ó ‡ˆ\c@ s!dZddlmZddlmZddlmZddlmZddlm Z ddlm Z ddl Z d d l mZd d lmZd d lmZd„Zd„Zied6ed6ed6Zd„Zd„Zd„Zd„Zd„Zdd„Zdd„Zd„ZdS(sX Multi-class / multi-label utility function ========================================== iÿÿÿÿ(tdivision(tchain(tissparse(tspmatrix(t dok_matrix(t lil_matrixNi(t string_types(t _Sequencei(t check_arraycC s3t|dƒr%tjtj|ƒƒSt|ƒSdS(Nt __array__(thasattrtnptuniquetasarraytset(ty((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pyt_unique_multiclassscC s&tjt|dddgƒjdƒS(Ntcsrtcsctcooi(R tarangeRtshape(R((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pyt_unique_indicatorstbinaryt multiclasssmultilabel-indicatorc s]|stdƒ‚ntd„|Dƒƒ}|tddgƒkrUtdgƒ}nt|ƒdkrztd|ƒ‚n|jƒ}|dkrÃttd„|DƒƒƒdkrÃtd ƒ‚ntj|dƒ‰ˆsôtd t|ƒƒ‚nttj ‡fd †|Dƒƒƒ}ttd „|DƒƒƒdkrJtd ƒ‚nt j t |ƒƒS(syExtract an ordered array of unique labels We don't allow: - mix of multilabel and multiclass (single label) targets - mix of label indicator matrix and anything else, because there are no explicit labels) - mix of label indicator matrices of different sizes - mix of string and integer labels At the moment, we also don't allow "multiclass-multioutput" input type. Parameters ---------- *ys : array-likes Returns ------- out : numpy array of shape [n_unique_labels] An ordered array of unique labels. Examples -------- >>> from sklearn.utils.multiclass import unique_labels >>> unique_labels([3, 5, 5, 5, 7, 7]) array([3, 5, 7]) >>> unique_labels([1, 2, 3, 4], [2, 2, 3, 4]) array([1, 2, 3, 4]) >>> unique_labels([1, 2, 10], [5, 11]) array([ 1, 2, 5, 10, 11]) sNo argument has been passed.cs s|]}t|ƒVqdS(N(ttype_of_target(t.0tx((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pys MsRRis'Mix type of y not allowed, got types %ssmultilabel-indicatorcs s.|]$}t|dddgƒjdVqdS(RRRiN(RR(RR((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pys XssCMulti-label binary indicator input with different numbers of labelssUnknown label type: %sc3 s|]}ˆ|ƒVqdS(N((RR(t_unique_labels(s7lib/python2.7/site-packages/sklearn/utils/multiclass.pys bscs s|]}t|tƒVqdS(N(t isinstanceR(Rtlabel((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pys ess,Mix of label input types (string and number)N( t ValueErrorRtlentpopt_FN_UNIQUE_LABELStgettNonetreprRt from_iterableR tarraytsorted(tystys_typest label_typet ys_labels((Rs7lib/python2.7/site-packages/sklearn/utils/multiclass.pyt unique_labels*s&   %"cC s.|jjdko-tj|jtƒ|kƒS(Ntf(tdtypetkindR talltastypetint(R((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pyt_is_integral_floatkscC st|dƒr!tj|ƒ}nt|dƒoO|jdkoO|jddksVtSt|ƒrÞt|tt fƒr†|j ƒ}nt |j ƒdkpÝtj |j ƒjdkoÝ|jjdkpÝttj |j ƒƒStj |ƒ}t |ƒdko|jjdkpt|ƒSdS( sƒ Check if ``y`` is in a multilabel format. Parameters ---------- y : numpy array of shape [n_samples] Target values. Returns ------- out : bool, Return ``True``, if ``y`` is in a multilabel format, else ```False``. Examples -------- >>> import numpy as np >>> from sklearn.utils.multiclass import is_multilabel >>> is_multilabel([0, 1, 0, 1]) False >>> is_multilabel([[1], [0, 2], []]) False >>> is_multilabel(np.array([[1, 0], [0, 0]])) True >>> is_multilabel(np.array([[1], [0], [0]])) False >>> is_multilabel(np.array([[1, 0, 0]])) True R RiiitbiuiN(R R R tndimRtFalseRRRRttocsrR tdataR tsizeR/R0R4(Rtlabels((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pyt is_multilabelos1 0$cC s/t|ƒ}|dkr+td|ƒ‚ndS( s*Ensure that target y is of a non-regression type. Only the following target types (as defined in type_of_target) are allowed: 'binary', 'multiclass', 'multiclass-multioutput', 'multilabel-indicator', 'multilabel-sequences' Parameters ---------- y : array-like RRsmulticlass-multioutputsmultilabel-indicatorsmultilabel-sequencessUnknown label type: %rN(RRsmulticlass-multioutputsmultilabel-indicatorsmultilabel-sequences(RR(Rty_type((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pytcheck_classification_targetss  