o tBh)J@sddlmZddlZddlmZmZ m Z ddl m Z ddZdd Zd d Zd d Zd4ddZddddZddZddZddZddZddZddZd d!Zd"d#Zd$d%Zd&d'Zd(d)Zd5d*d+Zd6d,d-Z d.d/Z!d0d1Z"d2d3Z#dS)7N)csr_mean_variance_axis0csc_mean_variance_axis0incr_mean_variance_axis0)_check_sample_weightcCs(t|r|jnt|}d|}t|)z2Raises a TypeError if X is not a CSR or CSC matrixz,Expected a CSR or CSC sparse matrix, got %s.)spissparseformattype TypeError)X input_typeerrrp/var/www/html/riverr-enterprise-integrations-main/venv/lib/python3.10/site-packages/sklearn/utils/sparsefuncs.py_raise_typeerrorsrcCs|dvr td|dS)N)rrz8Unknown axis value: %d. Use 0 for rows, or 1 for columns) ValueErroraxisrrr_raise_error_wrong_axiss rcCs6|jd|jdks J|j|j|jdd9_dS)a Inplace column scaling of a CSR matrix. Scale each feature of the data matrix by multiplying with specific scale provided by the caller assuming a (n_samples, n_features) shape. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix to normalize using the variance of the features. It should be of CSR format. scale : ndarray of shape (n_features,), dtype={np.float32, np.float64} Array of precomputed feature-wise values to use for scaling. rrclip)modeN)shapedatatakeindicesr scalerrrinplace_csr_column_scalesrcCs:|jd|jdks J|jt|t|j9_dS)aInplace row scaling of a CSR matrix. Scale each sample of the data matrix by multiplying with specific scale provided by the caller assuming a (n_samples, n_features) shape. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix to be scaled. It should be of CSR format. scale : ndarray of float of shape (n_samples,) Array of precomputed sample-wise values to use for scaling. rN)rrnprepeatdiffindptrrrrrinplace_csr_row_scale2s"r$FcCsxt|t|tjr|dkrt|||dSt|j||dSt|tjr6|dkr.t|||dSt|j||dSt|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`. r)weightsreturn_sum_weightsN) r isinstancer csr_matrix_csr_mean_var_axis0_csc_mean_var_axis0T csc_matrixr)r rr%r&rrrmean_variance_axisDs$$   r-)r%cCs,t|t|tjtjfst|t|dkr"tj|j ||j d}t|t|kr8t|ks=t dt d|dkr]t||j dkr\t d|j ddt|dnt||j dkrxt d|j ddt|d|dkr|j n|}|d urt |||j d}t|||||d S) a; 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_samples,) if axis=0 or (n_features,) 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)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'rr(r,rr sizefullrr.rr+r_incr_mean_var_axis0)r rr/r0r1r%rrrincr_mean_variance_axissB=$ r5cCBt|tjrt|j|dSt|tjrt||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. N)r'rr,r$r+r(rrrrrrinplace_column_scales   r7cCr6)aInplace row scaling of a CSR or CSC matrix. Scale each row of the data matrix by multiplying with specific scale provided by the caller assuming a (n_samples, n_features) shape. Parameters ---------- X : sparse matrix of shape (n_samples, n_features) Matrix to be scaled. It should be of CSR or CSC format. scale : ndarray of shape (n_features,), dtype={np.float32, np.float64} Array of precomputed sample-wise values to use for