Python数据可视化：箱线图多种库画法

import numpy as np 
import pandas as pd 
from matplotlib import pyplot as plt 
def list_generator(mean, dis, number): # 封装一下这个函数，用来后面生成数据 
 return np.random.normal(mean, dis * dis, number) # normal分布，输入的参数是均值、标准差以及生成的数量 
# 我们生成四组数据用来做实验，数据量分别为70-100 
y1 = list_generator(0.8531, 0.0956, 70) 
y2 = list_generator(0.8631, 0.0656, 80) 
y3 = list_generator(0.8731, 0.1056, 90) 
y4 = list_generator(0.8831, 0.0756, 100) 
# 如果数据大小不一，记得需要下面语句，把数组变为series 
y1 = pd.Series(np.array(y1)) 
y2 = pd.Series(np.array(y2)) 
y3 = pd.Series(np.array(y3)) 
y4 = pd.Series(np.array(y4)) 
data = pd.DataFrame({"1": y1, "2": y2, "3": y3, "4": y4, }) 
data.boxplot() # 这里，pandas自己有处理的过程，很方便哦。 
plt.ylabel("ylabel") 
plt.xlabel("xlabel") # 我们设置横纵坐标的标题。 
plt.show() 

import numpy as np 
import matplotlib.pyplot as plt 
fig, ax = plt.subplots() # 子图 
def list_generator(mean, dis, number): # 封装一下这个函数，用来后面生成数据 
 return np.random.normal(mean, dis * dis, number) # normal分布，输入的参数是均值、标准差以及生成的数量 
 
# 我们生成四组数据用来做实验，数据量分别为70-100 
# 分别代表男生、女生在20岁和30岁的花费分布 
girl20 = list_generator(1000, 29.2, 70) 
boy20 = list_generator(800, 11.5, 80) 
girl30 = list_generator(3000, 25.1056, 90) 
boy30 = list_generator(1000, 19.0756, 100) 
 
data=[girl20,boy20,girl30,boy30,] 
ax.boxplot(data) 
ax.set_xticklabels(["girl20", "boy20", "girl30", "boy30",]) # 设置x轴刻度标签 
plt.show() 

import numpy as np 
import matplotlib.pyplot as plt 
fig, ax = plt.subplots() # 子图 
def list_generator(mean, dis, number): # 封装一下这个函数，用来后面生成数据 
 return np.random.normal(mean, dis * dis, number) # normal分布，输入的参数是均值、标准差以及生成的数量 
 
# 我们生成四组数据用来做实验，数据量分别为70-100 
# 分别代表男生、女生在20岁和30岁的花费分布 
girl20 = list_generator(1000, 29.2, 70) 
boy20 = list_generator(800, 11.5, 80) 
girl30 = list_generator(3000, 25.1056, 90) 
boy30 = list_generator(1000, 19.0756, 100) 
 
 
data=[girl20,boy20,girl30,boy30,] 
# 用positions参数设置各箱线图的位置 
ax.boxplot(data,positions=[0, 0.6, 3, 3.7,])# 就是后面加了位置 
ax.set_xticklabels(["girl20", "boy20", "girl30", "boy30",]) # 设置x轴刻度标签 
plt.show() 

boxplot(self, x, notch=None, sym=None, vert=None, whis=None, 
 positions=None, widths=None, patch_artist=None, 
 bootstrap=None, usermedians=None, conf_intervals=None, 
 meanline=None, showmeans=None, showcaps=None, 
 showbox=None, showfliers=None, boxprops=None, 
 labels=None, flierprops=None, medianprops=None, 
 meanprops=None, capprops=None, whiskerprops=None, 
 manage_xticks=True, autorange=False, zorder=None)

boxplot(x=None, y=None, hue=None, data=None, order=None, hue_order=None, 
 orient=None, color=None, palette=None, saturation=.75, 
 width=.8, dodge=True, fliersize=5, linewidth=None, 
 whis=1.5, notch=False, ax=None, **kwargs) 

import pandas as pd 
import numpy as np 
import seaborn as sns 
import matplotlib.pyplot as plt 
# plt.rc("font", family="SimHei", size="15") 避免中文乱码，可不用

def list_generator(mean, dis, number): # 封装一下这个函数，用来后面生成数据 
 return np.random.normal(mean, dis * dis, number) # normal分布，输入的参数是均值、标准差以及生成的数量 
 
# 我们生成四组数据用来做实验，数据量分别为70-100 
# 分别代表男生、女生在20岁和30岁的花费分布 
# 构造数据库DataFrame 
num = 100 # 每组100个样本 
girl20 = list_generator(1000, 29.2, num) 
boy20 = list_generator(800, 11.5, num) 
girl30 = list_generator(3000, 25.1056, num) 
boy30 = list_generator(1000, 19.0756, num) 
girl_sex = ['female' for _ in range(num)] 
boy_sex = ['male' for _ in range(num)] 
age20 = [20 for _ in range(num)] 
age30 = [30 for _ in range(num)] 
 
girl_d1 = pd.DataFrame({'cost': girl20, 'sex': girl_sex, 'age': age20}) 
boy_d1 = pd.DataFrame({'cost': boy20, 'sex': boy_sex, 'age': age20}) 
girl_d2 = pd.DataFrame({'cost': girl30, 'sex': girl_sex, 'age': age30}) 
boy_d2 = pd.DataFrame({'cost': boy30, 'sex': boy_sex, 'age': age30}) 
data = pd.concat([girl_d1, boy_d1, girl_d2, boy_d2]) 
 
print(data.head()) 

sns.boxplot(x="age", y="cost", data=data, hue="sex", width=0.5, linewidth=1.0, palette="Set3") 

sns.boxplot(x="age", y="cost", data=data, hue="sex", width=0.5, linewidth=1.0, palette="Set3") 

sns.boxplot(x="sex", y="cost", data=data, hue="age", width=0.5, linewidth=1.0, palette="Set3")