output.py 文件源码

def parse_contribution(self):
        # MO contribution by percentage
        found = self.find(_re_con_00, keys_only=True)
        starts = [i + 3 for i in found]
        widths = [12, 6, 6, 6, 11, 6, 10, 12, 6, 6, 3]
        names = ['eV', 'occupation', 'vector', 'sym', '%', 'SFO',
                 'angmom', 'eV(sfo)', 'occ(sfo)', 'atom', 'symbol']
        dfs = []
        # Prints for both spins
        for i, start in enumerate(starts):
            stop = start
            while self[stop].strip(): stop += 1
            dfs.append(pd.read_fwf(StringIO('\n'.join(self[start:stop])),
                                   delim_whitespace=True, widths=widths,
                                   names=names))
            dfs[-1]['spin'] = i
        dfs = pd.concat(dfs).reset_index(drop=True)
        # Maybe a better way to do this
        def _snan(x):
            return np.nan if isinstance(x, str) and x.isspace() else x
        dfs = dfs.applymap(_snan)
        dfs.fillna(method='ffill', inplace=True)
        # Clean up
        dfs['symbol'] = dfs['symbol'].str.strip()
        dfs['angmom'] = dfs['angmom'].str.strip()
        dfs['angmom'].update(dfs['angmom'].map({'S': 'S:'}))
        dfs[['L', 'ml']] = dfs['angmom'].str.extract('(.*):(.*)', expand=True)
        dfs['%'] = dfs['%'].str.replace('%', '')
        dfs['%'].update(dfs['%'].map({"    ******": np.inf}))
        dfs['%'] = dfs['%'].astype(np.float64)
        dfs['occupation'] = dfs['occupation'].astype(np.float64)
        dfs['vector'] = dfs['vector'].astype(np.int64) - 1
        dfs['eV'] = dfs['eV'].astype(np.float64)
        dfs['atom'] -= 1
        self.contribution = dfs