fillna()

DataFrame.fillna(value=None, method=None, axis=None, inplace=False, limit=None, downcast=None, **kwargs)


pad/ffill：用前一个非缺失值去填充该缺失值
backfill/bfill：用下一个非缺失值填充该缺失值
None:指定一个值去替换缺失值


ref:
http://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.fillna.html