parsers.py 文件源码

def __parse_pairs__(self, filepath, delimiter = ',', target_col = 2, column_names = list(), sequence_length = None):
        assert("target" in column_names)
        with open(filepath, "r") as f:
            lines = f.readlines()
            try:
                if sequence_length is None:
                    dataframe = pd.read_csv(filepath, sep = delimiter, skip_blank_lines = True,
                        header = None, names = column_names, index_col = False)
                    sequence_length = np.asarray(dataframe[["i", "j"]]).max()
            except ValueError:
                return None
            data = np.full((sequence_length, sequence_length), np.nan, dtype = np.double)
            np.fill_diagonal(data, Params.DISTANCE_WITH_ITSELF)
            for line in lines:
                elements = line.rstrip("\r\n").split(delimiter)
                i, j, k = int(elements[0]) - 1, int(elements[1]) - 1, float(elements[target_col])
                data[i, j] = data[j, i] = k
            if np.isnan(data).any():
                # sequence_length is wrong or the input file has missing pairs
                warnings.warn("Warning: Pairs of residues are missing from the contacts text file")
                warnings.warn("Number of missing pairs: %i " % np.isnan(data).sum())
            return data