Python scipy.io.mmwrite() Examples

def save_mtx(data, destination, cell_names=None, gene_names=None):
    """Save a mtx file
    
    Parameters
    ----------
    data : array-like, shape=[n_samples, n_features]
        Input data, saved to destination/matrix.mtx
    destination : str
        Directory in which to save the data
    cell_names : list-like, shape=[n_samples], optional (default: None)
        Cell names associated with rows, saved to destination/cell_names.tsv.
        If `data` is a pandas DataFrame and `cell_names` is None,
        these are autopopulated from `data.index`.
    gene_names : list-like, shape=[n_features], optional (default: None)
        Cell names associated with rows, saved to destination/gene_names.tsv.
        If `data` is a pandas DataFrame and `gene_names` is None,
        these are autopopulated from `data.columns`.

    Examples
    --------
    >>> import scprep
    >>> scprep.io.save_mtx(data, destination="my_data")
    >>> reload = scprep.io.load_mtx("my_data/matrix.mtx",
    ...                             cell_names="my_data/cell_names.tsv",
    ...                             gene_names="my_data/gene_names.tsv")
    """
    if isinstance(data, pd.DataFrame):
        if cell_names is None:
            cell_names = data.index
        if gene_names is None:
            gene_names = data.columns
    data = utils.to_array_or_spmatrix(data)
    data = sparse.coo_matrix(data)
    # handle ~/ and relative paths
    destination = os.path.expanduser(destination)
    if not os.path.isdir(destination):
        os.mkdir(destination)
    if cell_names is not None:
        with open(os.path.join(destination, "cell_names.tsv"), "w") as handle:
            for name in cell_names:
                handle.write("{}\n".format(name))
    if gene_names is not None:
        with open(os.path.join(destination, "gene_names.tsv"), "w") as handle:
            for name in gene_names:
                handle.write("{}\n".format(name))
    sio.mmwrite(os.path.join(destination, "matrix.mtx"), data) 

def write_to_files(sparse_matrix, top_cells, ordered_tags_map, data_type, outfolder):
    """Write the umi and read sparse matrices to file in gzipped mtx format.

    Args:
        sparse_matrix (dok_matrix): Results in a sparse matrix.
        top_cells (set): Set of cells that are selected for output.
        ordered_tags_map (dict): Tags in order with indexes as values.
        data_type (string): A string definning if the data is umi or read based.
        outfolder (string): Path to the output folder.
    """
    prefix = os.path.join(outfolder,data_type + '_count')
    os.makedirs(prefix, exist_ok=True)
    io.mmwrite(os.path.join(prefix,'matrix.mtx'),sparse_matrix)
    with gzip.open(os.path.join(prefix,'barcodes.tsv.gz'), 'wb') as barcode_file:
        for barcode in top_cells:
            barcode_file.write('{}\n'.format(barcode).encode())
    with gzip.open(os.path.join(prefix,'features.tsv.gz'), 'wb') as feature_file:
        for feature in ordered_tags_map:
            feature_file.write('{}\n'.format(feature).encode())
    with open(os.path.join(prefix,'matrix.mtx'),'rb') as mtx_in:
        with gzip.open(os.path.join(prefix,'matrix.mtx') + '.gz','wb') as mtx_gz:
            shutil.copyfileobj(mtx_in, mtx_gz)
    os.remove(os.path.join(prefix,'matrix.mtx')) 

def store_matrix(matrix='',
                 output_dir_path='',
                 out_file_name='',
                 output_format=''):
    """store_matrix."""
    if not os.path.exists(output_dir_path):
        os.mkdir(output_dir_path)
    full_out_file_name = os.path.join(output_dir_path, out_file_name)
    if output_format == "MatrixMarket":
        if len(matrix.shape) == 1:
            raise Exception(
                "'MatrixMarket' format supports only 2D dimensional array\
                and not vectors")
        else:
            io.mmwrite(full_out_file_name, matrix, precision=None)
    elif output_format == "numpy":
        np.save(full_out_file_name, matrix)
    elif output_format == "joblib":
        joblib.dump(matrix, full_out_file_name)
    elif output_format == "text":
        with open(full_out_file_name, "w") as f:
            if len(matrix.shape) == 1:
                for x in matrix:
                    f.write("%s\n" % (x))
            else:
                raise Exception(
                    "'text' format supports only mono dimensional array\
                    and not matrices")
    logger.info("Written file: %s" % full_out_file_name) 

def generate_related_mat(folder, triples1, triples2, ref_ent1, ref_ent2):
    t = time.time()
    if "15" in folder:
        out_related_file = folder + "out_related_mat.npy"
        in_related_file = folder + "in_related_mat.npy"
        if os.path.exists(out_related_file):
            out_related_mat = np.load(out_related_file)
        else:
            out_related_mat = generate_out_related_mat(triples1, triples2, ref_ent1, ref_ent2)
            np.save(out_related_file, out_related_mat)
        if os.path.exists(in_related_file):
            in_related_mat = np.load(in_related_file)
        else:
            in_related_mat = generate_in_related_mat(triples1, triples2, ref_ent1, ref_ent2)
            np.save(in_related_file, in_related_mat)
        related_mat1 = out_related_mat
        # related_mat2 = out_related_mat + in_related_mat
        print("load related mat", round(time.time() - t, 2))
        return related_mat1
    else:
        out_related_file = folder + "out_related_mat.mtx"
        in_related_file = folder + "in_related_mat.mtx"
        if os.path.exists(out_related_file):
            out_related_mat = io.mmread(out_related_file)
        else:
            out_related_mat = generate_out_related_mat(triples1, triples2, ref_ent1, ref_ent2)
            io.mmwrite(out_related_file, sp.sparse.lil_matrix(out_related_mat))
        if os.path.exists(in_related_file):
            in_related_mat = io.mmread(in_related_file)
        else:
            in_related_mat = generate_in_related_mat(triples1, triples2, ref_ent1, ref_ent2)
            io.mmwrite(in_related_file, in_related_mat)
        related_mat1 = out_related_mat
        # related_mat2 = out_related_mat + in_related_mat
        print("load related mat", round(time.time() - t, 2))
        return related_mat1