcell__r+r+rr,rs* ^     1 1   r)'rr r&numbersrnumpyr$ZscipyrrZ scipy.statsrZ sklearn.utilsrZ _isotonicrr baser r r r utilsrrZutils._param_validationrrrZ utils.fixesrrZutils.validationrr__all__rrrr+r+r+r,sB    E G