:jOdZdZgdZddlZddlmZddlmZm Z ddl m Z m Z m Z mZmZdd lmZdd lmZGd d eZd ZGddee ZGddeeZy)z#Compressed Sparse Row matrix formatzrestructuredtext en) csr_array csr_matrixisspmatrix_csrN)spmatrix)_spbasesparray) csr_tocsc csr_tobsrcsr_count_blocksget_csr_submatrixcsr_sample_values)upcast) _cs_matrixceZdZdZdZddZej je_ddZejje_ddZ ejje _dfd Z ejje _ddZ ejje _ddZ ejje _e d Zd Zd Zd Zd ZdZdZdZdZdZdZdZdZdZdZxZS) _csr_basecsr)rc||dk7r td|jdk(r|r|jS|S|j\}}|j |j |j |jf||f|S)N)rrzvSparse arrays/matrices do not support an 'axes' parameter because swapping dimensions is the only logical permutation.rshapecopy) ValueErrorndimrr_csc_containerdataindicesindptr)selfaxesrMNs f/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/scipy/sparse/_csr.py transposez_csr_base.transposes  LM M 99>"&499; 0D 0zz1""DIIt||$(KK$19:AT#K Kc|jdk7r td|j|j|j}|j |j |j|j}}}|j|j}}t|jdD];}||} ||dz} || | j||<|| | j||<=|S)Nrz.Cannot convert a 1d sparse array to lil formatdtyperr) rr_lil_containerrr(sum_duplicatesrrrrowsrangetolist) rrlilptrinddatr+rnstartends r#tolilz_csr_base.tolil$s 99>MN N!!$**DJJ!? kk$,,tyyCXXsxxdtzz!}% .AFEac(C%n++-DG%n++-DG  .  r%c*|r|jS|SNr)rrs r#tocsrz_csr_base.tocsr7s 99; Kr%cJt||}|j|_|S)Nr8)supertocoohas_canonical_format)rrA __class__s r#r<z_csr_base.tocoo?s( GMtM $"&!:!:r%c |jdk7r td|j\}}|j|j|j ft |j|}tj|dz|}tj|j|}tj|jt|j}t|||jj|d|j j|d|j||||j|||f|j}d |_|S) Nrz.Cannot convert a 1d sparse array to csc formatmaxvalrr'Fr8rT)rrr_get_index_dtyperrmaxnnznpemptyrr(r astyperrhas_sorted_indices) rrr!r" idx_dtyperrrr>s r#tocscz_csr_base.tocscIs 99>MN Nzz1))4;; *E+.txx+;*= !a%y1((48895xxtzz(:;!Q++$$YU$;,,%%ie%<))     w 7tzz  J#r%c |jdk7r td|ddlm}|j ||S|dk(rR|j j ddd|j|jf}|j||j|S|\}}|j\}}|dks|dks||zd k7s||zd k7rtd |t|||||j|j} |j|j|jft||z|  } tj||zdz| } tj| | } tj | ||f|j" } t%|||||jj'| d |jj'| d |j | | | j) |j| | | f|jS)Nrz.Cannot convert a 1d sparse array to bsr formatr)estimate_blocksize) blocksize)rrrrzinvalid blocksize rAr'Fr8rC)rr_spfuncsrNtobsrrreshaperr_bsr_containerrr rDrErGrHzerosr(r rIravel)rrOrrNarg1RCr!r"blksrKrrrs r#rRz_csr_base.tobsras 99>MN N   4::(:4(@:A A % II%%b1-dll4;;GD&&t4::D&I ICAa**CAa1uAQ!q1uz #5i[!ABB#Aa!DKK ED--t{{DLL.I/21a4.@IXXad1fI6Fhht95G88T!AJdjj9D aAqkk(((?ll)))%)@iigtzz|  5 &&w'tzz' r%c|S)zBswap the members of x if this is a column-oriented matrix xs r#_swapz_csr_base._swaps r%c#K|jdk(r|jjd}d}t|j|j D]%\}}t ||z D]}|||dz}'t |jd|z D]}|ytjd|jj}t|tr|jddnd|jdf}d}|jddD]C} | |z |d<|j|| } |j || } |j| | |f|d| }Eyw)Nrrrr'Tr)rr(typeziprrr,rrGrUr isinstancer r?) rzerouvd_rri0i1rrs r#__iter__z_csr_base.__iter__sM 99>::??1%DADLL$))4 1q1uAJE   4::a=1,-    !4;;#4#45",T7"; 12!TZZPQ]AS ++ab/ BRF1Ill2b)G99R#D..$!8D.Q QB  sE Ec |jdk(r5|dvrtd|d|jd|jdfdS|j\}}t |}|dkr||z }|dks||k\rtd|dt |||j |j|j||dzd| \}}}|j|||fd|f|jd S) z]Returns a copy of row i of the matrix, as a (1 x n) CSR matrix (row vector). r)rrPindex () out of rangerTr8Frr(r) r IndexErrorrSrintr rrrr?r(rir!r"rrrs r#_getrowz_csr_base._getrows 99> 71#^!