sparseMatrixPrepare.py 文件源码

def preCompute(rowBased_row_array,rowBased_col_array,S_rowBased_data_array):
    """
    format affinity/similarity matrix
    """

    # Get parameters
    data_len=len(S_rowBased_data_array)
    row_indptr=sparseAP_cy.getIndptr(rowBased_row_array)
    if row_indptr[-1]!=data_len: row_indptr=np.concatenate((row_indptr,np.array([data_len])))
    row_to_col_ind_arr=np.lexsort((rowBased_row_array,rowBased_col_array))
    colBased_row_array=sparseAP_cy.npArrRearrange_int_para(rowBased_row_array,row_to_col_ind_arr)
    colBased_col_array=sparseAP_cy.npArrRearrange_int_para(rowBased_col_array,row_to_col_ind_arr)
    col_to_row_ind_arr=np.lexsort((colBased_col_array,colBased_row_array))
    col_indptr=sparseAP_cy.getIndptr(colBased_col_array)
    if col_indptr[-1]!=data_len: col_indptr=np.concatenate((col_indptr,np.array([data_len])))
    kk_col_index=sparseAP_cy.getKKIndex(colBased_row_array,colBased_col_array)

    #Initialize matrix A, R
    A_rowbased_data_array=np.array([0.0]*data_len)
    R_rowbased_data_array=np.array([0.0]*data_len)

    #Add random samll value to remove degeneracies
    random_state=np.random.RandomState(0)
    S_rowBased_data_array+=1e-12*random_state.randn(data_len)*(np.amax(S_rowBased_data_array)-np.amin(S_rowBased_data_array))

    #Convert row_to_col_ind_arr/col_to_row_ind_arr data type to np.int datatype so it is compatible with cython code
    row_to_col_ind_arr=row_to_col_ind_arr.astype(np.int)
    col_to_row_ind_arr=col_to_row_ind_arr.astype(np.int)

    return S_rowBased_data_array, A_rowbased_data_array, R_rowbased_data_array,col_indptr,row_indptr,row_to_col_ind_arr,col_to_row_ind_arr,kk_col_index