去除离群值

离群点的选择需要斟酌一下，这里选择的方法是extreme outlier。

• Subtract three times the interquartile range from the first quartile to determine the lower boundary.
• Add three times the interquartil.range to the first quartil.e to identify th.e upper boundary.

原始数据是这样的:

剔除离群点:

    first_quartile = data['A'].describe()['25%']
    third_quartile = data['A'].describe()['75%']
    iqr = third_quartile - first_quartile
    
    data = data[(data['A'] > (first_quartile - 3 * iqr)) &
           (data