dot_box

包点箱型图
箱型图 https://zhuanlan.zhihu.com/p/34059825
散点图 https://blog.csdn.net/qq_39949963/article/details/80750492

import matplotlib.pyplot as plt
import numpy as np

 #生成随机数据
y = np.random.normal(10, 0.04, size=200)
#随机生成数据的横坐标（在一定范围内）
x = np.random.normal(1, 0.02, size=len(y))
plt.plot(x,y,'g.',alpha=0.4)
plt.boxplot(y)
plt.show() 

# Import Data
df = pd.read_csv("mpg_ggplot2.csv")

# Draw Plot
plt.figure(figsize=(13,10), dpi= 80)
sns.boxplot(x='class', y='hwy', data=df, notch=False)

# Add N Obs inside boxplot (optional)
def add_n_obs(df,group_col,y):
    medians_dict = {grp[0]:grp[1][y].median() for grp in df.groupby(group_col)}
    xticklabels = [x.get_text() for x in plt.gca().get_xticklabels()]
    n_obs = df.groupby(group_col)[y].size().values
    for (x, xticklabel), n_ob in zip(enumerate(xticklabels), n_obs):
        plt.text(x, medians_dict[xticklabel]*1.01, "#obs : "+str(n_ob), horizontalalignment='center', fontdict={'size':14}, color='white')

add_n_obs(df,group_col='class',y='hwy')    

# Decoration
plt.title('Box Plot of Highway Mileage by Vehicle Class', fontsize=22)
plt.ylim(10, 40)
plt.show()

# Import Data
df = pd.read_csv("mpg_ggplot2.csv")

# Draw Plot
plt.figure(figsize=(13,10), dpi= 80)
sns.boxplot(x='class', y='hwy', data=df, hue='cyl')
sns.stripplot(x='class', y='hwy', data=df, color='black', size=3, jitter=1)

for i in range(len(df['class'].unique())-1):
    plt.vlines(i+.5, 10, 45, linestyles='solid', colors='gray', alpha=0.2)

# Decoration
plt.title('Box Plot of Highway Mileage by Vehicle Class', fontsize=22)
plt.legend(title='Cylinders')
plt.show()