scaling. N)r'rr,rr+r(r$rrrrrinplace_row_scales   r8cCsv||fD] }t|tjrtdq|dkr||jd7}|dkr'||jd7}|j|k}||j|j|k<||j|<dS)aQ Swaps 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)r'r ndarrayr rr)r mntm_maskrrrinplace_swap_row_csc s   r?c Csx||fD] }t|tjrtdq|dkr||jd7}|dkr'||jd7}||kr0||}}|j}||}||d}||}||d}||} ||} | | krr|j|d|| | 7<|| |j|d<|| |j|<t|jd||j|||j|||j|||j|dg|_t|jd||j|||j|||j|||j|dg|_dS)aQ Swaps 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. r9rrrN) r'r r:r rr# concatenaterr) r r;r<r=r#m_startm_stopn_startn_stopnz_mnz_nrrrinplace_swap_row_csr*sJ                rGcCsDt|tjrt|||dSt|tjrt|||dSt|dS)a\ Swaps 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. N)r'rr,r?r(rGrr r;r<rrrinplace_swap_rowjs   rIcCsp|dkr ||jd7}|dkr||jd7}t|tjr$t|||dSt|tjr2t|||dSt|dS)ah Swaps 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. rrN)rr'rr,rGr(r?rrHrrrinplace_swap_columns   rJcCsLtt|j}t||j|j|jf|jd}||j|j|}||fS)N)r) r flatnonzeror"r#r rrrreduceat)r ufunc major_indexvaluerrr _minor_reducesrPc Cs|j|}|dkr td|jd|}|dkr|n|}|t||\}}t|j||k}|||d||<|dk} t | |}t | |}|dkrgt j |t t ||ff|jd|fd} nt j ||t t |ff|j|dfd} | jS)Nr&zero-size array to reduction operationr)r.r)rrtocsctocsrsum_duplicatesrPr r"r#compressr coo_matrixzeroslenr.Aravel) r r min_or_maxNMmatrNrOnot_fullmaskresrrr_min_or_max_axiss(    rbcCs|dur2d|jvr td|jd}|jdkr|S||j}|jt |jkr0|||}|S|dkr:|d7}|dksB|dkrHt |||Std)NrrQrrz.invalid axis, use 0 for rows, or 1 for columns) rrr.r nnzreducerrZr productrb)r rr[zeror;rrr_sparse_min_or_maxs     rgcCt||tjt||tjfSN)rgr minimummaximumr rrrr_sparse_min_maxs  rmcCrhri)rgr fminfmaxrlrrr_sparse_nan_min_maxsrpcCs:t|tjtjfr|rt||dSt||dSt|dS)aCompute minimium 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. rN)r'rr(r,rprmr)r r ignore_nanrrr min_max_axiss    rrcCs|dkrd}n|dkrd}n |jdkrtd|j|dur0|dur&|jStt|j|S|dkrGt|j}|durC|dS||S|dkrp|durZtj|j |j dd St |t|j}tj|j |j d|d St d |) 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. rrcsrz#Expected CSR sparse format, got {0}Nintp) minlength)rwr%zUnsupported axis: {0}) r r rcr dotr"r#astypebincountrrr!r)r r sample_weightoutr%rrr count_nonzeros*   r}cCspt||}|s tjSt|dk}t|d\}}||r&t||||St|d|||t||||dS)zCompute the median of data with n_zeros additional zeros. This function is used to support sparse matrices; it modifies data in-place. rrrg@)rXr nanr}divmodsort_get_elem_at_rank)rn_zerosn_elems n_negativemiddleis_oddrrr _get_median4s  rcCs,||kr||S|||krdS|||S)z@Find the value in data augmented with n_zeros for the given rankrr)rankrrrrrrrJs   rc Cst|tjs td|j|j}|j\}}t|}t t |dd|ddD]\}\}}t |j ||}||j } t|| ||<q)|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. z%Expected matrix of CSC format, got %sNrsr)r'rr,r r r#rr rW enumeratezipcopyrr2r) r r# n_samples n_featuresmedianf_indstartendrnzrrrcsc_median_axis_0Ss   * r)NF)F)NN)$ scipy.sparsesparsernumpyr sparsefuncs_fastrr)rr*rr4utils.validationrrrrr$r-r5r7r8r?rGrIrJrPrbrgrmrprrr}rrrrrrrs4   <_@   $0