ó ‡ˆ\c@sßddlZddlmZddlmZddlmZmZm Z ddl m Z m Z m Z ddlmZmZddlZddlZdd d gZd „Zddded „Zd eee fd „ƒYZdS(iÿÿÿÿN(t interpolate(t spearmanri(t BaseEstimatortTransformerMixintRegressorMixin(tas_float_arrayt check_arraytcheck_consistent_length(t'_inplace_contiguous_isotonic_regressiont _make_uniquetcheck_increasingtisotonic_regressiontIsotonicRegressionc CsÞt||ƒ\}}|dk}|d krÚt|ƒdkrÚdtjd|d|ƒ}dtjt|ƒdƒ}tj|d|ƒ}tj|d|ƒ}tj|ƒtj|ƒkrÚtj dƒqÚn|S( sCDetermine 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, shape=(n_samples,) Training data. y : array-like, 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 igð¿gð?igà?ig\Âõ(\ÿ?swConfidence interval of the Spearman correlation coefficient spans zero. Determination of ``increasing`` may be suspect.(gð¿gð?( Rtlentmathtlogtsqrtttanhtnptsigntwarningstwarn( txtytrhot_tincreasing_booltFtF_setrho_0trho_1((s/lib/python2.7/site-packages/sklearn/isotonic.pyR s" cCs|rtjntjddd…}tj||dtjƒ}|dkrotjt|ƒdtjƒ}ntj||dtjƒ}t||ƒ|dk s°|dk rú|dkrÉtj }n|dkrátj}ntj ||||ƒn||S(s¨Solve the isotonic regression model:: min sum w[i] (y[i] - y_[i]) ** 2 subject to y_min = y_[1] <= y_[2] ... <= y_[n] = y_max where: - y[i] are inputs (real numbers) - y_[i] are fitted - w[i] are optional strictly positive weights (default to 1.0) Read more in the :ref:`User Guide `. Parameters ---------- y : iterable of floats The data. sample_weight : iterable of floats, optional, default: None Weights on each point of the regression. If None, weight is set to 1 (equal weights). y_min : optional, default: None If not None, set the lowest value of the fit to y_min. y_max : optional, default: None If not None, set the highest value of the fit to y_max. increasing : boolean, optional, default: True Whether to compute ``y_`` is increasing (if set to True) or decreasing (if set to False) Returns ------- y_ : list of floats Isotonic fit of y. References ---------- "Active set algorithms for isotonic regression; A unifying framework" by Michael J. Best and Nilotpal Chakravarti, section 3. Niÿÿÿÿtdtype( Rts_tarraytfloat64tNonetonesR Rtinftclip(Rt sample_weightty_minty_maxt increasingtorder((s/lib/python2.7/site-packages/sklearn/isotonic.pyR Ms,& !     cBsteZdZd d edd„Zd d„Zd„Zed„Zd d„Z d„Z d„Z d „Z d „Z RS( sI Isotonic regression model. The isotonic regression optimization problem is defined by:: min sum w_i (y[i] - y_[i]) ** 2 subject to y_[i] <= y_[j] whenever X[i] <= X[j] and min(y_) = y_min, max(y_) = y_max where: - ``y[i]`` are inputs (real numbers) - ``y_[i]`` are fitted - ``X`` specifies the order. If ``X`` is non-decreasing then ``y_`` is non-decreasing. - ``w[i]`` are optional strictly positive weights (default to 1.0) Read more in the :ref:`User Guide `. Parameters ---------- y_min : optional, default: None If not None, set the lowest value of the fit to y_min. y_max : optional, default: None If not None, set the highest value of the fit to y_max. increasing : boolean or string, optional, default: True If boolean, whether or not to fit the isotonic regression with y increasing or decreasing. The string value "auto" determines whether y should increase or decrease based on the Spearman correlation estimate's sign. out_of_bounds : string, optional, default: "nan" The ``out_of_bounds`` parameter handles how x-values outside of the training domain are handled. When set to "nan", predicted y-values will be NaN. When set to "clip", predicted y-values will be set to the value corresponding to the nearest train interval endpoint. When set to "raise", allow ``interp1d`` to throw ValueError. 