另一种选择是转换数据，以减轻异常值的影响。你可以通过winsorize你的数据来做到这一点。

import pandas as pd
from scipy.stats import mstats
%matplotlib inline

test_data = pd.Series(range(30))
test_data.plot()

# Truncate values to the 5th and 95th percentiles
transformed_test_data = pd.Series(mstats.winsorize(test_data, limits=[0.05, 0.05])) 
transformed_test_data.plot()

去掉离群值的函数

def drop_outliers(df, field_name):
    distance = 1.5 * (np.percentile(df[field_name], 75) - np.percentile(df[field_name], 25))
    df.drop(df[df[field_name] > distance + np.percentile(df[field_name], 75)].index, inplace=True)
    df.drop(df[df[field_name] < np.percentile(df[field_name], 25) - distance].index, inplace=True)

对于你的每一个数据帧列，你可以得到分位数:

q = df["col"].quantile(0.99)

然后用:

df[df["col"] < q]

如果需要移除上下异常值，将condition与and语句结合:

q_low = df["col"].quantile(0.01)
q_hi  = df["col"].quantile(0.99)

df_filtered = df[(df["col"] < q_hi) & (df["col"] > q_low)]

#------------------------------------------------------------------------------
# accept a dataframe, remove outliers, return cleaned data in a new dataframe
# see http://www.itl.nist.gov/div898/handbook/prc/section1/prc16.htm
#------------------------------------------------------------------------------
def remove_outlier(df_in, col_name):
    q1 = df_in[col_name].quantile(0.25)
    q3 = df_in[col_name].quantile(0.75)
    iqr = q3-q1 #Interquartile range
    fence_low  = q1-1.5*iqr
    fence_high = q3+1.5*iqr
    df_out = df_in.loc[(df_in[col_name] > fence_low) & (df_in[col_name] < fence_high)]
    return df_out

由于我正处于我的数据科学之旅的早期阶段，我使用下面的代码来处理异常值。

#Outlier Treatment

def outlier_detect(df):
    for i in df.describe().columns:
        Q1=df.describe().at['25%',i]
        Q3=df.describe().at['75%',i]
        IQR=Q3 - Q1
        LTV=Q1 - 1.5 * IQR
        UTV=Q3 + 1.5 * IQR
        x=np.array(df[i])
        p=[]
        for j in x:
            if j < LTV or j>UTV:
                p.append(df[i].median())
            else:
                p.append(j)
        df[i]=p
    return df

把98和2百分位作为离群值的极限

upper_limit = np.percentile(X_train.logerror.values, 98) 
lower_limit = np.percentile(X_train.logerror.values, 2) # Filter the outliers from the dataframe
data[‘target’].loc[X_train[‘target’]>upper_limit] = upper_limit data[‘target’].loc[X_train[‘target’]<lower_limit] = lower_limit