hKddlZddlmZddlmZddlmZ ddlm Z ddlm Z dZd Zd Zd Zd d ZdddZdZdZdZdZdZdZdZdZdZdZdZd!dZd"dZ dZ!dZ"dZ#dS)#N)_check_sample_weight)csc_mean_variance_axis0)csr_mean_variance_axis0)incr_mean_variance_axis0c~tj|r|jnt|}d|z}t |)z2Raises a TypeError if X is not a CSR or CSC matrixz,Expected a CSR or CSC sparse matrix, got %s.)spissparseformattype TypeError)X input_typeerrs a/var/www/html/services/rag-service/venv/lib/python3.11/site-packages/sklearn/utils/sparsefuncs.py_raise_typeerrorrs6[^^8aJ 8: EC C..c2|dvrtd|zdS)N)rrz8Unknown axis value: %d. Use 0 for rows, or 1 for columns) ValueErroraxiss r_raise_error_wrong_axisrs/ 6 F M   rc|jd|jdksJ|xj||jdzc_dS)a Inplace column scaling of a CSR matrix. Scale each feature of the data matrix by multiplying with specific scale provided by the caller assuming a (n_samples, n_features) shape. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix to normalize using the variance of the features. It should be of CSR format. scale : ndarray of shape (n_features,), dtype={np.float32, np.float64} Array of precomputed feature-wise values to use for scaling. rrclip)modeN)shapedatatakeindicesrscales rinplace_csr_column_scaler##sG ;q>QWQZ ' ' ' 'FFejjj000FFFFrc|jd|jdksJ|xjtj|tj|jzc_dS)aInplace row scaling of a CSR matrix. Scale each sample of the data matrix by multiplying with specific scale provided by the caller assuming a (n_samples, n_features) shape. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix to be scaled. It should be of CSR format. scale : ndarray of float of shape (n_samples,) Array of precomputed sample-wise values to use for scaling. rN)rrnprepeatdiffindptrr!s rinplace_csr_row_scaler)6sM ;q>QWQZ ' ' ' 'FFbirwqx00111FFFFrFczt|tj|r:|jdkr/|dkrt |||St |j||Stj|r:|jdkr/|dkrt |||St |j||St|dS)a4Compute mean and variance along an axis on a CSR or CSC matrix. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Input data. It can be of CSR or CSC format. axis : {0, 1} Axis along which the axis should be computed. weights : ndarray of shape (n_samples,) or (n_features,), default=None If axis is set to 0 shape is (n_samples,) or if axis is set to 1 shape is (n_features,). If it is set to None, then samples are equally weighted. .. versionadded:: 0.24 return_sum_weights : bool, default=False If True, returns the sum of weights seen for each feature if `axis=0` or each sample if `axis=1`. .. versionadded:: 0.24 Returns ------- means : ndarray of shape (n_features,), dtype=floating Feature-wise means. variances : ndarray of shape (n_features,), dtype=floating Feature-wise variances. sum_weights : ndarray of shape (n_features,), dtype=floating Returned if `return_sum_weights` is `True`. csrr)weightsreturn_sum_weightscscN)rr r r _csr_mean_var_axis0_csc_mean_var_axis0Tr)rrr,r-s rmean_variance_axisr2HsHD!!! {1~~!