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. f_ : function The stepwise interpolating function that covers the input domain ``X``. Notes ----- Ties are broken using the secondary method from 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 Leeuw, Hornik, Mair Journal of Statistical Software 2009 Correctness of Kruskal's algorithms for monotone regression with ties Leeuw, Psychometrica, 1977 tnancCs(||_||_||_||_dS(N(R(R)R*t out_of_bounds(tselfR(R)R*R-((s/lib/python2.7/site-packages/sklearn/isotonic.pyt__init__Ôs   cCs(t|jƒdkr$tdƒ‚ndS(NisX should be a 1d array(R tshapet ValueError(R.tXRR'((s/lib/python2.7/site-packages/sklearn/isotonic.pyt_check_fit_dataÛscs…|jd kr*tdj|jƒƒ‚n|jdk}tˆƒdkr`‡fd†|_n!tj|ˆddd |ƒ|_d S( sBuild the f_ interp1d function.traiseR,R&sIThe argument ``out_of_bounds`` must be in 'nan', 'clip', 'raise'; got {0}icsˆj|jƒS(N(trepeatR0(R(R(s/lib/python2.7/site-packages/sklearn/isotonic.pytëstkindtlineart bounds_errorN(R4R,R&(R-R1tformatR tf_Rtinterp1d(R.R2RR9((Rs/lib/python2.7/site-packages/sklearn/isotonic.pyt_build_fßs c CsKt|||ƒg||gD]}t|dtƒ^q\}}t|ƒ}|j|||ƒ|jdkr„t||ƒ|_n |j|_|d k rÝt|dtƒ}|dk}||||||}}}nt j t |ƒƒ}t j ||fƒ}g|||gD]"}||j t jdtƒ^q\}}}t|||ƒ\} } } | |_}t| | |j|jd|jƒ|_}t j|ƒt j|ƒ|_|_|r=t j t |ƒfdtƒ} t jt j|dd!|d ƒt j|dd!|d ƒƒ| dd+|| || fS||fSd S( s Build the y_ IsotonicRegression.t ensure_2dtautoitcopyR*RiiÿÿÿÿiþÿÿÿiN(RRtFalseRR3R*R t increasing_R#RR$R tlexsorttastypeR"R t_X_R R(R)t_y_tmintmaxtX_min_tX_max_tboolt logical_ort not_equal( R.R2RR'ttrim_duplicatesRtmaskR+R!tunique_Xtunique_ytunique_sample_weightt keep_data((s/lib/python2.7/site-packages/sklearn/isotonic.pyt_build_yðs:1    #>  %'cCsB|j|||ƒ\}}|||_|_|j||ƒ|S(sxFit the model using X, y as training data. Parameters ---------- X : array-like, shape=(n_samples,) Training data. y : array-like, shape=(n_samples,) Training target. sample_weight : array-like, shape=(n_samples,), optional, 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 `transform` needs X to interpolate new input data. (RTt _necessary_X_t _necessary_y_R=(R.R2RR'((s/lib/python2.7/site-packages/sklearn/isotonic.pytfit(scCs”t|ƒ}t|jƒdkr0tdƒ‚n|jdkrZtdj|jƒƒ‚n|jdkr‡tj||j|j ƒ}n|j |ƒS(s Transform new data by linear interpolation Parameters ---------- T : array-like, shape=(n_samples,) Data to transform. Returns ------- T_ : array, shape=(n_samples,) The transformed data is.Isotonic regression input should be a 1d arrayR4R,R&sIThe argument ``out_of_bounds`` must be in 'nan', 'clip', 'raise'; got {0}(R4R,R&( RR R0R1R-R:RR&RIRJR;(R.tT((s/lib/python2.7/site-packages/sklearn/isotonic.pyt transformOs  cCs |j|ƒS(s Predict new data by linear interpolation. Parameters ---------- T : array-like, shape=(n_samples,) Data to transform. Returns ------- T_ : array, shape=(n_samples,) Transformed data. (RY(R.RX((s/lib/python2.7/site-packages/sklearn/isotonic.pytpredictjs cCs)tt|ƒjƒ}|jddƒ|S(s1Pickle-protocol - return state of the estimator. R;N(tsuperR t __getstate__tpopR#(R.tstate((s/lib/python2.7/site-packages/sklearn/isotonic.pyR\yscCsQtt|ƒj|ƒt|dƒrMt|dƒrM|j|j|jƒndS(snPickle-protocol - set state of the estimator. We need to rebuild the interpolation function. RURVN(R[R t __setstate__thasattrR=RURV(R.R^((s/lib/python2.7/site-packages/sklearn/isotonic.pyR_€sN(t__name__t __module__t__doc__R#tTrueR/R3R=RTRWRYRZR\R_(((s/lib/python2.7/site-packages/sklearn/isotonic.pyR ‹sH     8 '   (tnumpyRtscipyRt scipy.statsRtbaseRRRtutilsRRRt _isotonicRR RRt__all__R R#RdR R (((s/lib/python2.7/site-packages/sklearn/isotonic.pyts     9  =