cC s2t|ttfƒs$t|dƒo1t|tƒ }|sMtd|ƒ‚n|jjdk}|rttdƒ‚nt|ƒr„dSyt j |ƒ}Wntk r«dSXyNt|ddƒ rùt|dtƒrùt|dtƒ rùtdƒ‚nWnt k r nX|j d ksO|j tkrSt|ƒrSt|jdtƒ rSdS|j d kry|jd dkrydS|j d kr¤|jd d kr¤d }nd }|j jd krât j||jtƒkƒrâd|Stt j|ƒƒd ks"|j d kr*t|dƒd kr*d|SdSdS(sìDetermine the type of data indicated by the target. Note that this type is the most specific type that can be inferred. For example: * ``binary`` is more specific but compatible with ``multiclass``. * ``multiclass`` of integers is more specific but compatible with ``continuous``. * ``multilabel-indicator`` is more specific but compatible with ``multiclass-multioutput``. Parameters ---------- y : array-like Returns ------- target_type : string One of: * 'continuous': `y` is an array-like of floats that are not all integers, and is 1d or a column vector. * 'continuous-multioutput': `y` is a 2d array of floats that are not all integers, and both dimensions are of size > 1. * 'binary': `y` contains <= 2 discrete values and is 1d or a column vector. * 'multiclass': `y` contains more than two discrete values, is not a sequence of sequences, and is 1d or a column vector. * 'multiclass-multioutput': `y` is a 2d array that contains more than two discrete values, is not a sequence of sequences, and both dimensions are of size > 1. * 'multilabel-indicator': `y` is a label indicator matrix, an array of two dimensions with at least two columns, and at most 2 unique values. * 'unknown': `y` is array-like but none of the above, such as a 3d array, sequence of sequences, or an array of non-sequence objects. Examples -------- >>> import numpy as np >>> type_of_target([0.1, 0.6]) 'continuous' >>> type_of_target([1, -1, -1, 1]) 'binary' >>> type_of_target(['a', 'b', 'a']) 'binary' >>> type_of_target([1.0, 2.0]) 'binary' >>> type_of_target([1, 0, 2]) 'multiclass' >>> type_of_target([1.0, 0.0, 3.0]) 'multiclass' >>> type_of_target(['a', 'b', 'c']) 'multiclass' >>> type_of_target(np.array([[1, 2], [3, 1]])) 'multiclass-multioutput' >>> type_of_target([[1, 2]]) 'multiclass-multioutput' >>> type_of_target(np.array([[1.5, 2.0], [3.0, 1.6]])) 'continuous-multioutput' >>> type_of_target(np.array([[0, 1], [1, 1]])) 'multilabel-indicator' R s:Expected array-like (array or non-string sequence), got %rt SparseSeriess!y cannot be class 'SparseSeries'.smultilabel-indicatortunknownisœYou appear to be using a legacy multi-label data representation. Sequence of sequences are no longer supported; use a binary array or sparse matrix instead.iis -multioutputtR.t continuousRRN(RtSequenceRR RRt __class__t__name__R<R R t IndexErrorR6R/tobjectR tflatRR0tanyR2R3R (Rtvalidt sparseseriestsuffix((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pyR®sB@$   ' *"" 0@cC s«t|ddƒdkr3|dkr3tdƒ‚nt|dk r§t|ddƒdk r‘tj|jt|ƒƒs¤td||jfƒ‚q¤q§t|ƒ|_tSntS(s!Private helper function for factorizing common classes param logic Estimators that implement the ``partial_fit`` API need to be provided with the list of possible classes at the first call to partial_fit. Subsequent calls to partial_fit should check that ``classes`` is still consistent with a previous value of ``clf.classes_`` when provided. This function returns True if it detects that this was the first call to ``partial_fit`` on ``clf``. In that case the ``classes_`` attribute is also set on ``clf``. tclasses_s8classes must be passed on the first call to partial_fit.sD`classes=%r` is not the same as on last call to partial_fit, was: %rN( tgetattrR$RR t array_equalRMR-tTrueR7(tclftclasses((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pyt_check_partial_fit_first_call%s$ cC sug}g}g}|j\}}t|ƒrÙ|jƒ}tj|jƒ}xt|ƒD]z}|j|j||j|d!} |dk r¾tj |ƒ| } tj |ƒtj | ƒ} nd} |jd||} tj |j |j||j|d!dt ƒ\} } tj| d| ƒ}d| krJ|| dkc| 7RR$RSRlR}(((s7lib/python2.7/site-packages/sklearn/utils/multiclass.pyts0     A  .  w # J