a jQ@sdZddlZddlmZddlmZddlZddlm Z ddl m Z ddl m Z d d lmZmZd d lmZmZd#d d Zd$ddZeeedZddZddZddZddZd%ddZd&ddZd'dd Zd!d"ZdS)(zAUtilities to handle multiclass/multioutput target in classifiers.N)Sequence)chain)issparse) get_namespace)VisibleDeprecationWarning) attach_unique cached_unique)_assert_all_finite check_arraycCs<t||d\}}t|ds|r0t|||dSt|SdS)Nxp __array__)rhasattrr asarraysetyris_array_api_compliantr>E:\soccer\ml_env\Lib\site-packages\sklearn/utils/multiclass.py_unique_multiclasssrcCs.t||d\}}|t|dgddjdS)Nr rZcsrZcscZcoo) input_name accept_sparser)rZaranger shape)rr_rrr_unique_indicatorsr)binary multiclassmultilabel-indicatorcs4t|ddi}t|\}t|dkr.tdtdd|D}|ddhkrRdh}t|d krjtd ||}|d krttd d|Dd krtd t|dstdt||r fdd|D} |Stt fdd|D}ttdd|Dd kr&td t|S)aExtract an ordered array of unique labels. We don't allow: - mix of multilabel and multiclass (single label) targets - mix of label indicator matrix and anything else, because there are no explicit labels) - mix of label indicator matrices of different sizes - mix of string and integer labels At the moment, we also don't allow "multiclass-multioutput" input type. Parameters ---------- *ys : array-likes Label values. Returns ------- out : ndarray of shape (n_unique_labels,) An ordered array of unique labels. Examples -------- >>> from sklearn.utils.multiclass import unique_labels >>> unique_labels([3, 5, 5, 5, 7, 7]) array([3, 5, 7]) >>> unique_labels([1, 2, 3, 4], [2, 2, 3, 4]) array([1, 2, 3, 4]) >>> unique_labels([1, 2, 10], [5, 11]) array([ 1, 2, 5, 10, 11]) Z return_tupleTrzNo argument has been passed.css|]}t|VqdSN)type_of_target).0xrrr Oz unique_labels..rr rz'Mix type of y not allowed, got types %sr!css$|]}t|gddjdVqdS)r)rrN)r rr$rrrrr&\szCMulti-label binary indicator input with different numbers of labelsNzUnknown label type: %scsg|]}|dqS)r rr(Z_unique_labelsrrr mr'z!unique_labels..c3s$|]}dd|dDVqdS)css|] }|VqdSr"r)r$irrrr&qr'z*unique_labels...r Nrr(r)rrr&qr'css|]}t|tVqdSr") isinstancestr)r$labelrrrr&tr'z,Mix of label input types (string and number))r rlen ValueErrorrpop_FN_UNIQUE_LABELSgetreprconcat unique_valuesr from_iterablersorted)ZysrZys_typesZ label_typeZ unique_ysZ ys_labelsrr)r unique_labels)sF         r9c Cs@t|\}}||jdo>t|||||j|j|kS)N real floating)risdtypedtypeboolallastypeZint64rrrr_is_integral_floatzs  r@c Cst|\}}t|ds$t|ts$|rtddddddd}ttdtzt |fddi|}WnLtt fy}z0t | d rt |fdt i|}WYd}~n d}~00Wdn1s0Yt|d r|jd kr|jd d ksdSt|rj|jd vr|}||j}t|jdkph|jd ksT|jd kohd|voh|jjdvpht|St||d}|jddko||jdpt|SdS)a~Check if ``y`` is in a multilabel format. Parameters ---------- y : ndarray 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 rTFrrZallow_ndZensure_all_finiteZ ensure_2dZensure_min_samplesZensure_min_featureserrorr<NComplex data not supportedrrr)ZdokZlilZbiur )r=zsigned integerzunsigned integer)rrr,rdictwarningscatch_warnings simplefilterrr r0r- startswithobjectndimrrformatZtocsrr6datar/sizer<kindr@r r;)rrrcheck_y_kwargselabelsrrr is_multilabelsB   H"   " rScCs(t|dd}|dvr$td|ddS)aAEnsure 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 Target values. rr)rr zmulticlass-multioutputr!zmultilabel-sequenceszUnknown label type: zy. Maybe you are trying to fit a classifier, which expects discrete classes on a regression target with continuous values.N)r#r0)rZy_typerrrcheck_classification_targetss  rUFc st\}}fdd}tts8ts8tdrDtt pF|}|sXtdjjdv}|rptdt r|dSt ddd d d d d }t t d ttsztfd di|WnNttfy} z0t| drtfd ti|WYd} ~ n d} ~ 00Wdn1s.0YzltrVd gddfnd } t| trvt dtt| dst| trt| tstdWntyYn0jdvr|StjsjdkrdS|Stsjtkrtjd ts|Sjdkr>jddkr>d} nd} |jdrtrbjn} || || tkrt | dd| St| r| j} t!jd dksЈjdkrt"| dkrd| SdSdS)a Determine 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, sparse matrix} Target values. If a sparse matrix, `y` is expected to be a CSR/CSC matrix. input_name : str, default="" The