<==<<DJJqM 2<> >zz1 F q5 FA q5AFwqc89 9 1 q$++t||TYY1q5!Q!H~~tWf5aV$(JJU< ST Tzz1 F q5 FA q5AFwqc89 9 1 q$++t||TYY1aQ!H~~tWf5aV$(JJU< >"DJJ>7 7$**Q-1mmCy1jjI.hhsxxtzz2!Q T\\499((Cc 3"%1!1CII !  ~~ckk)455r%cB|j|j|Sr7)rt_minor_index_fancyrrrs r#_get_intXarrayz_csr_base._get_intXarrays||C 33C88r%c |jdvr|j||dS|j\}}|j|\}}}|j||dz\}} |j|| } |j || } |dkDr | |k\| |kz} n | |k| |kDz} t |dkDr| | |z |zdk(z} | | |z |z} | | } tjdt| g} |dkr| ddd} t | ddd} dtdttjt||z |z f}|j| | | f||jd S) NrTr8rrrrPFro)rrrrrrabsrGarraylenrErqceilfloatr?r()rrrr!r"r3stopstrideiijj row_indicesrow_datar0 row_indptrrs r#_get_intXslicez_csr_base._get_intXslices 88y &&sCd&; ;zz1!kk!ntVSQ'Bll2b) 99R# A:%'K$,>?C%'K$,>?C v;? K%'61Q6 6C"3'%/F: C=XXq#k"234 A:"~Hk$B$/0KC3rwwuTE\':V'CDEFG~~xjA$(JJU<  F "3r%rc"t|tS)aIs `x` of csr_matrix type? .. warning:: SciPy sparse is shifting from a sparse matrix interface to a sparse array interface. In the next few releases we expect to deprecate the sparse matrix interface. For documentation of the matrix interface, see the :ref:`spmatrix interface docs `. For guidance on converting existing code to sparse arrays, see :ref:`Migration from spmatrix to sparray `. Parameters ---------- x object to check for being a csr matrix Returns ------- bool True if `x` is a csr matrix, False otherwise Examples -------- >>> from scipy.sparse import csr_array, csr_matrix, coo_matrix, isspmatrix_csr >>> isspmatrix_csr(csr_matrix([[5]])) True >>> isspmatrix_csr(csr_array([[5]])) False >>> isspmatrix_csr(coo_matrix([[5]])) False )rcrr]s r#rr)s@ a $$r%ceZdZdZy)rab Compressed Sparse Row array. This can be instantiated in several ways: csr_array(D) where D is a 2-D ndarray csr_array(S) with another sparse array or matrix S (equivalent to S.tocsr()) csr_array((M, N), [dtype]) to construct an empty array with shape (M, N) dtype is optional, defaulting to dtype='d'. csr_array((data, (row_ind, col_ind)), [shape=(M, N)]) where ``data``, ``row_ind`` and ``col_ind`` satisfy the relationship ``a[row_ind[k], col_ind[k]] = data[k]``. csr_array((data, indices, indptr), [shape=(M, N)]) is the standard CSR representation where the column indices for row i are stored in ``indices[indptr[i]:indptr[i+1]]`` and their corresponding values are stored in ``data[indptr[i]:indptr[i+1]]``. If the shape parameter is not supplied, the array dimensions are inferred from the index arrays. Attributes ---------- data : ndarray CSR format data array of the array indices : ndarray CSR format index array of the array indptr : ndarray CSR format index pointer array of the array has_sorted_indices : bool Whether indices are sorted has_canonical_format : bool Whether indices are sorted and no duplicate entries exist dtype : dtype Data type of the array shape : 2-tuple Shape of the array ndim : int Number of dimensions (this is always 2) format : str Three letter code for the format of the array storage, e.g. 