Pandas+Matplotlib 箱式图异常值分析示例

# -*- coding: utf-8 -*-
 
import pandas as pd
import matplotlib.pyplot as plt
 
catering_sale = '../data/catering_sale.xls'
data = pd.read_excel(catering_sale, index_col=u'日期') #指定日期列为索引，data类型为DataFrame
 
plt.rcParams['font.sans-serif'] = ['SimHei']  #指定字体为黑体
plt.rcParams['axes.unicode_minus'] = False  #显示负号
 
plt.figure()
p = data.boxplot(return_type='dict')  #画箱式图
 
x = p['fliers'][0].get_xdata()  #fliers为异常值标签，get_xdata()与get_ydata()用来获取横纵坐标数组
y = p['fliers'][0].get_ydata()
y.sort()
 
#使用annotate添加注释，xy表示标注点坐标, xytext表示注释坐标
for i in range(len(x)):
  if i > 0:
    plt.annotate(y[i], xy=(x[i], y[i]), xytext=(x[i]+0.05 - 0.8/(y[i]-y[i-1]), y[i]))
  else:
    plt.annotate(y[i], xy=(x[i], y[i]), xytext=(x[i]+0.08, y[i]))
 
plt.show()
 
 
​