o }Th@sddlmZddlZddlmZddlmZddl m Z ddl m Z dd Z d d Ze d d gd gdddddZddZddZdS))suppressN)sparse) is_scalar_nan)validate_params)_object_dtype_isnancCstttddl}||jur||WdSWdn1s%wYt|rQ|jjdkr;t |}|S|jjdvrKt j |j t d}|St|}|S||k}|S)Nrf)iudtype)r ImportErrorAttributeErrorpandasNAisnarr kindnpisnanzerosshapeboolr)X value_to_maskrXtrT/home/air/segue/gemini/back/venv/lib/python3.10/site-packages/sklearn/utils/_mask.py_get_dense_masks$     rcCs\t|s t||St|j|}|jdkrtjntj}|||j|j f|j t d}|S)aCompute the boolean mask X == value_to_mask. Parameters ---------- X : {ndarray, sparse matrix} of shape (n_samples, n_features) Input data, where ``n_samples`` is the number of samples and ``n_features`` is the number of features. value_to_mask : {int, float} The value which is to be masked in X. Returns ------- X_mask : {ndarray, sparse matrix} of shape (n_samples, n_features) Missing mask. csr)rr ) spissparserdataformat csr_matrix csc_matrixindicescopyindptrrr)rrrsparse_constructor Xt_sparserrr _get_mask&s   r*z array-likez sparse matrix)rmaskT)prefer_skip_nested_validationcCsDt|}t|jtjr|St|dr t|jd}||}|S)asReturn a mask which is safe to use on X. Parameters ---------- X : {array-like, sparse matrix} Data on which to apply mask. mask : array-like Mask to be used on X. Returns ------- mask : ndarray Array that is safe to use on X. Examples -------- >>> from sklearn.utils import safe_mask >>> from scipy.sparse import csr_matrix >>> data = csr_matrix([[1], [2], [3], [4], [5]]) >>> condition = [False, True, True, False, True] >>> mask = safe_mask(data, condition) >>> data[mask].toarray() array([[2], [3], [5]]) toarrayr)rasarray issubdtyper signedintegerhasattraranger)rr+indrrr safe_maskFs # r4cCs4|dkr|t||ddfStjd|jdfdS)aReturn a mask which is safer to use on X than safe_mask. This mask is safer than safe_mask since it returns an empty array, when a sparse matrix is sliced with a boolean mask with all False, instead of raising an unhelpful error in older versions of SciPy. See: https://github.com/scipy/scipy/issues/5361 Also note that we can avoid doing the dot product by checking if the len_mask is not zero in _huber_loss_and_gradient but this is not going to be the bottleneck, since the number of outliers and non_outliers are typically non-zero and it makes the code tougher to follow. Parameters ---------- X : {array-like, sparse matrix} Data on which to apply mask. mask : ndarray Mask to be used on X. len_mask : int The length of the mask. Returns ------- mask : ndarray Array that is safe to use on X. rNr)r)r4rrr)rr+len_maskrrraxis0_safe_slicess r6cCs0|t|kr tdtj|td}d||<|S)aYConvert list of indices to boolean mask. Parameters ---------- indices : list-like List of integers treated as indices. mask_length : int Length of boolean mask to be generated. This parameter must be greater than max(indices). Returns ------- mask : 1d boolean nd-array Boolean array that is True where indices are present, else False. Examples -------- >>> from sklearn.utils._mask import indices_to_mask >>> indices = [1, 2 , 3, 4] >>> indices_to_mask(indices, 5) array([False, True, True, True, True]) z-mask_length must be greater than max(indices)r T)rmax ValueErrorrr)r% mask_lengthr+rrrindices_to_masks r:) contextlibrnumpyrscipyrr_missingr_param_validationrfixesrrr*r4r6r:rrrrs"       & %