'csr' nnz : int Number of values stored in the array size : int Number of values stored in the array T : csr_array The transpose of the array mT : csr_array The matrix transpose of the array Notes ----- Sparse arrays can be used in arithmetic operations: they support addition, subtraction, multiplication, division, and matrix power. Advantages of the CSR format - efficient arithmetic operations CSR + CSR, CSR * CSR, etc. - efficient row slicing - fast matrix vector products Disadvantages of the CSR format - slow column slicing operations (consider CSC) - changes to the sparsity structure are expensive (consider LIL or DOK) Canonical Format - Within each row, indices are sorted by column. - There are no duplicate entries. Examples -------- >>> import numpy as np >>> from scipy.sparse import csr_array >>> csr_array((3, 4), dtype=np.int8).toarray() array([[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0]], dtype=int8) >>> row = np.array([0, 0, 1, 2, 2, 2]) >>> col = np.array([0, 2, 2, 0, 1, 2]) >>> data = np.array([1, 2, 3, 4, 5, 6]) >>> csr_array((data, (row, col)), shape=(3, 3)).toarray() array([[1, 0, 2], [0, 0, 3], [4, 5, 6]]) >>> indptr = np.array([0, 2, 3, 6]) >>> indices = np.array([0, 2, 2, 0, 1, 2]) >>> data = np.array([1, 2, 3, 4, 5, 6]) >>> csr_array((data, indices, indptr), shape=(3, 3)).toarray() array([[1, 0, 2], [0, 0, 3], [4, 5, 6]]) Duplicate entries are summed together: >>> row = np.array([0, 1, 2, 0]) >>> col = np.array([0, 1, 1, 0]) >>> data = np.array([1, 2, 4, 8]) >>> csr_array((data, (row, col)), shape=(3, 3)).toarray() array([[9, 0, 0], [0, 2, 0], [0, 4, 0]]) As an example of how to construct a CSR array incrementally, the following snippet builds a term-document array from texts: >>> docs = [["hello", "world", "hello"], ["goodbye", "cruel", "world"]] >>> indptr = [0] >>> indices = [] >>> data = [] >>> vocabulary = {} >>> for d in docs: ... for term in d: ... index = vocabulary.setdefault(term, len(vocabulary)) ... indices.append(index) ... data.append(1) ... indptr.append(len(indices)) ... >>> csr_array((data, indices, indptr), dtype=int).toarray() array([[2, 1, 0, 0], [0, 1, 1, 1]]) Nrrrrr\r%r#rrMs@r%rceZdZdZy)ra4 Compressed Sparse Row matrix. .. warning:: SciPy sparse is shifting from a sparse matrix interface to a sparse array interface. In the next few releases we expect to deprecate the sparse matrix interface. For documentation of the matrix interface, see the :ref:`spmatrix interface docs `. For guidance on converting existing code to sparse arrays, see :ref:`Migration from spmatrix to sparray `. This can be instantiated in several ways: csr_matrix(D) where D is a 2-D ndarray csr_matrix(S) with another sparse array or matrix S (equivalent to S.tocsr()) csr_matrix((M, N), [dtype]) to construct an empty matrix with shape (M, N) dtype is optional, defaulting to dtype='d'. csr_matrix((data, (row_ind, col_ind)), [shape=(M, N)]) where ``data``, ``row_ind`` and ``col_ind`` satisfy the relationship ``a[row_ind[k], col_ind[k]] = data[k]``. csr_matrix((data, indices, indptr), [shape=(M, N)]) is the standard CSR representation where the column indices for row i are stored in ``indices[indptr[i]:indptr[i+1]]`` and