1. 缺失值填充
pandas中缺失值填充通常使用fillna函数
import pandas as pd
t = pd.DataFrame({'age':[12,13,np.nan,12],'weight':[60,63,np.nan,60]})
#全部填充
t = t.fillna(t.mean())
#填充制定列
t['age'] = t['age'].fillna(t['age'].mean())
2. 字符串离散化
import pandas as pd
t = pd.DataFrame({'info':['China,Henan']})
location_list = t['info'].str.split(',').tolist()