data name used to construct the error message. .. versionadded:: 1.1.0 raise_unknown : bool, default=False If `True`, raise an error when the type of target returned by :func:`~sklearn.utils.multiclass.type_of_target` is `"unknown"`. .. versionadded:: 1.6 Returns ------- target_type : str 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 -------- >>> from sklearn.utils.multiclass import type_of_target >>> 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]]) 'multilabel-indicator' >>> 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' cs.r&r nd}td|dndSdS)zdDepending on the value of raise_unknown, either raise an error or return 'unknown'. rMzUnknown label type for z: unknownN)r0)inputr raise_unknownrrr_raise_or_return4s z(type_of_target.._raise_or_returnrz:Expected array-like (array or non-string sequence), got %r)Z SparseSeriesZ SparseArrayz1y cannot be class 'SparseSeries' or 'SparseArray'r!TFrrArBr<NrCzSupport for labels represented as bytes is deprecated in v1.5 and will error in v1.7. Convert the labels to a string or integer format.zYou 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 - the MultiLabelBinarizer transformer can convert to this format.)rrrrrz -multioutputrVr:rTZ continuousr )#rr,rrrr-r0 __class____name__rSrErFrGrHrr rIrJbyteswarn FutureWarning IndexErrorrKminrr<Zflatr;rManyr?intr r r/) rrrZrrr[ZvalidZ sparse_pandasrPrQZfirst_row_or_valsuffixrMrrYrr#sM       J$     (  .r#cCsrt|dddur"|dur"tdnL|durnt|dddur`t|jt|sntd||jfnt||_dSdS)a"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``. classes_Nz8classes must be passed on the first call to partial_fit.zD`classes=%r` is not the same as on last call to partial_fit, was: %rTF)getattrr0npZ array_equalrfr9)Zclfclassesrrr_check_partial_fit_first_calls  rjcCsg}g}g}|j\}}|dur(t|}t|rp|}t|j}t|D]}|j|j||j|d} |dur|| } t |t | } nd} |jd||} tj |j |j||j|ddd\} } tj | | d}d| vr|| dk| 7<d| vr@|||jdkr@t | dd} t |d| }|| || jd||| qNnht|D]^}tj |dd|fdd\} } || || jdtj | |d}||| qx|||fS)azCompute class priors from multioutput-multiclass target data. Parameters ---------- y : {array-like, sparse matrix} of size (n_samples, n_outputs) The labels for each example. sample_weight : array-like of shape (n_samples,), default=None Sample weights. Returns ------- classes : list of size n_outputs of ndarray of size (n_classes,) List of classes for each column. n_classes : list of int of size n_outputs Number of classes in each column. class_prior : list of size n_outputs of ndarray of size (n_classes,) Class distribution of each column. NrrT)Zreturn_inverse)weights)rrhrrZtocscdiffZindptrrangeindicessumuniquerMZbincountinsertappend)rZ sample_weightri n_classesZ class_prior n_samplesZ n_outputsZy_nnzkZ col_nonzeroZnz_samp_weightZzeros_samp_weight_sumZ classes_kZy_kZ class_prior_krrrclass_distributionsF         rvc Cs|jd}t||f}t||f}d}t|D]}t|d|D]}|dd|f|dd|f8<|dd|f|dd|f7<||dd|fdk|fd7<||dd|fdk|fd7<|d7}qDq2|dt|d} || S)ayCompute a continuous, tie-breaking OvR decision function from OvO. It is important to include a continuous value, not only votes, to make computing AUC or calibration meaningful. Parameters ---------- predictions : array-like of shape (n_samples, n_classifiers) Predicted classes for each binary classifier. confidences : array-like of shape (n_samples, n_classifiers) Decision functions or predicted probabilities for positive class for each binary classifier. n_classes : int Number of classes. n_classifiers must be ``n_classes * (n_classes - 1 ) / 2``. rrNrD)rrhZzerosrmabs) Z predictionsZ confidencesrsrtZvotesZsum_of_confidencesrur+jZtransformed_confidencesrrr_ovr_decision_functions  $$$$ ry)N)N)rVF)N)N)__doc__rFcollections.abcr itertoolsrnumpyrhZ scipy.sparserZutils._array_apirZ utils.fixesr_uniquer r Z validationr r rrr2r9r@rSrUr#rjrvryrrrrs0       QI J # J