their corresponding values are stored in ``data[indptr[i]:indptr[i+1]]``. If the shape parameter is not supplied, the matrix dimensions are inferred from the index arrays. Attributes ---------- data : ndarray CSR format data array of the matrix indices : ndarray CSR format index array of the matrix indptr : ndarray CSR format index pointer array of the matrix has_sorted_indices : bool Whether indices are sorted has_canonical_format : bool Whether indices are sorted and no duplicate entries exist dtype : dtype Data type of the matrix shape : 2-tuple Shape of the matrix ndim : int Number of dimensions (this is always 2) format : str Three letter code for the format of the matrix storage, e.g. 'csr' nnz : int Number of values stored in the matrix size : int Number of values stored in the matrix T : csr_matrix The transpose of the matrix mT : csr_matrix The matrix transpose Notes ----- Sparse matrices can be used in arithmetic operations: they support addition, subtraction, multiplication, division, and matrix power. Advantages of the CSR format - efficient arithmetic operations CSR + CSR, CSR * CSR, etc. - efficient row slicing - fast matrix vector products Disadvantages of the CSR format - slow column slicing operations (consider CSC) - changes to the sparsity structure are expensive (consider LIL or DOK) Canonical Format - Within each row, indices are sorted by column. - There are no duplicate entries. Examples -------- >>> import numpy as np >>> from scipy.sparse import csr_matrix >>> csr_matrix((3, 4), dtype=np.int8).toarray() array([[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0]], dtype=int8) >>> row = np.array([0, 0, 1, 2, 2, 2]) >>> col = np.array([0, 2, 2, 0, 1, 2]) >>> data = np.array([1, 2, 3, 4, 5, 6]) >>> csr_matrix((data, (row, col)), shape=(3, 3)).toarray() array([[1, 0, 2], [0, 0, 3], [4, 5, 6]]) >>> indptr = np.array([0, 2, 3, 6]) >>> indices = np.array([0, 2, 2, 0, 1, 2]) >>> data = np.array([1, 2, 3, 4, 5, 6]) >>> csr_matrix((data, indices, indptr), shape=(3, 3)).toarray() array([[1, 0, 2], [0, 0, 3], [4, 5, 6]]) Duplicate entries are summed together: >>> row = np.array([0, 1, 2, 0]) >>> col = np.array([0, 1, 1, 0]) >>> data = np.array([1, 2, 4, 8]) >>> csr_matrix((data, (row, col)), shape=(3, 3)).toarray() array([[9, 0, 0], [0, 2, 0], [0, 4, 0]]) As an example of how to construct a CSR matrix incrementally, the following snippet builds a term-document matrix from texts: >>> docs = [["hello", "world", "hello"], ["goodbye", "cruel", "world"]] >>> indptr = [0] >>> indices = [] >>> data = [] >>> vocabulary = {} >>> for d in docs: ... for term in d: ... index = vocabulary.setdefault(term, len(vocabulary)) ... indices.append(index) ... data.append(1) ... indptr.append(len(indices)) ... >>> csr_matrix((data, indices, indptr), dtype=int).toarray() array([[2, 1, 0, 0], [0, 1, 1, 1]]) Nrr\r%r#rrsIr%r)r __docformat____all__numpyrG_matrixr_baserr _sparsetoolsr r r r r_sputilsr _compressedrrrrrr\r%r#rsc)% 7#AA#T3 T3n %HA 7AHJ9Jr%