(e++ 199&77I 'W9K  Q AH-- 199&77I 'W9K  r)r,cpt|tj|r |jdvst |t j|dkr!t j|j||j }t j|t j|cxkrt j|ksntd|dkrWt j||jdkr3td|jddt j|dnVt j||jdkr3td |jddt j|d|dkr|j n|}|t|||j }t||||| S) a7 Compute incremental mean and variance along an axis on a CSR or CSC matrix. last_mean, last_var are the statistics computed at the last step by this function. Both must be initialized to 0-arrays of the proper size, i.e. the number of features in X. last_n is the number of samples encountered until now. Parameters ---------- X : CSR or CSC sparse matrix of shape (n_samples, n_features) Input data. axis : {0, 1} Axis along which the axis should be computed. last_mean : ndarray of shape (n_features,) or (n_samples,), dtype=floating Array of means to update with the new data X. Should be of shape (n_features,) if axis=0 or (n_samples,) if axis=1. last_var : ndarray of shape (n_features,) or (n_samples,), dtype=floating Array of variances to update with the new data X. Should be of shape (n_features,) if axis=0 or (n_samples,) if axis=1. last_n : float or ndarray of shape (n_features,) or (n_samples,), dtype=floating Sum of the weights seen so far, excluding the current weights If not float, it should be of shape (n_features,) if axis=0 or (n_samples,) if axis=1. If float it corresponds to having same weights for all samples (or features). weights : ndarray of shape (n_samples,) or (n_features,), default=None If axis is set to 0 shape is (n_samples,) or if axis is set to 1 shape is (n_features,). If it is set to None, then samples are equally weighted. .. versionadded:: 0.24 Returns ------- means : ndarray of shape (n_features,) or (n_samples,), dtype=floating Updated feature-wise means if axis = 0 or sample-wise means if axis = 1. variances : ndarray of shape (n_features,) or (n_samples,), dtype=floating Updated feature-wise variances if axis = 0 or sample-wise variances if axis = 1. n : ndarray of shape (n_features,) or (n_samples,), dtype=integral Updated number of seen samples per feature if axis=0 or number of seen features per sample if axis=1. If weights is not None, n is a sum of the weights of the seen samples or features instead of the actual number of seen samples or features. Notes ----- NaNs are ignored in the algorithm. )r.r+r)dtypez8last_mean, last_var, last_n do not have the same shapes.rzHIf axis=1, then last_mean, last_n, last_var should be of size n_samples z (Got z).zIIf axis=0, then last_mean, last_n, last_var should be of size n_features N) last_meanlast_varlast_nr,)rr r r rr%sizefullrr4rr1r_incr_mean_var_axis0)rrr5r6r7r,s rincr_mean_variance_axisr;sxD!!! KNNqx>99 wv!& HHH GI  "'("3"3 F F F Frwv F F F FSTTT qyy 79   + +K"#'!*KK46GI4F4FKKK  , 79   + +L#$71:LL57WY5G5GLLL  qyyaA&wAAA  Y&'   rctj|r"|jdkrt|j|dStj|r|jdkrt ||dSt |dS)aInplace column scaling of a CSC/CSR matrix. Scale each feature of the data matrix by multiplying with specific scale provided by the caller assuming a (n_samples, n_features) shape. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix to normalize using the variance of the features. It should be of CSC or CSR format. scale : ndarray of shape (n_features,), dtype={np.float32, np.float64} Array of precomputed feature-wise values to use for scaling. r.r+N)r r r r)r1r#rr!s rinplace_column_scaler=s~ {1~~!(e++ac5))))) QAH-- E*****rctj|r"|jdkrt|j|dStj|r|jdkrt ||dSt |dS)aInplace row scaling of a CSR or CSC matrix. Scale each row of the data matrix by multiplying with specific scale provided by the caller assuming a (n_samples, n_features) shape. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix to be scaled. It should be of CSR or CSC format. scale : ndarray of shape (n_features,), dtype={np.float32, np.float64} Array of precomputed sample-wise values to use for scaling. r.r+N)r r r r#r1r)rr!s rinplace_row_scaler?s~ {1~~!(e++ e,,,,, QAH--a'''''rc||fD]+}t|tjrtd,|dkr||jdz }|dkr||jdz }|j|k}||j|j|k<||j|<dS)aKSwap two rows of a CSC matrix in-place. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix whose two rows are to be swapped. It should be of CSC format. m : int Index of the row of X to be swapped. n : int Index of the row of X to be swapped. m and n should be valid integersrN) isinstancer%ndarrayrrr )rmntm_masks rinplace_swap_row_cscrHsV@@ a $ $ @>?? ? @ 1uu QWQZ1uu QWQZ Y!^F !AIai1nAIfrc <||fD]+}t|tjrtd,|dkr||jdz }|dkr||jdz }||kr||}}|j}||}||dz}||}||dz}||z } ||z } | | kr:|j|dz|xx| | z z cc<|| z|j|dz<|| z |j|<tj|jd||j|||j|||j|||j|dg|_tj|jd||j|||j|||j|||j|dg|_dS)aKSwap two rows of a CSR matrix in-place. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix whose two rows are to be swapped. It should be of CSR format. m : int Index of the row of X to be swapped. n : int Index of the row of X to be swapped. rArrrN) rBr%rCrrr( concatenater r) rrDrErFr(m_startm_stopn_startn_stopnz_mnz_ns rinplace_swap_row_csrrQ,sV@@ a $ $ @>?? ? @ 1uu QWQZ1uu QWQZ 1uu!1 XFQiG AE]FQiG AE]F G D G D t|| Qtd{*!D.Qtm  Ihwh  Igfn % IfWn % Igfn % Ifgg   AI^ F8G8  F76> " F6'> " F76> " F677O  AFFFrctj|r|jdkrt|||dStj|r|jdkrt |||dSt |dS)a[ Swap two rows of a CSC/CSR matrix in-place. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix whose two rows are to be swapped. It should be of CSR or CSC format. m : int Index of the row of X to be swapped. n : int Index of the row of X to be swapped. r.r+N)r r r rHrQrrrDrEs rinplace_swap_rowrTks  {1~~!(e++Q1%%%%% QAH--Q1%%%%%rcD|dkr||jdz }|dkr||jdz }tj|r|jdkrt |||dStj|r|jdkrt |||dSt |dS)ag Swap two columns of a CSC/CSR matrix in-place. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix whose two columns are to be swapped. It should be of CSR or CSC format. m : int Index of the column of X to be swapped. n : int Index of the column of X to be swapped. rrr.r+N)rr r r rQrHrrSs rinplace_swap_columnrVs  1uu QWQZ1uu QWQZ {1~~!(e++Q1%%%%% QAH--Q1%%%%%rctjtj|j}t ||j|j|jf|j}||j|j|}||fS)N)r) r% flatnonzeror'r(r rr rreduceat)rufunc major_indexvalues r _minor_reducer]so.!2!233K QAH-QW===A NN1618K#8 9 9E  rc $|j|}|dkrtd|jd|z }|dkr|n|}|t ||\}}t j|j||k}|||d||<|dk} t j | |}t j | |}|dkrBtj |t j t||ff|jd|f} nAtj ||t j t|ff|j|df} | jS)Nr&zero-size array to reduction operationr)r4r)rrtocsctocsrsum_duplicatesr]r%r'r(compressr coo_matrixzeroslenr4Aravel) rr min_or_maxNMmatr[r\not_fullmaskress r_min_or_max_axisrpsx  AAvvABBB DAqyy!'')))aggiiC&sJ77Kwsz"";/!3H jx!44E(O A:D+dK00K Ke $ $E qyym RXc%jj));7 8PQSTv   m ["(3u::"6"67 8PQSTv    5;;==rc|d|jvrtd|jd}|jdkr|S||j}|jtj |jkr |||}|S|dkr|dz }|dks|dkrt|||Std)Nrr_rrz.invalid axis, use 0 for rows, or 1 for columns) rrr4r nnzreducerrhr%prodrp)rrrizerorDs r_sparse_min_or_maxrvs | <<EFF Fw||A 5A::K   afllnn - - 5BGAG$$ $ $ 4##A axx    tqyy4444IJJJrcnt||tjt||tjfSN)rvr%minimummaximumrrs r_sparse_min_maxr|s.1dBJ//1dBJ// rcnt||tjt||tjfSrx)rvr%fminfmaxr{s r_sparse_nan_min_maxrs* q$ 0 02DQbg2V2V WWrctj|r-|jdvr$|rt||St ||St |dS)aCompute minimum and maximum along an axis on a CSR or CSC matrix. Optionally ignore NaN values. