ó ‡ˆ\c@`s½ddlmZmZddlZddlZddlZddlmZddl m Z m Z ddl m Z ddl mZdd l mZdd lmZd e e fd „ƒYZdS( i(tdivisiontabsolute_importNi(t OneHotEncoderi(t BaseEstimatortTransformerMixin(t check_array(tcheck_is_fitted(t FLOAT_DTYPES(t np_versiontKBinsDiscretizercB`sGeZdZdddd„Zd d„Zd„Zd„Zd„ZRS( s Bin continuous data into intervals. Read more in the :ref:`User Guide `. Parameters ---------- n_bins : int or array-like, shape (n_features,) (default=5) The number of bins to produce. Raises ValueError if ``n_bins < 2``. encode : {'onehot', 'onehot-dense', 'ordinal'}, (default='onehot') Method used to encode the transformed result. onehot Encode the transformed result with one-hot encoding and return a sparse matrix. Ignored features are always stacked to the right. onehot-dense Encode the transformed result with one-hot encoding and return a dense array. Ignored features are always stacked to the right. ordinal Return the bin identifier encoded as an integer value. strategy : {'uniform', 'quantile', 'kmeans'}, (default='quantile') Strategy used to define the widths of the bins. uniform All bins in each feature have identical widths. quantile All bins in each feature have the same number of points. kmeans Values in each bin have the same nearest center of a 1D k-means cluster. Attributes ---------- n_bins_ : int array, shape (n_features,) Number of bins per feature. Bins whose width are too small (i.e., <= 1e-8) are removed with a warning. bin_edges_ : array of arrays, shape (n_features, ) The edges of each bin. Contain arrays of varying shapes ``(n_bins_, )`` Ignored features will have empty arrays. Examples -------- >>> X = [[-2, 1, -4, -1], ... [-1, 2, -3, -0.5], ... [ 0, 3, -2, 0.5], ... [ 1, 4, -1, 2]] >>> est = KBinsDiscretizer(n_bins=3, encode='ordinal', strategy='uniform') >>> est.fit(X) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE KBinsDiscretizer(...) >>> Xt = est.transform(X) >>> Xt # doctest: +SKIP array([[ 0., 0., 0., 0.], [ 1., 1., 1., 0.], [ 2., 2., 2., 1.], [ 2., 2., 2., 2.]]) Sometimes it may be useful to convert the data back into the original feature space. The ``inverse_transform`` function converts the binned data into the original feature space. Each value will be equal to the mean of the two bin edges. >>> est.bin_edges_[0] array([-2., -1., 0., 1.]) >>> est.inverse_transform(Xt) array([[-1.5, 1.5, -3.5, -0.5], [-0.5, 2.5, -2.5, -0.5], [ 0.5, 3.5, -1.5, 0.5], [ 0.5, 3.5, -1.5, 1.5]]) Notes ----- In bin edges for feature ``i``, the first and last values are used only for ``inverse_transform``. During transform, bin edges are extended to:: np.concatenate([-np.inf, bin_edges_[i][1:-1], np.inf]) You can combine ``KBinsDiscretizer`` with :class:`sklearn.compose.ColumnTransformer` if you only want to preprocess part of the features. ``KBinsDiscretizer`` might produce constant features (e.g., when ``encode = 'onehot'`` and certain bins do not contain any data). These features can be removed with feature selection algorithms (e.g., :class:`sklearn.feature_selection.VarianceThreshold`). See also -------- sklearn.preprocessing.Binarizer : class used to bin values as ``0`` or ``1`` based on a parameter ``threshold``. itonehottquantilecC`s||_||_||_dS(N(tn_binstencodetstrategy(tselfR R R((sDlib/python2.7/site-packages/sklearn/preprocessing/_discretization.pyt__init__ws  cC`söt|ddƒ}d}|j|krEtdj||jƒƒ‚nd}|j|krxtd j||jƒƒ‚n|jd }|j|ƒ}tj|dt ƒ}x´t |ƒD]¦}|d d …|f} | j ƒ| j ƒ} } | | kr8t jd |ƒd ||sqBins whose width are too small (i.e., <= 1e-8) in feature %d are removed. Consider decreasing the number of bins.t categoriestsparse(R s onehot-denseR(RR R(ii (R R(%RR t ValueErrortformatRtshapet_validate_n_binstnptzerostobjecttrangetmintmaxtwarningstwarntarraytinftlinspaceRtlisttasarrayt percentiletclusterRtNonetfittcluster_centers_tsorttr_tediff1dtlent bin_edges_tn_bins_Rtaranget_encodertint(RtXtyt valid_encodetvalid_strategyt n_featuresR t bin_edgestjjtcolumntcol_mintcol_maxt quantilesRt uniform_edgesRtkmtcenterstmaskti((sDlib/python2.7/site-packages/sklearn/preprocessing/_discretization.pyR1|sh       $ "&2 !" "  %1cC`si|j}t|tjƒr t|tjtjfƒs]tdjt j t |ƒj ƒƒ‚n|dkr‡tdjt j |ƒƒ‚ntj ||dtj ƒSt|dtj dtdtƒ}|jdksã|jd|kròtd ƒ‚n|dk||kB}tj|ƒd}|jddkred jd „|Dƒƒ}td jt j |ƒƒ‚n|S( s9Returns n_bins_, the number of bins per feature. s>{} received an invalid n_bins type. Received {}, expected int.isH{} received an invalid number of bins. Received {}, expected at least 2.Rtcopyt ensure_2diis8n_bins must be a scalar or array of shape (n_features,).s, cs`s|]}t|ƒVqdS(N(tstr(t.0RK((sDlib/python2.7/site-packages/sklearn/preprocessing/_discretization.pys ðssk{} received an invalid number of bins at indices {}. Number of bins must be at least 2, and must be an int.(R t isinstancetnumberstNumbertIntegralR!tintegerRRR t__name__ttypetfullR;RtTruetFalsetndimRtwheretjoin(RR@t orig_binsR tbad_nbins_valuetviolating_indicestindices((sDlib/python2.7/site-packages/sklearn/preprocessing/_discretization.pyR Õs*     " c C`sHt|dgƒt|dtdtƒ}|jjd}|jd|krmtdj||jdƒƒ‚n|j}xŒt |jdƒD]w}d}d}||t j |d d …|fƒ}t j |d d …|f|||dƒ|d d …|fg:Œ0âŽyE>NtoutR(RRRXRR8RRRR7R$R!tabstdigitizetclipR R:t transform( RR<tXtR@RARBtrtoltatolteps((sDlib/python2.7/site-packages/sklearn/preprocessing/_discretization.pyRe÷s   'B cC`st|dgƒd|jkr4|jj|ƒ}nt|dtdtƒ}|jjd}|jd|kr‘t dj ||jdƒƒ‚nxjt |ƒD]\}|j |}|d|d d }|t j|d d …|fƒ|d d …|fs