sas7bdat.py 文件源码

def _chunk_to_dataframe(self):

        n = self._current_row_in_chunk_index
        m = self._current_row_in_file_index
        ix = range(m - n, m)
        rslt = pd.DataFrame(index=ix)

        js, jb = 0, 0
        for j in range(self.column_count):

            name = self.column_names[j]

            if self.column_types[j] == b'd':
                rslt[name] = self._byte_chunk[jb, :].view(
                    dtype=self.byte_order + 'd')
                rslt[name] = np.asarray(rslt[name], dtype=np.float64)
                if self.convert_dates and (self.column_formats[j] == "MMDDYY"):
                    epoch = pd.datetime(1960, 1, 1)
                    rslt[name] = epoch + pd.to_timedelta(rslt[name], unit='d')
                jb += 1
            elif self.column_types[j] == b's':
                rslt[name] = self._string_chunk[js, :]
                rslt[name] = rslt[name].apply(lambda x: x.rstrip(b'\x00 '))
                if self.encoding is not None:
                    rslt[name] = rslt[name].apply(
                        lambda x: x.decode(encoding=self.encoding))
                if self.blank_missing:
                    ii = rslt[name].str.len() == 0
                    rslt.loc[ii, name] = np.nan
                js += 1
            else:
                raise ValueError("unknown column type %s" %
                                 self.column_types[j])

        return rslt