# 这里我包装了一个异常值处理的代码，可以随便调用。
def outliers_proc(data, col_name, scale=3):
    """ 用于清洗异常值，默认用 box_plot（scale=3）进行清洗 :param data: 接收 pandas 数据格式 :param col_name: pandas 列名 :param scale: 尺度 :return: """

    def box_plot_outliers(data_ser, box_scale):
        """ 利用箱线图去除异常值 :param data_ser: 接收 pandas.Series 数据格式 :param box_scale: 箱线图尺度， :return: """
        iqr = box_scale * (data_ser.quantile(0.75) - data_ser.quantile(0.25))
        val_low = data_ser.quantile(0.25) - iqr
        val_up = data_ser.quantile(0.75) + iqr
        rule_low = (data_ser < val_low)
        rule_up = (data_ser > val_up)
        return (rule_low, rule_up), (val_low, val_up)

    data_n = data.copy()
    data_series = data_n[col_name]
    rule, value = box_plot_outliers(data_series, box_scale=scale)
    index = np.arange(data_series.shape[0])[rule[0] | rule[1]]
    print("Delete number is: {}".format(len(index)))
    data_n = data_n.drop(index)
    data_n.reset_index(drop=True, inplace=True)
    print("Now column number is: {}".format(data_n.shape[0]))
    index_low = np.arange(data_series.shape[0])[rule[0]]
    outliers = data_series.iloc[index_low]
    print("Description of data less than the lower bound is:")
    print(pd.Series(outliers).describe())
    index_up = np.arange(data_series.shape[0])[rule[1]]
    outliers = data_series.iloc[index_up]
    print("Description of data larger than the upper bound is:")
    print(pd.Series(outliers).describe())
    
    fig, ax = plt.subplots(1, 2, figsize=(10, 7))
    sns.boxplot(y=data[col_name], data=data, palette="Set1", ax=ax[0])
    sns.boxplot(y=data_n[col_name], data=data_n, palette="Set1", ax=ax[1])
    return data_n

# 我们可以删掉一些异常数据，以 power 为例。 
# 这里删不删同学可以自行判断
# 但是要注意 test 的数据不能删 = = 不能掩耳盗铃是不是

train = outliers_proc(train, 'power', scale=3)