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Input data. It should be of CSR or CSC format. axis : {0, 1} Axis along which the axis should be computed. ignore_nan : bool, default=False Ignore or passing through NaN values. .. versionadded:: 0.20 Returns ------- mins : ndarray of shape (n_features,), dtype={np.float32, np.float64} Feature-wise minima. maxs : ndarray of shape (n_features,), dtype={np.float32, np.float64} Feature-wise maxima. )r+r.rN)r r r rr|r)rr ignore_nans r min_max_axisrsb6 {1~~!(n44  1&qt444 4"14000 0rc|dkrd}n;|dkrd}n2|jdkr'td|j|5||jStjtj|j|S|dkr5tj|j}||dS||zS|dkr{|&tj|j |j d Stj |tj|j}tj|j |j d| Std |) aA variant of X.getnnz() with extension to weighting on axis 0. Useful in efficiently calculating multilabel metrics. Parameters ---------- X : sparse matrix of shape (n_samples, n_labels) Input data. It should be of CSR format. axis : {0, 1}, default=None The axis on which the data is aggregated. sample_weight : array-like of shape (n_samples,), default=None Weight for each row of X. Returns ------- nnz : int, float, ndarray of shape (n_samples,) or ndarray of shape (n_features,) Number of non-zero values in the array along a given axis. Otherwise, the total number of non-zero values in the array is returned. rrr+z#Expected CSR sparse format, got {0}Nintp) minlength)rr,zUnsupported axis: {0}) r rrrr%dotr'r(astypebincountr rr&r)rr sample_weightoutr,s r count_nonzerorsD, rzz  U  =DDQXNNOOO  |  5L6"'!(++];; ; gah  ::f%% %]""   ;qyAGAJ??? ?i rwqx/@/@AAG;qyAGAJPPP P077==>>>rc>t||z}|s tjStj|dk}t |d\}}||rt ||||St |dz |||t ||||zdz S)zCompute the median of data with n_zeros additional zeros. This function is used to support sparse matrices; it modifies data in-place. rrrg@)rfr%nanrdivmodsort_get_elem_at_rank)rn_zerosn_elems n_negativemiddleis_odds r _get_medianr;s $ii'!G v !$(++JGQ''NFFIIKKK D z7CCC &1*dJ@@ FD*g > > ?   rcJ||kr||S||z |krdS|||z S)z@Find the value in data augmented with n_zeros for the given rankr)rankrrrs rrrQs; jDz j7""q w rctj|r |jdkstd|jz|j}|j\}}t j|}tt|dd|ddD]F\}\}}t j |j ||}||j z } t|| ||<G|S)aCFind the median across axis 0 of a CSC matrix. It is equivalent to doing np.median(X, axis=0). Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Input data. It should be of CSC format. Returns ------- median : ndarray of shape (n_features,) Median. r.z%Expected matrix of CSC format, got %sNrr)r r r rr(rr%re enumeratezipcopyrr8r) rr( n_samples n_featuresmedianf_indstartendrnzs rcsc_median_axis_0rZs KNNLqx500?!(JKKK XFGIz Xj ! !F(VCRC[&*)E)EFF..|swqveCi())  "#D"--u Mr)NF)F)NN)$numpyr% scipy.sparsesparser utils.validationrsparsefuncs_fastrr0rr/rr:rrr#r)r2r;r=r?rHrQrTrVr]rprvr|rrrrrrrrrrs 333333    111&222$9999xNR[[[[[|.,:<<<~082KKK&XXX!!!!H3?3?3?3?l   ,   r